ftopal/huggingface-models · Datasets at Hugging Face

pipeline_tag stringclasses 48 values	library_name stringclasses 198 values	text stringlengths 1 900k	metadata stringlengths 2 438k	id stringlengths 5 122	last_modified null	tags sequencelengths 1 1.84k	sha null	created_at stringlengths 25 25	arxiv sequencelengths 0 201	languages sequencelengths 0 1.83k	tags_str stringlengths 17 9.34k	text_str stringlengths 0 389k	text_lists sequencelengths 0 722	processed_texts sequencelengths 1 723
text-generation	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	devesh220897/financial-chatbot-for-young-adults-4	null	[ "transformers", "safetensors", "gemma", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-27T00:28:21+00:00	[ "1910.09700" ]	[]	TAGS #transformers #safetensors #gemma #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us	# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact	[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]	[ "TAGS\n#transformers #safetensors #gemma #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_splice_reconstructed-seqsight_4096_512_46M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_splice_reconstructed](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_splice_reconstructed) dataset. It achieves the following results on the evaluation set: - Loss: 0.3479 - F1 Score: 0.8611 - Accuracy: 0.8604 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.9345 \| 0.7 \| 200 \| 0.8741 \| 0.5165 \| 0.5761 \| \| 0.7904 \| 1.4 \| 400 \| 0.5650 \| 0.7493 \| 0.7519 \| \| 0.5261 \| 2.1 \| 600 \| 0.4778 \| 0.7942 \| 0.7937 \| \| 0.478 \| 2.8 \| 800 \| 0.4621 \| 0.8103 \| 0.8097 \| \| 0.4593 \| 3.5 \| 1000 \| 0.4522 \| 0.8124 \| 0.8115 \| \| 0.4463 \| 4.2 \| 1200 \| 0.4375 \| 0.8194 \| 0.8181 \| \| 0.4347 \| 4.9 \| 1400 \| 0.4279 \| 0.8234 \| 0.8224 \| \| 0.4273 \| 5.59 \| 1600 \| 0.4331 \| 0.8230 \| 0.8227 \| \| 0.4151 \| 6.29 \| 1800 \| 0.4419 \| 0.8198 \| 0.8185 \| \| 0.4036 \| 6.99 \| 2000 \| 0.4257 \| 0.8270 \| 0.8255 \| \| 0.3988 \| 7.69 \| 2200 \| 0.3926 \| 0.8380 \| 0.8371 \| \| 0.3947 \| 8.39 \| 2400 \| 0.4171 \| 0.8293 \| 0.8281 \| \| 0.3959 \| 9.09 \| 2600 \| 0.4144 \| 0.8316 \| 0.8301 \| \| 0.3848 \| 9.79 \| 2800 \| 0.3916 \| 0.8441 \| 0.8431 \| \| 0.3842 \| 10.49 \| 3000 \| 0.3868 \| 0.8481 \| 0.8472 \| \| 0.3726 \| 11.19 \| 3200 \| 0.4221 \| 0.8294 \| 0.8284 \| \| 0.375 \| 11.89 \| 3400 \| 0.3941 \| 0.8421 \| 0.8409 \| \| 0.3636 \| 12.59 \| 3600 \| 0.3826 \| 0.8468 \| 0.8461 \| \| 0.3693 \| 13.29 \| 3800 \| 0.3817 \| 0.8479 \| 0.8470 \| \| 0.3604 \| 13.99 \| 4000 \| 0.3992 \| 0.8427 \| 0.8415 \| \| 0.3566 \| 14.69 \| 4200 \| 0.3819 \| 0.8512 \| 0.8503 \| \| 0.3539 \| 15.38 \| 4400 \| 0.3803 \| 0.8516 \| 0.8507 \| \| 0.3463 \| 16.08 \| 4600 \| 0.4195 \| 0.8349 \| 0.8338 \| \| 0.3498 \| 16.78 \| 4800 \| 0.3813 \| 0.8503 \| 0.8494 \| \| 0.345 \| 17.48 \| 5000 \| 0.3904 \| 0.8484 \| 0.8472 \| \| 0.3447 \| 18.18 \| 5200 \| 0.3690 \| 0.8580 \| 0.8573 \| \| 0.3424 \| 18.88 \| 5400 \| 0.3667 \| 0.8582 \| 0.8575 \| \| 0.3325 \| 19.58 \| 5600 \| 0.3646 \| 0.8591 \| 0.8584 \| \| 0.3418 \| 20.28 \| 5800 \| 0.3595 \| 0.8615 \| 0.8608 \| \| 0.336 \| 20.98 \| 6000 \| 0.3636 \| 0.8581 \| 0.8573 \| \| 0.3391 \| 21.68 \| 6200 \| 0.3748 \| 0.8532 \| 0.8525 \| \| 0.3304 \| 22.38 \| 6400 \| 0.3715 \| 0.8561 \| 0.8553 \| \| 0.3272 \| 23.08 \| 6600 \| 0.3687 \| 0.8565 \| 0.8555 \| \| 0.3302 \| 23.78 \| 6800 \| 0.3691 \| 0.8571 \| 0.8562 \| \| 0.3278 \| 24.48 \| 7000 \| 0.3756 \| 0.8573 \| 0.8564 \| \| 0.3219 \| 25.17 \| 7200 \| 0.3740 \| 0.8538 \| 0.8529 \| \| 0.3232 \| 25.87 \| 7400 \| 0.3772 \| 0.8535 \| 0.8525 \| \| 0.322 \| 26.57 \| 7600 \| 0.3782 \| 0.8552 \| 0.8542 \| \| 0.3195 \| 27.27 \| 7800 \| 0.3701 \| 0.8566 \| 0.8558 \| \| 0.3248 \| 27.97 \| 8000 \| 0.3707 \| 0.8558 \| 0.8549 \| \| 0.3255 \| 28.67 \| 8200 \| 0.3815 \| 0.8519 \| 0.8509 \| \| 0.318 \| 29.37 \| 8400 \| 0.3691 \| 0.8553 \| 0.8544 \| \| 0.3154 \| 30.07 \| 8600 \| 0.3580 \| 0.8620 \| 0.8612 \| \| 0.3157 \| 30.77 \| 8800 \| 0.3694 \| 0.8551 \| 0.8542 \| \| 0.3171 \| 31.47 \| 9000 \| 0.3643 \| 0.8562 \| 0.8553 \| \| 0.3198 \| 32.17 \| 9200 \| 0.3615 \| 0.8588 \| 0.8580 \| \| 0.3182 \| 32.87 \| 9400 \| 0.3648 \| 0.8578 \| 0.8571 \| \| 0.316 \| 33.57 \| 9600 \| 0.3717 \| 0.8543 \| 0.8534 \| \| 0.3129 \| 34.27 \| 9800 \| 0.3659 \| 0.8577 \| 0.8569 \| \| 0.3166 \| 34.97 \| 10000 \| 0.3673 \| 0.8564 \| 0.8555 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_splice_reconstructed-seqsight_4096_512_46M-L1_f", "results": []}]}	mahdibaghbanzadeh/GUE_splice_reconstructed-seqsight_4096_512_46M-L1_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_46M", "region:us" ]	null	2024-04-27T00:28:25+00:00	[]	[]	TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us	GUE\_splice\_reconstructed-seqsight\_4096\_512\_46M-L1\_f ========================================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_4096\_512\_46M on the mahdibaghbanzadeh/GUE\_splice\_reconstructed dataset. It achieves the following results on the evaluation set: * Loss: 0.3479 * F1 Score: 0.8611 * Accuracy: 0.8604 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]	[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]
text-generation	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	rPucs/gemma-7b-itTripletDolly-WebNLG	null	[ "transformers", "safetensors", "gemma", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-27T00:30:38+00:00	[ "1910.09700" ]	[]	TAGS #transformers #safetensors #gemma #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us	# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact	[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]	[ "TAGS\n#transformers #safetensors #gemma #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]
null	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	jsingh/autoflow-math-v0.3	null	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-04-27T00:32:14+00:00	[ "1910.09700" ]	[]	TAGS #transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us	# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact	[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]	[ "TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_splice_reconstructed-seqsight_4096_512_46M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_splice_reconstructed](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_splice_reconstructed) dataset. It achieves the following results on the evaluation set: - Loss: 0.3085 - F1 Score: 0.8848 - Accuracy: 0.8843 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.9058 \| 0.7 \| 200 \| 0.7893 \| 0.6650 \| 0.6637 \| \| 0.5287 \| 1.4 \| 400 \| 0.4440 \| 0.8207 \| 0.8196 \| \| 0.4396 \| 2.1 \| 600 \| 0.4073 \| 0.8350 \| 0.8338 \| \| 0.4028 \| 2.8 \| 800 \| 0.4125 \| 0.8360 \| 0.8352 \| \| 0.387 \| 3.5 \| 1000 \| 0.3674 \| 0.8587 \| 0.8582 \| \| 0.3728 \| 4.2 \| 1200 \| 0.3927 \| 0.8439 \| 0.8426 \| \| 0.3595 \| 4.9 \| 1400 \| 0.3759 \| 0.8529 \| 0.8520 \| \| 0.3518 \| 5.59 \| 1600 \| 0.3751 \| 0.8604 \| 0.8604 \| \| 0.3369 \| 6.29 \| 1800 \| 0.3757 \| 0.8575 \| 0.8564 \| \| 0.3277 \| 6.99 \| 2000 \| 0.3672 \| 0.8590 \| 0.8580 \| \| 0.3213 \| 7.69 \| 2200 \| 0.3529 \| 0.8647 \| 0.8639 \| \| 0.318 \| 8.39 \| 2400 \| 0.3513 \| 0.8681 \| 0.8674 \| \| 0.3154 \| 9.09 \| 2600 \| 0.3567 \| 0.8653 \| 0.8643 \| \| 0.3012 \| 9.79 \| 2800 \| 0.3442 \| 0.8697 \| 0.8689 \| \| 0.3008 \| 10.49 \| 3000 \| 0.3317 \| 0.8769 \| 0.8764 \| \| 0.2955 \| 11.19 \| 3200 \| 0.3715 \| 0.8606 \| 0.8597 \| \| 0.2961 \| 11.89 \| 3400 \| 0.3457 \| 0.8651 \| 0.8641 \| \| 0.2847 \| 12.59 \| 3600 \| 0.3518 \| 0.8628 \| 0.8621 \| \| 0.289 \| 13.29 \| 3800 \| 0.3271 \| 0.8747 \| 0.8742 \| \| 0.2789 \| 13.99 \| 4000 \| 0.3435 \| 0.8743 \| 0.8735 \| \| 0.2741 \| 14.69 \| 4200 \| 0.3318 \| 0.8768 \| 0.8762 \| \| 0.2738 \| 15.38 \| 4400 \| 0.3299 \| 0.8770 \| 0.8764 \| \| 0.2676 \| 16.08 \| 4600 \| 0.3491 \| 0.8695 \| 0.8687 \| \| 0.2718 \| 16.78 \| 4800 \| 0.3407 \| 0.8741 \| 0.8733 \| \| 0.2597 \| 17.48 \| 5000 \| 0.3563 \| 0.8644 \| 0.8637 \| \| 0.264 \| 18.18 \| 5200 \| 0.3287 \| 0.8805 \| 0.8799 \| \| 0.2607 \| 18.88 \| 5400 \| 0.3233 \| 0.8793 \| 0.8788 \| \| 0.2502 \| 19.58 \| 5600 \| 0.3305 \| 0.8790 \| 0.8783 \| \| 0.2586 \| 20.28 \| 5800 \| 0.3144 \| 0.8865 \| 0.8860 \| \| 0.2536 \| 20.98 \| 6000 \| 0.3183 \| 0.8865 \| 0.8860 \| \| 0.254 \| 21.68 \| 6200 \| 0.3390 \| 0.8742 \| 0.8735 \| \| 0.249 \| 22.38 \| 6400 \| 0.3305 \| 0.8790 \| 0.8783 \| \| 0.2439 \| 23.08 \| 6600 \| 0.3274 \| 0.8805 \| 0.8799 \| \| 0.2437 \| 23.78 \| 6800 \| 0.3310 \| 0.8823 \| 0.8816 \| \| 0.2391 \| 24.48 \| 7000 \| 0.3360 \| 0.8790 \| 0.8783 \| \| 0.2398 \| 25.17 \| 7200 \| 0.3339 \| 0.8789 \| 0.8783 \| \| 0.2389 \| 25.87 \| 7400 \| 0.3430 \| 0.8775 \| 0.8768 \| \| 0.2386 \| 26.57 \| 7600 \| 0.3329 \| 0.8805 \| 0.8799 \| \| 0.2317 \| 27.27 \| 7800 \| 0.3397 \| 0.8786 \| 0.8779 \| \| 0.237 \| 27.97 \| 8000 \| 0.3363 \| 0.8821 \| 0.8814 \| \| 0.2378 \| 28.67 \| 8200 \| 0.3350 \| 0.8825 \| 0.8819 \| \| 0.2293 \| 29.37 \| 8400 \| 0.3259 \| 0.8855 \| 0.8849 \| \| 0.2276 \| 30.07 \| 8600 \| 0.3260 \| 0.8853 \| 0.8847 \| \| 0.2258 \| 30.77 \| 8800 \| 0.3317 \| 0.8840 \| 0.8834 \| \| 0.2307 \| 31.47 \| 9000 \| 0.3354 \| 0.8834 \| 0.8827 \| \| 0.2279 \| 32.17 \| 9200 \| 0.3311 \| 0.8842 \| 0.8836 \| \| 0.2301 \| 32.87 \| 9400 \| 0.3304 \| 0.8820 \| 0.8814 \| \| 0.2277 \| 33.57 \| 9600 \| 0.3398 \| 0.8812 \| 0.8805 \| \| 0.2225 \| 34.27 \| 9800 \| 0.3342 \| 0.8829 \| 0.8823 \| \| 0.2288 \| 34.97 \| 10000 \| 0.3341 \| 0.8827 \| 0.8821 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_splice_reconstructed-seqsight_4096_512_46M-L8_f", "results": []}]}	mahdibaghbanzadeh/GUE_splice_reconstructed-seqsight_4096_512_46M-L8_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_46M", "region:us" ]	null	2024-04-27T00:33:37+00:00	[]	[]	TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us	GUE\_splice\_reconstructed-seqsight\_4096\_512\_46M-L8\_f ========================================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_4096\_512\_46M on the mahdibaghbanzadeh/GUE\_splice\_reconstructed dataset. It achieves the following results on the evaluation set: * Loss: 0.3085 * F1 Score: 0.8848 * Accuracy: 0.8843 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]	[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_splice_reconstructed-seqsight_4096_512_46M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_splice_reconstructed](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_splice_reconstructed) dataset. It achieves the following results on the evaluation set: - Loss: 0.2844 - F1 Score: 0.9056 - Accuracy: 0.9053 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.8179 \| 0.7 \| 200 \| 0.5204 \| 0.7837 \| 0.7830 \| \| 0.4352 \| 1.4 \| 400 \| 0.3973 \| 0.8452 \| 0.8446 \| \| 0.3886 \| 2.1 \| 600 \| 0.3784 \| 0.8550 \| 0.8540 \| \| 0.3519 \| 2.8 \| 800 \| 0.3853 \| 0.8541 \| 0.8534 \| \| 0.3325 \| 3.5 \| 1000 \| 0.3315 \| 0.8748 \| 0.8744 \| \| 0.318 \| 4.2 \| 1200 \| 0.3462 \| 0.8679 \| 0.8669 \| \| 0.3053 \| 4.9 \| 1400 \| 0.3358 \| 0.8734 \| 0.8726 \| \| 0.2965 \| 5.59 \| 1600 \| 0.3560 \| 0.8635 \| 0.8634 \| \| 0.2831 \| 6.29 \| 1800 \| 0.3516 \| 0.8673 \| 0.8665 \| \| 0.2708 \| 6.99 \| 2000 \| 0.3149 \| 0.8816 \| 0.8812 \| \| 0.2641 \| 7.69 \| 2200 \| 0.3367 \| 0.8767 \| 0.8759 \| \| 0.2582 \| 8.39 \| 2400 \| 0.3258 \| 0.8779 \| 0.8775 \| \| 0.2553 \| 9.09 \| 2600 \| 0.3211 \| 0.8842 \| 0.8834 \| \| 0.2426 \| 9.79 \| 2800 \| 0.3137 \| 0.8889 \| 0.8882 \| \| 0.2364 \| 10.49 \| 3000 \| 0.2944 \| 0.8936 \| 0.8932 \| \| 0.2299 \| 11.19 \| 3200 \| 0.3200 \| 0.8847 \| 0.8840 \| \| 0.2285 \| 11.89 \| 3400 \| 0.3317 \| 0.8815 \| 0.8808 \| \| 0.2136 \| 12.59 \| 3600 \| 0.3326 \| 0.8763 \| 0.8757 \| \| 0.2152 \| 13.29 \| 3800 \| 0.3053 \| 0.8900 \| 0.8895 \| \| 0.2078 \| 13.99 \| 4000 \| 0.3316 \| 0.8802 \| 0.8794 \| \| 0.2028 \| 14.69 \| 4200 \| 0.3239 \| 0.8866 \| 0.8858 \| \| 0.2028 \| 15.38 \| 4400 \| 0.3240 \| 0.8852 \| 0.8847 \| \| 0.1888 \| 16.08 \| 4600 \| 0.3376 \| 0.8841 \| 0.8834 \| \| 0.1919 \| 16.78 \| 4800 \| 0.3129 \| 0.8903 \| 0.8897 \| \| 0.1792 \| 17.48 \| 5000 \| 0.3338 \| 0.8873 \| 0.8867 \| \| 0.1846 \| 18.18 \| 5200 \| 0.3108 \| 0.8934 \| 0.8930 \| \| 0.1782 \| 18.88 \| 5400 \| 0.3161 \| 0.8889 \| 0.8884 \| \| 0.1699 \| 19.58 \| 5600 \| 0.3339 \| 0.8909 \| 0.8904 \| \| 0.1747 \| 20.28 \| 5800 \| 0.3043 \| 0.8986 \| 0.8983 \| \| 0.1631 \| 20.98 \| 6000 \| 0.3052 \| 0.9013 \| 0.9009 \| \| 0.1636 \| 21.68 \| 6200 \| 0.3347 \| 0.8882 \| 0.8878 \| \| 0.1586 \| 22.38 \| 6400 \| 0.3218 \| 0.8937 \| 0.8932 \| \| 0.157 \| 23.08 \| 6600 \| 0.3203 \| 0.8931 \| 0.8926 \| \| 0.1546 \| 23.78 \| 6800 \| 0.3180 \| 0.8977 \| 0.8974 \| \| 0.1484 \| 24.48 \| 7000 \| 0.3491 \| 0.8866 \| 0.8860 \| \| 0.1485 \| 25.17 \| 7200 \| 0.3209 \| 0.8927 \| 0.8924 \| \| 0.1447 \| 25.87 \| 7400 \| 0.3323 \| 0.8974 \| 0.8970 \| \| 0.1428 \| 26.57 \| 7600 \| 0.3301 \| 0.8965 \| 0.8961 \| \| 0.1394 \| 27.27 \| 7800 \| 0.3386 \| 0.8909 \| 0.8904 \| \| 0.1414 \| 27.97 \| 8000 \| 0.3319 \| 0.8981 \| 0.8976 \| \| 0.1398 \| 28.67 \| 8200 \| 0.3338 \| 0.8970 \| 0.8965 \| \| 0.1346 \| 29.37 \| 8400 \| 0.3304 \| 0.8972 \| 0.8968 \| \| 0.1327 \| 30.07 \| 8600 \| 0.3334 \| 0.8965 \| 0.8961 \| \| 0.1325 \| 30.77 \| 8800 \| 0.3449 \| 0.8931 \| 0.8926 \| \| 0.1338 \| 31.47 \| 9000 \| 0.3320 \| 0.8946 \| 0.8941 \| \| 0.1282 \| 32.17 \| 9200 \| 0.3409 \| 0.8963 \| 0.8959 \| \| 0.1276 \| 32.87 \| 9400 \| 0.3403 \| 0.8963 \| 0.8959 \| \| 0.1266 \| 33.57 \| 9600 \| 0.3470 \| 0.8940 \| 0.8935 \| \| 0.1238 \| 34.27 \| 9800 \| 0.3421 \| 0.8954 \| 0.8950 \| \| 0.1257 \| 34.97 \| 10000 \| 0.3406 \| 0.8959 \| 0.8954 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_splice_reconstructed-seqsight_4096_512_46M-L32_f", "results": []}]}	mahdibaghbanzadeh/GUE_splice_reconstructed-seqsight_4096_512_46M-L32_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_46M", "region:us" ]	null	2024-04-27T00:33:38+00:00	[]	[]	TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us	GUE\_splice\_reconstructed-seqsight\_4096\_512\_46M-L32\_f ========================================================== This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_4096\_512\_46M on the mahdibaghbanzadeh/GUE\_splice\_reconstructed dataset. It achieves the following results on the evaluation set: * Loss: 0.2844 * F1 Score: 0.9056 * Accuracy: 0.9053 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]	[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_tf_0-seqsight_4096_512_46M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_tf_0](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_0) dataset. It achieves the following results on the evaluation set: - Loss: 0.3687 - F1 Score: 0.8338 - Accuracy: 0.834 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.5178 \| 0.79 \| 200 \| 0.4899 \| 0.7461 \| 0.746 \| \| 0.4791 \| 1.58 \| 400 \| 0.4700 \| 0.7734 \| 0.774 \| \| 0.4718 \| 2.37 \| 600 \| 0.4727 \| 0.7702 \| 0.771 \| \| 0.4615 \| 3.16 \| 800 \| 0.4697 \| 0.766 \| 0.766 \| \| 0.4548 \| 3.95 \| 1000 \| 0.4594 \| 0.7833 \| 0.784 \| \| 0.4524 \| 4.74 \| 1200 \| 0.4634 \| 0.7769 \| 0.777 \| \| 0.453 \| 5.53 \| 1400 \| 0.4565 \| 0.7840 \| 0.784 \| \| 0.442 \| 6.32 \| 1600 \| 0.4560 \| 0.7830 \| 0.783 \| \| 0.447 \| 7.11 \| 1800 \| 0.4591 \| 0.7861 \| 0.786 \| \| 0.4436 \| 7.91 \| 2000 \| 0.4556 \| 0.7901 \| 0.79 \| \| 0.4384 \| 8.7 \| 2200 \| 0.4544 \| 0.7820 \| 0.782 \| \| 0.4351 \| 9.49 \| 2400 \| 0.4534 \| 0.7776 \| 0.778 \| \| 0.4356 \| 10.28 \| 2600 \| 0.4704 \| 0.7827 \| 0.783 \| \| 0.4329 \| 11.07 \| 2800 \| 0.4588 \| 0.7940 \| 0.794 \| \| 0.4323 \| 11.86 \| 3000 \| 0.4618 \| 0.7840 \| 0.784 \| \| 0.4306 \| 12.65 \| 3200 \| 0.4583 \| 0.7931 \| 0.793 \| \| 0.4259 \| 13.44 \| 3400 \| 0.4587 \| 0.7890 \| 0.789 \| \| 0.4277 \| 14.23 \| 3600 \| 0.4532 \| 0.7880 \| 0.788 \| \| 0.4276 \| 15.02 \| 3800 \| 0.4550 \| 0.7891 \| 0.789 \| \| 0.4277 \| 15.81 \| 4000 \| 0.4567 \| 0.7920 \| 0.792 \| \| 0.4216 \| 16.6 \| 4200 \| 0.4542 \| 0.7881 \| 0.788 \| \| 0.4247 \| 17.39 \| 4400 \| 0.4598 \| 0.7850 \| 0.785 \| \| 0.4213 \| 18.18 \| 4600 \| 0.4613 \| 0.7820 \| 0.782 \| \| 0.4207 \| 18.97 \| 4800 \| 0.4634 \| 0.7819 \| 0.782 \| \| 0.4256 \| 19.76 \| 5000 \| 0.4523 \| 0.7821 \| 0.782 \| \| 0.4206 \| 20.55 \| 5200 \| 0.4507 \| 0.7878 \| 0.788 \| \| 0.4201 \| 21.34 \| 5400 \| 0.4563 \| 0.7811 \| 0.781 \| \| 0.4175 \| 22.13 \| 5600 \| 0.4561 \| 0.7851 \| 0.785 \| \| 0.42 \| 22.92 \| 5800 \| 0.4546 \| 0.7821 \| 0.782 \| \| 0.4129 \| 23.72 \| 6000 \| 0.4567 \| 0.7861 \| 0.786 \| \| 0.4176 \| 24.51 \| 6200 \| 0.4500 \| 0.7890 \| 0.789 \| \| 0.4193 \| 25.3 \| 6400 \| 0.4516 \| 0.7931 \| 0.793 \| \| 0.4131 \| 26.09 \| 6600 \| 0.4523 \| 0.7820 \| 0.782 \| \| 0.4134 \| 26.88 \| 6800 \| 0.4575 \| 0.7790 \| 0.779 \| \| 0.4129 \| 27.67 \| 7000 \| 0.4518 \| 0.7889 \| 0.789 \| \| 0.4116 \| 28.46 \| 7200 \| 0.4501 \| 0.7849 \| 0.785 \| \| 0.4146 \| 29.25 \| 7400 \| 0.4514 \| 0.7930 \| 0.793 \| \| 0.4124 \| 30.04 \| 7600 \| 0.4532 \| 0.7860 \| 0.786 \| \| 0.4111 \| 30.83 \| 7800 \| 0.4543 \| 0.7831 \| 0.783 \| \| 0.4116 \| 31.62 \| 8000 \| 0.4488 \| 0.7859 \| 0.786 \| \| 0.4105 \| 32.41 \| 8200 \| 0.4534 \| 0.7830 \| 0.783 \| \| 0.4065 \| 33.2 \| 8400 \| 0.4553 \| 0.7860 \| 0.786 \| \| 0.4106 \| 33.99 \| 8600 \| 0.4539 \| 0.7880 \| 0.788 \| \| 0.4131 \| 34.78 \| 8800 \| 0.4506 \| 0.7869 \| 0.787 \| \| 0.4044 \| 35.57 \| 9000 \| 0.4538 \| 0.7870 \| 0.787 \| \| 0.4084 \| 36.36 \| 9200 \| 0.4561 \| 0.7841 \| 0.784 \| \| 0.4113 \| 37.15 \| 9400 \| 0.4573 \| 0.7810 \| 0.781 \| \| 0.4055 \| 37.94 \| 9600 \| 0.4545 \| 0.7870 \| 0.787 \| \| 0.4065 \| 38.74 \| 9800 \| 0.4552 \| 0.7870 \| 0.787 \| \| 0.4087 \| 39.53 \| 10000 \| 0.4548 \| 0.7870 \| 0.787 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_tf_0-seqsight_4096_512_46M-L1_f", "results": []}]}	mahdibaghbanzadeh/GUE_tf_0-seqsight_4096_512_46M-L1_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_46M", "region:us" ]	null	2024-04-27T00:34:25+00:00	[]	[]	TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us	GUE\_tf\_0-seqsight\_4096\_512\_46M-L1\_f ========================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_4096\_512\_46M on the mahdibaghbanzadeh/GUE\_tf\_0 dataset. It achieves the following results on the evaluation set: * Loss: 0.3687 * F1 Score: 0.8338 * Accuracy: 0.834 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]	[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_tf_0-seqsight_4096_512_46M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_tf_0](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_0) dataset. It achieves the following results on the evaluation set: - Loss: 0.3756 - F1 Score: 0.8367 - Accuracy: 0.837 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.5044 \| 0.79 \| 200 \| 0.4765 \| 0.7625 \| 0.763 \| \| 0.4678 \| 1.58 \| 400 \| 0.4608 \| 0.7760 \| 0.777 \| \| 0.4623 \| 2.37 \| 600 \| 0.4678 \| 0.7758 \| 0.777 \| \| 0.453 \| 3.16 \| 800 \| 0.4604 \| 0.7780 \| 0.778 \| \| 0.4461 \| 3.95 \| 1000 \| 0.4543 \| 0.7860 \| 0.787 \| \| 0.443 \| 4.74 \| 1200 \| 0.4557 \| 0.7826 \| 0.783 \| \| 0.4427 \| 5.53 \| 1400 \| 0.4569 \| 0.7880 \| 0.788 \| \| 0.4339 \| 6.32 \| 1600 \| 0.4522 \| 0.7961 \| 0.796 \| \| 0.4377 \| 7.11 \| 1800 \| 0.4591 \| 0.7889 \| 0.789 \| \| 0.4332 \| 7.91 \| 2000 \| 0.4540 \| 0.7950 \| 0.795 \| \| 0.4281 \| 8.7 \| 2200 \| 0.4491 \| 0.7889 \| 0.789 \| \| 0.4232 \| 9.49 \| 2400 \| 0.4480 \| 0.7898 \| 0.79 \| \| 0.4246 \| 10.28 \| 2600 \| 0.4617 \| 0.7928 \| 0.793 \| \| 0.4213 \| 11.07 \| 2800 \| 0.4589 \| 0.7959 \| 0.796 \| \| 0.4184 \| 11.86 \| 3000 \| 0.4577 \| 0.802 \| 0.802 \| \| 0.4163 \| 12.65 \| 3200 \| 0.4438 \| 0.7989 \| 0.799 \| \| 0.4113 \| 13.44 \| 3400 \| 0.4578 \| 0.7910 \| 0.791 \| \| 0.4123 \| 14.23 \| 3600 \| 0.4488 \| 0.7970 \| 0.797 \| \| 0.413 \| 15.02 \| 3800 \| 0.4524 \| 0.8030 \| 0.803 \| \| 0.4097 \| 15.81 \| 4000 \| 0.4458 \| 0.8031 \| 0.803 \| \| 0.4061 \| 16.6 \| 4200 \| 0.4506 \| 0.7931 \| 0.793 \| \| 0.4057 \| 17.39 \| 4400 \| 0.4582 \| 0.8010 \| 0.801 \| \| 0.4026 \| 18.18 \| 4600 \| 0.4506 \| 0.7940 \| 0.794 \| \| 0.4017 \| 18.97 \| 4800 \| 0.4537 \| 0.8030 \| 0.803 \| \| 0.4047 \| 19.76 \| 5000 \| 0.4480 \| 0.7930 \| 0.793 \| \| 0.4006 \| 20.55 \| 5200 \| 0.4479 \| 0.7959 \| 0.796 \| \| 0.3985 \| 21.34 \| 5400 \| 0.4518 \| 0.7920 \| 0.792 \| \| 0.3954 \| 22.13 \| 5600 \| 0.4491 \| 0.8031 \| 0.803 \| \| 0.3984 \| 22.92 \| 5800 \| 0.4509 \| 0.7981 \| 0.798 \| \| 0.3916 \| 23.72 \| 6000 \| 0.4593 \| 0.7910 \| 0.791 \| \| 0.3957 \| 24.51 \| 6200 \| 0.4412 \| 0.8000 \| 0.8 \| \| 0.3965 \| 25.3 \| 6400 \| 0.4484 \| 0.7930 \| 0.793 \| \| 0.3879 \| 26.09 \| 6600 \| 0.4487 \| 0.7859 \| 0.786 \| \| 0.3899 \| 26.88 \| 6800 \| 0.4514 \| 0.7890 \| 0.789 \| \| 0.3879 \| 27.67 \| 7000 \| 0.4503 \| 0.7930 \| 0.793 \| \| 0.3868 \| 28.46 \| 7200 \| 0.4499 \| 0.786 \| 0.786 \| \| 0.3886 \| 29.25 \| 7400 \| 0.4479 \| 0.7950 \| 0.795 \| \| 0.3864 \| 30.04 \| 7600 \| 0.4540 \| 0.7950 \| 0.795 \| \| 0.3848 \| 30.83 \| 7800 \| 0.4525 \| 0.7861 \| 0.786 \| \| 0.3853 \| 31.62 \| 8000 \| 0.4460 \| 0.7929 \| 0.793 \| \| 0.3846 \| 32.41 \| 8200 \| 0.4461 \| 0.7930 \| 0.793 \| \| 0.3812 \| 33.2 \| 8400 \| 0.4534 \| 0.7891 \| 0.789 \| \| 0.3829 \| 33.99 \| 8600 \| 0.4512 \| 0.7940 \| 0.794 \| \| 0.3851 \| 34.78 \| 8800 \| 0.4467 \| 0.7920 \| 0.792 \| \| 0.3764 \| 35.57 \| 9000 \| 0.4498 \| 0.7920 \| 0.792 \| \| 0.3816 \| 36.36 \| 9200 \| 0.4533 \| 0.7931 \| 0.793 \| \| 0.3819 \| 37.15 \| 9400 \| 0.4538 \| 0.7930 \| 0.793 \| \| 0.378 \| 37.94 \| 9600 \| 0.4510 \| 0.7891 \| 0.789 \| \| 0.3787 \| 38.74 \| 9800 \| 0.4517 \| 0.7901 \| 0.79 \| \| 0.3822 \| 39.53 \| 10000 \| 0.4516 \| 0.7891 \| 0.789 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_tf_0-seqsight_4096_512_46M-L8_f", "results": []}]}	mahdibaghbanzadeh/GUE_tf_0-seqsight_4096_512_46M-L8_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_46M", "region:us" ]	null	2024-04-27T00:34:33+00:00	[]	[]	TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us	GUE\_tf\_0-seqsight\_4096\_512\_46M-L8\_f ========================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_4096\_512\_46M on the mahdibaghbanzadeh/GUE\_tf\_0 dataset. It achieves the following results on the evaluation set: * Loss: 0.3756 * F1 Score: 0.8367 * Accuracy: 0.837 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]	[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # llava-1.5-7b-hf-ft-mix-vsft This model is a fine-tuned version of [llava-hf/llava-1.5-7b-hf](https://huggingface.co/llava-hf/llava-1.5-7b-hf) on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1.4e-05 - train_batch_size: 2 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 1 - mixed_precision_training: Native AMP ### Training results ### Framework versions - PEFT 0.10.0 - Transformers 4.40.1 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.19.1	{"library_name": "peft", "tags": ["trl", "sft", "generated_from_trainer"], "base_model": "llava-hf/llava-1.5-7b-hf", "model-index": [{"name": "llava-1.5-7b-hf-ft-mix-vsft", "results": []}]}	Salmoli/llava-1.5-7b-hf-ft-mix-vsft	null	[ "peft", "tensorboard", "safetensors", "trl", "sft", "generated_from_trainer", "base_model:llava-hf/llava-1.5-7b-hf", "region:us" ]	null	2024-04-27T00:38:53+00:00	[]	[]	TAGS #peft #tensorboard #safetensors #trl #sft #generated_from_trainer #base_model-llava-hf/llava-1.5-7b-hf #region-us	# llava-1.5-7b-hf-ft-mix-vsft This model is a fine-tuned version of llava-hf/llava-1.5-7b-hf on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1.4e-05 - train_batch_size: 2 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 1 - mixed_precision_training: Native AMP ### Training results ### Framework versions - PEFT 0.10.0 - Transformers 4.40.1 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.19.1	[ "# llava-1.5-7b-hf-ft-mix-vsft\n\nThis model is a fine-tuned version of llava-hf/llava-1.5-7b-hf on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1.4e-05\n- train_batch_size: 2\n- eval_batch_size: 8\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 1\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- PEFT 0.10.0\n- Transformers 4.40.1\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.19.1" ]	[ "TAGS\n#peft #tensorboard #safetensors #trl #sft #generated_from_trainer #base_model-llava-hf/llava-1.5-7b-hf #region-us \n", "# llava-1.5-7b-hf-ft-mix-vsft\n\nThis model is a fine-tuned version of llava-hf/llava-1.5-7b-hf on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1.4e-05\n- train_batch_size: 2\n- eval_batch_size: 8\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 1\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- PEFT 0.10.0\n- Transformers 4.40.1\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.19.1" ]
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_tf_0-seqsight_4096_512_46M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_tf_0](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_0) dataset. It achieves the following results on the evaluation set: - Loss: 0.3707 - F1 Score: 0.8345 - Accuracy: 0.835 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.4935 \| 0.79 \| 200 \| 0.4703 \| 0.7629 \| 0.763 \| \| 0.4608 \| 1.58 \| 400 \| 0.4577 \| 0.7818 \| 0.782 \| \| 0.4543 \| 2.37 \| 600 \| 0.4608 \| 0.7760 \| 0.777 \| \| 0.4441 \| 3.16 \| 800 \| 0.4574 \| 0.784 \| 0.784 \| \| 0.4378 \| 3.95 \| 1000 \| 0.4475 \| 0.7842 \| 0.785 \| \| 0.4322 \| 4.74 \| 1200 \| 0.4566 \| 0.7828 \| 0.783 \| \| 0.4326 \| 5.53 \| 1400 \| 0.4554 \| 0.7880 \| 0.788 \| \| 0.423 \| 6.32 \| 1600 \| 0.4503 \| 0.7901 \| 0.79 \| \| 0.4232 \| 7.11 \| 1800 \| 0.4613 \| 0.7920 \| 0.792 \| \| 0.4183 \| 7.91 \| 2000 \| 0.4526 \| 0.7910 \| 0.791 \| \| 0.4111 \| 8.7 \| 2200 \| 0.4646 \| 0.7780 \| 0.778 \| \| 0.4044 \| 9.49 \| 2400 \| 0.4524 \| 0.7880 \| 0.788 \| \| 0.407 \| 10.28 \| 2600 \| 0.4713 \| 0.7888 \| 0.789 \| \| 0.4011 \| 11.07 \| 2800 \| 0.4569 \| 0.7950 \| 0.795 \| \| 0.3959 \| 11.86 \| 3000 \| 0.4624 \| 0.7961 \| 0.796 \| \| 0.3912 \| 12.65 \| 3200 \| 0.4450 \| 0.7900 \| 0.79 \| \| 0.3851 \| 13.44 \| 3400 \| 0.4656 \| 0.7860 \| 0.786 \| \| 0.3828 \| 14.23 \| 3600 \| 0.4627 \| 0.7831 \| 0.783 \| \| 0.385 \| 15.02 \| 3800 \| 0.4619 \| 0.7840 \| 0.784 \| \| 0.3776 \| 15.81 \| 4000 \| 0.4544 \| 0.7890 \| 0.789 \| \| 0.3715 \| 16.6 \| 4200 \| 0.4675 \| 0.7900 \| 0.79 \| \| 0.3724 \| 17.39 \| 4400 \| 0.4740 \| 0.7829 \| 0.783 \| \| 0.3647 \| 18.18 \| 4600 \| 0.4801 \| 0.7770 \| 0.777 \| \| 0.3629 \| 18.97 \| 4800 \| 0.4775 \| 0.7906 \| 0.791 \| \| 0.3614 \| 19.76 \| 5000 \| 0.4744 \| 0.7791 \| 0.779 \| \| 0.3561 \| 20.55 \| 5200 \| 0.4928 \| 0.7791 \| 0.779 \| \| 0.3515 \| 21.34 \| 5400 \| 0.4892 \| 0.7790 \| 0.779 \| \| 0.3462 \| 22.13 \| 5600 \| 0.4900 \| 0.784 \| 0.784 \| \| 0.3465 \| 22.92 \| 5800 \| 0.5117 \| 0.77 \| 0.77 \| \| 0.3425 \| 23.72 \| 6000 \| 0.5007 \| 0.7827 \| 0.783 \| \| 0.3392 \| 24.51 \| 6200 \| 0.4958 \| 0.77 \| 0.77 \| \| 0.3388 \| 25.3 \| 6400 \| 0.5055 \| 0.7801 \| 0.78 \| \| 0.3305 \| 26.09 \| 6600 \| 0.5099 \| 0.7690 \| 0.769 \| \| 0.3297 \| 26.88 \| 6800 \| 0.5005 \| 0.7749 \| 0.775 \| \| 0.3299 \| 27.67 \| 7000 \| 0.5162 \| 0.7739 \| 0.774 \| \| 0.3221 \| 28.46 \| 7200 \| 0.5418 \| 0.7690 \| 0.769 \| \| 0.325 \| 29.25 \| 7400 \| 0.5136 \| 0.7720 \| 0.772 \| \| 0.3218 \| 30.04 \| 7600 \| 0.5461 \| 0.7697 \| 0.77 \| \| 0.3187 \| 30.83 \| 7800 \| 0.5346 \| 0.7718 \| 0.772 \| \| 0.3196 \| 31.62 \| 8000 \| 0.5273 \| 0.7721 \| 0.772 \| \| 0.3159 \| 32.41 \| 8200 \| 0.5496 \| 0.7727 \| 0.773 \| \| 0.3117 \| 33.2 \| 8400 \| 0.5563 \| 0.7758 \| 0.776 \| \| 0.3111 \| 33.99 \| 8600 \| 0.5353 \| 0.7729 \| 0.773 \| \| 0.315 \| 34.78 \| 8800 \| 0.5371 \| 0.7750 \| 0.775 \| \| 0.3025 \| 35.57 \| 9000 \| 0.5510 \| 0.7729 \| 0.773 \| \| 0.3085 \| 36.36 \| 9200 \| 0.5592 \| 0.7667 \| 0.767 \| \| 0.3092 \| 37.15 \| 9400 \| 0.5583 \| 0.7725 \| 0.773 \| \| 0.3065 \| 37.94 \| 9600 \| 0.5517 \| 0.7698 \| 0.77 \| \| 0.3047 \| 38.74 \| 9800 \| 0.5561 \| 0.7698 \| 0.77 \| \| 0.3058 \| 39.53 \| 10000 \| 0.5579 \| 0.7687 \| 0.769 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_tf_0-seqsight_4096_512_46M-L32_f", "results": []}]}	mahdibaghbanzadeh/GUE_tf_0-seqsight_4096_512_46M-L32_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_46M", "region:us" ]	null	2024-04-27T00:40:49+00:00	[]	[]	TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us	GUE\_tf\_0-seqsight\_4096\_512\_46M-L32\_f ========================================== This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_4096\_512\_46M on the mahdibaghbanzadeh/GUE\_tf\_0 dataset. It achieves the following results on the evaluation set: * Loss: 0.3707 * F1 Score: 0.8345 * Accuracy: 0.835 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]	[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_tf_1-seqsight_4096_512_46M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_tf_1](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_1) dataset. It achieves the following results on the evaluation set: - Loss: 0.3440 - F1 Score: 0.8597 - Accuracy: 0.86 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.5363 \| 0.83 \| 200 \| 0.5327 \| 0.7246 \| 0.725 \| \| 0.5001 \| 1.67 \| 400 \| 0.5163 \| 0.7348 \| 0.735 \| \| 0.4875 \| 2.5 \| 600 \| 0.5116 \| 0.7419 \| 0.742 \| \| 0.4785 \| 3.33 \| 800 \| 0.5076 \| 0.7285 \| 0.729 \| \| 0.4821 \| 4.17 \| 1000 \| 0.4986 \| 0.7499 \| 0.75 \| \| 0.4692 \| 5.0 \| 1200 \| 0.5033 \| 0.7500 \| 0.75 \| \| 0.4691 \| 5.83 \| 1400 \| 0.4966 \| 0.7480 \| 0.748 \| \| 0.4676 \| 6.67 \| 1600 \| 0.5014 \| 0.7538 \| 0.754 \| \| 0.4672 \| 7.5 \| 1800 \| 0.4977 \| 0.7529 \| 0.753 \| \| 0.4584 \| 8.33 \| 2000 \| 0.4960 \| 0.7569 \| 0.757 \| \| 0.4615 \| 9.17 \| 2200 \| 0.4971 \| 0.7539 \| 0.754 \| \| 0.4591 \| 10.0 \| 2400 \| 0.5072 \| 0.7468 \| 0.748 \| \| 0.4582 \| 10.83 \| 2600 \| 0.4998 \| 0.7505 \| 0.751 \| \| 0.4564 \| 11.67 \| 2800 \| 0.5020 \| 0.7440 \| 0.745 \| \| 0.4478 \| 12.5 \| 3000 \| 0.5042 \| 0.7483 \| 0.749 \| \| 0.459 \| 13.33 \| 3200 \| 0.4915 \| 0.7505 \| 0.751 \| \| 0.4477 \| 14.17 \| 3400 \| 0.4921 \| 0.7529 \| 0.753 \| \| 0.4504 \| 15.0 \| 3600 \| 0.5029 \| 0.7430 \| 0.744 \| \| 0.448 \| 15.83 \| 3800 \| 0.4952 \| 0.7508 \| 0.751 \| \| 0.4509 \| 16.67 \| 4000 \| 0.4993 \| 0.7505 \| 0.751 \| \| 0.445 \| 17.5 \| 4200 \| 0.4965 \| 0.7544 \| 0.755 \| \| 0.4414 \| 18.33 \| 4400 \| 0.5011 \| 0.7589 \| 0.759 \| \| 0.4473 \| 19.17 \| 4600 \| 0.4987 \| 0.7505 \| 0.751 \| \| 0.4435 \| 20.0 \| 4800 \| 0.4937 \| 0.7538 \| 0.754 \| \| 0.4454 \| 20.83 \| 5000 \| 0.4961 \| 0.7518 \| 0.752 \| \| 0.438 \| 21.67 \| 5200 \| 0.4953 \| 0.7468 \| 0.747 \| \| 0.4404 \| 22.5 \| 5400 \| 0.4954 \| 0.754 \| 0.754 \| \| 0.439 \| 23.33 \| 5600 \| 0.4940 \| 0.7546 \| 0.755 \| \| 0.441 \| 24.17 \| 5800 \| 0.4978 \| 0.7518 \| 0.752 \| \| 0.4402 \| 25.0 \| 6000 \| 0.4925 \| 0.7490 \| 0.749 \| \| 0.4375 \| 25.83 \| 6200 \| 0.4923 \| 0.7499 \| 0.75 \| \| 0.4352 \| 26.67 \| 6400 \| 0.4912 \| 0.7489 \| 0.749 \| \| 0.437 \| 27.5 \| 6600 \| 0.4953 \| 0.7540 \| 0.754 \| \| 0.4358 \| 28.33 \| 6800 \| 0.4912 \| 0.7510 \| 0.751 \| \| 0.4317 \| 29.17 \| 7000 \| 0.4930 \| 0.7490 \| 0.749 \| \| 0.4363 \| 30.0 \| 7200 \| 0.4909 \| 0.7559 \| 0.756 \| \| 0.4326 \| 30.83 \| 7400 \| 0.4944 \| 0.7458 \| 0.746 \| \| 0.431 \| 31.67 \| 7600 \| 0.4911 \| 0.7520 \| 0.752 \| \| 0.4318 \| 32.5 \| 7800 \| 0.4921 \| 0.7510 \| 0.751 \| \| 0.4303 \| 33.33 \| 8000 \| 0.4905 \| 0.7530 \| 0.753 \| \| 0.4334 \| 34.17 \| 8200 \| 0.4898 \| 0.7500 \| 0.75 \| \| 0.427 \| 35.0 \| 8400 \| 0.4901 \| 0.7490 \| 0.749 \| \| 0.4301 \| 35.83 \| 8600 \| 0.4907 \| 0.7500 \| 0.75 \| \| 0.4324 \| 36.67 \| 8800 \| 0.4899 \| 0.7540 \| 0.754 \| \| 0.427 \| 37.5 \| 9000 \| 0.4934 \| 0.7468 \| 0.747 \| \| 0.4287 \| 38.33 \| 9200 \| 0.4915 \| 0.7500 \| 0.75 \| \| 0.4273 \| 39.17 \| 9400 \| 0.4921 \| 0.748 \| 0.748 \| \| 0.4298 \| 40.0 \| 9600 \| 0.4915 \| 0.7520 \| 0.752 \| \| 0.4284 \| 40.83 \| 9800 \| 0.4911 \| 0.7480 \| 0.748 \| \| 0.4278 \| 41.67 \| 10000 \| 0.4909 \| 0.7490 \| 0.749 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_tf_1-seqsight_4096_512_46M-L1_f", "results": []}]}	mahdibaghbanzadeh/GUE_tf_1-seqsight_4096_512_46M-L1_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_46M", "region:us" ]	null	2024-04-27T00:41:08+00:00	[]	[]	TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us	GUE\_tf\_1-seqsight\_4096\_512\_46M-L1\_f ========================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_4096\_512\_46M on the mahdibaghbanzadeh/GUE\_tf\_1 dataset. It achieves the following results on the evaluation set: * Loss: 0.3440 * F1 Score: 0.8597 * Accuracy: 0.86 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]	[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]
null	null	sailboat	{"license": "apache-2.0"}	ikukou/sailboat	null	[ "license:apache-2.0", "region:us" ]	null	2024-04-27T00:43:12+00:00	[]	[]	TAGS #license-apache-2.0 #region-us	sailboat	[]	[ "TAGS\n#license-apache-2.0 #region-us \n" ]
image-classification	transformers	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # Boya1_RMSProp_1-e5_10Epoch_swin-large-patch4-window7-224_fold5 This model is a fine-tuned version of [microsoft/swin-large-patch4-window7-224](https://huggingface.co/microsoft/swin-large-patch4-window7-224) on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 1.1456 - Accuracy: 0.6720 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 10 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| 1.1558 \| 1.0 \| 924 \| 1.1699 \| 0.6023 \| \| 0.9755 \| 2.0 \| 1848 \| 0.9954 \| 0.6522 \| \| 0.7954 \| 3.0 \| 2772 \| 0.9696 \| 0.6753 \| \| 0.5362 \| 4.0 \| 3696 \| 0.9918 \| 0.6682 \| \| 0.5694 \| 5.0 \| 4620 \| 0.9924 \| 0.6712 \| \| 0.6743 \| 6.0 \| 5544 \| 1.0447 \| 0.6687 \| \| 0.5077 \| 7.0 \| 6468 \| 1.0595 \| 0.6717 \| \| 0.368 \| 8.0 \| 7392 \| 1.1004 \| 0.6717 \| \| 0.2622 \| 9.0 \| 8316 \| 1.1347 \| 0.6709 \| \| 0.267 \| 10.0 \| 9240 \| 1.1456 \| 0.6720 \| ### Framework versions - Transformers 4.35.0 - Pytorch 2.1.0 - Datasets 2.14.6 - Tokenizers 0.14.1	{"license": "apache-2.0", "tags": ["generated_from_trainer"], "datasets": ["imagefolder"], "metrics": ["accuracy"], "base_model": "microsoft/swin-large-patch4-window7-224", "model-index": [{"name": "Boya1_RMSProp_1-e5_10Epoch_swin-large-patch4-window7-224_fold5", "results": [{"task": {"type": "image-classification", "name": "Image Classification"}, "dataset": {"name": "imagefolder", "type": "imagefolder", "config": "default", "split": "test", "args": "default"}, "metrics": [{"type": "accuracy", "value": 0.6719978313906207, "name": "Accuracy"}]}]}]}	onizukal/Boya1_RMSProp_1-e5_10Epoch_swin-large-patch4-window7-224_fold5	null	[ "transformers", "safetensors", "swin", "image-classification", "generated_from_trainer", "dataset:imagefolder", "base_model:microsoft/swin-large-patch4-window7-224", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-27T00:44:34+00:00	[]	[]	TAGS #transformers #safetensors #swin #image-classification #generated_from_trainer #dataset-imagefolder #base_model-microsoft/swin-large-patch4-window7-224 #license-apache-2.0 #model-index #autotrain_compatible #endpoints_compatible #region-us	Boya1\_RMSProp\_1-e5\_10Epoch\_swin-large-patch4-window7-224\_fold5 =================================================================== This model is a fine-tuned version of microsoft/swin-large-patch4-window7-224 on the imagefolder dataset. It achieves the following results on the evaluation set: * Loss: 1.1456 * Accuracy: 0.6720 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 1e-05 * train\_batch\_size: 16 * eval\_batch\_size: 16 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * lr\_scheduler\_warmup\_ratio: 0.1 * num\_epochs: 10 ### Training results ### Framework versions * Transformers 4.35.0 * Pytorch 2.1.0 * Datasets 2.14.6 * Tokenizers 0.14.1	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 10", "### Training results", "### Framework versions\n\n\n* Transformers 4.35.0\n* Pytorch 2.1.0\n* Datasets 2.14.6\n* Tokenizers 0.14.1" ]	[ "TAGS\n#transformers #safetensors #swin #image-classification #generated_from_trainer #dataset-imagefolder #base_model-microsoft/swin-large-patch4-window7-224 #license-apache-2.0 #model-index #autotrain_compatible #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 10", "### Training results", "### Framework versions\n\n\n* Transformers 4.35.0\n* Pytorch 2.1.0\n* Datasets 2.14.6\n* Tokenizers 0.14.1" ]
text2text-generation	transformers	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # CS505_COQE_viT5_train_Instruction0_SPOAL_v1 This model is a fine-tuned version of [VietAI/vit5-large](https://huggingface.co/VietAI/vit5-large) on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 20 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.15.2	{"license": "mit", "tags": ["generated_from_trainer"], "base_model": "VietAI/vit5-large", "model-index": [{"name": "CS505_COQE_viT5_train_Instruction0_SPOAL_v1", "results": []}]}	ThuyNT/CS505_COQE_viT5_train_Instruction0_SPOAL_v1	null	[ "transformers", "tensorboard", "safetensors", "t5", "text2text-generation", "generated_from_trainer", "base_model:VietAI/vit5-large", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-27T00:45:10+00:00	[]	[]	TAGS #transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-VietAI/vit5-large #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us	# CS505_COQE_viT5_train_Instruction0_SPOAL_v1 This model is a fine-tuned version of VietAI/vit5-large on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 20 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.15.2	[ "# CS505_COQE_viT5_train_Instruction0_SPOAL_v1\n\nThis model is a fine-tuned version of VietAI/vit5-large on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 20\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]	[ "TAGS\n#transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-VietAI/vit5-large #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# CS505_COQE_viT5_train_Instruction0_SPOAL_v1\n\nThis model is a fine-tuned version of VietAI/vit5-large on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 20\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_tf_1-seqsight_4096_512_46M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_tf_1](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_1) dataset. It achieves the following results on the evaluation set: - Loss: 0.3395 - F1 Score: 0.8587 - Accuracy: 0.859 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.5242 \| 0.83 \| 200 \| 0.5228 \| 0.7387 \| 0.74 \| \| 0.4863 \| 1.67 \| 400 \| 0.5057 \| 0.7428 \| 0.743 \| \| 0.4772 \| 2.5 \| 600 \| 0.4998 \| 0.7559 \| 0.756 \| \| 0.4696 \| 3.33 \| 800 \| 0.4954 \| 0.7580 \| 0.758 \| \| 0.4708 \| 4.17 \| 1000 \| 0.4919 \| 0.7550 \| 0.755 \| \| 0.4593 \| 5.0 \| 1200 \| 0.4989 \| 0.7537 \| 0.754 \| \| 0.4586 \| 5.83 \| 1400 \| 0.4896 \| 0.7590 \| 0.759 \| \| 0.4549 \| 6.67 \| 1600 \| 0.4875 \| 0.7630 \| 0.763 \| \| 0.4559 \| 7.5 \| 1800 \| 0.4899 \| 0.7618 \| 0.762 \| \| 0.4469 \| 8.33 \| 2000 \| 0.4868 \| 0.7640 \| 0.764 \| \| 0.4491 \| 9.17 \| 2200 \| 0.4838 \| 0.7610 \| 0.761 \| \| 0.445 \| 10.0 \| 2400 \| 0.5029 \| 0.7458 \| 0.747 \| \| 0.4443 \| 10.83 \| 2600 \| 0.4904 \| 0.7595 \| 0.76 \| \| 0.4407 \| 11.67 \| 2800 \| 0.4849 \| 0.7636 \| 0.764 \| \| 0.4315 \| 12.5 \| 3000 \| 0.4869 \| 0.7516 \| 0.752 \| \| 0.4437 \| 13.33 \| 3200 \| 0.4789 \| 0.7668 \| 0.767 \| \| 0.4306 \| 14.17 \| 3400 \| 0.4806 \| 0.7607 \| 0.761 \| \| 0.4323 \| 15.0 \| 3600 \| 0.4877 \| 0.7603 \| 0.761 \| \| 0.4293 \| 15.83 \| 3800 \| 0.4833 \| 0.7558 \| 0.756 \| \| 0.4302 \| 16.67 \| 4000 \| 0.4819 \| 0.7590 \| 0.759 \| \| 0.4254 \| 17.5 \| 4200 \| 0.4873 \| 0.7620 \| 0.763 \| \| 0.4196 \| 18.33 \| 4400 \| 0.4848 \| 0.7600 \| 0.76 \| \| 0.4254 \| 19.17 \| 4600 \| 0.4872 \| 0.7545 \| 0.755 \| \| 0.4204 \| 20.0 \| 4800 \| 0.4785 \| 0.7630 \| 0.763 \| \| 0.4233 \| 20.83 \| 5000 \| 0.4829 \| 0.7719 \| 0.772 \| \| 0.4157 \| 21.67 \| 5200 \| 0.4803 \| 0.7618 \| 0.762 \| \| 0.4151 \| 22.5 \| 5400 \| 0.4865 \| 0.7609 \| 0.761 \| \| 0.4151 \| 23.33 \| 5600 \| 0.4885 \| 0.7528 \| 0.754 \| \| 0.4161 \| 24.17 \| 5800 \| 0.4884 \| 0.7557 \| 0.756 \| \| 0.4137 \| 25.0 \| 6000 \| 0.4851 \| 0.7590 \| 0.759 \| \| 0.411 \| 25.83 \| 6200 \| 0.4834 \| 0.7550 \| 0.755 \| \| 0.4078 \| 26.67 \| 6400 \| 0.4848 \| 0.7610 \| 0.761 \| \| 0.4098 \| 27.5 \| 6600 \| 0.4882 \| 0.7580 \| 0.758 \| \| 0.4089 \| 28.33 \| 6800 \| 0.4862 \| 0.7630 \| 0.763 \| \| 0.4039 \| 29.17 \| 7000 \| 0.4860 \| 0.7609 \| 0.761 \| \| 0.4091 \| 30.0 \| 7200 \| 0.4843 \| 0.7589 \| 0.759 \| \| 0.4036 \| 30.83 \| 7400 \| 0.4903 \| 0.7536 \| 0.754 \| \| 0.4007 \| 31.67 \| 7600 \| 0.4874 \| 0.762 \| 0.762 \| \| 0.4024 \| 32.5 \| 7800 \| 0.4933 \| 0.7570 \| 0.757 \| \| 0.4003 \| 33.33 \| 8000 \| 0.4869 \| 0.7589 \| 0.759 \| \| 0.4038 \| 34.17 \| 8200 \| 0.4885 \| 0.7569 \| 0.757 \| \| 0.3966 \| 35.0 \| 8400 \| 0.4872 \| 0.7630 \| 0.763 \| \| 0.3992 \| 35.83 \| 8600 \| 0.4895 \| 0.7549 \| 0.755 \| \| 0.4022 \| 36.67 \| 8800 \| 0.4880 \| 0.7559 \| 0.756 \| \| 0.3953 \| 37.5 \| 9000 \| 0.4931 \| 0.7485 \| 0.749 \| \| 0.3971 \| 38.33 \| 9200 \| 0.4926 \| 0.7580 \| 0.758 \| \| 0.3958 \| 39.17 \| 9400 \| 0.4919 \| 0.7599 \| 0.76 \| \| 0.3969 \| 40.0 \| 9600 \| 0.4915 \| 0.7559 \| 0.756 \| \| 0.3966 \| 40.83 \| 9800 \| 0.4915 \| 0.7640 \| 0.764 \| \| 0.3956 \| 41.67 \| 10000 \| 0.4909 \| 0.7579 \| 0.758 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_tf_1-seqsight_4096_512_46M-L8_f", "results": []}]}	mahdibaghbanzadeh/GUE_tf_1-seqsight_4096_512_46M-L8_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_46M", "region:us" ]	null	2024-04-27T00:48:37+00:00	[]	[]	TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us	GUE\_tf\_1-seqsight\_4096\_512\_46M-L8\_f ========================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_4096\_512\_46M on the mahdibaghbanzadeh/GUE\_tf\_1 dataset. It achieves the following results on the evaluation set: * Loss: 0.3395 * F1 Score: 0.8587 * Accuracy: 0.859 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]	[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_tf_1-seqsight_4096_512_46M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_tf_1](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_1) dataset. It achieves the following results on the evaluation set: - Loss: 0.3578 - F1 Score: 0.8591 - Accuracy: 0.86 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.5178 \| 0.83 \| 200 \| 0.5181 \| 0.7554 \| 0.756 \| \| 0.4819 \| 1.67 \| 400 \| 0.5070 \| 0.7479 \| 0.748 \| \| 0.4721 \| 2.5 \| 600 \| 0.5003 \| 0.7550 \| 0.755 \| \| 0.4633 \| 3.33 \| 800 \| 0.4913 \| 0.7500 \| 0.75 \| \| 0.4611 \| 4.17 \| 1000 \| 0.4880 \| 0.7457 \| 0.746 \| \| 0.451 \| 5.0 \| 1200 \| 0.4936 \| 0.7599 \| 0.76 \| \| 0.4455 \| 5.83 \| 1400 \| 0.4886 \| 0.7550 \| 0.755 \| \| 0.4398 \| 6.67 \| 1600 \| 0.4827 \| 0.7540 \| 0.754 \| \| 0.4403 \| 7.5 \| 1800 \| 0.4871 \| 0.7565 \| 0.757 \| \| 0.4285 \| 8.33 \| 2000 \| 0.4859 \| 0.7600 \| 0.76 \| \| 0.4291 \| 9.17 \| 2200 \| 0.4824 \| 0.756 \| 0.756 \| \| 0.4231 \| 10.0 \| 2400 \| 0.4961 \| 0.7518 \| 0.753 \| \| 0.4183 \| 10.83 \| 2600 \| 0.4858 \| 0.7586 \| 0.759 \| \| 0.4125 \| 11.67 \| 2800 \| 0.4818 \| 0.7580 \| 0.758 \| \| 0.4046 \| 12.5 \| 3000 \| 0.4903 \| 0.7595 \| 0.76 \| \| 0.4113 \| 13.33 \| 3200 \| 0.4825 \| 0.7658 \| 0.766 \| \| 0.3989 \| 14.17 \| 3400 \| 0.4853 \| 0.7730 \| 0.773 \| \| 0.3986 \| 15.0 \| 3600 \| 0.4928 \| 0.7634 \| 0.764 \| \| 0.3925 \| 15.83 \| 3800 \| 0.4894 \| 0.7678 \| 0.768 \| \| 0.3898 \| 16.67 \| 4000 \| 0.4929 \| 0.764 \| 0.764 \| \| 0.386 \| 17.5 \| 4200 \| 0.4984 \| 0.7664 \| 0.767 \| \| 0.374 \| 18.33 \| 4400 \| 0.5094 \| 0.7630 \| 0.763 \| \| 0.3786 \| 19.17 \| 4600 \| 0.5111 \| 0.7638 \| 0.764 \| \| 0.374 \| 20.0 \| 4800 \| 0.5076 \| 0.7560 \| 0.756 \| \| 0.3709 \| 20.83 \| 5000 \| 0.5112 \| 0.7650 \| 0.765 \| \| 0.3616 \| 21.67 \| 5200 \| 0.5153 \| 0.7609 \| 0.761 \| \| 0.3613 \| 22.5 \| 5400 \| 0.5168 \| 0.7610 \| 0.761 \| \| 0.3574 \| 23.33 \| 5600 \| 0.5195 \| 0.7615 \| 0.762 \| \| 0.3574 \| 24.17 \| 5800 \| 0.5281 \| 0.7595 \| 0.76 \| \| 0.352 \| 25.0 \| 6000 \| 0.5211 \| 0.7670 \| 0.767 \| \| 0.3476 \| 25.83 \| 6200 \| 0.5293 \| 0.7609 \| 0.761 \| \| 0.3458 \| 26.67 \| 6400 \| 0.5182 \| 0.7620 \| 0.762 \| \| 0.3432 \| 27.5 \| 6600 \| 0.5400 \| 0.7570 \| 0.757 \| \| 0.3399 \| 28.33 \| 6800 \| 0.5396 \| 0.7500 \| 0.75 \| \| 0.3329 \| 29.17 \| 7000 \| 0.5313 \| 0.7558 \| 0.756 \| \| 0.3357 \| 30.0 \| 7200 \| 0.5416 \| 0.7589 \| 0.759 \| \| 0.3301 \| 30.83 \| 7400 \| 0.5557 \| 0.7504 \| 0.751 \| \| 0.3245 \| 31.67 \| 7600 \| 0.5575 \| 0.7578 \| 0.758 \| \| 0.328 \| 32.5 \| 7800 \| 0.5649 \| 0.7580 \| 0.758 \| \| 0.3233 \| 33.33 \| 8000 \| 0.5662 \| 0.7546 \| 0.755 \| \| 0.33 \| 34.17 \| 8200 \| 0.5604 \| 0.7508 \| 0.751 \| \| 0.3193 \| 35.0 \| 8400 \| 0.5548 \| 0.7619 \| 0.762 \| \| 0.3212 \| 35.83 \| 8600 \| 0.5584 \| 0.7539 \| 0.754 \| \| 0.3185 \| 36.67 \| 8800 \| 0.5635 \| 0.7489 \| 0.749 \| \| 0.3152 \| 37.5 \| 9000 \| 0.5705 \| 0.7573 \| 0.758 \| \| 0.3089 \| 38.33 \| 9200 \| 0.5811 \| 0.7539 \| 0.754 \| \| 0.3108 \| 39.17 \| 9400 \| 0.5683 \| 0.7578 \| 0.758 \| \| 0.3144 \| 40.0 \| 9600 \| 0.5730 \| 0.7547 \| 0.755 \| \| 0.3124 \| 40.83 \| 9800 \| 0.5736 \| 0.7560 \| 0.756 \| \| 0.31 \| 41.67 \| 10000 \| 0.5746 \| 0.7518 \| 0.752 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_tf_1-seqsight_4096_512_46M-L32_f", "results": []}]}	mahdibaghbanzadeh/GUE_tf_1-seqsight_4096_512_46M-L32_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_46M", "region:us" ]	null	2024-04-27T00:48:37+00:00	[]	[]	TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us	GUE\_tf\_1-seqsight\_4096\_512\_46M-L32\_f ========================================== This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_4096\_512\_46M on the mahdibaghbanzadeh/GUE\_tf\_1 dataset. It achieves the following results on the evaluation set: * Loss: 0.3578 * F1 Score: 0.8591 * Accuracy: 0.86 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]	[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_tf_4-seqsight_4096_512_46M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_tf_4](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_4) dataset. It achieves the following results on the evaluation set: - Loss: 0.3559 - F1 Score: 0.8462 - Accuracy: 0.847 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.5287 \| 1.34 \| 200 \| 0.5089 \| 0.7376 \| 0.738 \| \| 0.4796 \| 2.68 \| 400 \| 0.4835 \| 0.7698 \| 0.77 \| \| 0.4591 \| 4.03 \| 600 \| 0.4711 \| 0.7733 \| 0.774 \| \| 0.4496 \| 5.37 \| 800 \| 0.4665 \| 0.7789 \| 0.779 \| \| 0.4341 \| 6.71 \| 1000 \| 0.4513 \| 0.7908 \| 0.791 \| \| 0.4287 \| 8.05 \| 1200 \| 0.4501 \| 0.7888 \| 0.789 \| \| 0.4239 \| 9.4 \| 1400 \| 0.4484 \| 0.7960 \| 0.796 \| \| 0.419 \| 10.74 \| 1600 \| 0.4484 \| 0.8027 \| 0.803 \| \| 0.4107 \| 12.08 \| 1800 \| 0.4510 \| 0.7993 \| 0.8 \| \| 0.4106 \| 13.42 \| 2000 \| 0.4351 \| 0.8010 \| 0.801 \| \| 0.3995 \| 14.77 \| 2200 \| 0.4371 \| 0.7987 \| 0.799 \| \| 0.4025 \| 16.11 \| 2400 \| 0.4327 \| 0.8100 \| 0.81 \| \| 0.3956 \| 17.45 \| 2600 \| 0.4302 \| 0.8110 \| 0.811 \| \| 0.3907 \| 18.79 \| 2800 \| 0.4324 \| 0.8090 \| 0.809 \| \| 0.394 \| 20.13 \| 3000 \| 0.4252 \| 0.8099 \| 0.81 \| \| 0.3851 \| 21.48 \| 3200 \| 0.4278 \| 0.8180 \| 0.818 \| \| 0.3797 \| 22.82 \| 3400 \| 0.4284 \| 0.8117 \| 0.812 \| \| 0.3805 \| 24.16 \| 3600 \| 0.4223 \| 0.8129 \| 0.813 \| \| 0.3756 \| 25.5 \| 3800 \| 0.4274 \| 0.8095 \| 0.81 \| \| 0.3731 \| 26.85 \| 4000 \| 0.4213 \| 0.8150 \| 0.815 \| \| 0.3697 \| 28.19 \| 4200 \| 0.4202 \| 0.8110 \| 0.811 \| \| 0.3623 \| 29.53 \| 4400 \| 0.4219 \| 0.8150 \| 0.815 \| \| 0.3626 \| 30.87 \| 4600 \| 0.4158 \| 0.8130 \| 0.813 \| \| 0.3615 \| 32.21 \| 4800 \| 0.4192 \| 0.8260 \| 0.826 \| \| 0.358 \| 33.56 \| 5000 \| 0.4179 \| 0.8159 \| 0.816 \| \| 0.3587 \| 34.9 \| 5200 \| 0.4164 \| 0.8140 \| 0.814 \| \| 0.3535 \| 36.24 \| 5400 \| 0.4185 \| 0.8199 \| 0.82 \| \| 0.3502 \| 37.58 \| 5600 \| 0.4194 \| 0.8189 \| 0.819 \| \| 0.3495 \| 38.93 \| 5800 \| 0.4166 \| 0.8150 \| 0.815 \| \| 0.3444 \| 40.27 \| 6000 \| 0.4211 \| 0.8140 \| 0.814 \| \| 0.3449 \| 41.61 \| 6200 \| 0.4179 \| 0.8190 \| 0.819 \| \| 0.3427 \| 42.95 \| 6400 \| 0.4192 \| 0.8160 \| 0.816 \| \| 0.3455 \| 44.3 \| 6600 \| 0.4171 \| 0.8198 \| 0.82 \| \| 0.3345 \| 45.64 \| 6800 \| 0.4180 \| 0.8180 \| 0.818 \| \| 0.338 \| 46.98 \| 7000 \| 0.4168 \| 0.8149 \| 0.815 \| \| 0.3369 \| 48.32 \| 7200 \| 0.4144 \| 0.8110 \| 0.811 \| \| 0.3356 \| 49.66 \| 7400 \| 0.4122 \| 0.8210 \| 0.821 \| \| 0.3338 \| 51.01 \| 7600 \| 0.4153 \| 0.8189 \| 0.819 \| \| 0.3316 \| 52.35 \| 7800 \| 0.4163 \| 0.8166 \| 0.817 \| \| 0.3275 \| 53.69 \| 8000 \| 0.4147 \| 0.8200 \| 0.82 \| \| 0.3327 \| 55.03 \| 8200 \| 0.4122 \| 0.8180 \| 0.818 \| \| 0.3313 \| 56.38 \| 8400 \| 0.4119 \| 0.8198 \| 0.82 \| \| 0.3263 \| 57.72 \| 8600 \| 0.4142 \| 0.8228 \| 0.823 \| \| 0.3257 \| 59.06 \| 8800 \| 0.4120 \| 0.8179 \| 0.818 \| \| 0.3257 \| 60.4 \| 9000 \| 0.4129 \| 0.8180 \| 0.818 \| \| 0.3227 \| 61.74 \| 9200 \| 0.4148 \| 0.8187 \| 0.819 \| \| 0.3229 \| 63.09 \| 9400 \| 0.4128 \| 0.8219 \| 0.822 \| \| 0.3251 \| 64.43 \| 9600 \| 0.4119 \| 0.8209 \| 0.821 \| \| 0.3206 \| 65.77 \| 9800 \| 0.4119 \| 0.8199 \| 0.82 \| \| 0.3228 \| 67.11 \| 10000 \| 0.4122 \| 0.8199 \| 0.82 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_tf_4-seqsight_4096_512_46M-L1_f", "results": []}]}	mahdibaghbanzadeh/GUE_tf_4-seqsight_4096_512_46M-L1_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_46M", "region:us" ]	null	2024-04-27T00:54:41+00:00	[]	[]	TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us	GUE\_tf\_4-seqsight\_4096\_512\_46M-L1\_f ========================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_4096\_512\_46M on the mahdibaghbanzadeh/GUE\_tf\_4 dataset. It achieves the following results on the evaluation set: * Loss: 0.3559 * F1 Score: 0.8462 * Accuracy: 0.847 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]	[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_tf_4-seqsight_4096_512_46M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_tf_4](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_4) dataset. It achieves the following results on the evaluation set: - Loss: 0.3872 - F1 Score: 0.8608 - Accuracy: 0.861 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.5114 \| 1.34 \| 200 \| 0.4841 \| 0.7588 \| 0.759 \| \| 0.4533 \| 2.68 \| 400 \| 0.4569 \| 0.7879 \| 0.788 \| \| 0.4314 \| 4.03 \| 600 \| 0.4494 \| 0.7879 \| 0.788 \| \| 0.4235 \| 5.37 \| 800 \| 0.4531 \| 0.7849 \| 0.785 \| \| 0.4091 \| 6.71 \| 1000 \| 0.4446 \| 0.7892 \| 0.79 \| \| 0.4027 \| 8.05 \| 1200 \| 0.4379 \| 0.8110 \| 0.811 \| \| 0.3978 \| 9.4 \| 1400 \| 0.4401 \| 0.8089 \| 0.809 \| \| 0.392 \| 10.74 \| 1600 \| 0.4347 \| 0.804 \| 0.804 \| \| 0.382 \| 12.08 \| 1800 \| 0.4428 \| 0.8020 \| 0.802 \| \| 0.3794 \| 13.42 \| 2000 \| 0.4361 \| 0.7995 \| 0.8 \| \| 0.3679 \| 14.77 \| 2200 \| 0.4246 \| 0.8059 \| 0.806 \| \| 0.3698 \| 16.11 \| 2400 \| 0.4268 \| 0.8108 \| 0.811 \| \| 0.3603 \| 17.45 \| 2600 \| 0.4300 \| 0.8089 \| 0.809 \| \| 0.3535 \| 18.79 \| 2800 \| 0.4289 \| 0.8220 \| 0.822 \| \| 0.3563 \| 20.13 \| 3000 \| 0.4140 \| 0.8100 \| 0.81 \| \| 0.3448 \| 21.48 \| 3200 \| 0.4314 \| 0.8023 \| 0.803 \| \| 0.3366 \| 22.82 \| 3400 \| 0.4326 \| 0.7985 \| 0.799 \| \| 0.3365 \| 24.16 \| 3600 \| 0.4185 \| 0.8029 \| 0.803 \| \| 0.3282 \| 25.5 \| 3800 \| 0.4323 \| 0.8017 \| 0.802 \| \| 0.3253 \| 26.85 \| 4000 \| 0.4284 \| 0.8069 \| 0.807 \| \| 0.3204 \| 28.19 \| 4200 \| 0.4233 \| 0.8070 \| 0.807 \| \| 0.311 \| 29.53 \| 4400 \| 0.4352 \| 0.8064 \| 0.807 \| \| 0.3127 \| 30.87 \| 4600 \| 0.4316 \| 0.8007 \| 0.801 \| \| 0.3054 \| 32.21 \| 4800 \| 0.4319 \| 0.8050 \| 0.805 \| \| 0.3041 \| 33.56 \| 5000 \| 0.4301 \| 0.8080 \| 0.808 \| \| 0.2983 \| 34.9 \| 5200 \| 0.4331 \| 0.8070 \| 0.807 \| \| 0.2925 \| 36.24 \| 5400 \| 0.4322 \| 0.8126 \| 0.813 \| \| 0.2899 \| 37.58 \| 5600 \| 0.4373 \| 0.808 \| 0.808 \| \| 0.2883 \| 38.93 \| 5800 \| 0.4288 \| 0.8030 \| 0.803 \| \| 0.2819 \| 40.27 \| 6000 \| 0.4460 \| 0.8142 \| 0.815 \| \| 0.2787 \| 41.61 \| 6200 \| 0.4333 \| 0.8130 \| 0.813 \| \| 0.2745 \| 42.95 \| 6400 \| 0.4375 \| 0.8140 \| 0.814 \| \| 0.2785 \| 44.3 \| 6600 \| 0.4389 \| 0.8157 \| 0.816 \| \| 0.2678 \| 45.64 \| 6800 \| 0.4411 \| 0.8140 \| 0.814 \| \| 0.2698 \| 46.98 \| 7000 \| 0.4366 \| 0.8148 \| 0.815 \| \| 0.2656 \| 48.32 \| 7200 \| 0.4422 \| 0.8217 \| 0.822 \| \| 0.2664 \| 49.66 \| 7400 \| 0.4372 \| 0.8218 \| 0.822 \| \| 0.2633 \| 51.01 \| 7600 \| 0.4431 \| 0.8140 \| 0.814 \| \| 0.2598 \| 52.35 \| 7800 \| 0.4473 \| 0.8165 \| 0.817 \| \| 0.2547 \| 53.69 \| 8000 \| 0.4394 \| 0.8200 \| 0.82 \| \| 0.2555 \| 55.03 \| 8200 \| 0.4385 \| 0.822 \| 0.822 \| \| 0.2551 \| 56.38 \| 8400 \| 0.4433 \| 0.8239 \| 0.824 \| \| 0.2517 \| 57.72 \| 8600 \| 0.4488 \| 0.8217 \| 0.822 \| \| 0.2521 \| 59.06 \| 8800 \| 0.4459 \| 0.8187 \| 0.819 \| \| 0.2506 \| 60.4 \| 9000 \| 0.4476 \| 0.8218 \| 0.822 \| \| 0.2491 \| 61.74 \| 9200 \| 0.4567 \| 0.8134 \| 0.814 \| \| 0.2485 \| 63.09 \| 9400 \| 0.4474 \| 0.8228 \| 0.823 \| \| 0.2474 \| 64.43 \| 9600 \| 0.4485 \| 0.8217 \| 0.822 \| \| 0.2433 \| 65.77 \| 9800 \| 0.4475 \| 0.8218 \| 0.822 \| \| 0.2437 \| 67.11 \| 10000 \| 0.4489 \| 0.8218 \| 0.822 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_tf_4-seqsight_4096_512_46M-L8_f", "results": []}]}	mahdibaghbanzadeh/GUE_tf_4-seqsight_4096_512_46M-L8_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_46M", "region:us" ]	null	2024-04-27T00:54:42+00:00	[]	[]	TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us	GUE\_tf\_4-seqsight\_4096\_512\_46M-L8\_f ========================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_4096\_512\_46M on the mahdibaghbanzadeh/GUE\_tf\_4 dataset. It achieves the following results on the evaluation set: * Loss: 0.3872 * F1 Score: 0.8608 * Accuracy: 0.861 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]	[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]
text2text-generation	transformers	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # CS505_COQE_viT5_train_Instruction0_OPSAL_v1 This model is a fine-tuned version of [VietAI/vit5-large](https://huggingface.co/VietAI/vit5-large) on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 20 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.15.2	{"license": "mit", "tags": ["generated_from_trainer"], "base_model": "VietAI/vit5-large", "model-index": [{"name": "CS505_COQE_viT5_train_Instruction0_OPSAL_v1", "results": []}]}	ThuyNT/CS505_COQE_viT5_train_Instruction0_OPSAL_v1	null	[ "transformers", "tensorboard", "safetensors", "t5", "text2text-generation", "generated_from_trainer", "base_model:VietAI/vit5-large", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-27T00:56:55+00:00	[]	[]	TAGS #transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-VietAI/vit5-large #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us	# CS505_COQE_viT5_train_Instruction0_OPSAL_v1 This model is a fine-tuned version of VietAI/vit5-large on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 20 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.15.2	[ "# CS505_COQE_viT5_train_Instruction0_OPSAL_v1\n\nThis model is a fine-tuned version of VietAI/vit5-large on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 20\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]	[ "TAGS\n#transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-VietAI/vit5-large #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# CS505_COQE_viT5_train_Instruction0_OPSAL_v1\n\nThis model is a fine-tuned version of VietAI/vit5-large on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 20\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]
text-generation	transformers	# Model This model is fine-tuned based on Meta-Llama/Meta-Llama-3-8B instructions via mlx-lm. Note: The glaive-function-calling-v2 dataset contains some invalid JSON and single quotes for the arguments' values. I have re-trained the model based on cleaned-up data. If you encounter issues with the function calling JSON format, you may try this new version here: https://huggingface.co/mzbac/llama-3-8B-Instruct-function-calling-v0.2 ## Usage ```python from transformers import AutoTokenizer, AutoModelForCausalLM import torch model_id = "mzbac/llama-3-8B-Instruct-function-calling" tokenizer = AutoTokenizer.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype=torch.bfloat16, device_map="auto", ) tool = { "name": "search_web", "description": "Perform a web search for a given search terms.", "parameter": { "type": "object", "properties": { "search_terms": { "type": "array", "items": {"type": "string"}, "description": "The search queries for which the search is performed.", "required": True, } } }, } messages = [ { "role": "system", "content": f"You are a helpful assistant with access to the following functions. Use them if required - {str(tool)}", }, {"role": "user", "content": "Today's news in Melbourne, just for your information, today is April 27, 2014."}, ] input_ids = tokenizer.apply_chat_template( messages, add_generation_prompt=True, return_tensors="pt" ).to(model.device) terminators = [ tokenizer.eos_token_id, tokenizer.convert_tokens_to_ids("<\|eot_id\|>") ] outputs = model.generate( input_ids, max_new_tokens=256, eos_token_id=terminators, do_sample=True, temperature=0.1, ) response = outputs[0] print(tokenizer.decode(response)) # <\|begin_of_text\|><\|start_header_id\|>system<\|end_header_id\|> # You are a helpful assistant with access to the following functions. Use them if required - {'name':'search_web', 'description': 'Perform a web search for a given search terms.', 'parameter': {'type': 'object', 'properties': {'search_terms': {'type': 'array', 'items': {'type':'string'}, 'description': 'The search queries for which the search is performed.','required': True}}}}<\|eot_id\|><\|start_header_id\|>user<\|end_header_id\|> # Today's news in Melbourne, just for your information, today is April 27, 2014.<\|eot_id\|><\|start_header_id\|>assistant<\|end_header_id\|> # <functioncall> {"name": "search_web", "arguments": '{"search_terms": ["Melbourne news", "April 27, 2014"]}'}<\|eot_id\|> ``` ## Training hyperparameters lora_config.yaml ```yaml # The path to the local model directory or Hugging Face repo. model: "meta-llama/Meta-Llama-3-8B-Instruct" # Whether or not to train (boolean) train: true # Directory with {train, valid, test}.jsonl files data: "data" # The PRNG seed seed: 0 # Number of layers to fine-tune lora_layers: 32 # Minibatch size. batch_size: 1 # Iterations to train for. iters: 6000 # Number of validation batches, -1 uses the entire validation set. val_batches: 25 # Adam learning rate. learning_rate: 1e-6 # Number of training steps between loss reporting. steps_per_report: 10 # Number of training steps between validations. steps_per_eval: 200 # Load path to resume training with the given adapter weights. resume_adapter_file: null # Save/load path for the trained adapter weights. adapter_path: "adapters" # Save the model every N iterations. save_every: 1000 # Evaluate on the test set after training test: false # Number of test set batches, -1 uses the entire test set. test_batches: 100 # Maximum sequence length. max_seq_length: 8192 # Use gradient checkpointing to reduce memory use. grad_checkpoint: false # LoRA parameters can only be specified in a config file lora_parameters: # The layer keys to apply LoRA to. # These will be applied for the last lora_layers keys: ['mlp.gate_proj', 'mlp.down_proj', 'self_attn.q_proj', 'mlp.up_proj', 'self_attn.o_proj','self_attn.v_proj', 'self_attn.k_proj'] rank: 128 alpha: 256 scale: 10.0 dropout: 0.05 # Schedule can only be specified in a config file, uncomment to use. #lr_schedule: # name: cosine_decay # warmup: 100 # 0 for no warmup # warmup_init: 1e-7 # 0 if not specified # arguments: [1e-6, 1000, 1e-7] # passed to scheduler ```	{"language": ["en"], "license": "llama3", "datasets": ["mzbac/glaive-function-calling-v2-llama-3-format"]}	mzbac/llama-3-8B-Instruct-function-calling	null	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "en", "dataset:mzbac/glaive-function-calling-v2-llama-3-format", "license:llama3", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-27T00:57:38+00:00	[]	[ "en" ]	TAGS #transformers #safetensors #llama #text-generation #conversational #en #dataset-mzbac/glaive-function-calling-v2-llama-3-format #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us	# Model This model is fine-tuned based on Meta-Llama/Meta-Llama-3-8B instructions via mlx-lm. Note: The glaive-function-calling-v2 dataset contains some invalid JSON and single quotes for the arguments' values. I have re-trained the model based on cleaned-up data. If you encounter issues with the function calling JSON format, you may try this new version here: URL ## Usage ## Training hyperparameters lora_config.yaml	[ "# Model\n\nThis model is fine-tuned based on Meta-Llama/Meta-Llama-3-8B instructions via mlx-lm.\n\nNote: The glaive-function-calling-v2 dataset contains some invalid JSON and single quotes for the arguments' values. I have re-trained the model based on cleaned-up data. If you encounter issues with the function calling JSON format, you may try this new version here: URL", "## Usage", "## Training hyperparameters\nlora_config.yaml" ]	[ "TAGS\n#transformers #safetensors #llama #text-generation #conversational #en #dataset-mzbac/glaive-function-calling-v2-llama-3-format #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model\n\nThis model is fine-tuned based on Meta-Llama/Meta-Llama-3-8B instructions via mlx-lm.\n\nNote: The glaive-function-calling-v2 dataset contains some invalid JSON and single quotes for the arguments' values. I have re-trained the model based on cleaned-up data. If you encounter issues with the function calling JSON format, you may try this new version here: URL", "## Usage", "## Training hyperparameters\nlora_config.yaml" ]
text2text-generation	transformers	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # CS505_COQE_viT5_train_Instruction0_PASOL_v1 This model is a fine-tuned version of [VietAI/vit5-large](https://huggingface.co/VietAI/vit5-large) on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 20 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.15.2	{"license": "mit", "tags": ["generated_from_trainer"], "base_model": "VietAI/vit5-large", "model-index": [{"name": "CS505_COQE_viT5_train_Instruction0_PASOL_v1", "results": []}]}	ThuyNT/CS505_COQE_viT5_train_Instruction0_PASOL_v1	null	[ "transformers", "tensorboard", "safetensors", "t5", "text2text-generation", "generated_from_trainer", "base_model:VietAI/vit5-large", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-27T00:59:33+00:00	[]	[]	TAGS #transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-VietAI/vit5-large #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us	# CS505_COQE_viT5_train_Instruction0_PASOL_v1 This model is a fine-tuned version of VietAI/vit5-large on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 20 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.15.2	[ "# CS505_COQE_viT5_train_Instruction0_PASOL_v1\n\nThis model is a fine-tuned version of VietAI/vit5-large on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 20\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]	[ "TAGS\n#transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-VietAI/vit5-large #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# CS505_COQE_viT5_train_Instruction0_PASOL_v1\n\nThis model is a fine-tuned version of VietAI/vit5-large on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 20\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]
text2text-generation	transformers	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # CS505_COQE_viT5_train_Instruction0_APSOL_v1 This model is a fine-tuned version of [VietAI/vit5-large](https://huggingface.co/VietAI/vit5-large) on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 20 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.15.2	{"license": "mit", "tags": ["generated_from_trainer"], "base_model": "VietAI/vit5-large", "model-index": [{"name": "CS505_COQE_viT5_train_Instruction0_APSOL_v1", "results": []}]}	ThuyNT/CS505_COQE_viT5_train_Instruction0_APSOL_v1	null	[ "transformers", "tensorboard", "safetensors", "t5", "text2text-generation", "generated_from_trainer", "base_model:VietAI/vit5-large", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-27T01:00:26+00:00	[]	[]	TAGS #transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-VietAI/vit5-large #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us	# CS505_COQE_viT5_train_Instruction0_APSOL_v1 This model is a fine-tuned version of VietAI/vit5-large on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 20 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.15.2	[ "# CS505_COQE_viT5_train_Instruction0_APSOL_v1\n\nThis model is a fine-tuned version of VietAI/vit5-large on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 20\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]	[ "TAGS\n#transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-VietAI/vit5-large #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# CS505_COQE_viT5_train_Instruction0_APSOL_v1\n\nThis model is a fine-tuned version of VietAI/vit5-large on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 20\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]
null	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	leminhnhat/bug-impact-level-falcon-7b	null	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-04-27T01:00:32+00:00	[ "1910.09700" ]	[]	TAGS #transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us	# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact	[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]	[ "TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]
text-generation	transformers	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # 0.001_4iters_bs128_nodpo_only4w_userresponse_iter_4 This model is a fine-tuned version of [ShenaoZhang/0.001_4iters_bs128_nodpo_only4w_userresponse_iter_3](https://huggingface.co/ShenaoZhang/0.001_4iters_bs128_nodpo_only4w_userresponse_iter_3) on the updated and the original datasets. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-07 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - distributed_type: multi-GPU - num_devices: 8 - gradient_accumulation_steps: 2 - total_train_batch_size: 128 - total_eval_batch_size: 64 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 1 ### Training results ### Framework versions - Transformers 4.40.0 - Pytorch 2.1.2+cu121 - Datasets 2.14.6 - Tokenizers 0.19.1	{"license": "mit", "tags": ["alignment-handbook", "trl", "dpo", "generated_from_trainer", "trl", "dpo", "generated_from_trainer"], "datasets": ["updated", "original"], "base_model": "ShenaoZhang/0.001_4iters_bs128_nodpo_only4w_userresponse_iter_3", "model-index": [{"name": "0.001_4iters_bs128_nodpo_only4w_userresponse_iter_4", "results": []}]}	ShenaoZhang/0.001_4iters_bs128_nodpo_only4w_userresponse_iter_4	null	[ "transformers", "safetensors", "mistral", "text-generation", "alignment-handbook", "trl", "dpo", "generated_from_trainer", "conversational", "dataset:updated", "dataset:original", "base_model:ShenaoZhang/0.001_4iters_bs128_nodpo_only4w_userresponse_iter_3", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-27T01:01:16+00:00	[]	[]	TAGS #transformers #safetensors #mistral #text-generation #alignment-handbook #trl #dpo #generated_from_trainer #conversational #dataset-updated #dataset-original #base_model-ShenaoZhang/0.001_4iters_bs128_nodpo_only4w_userresponse_iter_3 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us	# 0.001_4iters_bs128_nodpo_only4w_userresponse_iter_4 This model is a fine-tuned version of ShenaoZhang/0.001_4iters_bs128_nodpo_only4w_userresponse_iter_3 on the updated and the original datasets. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-07 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - distributed_type: multi-GPU - num_devices: 8 - gradient_accumulation_steps: 2 - total_train_batch_size: 128 - total_eval_batch_size: 64 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 1 ### Training results ### Framework versions - Transformers 4.40.0 - Pytorch 2.1.2+cu121 - Datasets 2.14.6 - Tokenizers 0.19.1	[ "# 0.001_4iters_bs128_nodpo_only4w_userresponse_iter_4\n\nThis model is a fine-tuned version of ShenaoZhang/0.001_4iters_bs128_nodpo_only4w_userresponse_iter_3 on the updated and the original datasets.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 128\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.19.1" ]	[ "TAGS\n#transformers #safetensors #mistral #text-generation #alignment-handbook #trl #dpo #generated_from_trainer #conversational #dataset-updated #dataset-original #base_model-ShenaoZhang/0.001_4iters_bs128_nodpo_only4w_userresponse_iter_3 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# 0.001_4iters_bs128_nodpo_only4w_userresponse_iter_4\n\nThis model is a fine-tuned version of ShenaoZhang/0.001_4iters_bs128_nodpo_only4w_userresponse_iter_3 on the updated and the original datasets.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 128\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.19.1" ]
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_tf_4-seqsight_4096_512_46M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_tf_4](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_4) dataset. It achieves the following results on the evaluation set: - Loss: 0.5633 - F1 Score: 0.8590 - Accuracy: 0.859 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.4994 \| 1.34 \| 200 \| 0.4682 \| 0.7780 \| 0.778 \| \| 0.4392 \| 2.68 \| 400 \| 0.4531 \| 0.7976 \| 0.798 \| \| 0.4164 \| 4.03 \| 600 \| 0.4410 \| 0.7987 \| 0.799 \| \| 0.4047 \| 5.37 \| 800 \| 0.4483 \| 0.7984 \| 0.799 \| \| 0.3858 \| 6.71 \| 1000 \| 0.4345 \| 0.8053 \| 0.806 \| \| 0.3737 \| 8.05 \| 1200 \| 0.4310 \| 0.8200 \| 0.82 \| \| 0.3573 \| 9.4 \| 1400 \| 0.4410 \| 0.8099 \| 0.81 \| \| 0.3463 \| 10.74 \| 1600 \| 0.4223 \| 0.8069 \| 0.807 \| \| 0.3289 \| 12.08 \| 1800 \| 0.4386 \| 0.8066 \| 0.807 \| \| 0.3161 \| 13.42 \| 2000 \| 0.4191 \| 0.8126 \| 0.813 \| \| 0.2995 \| 14.77 \| 2200 \| 0.4017 \| 0.8209 \| 0.821 \| \| 0.2898 \| 16.11 \| 2400 \| 0.4091 \| 0.8309 \| 0.831 \| \| 0.2732 \| 17.45 \| 2600 \| 0.4053 \| 0.8340 \| 0.834 \| \| 0.2635 \| 18.79 \| 2800 \| 0.4117 \| 0.8310 \| 0.831 \| \| 0.2499 \| 20.13 \| 3000 \| 0.3964 \| 0.8510 \| 0.851 \| \| 0.2425 \| 21.48 \| 3200 \| 0.4229 \| 0.8436 \| 0.844 \| \| 0.2274 \| 22.82 \| 3400 \| 0.4003 \| 0.8509 \| 0.851 \| \| 0.2198 \| 24.16 \| 3600 \| 0.4151 \| 0.8530 \| 0.853 \| \| 0.2084 \| 25.5 \| 3800 \| 0.4365 \| 0.8488 \| 0.849 \| \| 0.2023 \| 26.85 \| 4000 \| 0.4383 \| 0.8464 \| 0.847 \| \| 0.1914 \| 28.19 \| 4200 \| 0.4295 \| 0.8590 \| 0.859 \| \| 0.1869 \| 29.53 \| 4400 \| 0.4562 \| 0.8647 \| 0.865 \| \| 0.182 \| 30.87 \| 4600 \| 0.4308 \| 0.8560 \| 0.856 \| \| 0.1731 \| 32.21 \| 4800 \| 0.4319 \| 0.8680 \| 0.868 \| \| 0.1691 \| 33.56 \| 5000 \| 0.4492 \| 0.8659 \| 0.866 \| \| 0.1658 \| 34.9 \| 5200 \| 0.4321 \| 0.8640 \| 0.864 \| \| 0.1495 \| 36.24 \| 5400 \| 0.4748 \| 0.8544 \| 0.855 \| \| 0.1496 \| 37.58 \| 5600 \| 0.4670 \| 0.8709 \| 0.871 \| \| 0.1468 \| 38.93 \| 5800 \| 0.4527 \| 0.8709 \| 0.871 \| \| 0.1377 \| 40.27 \| 6000 \| 0.4790 \| 0.8747 \| 0.875 \| \| 0.1372 \| 41.61 \| 6200 \| 0.4706 \| 0.8749 \| 0.875 \| \| 0.1304 \| 42.95 \| 6400 \| 0.4814 \| 0.8758 \| 0.876 \| \| 0.1323 \| 44.3 \| 6600 \| 0.4978 \| 0.8678 \| 0.868 \| \| 0.1271 \| 45.64 \| 6800 \| 0.4728 \| 0.8759 \| 0.876 \| \| 0.1229 \| 46.98 \| 7000 \| 0.5029 \| 0.8748 \| 0.875 \| \| 0.1169 \| 48.32 \| 7200 \| 0.5104 \| 0.8798 \| 0.88 \| \| 0.1194 \| 49.66 \| 7400 \| 0.5029 \| 0.8728 \| 0.873 \| \| 0.1135 \| 51.01 \| 7600 \| 0.4992 \| 0.8809 \| 0.881 \| \| 0.1065 \| 52.35 \| 7800 \| 0.5255 \| 0.8737 \| 0.874 \| \| 0.109 \| 53.69 \| 8000 \| 0.5078 \| 0.8789 \| 0.879 \| \| 0.1066 \| 55.03 \| 8200 \| 0.4901 \| 0.8830 \| 0.883 \| \| 0.1047 \| 56.38 \| 8400 \| 0.5498 \| 0.8707 \| 0.871 \| \| 0.105 \| 57.72 \| 8600 \| 0.5313 \| 0.8737 \| 0.874 \| \| 0.1023 \| 59.06 \| 8800 \| 0.5276 \| 0.8738 \| 0.874 \| \| 0.1058 \| 60.4 \| 9000 \| 0.5221 \| 0.8718 \| 0.872 \| \| 0.0966 \| 61.74 \| 9200 \| 0.5393 \| 0.8707 \| 0.871 \| \| 0.0987 \| 63.09 \| 9400 \| 0.5360 \| 0.8728 \| 0.873 \| \| 0.0956 \| 64.43 \| 9600 \| 0.5407 \| 0.8737 \| 0.874 \| \| 0.0902 \| 65.77 \| 9800 \| 0.5391 \| 0.8738 \| 0.874 \| \| 0.0944 \| 67.11 \| 10000 \| 0.5416 \| 0.8748 \| 0.875 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_tf_4-seqsight_4096_512_46M-L32_f", "results": []}]}	mahdibaghbanzadeh/GUE_tf_4-seqsight_4096_512_46M-L32_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_46M", "region:us" ]	null	2024-04-27T01:02:22+00:00	[]	[]	TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us	GUE\_tf\_4-seqsight\_4096\_512\_46M-L32\_f ========================================== This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_4096\_512\_46M on the mahdibaghbanzadeh/GUE\_tf\_4 dataset. It achieves the following results on the evaluation set: * Loss: 0.5633 * F1 Score: 0.8590 * Accuracy: 0.859 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]	[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_tf_3-seqsight_4096_512_46M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_tf_3](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_3) dataset. It achieves the following results on the evaluation set: - Loss: 0.5315 - F1 Score: 0.7102 - Accuracy: 0.714 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.6226 \| 0.93 \| 200 \| 0.5869 \| 0.6793 \| 0.68 \| \| 0.5993 \| 1.87 \| 400 \| 0.5752 \| 0.692 \| 0.692 \| \| 0.591 \| 2.8 \| 600 \| 0.5625 \| 0.6920 \| 0.693 \| \| 0.5831 \| 3.74 \| 800 \| 0.5563 \| 0.6959 \| 0.696 \| \| 0.577 \| 4.67 \| 1000 \| 0.5522 \| 0.6977 \| 0.698 \| \| 0.574 \| 5.61 \| 1200 \| 0.5500 \| 0.7049 \| 0.705 \| \| 0.5676 \| 6.54 \| 1400 \| 0.5458 \| 0.7045 \| 0.705 \| \| 0.5636 \| 7.48 \| 1600 \| 0.5450 \| 0.7120 \| 0.712 \| \| 0.5573 \| 8.41 \| 1800 \| 0.5424 \| 0.7060 \| 0.706 \| \| 0.5589 \| 9.35 \| 2000 \| 0.5400 \| 0.7207 \| 0.721 \| \| 0.5506 \| 10.28 \| 2200 \| 0.5428 \| 0.7069 \| 0.707 \| \| 0.5493 \| 11.21 \| 2400 \| 0.5354 \| 0.7245 \| 0.725 \| \| 0.5483 \| 12.15 \| 2600 \| 0.5316 \| 0.7176 \| 0.719 \| \| 0.5444 \| 13.08 \| 2800 \| 0.5328 \| 0.7232 \| 0.725 \| \| 0.5452 \| 14.02 \| 3000 \| 0.5326 \| 0.7201 \| 0.72 \| \| 0.5421 \| 14.95 \| 3200 \| 0.5282 \| 0.7258 \| 0.726 \| \| 0.5399 \| 15.89 \| 3400 \| 0.5276 \| 0.7306 \| 0.731 \| \| 0.5373 \| 16.82 \| 3600 \| 0.5328 \| 0.7191 \| 0.719 \| \| 0.5357 \| 17.76 \| 3800 \| 0.5267 \| 0.7308 \| 0.732 \| \| 0.5358 \| 18.69 \| 4000 \| 0.5293 \| 0.7160 \| 0.716 \| \| 0.536 \| 19.63 \| 4200 \| 0.5270 \| 0.7248 \| 0.726 \| \| 0.5352 \| 20.56 \| 4400 \| 0.5266 \| 0.7281 \| 0.729 \| \| 0.5321 \| 21.5 \| 4600 \| 0.5293 \| 0.7079 \| 0.708 \| \| 0.529 \| 22.43 \| 4800 \| 0.5266 \| 0.7239 \| 0.724 \| \| 0.5304 \| 23.36 \| 5000 \| 0.5281 \| 0.7250 \| 0.725 \| \| 0.5283 \| 24.3 \| 5200 \| 0.5289 \| 0.7099 \| 0.71 \| \| 0.5249 \| 25.23 \| 5400 \| 0.5245 \| 0.7247 \| 0.726 \| \| 0.5307 \| 26.17 \| 5600 \| 0.5234 \| 0.7255 \| 0.726 \| \| 0.522 \| 27.1 \| 5800 \| 0.5223 \| 0.7278 \| 0.729 \| \| 0.5212 \| 28.04 \| 6000 \| 0.5244 \| 0.7169 \| 0.717 \| \| 0.5232 \| 28.97 \| 6200 \| 0.5285 \| 0.7181 \| 0.718 \| \| 0.5234 \| 29.91 \| 6400 \| 0.5250 \| 0.7268 \| 0.727 \| \| 0.522 \| 30.84 \| 6600 \| 0.5201 \| 0.7236 \| 0.724 \| \| 0.5196 \| 31.78 \| 6800 \| 0.5209 \| 0.7269 \| 0.727 \| \| 0.5165 \| 32.71 \| 7000 \| 0.5219 \| 0.7266 \| 0.727 \| \| 0.523 \| 33.64 \| 7200 \| 0.5196 \| 0.7205 \| 0.721 \| \| 0.5156 \| 34.58 \| 7400 \| 0.5252 \| 0.7210 \| 0.721 \| \| 0.518 \| 35.51 \| 7600 \| 0.5207 \| 0.7210 \| 0.721 \| \| 0.5168 \| 36.45 \| 7800 \| 0.5248 \| 0.7190 \| 0.719 \| \| 0.5147 \| 37.38 \| 8000 \| 0.5231 \| 0.7221 \| 0.722 \| \| 0.5117 \| 38.32 \| 8200 \| 0.5204 \| 0.7262 \| 0.727 \| \| 0.5136 \| 39.25 \| 8400 \| 0.5201 \| 0.7226 \| 0.723 \| \| 0.5128 \| 40.19 \| 8600 \| 0.5218 \| 0.7220 \| 0.722 \| \| 0.5125 \| 41.12 \| 8800 \| 0.5211 \| 0.7228 \| 0.723 \| \| 0.5149 \| 42.06 \| 9000 \| 0.5206 \| 0.7239 \| 0.724 \| \| 0.5136 \| 42.99 \| 9200 \| 0.5205 \| 0.7230 \| 0.723 \| \| 0.5104 \| 43.93 \| 9400 \| 0.5213 \| 0.7191 \| 0.719 \| \| 0.511 \| 44.86 \| 9600 \| 0.5198 \| 0.7258 \| 0.726 \| \| 0.5117 \| 45.79 \| 9800 \| 0.5206 \| 0.7299 \| 0.73 \| \| 0.5078 \| 46.73 \| 10000 \| 0.5208 \| 0.7269 \| 0.727 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_tf_3-seqsight_4096_512_46M-L1_f", "results": []}]}	mahdibaghbanzadeh/GUE_tf_3-seqsight_4096_512_46M-L1_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_46M", "region:us" ]	null	2024-04-27T01:02:54+00:00	[]	[]	TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us	GUE\_tf\_3-seqsight\_4096\_512\_46M-L1\_f ========================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_4096\_512\_46M on the mahdibaghbanzadeh/GUE\_tf\_3 dataset. It achieves the following results on the evaluation set: * Loss: 0.5315 * F1 Score: 0.7102 * Accuracy: 0.714 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]	[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]
text-generation	transformers	# Model Card for johnsnowlabs/JSL-MedLlama-3-70B-v2.0 [<img src="https://repository-images.githubusercontent.com/104670986/2e728700-ace4-11ea-9cfc-f3e060b25ddf">](http://www.johnsnowlabs.com) This model is developed by [John Snow Labs](https://www.johnsnowlabs.com/). This model is trained on medical datasets to provide state-of-the-art performance on biomedical benchmarks: [Open Medical LLM Leaderboard](https://huggingface.co/spaces/openlifescienceai/open_medical_llm_leaderboard). This model is available under a [CC-BY-NC-ND](https://creativecommons.org/licenses/by-nc-nd/4.0/deed.en) license and must also conform to this [Acceptable Use Policy](https://huggingface.co/johnsnowlabs). If you need to license this model for commercial use, please contact us at [email protected]. ## 💻 Usage ```python !pip install -qU transformers accelerate from transformers import AutoTokenizer import transformers import torch model = "johnsnowlabs/JSL-MedLlama-3-70B-v2.0" messages = [{"role": "user", "content": "What is a large language model?"}] tokenizer = AutoTokenizer.from_pretrained(model) prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) pipeline = transformers.pipeline( "text-generation", model=model, torch_dtype=torch.float16, device_map="auto", ) outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95) print(outputs[0]["generated_text"]) ``` ## 🏆 Evaluation \| Tasks \|Version\|Filter\|n-shot\| Metric \|Value \| \|Stderr\| \|-------------------------------\|-------\|------\|-----:\|--------\|-----:\|---\|-----:\| \|stem \|N/A \|none \| 0\|acc \|0.7773\|± \|0.0049\| \| \| \|none \| 0\|acc_norm\|0.7505\|± \|0.0059\| \| - medmcqa \|Yaml \|none \| 0\|acc \|0.7413\|± \|0.0068\| \| \| \|none \| 0\|acc_norm\|0.7413\|± \|0.0068\| \| - medqa_4options \|Yaml \|none \| 0\|acc \|0.7808\|± \|0.0116\| \| \| \|none \| 0\|acc_norm\|0.7808\|± \|0.0116\| \| - anatomy (mmlu) \| 0\|none \| 0\|acc \|0.8444\|± \|0.0313\| \| - clinical_knowledge (mmlu) \| 0\|none \| 0\|acc \|0.9245\|± \|0.0163\| \| - college_biology (mmlu) \| 0\|none \| 0\|acc \|0.9375\|± \|0.0202\| \| - college_medicine (mmlu) \| 0\|none \| 0\|acc \|0.8555\|± \|0.0268\| \| - medical_genetics (mmlu) \| 0\|none \| 0\|acc \|0.9300\|± \|0.0256\| \| - professional_medicine (mmlu)\| 0\|none \| 0\|acc \|0.9375\|± \|0.0147\| \| - pubmedqa \| 1\|none \| 0\|acc \|0.7820\|± \|0.0185\| \|Groups\|Version\|Filter\|n-shot\| Metric \|Value \| \|Stderr\| \|------\|-------\|------\|-----:\|--------\|-----:\|---\|-----:\| \|stem \|N/A \|none \| 0\|acc \|0.7773\|± \|0.0049\| \| \| \|none \| 0\|acc_norm\|0.7505\|± \|0.0059\|	{"language": ["en"], "license": "apache-2.0", "library_name": "transformers", "tags": ["medical"]}	johnsnowlabs/JSL-MedLlama-3-70B-v2.0	null	[ "transformers", "safetensors", "llama", "text-generation", "medical", "conversational", "en", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-27T01:04:43+00:00	[]	[ "en" ]	TAGS #transformers #safetensors #llama #text-generation #medical #conversational #en #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us	Model Card for johnsnowlabs/JSL-MedLlama-3-70B-v2.0 =================================================== <img src="URL This model is developed by John Snow Labs. This model is trained on medical datasets to provide state-of-the-art performance on biomedical benchmarks: Open Medical LLM Leaderboard. This model is available under a CC-BY-NC-ND license and must also conform to this Acceptable Use Policy. If you need to license this model for commercial use, please contact us at info@URL. Usage ----- Evaluation ----------	[]	[ "TAGS\n#transformers #safetensors #llama #text-generation #medical #conversational #en #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n" ]
null	null	# MeliodasExperiment26-7B MeliodasExperiment26-7B is an automated merge created by [Maxime Labonne](https://huggingface.co/mlabonne) using the following configuration. ## 🧩 Configuration ```yaml models: - model: mistralai/Mistral-7B-v0.1 - model: AurelPx/Meliodas-7b-dare - model: yam-peleg/Experiment26-7B merge_method: model_stock base_model: mistralai/Mistral-7B-v0.1 dtype: bfloat16 ``` ## 💻 Usage ```python !pip install -qU transformers accelerate from transformers import AutoTokenizer import transformers import torch model = "automerger/MeliodasExperiment26-7B" messages = [{"role": "user", "content": "What is a large language model?"}] tokenizer = AutoTokenizer.from_pretrained(model) prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) pipeline = transformers.pipeline( "text-generation", model=model, torch_dtype=torch.float16, device_map="auto", ) outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95) print(outputs[0]["generated_text"]) ```	{"license": "apache-2.0", "tags": ["merge", "mergekit", "lazymergekit", "automerger"]}	automerger/MeliodasExperiment26-7B	null	[ "merge", "mergekit", "lazymergekit", "automerger", "license:apache-2.0", "region:us" ]	null	2024-04-27T01:08:31+00:00	[]	[]	TAGS #merge #mergekit #lazymergekit #automerger #license-apache-2.0 #region-us	# MeliodasExperiment26-7B MeliodasExperiment26-7B is an automated merge created by Maxime Labonne using the following configuration. ## Configuration ## Usage	[ "# MeliodasExperiment26-7B\n\nMeliodasExperiment26-7B is an automated merge created by Maxime Labonne using the following configuration.", "## Configuration", "## Usage" ]	[ "TAGS\n#merge #mergekit #lazymergekit #automerger #license-apache-2.0 #region-us \n", "# MeliodasExperiment26-7B\n\nMeliodasExperiment26-7B is an automated merge created by Maxime Labonne using the following configuration.", "## Configuration", "## Usage" ]
text-generation	transformers	<div align="center"> <img width="260px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/BrQCb95lmEIFz79QAmoNA.png"></div> ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/fJIOPJnY6Ff6fUiSIuMEt.png) <div align="center"> <h1>Advancing Open-source Large Language Models in Medical Domain</h1> </div> <p align="center" style="margin-top: 0px;"> <a href="https://colab.research.google.com/drive/1F5oV20InEYeAJGmBwYF9NM_QhLmjBkKJ?usp=sharing"> <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="OpenChat Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 10px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style=" margin-right: 5px;">Online Demo</span> </a> \| <a href="https://github.com/openlifescience-ai"> <img src="https://github.githubassets.com/assets/GitHub-Mark-ea2971cee799.png" alt="GitHub Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style=" margin-right: 5px;">GitHub</span> </a> \| <a href="#"> <img src="https://github.com/alpayariyak/openchat/blob/master/assets/arxiv-logomark-small-square-border.png?raw=true" alt="ArXiv Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style="margin-right: 5px;">Paper</span> </a> \| <a href="https://discord.gg/A5Fjf5zC69"> <img src="https://cloud.githubusercontent.com/assets/6291467/26705903/96c2d66e-477c-11e7-9f4e-f3c0efe96c9a.png" alt="Discord Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text">Discord</span> </a> </p> ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/KGmRE5w2sepNtwsEu8t7K.jpeg) Introducing OpenBioLLM-70B: A State-of-the-Art Open Source Biomedical Large Language Model OpenBioLLM-70B is an advanced open source language model designed specifically for the biomedical domain. Developed by Saama AI Labs, this model leverages cutting-edge techniques to achieve state-of-the-art performance on a wide range of biomedical tasks. 🏥 Biomedical Specialization: OpenBioLLM-70B is tailored for the unique language and knowledge requirements of the medical and life sciences fields. It was fine-tuned on a vast corpus of high-quality biomedical data, enabling it to understand and generate text with domain-specific accuracy and fluency. 🎓 Superior Performance: With 70 billion parameters, OpenBioLLM-70B outperforms other open source biomedical language models of similar scale. It has also demonstrated better results compared to larger proprietary & open-source models like GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 on biomedical benchmarks. 🧠 Advanced Training Techniques: OpenBioLLM-70B builds upon the powerful foundations of the Meta-Llama-3-70B-Instruct and [Meta-Llama-3-70B-Instruct](meta-llama/Meta-Llama-3-70B-Instruct) models. It incorporates the DPO dataset and fine-tuning recipe along with a custom diverse medical instruction dataset. Key components of the training pipeline include: <div align="center"> <img width="1200px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/oPchsJsEpQoGcGXVbh7YS.png"> </div> - Policy Optimization: [Direct Preference Optimization: Your Language Model is Secretly a Reward Model (DPO)](https://arxiv.org/abs/2305.18290) - Fine-tuning dataset: Custom Medical Instruct dataset (We plan to release a sample training dataset in our upcoming paper; please stay updated) This combination of cutting-edge techniques enables OpenBioLLM-70B to align with key capabilities and preferences for biomedical applications. ⚙️ Release Details: - Model Size: 70 billion parameters - Quantization: Optimized quantized versions available [Here](https://huggingface.co/aaditya/OpenBioLLM-70B-GGUF) - Language(s) (NLP): en - Developed By: [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) from Saama AI Labs - License: Meta-Llama License - Fine-tuned from models: [Meta-Llama-3-70B-Instruct](meta-llama/Meta-Llama-3-70B-Instruct) - Resources for more information: - Paper: Coming soon The model can be fine-tuned for more specialized tasks and datasets as needed. OpenBioLLM-70B represents an important step forward in democratizing advanced language AI for the biomedical community. By leveraging state-of-the-art architectures and training techniques from leading open source efforts like Llama-3, we have created a powerful tool to accelerate innovation and discovery in healthcare and the life sciences. We are excited to share OpenBioLLM-70B with researchers and developers around the world. ### Use with transformers Important: Please use the exact chat template provided by Llama-3 instruct version. Otherwise there will be a degradation in the performance. The model output can be verbose in rare cases. Please consider setting temperature = 0 to make this happen less. See the snippet below for usage with Transformers: ```python import transformers import torch model_id = "aaditya/OpenBioLLM-Llama3-70B" pipeline = transformers.pipeline( "text-generation", model=model_id, model_kwargs={"torch_dtype": torch.bfloat16}, device="auto", ) messages = [ {"role": "system", "content": "You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience. Your name is OpenBioLLM, and you were developed by Saama AI Labs. who's willing to help answer the user's query with explanation. In your explanation, leverage your deep medical expertise such as relevant anatomical structures, physiological processes, diagnostic criteria, treatment guidelines, or other pertinent medical concepts. Use precise medical terminology while still aiming to make the explanation clear and accessible to a general audience."}, {"role": "user", "content": "How can i split a 3mg or 4mg waefin pill so i can get a 2.5mg pill?"}, ] prompt = pipeline.tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) terminators = [ pipeline.tokenizer.eos_token_id, pipeline.tokenizer.convert_tokens_to_ids("<\|eot_id\|>") ] outputs = pipeline( prompt, max_new_tokens=256, eos_token_id=terminators, do_sample=True, temperature=0.0, top_p=0.9, ) print(outputs[0]["generated_text"][len(prompt):]) ``` ## Training procedure ### Training hyperparameters <details> <summary>Click to see details</summary> - learning_rate: 0.0002 - lr_scheduler: cosine - train_batch_size: 12 - eval_batch_size: 8 - GPU: H100 80GB SXM5 - num_devices: 8 - optimizer: adamw_bnb_8bit - lr_scheduler_warmup_steps: 100 - num_epochs: 4 </details> ### Peft hyperparameters <details> <summary>Click to see details</summary> - adapter: qlora - lora_r: 128 - lora_alpha: 256 - lora_dropout: 0.05 - lora_target_linear: true -lora_target_modules: - q_proj - v_proj - k_proj - o_proj - gate_proj - down_proj - up_proj </details> ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2+cu121 - Datasets 2.18.0 - Tokenizers 0.15.1 - Axolotl - Lm harness for evaluation # Benchmark Results 🔥 OpenBioLLM-70B demonstrates superior performance compared to larger models, such as GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 across 9 diverse biomedical datasets, achieving state-of-the-art results with an average score of 86.06%, despite having a significantly smaller parameter count. The model's strong performance in domain-specific tasks, such as Clinical KG, Medical Genetics, and PubMedQA, highlights its ability to effectively capture and apply biomedical knowledge. 🚨 The GPT-4, Med-PaLM-1, and Med-PaLM-2 results are taken from their official papers. Since Med-PaLM doesn't provide zero-shot accuracy, we are using 5-shot accuracy from their paper for comparison. All results presented are in the zero-shot setting, except for Med-PaLM-2 and Med-PaLM-1, which use 5-shot accuracy. \| \| Clinical KG \| Medical Genetics \| Anatomy \| Pro Medicine \| College Biology \| College Medicine \| MedQA 4 opts \| PubMedQA \| MedMCQA \| Avg \| \|--------------------\|-------------\|------------------\|---------\|--------------\|-----------------\|------------------\|--------------\|----------\|---------\|-------\| \| OpenBioLLM-70B \| 92.93 \| 93.197 \| 83.904 \| 93.75 \| 93.827 \| 85.749 \| 78.162 \| 78.97 \| 74.014 \| 86.05588 \| \| Med-PaLM-2 (5-shot) \| 88.3 \| 90 \| 77.8 \| 95.2 \| 94.4 \| 80.9 \| 79.7 \| 79.2 \| 71.3 \| 84.08 \| \| GPT-4 \| 86.04 \| 91 \| 80 \| 93.01 \| 95.14 \| 76.88 \| 78.87 \| 75.2 \| 69.52 \| 82.85 \| \| Med-PaLM-1 (Flan-PaLM, 5-shot) \| 80.4 \| 75 \| 63.7 \| 83.8 \| 88.9 \| 76.3 \| 67.6 \| 79 \| 57.6 \| 74.7 \| \| OpenBioLLM-8B \| 76.101 \| 86.1 \| 69.829 \| 78.21 \| 84.213 \| 68.042 \| 58.993 \| 74.12 \| 56.913 \| 72.502 \| \| Gemini-1.0 \| 76.7 \| 75.8 \| 66.7 \| 77.7 \| 88 \| 69.2 \| 58 \| 70.7 \| 54.3 \| 70.79 \| \| GPT-3.5 Turbo 1106 \| 74.71 \| 74 \| 72.79 \| 72.79 \| 72.91 \| 64.73 \| 57.71 \| 72.66 \| 53.79 \| 66 \| \| Meditron-70B \| 66.79 \| 69 \| 53.33 \| 71.69 \| 76.38 \| 63 \| 57.1 \| 76.6 \| 46.85 \| 64.52 \| \| gemma-7b \| 69.81 \| 70 \| 59.26 \| 66.18 \| 79.86 \| 60.12 \| 47.21 \| 76.2 \| 48.96 \| 64.18 \| \| Mistral-7B-v0.1 \| 68.68 \| 71 \| 55.56 \| 68.38 \| 68.06 \| 59.54 \| 50.82 \| 75.4 \| 48.2 \| 62.85 \| \| Apollo-7B \| 62.26 \| 72 \| 61.48 \| 69.12 \| 70.83 \| 55.49 \| 55.22 \| 39.8 \| 53.77 \| 60 \| \| MedAlpaca-7b \| 57.36 \| 69 \| 57.04 \| 67.28 \| 65.28 \| 54.34 \| 41.71 \| 72.8 \| 37.51 \| 58.03 \| \| BioMistral-7B \| 59.9 \| 64 \| 56.5 \| 60.4 \| 59 \| 54.7 \| 50.6 \| 77.5 \| 48.1 \| 57.3 \| \| AlpaCare-llama2-7b \| 49.81 \| 49 \| 45.92 \| 33.82 \| 50 \| 43.35 \| 29.77 \| 72.2 \| 34.42 \| 45.36 \| \| ClinicalGPT \| 30.56 \| 27 \| 30.37 \| 19.48 \| 25 \| 24.27 \| 26.08 \| 63.8 \| 28.18 \| 30.52 \| <div align="center"> <img width="1600px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/_SzdcJSBjZyo8RS1bTEkP.png"> </div> ## Detailed Medical Subjectwise accuracy ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/UXF-V0col0Z0sS6BGPBkE.png) # Use Cases & Examples 🚨 Below results are from the quantized version of OpenBioLLM-70B # Summarize Clinical Notes OpenBioLLM-70B can efficiently analyze and summarize complex clinical notes, EHR data, and discharge summaries, extracting key information and generating concise, structured summaries ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/xdwdBgOxNi_TfML0hKlI8.png) # Answer Medical Questions OpenBioLLM-70B can provide answers to a wide range of medical questions. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/zO95GlwOQEZqCKQF69mE6.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/OKBczKw7gWeW5xsuDpc27.png) <details> <summary>Click to see details</summary> ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/eJGHT5khppYvJb8fQ-YW4.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/Cnbwrqa_-ORHRuNRC2P6Y.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/J9DhdcvukAc9mnnW9fj2C.png) </details> # Clinical Entity Recognition OpenBioLLM-70B can perform advanced clinical entity recognition by identifying and extracting key medical concepts, such as diseases, symptoms, medications, procedures, and anatomical structures, from unstructured clinical text. By leveraging its deep understanding of medical terminology and context, the model can accurately annotate and categorize clinical entities, enabling more efficient information retrieval, data analysis, and knowledge discovery from electronic health records, research articles, and other biomedical text sources. This capability can support various downstream applications, such as clinical decision support, pharmacovigilance, and medical research. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/_69BW4k9LVABFwtxixL45.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/DKy5wYCoPhoPPUc1-x8_J.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/7WD9zCCBZT4-4XlfnIQjl.png) # Biomarkers Extraction ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/ZttoM4AiteT7gFYVhjIpN.png) # Classification OpenBioLLM-70B can perform various biomedical classification tasks, such as disease prediction, sentiment analysis, medical document categorization ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/Bf5MW1d75qT-1F_TR_hC0.png) # De-Identification OpenBioLLM-70B can detect and remove personally identifiable information (PII) from medical records, ensuring patient privacy and compliance with data protection regulations like HIPAA. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/hKX4kzm--Tw5bj6K78msy.png) Advisory Notice! While OpenBioLLM-70B leverages high-quality data sources, its outputs may still contain inaccuracies, biases, or misalignments that could pose risks if relied upon for medical decision-making without further testing and refinement. The model's performance has not yet been rigorously evaluated in randomized controlled trials or real-world healthcare environments. Therefore, we strongly advise against using OpenBioLLM-70B for any direct patient care, clinical decision support, or other professional medical purposes at this time. Its use should be limited to research, development, and exploratory applications by qualified individuals who understand its limitations. OpenBioLLM-70B is intended solely as a research tool to assist healthcare professionals and should never be considered a replacement for the professional judgment and expertise of a qualified medical doctor. Appropriately adapting and validating OpenBioLLM-70B for specific medical use cases would require significant additional work, potentially including: - Thorough testing and evaluation in relevant clinical scenarios - Alignment with evidence-based guidelines and best practices - Mitigation of potential biases and failure modes - Integration with human oversight and interpretation - Compliance with regulatory and ethical standards Always consult a qualified healthcare provider for personal medical needs. # Citation If you find OpenBioLLM-70B & 8B useful in your work, please cite the model as follows: ``` @misc{OpenBioLLMs, author = {Ankit Pal, Malaikannan Sankarasubbu}, title = {OpenBioLLMs: Advancing Open-Source Large Language Models for Healthcare and Life Sciences}, year = {2024}, publisher = {Hugging Face}, journal = {Hugging Face repository}, howpublished = {\url{https://huggingface.co/aaditya/OpenBioLLM-Llama3-70B}} } ``` The accompanying paper is currently in progress and will be released soon. <div align="center"> <h2> 💌 Contact </h2> </div> We look forward to hearing you and collaborating on this exciting project! Contributors:** - [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) [aadityaura at gmail dot com] - Saama AI Labs - Note: I am looking for a funded PhD opportunity, especially if it fits my Responsible Generative AI, Multimodal LLMs, Geometric Deep Learning, and Healthcare AI skillset. # References We thank the [Meta Team](meta-llama/Meta-Llama-3-70B-Instruct) for their amazing models! Result sources - [1] GPT-4 [Capabilities of GPT-4 on Medical Challenge Problems] (https://arxiv.org/abs/2303.13375) - [2] Med-PaLM-1 [Large Language Models Encode Clinical Knowledge](https://arxiv.org/abs/2212.13138) - [3] Med-PaLM-2 [Towards Expert-Level Medical Question Answering with Large Language Models](https://arxiv.org/abs/2305.09617) - [4] Gemini-1.0 [Gemini Goes to Med School](https://arxiv.org/abs/2402.07023)	{"language": ["en"], "license": "llama3", "tags": ["llama-3", "llama", "Mixtral", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "distillation"], "base_model": "meta-llama/Meta-Llama-3-70B-Instruct", "widget": [{"example_title": "OpenBioLLM-70B", "messages": [{"role": "system", "content": "You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience."}, {"role": "user", "content": "How long does it take for newborn jaundice to go away?"}], "output": {"text": "Newborn jaundice, also known as neonatal jaundice, is a common condition in newborns where the yellowing of the skin and eyes occurs due to an elevated level of bilirubin in the blood. Bilirubin is a yellow pigment that forms when red blood cells break down. In most cases, newborn jaundice resolves on its own without any specific treatment.\nThe duration of newborn jaundice can vary depending on several factors such as the underlying cause, gestational age at birth, and individual variations in bilirubin metabolism. Here are some general guidelines:\n1. Physiological jaundice: This is the most common type of newborn jaundice and usually appears within 24-72 hours after birth. It tends to peak between the second and fifth day of life and gradually improves over the next week or two. By the time the baby is one week old, the jaundice should have mostly resolved. 2. Breast milk jaundice: This type of jaundice occurs in breastfed babies and may appear later than physiological jaundice, typically between the fifth and fourteenth day of life. It tends to persist for a longer duration but usually resolves within six weeks after birth. 3. Pathological jaundice: This type of jaundice is less common and occurs due to an underlying medical condition that affects bilirubin metabolism or liver function. The duration of pathological jaundice depends on the specific cause and may require treatment.\nIt's important for parents to monitor their newborn's jaundice closely and seek medical advice if the jaundice progresses rapidly, becomes severe, or is accompanied by other symptoms such as poor feeding, lethargy, or excessive sleepiness. In these cases, further evaluation and management may be necessary. Remember that each baby is unique, and the timing of jaundice resolution can vary. If you have concerns about your newborn's jaundice, it's always best to consult with a healthcare professional for personalized advice and guidance."}}], "model-index": [{"name": "OpenBioLLM-70B", "results": []}]}	LoneStriker/OpenBioLLM-Llama3-70B-2.4bpw-h6-exl2	null	[ "transformers", "pytorch", "llama", "text-generation", "llama-3", "Mixtral", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "distillation", "conversational", "en", "arxiv:2305.18290", "arxiv:2303.13375", "arxiv:2212.13138", "arxiv:2305.09617", "arxiv:2402.07023", "base_model:meta-llama/Meta-Llama-3-70B-Instruct", "license:llama3", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-27T01:08:34+00:00	[ "2305.18290", "2303.13375", "2212.13138", "2305.09617", "2402.07023" ]	[ "en" ]	TAGS #transformers #pytorch #llama #text-generation #llama-3 #Mixtral #instruct #finetune #chatml #DPO #RLHF #gpt4 #distillation #conversational #en #arxiv-2305.18290 #arxiv-2303.13375 #arxiv-2212.13138 #arxiv-2305.09617 #arxiv-2402.07023 #base_model-meta-llama/Meta-Llama-3-70B-Instruct #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us	![](URL <p>!image/png</p> <div align=) Advancing Open-source Large Language Models in Medical Domain ============================================================= Online Demo \| GitHub \| [![](URL alt=)](#) \| Discord !image/jpeg Introducing OpenBioLLM-70B: A State-of-the-Art Open Source Biomedical Large Language Model OpenBioLLM-70B is an advanced open source language model designed specifically for the biomedical domain. Developed by Saama AI Labs, this model leverages cutting-edge techniques to achieve state-of-the-art performance on a wide range of biomedical tasks. Biomedical Specialization: OpenBioLLM-70B is tailored for the unique language and knowledge requirements of the medical and life sciences fields. It was fine-tuned on a vast corpus of high-quality biomedical data, enabling it to understand and generate text with domain-specific accuracy and fluency. Superior Performance: With 70 billion parameters, OpenBioLLM-70B outperforms other open source biomedical language models of similar scale. It has also demonstrated better results compared to larger proprietary & open-source models like GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 on biomedical benchmarks. Advanced Training Techniques: OpenBioLLM-70B builds upon the powerful foundations of the Meta-Llama-3-70B-Instruct and Meta-Llama-3-70B-Instruct models. It incorporates the DPO dataset and fine-tuning recipe along with a custom diverse medical instruction dataset. Key components of the training pipeline include: ![](URL </div> <ul> <li>Policy Optimization: Direct Preference Optimization: Your Language Model is Secretly a Reward Model (DPO)</li> <li>Fine-tuning dataset: Custom Medical Instruct dataset (We plan to release a sample training dataset in our upcoming paper; please stay updated)</li> </ul> <p>This combination of cutting-edge techniques enables OpenBioLLM-70B to align with key capabilities and preferences for biomedical applications.</p> <p>️ Release Details:</p> <ul> <li>Model Size: 70 billion parameters</li> <li>Quantization: Optimized quantized versions available Here</li> <li>Language(s) (NLP): en</li> <li>Developed By: Ankit Pal (Aaditya Ura) from Saama AI Labs</li> <li>License: Meta-Llama License</li> <li>Fine-tuned from models: Meta-Llama-3-70B-Instruct</li> <li>Resources for more information: <ul> <li>Paper: Coming soon</li> </ul> </li> </ul> <p>The model can be fine-tuned for more specialized tasks and datasets as needed.</p> <p>OpenBioLLM-70B represents an important step forward in democratizing advanced language AI for the biomedical community. By leveraging state-of-the-art architectures and training techniques from leading open source efforts like Llama-3, we have created a powerful tool to accelerate innovation and discovery in healthcare and the life sciences.</p> <p>We are excited to share OpenBioLLM-70B with researchers and developers around the world.</p> <h3>Use with transformers</h3> <p>Important: Please use the exact chat template provided by Llama-3 instruct version. Otherwise there will be a degradation in the performance. The model output can be verbose in rare cases. Please consider setting temperature = 0 to make this happen less.</p> <p>See the snippet below for usage with Transformers:</p> <h2>Training procedure</h2> <h3>Training hyperparameters</h3> <details> <summary>Click to see details</summary> <ul> <li>learning_rate: 0.0002</li> <li>lr_scheduler: cosine</li> <li>train_batch_size: 12</li> <li>eval_batch_size: 8</li> <li>GPU: H100 80GB SXM5</li> <li>num_devices: 8</li> <li>optimizer: adamw_bnb_8bit</li> <li>lr_scheduler_warmup_steps: 100</li> <li>num_epochs: 4</li> </ul> </details> <h3>Peft hyperparameters</h3> <details> <summary>Click to see details</summary> <ul> <li>adapter: qlora</li> <li>lora_r: 128</li> <li>lora_alpha: 256</li> <li>lora_dropout: 0.05</li> <li>lora_target_linear: true</li> </ul> <p>-lora_target_modules:</p> <ul> <li>q_proj</li> <li>v_proj</li> <li>k_proj</li> <li>o_proj</li> <li>gate_proj</li> <li>down_proj</li> <li>up_proj</li> </ul> </details> <h3>Training results</h3> <h3>Framework versions</h3> <ul> <li>Transformers 4.39.3</li> <li>Pytorch 2.1.2+cu121</li> <li>Datasets 2.18.0</li> <li>Tokenizers 0.15.1</li> <li>Axolotl</li> <li>Lm harness for evaluation</li> </ul> <h1>Benchmark Results</h1> <p>OpenBioLLM-70B demonstrates superior performance compared to larger models, such as GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 across 9 diverse biomedical datasets, achieving state-of-the-art results with an average score of 86.06%, despite having a significantly smaller parameter count. The model's strong performance in domain-specific tasks, such as Clinical KG, Medical Genetics, and PubMedQA, highlights its ability to effectively capture and apply biomedical knowledge.</p> <p>The GPT-4, Med-PaLM-1, and Med-PaLM-2 results are taken from their official papers. Since Med-PaLM doesn't provide zero-shot accuracy, we are using 5-shot accuracy from their paper for comparison. All results presented are in the zero-shot setting, except for Med-PaLM-2 and Med-PaLM-1, which use 5-shot accuracy.</p> <p></p> <div align=) ![](URL </div> <h2>Detailed Medical Subjectwise accuracy</h2> <p>!image/png</p> <h1>Use Cases & Examples</h1> <p>Below results are from the quantized version of OpenBioLLM-70B</p> <h1>Summarize Clinical Notes</h1> <p>OpenBioLLM-70B can efficiently analyze and summarize complex clinical notes, EHR data, and discharge summaries, extracting key information and generating concise, structured summaries</p> <p>!image/png</p> <h1>Answer Medical Questions</h1> <p>OpenBioLLM-70B can provide answers to a wide range of medical questions.</p> <p>!image/png !image/png</p> <details> <summary>Click to see details</summary> <p>!image/png !image/png !image/png</p> </details> <h1>Clinical Entity Recognition</h1> <p>OpenBioLLM-70B can perform advanced clinical entity recognition by identifying and extracting key medical concepts, such as diseases, symptoms, medications, procedures, and anatomical structures, from unstructured clinical text. By leveraging its deep understanding of medical terminology and context, the model can accurately annotate and categorize clinical entities, enabling more efficient information retrieval, data analysis, and knowledge discovery from electronic health records, research articles, and other biomedical text sources. This capability can support various downstream applications, such as clinical decision support, pharmacovigilance, and medical research.</p> <p>!image/png !image/png !image/png</p> <h1>Biomarkers Extraction</h1> <p>!image/png</p> <h1>Classification</h1> <p>OpenBioLLM-70B can perform various biomedical classification tasks, such as disease prediction, sentiment analysis, medical document categorization</p> <p>!image/png</p> <h1>De-Identification</h1> <p>OpenBioLLM-70B can detect and remove personally identifiable information (PII) from medical records, ensuring patient privacy and compliance with data protection regulations like HIPAA.</p> <p>!image/png</p> <p>Advisory Notice!</p> <p>While OpenBioLLM-70B leverages high-quality data sources, its outputs may still contain inaccuracies, biases, or misalignments that could pose risks if relied upon for medical decision-making without further testing and refinement. The model's performance has not yet been rigorously evaluated in randomized controlled trials or real-world healthcare environments.</p> <p>Therefore, we strongly advise against using OpenBioLLM-70B for any direct patient care, clinical decision support, or other professional medical purposes at this time. Its use should be limited to research, development, and exploratory applications by qualified individuals who understand its limitations. OpenBioLLM-70B is intended solely as a research tool to assist healthcare professionals and should never be considered a replacement for the professional judgment and expertise of a qualified medical doctor.</p> <p>Appropriately adapting and validating OpenBioLLM-70B for specific medical use cases would require significant additional work, potentially including:</p> <ul> <li>Thorough testing and evaluation in relevant clinical scenarios</li> <li>Alignment with evidence-based guidelines and best practices</li> <li>Mitigation of potential biases and failure modes</li> <li>Integration with human oversight and interpretation</li> <li>Compliance with regulatory and ethical standards</li> </ul> <p>Always consult a qualified healthcare provider for personal medical needs.</p> <p>If you find OpenBioLLM-70B & 8B useful in your work, please cite the model as follows:</p> <p>The accompanying paper is currently in progress and will be released soon.</p> <div align=) Contact -------- We look forward to hearing you and collaborating on this exciting project! Contributors: * Ankit Pal (Aaditya Ura) [aadityaura at gmail dot com] * Saama AI Labs * Note: I am looking for a funded PhD opportunity, especially if it fits my Responsible Generative AI, Multimodal LLMs, Geometric Deep Learning, and Healthcare AI skillset. References ========== We thank the Meta Team for their amazing models! Result sources * [1] GPT-4 [Capabilities of GPT-4 on Medical Challenge Problems] (URL * [2] Med-PaLM-1 Large Language Models Encode Clinical Knowledge * [3] Med-PaLM-2 Towards Expert-Level Medical Question Answering with Large Language Models * [4] Gemini-1.0 Gemini Goes to Med School	[]	[ "TAGS\n#transformers #pytorch #llama #text-generation #llama-3 #Mixtral #instruct #finetune #chatml #DPO #RLHF #gpt4 #distillation #conversational #en #arxiv-2305.18290 #arxiv-2303.13375 #arxiv-2212.13138 #arxiv-2305.09617 #arxiv-2402.07023 #base_model-meta-llama/Meta-Llama-3-70B-Instruct #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n" ]
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_tf_3-seqsight_4096_512_46M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_tf_3](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_3) dataset. It achieves the following results on the evaluation set: - Loss: 0.5223 - F1 Score: 0.7373 - Accuracy: 0.739 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.6108 \| 0.93 \| 200 \| 0.5608 \| 0.6923 \| 0.693 \| \| 0.5825 \| 1.87 \| 400 \| 0.5563 \| 0.7069 \| 0.707 \| \| 0.5685 \| 2.8 \| 600 \| 0.5375 \| 0.7158 \| 0.716 \| \| 0.5571 \| 3.74 \| 800 \| 0.5398 \| 0.7010 \| 0.701 \| \| 0.549 \| 4.67 \| 1000 \| 0.5198 \| 0.7276 \| 0.728 \| \| 0.5494 \| 5.61 \| 1200 \| 0.5403 \| 0.7126 \| 0.713 \| \| 0.56 \| 6.54 \| 1400 \| 0.5349 \| 0.7261 \| 0.726 \| \| 0.5408 \| 7.48 \| 1600 \| 0.5267 \| 0.7380 \| 0.739 \| \| 0.5303 \| 8.41 \| 1800 \| 0.5230 \| 0.7210 \| 0.721 \| \| 0.526 \| 9.35 \| 2000 \| 0.5232 \| 0.7299 \| 0.732 \| \| 0.5144 \| 10.28 \| 2200 \| 0.5267 \| 0.7450 \| 0.745 \| \| 0.5123 \| 11.21 \| 2400 \| 0.5370 \| 0.7337 \| 0.735 \| \| 0.5033 \| 12.15 \| 2600 \| 0.5448 \| 0.7354 \| 0.738 \| \| 0.4978 \| 13.08 \| 2800 \| 0.5457 \| 0.7251 \| 0.73 \| \| 0.4941 \| 14.02 \| 3000 \| 0.5301 \| 0.7247 \| 0.725 \| \| 0.4876 \| 14.95 \| 3200 \| 0.5307 \| 0.7329 \| 0.734 \| \| 0.4826 \| 15.89 \| 3400 \| 0.5366 \| 0.7454 \| 0.746 \| \| 0.4758 \| 16.82 \| 3600 \| 0.5519 \| 0.7237 \| 0.724 \| \| 0.4688 \| 17.76 \| 3800 \| 0.5397 \| 0.7368 \| 0.737 \| \| 0.4654 \| 18.69 \| 4000 \| 0.5552 \| 0.7381 \| 0.738 \| \| 0.4639 \| 19.63 \| 4200 \| 0.5405 \| 0.7293 \| 0.731 \| \| 0.4603 \| 20.56 \| 4400 \| 0.5599 \| 0.7334 \| 0.734 \| \| 0.4531 \| 21.5 \| 4600 \| 0.5641 \| 0.7199 \| 0.72 \| \| 0.4439 \| 22.43 \| 4800 \| 0.5755 \| 0.7261 \| 0.726 \| \| 0.445 \| 23.36 \| 5000 \| 0.5866 \| 0.7261 \| 0.726 \| \| 0.4357 \| 24.3 \| 5200 \| 0.5901 \| 0.7194 \| 0.72 \| \| 0.4346 \| 25.23 \| 5400 \| 0.5861 \| 0.7320 \| 0.732 \| \| 0.432 \| 26.17 \| 5600 \| 0.5853 \| 0.7281 \| 0.729 \| \| 0.4265 \| 27.1 \| 5800 \| 0.5771 \| 0.7338 \| 0.734 \| \| 0.4206 \| 28.04 \| 6000 \| 0.5928 \| 0.7286 \| 0.729 \| \| 0.4202 \| 28.97 \| 6200 \| 0.5858 \| 0.7271 \| 0.727 \| \| 0.4166 \| 29.91 \| 6400 \| 0.5868 \| 0.7288 \| 0.729 \| \| 0.4071 \| 30.84 \| 6600 \| 0.5710 \| 0.7360 \| 0.737 \| \| 0.4075 \| 31.78 \| 6800 \| 0.5829 \| 0.7309 \| 0.731 \| \| 0.3999 \| 32.71 \| 7000 \| 0.5909 \| 0.7318 \| 0.732 \| \| 0.3992 \| 33.64 \| 7200 \| 0.5878 \| 0.7334 \| 0.734 \| \| 0.396 \| 34.58 \| 7400 \| 0.6131 \| 0.726 \| 0.726 \| \| 0.3995 \| 35.51 \| 7600 \| 0.6044 \| 0.7311 \| 0.731 \| \| 0.394 \| 36.45 \| 7800 \| 0.6331 \| 0.7281 \| 0.728 \| \| 0.3908 \| 37.38 \| 8000 \| 0.6152 \| 0.7338 \| 0.734 \| \| 0.3844 \| 38.32 \| 8200 \| 0.6255 \| 0.7268 \| 0.727 \| \| 0.3858 \| 39.25 \| 8400 \| 0.6303 \| 0.7271 \| 0.727 \| \| 0.3823 \| 40.19 \| 8600 \| 0.6294 \| 0.7300 \| 0.73 \| \| 0.3774 \| 41.12 \| 8800 \| 0.6246 \| 0.7296 \| 0.73 \| \| 0.3794 \| 42.06 \| 9000 \| 0.6387 \| 0.7329 \| 0.733 \| \| 0.3797 \| 42.99 \| 9200 \| 0.6269 \| 0.7280 \| 0.728 \| \| 0.3781 \| 43.93 \| 9400 \| 0.6261 \| 0.7280 \| 0.728 \| \| 0.3771 \| 44.86 \| 9600 \| 0.6308 \| 0.7369 \| 0.737 \| \| 0.3733 \| 45.79 \| 9800 \| 0.6318 \| 0.7350 \| 0.735 \| \| 0.3734 \| 46.73 \| 10000 \| 0.6363 \| 0.7370 \| 0.737 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_tf_3-seqsight_4096_512_46M-L32_f", "results": []}]}	mahdibaghbanzadeh/GUE_tf_3-seqsight_4096_512_46M-L32_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_46M", "region:us" ]	null	2024-04-27T01:09:05+00:00	[]	[]	TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us	GUE\_tf\_3-seqsight\_4096\_512\_46M-L32\_f ========================================== This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_4096\_512\_46M on the mahdibaghbanzadeh/GUE\_tf\_3 dataset. It achieves the following results on the evaluation set: * Loss: 0.5223 * F1 Score: 0.7373 * Accuracy: 0.739 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]	[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_tf_3-seqsight_4096_512_46M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_tf_3](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_3) dataset. It achieves the following results on the evaluation set: - Loss: 0.5282 - F1 Score: 0.7300 - Accuracy: 0.733 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.6154 \| 0.93 \| 200 \| 0.5729 \| 0.6841 \| 0.684 \| \| 0.589 \| 1.87 \| 400 \| 0.5770 \| 0.6839 \| 0.685 \| \| 0.5798 \| 2.8 \| 600 \| 0.5512 \| 0.7087 \| 0.709 \| \| 0.5697 \| 3.74 \| 800 \| 0.5494 \| 0.7090 \| 0.709 \| \| 0.5615 \| 4.67 \| 1000 \| 0.5368 \| 0.7056 \| 0.706 \| \| 0.5596 \| 5.61 \| 1200 \| 0.5311 \| 0.7168 \| 0.718 \| \| 0.5522 \| 6.54 \| 1400 \| 0.5327 \| 0.7135 \| 0.714 \| \| 0.5454 \| 7.48 \| 1600 \| 0.5327 \| 0.7259 \| 0.726 \| \| 0.5423 \| 8.41 \| 1800 \| 0.5324 \| 0.7204 \| 0.721 \| \| 0.5427 \| 9.35 \| 2000 \| 0.5291 \| 0.7278 \| 0.729 \| \| 0.5336 \| 10.28 \| 2200 \| 0.5332 \| 0.7271 \| 0.727 \| \| 0.5328 \| 11.21 \| 2400 \| 0.5336 \| 0.7270 \| 0.728 \| \| 0.529 \| 12.15 \| 2600 \| 0.5335 \| 0.7315 \| 0.734 \| \| 0.5253 \| 13.08 \| 2800 \| 0.5434 \| 0.7352 \| 0.74 \| \| 0.5254 \| 14.02 \| 3000 \| 0.5290 \| 0.7342 \| 0.735 \| \| 0.5218 \| 14.95 \| 3200 \| 0.5234 \| 0.7374 \| 0.739 \| \| 0.5188 \| 15.89 \| 3400 \| 0.5281 \| 0.7245 \| 0.725 \| \| 0.5138 \| 16.82 \| 3600 \| 0.5324 \| 0.7216 \| 0.722 \| \| 0.5121 \| 17.76 \| 3800 \| 0.5307 \| 0.7321 \| 0.733 \| \| 0.5101 \| 18.69 \| 4000 \| 0.5323 \| 0.7181 \| 0.718 \| \| 0.5105 \| 19.63 \| 4200 \| 0.5319 \| 0.7356 \| 0.737 \| \| 0.5089 \| 20.56 \| 4400 \| 0.5318 \| 0.7387 \| 0.74 \| \| 0.505 \| 21.5 \| 4600 \| 0.5371 \| 0.7210 \| 0.721 \| \| 0.4987 \| 22.43 \| 4800 \| 0.5385 \| 0.7294 \| 0.73 \| \| 0.5028 \| 23.36 \| 5000 \| 0.5404 \| 0.7281 \| 0.728 \| \| 0.4989 \| 24.3 \| 5200 \| 0.5474 \| 0.7233 \| 0.724 \| \| 0.494 \| 25.23 \| 5400 \| 0.5340 \| 0.7340 \| 0.735 \| \| 0.498 \| 26.17 \| 5600 \| 0.5314 \| 0.7328 \| 0.734 \| \| 0.4909 \| 27.1 \| 5800 \| 0.5373 \| 0.7275 \| 0.728 \| \| 0.4893 \| 28.04 \| 6000 \| 0.5386 \| 0.7297 \| 0.73 \| \| 0.4903 \| 28.97 \| 6200 \| 0.5429 \| 0.7150 \| 0.715 \| \| 0.4912 \| 29.91 \| 6400 \| 0.5367 \| 0.7233 \| 0.724 \| \| 0.4869 \| 30.84 \| 6600 \| 0.5278 \| 0.7353 \| 0.736 \| \| 0.4845 \| 31.78 \| 6800 \| 0.5310 \| 0.7338 \| 0.734 \| \| 0.4836 \| 32.71 \| 7000 \| 0.5335 \| 0.7375 \| 0.738 \| \| 0.4839 \| 33.64 \| 7200 \| 0.5342 \| 0.7209 \| 0.721 \| \| 0.4788 \| 34.58 \| 7400 \| 0.5403 \| 0.7180 \| 0.718 \| \| 0.4833 \| 35.51 \| 7600 \| 0.5345 \| 0.7190 \| 0.719 \| \| 0.4801 \| 36.45 \| 7800 \| 0.5404 \| 0.7220 \| 0.722 \| \| 0.4782 \| 37.38 \| 8000 \| 0.5353 \| 0.7308 \| 0.731 \| \| 0.4756 \| 38.32 \| 8200 \| 0.5350 \| 0.7366 \| 0.737 \| \| 0.4741 \| 39.25 \| 8400 \| 0.5389 \| 0.7359 \| 0.736 \| \| 0.4746 \| 40.19 \| 8600 \| 0.5369 \| 0.7318 \| 0.732 \| \| 0.4745 \| 41.12 \| 8800 \| 0.5377 \| 0.7328 \| 0.733 \| \| 0.4741 \| 42.06 \| 9000 \| 0.5390 \| 0.7280 \| 0.728 \| \| 0.4745 \| 42.99 \| 9200 \| 0.5382 \| 0.7260 \| 0.726 \| \| 0.472 \| 43.93 \| 9400 \| 0.5387 \| 0.7251 \| 0.725 \| \| 0.4707 \| 44.86 \| 9600 \| 0.5377 \| 0.7300 \| 0.73 \| \| 0.4701 \| 45.79 \| 9800 \| 0.5391 \| 0.728 \| 0.728 \| \| 0.4677 \| 46.73 \| 10000 \| 0.5395 \| 0.7290 \| 0.729 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_tf_3-seqsight_4096_512_46M-L8_f", "results": []}]}	mahdibaghbanzadeh/GUE_tf_3-seqsight_4096_512_46M-L8_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_46M", "region:us" ]	null	2024-04-27T01:09:05+00:00	[]	[]	TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us	GUE\_tf\_3-seqsight\_4096\_512\_46M-L8\_f ========================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_4096\_512\_46M on the mahdibaghbanzadeh/GUE\_tf\_3 dataset. It achieves the following results on the evaluation set: * Loss: 0.5282 * F1 Score: 0.7300 * Accuracy: 0.733 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]	[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]
text-generation	transformers	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # 0.001_4iters_bs256_nodpo_only4w_userresponse_iter_4 This model is a fine-tuned version of [ShenaoZhang/0.001_4iters_bs256_nodpo_only4w_userresponse_iter_3](https://huggingface.co/ShenaoZhang/0.001_4iters_bs256_nodpo_only4w_userresponse_iter_3) on the updated and the original datasets. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-07 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - distributed_type: multi-GPU - num_devices: 8 - gradient_accumulation_steps: 4 - total_train_batch_size: 256 - total_eval_batch_size: 64 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 1 ### Training results ### Framework versions - Transformers 4.40.0 - Pytorch 2.1.2+cu121 - Datasets 2.14.6 - Tokenizers 0.19.1	{"license": "mit", "tags": ["alignment-handbook", "trl", "dpo", "generated_from_trainer", "trl", "dpo", "generated_from_trainer"], "datasets": ["updated", "original"], "base_model": "ShenaoZhang/0.001_4iters_bs256_nodpo_only4w_userresponse_iter_3", "model-index": [{"name": "0.001_4iters_bs256_nodpo_only4w_userresponse_iter_4", "results": []}]}	ShenaoZhang/0.001_4iters_bs256_nodpo_only4w_userresponse_iter_4	null	[ "transformers", "safetensors", "mistral", "text-generation", "alignment-handbook", "trl", "dpo", "generated_from_trainer", "conversational", "dataset:updated", "dataset:original", "base_model:ShenaoZhang/0.001_4iters_bs256_nodpo_only4w_userresponse_iter_3", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-27T01:10:49+00:00	[]	[]	TAGS #transformers #safetensors #mistral #text-generation #alignment-handbook #trl #dpo #generated_from_trainer #conversational #dataset-updated #dataset-original #base_model-ShenaoZhang/0.001_4iters_bs256_nodpo_only4w_userresponse_iter_3 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us	# 0.001_4iters_bs256_nodpo_only4w_userresponse_iter_4 This model is a fine-tuned version of ShenaoZhang/0.001_4iters_bs256_nodpo_only4w_userresponse_iter_3 on the updated and the original datasets. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-07 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - distributed_type: multi-GPU - num_devices: 8 - gradient_accumulation_steps: 4 - total_train_batch_size: 256 - total_eval_batch_size: 64 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 1 ### Training results ### Framework versions - Transformers 4.40.0 - Pytorch 2.1.2+cu121 - Datasets 2.14.6 - Tokenizers 0.19.1	[ "# 0.001_4iters_bs256_nodpo_only4w_userresponse_iter_4\n\nThis model is a fine-tuned version of ShenaoZhang/0.001_4iters_bs256_nodpo_only4w_userresponse_iter_3 on the updated and the original datasets.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.19.1" ]	[ "TAGS\n#transformers #safetensors #mistral #text-generation #alignment-handbook #trl #dpo #generated_from_trainer #conversational #dataset-updated #dataset-original #base_model-ShenaoZhang/0.001_4iters_bs256_nodpo_only4w_userresponse_iter_3 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# 0.001_4iters_bs256_nodpo_only4w_userresponse_iter_4\n\nThis model is a fine-tuned version of ShenaoZhang/0.001_4iters_bs256_nodpo_only4w_userresponse_iter_3 on the updated and the original datasets.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.19.1" ]
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_tf_2-seqsight_4096_512_46M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_tf_2](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_2) dataset. It achieves the following results on the evaluation set: - Loss: 0.4291 - F1 Score: 0.7986 - Accuracy: 0.799 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.5673 \| 1.34 \| 200 \| 0.5263 \| 0.7249 \| 0.726 \| \| 0.5317 \| 2.68 \| 400 \| 0.5122 \| 0.7597 \| 0.76 \| \| 0.5187 \| 4.03 \| 600 \| 0.5044 \| 0.7569 \| 0.757 \| \| 0.5111 \| 5.37 \| 800 \| 0.4975 \| 0.7610 \| 0.761 \| \| 0.507 \| 6.71 \| 1000 \| 0.4986 \| 0.7528 \| 0.753 \| \| 0.498 \| 8.05 \| 1200 \| 0.4975 \| 0.7568 \| 0.757 \| \| 0.4929 \| 9.4 \| 1400 \| 0.4913 \| 0.7577 \| 0.758 \| \| 0.4904 \| 10.74 \| 1600 \| 0.4857 \| 0.7549 \| 0.755 \| \| 0.4838 \| 12.08 \| 1800 \| 0.4980 \| 0.7636 \| 0.764 \| \| 0.4827 \| 13.42 \| 2000 \| 0.4954 \| 0.7569 \| 0.757 \| \| 0.4799 \| 14.77 \| 2200 \| 0.4875 \| 0.7448 \| 0.746 \| \| 0.4719 \| 16.11 \| 2400 \| 0.4951 \| 0.7579 \| 0.758 \| \| 0.4755 \| 17.45 \| 2600 \| 0.4845 \| 0.7579 \| 0.758 \| \| 0.4659 \| 18.79 \| 2800 \| 0.4827 \| 0.7617 \| 0.762 \| \| 0.4668 \| 20.13 \| 3000 \| 0.4839 \| 0.7590 \| 0.759 \| \| 0.4635 \| 21.48 \| 3200 \| 0.4930 \| 0.7630 \| 0.763 \| \| 0.4629 \| 22.82 \| 3400 \| 0.4865 \| 0.7679 \| 0.768 \| \| 0.4582 \| 24.16 \| 3600 \| 0.4818 \| 0.7678 \| 0.768 \| \| 0.4549 \| 25.5 \| 3800 \| 0.4871 \| 0.7581 \| 0.759 \| \| 0.454 \| 26.85 \| 4000 \| 0.4836 \| 0.7614 \| 0.762 \| \| 0.453 \| 28.19 \| 4200 \| 0.4829 \| 0.7605 \| 0.761 \| \| 0.4509 \| 29.53 \| 4400 \| 0.4892 \| 0.7610 \| 0.761 \| \| 0.4503 \| 30.87 \| 4600 \| 0.4881 \| 0.7639 \| 0.764 \| \| 0.4481 \| 32.21 \| 4800 \| 0.4908 \| 0.7608 \| 0.761 \| \| 0.4482 \| 33.56 \| 5000 \| 0.4896 \| 0.7600 \| 0.76 \| \| 0.4467 \| 34.9 \| 5200 \| 0.4922 \| 0.7669 \| 0.767 \| \| 0.4395 \| 36.24 \| 5400 \| 0.4873 \| 0.7709 \| 0.771 \| \| 0.4408 \| 37.58 \| 5600 \| 0.4899 \| 0.7648 \| 0.765 \| \| 0.441 \| 38.93 \| 5800 \| 0.4909 \| 0.7654 \| 0.766 \| \| 0.4376 \| 40.27 \| 6000 \| 0.4887 \| 0.7575 \| 0.758 \| \| 0.4365 \| 41.61 \| 6200 \| 0.4922 \| 0.7615 \| 0.762 \| \| 0.4366 \| 42.95 \| 6400 \| 0.4944 \| 0.7647 \| 0.765 \| \| 0.4332 \| 44.3 \| 6600 \| 0.4940 \| 0.7598 \| 0.76 \| \| 0.439 \| 45.64 \| 6800 \| 0.4908 \| 0.7649 \| 0.765 \| \| 0.4314 \| 46.98 \| 7000 \| 0.4927 \| 0.7637 \| 0.764 \| \| 0.4287 \| 48.32 \| 7200 \| 0.4924 \| 0.7629 \| 0.763 \| \| 0.4272 \| 49.66 \| 7400 \| 0.4949 \| 0.7647 \| 0.765 \| \| 0.4269 \| 51.01 \| 7600 \| 0.4926 \| 0.7637 \| 0.764 \| \| 0.4263 \| 52.35 \| 7800 \| 0.4964 \| 0.7577 \| 0.758 \| \| 0.4277 \| 53.69 \| 8000 \| 0.4943 \| 0.7582 \| 0.759 \| \| 0.4234 \| 55.03 \| 8200 \| 0.4959 \| 0.7579 \| 0.758 \| \| 0.4255 \| 56.38 \| 8400 \| 0.4950 \| 0.7599 \| 0.76 \| \| 0.4274 \| 57.72 \| 8600 \| 0.4958 \| 0.7535 \| 0.754 \| \| 0.4214 \| 59.06 \| 8800 \| 0.4952 \| 0.7547 \| 0.755 \| \| 0.4185 \| 60.4 \| 9000 \| 0.4988 \| 0.7588 \| 0.759 \| \| 0.4247 \| 61.74 \| 9200 \| 0.4964 \| 0.7577 \| 0.758 \| \| 0.4226 \| 63.09 \| 9400 \| 0.4972 \| 0.7618 \| 0.762 \| \| 0.4185 \| 64.43 \| 9600 \| 0.4971 \| 0.7616 \| 0.762 \| \| 0.4254 \| 65.77 \| 9800 \| 0.4965 \| 0.7587 \| 0.759 \| \| 0.4151 \| 67.11 \| 10000 \| 0.4965 \| 0.7596 \| 0.76 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_tf_2-seqsight_4096_512_46M-L1_f", "results": []}]}	mahdibaghbanzadeh/GUE_tf_2-seqsight_4096_512_46M-L1_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_46M", "region:us" ]	null	2024-04-27T01:12:28+00:00	[]	[]	TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us	GUE\_tf\_2-seqsight\_4096\_512\_46M-L1\_f ========================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_4096\_512\_46M on the mahdibaghbanzadeh/GUE\_tf\_2 dataset. It achieves the following results on the evaluation set: * Loss: 0.4291 * F1 Score: 0.7986 * Accuracy: 0.799 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]	[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]
null	transformers	# Uploaded model - Developed by: berger815 - License: apache-2.0 - Finetuned from model : unsloth/llama-3-8b-bnb-4bit This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)	{"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "llama", "gguf"], "base_model": "unsloth/llama-3-8b-bnb-4bit"}	berger815/sail	null	[ "transformers", "gguf", "llama", "text-generation-inference", "unsloth", "en", "base_model:unsloth/llama-3-8b-bnb-4bit", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2024-04-27T01:14:05+00:00	[]	[ "en" ]	TAGS #transformers #gguf #llama #text-generation-inference #unsloth #en #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us	# Uploaded model - Developed by: berger815 - License: apache-2.0 - Finetuned from model : unsloth/llama-3-8b-bnb-4bit This llama model was trained 2x faster with Unsloth and Huggingface's TRL library. <img src="URL width="200"/>	[ "# Uploaded model\n\n- Developed by: berger815\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]	[ "TAGS\n#transformers #gguf #llama #text-generation-inference #unsloth #en #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us \n", "# Uploaded model\n\n- Developed by: berger815\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_tf_2-seqsight_4096_512_46M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_tf_2](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_2) dataset. It achieves the following results on the evaluation set: - Loss: 0.4177 - F1 Score: 0.8059 - Accuracy: 0.806 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.5544 \| 1.34 \| 200 \| 0.5176 \| 0.7450 \| 0.745 \| \| 0.5145 \| 2.68 \| 400 \| 0.5058 \| 0.7586 \| 0.759 \| \| 0.5023 \| 4.03 \| 600 \| 0.4987 \| 0.7597 \| 0.76 \| \| 0.493 \| 5.37 \| 800 \| 0.4933 \| 0.7609 \| 0.761 \| \| 0.4858 \| 6.71 \| 1000 \| 0.4995 \| 0.7535 \| 0.754 \| \| 0.4776 \| 8.05 \| 1200 \| 0.4864 \| 0.7579 \| 0.758 \| \| 0.4701 \| 9.4 \| 1400 \| 0.4893 \| 0.7530 \| 0.753 \| \| 0.4687 \| 10.74 \| 1600 \| 0.4842 \| 0.7609 \| 0.761 \| \| 0.4636 \| 12.08 \| 1800 \| 0.4857 \| 0.7640 \| 0.764 \| \| 0.4569 \| 13.42 \| 2000 \| 0.4932 \| 0.7570 \| 0.757 \| \| 0.4552 \| 14.77 \| 2200 \| 0.4921 \| 0.7446 \| 0.747 \| \| 0.4445 \| 16.11 \| 2400 \| 0.4963 \| 0.7540 \| 0.754 \| \| 0.4464 \| 17.45 \| 2600 \| 0.4895 \| 0.7472 \| 0.748 \| \| 0.436 \| 18.79 \| 2800 \| 0.4813 \| 0.7595 \| 0.76 \| \| 0.4342 \| 20.13 \| 3000 \| 0.4896 \| 0.7710 \| 0.771 \| \| 0.4303 \| 21.48 \| 3200 \| 0.4968 \| 0.7720 \| 0.772 \| \| 0.4297 \| 22.82 \| 3400 \| 0.4859 \| 0.7587 \| 0.759 \| \| 0.4236 \| 24.16 \| 3600 \| 0.4871 \| 0.7634 \| 0.764 \| \| 0.4179 \| 25.5 \| 3800 \| 0.4942 \| 0.7676 \| 0.768 \| \| 0.4168 \| 26.85 \| 4000 \| 0.4995 \| 0.7535 \| 0.754 \| \| 0.4116 \| 28.19 \| 4200 \| 0.4928 \| 0.7600 \| 0.76 \| \| 0.4127 \| 29.53 \| 4400 \| 0.4995 \| 0.7506 \| 0.751 \| \| 0.4094 \| 30.87 \| 4600 \| 0.4962 \| 0.7628 \| 0.763 \| \| 0.4058 \| 32.21 \| 4800 \| 0.5047 \| 0.7649 \| 0.765 \| \| 0.4039 \| 33.56 \| 5000 \| 0.5042 \| 0.7620 \| 0.762 \| \| 0.4001 \| 34.9 \| 5200 \| 0.5061 \| 0.75 \| 0.75 \| \| 0.3923 \| 36.24 \| 5400 \| 0.5088 \| 0.7546 \| 0.755 \| \| 0.392 \| 37.58 \| 5600 \| 0.5064 \| 0.7567 \| 0.757 \| \| 0.3905 \| 38.93 \| 5800 \| 0.5066 \| 0.7522 \| 0.753 \| \| 0.3837 \| 40.27 \| 6000 \| 0.5184 \| 0.7472 \| 0.749 \| \| 0.3843 \| 41.61 \| 6200 \| 0.5116 \| 0.7604 \| 0.761 \| \| 0.3827 \| 42.95 \| 6400 \| 0.5182 \| 0.7619 \| 0.762 \| \| 0.3759 \| 44.3 \| 6600 \| 0.5226 \| 0.7499 \| 0.75 \| \| 0.3827 \| 45.64 \| 6800 \| 0.5227 \| 0.7590 \| 0.759 \| \| 0.3748 \| 46.98 \| 7000 \| 0.5185 \| 0.7599 \| 0.76 \| \| 0.3724 \| 48.32 \| 7200 \| 0.5180 \| 0.7597 \| 0.76 \| \| 0.3689 \| 49.66 \| 7400 \| 0.5216 \| 0.7549 \| 0.755 \| \| 0.3688 \| 51.01 \| 7600 \| 0.5168 \| 0.7558 \| 0.756 \| \| 0.3682 \| 52.35 \| 7800 \| 0.5278 \| 0.7558 \| 0.756 \| \| 0.3671 \| 53.69 \| 8000 \| 0.5224 \| 0.7484 \| 0.749 \| \| 0.3623 \| 55.03 \| 8200 \| 0.5258 \| 0.76 \| 0.76 \| \| 0.3639 \| 56.38 \| 8400 \| 0.5292 \| 0.7527 \| 0.753 \| \| 0.3653 \| 57.72 \| 8600 \| 0.5249 \| 0.7476 \| 0.748 \| \| 0.3592 \| 59.06 \| 8800 \| 0.5289 \| 0.7520 \| 0.752 \| \| 0.3548 \| 60.4 \| 9000 \| 0.5363 \| 0.7509 \| 0.751 \| \| 0.361 \| 61.74 \| 9200 \| 0.5303 \| 0.7498 \| 0.75 \| \| 0.3578 \| 63.09 \| 9400 \| 0.5297 \| 0.7530 \| 0.753 \| \| 0.355 \| 64.43 \| 9600 \| 0.5298 \| 0.7497 \| 0.75 \| \| 0.3611 \| 65.77 \| 9800 \| 0.5298 \| 0.7499 \| 0.75 \| \| 0.3525 \| 67.11 \| 10000 \| 0.5308 \| 0.7508 \| 0.751 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_tf_2-seqsight_4096_512_46M-L8_f", "results": []}]}	mahdibaghbanzadeh/GUE_tf_2-seqsight_4096_512_46M-L8_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_46M", "region:us" ]	null	2024-04-27T01:16:29+00:00	[]	[]	TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us	GUE\_tf\_2-seqsight\_4096\_512\_46M-L8\_f ========================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_4096\_512\_46M on the mahdibaghbanzadeh/GUE\_tf\_2 dataset. It achieves the following results on the evaluation set: * Loss: 0.4177 * F1 Score: 0.8059 * Accuracy: 0.806 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]	[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_tf_2-seqsight_4096_512_46M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_tf_2](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_2) dataset. It achieves the following results on the evaluation set: - Loss: 0.4244 - F1 Score: 0.8144 - Accuracy: 0.815 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.5473 \| 1.34 \| 200 \| 0.5045 \| 0.7480 \| 0.748 \| \| 0.5072 \| 2.68 \| 400 \| 0.5003 \| 0.7693 \| 0.77 \| \| 0.4937 \| 4.03 \| 600 \| 0.4978 \| 0.7570 \| 0.758 \| \| 0.4809 \| 5.37 \| 800 \| 0.4858 \| 0.7698 \| 0.77 \| \| 0.4694 \| 6.71 \| 1000 \| 0.4840 \| 0.7699 \| 0.77 \| \| 0.4588 \| 8.05 \| 1200 \| 0.4779 \| 0.7718 \| 0.772 \| \| 0.4478 \| 9.4 \| 1400 \| 0.4832 \| 0.7700 \| 0.77 \| \| 0.4415 \| 10.74 \| 1600 \| 0.4833 \| 0.7599 \| 0.76 \| \| 0.4325 \| 12.08 \| 1800 \| 0.4849 \| 0.7457 \| 0.746 \| \| 0.4207 \| 13.42 \| 2000 \| 0.4910 \| 0.7690 \| 0.769 \| \| 0.4159 \| 14.77 \| 2200 \| 0.4891 \| 0.7501 \| 0.752 \| \| 0.4005 \| 16.11 \| 2400 \| 0.5130 \| 0.766 \| 0.766 \| \| 0.397 \| 17.45 \| 2600 \| 0.4905 \| 0.7658 \| 0.766 \| \| 0.3812 \| 18.79 \| 2800 \| 0.4931 \| 0.7539 \| 0.754 \| \| 0.38 \| 20.13 \| 3000 \| 0.5029 \| 0.7689 \| 0.769 \| \| 0.366 \| 21.48 \| 3200 \| 0.5259 \| 0.7650 \| 0.765 \| \| 0.3615 \| 22.82 \| 3400 \| 0.5142 \| 0.7600 \| 0.76 \| \| 0.3533 \| 24.16 \| 3600 \| 0.5133 \| 0.7558 \| 0.756 \| \| 0.3404 \| 25.5 \| 3800 \| 0.5249 \| 0.7559 \| 0.756 \| \| 0.3372 \| 26.85 \| 4000 \| 0.5349 \| 0.7529 \| 0.753 \| \| 0.3282 \| 28.19 \| 4200 \| 0.5312 \| 0.7620 \| 0.762 \| \| 0.3224 \| 29.53 \| 4400 \| 0.5504 \| 0.7568 \| 0.757 \| \| 0.3177 \| 30.87 \| 4600 \| 0.5576 \| 0.7588 \| 0.759 \| \| 0.3093 \| 32.21 \| 4800 \| 0.5691 \| 0.7640 \| 0.764 \| \| 0.3065 \| 33.56 \| 5000 \| 0.5583 \| 0.7640 \| 0.764 \| \| 0.293 \| 34.9 \| 5200 \| 0.5930 \| 0.7468 \| 0.747 \| \| 0.2857 \| 36.24 \| 5400 \| 0.5897 \| 0.7610 \| 0.761 \| \| 0.2831 \| 37.58 \| 5600 \| 0.5956 \| 0.7559 \| 0.756 \| \| 0.2758 \| 38.93 \| 5800 \| 0.5931 \| 0.7526 \| 0.753 \| \| 0.2693 \| 40.27 \| 6000 \| 0.6084 \| 0.7511 \| 0.752 \| \| 0.2641 \| 41.61 \| 6200 \| 0.6205 \| 0.7555 \| 0.756 \| \| 0.2624 \| 42.95 \| 6400 \| 0.6236 \| 0.7680 \| 0.768 \| \| 0.2524 \| 44.3 \| 6600 \| 0.6303 \| 0.7579 \| 0.758 \| \| 0.2578 \| 45.64 \| 6800 \| 0.6329 \| 0.7589 \| 0.759 \| \| 0.251 \| 46.98 \| 7000 \| 0.6389 \| 0.7609 \| 0.761 \| \| 0.2421 \| 48.32 \| 7200 \| 0.6307 \| 0.7588 \| 0.759 \| \| 0.2375 \| 49.66 \| 7400 \| 0.6399 \| 0.7619 \| 0.762 \| \| 0.2346 \| 51.01 \| 7600 \| 0.6300 \| 0.7610 \| 0.761 \| \| 0.2343 \| 52.35 \| 7800 \| 0.6554 \| 0.7590 \| 0.759 \| \| 0.2256 \| 53.69 \| 8000 \| 0.6766 \| 0.7539 \| 0.754 \| \| 0.2247 \| 55.03 \| 8200 \| 0.6589 \| 0.7599 \| 0.76 \| \| 0.2262 \| 56.38 \| 8400 \| 0.6732 \| 0.7629 \| 0.763 \| \| 0.2237 \| 57.72 \| 8600 \| 0.6709 \| 0.7568 \| 0.757 \| \| 0.219 \| 59.06 \| 8800 \| 0.6830 \| 0.7598 \| 0.76 \| \| 0.2108 \| 60.4 \| 9000 \| 0.6949 \| 0.7589 \| 0.759 \| \| 0.2168 \| 61.74 \| 9200 \| 0.6767 \| 0.7609 \| 0.761 \| \| 0.2109 \| 63.09 \| 9400 \| 0.6819 \| 0.7520 \| 0.752 \| \| 0.2095 \| 64.43 \| 9600 \| 0.6936 \| 0.7629 \| 0.763 \| \| 0.2098 \| 65.77 \| 9800 \| 0.6890 \| 0.7590 \| 0.759 \| \| 0.2081 \| 67.11 \| 10000 \| 0.6882 \| 0.7630 \| 0.763 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_tf_2-seqsight_4096_512_46M-L32_f", "results": []}]}	mahdibaghbanzadeh/GUE_tf_2-seqsight_4096_512_46M-L32_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_46M", "region:us" ]	null	2024-04-27T01:16:37+00:00	[]	[]	TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us	GUE\_tf\_2-seqsight\_4096\_512\_46M-L32\_f ========================================== This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_4096\_512\_46M on the mahdibaghbanzadeh/GUE\_tf\_2 dataset. It achieves the following results on the evaluation set: * Loss: 0.4244 * F1 Score: 0.8144 * Accuracy: 0.815 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]	[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_virus_covid-seqsight_4096_512_46M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_virus_covid](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_virus_covid) dataset. It achieves the following results on the evaluation set: - Loss: 1.4763 - F1 Score: 0.4656 - Accuracy: 0.4567 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 2.1823 \| 0.35 \| 200 \| 2.1755 \| 0.1308 \| 0.1550 \| \| 2.1713 \| 0.7 \| 400 \| 2.1631 \| 0.1232 \| 0.1561 \| \| 2.1562 \| 1.05 \| 600 \| 2.1489 \| 0.1267 \| 0.1598 \| \| 2.1422 \| 1.4 \| 800 \| 2.1259 \| 0.1591 \| 0.1855 \| \| 2.1125 \| 1.75 \| 1000 \| 2.0921 \| 0.2001 \| 0.2172 \| \| 2.0522 \| 2.09 \| 1200 \| 2.0180 \| 0.2094 \| 0.2229 \| \| 2.0008 \| 2.44 \| 1400 \| 2.0021 \| 0.2175 \| 0.2235 \| \| 1.9803 \| 2.79 \| 1600 \| 1.9652 \| 0.2402 \| 0.2482 \| \| 1.9533 \| 3.14 \| 1800 \| 1.9438 \| 0.2502 \| 0.2591 \| \| 1.9191 \| 3.49 \| 2000 \| 1.9104 \| 0.2594 \| 0.2681 \| \| 1.898 \| 3.84 \| 2200 \| 1.8906 \| 0.2787 \| 0.2826 \| \| 1.874 \| 4.19 \| 2400 \| 1.8751 \| 0.2928 \| 0.2907 \| \| 1.8486 \| 4.54 \| 2600 \| 1.8183 \| 0.3136 \| 0.3125 \| \| 1.8371 \| 4.89 \| 2800 \| 1.8066 \| 0.3193 \| 0.3211 \| \| 1.8173 \| 5.24 \| 3000 \| 1.7830 \| 0.3277 \| 0.3274 \| \| 1.7984 \| 5.58 \| 3200 \| 1.7757 \| 0.3458 \| 0.3403 \| \| 1.7731 \| 5.93 \| 3400 \| 1.7557 \| 0.3397 \| 0.3405 \| \| 1.7691 \| 6.28 \| 3600 \| 1.7237 \| 0.3532 \| 0.3449 \| \| 1.7417 \| 6.63 \| 3800 \| 1.7201 \| 0.3604 \| 0.3551 \| \| 1.7384 \| 6.98 \| 4000 \| 1.6938 \| 0.3712 \| 0.3625 \| \| 1.7209 \| 7.33 \| 4200 \| 1.6768 \| 0.3679 \| 0.3640 \| \| 1.7136 \| 7.68 \| 4400 \| 1.6731 \| 0.3859 \| 0.3760 \| \| 1.7088 \| 8.03 \| 4600 \| 1.6489 \| 0.3892 \| 0.3776 \| \| 1.6831 \| 8.38 \| 4800 \| 1.6485 \| 0.3828 \| 0.3748 \| \| 1.6867 \| 8.73 \| 5000 \| 1.6315 \| 0.3822 \| 0.3806 \| \| 1.6676 \| 9.08 \| 5200 \| 1.6224 \| 0.4034 \| 0.3878 \| \| 1.6583 \| 9.42 \| 5400 \| 1.5976 \| 0.3983 \| 0.3943 \| \| 1.6444 \| 9.77 \| 5600 \| 1.5920 \| 0.4158 \| 0.4085 \| \| 1.6423 \| 10.12 \| 5800 \| 1.5823 \| 0.4177 \| 0.4045 \| \| 1.6388 \| 10.47 \| 6000 \| 1.5672 \| 0.4187 \| 0.4129 \| \| 1.6279 \| 10.82 \| 6200 \| 1.5768 \| 0.4160 \| 0.4046 \| \| 1.6126 \| 11.17 \| 6400 \| 1.5586 \| 0.4314 \| 0.4186 \| \| 1.6081 \| 11.52 \| 6600 \| 1.5500 \| 0.4324 \| 0.4235 \| \| 1.6111 \| 11.87 \| 6800 \| 1.5411 \| 0.4372 \| 0.4322 \| \| 1.6029 \| 12.22 \| 7000 \| 1.5316 \| 0.4445 \| 0.4380 \| \| 1.587 \| 12.57 \| 7200 \| 1.5282 \| 0.4388 \| 0.4354 \| \| 1.5933 \| 12.91 \| 7400 \| 1.5249 \| 0.4433 \| 0.4384 \| \| 1.5853 \| 13.26 \| 7600 \| 1.5170 \| 0.4500 \| 0.4448 \| \| 1.5763 \| 13.61 \| 7800 \| 1.5102 \| 0.4547 \| 0.4473 \| \| 1.5714 \| 13.96 \| 8000 \| 1.5047 \| 0.4578 \| 0.4488 \| \| 1.5627 \| 14.31 \| 8200 \| 1.5040 \| 0.4541 \| 0.4468 \| \| 1.5692 \| 14.66 \| 8400 \| 1.5010 \| 0.4592 \| 0.4483 \| \| 1.5674 \| 15.01 \| 8600 \| 1.4997 \| 0.4604 \| 0.4539 \| \| 1.5651 \| 15.36 \| 8800 \| 1.4966 \| 0.4577 \| 0.4481 \| \| 1.551 \| 15.71 \| 9000 \| 1.4878 \| 0.4596 \| 0.4544 \| \| 1.5595 \| 16.06 \| 9200 \| 1.4864 \| 0.4639 \| 0.4564 \| \| 1.5496 \| 16.4 \| 9400 \| 1.4850 \| 0.4660 \| 0.4594 \| \| 1.5506 \| 16.75 \| 9600 \| 1.4848 \| 0.4615 \| 0.4557 \| \| 1.5503 \| 17.1 \| 9800 \| 1.4855 \| 0.4610 \| 0.4553 \| \| 1.5622 \| 17.45 \| 10000 \| 1.4856 \| 0.4608 \| 0.4543 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_virus_covid-seqsight_4096_512_46M-L1_f", "results": []}]}	mahdibaghbanzadeh/GUE_virus_covid-seqsight_4096_512_46M-L1_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_46M", "region:us" ]	null	2024-04-27T01:17:02+00:00	[]	[]	TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us	GUE\_virus\_covid-seqsight\_4096\_512\_46M-L1\_f ================================================ This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_4096\_512\_46M on the mahdibaghbanzadeh/GUE\_virus\_covid dataset. It achieves the following results on the evaluation set: * Loss: 1.4763 * F1 Score: 0.4656 * Accuracy: 0.4567 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]	[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_virus_covid-seqsight_4096_512_46M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_virus_covid](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_virus_covid) dataset. It achieves the following results on the evaluation set: - Loss: 1.1081 - F1 Score: 0.5885 - Accuracy: 0.5836 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 2.1813 \| 0.35 \| 200 \| 2.1726 \| 0.1379 \| 0.1588 \| \| 2.1662 \| 0.7 \| 400 \| 2.1509 \| 0.1381 \| 0.1652 \| \| 2.1037 \| 1.05 \| 600 \| 2.0112 \| 0.2257 \| 0.2359 \| \| 1.9819 \| 1.4 \| 800 \| 1.9200 \| 0.2583 \| 0.2687 \| \| 1.8868 \| 1.75 \| 1000 \| 1.8249 \| 0.3095 \| 0.3102 \| \| 1.8165 \| 2.09 \| 1200 \| 1.7372 \| 0.3276 \| 0.3355 \| \| 1.7544 \| 2.44 \| 1400 \| 1.6856 \| 0.3698 \| 0.3568 \| \| 1.6947 \| 2.79 \| 1600 \| 1.6089 \| 0.3855 \| 0.3813 \| \| 1.6505 \| 3.14 \| 1800 \| 1.5679 \| 0.4055 \| 0.4033 \| \| 1.6094 \| 3.49 \| 2000 \| 1.5561 \| 0.4103 \| 0.4004 \| \| 1.5905 \| 3.84 \| 2200 \| 1.5347 \| 0.4307 \| 0.4259 \| \| 1.5608 \| 4.19 \| 2400 \| 1.4948 \| 0.4371 \| 0.4297 \| \| 1.5426 \| 4.54 \| 2600 \| 1.4540 \| 0.4686 \| 0.4594 \| \| 1.5276 \| 4.89 \| 2800 \| 1.4528 \| 0.4607 \| 0.4530 \| \| 1.501 \| 5.24 \| 3000 \| 1.4105 \| 0.4782 \| 0.4726 \| \| 1.492 \| 5.58 \| 3200 \| 1.3877 \| 0.4903 \| 0.4852 \| \| 1.456 \| 5.93 \| 3400 \| 1.3723 \| 0.4943 \| 0.4924 \| \| 1.4394 \| 6.28 \| 3600 \| 1.3620 \| 0.4935 \| 0.4774 \| \| 1.4203 \| 6.63 \| 3800 \| 1.3357 \| 0.5014 \| 0.4939 \| \| 1.4029 \| 6.98 \| 4000 \| 1.3041 \| 0.5138 \| 0.5080 \| \| 1.3836 \| 7.33 \| 4200 \| 1.2996 \| 0.5153 \| 0.5026 \| \| 1.3682 \| 7.68 \| 4400 \| 1.2885 \| 0.5183 \| 0.5065 \| \| 1.3661 \| 8.03 \| 4600 \| 1.2755 \| 0.5245 \| 0.5152 \| \| 1.3392 \| 8.38 \| 4800 \| 1.2771 \| 0.5231 \| 0.5151 \| \| 1.3477 \| 8.73 \| 5000 \| 1.2642 \| 0.5257 \| 0.5173 \| \| 1.3332 \| 9.08 \| 5200 \| 1.2546 \| 0.5357 \| 0.5257 \| \| 1.3227 \| 9.42 \| 5400 \| 1.2411 \| 0.5363 \| 0.5317 \| \| 1.3048 \| 9.77 \| 5600 \| 1.2315 \| 0.5333 \| 0.5315 \| \| 1.3071 \| 10.12 \| 5800 \| 1.2159 \| 0.5470 \| 0.5413 \| \| 1.2925 \| 10.47 \| 6000 \| 1.1937 \| 0.5575 \| 0.5557 \| \| 1.274 \| 10.82 \| 6200 \| 1.1954 \| 0.5525 \| 0.5405 \| \| 1.2555 \| 11.17 \| 6400 \| 1.1973 \| 0.5570 \| 0.5376 \| \| 1.2539 \| 11.52 \| 6600 \| 1.1798 \| 0.5659 \| 0.5568 \| \| 1.2569 \| 11.87 \| 6800 \| 1.1652 \| 0.5652 \| 0.5551 \| \| 1.2441 \| 12.22 \| 7000 \| 1.1593 \| 0.5680 \| 0.5586 \| \| 1.2274 \| 12.57 \| 7200 \| 1.1594 \| 0.5758 \| 0.5644 \| \| 1.232 \| 12.91 \| 7400 \| 1.1576 \| 0.5676 \| 0.5604 \| \| 1.2214 \| 13.26 \| 7600 \| 1.1409 \| 0.5732 \| 0.5635 \| \| 1.2106 \| 13.61 \| 7800 \| 1.1350 \| 0.5753 \| 0.5673 \| \| 1.2049 \| 13.96 \| 8000 \| 1.1360 \| 0.5757 \| 0.5671 \| \| 1.2026 \| 14.31 \| 8200 \| 1.1227 \| 0.5800 \| 0.5723 \| \| 1.2048 \| 14.66 \| 8400 \| 1.1148 \| 0.5845 \| 0.5755 \| \| 1.1968 \| 15.01 \| 8600 \| 1.1170 \| 0.5797 \| 0.5730 \| \| 1.1996 \| 15.36 \| 8800 \| 1.1114 \| 0.5863 \| 0.5770 \| \| 1.1758 \| 15.71 \| 9000 \| 1.1122 \| 0.5819 \| 0.5766 \| \| 1.1923 \| 16.06 \| 9200 \| 1.1091 \| 0.5861 \| 0.5783 \| \| 1.1735 \| 16.4 \| 9400 \| 1.1096 \| 0.5851 \| 0.5801 \| \| 1.1799 \| 16.75 \| 9600 \| 1.1072 \| 0.5845 \| 0.5782 \| \| 1.1815 \| 17.1 \| 9800 \| 1.1085 \| 0.5853 \| 0.5787 \| \| 1.181 \| 17.45 \| 10000 \| 1.1072 \| 0.5865 \| 0.5802 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_virus_covid-seqsight_4096_512_46M-L8_f", "results": []}]}	mahdibaghbanzadeh/GUE_virus_covid-seqsight_4096_512_46M-L8_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_46M", "region:us" ]	null	2024-04-27T01:17:17+00:00	[]	[]	TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us	GUE\_virus\_covid-seqsight\_4096\_512\_46M-L8\_f ================================================ This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_4096\_512\_46M on the mahdibaghbanzadeh/GUE\_virus\_covid dataset. It achieves the following results on the evaluation set: * Loss: 1.1081 * F1 Score: 0.5885 * Accuracy: 0.5836 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]	[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]
text2text-generation	transformers	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # CS505_COQE_viT5_train_Instruction0_SPAOL_v1 This model is a fine-tuned version of [VietAI/vit5-large](https://huggingface.co/VietAI/vit5-large) on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 20 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.15.2	{"license": "mit", "tags": ["generated_from_trainer"], "base_model": "VietAI/vit5-large", "model-index": [{"name": "CS505_COQE_viT5_train_Instruction0_SPAOL_v1", "results": []}]}	ThuyNT/CS505_COQE_viT5_train_Instruction0_SPAOL_v1	null	[ "transformers", "tensorboard", "safetensors", "t5", "text2text-generation", "generated_from_trainer", "base_model:VietAI/vit5-large", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-27T01:17:27+00:00	[]	[]	TAGS #transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-VietAI/vit5-large #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us	# CS505_COQE_viT5_train_Instruction0_SPAOL_v1 This model is a fine-tuned version of VietAI/vit5-large on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 20 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.15.2	[ "# CS505_COQE_viT5_train_Instruction0_SPAOL_v1\n\nThis model is a fine-tuned version of VietAI/vit5-large on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 20\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]	[ "TAGS\n#transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-VietAI/vit5-large #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# CS505_COQE_viT5_train_Instruction0_SPAOL_v1\n\nThis model is a fine-tuned version of VietAI/vit5-large on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 20\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]
text-generation	transformers	<div align="center"> <img width="260px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/BrQCb95lmEIFz79QAmoNA.png"></div> ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/fJIOPJnY6Ff6fUiSIuMEt.png) <div align="center"> <h1>Advancing Open-source Large Language Models in Medical Domain</h1> </div> <p align="center" style="margin-top: 0px;"> <a href="https://colab.research.google.com/drive/1F5oV20InEYeAJGmBwYF9NM_QhLmjBkKJ?usp=sharing"> <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="OpenChat Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 10px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style=" margin-right: 5px;">Online Demo</span> </a> \| <a href="https://github.com/openlifescience-ai"> <img src="https://github.githubassets.com/assets/GitHub-Mark-ea2971cee799.png" alt="GitHub Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style=" margin-right: 5px;">GitHub</span> </a> \| <a href="#"> <img src="https://github.com/alpayariyak/openchat/blob/master/assets/arxiv-logomark-small-square-border.png?raw=true" alt="ArXiv Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style="margin-right: 5px;">Paper</span> </a> \| <a href="https://discord.gg/A5Fjf5zC69"> <img src="https://cloud.githubusercontent.com/assets/6291467/26705903/96c2d66e-477c-11e7-9f4e-f3c0efe96c9a.png" alt="Discord Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text">Discord</span> </a> </p> ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/KGmRE5w2sepNtwsEu8t7K.jpeg) Introducing OpenBioLLM-70B: A State-of-the-Art Open Source Biomedical Large Language Model OpenBioLLM-70B is an advanced open source language model designed specifically for the biomedical domain. Developed by Saama AI Labs, this model leverages cutting-edge techniques to achieve state-of-the-art performance on a wide range of biomedical tasks. 🏥 Biomedical Specialization: OpenBioLLM-70B is tailored for the unique language and knowledge requirements of the medical and life sciences fields. It was fine-tuned on a vast corpus of high-quality biomedical data, enabling it to understand and generate text with domain-specific accuracy and fluency. 🎓 Superior Performance: With 70 billion parameters, OpenBioLLM-70B outperforms other open source biomedical language models of similar scale. It has also demonstrated better results compared to larger proprietary & open-source models like GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 on biomedical benchmarks. 🧠 Advanced Training Techniques: OpenBioLLM-70B builds upon the powerful foundations of the Meta-Llama-3-70B-Instruct and [Meta-Llama-3-70B-Instruct](meta-llama/Meta-Llama-3-70B-Instruct) models. It incorporates the DPO dataset and fine-tuning recipe along with a custom diverse medical instruction dataset. Key components of the training pipeline include: <div align="center"> <img width="1200px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/oPchsJsEpQoGcGXVbh7YS.png"> </div> - Policy Optimization: [Direct Preference Optimization: Your Language Model is Secretly a Reward Model (DPO)](https://arxiv.org/abs/2305.18290) - Fine-tuning dataset: Custom Medical Instruct dataset (We plan to release a sample training dataset in our upcoming paper; please stay updated) This combination of cutting-edge techniques enables OpenBioLLM-70B to align with key capabilities and preferences for biomedical applications. ⚙️ Release Details: - Model Size: 70 billion parameters - Quantization: Optimized quantized versions available [Here](https://huggingface.co/aaditya/OpenBioLLM-70B-GGUF) - Language(s) (NLP): en - Developed By: [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) from Saama AI Labs - License: Meta-Llama License - Fine-tuned from models: [Meta-Llama-3-70B-Instruct](meta-llama/Meta-Llama-3-70B-Instruct) - Resources for more information: - Paper: Coming soon The model can be fine-tuned for more specialized tasks and datasets as needed. OpenBioLLM-70B represents an important step forward in democratizing advanced language AI for the biomedical community. By leveraging state-of-the-art architectures and training techniques from leading open source efforts like Llama-3, we have created a powerful tool to accelerate innovation and discovery in healthcare and the life sciences. We are excited to share OpenBioLLM-70B with researchers and developers around the world. ### Use with transformers Important: Please use the exact chat template provided by Llama-3 instruct version. Otherwise there will be a degradation in the performance. The model output can be verbose in rare cases. Please consider setting temperature = 0 to make this happen less. See the snippet below for usage with Transformers: ```python import transformers import torch model_id = "aaditya/OpenBioLLM-Llama3-70B" pipeline = transformers.pipeline( "text-generation", model=model_id, model_kwargs={"torch_dtype": torch.bfloat16}, device="auto", ) messages = [ {"role": "system", "content": "You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience. Your name is OpenBioLLM, and you were developed by Saama AI Labs. who's willing to help answer the user's query with explanation. In your explanation, leverage your deep medical expertise such as relevant anatomical structures, physiological processes, diagnostic criteria, treatment guidelines, or other pertinent medical concepts. Use precise medical terminology while still aiming to make the explanation clear and accessible to a general audience."}, {"role": "user", "content": "How can i split a 3mg or 4mg waefin pill so i can get a 2.5mg pill?"}, ] prompt = pipeline.tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) terminators = [ pipeline.tokenizer.eos_token_id, pipeline.tokenizer.convert_tokens_to_ids("<\|eot_id\|>") ] outputs = pipeline( prompt, max_new_tokens=256, eos_token_id=terminators, do_sample=True, temperature=0.0, top_p=0.9, ) print(outputs[0]["generated_text"][len(prompt):]) ``` ## Training procedure ### Training hyperparameters <details> <summary>Click to see details</summary> - learning_rate: 0.0002 - lr_scheduler: cosine - train_batch_size: 12 - eval_batch_size: 8 - GPU: H100 80GB SXM5 - num_devices: 8 - optimizer: adamw_bnb_8bit - lr_scheduler_warmup_steps: 100 - num_epochs: 4 </details> ### Peft hyperparameters <details> <summary>Click to see details</summary> - adapter: qlora - lora_r: 128 - lora_alpha: 256 - lora_dropout: 0.05 - lora_target_linear: true -lora_target_modules: - q_proj - v_proj - k_proj - o_proj - gate_proj - down_proj - up_proj </details> ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2+cu121 - Datasets 2.18.0 - Tokenizers 0.15.1 - Axolotl - Lm harness for evaluation # Benchmark Results 🔥 OpenBioLLM-70B demonstrates superior performance compared to larger models, such as GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 across 9 diverse biomedical datasets, achieving state-of-the-art results with an average score of 86.06%, despite having a significantly smaller parameter count. The model's strong performance in domain-specific tasks, such as Clinical KG, Medical Genetics, and PubMedQA, highlights its ability to effectively capture and apply biomedical knowledge. 🚨 The GPT-4, Med-PaLM-1, and Med-PaLM-2 results are taken from their official papers. Since Med-PaLM doesn't provide zero-shot accuracy, we are using 5-shot accuracy from their paper for comparison. All results presented are in the zero-shot setting, except for Med-PaLM-2 and Med-PaLM-1, which use 5-shot accuracy. \| \| Clinical KG \| Medical Genetics \| Anatomy \| Pro Medicine \| College Biology \| College Medicine \| MedQA 4 opts \| PubMedQA \| MedMCQA \| Avg \| \|--------------------\|-------------\|------------------\|---------\|--------------\|-----------------\|------------------\|--------------\|----------\|---------\|-------\| \| OpenBioLLM-70B \| 92.93 \| 93.197 \| 83.904 \| 93.75 \| 93.827 \| 85.749 \| 78.162 \| 78.97 \| 74.014 \| 86.05588 \| \| Med-PaLM-2 (5-shot) \| 88.3 \| 90 \| 77.8 \| 95.2 \| 94.4 \| 80.9 \| 79.7 \| 79.2 \| 71.3 \| 84.08 \| \| GPT-4 \| 86.04 \| 91 \| 80 \| 93.01 \| 95.14 \| 76.88 \| 78.87 \| 75.2 \| 69.52 \| 82.85 \| \| Med-PaLM-1 (Flan-PaLM, 5-shot) \| 80.4 \| 75 \| 63.7 \| 83.8 \| 88.9 \| 76.3 \| 67.6 \| 79 \| 57.6 \| 74.7 \| \| OpenBioLLM-8B \| 76.101 \| 86.1 \| 69.829 \| 78.21 \| 84.213 \| 68.042 \| 58.993 \| 74.12 \| 56.913 \| 72.502 \| \| Gemini-1.0 \| 76.7 \| 75.8 \| 66.7 \| 77.7 \| 88 \| 69.2 \| 58 \| 70.7 \| 54.3 \| 70.79 \| \| GPT-3.5 Turbo 1106 \| 74.71 \| 74 \| 72.79 \| 72.79 \| 72.91 \| 64.73 \| 57.71 \| 72.66 \| 53.79 \| 66 \| \| Meditron-70B \| 66.79 \| 69 \| 53.33 \| 71.69 \| 76.38 \| 63 \| 57.1 \| 76.6 \| 46.85 \| 64.52 \| \| gemma-7b \| 69.81 \| 70 \| 59.26 \| 66.18 \| 79.86 \| 60.12 \| 47.21 \| 76.2 \| 48.96 \| 64.18 \| \| Mistral-7B-v0.1 \| 68.68 \| 71 \| 55.56 \| 68.38 \| 68.06 \| 59.54 \| 50.82 \| 75.4 \| 48.2 \| 62.85 \| \| Apollo-7B \| 62.26 \| 72 \| 61.48 \| 69.12 \| 70.83 \| 55.49 \| 55.22 \| 39.8 \| 53.77 \| 60 \| \| MedAlpaca-7b \| 57.36 \| 69 \| 57.04 \| 67.28 \| 65.28 \| 54.34 \| 41.71 \| 72.8 \| 37.51 \| 58.03 \| \| BioMistral-7B \| 59.9 \| 64 \| 56.5 \| 60.4 \| 59 \| 54.7 \| 50.6 \| 77.5 \| 48.1 \| 57.3 \| \| AlpaCare-llama2-7b \| 49.81 \| 49 \| 45.92 \| 33.82 \| 50 \| 43.35 \| 29.77 \| 72.2 \| 34.42 \| 45.36 \| \| ClinicalGPT \| 30.56 \| 27 \| 30.37 \| 19.48 \| 25 \| 24.27 \| 26.08 \| 63.8 \| 28.18 \| 30.52 \| <div align="center"> <img width="1600px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/_SzdcJSBjZyo8RS1bTEkP.png"> </div> ## Detailed Medical Subjectwise accuracy ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/UXF-V0col0Z0sS6BGPBkE.png) # Use Cases & Examples 🚨 Below results are from the quantized version of OpenBioLLM-70B # Summarize Clinical Notes OpenBioLLM-70B can efficiently analyze and summarize complex clinical notes, EHR data, and discharge summaries, extracting key information and generating concise, structured summaries ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/xdwdBgOxNi_TfML0hKlI8.png) # Answer Medical Questions OpenBioLLM-70B can provide answers to a wide range of medical questions. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/zO95GlwOQEZqCKQF69mE6.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/OKBczKw7gWeW5xsuDpc27.png) <details> <summary>Click to see details</summary> ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/eJGHT5khppYvJb8fQ-YW4.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/Cnbwrqa_-ORHRuNRC2P6Y.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/J9DhdcvukAc9mnnW9fj2C.png) </details> # Clinical Entity Recognition OpenBioLLM-70B can perform advanced clinical entity recognition by identifying and extracting key medical concepts, such as diseases, symptoms, medications, procedures, and anatomical structures, from unstructured clinical text. By leveraging its deep understanding of medical terminology and context, the model can accurately annotate and categorize clinical entities, enabling more efficient information retrieval, data analysis, and knowledge discovery from electronic health records, research articles, and other biomedical text sources. This capability can support various downstream applications, such as clinical decision support, pharmacovigilance, and medical research. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/_69BW4k9LVABFwtxixL45.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/DKy5wYCoPhoPPUc1-x8_J.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/7WD9zCCBZT4-4XlfnIQjl.png) # Biomarkers Extraction ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/ZttoM4AiteT7gFYVhjIpN.png) # Classification OpenBioLLM-70B can perform various biomedical classification tasks, such as disease prediction, sentiment analysis, medical document categorization ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/Bf5MW1d75qT-1F_TR_hC0.png) # De-Identification OpenBioLLM-70B can detect and remove personally identifiable information (PII) from medical records, ensuring patient privacy and compliance with data protection regulations like HIPAA. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/hKX4kzm--Tw5bj6K78msy.png) Advisory Notice! While OpenBioLLM-70B leverages high-quality data sources, its outputs may still contain inaccuracies, biases, or misalignments that could pose risks if relied upon for medical decision-making without further testing and refinement. The model's performance has not yet been rigorously evaluated in randomized controlled trials or real-world healthcare environments. Therefore, we strongly advise against using OpenBioLLM-70B for any direct patient care, clinical decision support, or other professional medical purposes at this time. Its use should be limited to research, development, and exploratory applications by qualified individuals who understand its limitations. OpenBioLLM-70B is intended solely as a research tool to assist healthcare professionals and should never be considered a replacement for the professional judgment and expertise of a qualified medical doctor. Appropriately adapting and validating OpenBioLLM-70B for specific medical use cases would require significant additional work, potentially including: - Thorough testing and evaluation in relevant clinical scenarios - Alignment with evidence-based guidelines and best practices - Mitigation of potential biases and failure modes - Integration with human oversight and interpretation - Compliance with regulatory and ethical standards Always consult a qualified healthcare provider for personal medical needs. # Citation If you find OpenBioLLM-70B & 8B useful in your work, please cite the model as follows: ``` @misc{OpenBioLLMs, author = {Ankit Pal, Malaikannan Sankarasubbu}, title = {OpenBioLLMs: Advancing Open-Source Large Language Models for Healthcare and Life Sciences}, year = {2024}, publisher = {Hugging Face}, journal = {Hugging Face repository}, howpublished = {\url{https://huggingface.co/aaditya/OpenBioLLM-Llama3-70B}} } ``` The accompanying paper is currently in progress and will be released soon. <div align="center"> <h2> 💌 Contact </h2> </div> We look forward to hearing you and collaborating on this exciting project! Contributors:** - [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) [aadityaura at gmail dot com] - Saama AI Labs - Note: I am looking for a funded PhD opportunity, especially if it fits my Responsible Generative AI, Multimodal LLMs, Geometric Deep Learning, and Healthcare AI skillset. # References We thank the [Meta Team](meta-llama/Meta-Llama-3-70B-Instruct) for their amazing models! Result sources - [1] GPT-4 [Capabilities of GPT-4 on Medical Challenge Problems] (https://arxiv.org/abs/2303.13375) - [2] Med-PaLM-1 [Large Language Models Encode Clinical Knowledge](https://arxiv.org/abs/2212.13138) - [3] Med-PaLM-2 [Towards Expert-Level Medical Question Answering with Large Language Models](https://arxiv.org/abs/2305.09617) - [4] Gemini-1.0 [Gemini Goes to Med School](https://arxiv.org/abs/2402.07023)	{"language": ["en"], "license": "llama3", "tags": ["llama-3", "llama", "Mixtral", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "distillation"], "base_model": "meta-llama/Meta-Llama-3-70B-Instruct", "widget": [{"example_title": "OpenBioLLM-70B", "messages": [{"role": "system", "content": "You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience."}, {"role": "user", "content": "How long does it take for newborn jaundice to go away?"}], "output": {"text": "Newborn jaundice, also known as neonatal jaundice, is a common condition in newborns where the yellowing of the skin and eyes occurs due to an elevated level of bilirubin in the blood. Bilirubin is a yellow pigment that forms when red blood cells break down. In most cases, newborn jaundice resolves on its own without any specific treatment.\nThe duration of newborn jaundice can vary depending on several factors such as the underlying cause, gestational age at birth, and individual variations in bilirubin metabolism. Here are some general guidelines:\n1. Physiological jaundice: This is the most common type of newborn jaundice and usually appears within 24-72 hours after birth. It tends to peak between the second and fifth day of life and gradually improves over the next week or two. By the time the baby is one week old, the jaundice should have mostly resolved. 2. Breast milk jaundice: This type of jaundice occurs in breastfed babies and may appear later than physiological jaundice, typically between the fifth and fourteenth day of life. It tends to persist for a longer duration but usually resolves within six weeks after birth. 3. Pathological jaundice: This type of jaundice is less common and occurs due to an underlying medical condition that affects bilirubin metabolism or liver function. The duration of pathological jaundice depends on the specific cause and may require treatment.\nIt's important for parents to monitor their newborn's jaundice closely and seek medical advice if the jaundice progresses rapidly, becomes severe, or is accompanied by other symptoms such as poor feeding, lethargy, or excessive sleepiness. In these cases, further evaluation and management may be necessary. Remember that each baby is unique, and the timing of jaundice resolution can vary. If you have concerns about your newborn's jaundice, it's always best to consult with a healthcare professional for personalized advice and guidance."}}], "model-index": [{"name": "OpenBioLLM-70B", "results": []}]}	LoneStriker/OpenBioLLM-Llama3-70B-3.5bpw-h6-exl2	null	[ "transformers", "pytorch", "llama", "text-generation", "llama-3", "Mixtral", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "distillation", "conversational", "en", "arxiv:2305.18290", "arxiv:2303.13375", "arxiv:2212.13138", "arxiv:2305.09617", "arxiv:2402.07023", "base_model:meta-llama/Meta-Llama-3-70B-Instruct", "license:llama3", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-27T01:18:25+00:00	[ "2305.18290", "2303.13375", "2212.13138", "2305.09617", "2402.07023" ]	[ "en" ]	TAGS #transformers #pytorch #llama #text-generation #llama-3 #Mixtral #instruct #finetune #chatml #DPO #RLHF #gpt4 #distillation #conversational #en #arxiv-2305.18290 #arxiv-2303.13375 #arxiv-2212.13138 #arxiv-2305.09617 #arxiv-2402.07023 #base_model-meta-llama/Meta-Llama-3-70B-Instruct #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us	![](URL <p>!image/png</p> <div align=) Advancing Open-source Large Language Models in Medical Domain ============================================================= Online Demo \| GitHub \| [![](URL alt=)](#) \| Discord !image/jpeg Introducing OpenBioLLM-70B: A State-of-the-Art Open Source Biomedical Large Language Model OpenBioLLM-70B is an advanced open source language model designed specifically for the biomedical domain. Developed by Saama AI Labs, this model leverages cutting-edge techniques to achieve state-of-the-art performance on a wide range of biomedical tasks. Biomedical Specialization: OpenBioLLM-70B is tailored for the unique language and knowledge requirements of the medical and life sciences fields. It was fine-tuned on a vast corpus of high-quality biomedical data, enabling it to understand and generate text with domain-specific accuracy and fluency. Superior Performance: With 70 billion parameters, OpenBioLLM-70B outperforms other open source biomedical language models of similar scale. It has also demonstrated better results compared to larger proprietary & open-source models like GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 on biomedical benchmarks. Advanced Training Techniques: OpenBioLLM-70B builds upon the powerful foundations of the Meta-Llama-3-70B-Instruct and Meta-Llama-3-70B-Instruct models. It incorporates the DPO dataset and fine-tuning recipe along with a custom diverse medical instruction dataset. Key components of the training pipeline include: ![](URL </div> <ul> <li>Policy Optimization: Direct Preference Optimization: Your Language Model is Secretly a Reward Model (DPO)</li> <li>Fine-tuning dataset: Custom Medical Instruct dataset (We plan to release a sample training dataset in our upcoming paper; please stay updated)</li> </ul> <p>This combination of cutting-edge techniques enables OpenBioLLM-70B to align with key capabilities and preferences for biomedical applications.</p> <p>️ Release Details:</p> <ul> <li>Model Size: 70 billion parameters</li> <li>Quantization: Optimized quantized versions available Here</li> <li>Language(s) (NLP): en</li> <li>Developed By: Ankit Pal (Aaditya Ura) from Saama AI Labs</li> <li>License: Meta-Llama License</li> <li>Fine-tuned from models: Meta-Llama-3-70B-Instruct</li> <li>Resources for more information: <ul> <li>Paper: Coming soon</li> </ul> </li> </ul> <p>The model can be fine-tuned for more specialized tasks and datasets as needed.</p> <p>OpenBioLLM-70B represents an important step forward in democratizing advanced language AI for the biomedical community. By leveraging state-of-the-art architectures and training techniques from leading open source efforts like Llama-3, we have created a powerful tool to accelerate innovation and discovery in healthcare and the life sciences.</p> <p>We are excited to share OpenBioLLM-70B with researchers and developers around the world.</p> <h3>Use with transformers</h3> <p>Important: Please use the exact chat template provided by Llama-3 instruct version. Otherwise there will be a degradation in the performance. The model output can be verbose in rare cases. Please consider setting temperature = 0 to make this happen less.</p> <p>See the snippet below for usage with Transformers:</p> <h2>Training procedure</h2> <h3>Training hyperparameters</h3> <details> <summary>Click to see details</summary> <ul> <li>learning_rate: 0.0002</li> <li>lr_scheduler: cosine</li> <li>train_batch_size: 12</li> <li>eval_batch_size: 8</li> <li>GPU: H100 80GB SXM5</li> <li>num_devices: 8</li> <li>optimizer: adamw_bnb_8bit</li> <li>lr_scheduler_warmup_steps: 100</li> <li>num_epochs: 4</li> </ul> </details> <h3>Peft hyperparameters</h3> <details> <summary>Click to see details</summary> <ul> <li>adapter: qlora</li> <li>lora_r: 128</li> <li>lora_alpha: 256</li> <li>lora_dropout: 0.05</li> <li>lora_target_linear: true</li> </ul> <p>-lora_target_modules:</p> <ul> <li>q_proj</li> <li>v_proj</li> <li>k_proj</li> <li>o_proj</li> <li>gate_proj</li> <li>down_proj</li> <li>up_proj</li> </ul> </details> <h3>Training results</h3> <h3>Framework versions</h3> <ul> <li>Transformers 4.39.3</li> <li>Pytorch 2.1.2+cu121</li> <li>Datasets 2.18.0</li> <li>Tokenizers 0.15.1</li> <li>Axolotl</li> <li>Lm harness for evaluation</li> </ul> <h1>Benchmark Results</h1> <p>OpenBioLLM-70B demonstrates superior performance compared to larger models, such as GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 across 9 diverse biomedical datasets, achieving state-of-the-art results with an average score of 86.06%, despite having a significantly smaller parameter count. The model's strong performance in domain-specific tasks, such as Clinical KG, Medical Genetics, and PubMedQA, highlights its ability to effectively capture and apply biomedical knowledge.</p> <p>The GPT-4, Med-PaLM-1, and Med-PaLM-2 results are taken from their official papers. Since Med-PaLM doesn't provide zero-shot accuracy, we are using 5-shot accuracy from their paper for comparison. All results presented are in the zero-shot setting, except for Med-PaLM-2 and Med-PaLM-1, which use 5-shot accuracy.</p> <p></p> <div align=) ![](URL </div> <h2>Detailed Medical Subjectwise accuracy</h2> <p>!image/png</p> <h1>Use Cases & Examples</h1> <p>Below results are from the quantized version of OpenBioLLM-70B</p> <h1>Summarize Clinical Notes</h1> <p>OpenBioLLM-70B can efficiently analyze and summarize complex clinical notes, EHR data, and discharge summaries, extracting key information and generating concise, structured summaries</p> <p>!image/png</p> <h1>Answer Medical Questions</h1> <p>OpenBioLLM-70B can provide answers to a wide range of medical questions.</p> <p>!image/png !image/png</p> <details> <summary>Click to see details</summary> <p>!image/png !image/png !image/png</p> </details> <h1>Clinical Entity Recognition</h1> <p>OpenBioLLM-70B can perform advanced clinical entity recognition by identifying and extracting key medical concepts, such as diseases, symptoms, medications, procedures, and anatomical structures, from unstructured clinical text. By leveraging its deep understanding of medical terminology and context, the model can accurately annotate and categorize clinical entities, enabling more efficient information retrieval, data analysis, and knowledge discovery from electronic health records, research articles, and other biomedical text sources. This capability can support various downstream applications, such as clinical decision support, pharmacovigilance, and medical research.</p> <p>!image/png !image/png !image/png</p> <h1>Biomarkers Extraction</h1> <p>!image/png</p> <h1>Classification</h1> <p>OpenBioLLM-70B can perform various biomedical classification tasks, such as disease prediction, sentiment analysis, medical document categorization</p> <p>!image/png</p> <h1>De-Identification</h1> <p>OpenBioLLM-70B can detect and remove personally identifiable information (PII) from medical records, ensuring patient privacy and compliance with data protection regulations like HIPAA.</p> <p>!image/png</p> <p>Advisory Notice!</p> <p>While OpenBioLLM-70B leverages high-quality data sources, its outputs may still contain inaccuracies, biases, or misalignments that could pose risks if relied upon for medical decision-making without further testing and refinement. The model's performance has not yet been rigorously evaluated in randomized controlled trials or real-world healthcare environments.</p> <p>Therefore, we strongly advise against using OpenBioLLM-70B for any direct patient care, clinical decision support, or other professional medical purposes at this time. Its use should be limited to research, development, and exploratory applications by qualified individuals who understand its limitations. OpenBioLLM-70B is intended solely as a research tool to assist healthcare professionals and should never be considered a replacement for the professional judgment and expertise of a qualified medical doctor.</p> <p>Appropriately adapting and validating OpenBioLLM-70B for specific medical use cases would require significant additional work, potentially including:</p> <ul> <li>Thorough testing and evaluation in relevant clinical scenarios</li> <li>Alignment with evidence-based guidelines and best practices</li> <li>Mitigation of potential biases and failure modes</li> <li>Integration with human oversight and interpretation</li> <li>Compliance with regulatory and ethical standards</li> </ul> <p>Always consult a qualified healthcare provider for personal medical needs.</p> <p>If you find OpenBioLLM-70B & 8B useful in your work, please cite the model as follows:</p> <p>The accompanying paper is currently in progress and will be released soon.</p> <div align=) Contact -------- We look forward to hearing you and collaborating on this exciting project! Contributors: * Ankit Pal (Aaditya Ura) [aadityaura at gmail dot com] * Saama AI Labs * Note: I am looking for a funded PhD opportunity, especially if it fits my Responsible Generative AI, Multimodal LLMs, Geometric Deep Learning, and Healthcare AI skillset. References ========== We thank the Meta Team for their amazing models! Result sources * [1] GPT-4 [Capabilities of GPT-4 on Medical Challenge Problems] (URL * [2] Med-PaLM-1 Large Language Models Encode Clinical Knowledge * [3] Med-PaLM-2 Towards Expert-Level Medical Question Answering with Large Language Models * [4] Gemini-1.0 Gemini Goes to Med School	[]	[ "TAGS\n#transformers #pytorch #llama #text-generation #llama-3 #Mixtral #instruct #finetune #chatml #DPO #RLHF #gpt4 #distillation #conversational #en #arxiv-2305.18290 #arxiv-2303.13375 #arxiv-2212.13138 #arxiv-2305.09617 #arxiv-2402.07023 #base_model-meta-llama/Meta-Llama-3-70B-Instruct #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n" ]
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # llama2-envi-tran-10000 This model is a fine-tuned version of [unsloth/llama-2-7b-bnb-4bit](https://huggingface.co/unsloth/llama-2-7b-bnb-4bit) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.0906 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0002 - train_batch_size: 8 - eval_batch_size: 4 - seed: 3407 - gradient_accumulation_steps: 4 - total_train_batch_size: 32 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 5 - num_epochs: 5 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| 1.1238 \| 0.33 \| 104 \| 0.9544 \| \| 1.0108 \| 0.67 \| 208 \| 0.9355 \| \| 1.0058 \| 1.0 \| 312 \| 0.9277 \| \| 0.9212 \| 1.33 \| 416 \| 0.9363 \| \| 0.9255 \| 1.66 \| 520 \| 0.9323 \| \| 0.9222 \| 2.0 \| 624 \| 0.9275 \| \| 0.7975 \| 2.33 \| 728 \| 0.9634 \| \| 0.802 \| 2.66 \| 832 \| 0.9622 \| \| 0.7979 \| 3.0 \| 936 \| 0.9654 \| \| 0.6747 \| 3.33 \| 1040 \| 1.0305 \| \| 0.6646 \| 3.66 \| 1144 \| 1.0320 \| \| 0.6697 \| 3.99 \| 1248 \| 1.0257 \| \| 0.5873 \| 4.33 \| 1352 \| 1.0879 \| \| 0.5792 \| 4.66 \| 1456 \| 1.0902 \| \| 0.5819 \| 4.99 \| 1560 \| 1.0906 \| ### Framework versions - PEFT 0.10.0 - Transformers 4.39.3 - Pytorch 2.2.2+cu121 - Datasets 2.16.0 - Tokenizers 0.15.2	{"license": "apache-2.0", "library_name": "peft", "tags": ["trl", "sft", "unsloth", "generated_from_trainer"], "base_model": "unsloth/llama-2-7b-bnb-4bit", "model-index": [{"name": "llama2-envi-tran-10000", "results": []}]}	mob2711/llama2-envi-tran-10000	null	[ "peft", "tensorboard", "safetensors", "trl", "sft", "unsloth", "generated_from_trainer", "base_model:unsloth/llama-2-7b-bnb-4bit", "license:apache-2.0", "region:us" ]	null	2024-04-27T01:22:19+00:00	[]	[]	TAGS #peft #tensorboard #safetensors #trl #sft #unsloth #generated_from_trainer #base_model-unsloth/llama-2-7b-bnb-4bit #license-apache-2.0 #region-us	llama2-envi-tran-10000 ====================== This model is a fine-tuned version of unsloth/llama-2-7b-bnb-4bit on the None dataset. It achieves the following results on the evaluation set: * Loss: 1.0906 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0002 * train\_batch\_size: 8 * eval\_batch\_size: 4 * seed: 3407 * gradient\_accumulation\_steps: 4 * total\_train\_batch\_size: 32 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: cosine * lr\_scheduler\_warmup\_steps: 5 * num\_epochs: 5 * mixed\_precision\_training: Native AMP ### Training results ### Framework versions * PEFT 0.10.0 * Transformers 4.39.3 * Pytorch 2.2.2+cu121 * Datasets 2.16.0 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 4\n* seed: 3407\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 32\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\n* lr\\_scheduler\\_warmup\\_steps: 5\n* num\\_epochs: 5\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.39.3\n* Pytorch 2.2.2+cu121\n* Datasets 2.16.0\n* Tokenizers 0.15.2" ]	[ "TAGS\n#peft #tensorboard #safetensors #trl #sft #unsloth #generated_from_trainer #base_model-unsloth/llama-2-7b-bnb-4bit #license-apache-2.0 #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 4\n* seed: 3407\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 32\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\n* lr\\_scheduler\\_warmup\\_steps: 5\n* num\\_epochs: 5\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.39.3\n* Pytorch 2.2.2+cu121\n* Datasets 2.16.0\n* Tokenizers 0.15.2" ]
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_virus_covid-seqsight_4096_512_46M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_virus_covid](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_virus_covid) dataset. It achieves the following results on the evaluation set: - Loss: 0.9287 - F1 Score: 0.6412 - Accuracy: 0.6377 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 2.1803 \| 0.35 \| 200 \| 2.1724 \| 0.1376 \| 0.1585 \| \| 2.1374 \| 0.7 \| 400 \| 2.0178 \| 0.2202 \| 0.2345 \| \| 1.9484 \| 1.05 \| 600 \| 1.8007 \| 0.2992 \| 0.3036 \| \| 1.7811 \| 1.4 \| 800 \| 1.6615 \| 0.3624 \| 0.3585 \| \| 1.6659 \| 1.75 \| 1000 \| 1.5691 \| 0.3986 \| 0.3904 \| \| 1.6027 \| 2.09 \| 1200 \| 1.5203 \| 0.4294 \| 0.4277 \| \| 1.5534 \| 2.44 \| 1400 \| 1.4686 \| 0.4508 \| 0.4411 \| \| 1.5018 \| 2.79 \| 1600 \| 1.4101 \| 0.4675 \| 0.4615 \| \| 1.4466 \| 3.14 \| 1800 \| 1.3581 \| 0.4899 \| 0.4825 \| \| 1.4037 \| 3.49 \| 2000 \| 1.3517 \| 0.5056 \| 0.4869 \| \| 1.377 \| 3.84 \| 2200 \| 1.3013 \| 0.5177 \| 0.5086 \| \| 1.3263 \| 4.19 \| 2400 \| 1.2510 \| 0.5357 \| 0.5213 \| \| 1.3028 \| 4.54 \| 2600 \| 1.2173 \| 0.5464 \| 0.5419 \| \| 1.2795 \| 4.89 \| 2800 \| 1.1947 \| 0.5545 \| 0.5496 \| \| 1.2464 \| 5.24 \| 3000 \| 1.1615 \| 0.5598 \| 0.5533 \| \| 1.2267 \| 5.58 \| 3200 \| 1.1412 \| 0.5649 \| 0.5616 \| \| 1.1977 \| 5.93 \| 3400 \| 1.1200 \| 0.5797 \| 0.5745 \| \| 1.1765 \| 6.28 \| 3600 \| 1.1011 \| 0.5797 \| 0.5772 \| \| 1.1565 \| 6.63 \| 3800 \| 1.0822 \| 0.5955 \| 0.5883 \| \| 1.1371 \| 6.98 \| 4000 \| 1.0718 \| 0.5937 \| 0.5913 \| \| 1.1211 \| 7.33 \| 4200 \| 1.0479 \| 0.6054 \| 0.6015 \| \| 1.0994 \| 7.68 \| 4400 \| 1.0352 \| 0.6091 \| 0.6043 \| \| 1.1013 \| 8.03 \| 4600 \| 1.0245 \| 0.6073 \| 0.6066 \| \| 1.0758 \| 8.38 \| 4800 \| 1.0250 \| 0.6050 \| 0.6031 \| \| 1.078 \| 8.73 \| 5000 \| 1.0151 \| 0.6113 \| 0.6070 \| \| 1.0639 \| 9.08 \| 5200 \| 1.0008 \| 0.6213 \| 0.6143 \| \| 1.0561 \| 9.42 \| 5400 \| 0.9956 \| 0.6152 \| 0.6144 \| \| 1.0403 \| 9.77 \| 5600 \| 0.9815 \| 0.6249 \| 0.6214 \| \| 1.0424 \| 10.12 \| 5800 \| 0.9702 \| 0.6322 \| 0.6296 \| \| 1.0282 \| 10.47 \| 6000 \| 0.9714 \| 0.6280 \| 0.6233 \| \| 1.016 \| 10.82 \| 6200 \| 0.9732 \| 0.6329 \| 0.6233 \| \| 1.0003 \| 11.17 \| 6400 \| 0.9658 \| 0.6333 \| 0.6260 \| \| 0.9984 \| 11.52 \| 6600 \| 0.9598 \| 0.6355 \| 0.6270 \| \| 1.0111 \| 11.87 \| 6800 \| 0.9515 \| 0.6374 \| 0.6307 \| \| 0.9989 \| 12.22 \| 7000 \| 0.9558 \| 0.6380 \| 0.6304 \| \| 0.9844 \| 12.57 \| 7200 \| 0.9471 \| 0.6473 \| 0.6359 \| \| 0.9938 \| 12.91 \| 7400 \| 0.9502 \| 0.6389 \| 0.6315 \| \| 0.9856 \| 13.26 \| 7600 \| 0.9465 \| 0.6386 \| 0.6295 \| \| 0.9793 \| 13.61 \| 7800 \| 0.9420 \| 0.6399 \| 0.6309 \| \| 0.9789 \| 13.96 \| 8000 \| 0.9383 \| 0.6436 \| 0.6387 \| \| 0.9654 \| 14.31 \| 8200 \| 0.9317 \| 0.6444 \| 0.6380 \| \| 0.9687 \| 14.66 \| 8400 \| 0.9353 \| 0.6449 \| 0.6370 \| \| 0.9773 \| 15.01 \| 8600 \| 0.9351 \| 0.6430 \| 0.6386 \| \| 0.9756 \| 15.36 \| 8800 \| 0.9294 \| 0.6461 \| 0.6404 \| \| 0.9526 \| 15.71 \| 9000 \| 0.9306 \| 0.6453 \| 0.6406 \| \| 0.9682 \| 16.06 \| 9200 \| 0.9280 \| 0.6466 \| 0.6404 \| \| 0.959 \| 16.4 \| 9400 \| 0.9295 \| 0.6447 \| 0.6413 \| \| 0.9609 \| 16.75 \| 9600 \| 0.9266 \| 0.6493 \| 0.6435 \| \| 0.961 \| 17.1 \| 9800 \| 0.9272 \| 0.6478 \| 0.6419 \| \| 0.9618 \| 17.45 \| 10000 \| 0.9274 \| 0.6472 \| 0.6416 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_virus_covid-seqsight_4096_512_46M-L32_f", "results": []}]}	mahdibaghbanzadeh/GUE_virus_covid-seqsight_4096_512_46M-L32_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_46M", "region:us" ]	null	2024-04-27T01:23:35+00:00	[]	[]	TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us	GUE\_virus\_covid-seqsight\_4096\_512\_46M-L32\_f ================================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_4096\_512\_46M on the mahdibaghbanzadeh/GUE\_virus\_covid dataset. It achieves the following results on the evaluation set: * Loss: 0.9287 * F1 Score: 0.6412 * Accuracy: 0.6377 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]	[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_prom_prom_300_tata-seqsight_8192_512_30M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_8192_512_30M](https://huggingface.co/mahdibaghbanzadeh/seqsight_8192_512_30M) on the [mahdibaghbanzadeh/GUE_prom_prom_300_tata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_300_tata) dataset. It achieves the following results on the evaluation set: - Loss: 0.4320 - F1 Score: 0.8043 - Accuracy: 0.8042 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:------:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.5915 \| 5.13 \| 200 \| 0.5190 \| 0.7535 \| 0.7569 \| \| 0.4672 \| 10.26 \| 400 \| 0.4808 \| 0.8027 \| 0.8026 \| \| 0.4394 \| 15.38 \| 600 \| 0.4687 \| 0.8043 \| 0.8042 \| \| 0.4249 \| 20.51 \| 800 \| 0.4618 \| 0.8027 \| 0.8026 \| \| 0.4111 \| 25.64 \| 1000 \| 0.4633 \| 0.8027 \| 0.8026 \| \| 0.3977 \| 30.77 \| 1200 \| 0.4591 \| 0.7960 \| 0.7961 \| \| 0.3912 \| 35.9 \| 1400 \| 0.4620 \| 0.7910 \| 0.7912 \| \| 0.3805 \| 41.03 \| 1600 \| 0.4727 \| 0.7970 \| 0.7977 \| \| 0.3741 \| 46.15 \| 1800 \| 0.4665 \| 0.7926 \| 0.7928 \| \| 0.3649 \| 51.28 \| 2000 \| 0.4732 \| 0.7929 \| 0.7928 \| \| 0.3586 \| 56.41 \| 2200 \| 0.4765 \| 0.8044 \| 0.8042 \| \| 0.3517 \| 61.54 \| 2400 \| 0.4861 \| 0.8043 \| 0.8042 \| \| 0.3458 \| 66.67 \| 2600 \| 0.4956 \| 0.7976 \| 0.7977 \| \| 0.3372 \| 71.79 \| 2800 \| 0.4924 \| 0.7978 \| 0.7977 \| \| 0.3364 \| 76.92 \| 3000 \| 0.4950 \| 0.7913 \| 0.7912 \| \| 0.3278 \| 82.05 \| 3200 \| 0.5055 \| 0.8027 \| 0.8026 \| \| 0.3257 \| 87.18 \| 3400 \| 0.5066 \| 0.7945 \| 0.7945 \| \| 0.3199 \| 92.31 \| 3600 \| 0.5064 \| 0.7995 \| 0.7993 \| \| 0.3145 \| 97.44 \| 3800 \| 0.5131 \| 0.7946 \| 0.7945 \| \| 0.3079 \| 102.56 \| 4000 \| 0.5167 \| 0.7961 \| 0.7961 \| \| 0.3039 \| 107.69 \| 4200 \| 0.5190 \| 0.7962 \| 0.7961 \| \| 0.3005 \| 112.82 \| 4400 \| 0.5159 \| 0.7995 \| 0.7993 \| \| 0.299 \| 117.95 \| 4600 \| 0.5180 \| 0.7962 \| 0.7961 \| \| 0.2902 \| 123.08 \| 4800 \| 0.5274 \| 0.7962 \| 0.7961 \| \| 0.2866 \| 128.21 \| 5000 \| 0.5370 \| 0.7930 \| 0.7928 \| \| 0.2893 \| 133.33 \| 5200 \| 0.5397 \| 0.7895 \| 0.7896 \| \| 0.2819 \| 138.46 \| 5400 \| 0.5363 \| 0.7977 \| 0.7977 \| \| 0.28 \| 143.59 \| 5600 \| 0.5435 \| 0.7881 \| 0.7879 \| \| 0.2805 \| 148.72 \| 5800 \| 0.5464 \| 0.7977 \| 0.7977 \| \| 0.2758 \| 153.85 \| 6000 \| 0.5409 \| 0.7929 \| 0.7928 \| \| 0.2747 \| 158.97 \| 6200 \| 0.5477 \| 0.7913 \| 0.7912 \| \| 0.2723 \| 164.1 \| 6400 \| 0.5517 \| 0.7961 \| 0.7961 \| \| 0.2702 \| 169.23 \| 6600 \| 0.5529 \| 0.7913 \| 0.7912 \| \| 0.2657 \| 174.36 \| 6800 \| 0.5580 \| 0.7897 \| 0.7896 \| \| 0.2628 \| 179.49 \| 7000 \| 0.5535 \| 0.7913 \| 0.7912 \| \| 0.2604 \| 184.62 \| 7200 \| 0.5698 \| 0.7912 \| 0.7912 \| \| 0.2595 \| 189.74 \| 7400 \| 0.5668 \| 0.7929 \| 0.7928 \| \| 0.2612 \| 194.87 \| 7600 \| 0.5702 \| 0.7962 \| 0.7961 \| \| 0.2589 \| 200.0 \| 7800 \| 0.5739 \| 0.7896 \| 0.7896 \| \| 0.2595 \| 205.13 \| 8000 \| 0.5653 \| 0.7880 \| 0.7879 \| \| 0.2554 \| 210.26 \| 8200 \| 0.5758 \| 0.7897 \| 0.7896 \| \| 0.2514 \| 215.38 \| 8400 \| 0.5829 \| 0.7863 \| 0.7863 \| \| 0.2531 \| 220.51 \| 8600 \| 0.5787 \| 0.7880 \| 0.7879 \| \| 0.2506 \| 225.64 \| 8800 \| 0.5808 \| 0.7881 \| 0.7879 \| \| 0.2529 \| 230.77 \| 9000 \| 0.5799 \| 0.7929 \| 0.7928 \| \| 0.247 \| 235.9 \| 9200 \| 0.5822 \| 0.7946 \| 0.7945 \| \| 0.2498 \| 241.03 \| 9400 \| 0.5814 \| 0.7913 \| 0.7912 \| \| 0.2467 \| 246.15 \| 9600 \| 0.5820 \| 0.7930 \| 0.7928 \| \| 0.2499 \| 251.28 \| 9800 \| 0.5824 \| 0.7913 \| 0.7912 \| \| 0.2494 \| 256.41 \| 10000 \| 0.5827 \| 0.7913 \| 0.7912 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_8192_512_30M", "model-index": [{"name": "GUE_prom_prom_300_tata-seqsight_8192_512_30M-L1_f", "results": []}]}	mahdibaghbanzadeh/GUE_prom_prom_300_tata-seqsight_8192_512_30M-L1_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_8192_512_30M", "region:us" ]	null	2024-04-27T01:23:36+00:00	[]	[]	TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us	GUE\_prom\_prom\_300\_tata-seqsight\_8192\_512\_30M-L1\_f ========================================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_8192\_512\_30M on the mahdibaghbanzadeh/GUE\_prom\_prom\_300\_tata dataset. It achieves the following results on the evaluation set: * Loss: 0.4320 * F1 Score: 0.8043 * Accuracy: 0.8042 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]	[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_prom_prom_300_tata-seqsight_8192_512_30M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_8192_512_30M](https://huggingface.co/mahdibaghbanzadeh/seqsight_8192_512_30M) on the [mahdibaghbanzadeh/GUE_prom_prom_300_tata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_300_tata) dataset. It achieves the following results on the evaluation set: - Loss: 0.4340 - F1 Score: 0.8107 - Accuracy: 0.8108 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:------:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.5361 \| 5.13 \| 200 \| 0.4726 \| 0.7999 \| 0.8010 \| \| 0.4311 \| 10.26 \| 400 \| 0.4750 \| 0.7991 \| 0.7993 \| \| 0.3906 \| 15.38 \| 600 \| 0.4535 \| 0.8156 \| 0.8157 \| \| 0.3587 \| 20.51 \| 800 \| 0.4676 \| 0.8189 \| 0.8189 \| \| 0.338 \| 25.64 \| 1000 \| 0.4852 \| 0.8141 \| 0.8140 \| \| 0.3033 \| 30.77 \| 1200 \| 0.5177 \| 0.7927 \| 0.7928 \| \| 0.2868 \| 35.9 \| 1400 \| 0.5366 \| 0.8027 \| 0.8026 \| \| 0.264 \| 41.03 \| 1600 \| 0.5506 \| 0.8093 \| 0.8091 \| \| 0.2439 \| 46.15 \| 1800 \| 0.5622 \| 0.7961 \| 0.7961 \| \| 0.2265 \| 51.28 \| 2000 \| 0.5868 \| 0.8010 \| 0.8010 \| \| 0.2082 \| 56.41 \| 2200 \| 0.6659 \| 0.7979 \| 0.7977 \| \| 0.1918 \| 61.54 \| 2400 \| 0.7247 \| 0.7755 \| 0.7765 \| \| 0.1845 \| 66.67 \| 2600 \| 0.6934 \| 0.7815 \| 0.7814 \| \| 0.1682 \| 71.79 \| 2800 \| 0.7161 \| 0.7878 \| 0.7879 \| \| 0.1634 \| 76.92 \| 3000 \| 0.7996 \| 0.7763 \| 0.7765 \| \| 0.1513 \| 82.05 \| 3200 \| 0.8184 \| 0.7799 \| 0.7798 \| \| 0.1417 \| 87.18 \| 3400 \| 0.8684 \| 0.7552 \| 0.7569 \| \| 0.1415 \| 92.31 \| 3600 \| 0.8256 \| 0.7864 \| 0.7863 \| \| 0.1262 \| 97.44 \| 3800 \| 0.8991 \| 0.7653 \| 0.7651 \| \| 0.1194 \| 102.56 \| 4000 \| 0.9260 \| 0.7717 \| 0.7716 \| \| 0.1182 \| 107.69 \| 4200 \| 0.9309 \| 0.7648 \| 0.7651 \| \| 0.1072 \| 112.82 \| 4400 \| 0.9617 \| 0.7685 \| 0.7684 \| \| 0.1034 \| 117.95 \| 4600 \| 0.9810 \| 0.7750 \| 0.7749 \| \| 0.1029 \| 123.08 \| 4800 \| 0.9391 \| 0.7766 \| 0.7765 \| \| 0.0926 \| 128.21 \| 5000 \| 1.0178 \| 0.7668 \| 0.7667 \| \| 0.0956 \| 133.33 \| 5200 \| 0.9644 \| 0.7749 \| 0.7749 \| \| 0.0872 \| 138.46 \| 5400 \| 1.0404 \| 0.7766 \| 0.7765 \| \| 0.0829 \| 143.59 \| 5600 \| 1.0505 \| 0.7797 \| 0.7798 \| \| 0.0811 \| 148.72 \| 5800 \| 1.0447 \| 0.7815 \| 0.7814 \| \| 0.0792 \| 153.85 \| 6000 \| 1.0644 \| 0.7797 \| 0.7798 \| \| 0.0774 \| 158.97 \| 6200 \| 1.1230 \| 0.7782 \| 0.7781 \| \| 0.0736 \| 164.1 \| 6400 \| 1.0981 \| 0.7799 \| 0.7798 \| \| 0.0747 \| 169.23 \| 6600 \| 1.0630 \| 0.7798 \| 0.7798 \| \| 0.0729 \| 174.36 \| 6800 \| 1.0963 \| 0.7813 \| 0.7814 \| \| 0.07 \| 179.49 \| 7000 \| 1.1042 \| 0.7766 \| 0.7765 \| \| 0.0679 \| 184.62 \| 7200 \| 1.1413 \| 0.7718 \| 0.7716 \| \| 0.0635 \| 189.74 \| 7400 \| 1.1705 \| 0.7750 \| 0.7749 \| \| 0.0645 \| 194.87 \| 7600 \| 1.1721 \| 0.7782 \| 0.7781 \| \| 0.0669 \| 200.0 \| 7800 \| 1.1447 \| 0.7767 \| 0.7765 \| \| 0.0659 \| 205.13 \| 8000 \| 1.1749 \| 0.7766 \| 0.7765 \| \| 0.0616 \| 210.26 \| 8200 \| 1.1785 \| 0.7750 \| 0.7749 \| \| 0.0553 \| 215.38 \| 8400 \| 1.2185 \| 0.7701 \| 0.7700 \| \| 0.0645 \| 220.51 \| 8600 \| 1.1544 \| 0.7766 \| 0.7765 \| \| 0.0574 \| 225.64 \| 8800 \| 1.2041 \| 0.7734 \| 0.7732 \| \| 0.0631 \| 230.77 \| 9000 \| 1.1826 \| 0.7782 \| 0.7781 \| \| 0.0556 \| 235.9 \| 9200 \| 1.1807 \| 0.7782 \| 0.7781 \| \| 0.061 \| 241.03 \| 9400 \| 1.1816 \| 0.7782 \| 0.7781 \| \| 0.0562 \| 246.15 \| 9600 \| 1.2023 \| 0.7814 \| 0.7814 \| \| 0.0563 \| 251.28 \| 9800 \| 1.1978 \| 0.7783 \| 0.7781 \| \| 0.0553 \| 256.41 \| 10000 \| 1.1962 \| 0.7831 \| 0.7830 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_8192_512_30M", "model-index": [{"name": "GUE_prom_prom_300_tata-seqsight_8192_512_30M-L8_f", "results": []}]}	mahdibaghbanzadeh/GUE_prom_prom_300_tata-seqsight_8192_512_30M-L8_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_8192_512_30M", "region:us" ]	null	2024-04-27T01:26:35+00:00	[]	[]	TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us	GUE\_prom\_prom\_300\_tata-seqsight\_8192\_512\_30M-L8\_f ========================================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_8192\_512\_30M on the mahdibaghbanzadeh/GUE\_prom\_prom\_300\_tata dataset. It achieves the following results on the evaluation set: * Loss: 0.4340 * F1 Score: 0.8107 * Accuracy: 0.8108 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]	[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]
text2text-generation	transformers	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # CS505_COQE_viT5_train_Instruction0_OPASL_v1 This model is a fine-tuned version of [VietAI/vit5-large](https://huggingface.co/VietAI/vit5-large) on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 20 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.15.2	{"license": "mit", "tags": ["generated_from_trainer"], "base_model": "VietAI/vit5-large", "model-index": [{"name": "CS505_COQE_viT5_train_Instruction0_OPASL_v1", "results": []}]}	ThuyNT/CS505_COQE_viT5_train_Instruction0_OPASL_v1	null	[ "transformers", "tensorboard", "safetensors", "t5", "text2text-generation", "generated_from_trainer", "base_model:VietAI/vit5-large", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-27T01:29:08+00:00	[]	[]	TAGS #transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-VietAI/vit5-large #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us	# CS505_COQE_viT5_train_Instruction0_OPASL_v1 This model is a fine-tuned version of VietAI/vit5-large on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 20 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.15.2	[ "# CS505_COQE_viT5_train_Instruction0_OPASL_v1\n\nThis model is a fine-tuned version of VietAI/vit5-large on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 20\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]	[ "TAGS\n#transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-VietAI/vit5-large #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# CS505_COQE_viT5_train_Instruction0_OPASL_v1\n\nThis model is a fine-tuned version of VietAI/vit5-large on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 20\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_prom_prom_300_tata-seqsight_8192_512_30M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_8192_512_30M](https://huggingface.co/mahdibaghbanzadeh/seqsight_8192_512_30M) on the [mahdibaghbanzadeh/GUE_prom_prom_300_tata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_300_tata) dataset. It achieves the following results on the evaluation set: - Loss: 0.4592 - F1 Score: 0.8205 - Accuracy: 0.8206 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:------:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.5086 \| 5.13 \| 200 \| 0.4565 \| 0.7930 \| 0.7928 \| \| 0.3952 \| 10.26 \| 400 \| 0.5182 \| 0.7677 \| 0.7700 \| \| 0.33 \| 15.38 \| 600 \| 0.4784 \| 0.8207 \| 0.8206 \| \| 0.2734 \| 20.51 \| 800 \| 0.5296 \| 0.8043 \| 0.8042 \| \| 0.2262 \| 25.64 \| 1000 \| 0.6202 \| 0.8027 \| 0.8026 \| \| 0.1855 \| 30.77 \| 1200 \| 0.7224 \| 0.7817 \| 0.7830 \| \| 0.1554 \| 35.9 \| 1400 \| 0.7096 \| 0.8106 \| 0.8108 \| \| 0.1271 \| 41.03 \| 1600 \| 0.7358 \| 0.8093 \| 0.8091 \| \| 0.1132 \| 46.15 \| 1800 \| 0.7646 \| 0.8027 \| 0.8026 \| \| 0.0916 \| 51.28 \| 2000 \| 0.9272 \| 0.7911 \| 0.7912 \| \| 0.0795 \| 56.41 \| 2200 \| 0.9784 \| 0.7924 \| 0.7928 \| \| 0.0763 \| 61.54 \| 2400 \| 1.0530 \| 0.7833 \| 0.7847 \| \| 0.0701 \| 66.67 \| 2600 \| 0.9257 \| 0.8027 \| 0.8026 \| \| 0.0577 \| 71.79 \| 2800 \| 1.0282 \| 0.7993 \| 0.7993 \| \| 0.056 \| 76.92 \| 3000 \| 1.0811 \| 0.7979 \| 0.7977 \| \| 0.0545 \| 82.05 \| 3200 \| 1.0417 \| 0.7831 \| 0.7830 \| \| 0.0496 \| 87.18 \| 3400 \| 0.9956 \| 0.7913 \| 0.7912 \| \| 0.0465 \| 92.31 \| 3600 \| 1.1224 \| 0.7911 \| 0.7912 \| \| 0.0431 \| 97.44 \| 3800 \| 1.0531 \| 0.7946 \| 0.7945 \| \| 0.0384 \| 102.56 \| 4000 \| 1.1811 \| 0.7995 \| 0.7993 \| \| 0.0383 \| 107.69 \| 4200 \| 1.1002 \| 0.8011 \| 0.8010 \| \| 0.0355 \| 112.82 \| 4400 \| 1.1293 \| 0.7995 \| 0.7993 \| \| 0.0357 \| 117.95 \| 4600 \| 1.1393 \| 0.8027 \| 0.8026 \| \| 0.0332 \| 123.08 \| 4800 \| 1.2111 \| 0.7944 \| 0.7945 \| \| 0.0289 \| 128.21 \| 5000 \| 1.2221 \| 0.7995 \| 0.7993 \| \| 0.0283 \| 133.33 \| 5200 \| 1.2444 \| 0.7977 \| 0.7977 \| \| 0.0287 \| 138.46 \| 5400 \| 1.2123 \| 0.8027 \| 0.8026 \| \| 0.0266 \| 143.59 \| 5600 \| 1.2331 \| 0.8044 \| 0.8042 \| \| 0.0273 \| 148.72 \| 5800 \| 1.2408 \| 0.8011 \| 0.8010 \| \| 0.0255 \| 153.85 \| 6000 \| 1.2152 \| 0.8044 \| 0.8042 \| \| 0.0252 \| 158.97 \| 6200 \| 1.2034 \| 0.8011 \| 0.8010 \| \| 0.0232 \| 164.1 \| 6400 \| 1.1980 \| 0.7995 \| 0.7993 \| \| 0.0252 \| 169.23 \| 6600 \| 1.2003 \| 0.7913 \| 0.7912 \| \| 0.0218 \| 174.36 \| 6800 \| 1.2275 \| 0.7946 \| 0.7945 \| \| 0.0209 \| 179.49 \| 7000 \| 1.3166 \| 0.7993 \| 0.7993 \| \| 0.0202 \| 184.62 \| 7200 \| 1.2827 \| 0.7995 \| 0.7993 \| \| 0.0202 \| 189.74 \| 7400 \| 1.2810 \| 0.7962 \| 0.7961 \| \| 0.0184 \| 194.87 \| 7600 \| 1.2615 \| 0.7929 \| 0.7928 \| \| 0.0194 \| 200.0 \| 7800 \| 1.2767 \| 0.7930 \| 0.7928 \| \| 0.02 \| 205.13 \| 8000 \| 1.2672 \| 0.7978 \| 0.7977 \| \| 0.0211 \| 210.26 \| 8200 \| 1.2335 \| 0.7962 \| 0.7961 \| \| 0.0172 \| 215.38 \| 8400 \| 1.3205 \| 0.7962 \| 0.7961 \| \| 0.018 \| 220.51 \| 8600 \| 1.3163 \| 0.7979 \| 0.7977 \| \| 0.016 \| 225.64 \| 8800 \| 1.3450 \| 0.7913 \| 0.7912 \| \| 0.0175 \| 230.77 \| 9000 \| 1.3278 \| 0.7995 \| 0.7993 \| \| 0.0151 \| 235.9 \| 9200 \| 1.3556 \| 0.7962 \| 0.7961 \| \| 0.0159 \| 241.03 \| 9400 \| 1.3456 \| 0.7979 \| 0.7977 \| \| 0.0148 \| 246.15 \| 9600 \| 1.3545 \| 0.7962 \| 0.7961 \| \| 0.015 \| 251.28 \| 9800 \| 1.3576 \| 0.7979 \| 0.7977 \| \| 0.0136 \| 256.41 \| 10000 \| 1.3621 \| 0.7962 \| 0.7961 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_8192_512_30M", "model-index": [{"name": "GUE_prom_prom_300_tata-seqsight_8192_512_30M-L32_f", "results": []}]}	mahdibaghbanzadeh/GUE_prom_prom_300_tata-seqsight_8192_512_30M-L32_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_8192_512_30M", "region:us" ]	null	2024-04-27T01:30:04+00:00	[]	[]	TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us	GUE\_prom\_prom\_300\_tata-seqsight\_8192\_512\_30M-L32\_f ========================================================== This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_8192\_512\_30M on the mahdibaghbanzadeh/GUE\_prom\_prom\_300\_tata dataset. It achieves the following results on the evaluation set: * Loss: 0.4592 * F1 Score: 0.8205 * Accuracy: 0.8206 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]	[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_prom_prom_300_notata-seqsight_8192_512_30M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_8192_512_30M](https://huggingface.co/mahdibaghbanzadeh/seqsight_8192_512_30M) on the [mahdibaghbanzadeh/GUE_prom_prom_300_notata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_300_notata) dataset. It achieves the following results on the evaluation set: - Loss: 0.1256 - F1 Score: 0.9533 - Accuracy: 0.9533 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.3525 \| 0.6 \| 200 \| 0.1641 \| 0.9355 \| 0.9356 \| \| 0.1746 \| 1.2 \| 400 \| 0.1422 \| 0.9448 \| 0.9448 \| \| 0.1614 \| 1.81 \| 600 \| 0.1324 \| 0.9467 \| 0.9467 \| \| 0.1496 \| 2.41 \| 800 \| 0.1273 \| 0.9487 \| 0.9487 \| \| 0.1434 \| 3.01 \| 1000 \| 0.1223 \| 0.9514 \| 0.9514 \| \| 0.1416 \| 3.61 \| 1200 \| 0.1195 \| 0.9529 \| 0.9529 \| \| 0.1389 \| 4.22 \| 1400 \| 0.1215 \| 0.9527 \| 0.9527 \| \| 0.1355 \| 4.82 \| 1600 \| 0.1168 \| 0.9540 \| 0.9540 \| \| 0.132 \| 5.42 \| 1800 \| 0.1173 \| 0.9542 \| 0.9542 \| \| 0.1277 \| 6.02 \| 2000 \| 0.1153 \| 0.9533 \| 0.9533 \| \| 0.1289 \| 6.63 \| 2200 \| 0.1133 \| 0.9542 \| 0.9542 \| \| 0.1253 \| 7.23 \| 2400 \| 0.1126 \| 0.9553 \| 0.9553 \| \| 0.122 \| 7.83 \| 2600 \| 0.1120 \| 0.9557 \| 0.9557 \| \| 0.125 \| 8.43 \| 2800 \| 0.1117 \| 0.9574 \| 0.9574 \| \| 0.1245 \| 9.04 \| 3000 \| 0.1137 \| 0.9544 \| 0.9544 \| \| 0.1219 \| 9.64 \| 3200 \| 0.1172 \| 0.9557 \| 0.9557 \| \| 0.1194 \| 10.24 \| 3400 \| 0.1133 \| 0.9557 \| 0.9557 \| \| 0.1223 \| 10.84 \| 3600 \| 0.1084 \| 0.9600 \| 0.9601 \| \| 0.1147 \| 11.45 \| 3800 \| 0.1077 \| 0.9595 \| 0.9595 \| \| 0.114 \| 12.05 \| 4000 \| 0.1084 \| 0.9597 \| 0.9597 \| \| 0.1192 \| 12.65 \| 4200 \| 0.1076 \| 0.9568 \| 0.9568 \| \| 0.1193 \| 13.25 \| 4400 \| 0.1075 \| 0.9587 \| 0.9587 \| \| 0.1142 \| 13.86 \| 4600 \| 0.1064 \| 0.9597 \| 0.9597 \| \| 0.1148 \| 14.46 \| 4800 \| 0.1082 \| 0.9583 \| 0.9584 \| \| 0.1122 \| 15.06 \| 5000 \| 0.1051 \| 0.9589 \| 0.9589 \| \| 0.1125 \| 15.66 \| 5200 \| 0.1068 \| 0.9587 \| 0.9587 \| \| 0.1146 \| 16.27 \| 5400 \| 0.1062 \| 0.9587 \| 0.9587 \| \| 0.1106 \| 16.87 \| 5600 \| 0.1041 \| 0.9604 \| 0.9604 \| \| 0.1111 \| 17.47 \| 5800 \| 0.1042 \| 0.9595 \| 0.9595 \| \| 0.1158 \| 18.07 \| 6000 \| 0.1045 \| 0.9593 \| 0.9593 \| \| 0.1103 \| 18.67 \| 6200 \| 0.1052 \| 0.9585 \| 0.9585 \| \| 0.1118 \| 19.28 \| 6400 \| 0.1043 \| 0.9604 \| 0.9604 \| \| 0.1096 \| 19.88 \| 6600 \| 0.1067 \| 0.9583 \| 0.9584 \| \| 0.1107 \| 20.48 \| 6800 \| 0.1058 \| 0.9597 \| 0.9597 \| \| 0.1079 \| 21.08 \| 7000 \| 0.1042 \| 0.9602 \| 0.9602 \| \| 0.1086 \| 21.69 \| 7200 \| 0.1042 \| 0.9612 \| 0.9612 \| \| 0.1078 \| 22.29 \| 7400 \| 0.1054 \| 0.9612 \| 0.9612 \| \| 0.1101 \| 22.89 \| 7600 \| 0.1028 \| 0.9616 \| 0.9616 \| \| 0.1092 \| 23.49 \| 7800 \| 0.1026 \| 0.9606 \| 0.9606 \| \| 0.1054 \| 24.1 \| 8000 \| 0.1034 \| 0.9602 \| 0.9602 \| \| 0.108 \| 24.7 \| 8200 \| 0.1033 \| 0.9599 \| 0.9599 \| \| 0.1071 \| 25.3 \| 8400 \| 0.1044 \| 0.9600 \| 0.9601 \| \| 0.1075 \| 25.9 \| 8600 \| 0.1023 \| 0.9608 \| 0.9608 \| \| 0.1071 \| 26.51 \| 8800 \| 0.1024 \| 0.9606 \| 0.9606 \| \| 0.1078 \| 27.11 \| 9000 \| 0.1025 \| 0.9608 \| 0.9608 \| \| 0.1052 \| 27.71 \| 9200 \| 0.1031 \| 0.9606 \| 0.9606 \| \| 0.1041 \| 28.31 \| 9400 \| 0.1030 \| 0.9608 \| 0.9608 \| \| 0.1089 \| 28.92 \| 9600 \| 0.1026 \| 0.9608 \| 0.9608 \| \| 0.1043 \| 29.52 \| 9800 \| 0.1029 \| 0.9608 \| 0.9608 \| \| 0.1089 \| 30.12 \| 10000 \| 0.1028 \| 0.9608 \| 0.9608 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_8192_512_30M", "model-index": [{"name": "GUE_prom_prom_300_notata-seqsight_8192_512_30M-L1_f", "results": []}]}	mahdibaghbanzadeh/GUE_prom_prom_300_notata-seqsight_8192_512_30M-L1_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_8192_512_30M", "region:us" ]	null	2024-04-27T01:30:18+00:00	[]	[]	TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us	GUE\_prom\_prom\_300\_notata-seqsight\_8192\_512\_30M-L1\_f =========================================================== This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_8192\_512\_30M on the mahdibaghbanzadeh/GUE\_prom\_prom\_300\_notata dataset. It achieves the following results on the evaluation set: * Loss: 0.1256 * F1 Score: 0.9533 * Accuracy: 0.9533 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]	[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]
text-generation	transformers	<div align="center"> <img width="260px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/BrQCb95lmEIFz79QAmoNA.png"></div> ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/fJIOPJnY6Ff6fUiSIuMEt.png) <div align="center"> <h1>Advancing Open-source Large Language Models in Medical Domain</h1> </div> <p align="center" style="margin-top: 0px;"> <a href="https://colab.research.google.com/drive/1F5oV20InEYeAJGmBwYF9NM_QhLmjBkKJ?usp=sharing"> <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="OpenChat Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 10px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style=" margin-right: 5px;">Online Demo</span> </a> \| <a href="https://github.com/openlifescience-ai"> <img src="https://github.githubassets.com/assets/GitHub-Mark-ea2971cee799.png" alt="GitHub Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style=" margin-right: 5px;">GitHub</span> </a> \| <a href="#"> <img src="https://github.com/alpayariyak/openchat/blob/master/assets/arxiv-logomark-small-square-border.png?raw=true" alt="ArXiv Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style="margin-right: 5px;">Paper</span> </a> \| <a href="https://discord.gg/A5Fjf5zC69"> <img src="https://cloud.githubusercontent.com/assets/6291467/26705903/96c2d66e-477c-11e7-9f4e-f3c0efe96c9a.png" alt="Discord Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text">Discord</span> </a> </p> ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/KGmRE5w2sepNtwsEu8t7K.jpeg) Introducing OpenBioLLM-70B: A State-of-the-Art Open Source Biomedical Large Language Model OpenBioLLM-70B is an advanced open source language model designed specifically for the biomedical domain. Developed by Saama AI Labs, this model leverages cutting-edge techniques to achieve state-of-the-art performance on a wide range of biomedical tasks. 🏥 Biomedical Specialization: OpenBioLLM-70B is tailored for the unique language and knowledge requirements of the medical and life sciences fields. It was fine-tuned on a vast corpus of high-quality biomedical data, enabling it to understand and generate text with domain-specific accuracy and fluency. 🎓 Superior Performance: With 70 billion parameters, OpenBioLLM-70B outperforms other open source biomedical language models of similar scale. It has also demonstrated better results compared to larger proprietary & open-source models like GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 on biomedical benchmarks. 🧠 Advanced Training Techniques: OpenBioLLM-70B builds upon the powerful foundations of the Meta-Llama-3-70B-Instruct and [Meta-Llama-3-70B-Instruct](meta-llama/Meta-Llama-3-70B-Instruct) models. It incorporates the DPO dataset and fine-tuning recipe along with a custom diverse medical instruction dataset. Key components of the training pipeline include: <div align="center"> <img width="1200px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/oPchsJsEpQoGcGXVbh7YS.png"> </div> - Policy Optimization: [Direct Preference Optimization: Your Language Model is Secretly a Reward Model (DPO)](https://arxiv.org/abs/2305.18290) - Fine-tuning dataset: Custom Medical Instruct dataset (We plan to release a sample training dataset in our upcoming paper; please stay updated) This combination of cutting-edge techniques enables OpenBioLLM-70B to align with key capabilities and preferences for biomedical applications. ⚙️ Release Details: - Model Size: 70 billion parameters - Quantization: Optimized quantized versions available [Here](https://huggingface.co/aaditya/OpenBioLLM-70B-GGUF) - Language(s) (NLP): en - Developed By: [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) from Saama AI Labs - License: Meta-Llama License - Fine-tuned from models: [Meta-Llama-3-70B-Instruct](meta-llama/Meta-Llama-3-70B-Instruct) - Resources for more information: - Paper: Coming soon The model can be fine-tuned for more specialized tasks and datasets as needed. OpenBioLLM-70B represents an important step forward in democratizing advanced language AI for the biomedical community. By leveraging state-of-the-art architectures and training techniques from leading open source efforts like Llama-3, we have created a powerful tool to accelerate innovation and discovery in healthcare and the life sciences. We are excited to share OpenBioLLM-70B with researchers and developers around the world. ### Use with transformers Important: Please use the exact chat template provided by Llama-3 instruct version. Otherwise there will be a degradation in the performance. The model output can be verbose in rare cases. Please consider setting temperature = 0 to make this happen less. See the snippet below for usage with Transformers: ```python import transformers import torch model_id = "aaditya/OpenBioLLM-Llama3-70B" pipeline = transformers.pipeline( "text-generation", model=model_id, model_kwargs={"torch_dtype": torch.bfloat16}, device="auto", ) messages = [ {"role": "system", "content": "You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience. Your name is OpenBioLLM, and you were developed by Saama AI Labs. who's willing to help answer the user's query with explanation. In your explanation, leverage your deep medical expertise such as relevant anatomical structures, physiological processes, diagnostic criteria, treatment guidelines, or other pertinent medical concepts. Use precise medical terminology while still aiming to make the explanation clear and accessible to a general audience."}, {"role": "user", "content": "How can i split a 3mg or 4mg waefin pill so i can get a 2.5mg pill?"}, ] prompt = pipeline.tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) terminators = [ pipeline.tokenizer.eos_token_id, pipeline.tokenizer.convert_tokens_to_ids("<\|eot_id\|>") ] outputs = pipeline( prompt, max_new_tokens=256, eos_token_id=terminators, do_sample=True, temperature=0.0, top_p=0.9, ) print(outputs[0]["generated_text"][len(prompt):]) ``` ## Training procedure ### Training hyperparameters <details> <summary>Click to see details</summary> - learning_rate: 0.0002 - lr_scheduler: cosine - train_batch_size: 12 - eval_batch_size: 8 - GPU: H100 80GB SXM5 - num_devices: 8 - optimizer: adamw_bnb_8bit - lr_scheduler_warmup_steps: 100 - num_epochs: 4 </details> ### Peft hyperparameters <details> <summary>Click to see details</summary> - adapter: qlora - lora_r: 128 - lora_alpha: 256 - lora_dropout: 0.05 - lora_target_linear: true -lora_target_modules: - q_proj - v_proj - k_proj - o_proj - gate_proj - down_proj - up_proj </details> ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2+cu121 - Datasets 2.18.0 - Tokenizers 0.15.1 - Axolotl - Lm harness for evaluation # Benchmark Results 🔥 OpenBioLLM-70B demonstrates superior performance compared to larger models, such as GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 across 9 diverse biomedical datasets, achieving state-of-the-art results with an average score of 86.06%, despite having a significantly smaller parameter count. The model's strong performance in domain-specific tasks, such as Clinical KG, Medical Genetics, and PubMedQA, highlights its ability to effectively capture and apply biomedical knowledge. 🚨 The GPT-4, Med-PaLM-1, and Med-PaLM-2 results are taken from their official papers. Since Med-PaLM doesn't provide zero-shot accuracy, we are using 5-shot accuracy from their paper for comparison. All results presented are in the zero-shot setting, except for Med-PaLM-2 and Med-PaLM-1, which use 5-shot accuracy. \| \| Clinical KG \| Medical Genetics \| Anatomy \| Pro Medicine \| College Biology \| College Medicine \| MedQA 4 opts \| PubMedQA \| MedMCQA \| Avg \| \|--------------------\|-------------\|------------------\|---------\|--------------\|-----------------\|------------------\|--------------\|----------\|---------\|-------\| \| OpenBioLLM-70B \| 92.93 \| 93.197 \| 83.904 \| 93.75 \| 93.827 \| 85.749 \| 78.162 \| 78.97 \| 74.014 \| 86.05588 \| \| Med-PaLM-2 (5-shot) \| 88.3 \| 90 \| 77.8 \| 95.2 \| 94.4 \| 80.9 \| 79.7 \| 79.2 \| 71.3 \| 84.08 \| \| GPT-4 \| 86.04 \| 91 \| 80 \| 93.01 \| 95.14 \| 76.88 \| 78.87 \| 75.2 \| 69.52 \| 82.85 \| \| Med-PaLM-1 (Flan-PaLM, 5-shot) \| 80.4 \| 75 \| 63.7 \| 83.8 \| 88.9 \| 76.3 \| 67.6 \| 79 \| 57.6 \| 74.7 \| \| OpenBioLLM-8B \| 76.101 \| 86.1 \| 69.829 \| 78.21 \| 84.213 \| 68.042 \| 58.993 \| 74.12 \| 56.913 \| 72.502 \| \| Gemini-1.0 \| 76.7 \| 75.8 \| 66.7 \| 77.7 \| 88 \| 69.2 \| 58 \| 70.7 \| 54.3 \| 70.79 \| \| GPT-3.5 Turbo 1106 \| 74.71 \| 74 \| 72.79 \| 72.79 \| 72.91 \| 64.73 \| 57.71 \| 72.66 \| 53.79 \| 66 \| \| Meditron-70B \| 66.79 \| 69 \| 53.33 \| 71.69 \| 76.38 \| 63 \| 57.1 \| 76.6 \| 46.85 \| 64.52 \| \| gemma-7b \| 69.81 \| 70 \| 59.26 \| 66.18 \| 79.86 \| 60.12 \| 47.21 \| 76.2 \| 48.96 \| 64.18 \| \| Mistral-7B-v0.1 \| 68.68 \| 71 \| 55.56 \| 68.38 \| 68.06 \| 59.54 \| 50.82 \| 75.4 \| 48.2 \| 62.85 \| \| Apollo-7B \| 62.26 \| 72 \| 61.48 \| 69.12 \| 70.83 \| 55.49 \| 55.22 \| 39.8 \| 53.77 \| 60 \| \| MedAlpaca-7b \| 57.36 \| 69 \| 57.04 \| 67.28 \| 65.28 \| 54.34 \| 41.71 \| 72.8 \| 37.51 \| 58.03 \| \| BioMistral-7B \| 59.9 \| 64 \| 56.5 \| 60.4 \| 59 \| 54.7 \| 50.6 \| 77.5 \| 48.1 \| 57.3 \| \| AlpaCare-llama2-7b \| 49.81 \| 49 \| 45.92 \| 33.82 \| 50 \| 43.35 \| 29.77 \| 72.2 \| 34.42 \| 45.36 \| \| ClinicalGPT \| 30.56 \| 27 \| 30.37 \| 19.48 \| 25 \| 24.27 \| 26.08 \| 63.8 \| 28.18 \| 30.52 \| <div align="center"> <img width="1600px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/_SzdcJSBjZyo8RS1bTEkP.png"> </div> ## Detailed Medical Subjectwise accuracy ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/UXF-V0col0Z0sS6BGPBkE.png) # Use Cases & Examples 🚨 Below results are from the quantized version of OpenBioLLM-70B # Summarize Clinical Notes OpenBioLLM-70B can efficiently analyze and summarize complex clinical notes, EHR data, and discharge summaries, extracting key information and generating concise, structured summaries ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/xdwdBgOxNi_TfML0hKlI8.png) # Answer Medical Questions OpenBioLLM-70B can provide answers to a wide range of medical questions. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/zO95GlwOQEZqCKQF69mE6.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/OKBczKw7gWeW5xsuDpc27.png) <details> <summary>Click to see details</summary> ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/eJGHT5khppYvJb8fQ-YW4.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/Cnbwrqa_-ORHRuNRC2P6Y.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/J9DhdcvukAc9mnnW9fj2C.png) </details> # Clinical Entity Recognition OpenBioLLM-70B can perform advanced clinical entity recognition by identifying and extracting key medical concepts, such as diseases, symptoms, medications, procedures, and anatomical structures, from unstructured clinical text. By leveraging its deep understanding of medical terminology and context, the model can accurately annotate and categorize clinical entities, enabling more efficient information retrieval, data analysis, and knowledge discovery from electronic health records, research articles, and other biomedical text sources. This capability can support various downstream applications, such as clinical decision support, pharmacovigilance, and medical research. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/_69BW4k9LVABFwtxixL45.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/DKy5wYCoPhoPPUc1-x8_J.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/7WD9zCCBZT4-4XlfnIQjl.png) # Biomarkers Extraction ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/ZttoM4AiteT7gFYVhjIpN.png) # Classification OpenBioLLM-70B can perform various biomedical classification tasks, such as disease prediction, sentiment analysis, medical document categorization ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/Bf5MW1d75qT-1F_TR_hC0.png) # De-Identification OpenBioLLM-70B can detect and remove personally identifiable information (PII) from medical records, ensuring patient privacy and compliance with data protection regulations like HIPAA. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/hKX4kzm--Tw5bj6K78msy.png) Advisory Notice! While OpenBioLLM-70B leverages high-quality data sources, its outputs may still contain inaccuracies, biases, or misalignments that could pose risks if relied upon for medical decision-making without further testing and refinement. The model's performance has not yet been rigorously evaluated in randomized controlled trials or real-world healthcare environments. Therefore, we strongly advise against using OpenBioLLM-70B for any direct patient care, clinical decision support, or other professional medical purposes at this time. Its use should be limited to research, development, and exploratory applications by qualified individuals who understand its limitations. OpenBioLLM-70B is intended solely as a research tool to assist healthcare professionals and should never be considered a replacement for the professional judgment and expertise of a qualified medical doctor. Appropriately adapting and validating OpenBioLLM-70B for specific medical use cases would require significant additional work, potentially including: - Thorough testing and evaluation in relevant clinical scenarios - Alignment with evidence-based guidelines and best practices - Mitigation of potential biases and failure modes - Integration with human oversight and interpretation - Compliance with regulatory and ethical standards Always consult a qualified healthcare provider for personal medical needs. # Citation If you find OpenBioLLM-70B & 8B useful in your work, please cite the model as follows: ``` @misc{OpenBioLLMs, author = {Ankit Pal, Malaikannan Sankarasubbu}, title = {OpenBioLLMs: Advancing Open-Source Large Language Models for Healthcare and Life Sciences}, year = {2024}, publisher = {Hugging Face}, journal = {Hugging Face repository}, howpublished = {\url{https://huggingface.co/aaditya/OpenBioLLM-Llama3-70B}} } ``` The accompanying paper is currently in progress and will be released soon. <div align="center"> <h2> 💌 Contact </h2> </div> We look forward to hearing you and collaborating on this exciting project! Contributors:** - [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) [aadityaura at gmail dot com] - Saama AI Labs - Note: I am looking for a funded PhD opportunity, especially if it fits my Responsible Generative AI, Multimodal LLMs, Geometric Deep Learning, and Healthcare AI skillset. # References We thank the [Meta Team](meta-llama/Meta-Llama-3-70B-Instruct) for their amazing models! Result sources - [1] GPT-4 [Capabilities of GPT-4 on Medical Challenge Problems] (https://arxiv.org/abs/2303.13375) - [2] Med-PaLM-1 [Large Language Models Encode Clinical Knowledge](https://arxiv.org/abs/2212.13138) - [3] Med-PaLM-2 [Towards Expert-Level Medical Question Answering with Large Language Models](https://arxiv.org/abs/2305.09617) - [4] Gemini-1.0 [Gemini Goes to Med School](https://arxiv.org/abs/2402.07023)	{"language": ["en"], "license": "llama3", "tags": ["llama-3", "llama", "Mixtral", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "distillation"], "base_model": "meta-llama/Meta-Llama-3-70B-Instruct", "widget": [{"example_title": "OpenBioLLM-70B", "messages": [{"role": "system", "content": "You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience."}, {"role": "user", "content": "How long does it take for newborn jaundice to go away?"}], "output": {"text": "Newborn jaundice, also known as neonatal jaundice, is a common condition in newborns where the yellowing of the skin and eyes occurs due to an elevated level of bilirubin in the blood. Bilirubin is a yellow pigment that forms when red blood cells break down. In most cases, newborn jaundice resolves on its own without any specific treatment.\nThe duration of newborn jaundice can vary depending on several factors such as the underlying cause, gestational age at birth, and individual variations in bilirubin metabolism. Here are some general guidelines:\n1. Physiological jaundice: This is the most common type of newborn jaundice and usually appears within 24-72 hours after birth. It tends to peak between the second and fifth day of life and gradually improves over the next week or two. By the time the baby is one week old, the jaundice should have mostly resolved. 2. Breast milk jaundice: This type of jaundice occurs in breastfed babies and may appear later than physiological jaundice, typically between the fifth and fourteenth day of life. It tends to persist for a longer duration but usually resolves within six weeks after birth. 3. Pathological jaundice: This type of jaundice is less common and occurs due to an underlying medical condition that affects bilirubin metabolism or liver function. The duration of pathological jaundice depends on the specific cause and may require treatment.\nIt's important for parents to monitor their newborn's jaundice closely and seek medical advice if the jaundice progresses rapidly, becomes severe, or is accompanied by other symptoms such as poor feeding, lethargy, or excessive sleepiness. In these cases, further evaluation and management may be necessary. Remember that each baby is unique, and the timing of jaundice resolution can vary. If you have concerns about your newborn's jaundice, it's always best to consult with a healthcare professional for personalized advice and guidance."}}], "model-index": [{"name": "OpenBioLLM-70B", "results": []}]}	LoneStriker/OpenBioLLM-Llama3-70B-4.0bpw-h6-exl2	null	[ "transformers", "pytorch", "llama", "text-generation", "llama-3", "Mixtral", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "distillation", "conversational", "en", "arxiv:2305.18290", "arxiv:2303.13375", "arxiv:2212.13138", "arxiv:2305.09617", "arxiv:2402.07023", "base_model:meta-llama/Meta-Llama-3-70B-Instruct", "license:llama3", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]	null	2024-04-27T01:31:50+00:00	[ "2305.18290", "2303.13375", "2212.13138", "2305.09617", "2402.07023" ]	[ "en" ]	TAGS #transformers #pytorch #llama #text-generation #llama-3 #Mixtral #instruct #finetune #chatml #DPO #RLHF #gpt4 #distillation #conversational #en #arxiv-2305.18290 #arxiv-2303.13375 #arxiv-2212.13138 #arxiv-2305.09617 #arxiv-2402.07023 #base_model-meta-llama/Meta-Llama-3-70B-Instruct #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us	![](URL <p>!image/png</p> <div align=) Advancing Open-source Large Language Models in Medical Domain ============================================================= Online Demo \| GitHub \| [![](URL alt=)](#) \| Discord !image/jpeg Introducing OpenBioLLM-70B: A State-of-the-Art Open Source Biomedical Large Language Model OpenBioLLM-70B is an advanced open source language model designed specifically for the biomedical domain. Developed by Saama AI Labs, this model leverages cutting-edge techniques to achieve state-of-the-art performance on a wide range of biomedical tasks. Biomedical Specialization: OpenBioLLM-70B is tailored for the unique language and knowledge requirements of the medical and life sciences fields. It was fine-tuned on a vast corpus of high-quality biomedical data, enabling it to understand and generate text with domain-specific accuracy and fluency. Superior Performance: With 70 billion parameters, OpenBioLLM-70B outperforms other open source biomedical language models of similar scale. It has also demonstrated better results compared to larger proprietary & open-source models like GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 on biomedical benchmarks. Advanced Training Techniques: OpenBioLLM-70B builds upon the powerful foundations of the Meta-Llama-3-70B-Instruct and Meta-Llama-3-70B-Instruct models. It incorporates the DPO dataset and fine-tuning recipe along with a custom diverse medical instruction dataset. Key components of the training pipeline include: ![](URL </div> <ul> <li>Policy Optimization: Direct Preference Optimization: Your Language Model is Secretly a Reward Model (DPO)</li> <li>Fine-tuning dataset: Custom Medical Instruct dataset (We plan to release a sample training dataset in our upcoming paper; please stay updated)</li> </ul> <p>This combination of cutting-edge techniques enables OpenBioLLM-70B to align with key capabilities and preferences for biomedical applications.</p> <p>️ Release Details:</p> <ul> <li>Model Size: 70 billion parameters</li> <li>Quantization: Optimized quantized versions available Here</li> <li>Language(s) (NLP): en</li> <li>Developed By: Ankit Pal (Aaditya Ura) from Saama AI Labs</li> <li>License: Meta-Llama License</li> <li>Fine-tuned from models: Meta-Llama-3-70B-Instruct</li> <li>Resources for more information: <ul> <li>Paper: Coming soon</li> </ul> </li> </ul> <p>The model can be fine-tuned for more specialized tasks and datasets as needed.</p> <p>OpenBioLLM-70B represents an important step forward in democratizing advanced language AI for the biomedical community. By leveraging state-of-the-art architectures and training techniques from leading open source efforts like Llama-3, we have created a powerful tool to accelerate innovation and discovery in healthcare and the life sciences.</p> <p>We are excited to share OpenBioLLM-70B with researchers and developers around the world.</p> <h3>Use with transformers</h3> <p>Important: Please use the exact chat template provided by Llama-3 instruct version. Otherwise there will be a degradation in the performance. The model output can be verbose in rare cases. Please consider setting temperature = 0 to make this happen less.</p> <p>See the snippet below for usage with Transformers:</p> <h2>Training procedure</h2> <h3>Training hyperparameters</h3> <details> <summary>Click to see details</summary> <ul> <li>learning_rate: 0.0002</li> <li>lr_scheduler: cosine</li> <li>train_batch_size: 12</li> <li>eval_batch_size: 8</li> <li>GPU: H100 80GB SXM5</li> <li>num_devices: 8</li> <li>optimizer: adamw_bnb_8bit</li> <li>lr_scheduler_warmup_steps: 100</li> <li>num_epochs: 4</li> </ul> </details> <h3>Peft hyperparameters</h3> <details> <summary>Click to see details</summary> <ul> <li>adapter: qlora</li> <li>lora_r: 128</li> <li>lora_alpha: 256</li> <li>lora_dropout: 0.05</li> <li>lora_target_linear: true</li> </ul> <p>-lora_target_modules:</p> <ul> <li>q_proj</li> <li>v_proj</li> <li>k_proj</li> <li>o_proj</li> <li>gate_proj</li> <li>down_proj</li> <li>up_proj</li> </ul> </details> <h3>Training results</h3> <h3>Framework versions</h3> <ul> <li>Transformers 4.39.3</li> <li>Pytorch 2.1.2+cu121</li> <li>Datasets 2.18.0</li> <li>Tokenizers 0.15.1</li> <li>Axolotl</li> <li>Lm harness for evaluation</li> </ul> <h1>Benchmark Results</h1> <p>OpenBioLLM-70B demonstrates superior performance compared to larger models, such as GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 across 9 diverse biomedical datasets, achieving state-of-the-art results with an average score of 86.06%, despite having a significantly smaller parameter count. The model's strong performance in domain-specific tasks, such as Clinical KG, Medical Genetics, and PubMedQA, highlights its ability to effectively capture and apply biomedical knowledge.</p> <p>The GPT-4, Med-PaLM-1, and Med-PaLM-2 results are taken from their official papers. Since Med-PaLM doesn't provide zero-shot accuracy, we are using 5-shot accuracy from their paper for comparison. All results presented are in the zero-shot setting, except for Med-PaLM-2 and Med-PaLM-1, which use 5-shot accuracy.</p> <p></p> <div align=) ![](URL </div> <h2>Detailed Medical Subjectwise accuracy</h2> <p>!image/png</p> <h1>Use Cases & Examples</h1> <p>Below results are from the quantized version of OpenBioLLM-70B</p> <h1>Summarize Clinical Notes</h1> <p>OpenBioLLM-70B can efficiently analyze and summarize complex clinical notes, EHR data, and discharge summaries, extracting key information and generating concise, structured summaries</p> <p>!image/png</p> <h1>Answer Medical Questions</h1> <p>OpenBioLLM-70B can provide answers to a wide range of medical questions.</p> <p>!image/png !image/png</p> <details> <summary>Click to see details</summary> <p>!image/png !image/png !image/png</p> </details> <h1>Clinical Entity Recognition</h1> <p>OpenBioLLM-70B can perform advanced clinical entity recognition by identifying and extracting key medical concepts, such as diseases, symptoms, medications, procedures, and anatomical structures, from unstructured clinical text. By leveraging its deep understanding of medical terminology and context, the model can accurately annotate and categorize clinical entities, enabling more efficient information retrieval, data analysis, and knowledge discovery from electronic health records, research articles, and other biomedical text sources. This capability can support various downstream applications, such as clinical decision support, pharmacovigilance, and medical research.</p> <p>!image/png !image/png !image/png</p> <h1>Biomarkers Extraction</h1> <p>!image/png</p> <h1>Classification</h1> <p>OpenBioLLM-70B can perform various biomedical classification tasks, such as disease prediction, sentiment analysis, medical document categorization</p> <p>!image/png</p> <h1>De-Identification</h1> <p>OpenBioLLM-70B can detect and remove personally identifiable information (PII) from medical records, ensuring patient privacy and compliance with data protection regulations like HIPAA.</p> <p>!image/png</p> <p>Advisory Notice!</p> <p>While OpenBioLLM-70B leverages high-quality data sources, its outputs may still contain inaccuracies, biases, or misalignments that could pose risks if relied upon for medical decision-making without further testing and refinement. The model's performance has not yet been rigorously evaluated in randomized controlled trials or real-world healthcare environments.</p> <p>Therefore, we strongly advise against using OpenBioLLM-70B for any direct patient care, clinical decision support, or other professional medical purposes at this time. Its use should be limited to research, development, and exploratory applications by qualified individuals who understand its limitations. OpenBioLLM-70B is intended solely as a research tool to assist healthcare professionals and should never be considered a replacement for the professional judgment and expertise of a qualified medical doctor.</p> <p>Appropriately adapting and validating OpenBioLLM-70B for specific medical use cases would require significant additional work, potentially including:</p> <ul> <li>Thorough testing and evaluation in relevant clinical scenarios</li> <li>Alignment with evidence-based guidelines and best practices</li> <li>Mitigation of potential biases and failure modes</li> <li>Integration with human oversight and interpretation</li> <li>Compliance with regulatory and ethical standards</li> </ul> <p>Always consult a qualified healthcare provider for personal medical needs.</p> <p>If you find OpenBioLLM-70B & 8B useful in your work, please cite the model as follows:</p> <p>The accompanying paper is currently in progress and will be released soon.</p> <div align=) Contact -------- We look forward to hearing you and collaborating on this exciting project! Contributors: * Ankit Pal (Aaditya Ura) [aadityaura at gmail dot com] * Saama AI Labs * Note: I am looking for a funded PhD opportunity, especially if it fits my Responsible Generative AI, Multimodal LLMs, Geometric Deep Learning, and Healthcare AI skillset. References ========== We thank the Meta Team for their amazing models! Result sources * [1] GPT-4 [Capabilities of GPT-4 on Medical Challenge Problems] (URL * [2] Med-PaLM-1 Large Language Models Encode Clinical Knowledge * [3] Med-PaLM-2 Towards Expert-Level Medical Question Answering with Large Language Models * [4] Gemini-1.0 Gemini Goes to Med School	[]	[ "TAGS\n#transformers #pytorch #llama #text-generation #llama-3 #Mixtral #instruct #finetune #chatml #DPO #RLHF #gpt4 #distillation #conversational #en #arxiv-2305.18290 #arxiv-2303.13375 #arxiv-2212.13138 #arxiv-2305.09617 #arxiv-2402.07023 #base_model-meta-llama/Meta-Llama-3-70B-Instruct #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n" ]
text2text-generation	transformers	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # CS505_COQE_viT5_train_Instruction0_PAOSL_v1 This model is a fine-tuned version of [VietAI/vit5-large](https://huggingface.co/VietAI/vit5-large) on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 20 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.15.2	{"license": "mit", "tags": ["generated_from_trainer"], "base_model": "VietAI/vit5-large", "model-index": [{"name": "CS505_COQE_viT5_train_Instruction0_PAOSL_v1", "results": []}]}	ThuyNT/CS505_COQE_viT5_train_Instruction0_PAOSL_v1	null	[ "transformers", "tensorboard", "safetensors", "t5", "text2text-generation", "generated_from_trainer", "base_model:VietAI/vit5-large", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-27T01:31:54+00:00	[]	[]	TAGS #transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-VietAI/vit5-large #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us	# CS505_COQE_viT5_train_Instruction0_PAOSL_v1 This model is a fine-tuned version of VietAI/vit5-large on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 20 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.15.2	[ "# CS505_COQE_viT5_train_Instruction0_PAOSL_v1\n\nThis model is a fine-tuned version of VietAI/vit5-large on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 20\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]	[ "TAGS\n#transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-VietAI/vit5-large #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# CS505_COQE_viT5_train_Instruction0_PAOSL_v1\n\nThis model is a fine-tuned version of VietAI/vit5-large on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 20\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]
fill-mask	transformers	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # model_3 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 3e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results ### Framework versions - Transformers 4.40.0 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1	{"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "bert-base-uncased", "model-index": [{"name": "model_3", "results": []}]}	beloiual/model_3	null	[ "transformers", "tensorboard", "safetensors", "bert", "fill-mask", "generated_from_trainer", "base_model:bert-base-uncased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-27T01:32:50+00:00	[]	[]	TAGS #transformers #tensorboard #safetensors #bert #fill-mask #generated_from_trainer #base_model-bert-base-uncased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us	# model_3 This model is a fine-tuned version of bert-base-uncased on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 3e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results ### Framework versions - Transformers 4.40.0 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1	[ "# model_3\n\nThis model is a fine-tuned version of bert-base-uncased on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 3e-05\n- train_batch_size: 32\n- eval_batch_size: 32\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 3", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]	[ "TAGS\n#transformers #tensorboard #safetensors #bert #fill-mask #generated_from_trainer #base_model-bert-base-uncased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "# model_3\n\nThis model is a fine-tuned version of bert-base-uncased on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 3e-05\n- train_batch_size: 32\n- eval_batch_size: 32\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 3", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]
text2text-generation	transformers	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # CS505_COQE_viT5_train_Instruction0_APOSL_v1 This model is a fine-tuned version of [VietAI/vit5-large](https://huggingface.co/VietAI/vit5-large) on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 20 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.15.2	{"license": "mit", "tags": ["generated_from_trainer"], "base_model": "VietAI/vit5-large", "model-index": [{"name": "CS505_COQE_viT5_train_Instruction0_APOSL_v1", "results": []}]}	ThuyNT/CS505_COQE_viT5_train_Instruction0_APOSL_v1	null	[ "transformers", "tensorboard", "safetensors", "t5", "text2text-generation", "generated_from_trainer", "base_model:VietAI/vit5-large", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-27T01:33:01+00:00	[]	[]	TAGS #transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-VietAI/vit5-large #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us	# CS505_COQE_viT5_train_Instruction0_APOSL_v1 This model is a fine-tuned version of VietAI/vit5-large on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 20 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.15.2	[ "# CS505_COQE_viT5_train_Instruction0_APOSL_v1\n\nThis model is a fine-tuned version of VietAI/vit5-large on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 20\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]	[ "TAGS\n#transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-VietAI/vit5-large #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# CS505_COQE_viT5_train_Instruction0_APOSL_v1\n\nThis model is a fine-tuned version of VietAI/vit5-large on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 20\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]
token-classification	transformers	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # model_3_edges This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 3e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results ### Framework versions - Transformers 4.40.0 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1	{"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "distilbert/distilbert-base-uncased", "model-index": [{"name": "model_3_edges", "results": []}]}	beloiual/model_3_edges	null	[ "transformers", "tensorboard", "safetensors", "distilbert", "token-classification", "generated_from_trainer", "base_model:distilbert/distilbert-base-uncased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-27T01:35:09+00:00	[]	[]	TAGS #transformers #tensorboard #safetensors #distilbert #token-classification #generated_from_trainer #base_model-distilbert/distilbert-base-uncased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us	# model_3_edges This model is a fine-tuned version of distilbert/distilbert-base-uncased on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 3e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results ### Framework versions - Transformers 4.40.0 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1	[ "# model_3_edges\n\nThis model is a fine-tuned version of distilbert/distilbert-base-uncased on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 3e-05\n- train_batch_size: 32\n- eval_batch_size: 32\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 3", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]	[ "TAGS\n#transformers #tensorboard #safetensors #distilbert #token-classification #generated_from_trainer #base_model-distilbert/distilbert-base-uncased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "# model_3_edges\n\nThis model is a fine-tuned version of distilbert/distilbert-base-uncased on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 3e-05\n- train_batch_size: 32\n- eval_batch_size: 32\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 3", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]
text-generation	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	obamaTeo/mistral-finetune-16bit-ver9-wiki-GPTQ	null	[ "transformers", "safetensors", "mistral", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]	null	2024-04-27T01:43:19+00:00	[ "1910.09700" ]	[]	TAGS #transformers #safetensors #mistral #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us	# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact	[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]	[ "TAGS\n#transformers #safetensors #mistral #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]
text-generation	transformers	Hello, my name is nanit. I am an AI assistant designed to help you with various tasks and provide information. I can assist with answering questions, providing recommendations, and performing calculations. I am constantly learning and improving to better serve you. If you have any specific questions or tasks you would like assistance with, please let me know.	{"license": "other", "library_name": "transformers"}	AlanRobotics/nanit_slerp	null	[ "transformers", "safetensors", "phi", "text-generation", "custom_code", "license:other", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-27T01:43:40+00:00	[]	[]	TAGS #transformers #safetensors #phi #text-generation #custom_code #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us	Hello, my name is nanit. I am an AI assistant designed to help you with various tasks and provide information. I can assist with answering questions, providing recommendations, and performing calculations. I am constantly learning and improving to better serve you. If you have any specific questions or tasks you would like assistance with, please let me know.	[]	[ "TAGS\n#transformers #safetensors #phi #text-generation #custom_code #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n" ]
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_prom_prom_300_notata-seqsight_8192_512_30M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_8192_512_30M](https://huggingface.co/mahdibaghbanzadeh/seqsight_8192_512_30M) on the [mahdibaghbanzadeh/GUE_prom_prom_300_notata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_300_notata) dataset. It achieves the following results on the evaluation set: - Loss: 0.1197 - F1 Score: 0.9561 - Accuracy: 0.9561 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.2892 \| 0.6 \| 200 \| 0.1442 \| 0.9422 \| 0.9422 \| \| 0.1464 \| 1.2 \| 400 \| 0.1229 \| 0.9527 \| 0.9527 \| \| 0.1407 \| 1.81 \| 600 \| 0.1152 \| 0.9527 \| 0.9527 \| \| 0.1283 \| 2.41 \| 800 \| 0.1134 \| 0.9538 \| 0.9538 \| \| 0.1259 \| 3.01 \| 1000 \| 0.1108 \| 0.9567 \| 0.9567 \| \| 0.1226 \| 3.61 \| 1200 \| 0.1075 \| 0.9572 \| 0.9572 \| \| 0.1187 \| 4.22 \| 1400 \| 0.1088 \| 0.9572 \| 0.9572 \| \| 0.1171 \| 4.82 \| 1600 \| 0.1053 \| 0.9597 \| 0.9597 \| \| 0.1127 \| 5.42 \| 1800 \| 0.1074 \| 0.9598 \| 0.9599 \| \| 0.1087 \| 6.02 \| 2000 \| 0.1091 \| 0.9574 \| 0.9574 \| \| 0.1101 \| 6.63 \| 2200 \| 0.1026 \| 0.9610 \| 0.9610 \| \| 0.1064 \| 7.23 \| 2400 \| 0.1037 \| 0.9612 \| 0.9612 \| \| 0.1036 \| 7.83 \| 2600 \| 0.1029 \| 0.9608 \| 0.9608 \| \| 0.107 \| 8.43 \| 2800 \| 0.1051 \| 0.9604 \| 0.9604 \| \| 0.1064 \| 9.04 \| 3000 \| 0.1087 \| 0.9589 \| 0.9589 \| \| 0.1017 \| 9.64 \| 3200 \| 0.1077 \| 0.9599 \| 0.9599 \| \| 0.0991 \| 10.24 \| 3400 \| 0.1037 \| 0.9602 \| 0.9602 \| \| 0.1013 \| 10.84 \| 3600 \| 0.1003 \| 0.9614 \| 0.9614 \| \| 0.0961 \| 11.45 \| 3800 \| 0.1008 \| 0.9602 \| 0.9602 \| \| 0.0949 \| 12.05 \| 4000 \| 0.1015 \| 0.9623 \| 0.9623 \| \| 0.0978 \| 12.65 \| 4200 \| 0.0998 \| 0.9625 \| 0.9625 \| \| 0.0992 \| 13.25 \| 4400 \| 0.1029 \| 0.9616 \| 0.9616 \| \| 0.0942 \| 13.86 \| 4600 \| 0.0990 \| 0.9627 \| 0.9627 \| \| 0.0942 \| 14.46 \| 4800 \| 0.1035 \| 0.9621 \| 0.9621 \| \| 0.0914 \| 15.06 \| 5000 \| 0.0984 \| 0.9627 \| 0.9627 \| \| 0.0906 \| 15.66 \| 5200 \| 0.1076 \| 0.9587 \| 0.9587 \| \| 0.0923 \| 16.27 \| 5400 \| 0.1026 \| 0.9604 \| 0.9604 \| \| 0.0887 \| 16.87 \| 5600 \| 0.0984 \| 0.9619 \| 0.9619 \| \| 0.0898 \| 17.47 \| 5800 \| 0.0975 \| 0.9627 \| 0.9627 \| \| 0.0934 \| 18.07 \| 6000 \| 0.1006 \| 0.9619 \| 0.9619 \| \| 0.0871 \| 18.67 \| 6200 \| 0.1059 \| 0.9608 \| 0.9608 \| \| 0.0863 \| 19.28 \| 6400 \| 0.1008 \| 0.9617 \| 0.9617 \| \| 0.0859 \| 19.88 \| 6600 \| 0.1005 \| 0.9627 \| 0.9627 \| \| 0.0868 \| 20.48 \| 6800 \| 0.1025 \| 0.9621 \| 0.9621 \| \| 0.0854 \| 21.08 \| 7000 \| 0.0992 \| 0.9617 \| 0.9617 \| \| 0.0852 \| 21.69 \| 7200 \| 0.0999 \| 0.9629 \| 0.9629 \| \| 0.0841 \| 22.29 \| 7400 \| 0.1009 \| 0.9631 \| 0.9631 \| \| 0.0862 \| 22.89 \| 7600 \| 0.0965 \| 0.9627 \| 0.9627 \| \| 0.083 \| 23.49 \| 7800 \| 0.1022 \| 0.9621 \| 0.9621 \| \| 0.0834 \| 24.1 \| 8000 \| 0.0979 \| 0.9640 \| 0.9640 \| \| 0.0825 \| 24.7 \| 8200 \| 0.1071 \| 0.9617 \| 0.9617 \| \| 0.0827 \| 25.3 \| 8400 \| 0.1026 \| 0.9625 \| 0.9625 \| \| 0.084 \| 25.9 \| 8600 \| 0.0993 \| 0.9627 \| 0.9627 \| \| 0.0817 \| 26.51 \| 8800 \| 0.0999 \| 0.9631 \| 0.9631 \| \| 0.0817 \| 27.11 \| 9000 \| 0.0997 \| 0.9627 \| 0.9627 \| \| 0.0811 \| 27.71 \| 9200 \| 0.1009 \| 0.9627 \| 0.9627 \| \| 0.079 \| 28.31 \| 9400 \| 0.1009 \| 0.9627 \| 0.9627 \| \| 0.0823 \| 28.92 \| 9600 \| 0.0995 \| 0.9623 \| 0.9623 \| \| 0.0789 \| 29.52 \| 9800 \| 0.0999 \| 0.9621 \| 0.9621 \| \| 0.0842 \| 30.12 \| 10000 \| 0.1002 \| 0.9631 \| 0.9631 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_8192_512_30M", "model-index": [{"name": "GUE_prom_prom_300_notata-seqsight_8192_512_30M-L8_f", "results": []}]}	mahdibaghbanzadeh/GUE_prom_prom_300_notata-seqsight_8192_512_30M-L8_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_8192_512_30M", "region:us" ]	null	2024-04-27T01:45:21+00:00	[]	[]	TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us	GUE\_prom\_prom\_300\_notata-seqsight\_8192\_512\_30M-L8\_f =========================================================== This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_8192\_512\_30M on the mahdibaghbanzadeh/GUE\_prom\_prom\_300\_notata dataset. It achieves the following results on the evaluation set: * Loss: 0.1197 * F1 Score: 0.9561 * Accuracy: 0.9561 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]	[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]
text-generation	transformers	<div align="center"> <img width="260px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/BrQCb95lmEIFz79QAmoNA.png"></div> ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/fJIOPJnY6Ff6fUiSIuMEt.png) <div align="center"> <h1>Advancing Open-source Large Language Models in Medical Domain</h1> </div> <p align="center" style="margin-top: 0px;"> <a href="https://colab.research.google.com/drive/1F5oV20InEYeAJGmBwYF9NM_QhLmjBkKJ?usp=sharing"> <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="OpenChat Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 10px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style=" margin-right: 5px;">Online Demo</span> </a> \| <a href="https://github.com/openlifescience-ai"> <img src="https://github.githubassets.com/assets/GitHub-Mark-ea2971cee799.png" alt="GitHub Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style=" margin-right: 5px;">GitHub</span> </a> \| <a href="#"> <img src="https://github.com/alpayariyak/openchat/blob/master/assets/arxiv-logomark-small-square-border.png?raw=true" alt="ArXiv Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style="margin-right: 5px;">Paper</span> </a> \| <a href="https://discord.gg/A5Fjf5zC69"> <img src="https://cloud.githubusercontent.com/assets/6291467/26705903/96c2d66e-477c-11e7-9f4e-f3c0efe96c9a.png" alt="Discord Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text">Discord</span> </a> </p> ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/KGmRE5w2sepNtwsEu8t7K.jpeg) Introducing OpenBioLLM-70B: A State-of-the-Art Open Source Biomedical Large Language Model OpenBioLLM-70B is an advanced open source language model designed specifically for the biomedical domain. Developed by Saama AI Labs, this model leverages cutting-edge techniques to achieve state-of-the-art performance on a wide range of biomedical tasks. 🏥 Biomedical Specialization: OpenBioLLM-70B is tailored for the unique language and knowledge requirements of the medical and life sciences fields. It was fine-tuned on a vast corpus of high-quality biomedical data, enabling it to understand and generate text with domain-specific accuracy and fluency. 🎓 Superior Performance: With 70 billion parameters, OpenBioLLM-70B outperforms other open source biomedical language models of similar scale. It has also demonstrated better results compared to larger proprietary & open-source models like GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 on biomedical benchmarks. 🧠 Advanced Training Techniques: OpenBioLLM-70B builds upon the powerful foundations of the Meta-Llama-3-70B-Instruct and [Meta-Llama-3-70B-Instruct](meta-llama/Meta-Llama-3-70B-Instruct) models. It incorporates the DPO dataset and fine-tuning recipe along with a custom diverse medical instruction dataset. Key components of the training pipeline include: <div align="center"> <img width="1200px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/oPchsJsEpQoGcGXVbh7YS.png"> </div> - Policy Optimization: [Direct Preference Optimization: Your Language Model is Secretly a Reward Model (DPO)](https://arxiv.org/abs/2305.18290) - Fine-tuning dataset: Custom Medical Instruct dataset (We plan to release a sample training dataset in our upcoming paper; please stay updated) This combination of cutting-edge techniques enables OpenBioLLM-70B to align with key capabilities and preferences for biomedical applications. ⚙️ Release Details: - Model Size: 70 billion parameters - Quantization: Optimized quantized versions available [Here](https://huggingface.co/aaditya/OpenBioLLM-70B-GGUF) - Language(s) (NLP): en - Developed By: [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) from Saama AI Labs - License: Meta-Llama License - Fine-tuned from models: [Meta-Llama-3-70B-Instruct](meta-llama/Meta-Llama-3-70B-Instruct) - Resources for more information: - Paper: Coming soon The model can be fine-tuned for more specialized tasks and datasets as needed. OpenBioLLM-70B represents an important step forward in democratizing advanced language AI for the biomedical community. By leveraging state-of-the-art architectures and training techniques from leading open source efforts like Llama-3, we have created a powerful tool to accelerate innovation and discovery in healthcare and the life sciences. We are excited to share OpenBioLLM-70B with researchers and developers around the world. ### Use with transformers Important: Please use the exact chat template provided by Llama-3 instruct version. Otherwise there will be a degradation in the performance. The model output can be verbose in rare cases. Please consider setting temperature = 0 to make this happen less. See the snippet below for usage with Transformers: ```python import transformers import torch model_id = "aaditya/OpenBioLLM-Llama3-70B" pipeline = transformers.pipeline( "text-generation", model=model_id, model_kwargs={"torch_dtype": torch.bfloat16}, device="auto", ) messages = [ {"role": "system", "content": "You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience. Your name is OpenBioLLM, and you were developed by Saama AI Labs. who's willing to help answer the user's query with explanation. In your explanation, leverage your deep medical expertise such as relevant anatomical structures, physiological processes, diagnostic criteria, treatment guidelines, or other pertinent medical concepts. Use precise medical terminology while still aiming to make the explanation clear and accessible to a general audience."}, {"role": "user", "content": "How can i split a 3mg or 4mg waefin pill so i can get a 2.5mg pill?"}, ] prompt = pipeline.tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) terminators = [ pipeline.tokenizer.eos_token_id, pipeline.tokenizer.convert_tokens_to_ids("<\|eot_id\|>") ] outputs = pipeline( prompt, max_new_tokens=256, eos_token_id=terminators, do_sample=True, temperature=0.0, top_p=0.9, ) print(outputs[0]["generated_text"][len(prompt):]) ``` ## Training procedure ### Training hyperparameters <details> <summary>Click to see details</summary> - learning_rate: 0.0002 - lr_scheduler: cosine - train_batch_size: 12 - eval_batch_size: 8 - GPU: H100 80GB SXM5 - num_devices: 8 - optimizer: adamw_bnb_8bit - lr_scheduler_warmup_steps: 100 - num_epochs: 4 </details> ### Peft hyperparameters <details> <summary>Click to see details</summary> - adapter: qlora - lora_r: 128 - lora_alpha: 256 - lora_dropout: 0.05 - lora_target_linear: true -lora_target_modules: - q_proj - v_proj - k_proj - o_proj - gate_proj - down_proj - up_proj </details> ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2+cu121 - Datasets 2.18.0 - Tokenizers 0.15.1 - Axolotl - Lm harness for evaluation # Benchmark Results 🔥 OpenBioLLM-70B demonstrates superior performance compared to larger models, such as GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 across 9 diverse biomedical datasets, achieving state-of-the-art results with an average score of 86.06%, despite having a significantly smaller parameter count. The model's strong performance in domain-specific tasks, such as Clinical KG, Medical Genetics, and PubMedQA, highlights its ability to effectively capture and apply biomedical knowledge. 🚨 The GPT-4, Med-PaLM-1, and Med-PaLM-2 results are taken from their official papers. Since Med-PaLM doesn't provide zero-shot accuracy, we are using 5-shot accuracy from their paper for comparison. All results presented are in the zero-shot setting, except for Med-PaLM-2 and Med-PaLM-1, which use 5-shot accuracy. \| \| Clinical KG \| Medical Genetics \| Anatomy \| Pro Medicine \| College Biology \| College Medicine \| MedQA 4 opts \| PubMedQA \| MedMCQA \| Avg \| \|--------------------\|-------------\|------------------\|---------\|--------------\|-----------------\|------------------\|--------------\|----------\|---------\|-------\| \| OpenBioLLM-70B \| 92.93 \| 93.197 \| 83.904 \| 93.75 \| 93.827 \| 85.749 \| 78.162 \| 78.97 \| 74.014 \| 86.05588 \| \| Med-PaLM-2 (5-shot) \| 88.3 \| 90 \| 77.8 \| 95.2 \| 94.4 \| 80.9 \| 79.7 \| 79.2 \| 71.3 \| 84.08 \| \| GPT-4 \| 86.04 \| 91 \| 80 \| 93.01 \| 95.14 \| 76.88 \| 78.87 \| 75.2 \| 69.52 \| 82.85 \| \| Med-PaLM-1 (Flan-PaLM, 5-shot) \| 80.4 \| 75 \| 63.7 \| 83.8 \| 88.9 \| 76.3 \| 67.6 \| 79 \| 57.6 \| 74.7 \| \| OpenBioLLM-8B \| 76.101 \| 86.1 \| 69.829 \| 78.21 \| 84.213 \| 68.042 \| 58.993 \| 74.12 \| 56.913 \| 72.502 \| \| Gemini-1.0 \| 76.7 \| 75.8 \| 66.7 \| 77.7 \| 88 \| 69.2 \| 58 \| 70.7 \| 54.3 \| 70.79 \| \| GPT-3.5 Turbo 1106 \| 74.71 \| 74 \| 72.79 \| 72.79 \| 72.91 \| 64.73 \| 57.71 \| 72.66 \| 53.79 \| 66 \| \| Meditron-70B \| 66.79 \| 69 \| 53.33 \| 71.69 \| 76.38 \| 63 \| 57.1 \| 76.6 \| 46.85 \| 64.52 \| \| gemma-7b \| 69.81 \| 70 \| 59.26 \| 66.18 \| 79.86 \| 60.12 \| 47.21 \| 76.2 \| 48.96 \| 64.18 \| \| Mistral-7B-v0.1 \| 68.68 \| 71 \| 55.56 \| 68.38 \| 68.06 \| 59.54 \| 50.82 \| 75.4 \| 48.2 \| 62.85 \| \| Apollo-7B \| 62.26 \| 72 \| 61.48 \| 69.12 \| 70.83 \| 55.49 \| 55.22 \| 39.8 \| 53.77 \| 60 \| \| MedAlpaca-7b \| 57.36 \| 69 \| 57.04 \| 67.28 \| 65.28 \| 54.34 \| 41.71 \| 72.8 \| 37.51 \| 58.03 \| \| BioMistral-7B \| 59.9 \| 64 \| 56.5 \| 60.4 \| 59 \| 54.7 \| 50.6 \| 77.5 \| 48.1 \| 57.3 \| \| AlpaCare-llama2-7b \| 49.81 \| 49 \| 45.92 \| 33.82 \| 50 \| 43.35 \| 29.77 \| 72.2 \| 34.42 \| 45.36 \| \| ClinicalGPT \| 30.56 \| 27 \| 30.37 \| 19.48 \| 25 \| 24.27 \| 26.08 \| 63.8 \| 28.18 \| 30.52 \| <div align="center"> <img width="1600px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/_SzdcJSBjZyo8RS1bTEkP.png"> </div> ## Detailed Medical Subjectwise accuracy ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/UXF-V0col0Z0sS6BGPBkE.png) # Use Cases & Examples 🚨 Below results are from the quantized version of OpenBioLLM-70B # Summarize Clinical Notes OpenBioLLM-70B can efficiently analyze and summarize complex clinical notes, EHR data, and discharge summaries, extracting key information and generating concise, structured summaries ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/xdwdBgOxNi_TfML0hKlI8.png) # Answer Medical Questions OpenBioLLM-70B can provide answers to a wide range of medical questions. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/zO95GlwOQEZqCKQF69mE6.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/OKBczKw7gWeW5xsuDpc27.png) <details> <summary>Click to see details</summary> ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/eJGHT5khppYvJb8fQ-YW4.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/Cnbwrqa_-ORHRuNRC2P6Y.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/J9DhdcvukAc9mnnW9fj2C.png) </details> # Clinical Entity Recognition OpenBioLLM-70B can perform advanced clinical entity recognition by identifying and extracting key medical concepts, such as diseases, symptoms, medications, procedures, and anatomical structures, from unstructured clinical text. By leveraging its deep understanding of medical terminology and context, the model can accurately annotate and categorize clinical entities, enabling more efficient information retrieval, data analysis, and knowledge discovery from electronic health records, research articles, and other biomedical text sources. This capability can support various downstream applications, such as clinical decision support, pharmacovigilance, and medical research. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/_69BW4k9LVABFwtxixL45.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/DKy5wYCoPhoPPUc1-x8_J.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/7WD9zCCBZT4-4XlfnIQjl.png) # Biomarkers Extraction ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/ZttoM4AiteT7gFYVhjIpN.png) # Classification OpenBioLLM-70B can perform various biomedical classification tasks, such as disease prediction, sentiment analysis, medical document categorization ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/Bf5MW1d75qT-1F_TR_hC0.png) # De-Identification OpenBioLLM-70B can detect and remove personally identifiable information (PII) from medical records, ensuring patient privacy and compliance with data protection regulations like HIPAA. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/hKX4kzm--Tw5bj6K78msy.png) Advisory Notice! While OpenBioLLM-70B leverages high-quality data sources, its outputs may still contain inaccuracies, biases, or misalignments that could pose risks if relied upon for medical decision-making without further testing and refinement. The model's performance has not yet been rigorously evaluated in randomized controlled trials or real-world healthcare environments. Therefore, we strongly advise against using OpenBioLLM-70B for any direct patient care, clinical decision support, or other professional medical purposes at this time. Its use should be limited to research, development, and exploratory applications by qualified individuals who understand its limitations. OpenBioLLM-70B is intended solely as a research tool to assist healthcare professionals and should never be considered a replacement for the professional judgment and expertise of a qualified medical doctor. Appropriately adapting and validating OpenBioLLM-70B for specific medical use cases would require significant additional work, potentially including: - Thorough testing and evaluation in relevant clinical scenarios - Alignment with evidence-based guidelines and best practices - Mitigation of potential biases and failure modes - Integration with human oversight and interpretation - Compliance with regulatory and ethical standards Always consult a qualified healthcare provider for personal medical needs. # Citation If you find OpenBioLLM-70B & 8B useful in your work, please cite the model as follows: ``` @misc{OpenBioLLMs, author = {Ankit Pal, Malaikannan Sankarasubbu}, title = {OpenBioLLMs: Advancing Open-Source Large Language Models for Healthcare and Life Sciences}, year = {2024}, publisher = {Hugging Face}, journal = {Hugging Face repository}, howpublished = {\url{https://huggingface.co/aaditya/OpenBioLLM-Llama3-70B}} } ``` The accompanying paper is currently in progress and will be released soon. <div align="center"> <h2> 💌 Contact </h2> </div> We look forward to hearing you and collaborating on this exciting project! Contributors:** - [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) [aadityaura at gmail dot com] - Saama AI Labs - Note: I am looking for a funded PhD opportunity, especially if it fits my Responsible Generative AI, Multimodal LLMs, Geometric Deep Learning, and Healthcare AI skillset. # References We thank the [Meta Team](meta-llama/Meta-Llama-3-70B-Instruct) for their amazing models! Result sources - [1] GPT-4 [Capabilities of GPT-4 on Medical Challenge Problems] (https://arxiv.org/abs/2303.13375) - [2] Med-PaLM-1 [Large Language Models Encode Clinical Knowledge](https://arxiv.org/abs/2212.13138) - [3] Med-PaLM-2 [Towards Expert-Level Medical Question Answering with Large Language Models](https://arxiv.org/abs/2305.09617) - [4] Gemini-1.0 [Gemini Goes to Med School](https://arxiv.org/abs/2402.07023)	{"language": ["en"], "license": "llama3", "tags": ["llama-3", "llama", "Mixtral", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "distillation"], "base_model": "meta-llama/Meta-Llama-3-70B-Instruct", "widget": [{"example_title": "OpenBioLLM-70B", "messages": [{"role": "system", "content": "You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience."}, {"role": "user", "content": "How long does it take for newborn jaundice to go away?"}], "output": {"text": "Newborn jaundice, also known as neonatal jaundice, is a common condition in newborns where the yellowing of the skin and eyes occurs due to an elevated level of bilirubin in the blood. Bilirubin is a yellow pigment that forms when red blood cells break down. In most cases, newborn jaundice resolves on its own without any specific treatment.\nThe duration of newborn jaundice can vary depending on several factors such as the underlying cause, gestational age at birth, and individual variations in bilirubin metabolism. Here are some general guidelines:\n1. Physiological jaundice: This is the most common type of newborn jaundice and usually appears within 24-72 hours after birth. It tends to peak between the second and fifth day of life and gradually improves over the next week or two. By the time the baby is one week old, the jaundice should have mostly resolved. 2. Breast milk jaundice: This type of jaundice occurs in breastfed babies and may appear later than physiological jaundice, typically between the fifth and fourteenth day of life. It tends to persist for a longer duration but usually resolves within six weeks after birth. 3. Pathological jaundice: This type of jaundice is less common and occurs due to an underlying medical condition that affects bilirubin metabolism or liver function. The duration of pathological jaundice depends on the specific cause and may require treatment.\nIt's important for parents to monitor their newborn's jaundice closely and seek medical advice if the jaundice progresses rapidly, becomes severe, or is accompanied by other symptoms such as poor feeding, lethargy, or excessive sleepiness. In these cases, further evaluation and management may be necessary. Remember that each baby is unique, and the timing of jaundice resolution can vary. If you have concerns about your newborn's jaundice, it's always best to consult with a healthcare professional for personalized advice and guidance."}}], "model-index": [{"name": "OpenBioLLM-70B", "results": []}]}	LoneStriker/OpenBioLLM-Llama3-70B-4.65bpw-h6-exl2	null	[ "transformers", "pytorch", "llama", "text-generation", "llama-3", "Mixtral", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "distillation", "conversational", "en", "arxiv:2305.18290", "arxiv:2303.13375", "arxiv:2212.13138", "arxiv:2305.09617", "arxiv:2402.07023", "base_model:meta-llama/Meta-Llama-3-70B-Instruct", "license:llama3", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-27T01:46:57+00:00	[ "2305.18290", "2303.13375", "2212.13138", "2305.09617", "2402.07023" ]	[ "en" ]	TAGS #transformers #pytorch #llama #text-generation #llama-3 #Mixtral #instruct #finetune #chatml #DPO #RLHF #gpt4 #distillation #conversational #en #arxiv-2305.18290 #arxiv-2303.13375 #arxiv-2212.13138 #arxiv-2305.09617 #arxiv-2402.07023 #base_model-meta-llama/Meta-Llama-3-70B-Instruct #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us	![](URL <p>!image/png</p> <div align=) Advancing Open-source Large Language Models in Medical Domain ============================================================= Online Demo \| GitHub \| [![](URL alt=)](#) \| Discord !image/jpeg Introducing OpenBioLLM-70B: A State-of-the-Art Open Source Biomedical Large Language Model OpenBioLLM-70B is an advanced open source language model designed specifically for the biomedical domain. Developed by Saama AI Labs, this model leverages cutting-edge techniques to achieve state-of-the-art performance on a wide range of biomedical tasks. Biomedical Specialization: OpenBioLLM-70B is tailored for the unique language and knowledge requirements of the medical and life sciences fields. It was fine-tuned on a vast corpus of high-quality biomedical data, enabling it to understand and generate text with domain-specific accuracy and fluency. Superior Performance: With 70 billion parameters, OpenBioLLM-70B outperforms other open source biomedical language models of similar scale. It has also demonstrated better results compared to larger proprietary & open-source models like GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 on biomedical benchmarks. Advanced Training Techniques: OpenBioLLM-70B builds upon the powerful foundations of the Meta-Llama-3-70B-Instruct and Meta-Llama-3-70B-Instruct models. It incorporates the DPO dataset and fine-tuning recipe along with a custom diverse medical instruction dataset. Key components of the training pipeline include: ![](URL </div> <ul> <li>Policy Optimization: Direct Preference Optimization: Your Language Model is Secretly a Reward Model (DPO)</li> <li>Fine-tuning dataset: Custom Medical Instruct dataset (We plan to release a sample training dataset in our upcoming paper; please stay updated)</li> </ul> <p>This combination of cutting-edge techniques enables OpenBioLLM-70B to align with key capabilities and preferences for biomedical applications.</p> <p>️ Release Details:</p> <ul> <li>Model Size: 70 billion parameters</li> <li>Quantization: Optimized quantized versions available Here</li> <li>Language(s) (NLP): en</li> <li>Developed By: Ankit Pal (Aaditya Ura) from Saama AI Labs</li> <li>License: Meta-Llama License</li> <li>Fine-tuned from models: Meta-Llama-3-70B-Instruct</li> <li>Resources for more information: <ul> <li>Paper: Coming soon</li> </ul> </li> </ul> <p>The model can be fine-tuned for more specialized tasks and datasets as needed.</p> <p>OpenBioLLM-70B represents an important step forward in democratizing advanced language AI for the biomedical community. By leveraging state-of-the-art architectures and training techniques from leading open source efforts like Llama-3, we have created a powerful tool to accelerate innovation and discovery in healthcare and the life sciences.</p> <p>We are excited to share OpenBioLLM-70B with researchers and developers around the world.</p> <h3>Use with transformers</h3> <p>Important: Please use the exact chat template provided by Llama-3 instruct version. Otherwise there will be a degradation in the performance. The model output can be verbose in rare cases. Please consider setting temperature = 0 to make this happen less.</p> <p>See the snippet below for usage with Transformers:</p> <h2>Training procedure</h2> <h3>Training hyperparameters</h3> <details> <summary>Click to see details</summary> <ul> <li>learning_rate: 0.0002</li> <li>lr_scheduler: cosine</li> <li>train_batch_size: 12</li> <li>eval_batch_size: 8</li> <li>GPU: H100 80GB SXM5</li> <li>num_devices: 8</li> <li>optimizer: adamw_bnb_8bit</li> <li>lr_scheduler_warmup_steps: 100</li> <li>num_epochs: 4</li> </ul> </details> <h3>Peft hyperparameters</h3> <details> <summary>Click to see details</summary> <ul> <li>adapter: qlora</li> <li>lora_r: 128</li> <li>lora_alpha: 256</li> <li>lora_dropout: 0.05</li> <li>lora_target_linear: true</li> </ul> <p>-lora_target_modules:</p> <ul> <li>q_proj</li> <li>v_proj</li> <li>k_proj</li> <li>o_proj</li> <li>gate_proj</li> <li>down_proj</li> <li>up_proj</li> </ul> </details> <h3>Training results</h3> <h3>Framework versions</h3> <ul> <li>Transformers 4.39.3</li> <li>Pytorch 2.1.2+cu121</li> <li>Datasets 2.18.0</li> <li>Tokenizers 0.15.1</li> <li>Axolotl</li> <li>Lm harness for evaluation</li> </ul> <h1>Benchmark Results</h1> <p>OpenBioLLM-70B demonstrates superior performance compared to larger models, such as GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 across 9 diverse biomedical datasets, achieving state-of-the-art results with an average score of 86.06%, despite having a significantly smaller parameter count. The model's strong performance in domain-specific tasks, such as Clinical KG, Medical Genetics, and PubMedQA, highlights its ability to effectively capture and apply biomedical knowledge.</p> <p>The GPT-4, Med-PaLM-1, and Med-PaLM-2 results are taken from their official papers. Since Med-PaLM doesn't provide zero-shot accuracy, we are using 5-shot accuracy from their paper for comparison. All results presented are in the zero-shot setting, except for Med-PaLM-2 and Med-PaLM-1, which use 5-shot accuracy.</p> <p></p> <div align=) ![](URL </div> <h2>Detailed Medical Subjectwise accuracy</h2> <p>!image/png</p> <h1>Use Cases & Examples</h1> <p>Below results are from the quantized version of OpenBioLLM-70B</p> <h1>Summarize Clinical Notes</h1> <p>OpenBioLLM-70B can efficiently analyze and summarize complex clinical notes, EHR data, and discharge summaries, extracting key information and generating concise, structured summaries</p> <p>!image/png</p> <h1>Answer Medical Questions</h1> <p>OpenBioLLM-70B can provide answers to a wide range of medical questions.</p> <p>!image/png !image/png</p> <details> <summary>Click to see details</summary> <p>!image/png !image/png !image/png</p> </details> <h1>Clinical Entity Recognition</h1> <p>OpenBioLLM-70B can perform advanced clinical entity recognition by identifying and extracting key medical concepts, such as diseases, symptoms, medications, procedures, and anatomical structures, from unstructured clinical text. By leveraging its deep understanding of medical terminology and context, the model can accurately annotate and categorize clinical entities, enabling more efficient information retrieval, data analysis, and knowledge discovery from electronic health records, research articles, and other biomedical text sources. This capability can support various downstream applications, such as clinical decision support, pharmacovigilance, and medical research.</p> <p>!image/png !image/png !image/png</p> <h1>Biomarkers Extraction</h1> <p>!image/png</p> <h1>Classification</h1> <p>OpenBioLLM-70B can perform various biomedical classification tasks, such as disease prediction, sentiment analysis, medical document categorization</p> <p>!image/png</p> <h1>De-Identification</h1> <p>OpenBioLLM-70B can detect and remove personally identifiable information (PII) from medical records, ensuring patient privacy and compliance with data protection regulations like HIPAA.</p> <p>!image/png</p> <p>Advisory Notice!</p> <p>While OpenBioLLM-70B leverages high-quality data sources, its outputs may still contain inaccuracies, biases, or misalignments that could pose risks if relied upon for medical decision-making without further testing and refinement. The model's performance has not yet been rigorously evaluated in randomized controlled trials or real-world healthcare environments.</p> <p>Therefore, we strongly advise against using OpenBioLLM-70B for any direct patient care, clinical decision support, or other professional medical purposes at this time. Its use should be limited to research, development, and exploratory applications by qualified individuals who understand its limitations. OpenBioLLM-70B is intended solely as a research tool to assist healthcare professionals and should never be considered a replacement for the professional judgment and expertise of a qualified medical doctor.</p> <p>Appropriately adapting and validating OpenBioLLM-70B for specific medical use cases would require significant additional work, potentially including:</p> <ul> <li>Thorough testing and evaluation in relevant clinical scenarios</li> <li>Alignment with evidence-based guidelines and best practices</li> <li>Mitigation of potential biases and failure modes</li> <li>Integration with human oversight and interpretation</li> <li>Compliance with regulatory and ethical standards</li> </ul> <p>Always consult a qualified healthcare provider for personal medical needs.</p> <p>If you find OpenBioLLM-70B & 8B useful in your work, please cite the model as follows:</p> <p>The accompanying paper is currently in progress and will be released soon.</p> <div align=) Contact -------- We look forward to hearing you and collaborating on this exciting project! Contributors: * Ankit Pal (Aaditya Ura) [aadityaura at gmail dot com] * Saama AI Labs * Note: I am looking for a funded PhD opportunity, especially if it fits my Responsible Generative AI, Multimodal LLMs, Geometric Deep Learning, and Healthcare AI skillset. References ========== We thank the Meta Team for their amazing models! Result sources * [1] GPT-4 [Capabilities of GPT-4 on Medical Challenge Problems] (URL * [2] Med-PaLM-1 Large Language Models Encode Clinical Knowledge * [3] Med-PaLM-2 Towards Expert-Level Medical Question Answering with Large Language Models * [4] Gemini-1.0 Gemini Goes to Med School	[]	[ "TAGS\n#transformers #pytorch #llama #text-generation #llama-3 #Mixtral #instruct #finetune #chatml #DPO #RLHF #gpt4 #distillation #conversational #en #arxiv-2305.18290 #arxiv-2303.13375 #arxiv-2212.13138 #arxiv-2305.09617 #arxiv-2402.07023 #base_model-meta-llama/Meta-Llama-3-70B-Instruct #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n" ]
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_prom_prom_300_notata-seqsight_8192_512_30M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_8192_512_30M](https://huggingface.co/mahdibaghbanzadeh/seqsight_8192_512_30M) on the [mahdibaghbanzadeh/GUE_prom_prom_300_notata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_300_notata) dataset. It achieves the following results on the evaluation set: - Loss: 0.1357 - F1 Score: 0.9563 - Accuracy: 0.9563 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.2577 \| 0.6 \| 200 \| 0.1254 \| 0.9495 \| 0.9495 \| \| 0.1373 \| 1.2 \| 400 \| 0.1190 \| 0.9538 \| 0.9538 \| \| 0.1331 \| 1.81 \| 600 \| 0.1103 \| 0.9567 \| 0.9567 \| \| 0.1203 \| 2.41 \| 800 \| 0.1086 \| 0.9580 \| 0.9580 \| \| 0.117 \| 3.01 \| 1000 \| 0.1067 \| 0.9606 \| 0.9606 \| \| 0.1152 \| 3.61 \| 1200 \| 0.1070 \| 0.9578 \| 0.9578 \| \| 0.1095 \| 4.22 \| 1400 \| 0.1018 \| 0.9601 \| 0.9601 \| \| 0.1085 \| 4.82 \| 1600 \| 0.1010 \| 0.9601 \| 0.9601 \| \| 0.1024 \| 5.42 \| 1800 \| 0.1047 \| 0.9587 \| 0.9587 \| \| 0.0985 \| 6.02 \| 2000 \| 0.1062 \| 0.9593 \| 0.9593 \| \| 0.0992 \| 6.63 \| 2200 \| 0.0972 \| 0.9627 \| 0.9627 \| \| 0.0949 \| 7.23 \| 2400 \| 0.1007 \| 0.9627 \| 0.9627 \| \| 0.0927 \| 7.83 \| 2600 \| 0.0981 \| 0.9614 \| 0.9614 \| \| 0.093 \| 8.43 \| 2800 \| 0.1121 \| 0.9602 \| 0.9602 \| \| 0.0913 \| 9.04 \| 3000 \| 0.1099 \| 0.9593 \| 0.9593 \| \| 0.0873 \| 9.64 \| 3200 \| 0.0982 \| 0.9625 \| 0.9625 \| \| 0.0817 \| 10.24 \| 3400 \| 0.0991 \| 0.9653 \| 0.9653 \| \| 0.0849 \| 10.84 \| 3600 \| 0.0946 \| 0.9648 \| 0.9648 \| \| 0.0793 \| 11.45 \| 3800 \| 0.0945 \| 0.9653 \| 0.9653 \| \| 0.0775 \| 12.05 \| 4000 \| 0.0976 \| 0.9663 \| 0.9663 \| \| 0.0794 \| 12.65 \| 4200 \| 0.0920 \| 0.9661 \| 0.9661 \| \| 0.0761 \| 13.25 \| 4400 \| 0.1008 \| 0.9636 \| 0.9636 \| \| 0.0744 \| 13.86 \| 4600 \| 0.0911 \| 0.9655 \| 0.9655 \| \| 0.0725 \| 14.46 \| 4800 \| 0.0953 \| 0.9665 \| 0.9665 \| \| 0.069 \| 15.06 \| 5000 \| 0.0946 \| 0.9657 \| 0.9657 \| \| 0.0673 \| 15.66 \| 5200 \| 0.1017 \| 0.9647 \| 0.9648 \| \| 0.0683 \| 16.27 \| 5400 \| 0.0974 \| 0.9666 \| 0.9666 \| \| 0.0648 \| 16.87 \| 5600 \| 0.0977 \| 0.9659 \| 0.9659 \| \| 0.0618 \| 17.47 \| 5800 \| 0.0996 \| 0.9663 \| 0.9663 \| \| 0.0661 \| 18.07 \| 6000 \| 0.0960 \| 0.9685 \| 0.9685 \| \| 0.0604 \| 18.67 \| 6200 \| 0.1063 \| 0.9653 \| 0.9653 \| \| 0.0578 \| 19.28 \| 6400 \| 0.1030 \| 0.9670 \| 0.9670 \| \| 0.0597 \| 19.88 \| 6600 \| 0.1022 \| 0.9674 \| 0.9674 \| \| 0.0561 \| 20.48 \| 6800 \| 0.1018 \| 0.9680 \| 0.9680 \| \| 0.0561 \| 21.08 \| 7000 \| 0.1037 \| 0.9659 \| 0.9659 \| \| 0.0551 \| 21.69 \| 7200 \| 0.1060 \| 0.9661 \| 0.9661 \| \| 0.0553 \| 22.29 \| 7400 \| 0.1049 \| 0.9680 \| 0.9680 \| \| 0.0551 \| 22.89 \| 7600 \| 0.1014 \| 0.9661 \| 0.9661 \| \| 0.0525 \| 23.49 \| 7800 \| 0.1117 \| 0.9648 \| 0.9648 \| \| 0.0512 \| 24.1 \| 8000 \| 0.1035 \| 0.9682 \| 0.9682 \| \| 0.05 \| 24.7 \| 8200 \| 0.1084 \| 0.9648 \| 0.9648 \| \| 0.0496 \| 25.3 \| 8400 \| 0.1062 \| 0.9672 \| 0.9672 \| \| 0.0507 \| 25.9 \| 8600 \| 0.1045 \| 0.9666 \| 0.9666 \| \| 0.0467 \| 26.51 \| 8800 \| 0.1060 \| 0.9682 \| 0.9682 \| \| 0.0493 \| 27.11 \| 9000 \| 0.1060 \| 0.9672 \| 0.9672 \| \| 0.0459 \| 27.71 \| 9200 \| 0.1086 \| 0.9666 \| 0.9666 \| \| 0.0451 \| 28.31 \| 9400 \| 0.1074 \| 0.9672 \| 0.9672 \| \| 0.0477 \| 28.92 \| 9600 \| 0.1075 \| 0.9672 \| 0.9672 \| \| 0.0438 \| 29.52 \| 9800 \| 0.1086 \| 0.9680 \| 0.9680 \| \| 0.0471 \| 30.12 \| 10000 \| 0.1084 \| 0.9676 \| 0.9676 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_8192_512_30M", "model-index": [{"name": "GUE_prom_prom_300_notata-seqsight_8192_512_30M-L32_f", "results": []}]}	mahdibaghbanzadeh/GUE_prom_prom_300_notata-seqsight_8192_512_30M-L32_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_8192_512_30M", "region:us" ]	null	2024-04-27T01:49:08+00:00	[]	[]	TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us	GUE\_prom\_prom\_300\_notata-seqsight\_8192\_512\_30M-L32\_f ============================================================ This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_8192\_512\_30M on the mahdibaghbanzadeh/GUE\_prom\_prom\_300\_notata dataset. It achieves the following results on the evaluation set: * Loss: 0.1357 * F1 Score: 0.9563 * Accuracy: 0.9563 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]	[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_prom_prom_core_all-seqsight_8192_512_30M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_8192_512_30M](https://huggingface.co/mahdibaghbanzadeh/seqsight_8192_512_30M) on the [mahdibaghbanzadeh/GUE_prom_prom_core_all](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_core_all) dataset. It achieves the following results on the evaluation set: - Loss: 0.4231 - F1 Score: 0.8098 - Accuracy: 0.8098 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.5588 \| 0.54 \| 200 \| 0.4980 \| 0.7634 \| 0.7649 \| \| 0.4803 \| 1.08 \| 400 \| 0.4776 \| 0.7765 \| 0.7772 \| \| 0.4628 \| 1.62 \| 600 \| 0.4580 \| 0.7869 \| 0.7870 \| \| 0.4571 \| 2.16 \| 800 \| 0.4592 \| 0.7882 \| 0.7883 \| \| 0.4496 \| 2.7 \| 1000 \| 0.4558 \| 0.7871 \| 0.7875 \| \| 0.4478 \| 3.24 \| 1200 \| 0.4512 \| 0.7892 \| 0.7895 \| \| 0.4421 \| 3.78 \| 1400 \| 0.4567 \| 0.7850 \| 0.7860 \| \| 0.4374 \| 4.32 \| 1600 \| 0.4588 \| 0.7866 \| 0.7873 \| \| 0.4377 \| 4.86 \| 1800 \| 0.4518 \| 0.7891 \| 0.7895 \| \| 0.4366 \| 5.41 \| 2000 \| 0.4540 \| 0.7877 \| 0.7883 \| \| 0.432 \| 5.95 \| 2200 \| 0.4466 \| 0.7939 \| 0.7939 \| \| 0.4349 \| 6.49 \| 2400 \| 0.4450 \| 0.7932 \| 0.7934 \| \| 0.4274 \| 7.03 \| 2600 \| 0.4426 \| 0.7986 \| 0.7986 \| \| 0.4312 \| 7.57 \| 2800 \| 0.4462 \| 0.7942 \| 0.7944 \| \| 0.4242 \| 8.11 \| 3000 \| 0.4489 \| 0.7917 \| 0.7922 \| \| 0.427 \| 8.65 \| 3200 \| 0.4402 \| 0.7966 \| 0.7966 \| \| 0.4282 \| 9.19 \| 3400 \| 0.4431 \| 0.7969 \| 0.7970 \| \| 0.4242 \| 9.73 \| 3600 \| 0.4561 \| 0.7871 \| 0.7882 \| \| 0.4275 \| 10.27 \| 3800 \| 0.4456 \| 0.7933 \| 0.7937 \| \| 0.4224 \| 10.81 \| 4000 \| 0.4426 \| 0.7976 \| 0.7976 \| \| 0.4226 \| 11.35 \| 4200 \| 0.4479 \| 0.7925 \| 0.7929 \| \| 0.4237 \| 11.89 \| 4400 \| 0.4473 \| 0.7917 \| 0.7924 \| \| 0.4201 \| 12.43 \| 4600 \| 0.4396 \| 0.7998 \| 0.7998 \| \| 0.4193 \| 12.97 \| 4800 \| 0.4427 \| 0.7960 \| 0.7963 \| \| 0.4218 \| 13.51 \| 5000 \| 0.4529 \| 0.7881 \| 0.7894 \| \| 0.4195 \| 14.05 \| 5200 \| 0.4406 \| 0.7973 \| 0.7975 \| \| 0.4216 \| 14.59 \| 5400 \| 0.4386 \| 0.7969 \| 0.7970 \| \| 0.4208 \| 15.14 \| 5600 \| 0.4366 \| 0.7986 \| 0.7986 \| \| 0.4199 \| 15.68 \| 5800 \| 0.4480 \| 0.7944 \| 0.7951 \| \| 0.4136 \| 16.22 \| 6000 \| 0.4459 \| 0.7959 \| 0.7965 \| \| 0.4206 \| 16.76 \| 6200 \| 0.4396 \| 0.7950 \| 0.7954 \| \| 0.4201 \| 17.3 \| 6400 \| 0.4373 \| 0.7973 \| 0.7976 \| \| 0.4166 \| 17.84 \| 6600 \| 0.4403 \| 0.7954 \| 0.7958 \| \| 0.4152 \| 18.38 \| 6800 \| 0.4479 \| 0.7956 \| 0.7965 \| \| 0.4167 \| 18.92 \| 7000 \| 0.4396 \| 0.7961 \| 0.7966 \| \| 0.4113 \| 19.46 \| 7200 \| 0.4400 \| 0.7975 \| 0.7978 \| \| 0.4222 \| 20.0 \| 7400 \| 0.4378 \| 0.7965 \| 0.7968 \| \| 0.4179 \| 20.54 \| 7600 \| 0.4394 \| 0.7961 \| 0.7965 \| \| 0.4143 \| 21.08 \| 7800 \| 0.4409 \| 0.7966 \| 0.7970 \| \| 0.4166 \| 21.62 \| 8000 \| 0.4361 \| 0.7959 \| 0.7961 \| \| 0.4143 \| 22.16 \| 8200 \| 0.4396 \| 0.7978 \| 0.7981 \| \| 0.4185 \| 22.7 \| 8400 \| 0.4414 \| 0.7981 \| 0.7986 \| \| 0.4112 \| 23.24 \| 8600 \| 0.4363 \| 0.7959 \| 0.7961 \| \| 0.4098 \| 23.78 \| 8800 \| 0.4384 \| 0.7970 \| 0.7973 \| \| 0.4146 \| 24.32 \| 9000 \| 0.4372 \| 0.7965 \| 0.7968 \| \| 0.4143 \| 24.86 \| 9200 \| 0.4373 \| 0.7963 \| 0.7966 \| \| 0.4212 \| 25.41 \| 9400 \| 0.4369 \| 0.7972 \| 0.7975 \| \| 0.4085 \| 25.95 \| 9600 \| 0.4369 \| 0.7971 \| 0.7973 \| \| 0.4184 \| 26.49 \| 9800 \| 0.4384 \| 0.7969 \| 0.7973 \| \| 0.4112 \| 27.03 \| 10000 \| 0.4381 \| 0.7970 \| 0.7973 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_8192_512_30M", "model-index": [{"name": "GUE_prom_prom_core_all-seqsight_8192_512_30M-L1_f", "results": []}]}	mahdibaghbanzadeh/GUE_prom_prom_core_all-seqsight_8192_512_30M-L1_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_8192_512_30M", "region:us" ]	null	2024-04-27T01:51:59+00:00	[]	[]	TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us	GUE\_prom\_prom\_core\_all-seqsight\_8192\_512\_30M-L1\_f ========================================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_8192\_512\_30M on the mahdibaghbanzadeh/GUE\_prom\_prom\_core\_all dataset. It achieves the following results on the evaluation set: * Loss: 0.4231 * F1 Score: 0.8098 * Accuracy: 0.8098 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]	[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_prom_prom_core_all-seqsight_8192_512_30M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_8192_512_30M](https://huggingface.co/mahdibaghbanzadeh/seqsight_8192_512_30M) on the [mahdibaghbanzadeh/GUE_prom_prom_core_all](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_core_all) dataset. It achieves the following results on the evaluation set: - Loss: 0.4079 - F1 Score: 0.8099 - Accuracy: 0.8100 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.5264 \| 0.54 \| 200 \| 0.4686 \| 0.7814 \| 0.7818 \| \| 0.4549 \| 1.08 \| 400 \| 0.4736 \| 0.7859 \| 0.7872 \| \| 0.4386 \| 1.62 \| 600 \| 0.4442 \| 0.7933 \| 0.7934 \| \| 0.4338 \| 2.16 \| 800 \| 0.4449 \| 0.7924 \| 0.7927 \| \| 0.4286 \| 2.7 \| 1000 \| 0.4395 \| 0.7962 \| 0.7965 \| \| 0.4289 \| 3.24 \| 1200 \| 0.4338 \| 0.7990 \| 0.7992 \| \| 0.4217 \| 3.78 \| 1400 \| 0.4411 \| 0.7937 \| 0.7944 \| \| 0.4167 \| 4.32 \| 1600 \| 0.4407 \| 0.7983 \| 0.7986 \| \| 0.4204 \| 4.86 \| 1800 \| 0.4373 \| 0.7972 \| 0.7975 \| \| 0.4174 \| 5.41 \| 2000 \| 0.4398 \| 0.7970 \| 0.7975 \| \| 0.4149 \| 5.95 \| 2200 \| 0.4392 \| 0.8025 \| 0.8025 \| \| 0.4181 \| 6.49 \| 2400 \| 0.4310 \| 0.8040 \| 0.8041 \| \| 0.4099 \| 7.03 \| 2600 \| 0.4356 \| 0.8042 \| 0.8042 \| \| 0.4133 \| 7.57 \| 2800 \| 0.4323 \| 0.8007 \| 0.8007 \| \| 0.4071 \| 8.11 \| 3000 \| 0.4342 \| 0.7974 \| 0.7976 \| \| 0.4064 \| 8.65 \| 3200 \| 0.4309 \| 0.8012 \| 0.8014 \| \| 0.4103 \| 9.19 \| 3400 \| 0.4332 \| 0.8013 \| 0.8014 \| \| 0.4048 \| 9.73 \| 3600 \| 0.4405 \| 0.7982 \| 0.7988 \| \| 0.4089 \| 10.27 \| 3800 \| 0.4359 \| 0.8012 \| 0.8015 \| \| 0.404 \| 10.81 \| 4000 \| 0.4351 \| 0.8049 \| 0.8049 \| \| 0.4014 \| 11.35 \| 4200 \| 0.4333 \| 0.8017 \| 0.8019 \| \| 0.4031 \| 11.89 \| 4400 \| 0.4320 \| 0.8016 \| 0.8020 \| \| 0.3985 \| 12.43 \| 4600 \| 0.4300 \| 0.8035 \| 0.8035 \| \| 0.3992 \| 12.97 \| 4800 \| 0.4322 \| 0.8041 \| 0.8042 \| \| 0.3996 \| 13.51 \| 5000 \| 0.4400 \| 0.7977 \| 0.7986 \| \| 0.3982 \| 14.05 \| 5200 \| 0.4290 \| 0.8077 \| 0.8078 \| \| 0.3978 \| 14.59 \| 5400 \| 0.4289 \| 0.8055 \| 0.8056 \| \| 0.3976 \| 15.14 \| 5600 \| 0.4280 \| 0.8074 \| 0.8074 \| \| 0.395 \| 15.68 \| 5800 \| 0.4372 \| 0.8009 \| 0.8015 \| \| 0.3912 \| 16.22 \| 6000 \| 0.4322 \| 0.8028 \| 0.8034 \| \| 0.3948 \| 16.76 \| 6200 \| 0.4253 \| 0.8059 \| 0.8063 \| \| 0.3948 \| 17.3 \| 6400 \| 0.4250 \| 0.8069 \| 0.8071 \| \| 0.3926 \| 17.84 \| 6600 \| 0.4285 \| 0.8068 \| 0.8069 \| \| 0.3893 \| 18.38 \| 6800 \| 0.4347 \| 0.8002 \| 0.8010 \| \| 0.3894 \| 18.92 \| 7000 \| 0.4267 \| 0.8048 \| 0.8052 \| \| 0.3871 \| 19.46 \| 7200 \| 0.4276 \| 0.8072 \| 0.8074 \| \| 0.3959 \| 20.0 \| 7400 \| 0.4258 \| 0.8069 \| 0.8071 \| \| 0.3886 \| 20.54 \| 7600 \| 0.4261 \| 0.8075 \| 0.8078 \| \| 0.3876 \| 21.08 \| 7800 \| 0.4278 \| 0.8088 \| 0.8090 \| \| 0.3883 \| 21.62 \| 8000 \| 0.4230 \| 0.8094 \| 0.8095 \| \| 0.3849 \| 22.16 \| 8200 \| 0.4264 \| 0.8072 \| 0.8074 \| \| 0.3894 \| 22.7 \| 8400 \| 0.4281 \| 0.8060 \| 0.8064 \| \| 0.3834 \| 23.24 \| 8600 \| 0.4238 \| 0.8075 \| 0.8076 \| \| 0.3827 \| 23.78 \| 8800 \| 0.4259 \| 0.8069 \| 0.8071 \| \| 0.3844 \| 24.32 \| 9000 \| 0.4245 \| 0.8082 \| 0.8083 \| \| 0.3844 \| 24.86 \| 9200 \| 0.4240 \| 0.8081 \| 0.8083 \| \| 0.3904 \| 25.41 \| 9400 \| 0.4242 \| 0.8069 \| 0.8071 \| \| 0.3788 \| 25.95 \| 9600 \| 0.4256 \| 0.8080 \| 0.8081 \| \| 0.3894 \| 26.49 \| 9800 \| 0.4259 \| 0.8055 \| 0.8057 \| \| 0.381 \| 27.03 \| 10000 \| 0.4260 \| 0.8067 \| 0.8069 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_8192_512_30M", "model-index": [{"name": "GUE_prom_prom_core_all-seqsight_8192_512_30M-L8_f", "results": []}]}	mahdibaghbanzadeh/GUE_prom_prom_core_all-seqsight_8192_512_30M-L8_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_8192_512_30M", "region:us" ]	null	2024-04-27T01:54:10+00:00	[]	[]	TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us	GUE\_prom\_prom\_core\_all-seqsight\_8192\_512\_30M-L8\_f ========================================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_8192\_512\_30M on the mahdibaghbanzadeh/GUE\_prom\_prom\_core\_all dataset. It achieves the following results on the evaluation set: * Loss: 0.4079 * F1 Score: 0.8099 * Accuracy: 0.8100 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]	[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]
token-classification	transformers	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # model_3_edges This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 3e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results ### Framework versions - Transformers 4.40.0 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1	{"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "distilbert/distilbert-base-uncased", "model-index": [{"name": "model_3_edges", "results": []}]}	anirudhramoo/model_3_edges	null	[ "transformers", "tensorboard", "safetensors", "distilbert", "token-classification", "generated_from_trainer", "base_model:distilbert/distilbert-base-uncased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-27T01:55:41+00:00	[]	[]	TAGS #transformers #tensorboard #safetensors #distilbert #token-classification #generated_from_trainer #base_model-distilbert/distilbert-base-uncased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us	# model_3_edges This model is a fine-tuned version of distilbert/distilbert-base-uncased on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 3e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results ### Framework versions - Transformers 4.40.0 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1	[ "# model_3_edges\n\nThis model is a fine-tuned version of distilbert/distilbert-base-uncased on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 3e-05\n- train_batch_size: 32\n- eval_batch_size: 32\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 3", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]	[ "TAGS\n#transformers #tensorboard #safetensors #distilbert #token-classification #generated_from_trainer #base_model-distilbert/distilbert-base-uncased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "# model_3_edges\n\nThis model is a fine-tuned version of distilbert/distilbert-base-uncased on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 3e-05\n- train_batch_size: 32\n- eval_batch_size: 32\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 3", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]
null	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	jd0g/Mistral-7B-NLI-v1.0	null	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-04-27T01:55:53+00:00	[ "1910.09700" ]	[]	TAGS #transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us	# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact	[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]	[ "TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]
text-generation	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	pruning/yegu2vs	null	[ "transformers", "safetensors", "stablelm", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-27T01:59:04+00:00	[ "1910.09700" ]	[]	TAGS #transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us	# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact	[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]	[ "TAGS\n#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]
text-generation	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	pruning/5ww0fon	null	[ "transformers", "safetensors", "stablelm", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-27T01:59:04+00:00	[ "1910.09700" ]	[]	TAGS #transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us	# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact	[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]	[ "TAGS\n#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]
text-generation	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	pruning/lfucypx	null	[ "transformers", "safetensors", "stablelm", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-27T01:59:04+00:00	[ "1910.09700" ]	[]	TAGS #transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us	# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact	[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]	[ "TAGS\n#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]
text-generation	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	pruning/fcku0mx	null	[ "transformers", "safetensors", "stablelm", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-27T01:59:04+00:00	[ "1910.09700" ]	[]	TAGS #transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us	# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact	[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]	[ "TAGS\n#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]
text-generation	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	pruning/ehgnwni	null	[ "transformers", "safetensors", "stablelm", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-27T01:59:04+00:00	[ "1910.09700" ]	[]	TAGS #transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us	# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact	[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]	[ "TAGS\n#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]
text-generation	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	pruning/2evd8w5	null	[ "transformers", "safetensors", "stablelm", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-27T01:59:04+00:00	[ "1910.09700" ]	[]	TAGS #transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us	# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact	[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]	[ "TAGS\n#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]
text-generation	transformers	# Description 4-bit AWQ-quantized version of [stylellm/HongLouMeng-6b](https://huggingface.co/stylellm/HongLouMeng-6b)	{"license": "other", "license_name": "yi-license", "license_link": "https://huggingface.co/01-ai/Yi-6B/blob/main/LICENSE"}	stylellm/HongLouMeng-6b-AWQ	null	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "license:other", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]	null	2024-04-27T01:59:09+00:00	[]	[]	TAGS #transformers #safetensors #llama #text-generation #conversational #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us	# Description 4-bit AWQ-quantized version of stylellm/HongLouMeng-6b	[ "# Description\n4-bit AWQ-quantized version of stylellm/HongLouMeng-6b" ]	[ "TAGS\n#transformers #safetensors #llama #text-generation #conversational #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n", "# Description\n4-bit AWQ-quantized version of stylellm/HongLouMeng-6b" ]
null	transformers	## About <!-- ### quantize_version: 1 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: --> <!-- ### vocab_type: --> weighted/imatrix quants of https://huggingface.co/aaditya/OpenBioLLM-Llama3-70B <!-- provided-files --> static quants are available at https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-IQ1_S.gguf) \| i1-IQ1_S \| 15.4 \| for the desperate \| \| [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-IQ1_M.gguf) \| i1-IQ1_M \| 16.9 \| for the desperate \| \| [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-IQ2_XXS.gguf) \| i1-IQ2_XXS \| 19.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-IQ2_XS.gguf) \| i1-IQ2_XS \| 21.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-IQ2_S.gguf) \| i1-IQ2_S \| 22.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-IQ2_M.gguf) \| i1-IQ2_M \| 24.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-Q2_K.gguf) \| i1-Q2_K \| 26.5 \| IQ3_XXS probably better \| \| [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-IQ3_XXS.gguf) \| i1-IQ3_XXS \| 27.6 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-IQ3_XS.gguf) \| i1-IQ3_XS \| 29.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-IQ3_S.gguf) \| i1-IQ3_S \| 31.0 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-Q3_K_S.gguf) \| i1-Q3_K_S \| 31.0 \| IQ3_XS probably better \| \| [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-IQ3_M.gguf) \| i1-IQ3_M \| 32.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-Q3_K_M.gguf) \| i1-Q3_K_M \| 34.4 \| IQ3_S probably better \| \| [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-Q3_K_L.gguf) \| i1-Q3_K_L \| 37.2 \| IQ3_M probably better \| \| [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-IQ4_XS.gguf) \| i1-IQ4_XS \| 38.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-Q4_0.gguf) \| i1-Q4_0 \| 40.2 \| fast, low quality \| \| [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-Q4_K_S.gguf) \| i1-Q4_K_S \| 40.4 \| optimal size/speed/quality \| \| [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-Q4_K_M.gguf) \| i1-Q4_K_M \| 42.6 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-Q5_K_S.gguf) \| i1-Q5_K_S \| 48.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-Q5_K_M.gguf) \| i1-Q5_K_M \| 50.1 \| \| \| [PART 1](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-Q6_K.gguf.part2of2) \| i1-Q6_K \| 58.0 \| practically like static Q6_K \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. <!-- end -->	{"language": ["en"], "license": "llama3", "library_name": "transformers", "tags": ["llama-3", "llama", "Mixtral", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "distillation"], "base_model": "aaditya/OpenBioLLM-Llama3-70B", "quantized_by": "mradermacher"}	mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF	null	[ "transformers", "gguf", "llama-3", "llama", "Mixtral", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "distillation", "en", "base_model:aaditya/OpenBioLLM-Llama3-70B", "license:llama3", "endpoints_compatible", "region:us" ]	null	2024-04-27T01:59:56+00:00	[]	[ "en" ]	TAGS #transformers #gguf #llama-3 #llama #Mixtral #instruct #finetune #chatml #DPO #RLHF #gpt4 #distillation #en #base_model-aaditya/OpenBioLLM-Llama3-70B #license-llama3 #endpoints_compatible #region-us	About ----- weighted/imatrix quants of URL static quants are available at URL Usage ----- If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. Provided Quants --------------- (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): !URL And here are Artefact2's thoughts on the matter: URL FAQ / Model Request ------------------- See URL for some answers to questions you might have and/or if you want some other model quantized. Thanks ------ I thank my company, nethype GmbH, for letting me use its servers and providing upgrades to my workstation to enable this work in my free time.	[]	[ "TAGS\n#transformers #gguf #llama-3 #llama #Mixtral #instruct #finetune #chatml #DPO #RLHF #gpt4 #distillation #en #base_model-aaditya/OpenBioLLM-Llama3-70B #license-llama3 #endpoints_compatible #region-us \n" ]
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_prom_prom_core_all-seqsight_8192_512_30M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_8192_512_30M](https://huggingface.co/mahdibaghbanzadeh/seqsight_8192_512_30M) on the [mahdibaghbanzadeh/GUE_prom_prom_core_all](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_core_all) dataset. It achieves the following results on the evaluation set: - Loss: 0.4067 - F1 Score: 0.8189 - Accuracy: 0.8189 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.5065 \| 0.54 \| 200 \| 0.4591 \| 0.7903 \| 0.7904 \| \| 0.446 \| 1.08 \| 400 \| 0.4695 \| 0.7843 \| 0.7860 \| \| 0.4311 \| 1.62 \| 600 \| 0.4409 \| 0.7956 \| 0.7959 \| \| 0.4271 \| 2.16 \| 800 \| 0.4442 \| 0.7928 \| 0.7932 \| \| 0.4215 \| 2.7 \| 1000 \| 0.4350 \| 0.8007 \| 0.8010 \| \| 0.4218 \| 3.24 \| 1200 \| 0.4286 \| 0.8030 \| 0.8030 \| \| 0.4131 \| 3.78 \| 1400 \| 0.4343 \| 0.7960 \| 0.7965 \| \| 0.4094 \| 4.32 \| 1600 \| 0.4329 \| 0.7994 \| 0.7995 \| \| 0.4105 \| 4.86 \| 1800 \| 0.4361 \| 0.7977 \| 0.7980 \| \| 0.406 \| 5.41 \| 2000 \| 0.4350 \| 0.8007 \| 0.8010 \| \| 0.4037 \| 5.95 \| 2200 \| 0.4336 \| 0.8078 \| 0.8078 \| \| 0.4044 \| 6.49 \| 2400 \| 0.4245 \| 0.8040 \| 0.8041 \| \| 0.3964 \| 7.03 \| 2600 \| 0.4262 \| 0.8053 \| 0.8054 \| \| 0.3959 \| 7.57 \| 2800 \| 0.4255 \| 0.8037 \| 0.8037 \| \| 0.3925 \| 8.11 \| 3000 \| 0.4263 \| 0.8048 \| 0.8049 \| \| 0.3865 \| 8.65 \| 3200 \| 0.4245 \| 0.8067 \| 0.8069 \| \| 0.3904 \| 9.19 \| 3400 \| 0.4300 \| 0.8071 \| 0.8071 \| \| 0.3841 \| 9.73 \| 3600 \| 0.4312 \| 0.8044 \| 0.8049 \| \| 0.3855 \| 10.27 \| 3800 \| 0.4348 \| 0.8053 \| 0.8056 \| \| 0.3805 \| 10.81 \| 4000 \| 0.4330 \| 0.8063 \| 0.8063 \| \| 0.3749 \| 11.35 \| 4200 \| 0.4266 \| 0.8092 \| 0.8093 \| \| 0.3775 \| 11.89 \| 4400 \| 0.4275 \| 0.8081 \| 0.8084 \| \| 0.3708 \| 12.43 \| 4600 \| 0.4262 \| 0.8130 \| 0.8130 \| \| 0.3731 \| 12.97 \| 4800 \| 0.4267 \| 0.8098 \| 0.8100 \| \| 0.3709 \| 13.51 \| 5000 \| 0.4308 \| 0.8051 \| 0.8057 \| \| 0.3675 \| 14.05 \| 5200 \| 0.4300 \| 0.8127 \| 0.8127 \| \| 0.3654 \| 14.59 \| 5400 \| 0.4312 \| 0.8115 \| 0.8117 \| \| 0.3665 \| 15.14 \| 5600 \| 0.4265 \| 0.8123 \| 0.8123 \| \| 0.3618 \| 15.68 \| 5800 \| 0.4333 \| 0.8090 \| 0.8093 \| \| 0.3589 \| 16.22 \| 6000 \| 0.4283 \| 0.8101 \| 0.8105 \| \| 0.3591 \| 16.76 \| 6200 \| 0.4188 \| 0.8100 \| 0.8103 \| \| 0.3592 \| 17.3 \| 6400 \| 0.4231 \| 0.8118 \| 0.8120 \| \| 0.3575 \| 17.84 \| 6600 \| 0.4267 \| 0.8109 \| 0.8110 \| \| 0.3505 \| 18.38 \| 6800 \| 0.4350 \| 0.8037 \| 0.8044 \| \| 0.3527 \| 18.92 \| 7000 \| 0.4257 \| 0.8120 \| 0.8123 \| \| 0.3468 \| 19.46 \| 7200 \| 0.4292 \| 0.8099 \| 0.8101 \| \| 0.3558 \| 20.0 \| 7400 \| 0.4245 \| 0.8129 \| 0.8130 \| \| 0.346 \| 20.54 \| 7600 \| 0.4263 \| 0.8092 \| 0.8095 \| \| 0.3479 \| 21.08 \| 7800 \| 0.4252 \| 0.8115 \| 0.8117 \| \| 0.3449 \| 21.62 \| 8000 \| 0.4228 \| 0.8111 \| 0.8111 \| \| 0.3426 \| 22.16 \| 8200 \| 0.4274 \| 0.8125 \| 0.8127 \| \| 0.3462 \| 22.7 \| 8400 \| 0.4288 \| 0.8082 \| 0.8086 \| \| 0.3417 \| 23.24 \| 8600 \| 0.4225 \| 0.8141 \| 0.8142 \| \| 0.3408 \| 23.78 \| 8800 \| 0.4259 \| 0.8131 \| 0.8132 \| \| 0.3422 \| 24.32 \| 9000 \| 0.4230 \| 0.8131 \| 0.8132 \| \| 0.3403 \| 24.86 \| 9200 \| 0.4245 \| 0.8137 \| 0.8139 \| \| 0.3457 \| 25.41 \| 9400 \| 0.4242 \| 0.8125 \| 0.8127 \| \| 0.3364 \| 25.95 \| 9600 \| 0.4270 \| 0.8134 \| 0.8135 \| \| 0.3418 \| 26.49 \| 9800 \| 0.4278 \| 0.8111 \| 0.8113 \| \| 0.3354 \| 27.03 \| 10000 \| 0.4276 \| 0.8120 \| 0.8122 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_8192_512_30M", "model-index": [{"name": "GUE_prom_prom_core_all-seqsight_8192_512_30M-L32_f", "results": []}]}	mahdibaghbanzadeh/GUE_prom_prom_core_all-seqsight_8192_512_30M-L32_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_8192_512_30M", "region:us" ]	null	2024-04-27T02:01:26+00:00	[]	[]	TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us	GUE\_prom\_prom\_core\_all-seqsight\_8192\_512\_30M-L32\_f ========================================================== This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_8192\_512\_30M on the mahdibaghbanzadeh/GUE\_prom\_prom\_core\_all dataset. It achieves the following results on the evaluation set: * Loss: 0.4067 * F1 Score: 0.8189 * Accuracy: 0.8189 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]	[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]
text-generation	transformers	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # 0.001_4iters_bs256_nodpo_only4w_iter_3 This model is a fine-tuned version of [ShenaoZhang/0.001_4iters_bs256_nodpo_only4w_iter_2](https://huggingface.co/ShenaoZhang/0.001_4iters_bs256_nodpo_only4w_iter_2) on the updated and the original datasets. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-07 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - distributed_type: multi-GPU - num_devices: 8 - gradient_accumulation_steps: 4 - total_train_batch_size: 256 - total_eval_batch_size: 64 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 1 ### Training results ### Framework versions - Transformers 4.40.0 - Pytorch 2.1.2+cu121 - Datasets 2.14.6 - Tokenizers 0.19.1	{"license": "mit", "tags": ["alignment-handbook", "trl", "dpo", "generated_from_trainer", "trl", "dpo", "generated_from_trainer"], "datasets": ["updated", "original"], "base_model": "ShenaoZhang/0.001_4iters_bs256_nodpo_only4w_iter_2", "model-index": [{"name": "0.001_4iters_bs256_nodpo_only4w_iter_3", "results": []}]}	ShenaoZhang/0.001_4iters_bs256_nodpo_only4w_iter_3	null	[ "transformers", "safetensors", "mistral", "text-generation", "alignment-handbook", "trl", "dpo", "generated_from_trainer", "conversational", "dataset:updated", "dataset:original", "base_model:ShenaoZhang/0.001_4iters_bs256_nodpo_only4w_iter_2", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-27T02:01:33+00:00	[]	[]	TAGS #transformers #safetensors #mistral #text-generation #alignment-handbook #trl #dpo #generated_from_trainer #conversational #dataset-updated #dataset-original #base_model-ShenaoZhang/0.001_4iters_bs256_nodpo_only4w_iter_2 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us	# 0.001_4iters_bs256_nodpo_only4w_iter_3 This model is a fine-tuned version of ShenaoZhang/0.001_4iters_bs256_nodpo_only4w_iter_2 on the updated and the original datasets. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-07 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - distributed_type: multi-GPU - num_devices: 8 - gradient_accumulation_steps: 4 - total_train_batch_size: 256 - total_eval_batch_size: 64 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 1 ### Training results ### Framework versions - Transformers 4.40.0 - Pytorch 2.1.2+cu121 - Datasets 2.14.6 - Tokenizers 0.19.1	[ "# 0.001_4iters_bs256_nodpo_only4w_iter_3\n\nThis model is a fine-tuned version of ShenaoZhang/0.001_4iters_bs256_nodpo_only4w_iter_2 on the updated and the original datasets.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.19.1" ]	[ "TAGS\n#transformers #safetensors #mistral #text-generation #alignment-handbook #trl #dpo #generated_from_trainer #conversational #dataset-updated #dataset-original #base_model-ShenaoZhang/0.001_4iters_bs256_nodpo_only4w_iter_2 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# 0.001_4iters_bs256_nodpo_only4w_iter_3\n\nThis model is a fine-tuned version of ShenaoZhang/0.001_4iters_bs256_nodpo_only4w_iter_2 on the updated and the original datasets.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.19.1" ]
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_prom_prom_core_notata-seqsight_8192_512_30M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_8192_512_30M](https://huggingface.co/mahdibaghbanzadeh/seqsight_8192_512_30M) on the [mahdibaghbanzadeh/GUE_prom_prom_core_notata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_core_notata) dataset. It achieves the following results on the evaluation set: - Loss: 0.3822 - F1 Score: 0.8334 - Accuracy: 0.8334 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.5488 \| 0.6 \| 200 \| 0.4335 \| 0.7988 \| 0.7995 \| \| 0.4495 \| 1.2 \| 400 \| 0.4023 \| 0.8161 \| 0.8161 \| \| 0.43 \| 1.81 \| 600 \| 0.3943 \| 0.8239 \| 0.8240 \| \| 0.4301 \| 2.41 \| 800 \| 0.3876 \| 0.8230 \| 0.8231 \| \| 0.4157 \| 3.01 \| 1000 \| 0.3833 \| 0.8268 \| 0.8268 \| \| 0.4118 \| 3.61 \| 1200 \| 0.3797 \| 0.8285 \| 0.8285 \| \| 0.4131 \| 4.22 \| 1400 \| 0.3810 \| 0.8274 \| 0.8274 \| \| 0.4074 \| 4.82 \| 1600 \| 0.3778 \| 0.8303 \| 0.8304 \| \| 0.3984 \| 5.42 \| 1800 \| 0.3786 \| 0.8300 \| 0.8300 \| \| 0.4015 \| 6.02 \| 2000 \| 0.3758 \| 0.8295 \| 0.8297 \| \| 0.3992 \| 6.63 \| 2200 \| 0.3731 \| 0.8310 \| 0.8310 \| \| 0.3953 \| 7.23 \| 2400 \| 0.3751 \| 0.8323 \| 0.8325 \| \| 0.396 \| 7.83 \| 2600 \| 0.3715 \| 0.8319 \| 0.8319 \| \| 0.3882 \| 8.43 \| 2800 \| 0.3801 \| 0.8325 \| 0.8329 \| \| 0.394 \| 9.04 \| 3000 \| 0.3714 \| 0.8331 \| 0.8332 \| \| 0.3891 \| 9.64 \| 3200 \| 0.3694 \| 0.8327 \| 0.8327 \| \| 0.3915 \| 10.24 \| 3400 \| 0.3700 \| 0.8344 \| 0.8344 \| \| 0.3855 \| 10.84 \| 3600 \| 0.3704 \| 0.8359 \| 0.8359 \| \| 0.387 \| 11.45 \| 3800 \| 0.3690 \| 0.8347 \| 0.8347 \| \| 0.3841 \| 12.05 \| 4000 \| 0.3679 \| 0.8363 \| 0.8363 \| \| 0.3844 \| 12.65 \| 4200 \| 0.3713 \| 0.8364 \| 0.8364 \| \| 0.3836 \| 13.25 \| 4400 \| 0.3693 \| 0.8385 \| 0.8385 \| \| 0.3875 \| 13.86 \| 4600 \| 0.3697 \| 0.8368 \| 0.8368 \| \| 0.3828 \| 14.46 \| 4800 \| 0.3696 \| 0.8366 \| 0.8366 \| \| 0.3801 \| 15.06 \| 5000 \| 0.3684 \| 0.8362 \| 0.8363 \| \| 0.3785 \| 15.66 \| 5200 \| 0.3678 \| 0.8385 \| 0.8385 \| \| 0.3792 \| 16.27 \| 5400 \| 0.3700 \| 0.8368 \| 0.8368 \| \| 0.3788 \| 16.87 \| 5600 \| 0.3746 \| 0.8328 \| 0.8332 \| \| 0.3774 \| 17.47 \| 5800 \| 0.3755 \| 0.8335 \| 0.8338 \| \| 0.3827 \| 18.07 \| 6000 \| 0.3699 \| 0.8381 \| 0.8383 \| \| 0.3788 \| 18.67 \| 6200 \| 0.3672 \| 0.8374 \| 0.8374 \| \| 0.3824 \| 19.28 \| 6400 \| 0.3672 \| 0.8382 \| 0.8381 \| \| 0.3798 \| 19.88 \| 6600 \| 0.3674 \| 0.8375 \| 0.8376 \| \| 0.3732 \| 20.48 \| 6800 \| 0.3686 \| 0.8371 \| 0.8372 \| \| 0.384 \| 21.08 \| 7000 \| 0.3672 \| 0.8389 \| 0.8391 \| \| 0.3794 \| 21.69 \| 7200 \| 0.3673 \| 0.8379 \| 0.8379 \| \| 0.3723 \| 22.29 \| 7400 \| 0.3667 \| 0.8364 \| 0.8364 \| \| 0.3757 \| 22.89 \| 7600 \| 0.3674 \| 0.8394 \| 0.8395 \| \| 0.3773 \| 23.49 \| 7800 \| 0.3658 \| 0.8379 \| 0.8379 \| \| 0.3766 \| 24.1 \| 8000 \| 0.3675 \| 0.8373 \| 0.8374 \| \| 0.3772 \| 24.7 \| 8200 \| 0.3696 \| 0.8360 \| 0.8363 \| \| 0.3701 \| 25.3 \| 8400 \| 0.3690 \| 0.8382 \| 0.8383 \| \| 0.3789 \| 25.9 \| 8600 \| 0.3663 \| 0.8390 \| 0.8391 \| \| 0.3779 \| 26.51 \| 8800 \| 0.3662 \| 0.8383 \| 0.8383 \| \| 0.3753 \| 27.11 \| 9000 \| 0.3665 \| 0.8398 \| 0.8398 \| \| 0.3807 \| 27.71 \| 9200 \| 0.3664 \| 0.8386 \| 0.8387 \| \| 0.3687 \| 28.31 \| 9400 \| 0.3675 \| 0.8395 \| 0.8396 \| \| 0.3762 \| 28.92 \| 9600 \| 0.3668 \| 0.8385 \| 0.8385 \| \| 0.379 \| 29.52 \| 9800 \| 0.3665 \| 0.8388 \| 0.8389 \| \| 0.3675 \| 30.12 \| 10000 \| 0.3668 \| 0.8390 \| 0.8391 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_8192_512_30M", "model-index": [{"name": "GUE_prom_prom_core_notata-seqsight_8192_512_30M-L1_f", "results": []}]}	mahdibaghbanzadeh/GUE_prom_prom_core_notata-seqsight_8192_512_30M-L1_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_8192_512_30M", "region:us" ]	null	2024-04-27T02:03:27+00:00	[]	[]	TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us	GUE\_prom\_prom\_core\_notata-seqsight\_8192\_512\_30M-L1\_f ============================================================ This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_8192\_512\_30M on the mahdibaghbanzadeh/GUE\_prom\_prom\_core\_notata dataset. It achieves the following results on the evaluation set: * Loss: 0.3822 * F1 Score: 0.8334 * Accuracy: 0.8334 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]	[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]
text-generation	transformers	# EinsteinBagel-8B (Einstein V6.1 & Bagel V1.0) This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). The purpose of this experiment was to combine the maximum amount of finetuned datasets possible for the Llama 3 8B architecture. ## Merge Details ### Merge Method This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) as a base. ### Models Merged The following models were included in the merge: * [Weyaxi/Einstein-v6.1-Llama3-8B](https://huggingface.co/Weyaxi/Einstein-v6.1-Llama3-8B) * [jondurbin/bagel-8b-v1.0](https://huggingface.co/jondurbin/bagel-8b-v1.0) ### Configuration The following YAML configuration was used to produce this model: ```yaml models: - model: meta-llama/Meta-Llama-3-8B - model: jondurbin/bagel-8b-v1.0 - model: Weyaxi/Einstein-v6.1-Llama3-8B merge_method: model_stock base_model: meta-llama/Meta-Llama-3-8B dtype: bfloat16 ```	{"license": "llama3", "library_name": "transformers", "tags": ["mergekit", "merge"], "base_model": ["Weyaxi/Einstein-v6.1-Llama3-8B", "meta-llama/Meta-Llama-3-8B", "jondurbin/bagel-8b-v1.0"]}	TitleOS/EinsteinBagel-8B	null	[ "transformers", "safetensors", "llama", "text-generation", "mergekit", "merge", "arxiv:2403.19522", "base_model:Weyaxi/Einstein-v6.1-Llama3-8B", "base_model:meta-llama/Meta-Llama-3-8B", "base_model:jondurbin/bagel-8b-v1.0", "license:llama3", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-27T02:04:04+00:00	[ "2403.19522" ]	[]	TAGS #transformers #safetensors #llama #text-generation #mergekit #merge #arxiv-2403.19522 #base_model-Weyaxi/Einstein-v6.1-Llama3-8B #base_model-meta-llama/Meta-Llama-3-8B #base_model-jondurbin/bagel-8b-v1.0 #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us	# EinsteinBagel-8B (Einstein V6.1 & Bagel V1.0) This is a merge of pre-trained language models created using mergekit. The purpose of this experiment was to combine the maximum amount of finetuned datasets possible for the Llama 3 8B architecture. ## Merge Details ### Merge Method This model was merged using the Model Stock merge method using meta-llama/Meta-Llama-3-8B as a base. ### Models Merged The following models were included in the merge: * Weyaxi/Einstein-v6.1-Llama3-8B * jondurbin/bagel-8b-v1.0 ### Configuration The following YAML configuration was used to produce this model:	[ "# EinsteinBagel-8B (Einstein V6.1 & Bagel V1.0)\n\nThis is a merge of pre-trained language models created using mergekit.\nThe purpose of this experiment was to combine the maximum amount of finetuned datasets possible for the Llama 3 8B architecture.", "## Merge Details", "### Merge Method\n\nThis model was merged using the Model Stock merge method using meta-llama/Meta-Llama-3-8B as a base.", "### Models Merged\n\nThe following models were included in the merge:\n* Weyaxi/Einstein-v6.1-Llama3-8B\n* jondurbin/bagel-8b-v1.0", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]	[ "TAGS\n#transformers #safetensors #llama #text-generation #mergekit #merge #arxiv-2403.19522 #base_model-Weyaxi/Einstein-v6.1-Llama3-8B #base_model-meta-llama/Meta-Llama-3-8B #base_model-jondurbin/bagel-8b-v1.0 #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# EinsteinBagel-8B (Einstein V6.1 & Bagel V1.0)\n\nThis is a merge of pre-trained language models created using mergekit.\nThe purpose of this experiment was to combine the maximum amount of finetuned datasets possible for the Llama 3 8B architecture.", "## Merge Details", "### Merge Method\n\nThis model was merged using the Model Stock merge method using meta-llama/Meta-Llama-3-8B as a base.", "### Models Merged\n\nThe following models were included in the merge:\n* Weyaxi/Einstein-v6.1-Llama3-8B\n* jondurbin/bagel-8b-v1.0", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]
text-generation	transformers	<div align="center"> <img width="260px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/BrQCb95lmEIFz79QAmoNA.png"></div> ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/fJIOPJnY6Ff6fUiSIuMEt.png) <div align="center"> <h1>Advancing Open-source Large Language Models in Medical Domain</h1> </div> <p align="center" style="margin-top: 0px;"> <a href="https://colab.research.google.com/drive/1F5oV20InEYeAJGmBwYF9NM_QhLmjBkKJ?usp=sharing"> <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="OpenChat Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 10px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style=" margin-right: 5px;">Online Demo</span> </a> \| <a href="https://github.com/openlifescience-ai"> <img src="https://github.githubassets.com/assets/GitHub-Mark-ea2971cee799.png" alt="GitHub Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style=" margin-right: 5px;">GitHub</span> </a> \| <a href="#"> <img src="https://github.com/alpayariyak/openchat/blob/master/assets/arxiv-logomark-small-square-border.png?raw=true" alt="ArXiv Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style="margin-right: 5px;">Paper</span> </a> \| <a href="https://discord.gg/A5Fjf5zC69"> <img src="https://cloud.githubusercontent.com/assets/6291467/26705903/96c2d66e-477c-11e7-9f4e-f3c0efe96c9a.png" alt="Discord Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text">Discord</span> </a> </p> ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/KGmRE5w2sepNtwsEu8t7K.jpeg) Introducing OpenBioLLM-70B: A State-of-the-Art Open Source Biomedical Large Language Model OpenBioLLM-70B is an advanced open source language model designed specifically for the biomedical domain. Developed by Saama AI Labs, this model leverages cutting-edge techniques to achieve state-of-the-art performance on a wide range of biomedical tasks. 🏥 Biomedical Specialization: OpenBioLLM-70B is tailored for the unique language and knowledge requirements of the medical and life sciences fields. It was fine-tuned on a vast corpus of high-quality biomedical data, enabling it to understand and generate text with domain-specific accuracy and fluency. 🎓 Superior Performance: With 70 billion parameters, OpenBioLLM-70B outperforms other open source biomedical language models of similar scale. It has also demonstrated better results compared to larger proprietary & open-source models like GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 on biomedical benchmarks. 🧠 Advanced Training Techniques: OpenBioLLM-70B builds upon the powerful foundations of the Meta-Llama-3-70B-Instruct and [Meta-Llama-3-70B-Instruct](meta-llama/Meta-Llama-3-70B-Instruct) models. It incorporates the DPO dataset and fine-tuning recipe along with a custom diverse medical instruction dataset. Key components of the training pipeline include: <div align="center"> <img width="1200px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/oPchsJsEpQoGcGXVbh7YS.png"> </div> - Policy Optimization: [Direct Preference Optimization: Your Language Model is Secretly a Reward Model (DPO)](https://arxiv.org/abs/2305.18290) - Fine-tuning dataset: Custom Medical Instruct dataset (We plan to release a sample training dataset in our upcoming paper; please stay updated) This combination of cutting-edge techniques enables OpenBioLLM-70B to align with key capabilities and preferences for biomedical applications. ⚙️ Release Details: - Model Size: 70 billion parameters - Quantization: Optimized quantized versions available [Here](https://huggingface.co/aaditya/OpenBioLLM-70B-GGUF) - Language(s) (NLP): en - Developed By: [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) from Saama AI Labs - License: Meta-Llama License - Fine-tuned from models: [Meta-Llama-3-70B-Instruct](meta-llama/Meta-Llama-3-70B-Instruct) - Resources for more information: - Paper: Coming soon The model can be fine-tuned for more specialized tasks and datasets as needed. OpenBioLLM-70B represents an important step forward in democratizing advanced language AI for the biomedical community. By leveraging state-of-the-art architectures and training techniques from leading open source efforts like Llama-3, we have created a powerful tool to accelerate innovation and discovery in healthcare and the life sciences. We are excited to share OpenBioLLM-70B with researchers and developers around the world. ### Use with transformers Important: Please use the exact chat template provided by Llama-3 instruct version. Otherwise there will be a degradation in the performance. The model output can be verbose in rare cases. Please consider setting temperature = 0 to make this happen less. See the snippet below for usage with Transformers: ```python import transformers import torch model_id = "aaditya/OpenBioLLM-Llama3-70B" pipeline = transformers.pipeline( "text-generation", model=model_id, model_kwargs={"torch_dtype": torch.bfloat16}, device="auto", ) messages = [ {"role": "system", "content": "You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience. Your name is OpenBioLLM, and you were developed by Saama AI Labs. who's willing to help answer the user's query with explanation. In your explanation, leverage your deep medical expertise such as relevant anatomical structures, physiological processes, diagnostic criteria, treatment guidelines, or other pertinent medical concepts. Use precise medical terminology while still aiming to make the explanation clear and accessible to a general audience."}, {"role": "user", "content": "How can i split a 3mg or 4mg waefin pill so i can get a 2.5mg pill?"}, ] prompt = pipeline.tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) terminators = [ pipeline.tokenizer.eos_token_id, pipeline.tokenizer.convert_tokens_to_ids("<\|eot_id\|>") ] outputs = pipeline( prompt, max_new_tokens=256, eos_token_id=terminators, do_sample=True, temperature=0.0, top_p=0.9, ) print(outputs[0]["generated_text"][len(prompt):]) ``` ## Training procedure ### Training hyperparameters <details> <summary>Click to see details</summary> - learning_rate: 0.0002 - lr_scheduler: cosine - train_batch_size: 12 - eval_batch_size: 8 - GPU: H100 80GB SXM5 - num_devices: 8 - optimizer: adamw_bnb_8bit - lr_scheduler_warmup_steps: 100 - num_epochs: 4 </details> ### Peft hyperparameters <details> <summary>Click to see details</summary> - adapter: qlora - lora_r: 128 - lora_alpha: 256 - lora_dropout: 0.05 - lora_target_linear: true -lora_target_modules: - q_proj - v_proj - k_proj - o_proj - gate_proj - down_proj - up_proj </details> ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2+cu121 - Datasets 2.18.0 - Tokenizers 0.15.1 - Axolotl - Lm harness for evaluation # Benchmark Results 🔥 OpenBioLLM-70B demonstrates superior performance compared to larger models, such as GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 across 9 diverse biomedical datasets, achieving state-of-the-art results with an average score of 86.06%, despite having a significantly smaller parameter count. The model's strong performance in domain-specific tasks, such as Clinical KG, Medical Genetics, and PubMedQA, highlights its ability to effectively capture and apply biomedical knowledge. 🚨 The GPT-4, Med-PaLM-1, and Med-PaLM-2 results are taken from their official papers. Since Med-PaLM doesn't provide zero-shot accuracy, we are using 5-shot accuracy from their paper for comparison. All results presented are in the zero-shot setting, except for Med-PaLM-2 and Med-PaLM-1, which use 5-shot accuracy. \| \| Clinical KG \| Medical Genetics \| Anatomy \| Pro Medicine \| College Biology \| College Medicine \| MedQA 4 opts \| PubMedQA \| MedMCQA \| Avg \| \|--------------------\|-------------\|------------------\|---------\|--------------\|-----------------\|------------------\|--------------\|----------\|---------\|-------\| \| OpenBioLLM-70B \| 92.93 \| 93.197 \| 83.904 \| 93.75 \| 93.827 \| 85.749 \| 78.162 \| 78.97 \| 74.014 \| 86.05588 \| \| Med-PaLM-2 (5-shot) \| 88.3 \| 90 \| 77.8 \| 95.2 \| 94.4 \| 80.9 \| 79.7 \| 79.2 \| 71.3 \| 84.08 \| \| GPT-4 \| 86.04 \| 91 \| 80 \| 93.01 \| 95.14 \| 76.88 \| 78.87 \| 75.2 \| 69.52 \| 82.85 \| \| Med-PaLM-1 (Flan-PaLM, 5-shot) \| 80.4 \| 75 \| 63.7 \| 83.8 \| 88.9 \| 76.3 \| 67.6 \| 79 \| 57.6 \| 74.7 \| \| OpenBioLLM-8B \| 76.101 \| 86.1 \| 69.829 \| 78.21 \| 84.213 \| 68.042 \| 58.993 \| 74.12 \| 56.913 \| 72.502 \| \| Gemini-1.0 \| 76.7 \| 75.8 \| 66.7 \| 77.7 \| 88 \| 69.2 \| 58 \| 70.7 \| 54.3 \| 70.79 \| \| GPT-3.5 Turbo 1106 \| 74.71 \| 74 \| 72.79 \| 72.79 \| 72.91 \| 64.73 \| 57.71 \| 72.66 \| 53.79 \| 66 \| \| Meditron-70B \| 66.79 \| 69 \| 53.33 \| 71.69 \| 76.38 \| 63 \| 57.1 \| 76.6 \| 46.85 \| 64.52 \| \| gemma-7b \| 69.81 \| 70 \| 59.26 \| 66.18 \| 79.86 \| 60.12 \| 47.21 \| 76.2 \| 48.96 \| 64.18 \| \| Mistral-7B-v0.1 \| 68.68 \| 71 \| 55.56 \| 68.38 \| 68.06 \| 59.54 \| 50.82 \| 75.4 \| 48.2 \| 62.85 \| \| Apollo-7B \| 62.26 \| 72 \| 61.48 \| 69.12 \| 70.83 \| 55.49 \| 55.22 \| 39.8 \| 53.77 \| 60 \| \| MedAlpaca-7b \| 57.36 \| 69 \| 57.04 \| 67.28 \| 65.28 \| 54.34 \| 41.71 \| 72.8 \| 37.51 \| 58.03 \| \| BioMistral-7B \| 59.9 \| 64 \| 56.5 \| 60.4 \| 59 \| 54.7 \| 50.6 \| 77.5 \| 48.1 \| 57.3 \| \| AlpaCare-llama2-7b \| 49.81 \| 49 \| 45.92 \| 33.82 \| 50 \| 43.35 \| 29.77 \| 72.2 \| 34.42 \| 45.36 \| \| ClinicalGPT \| 30.56 \| 27 \| 30.37 \| 19.48 \| 25 \| 24.27 \| 26.08 \| 63.8 \| 28.18 \| 30.52 \| <div align="center"> <img width="1600px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/_SzdcJSBjZyo8RS1bTEkP.png"> </div> ## Detailed Medical Subjectwise accuracy ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/UXF-V0col0Z0sS6BGPBkE.png) # Use Cases & Examples 🚨 Below results are from the quantized version of OpenBioLLM-70B # Summarize Clinical Notes OpenBioLLM-70B can efficiently analyze and summarize complex clinical notes, EHR data, and discharge summaries, extracting key information and generating concise, structured summaries ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/xdwdBgOxNi_TfML0hKlI8.png) # Answer Medical Questions OpenBioLLM-70B can provide answers to a wide range of medical questions. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/zO95GlwOQEZqCKQF69mE6.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/OKBczKw7gWeW5xsuDpc27.png) <details> <summary>Click to see details</summary> ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/eJGHT5khppYvJb8fQ-YW4.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/Cnbwrqa_-ORHRuNRC2P6Y.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/J9DhdcvukAc9mnnW9fj2C.png) </details> # Clinical Entity Recognition OpenBioLLM-70B can perform advanced clinical entity recognition by identifying and extracting key medical concepts, such as diseases, symptoms, medications, procedures, and anatomical structures, from unstructured clinical text. By leveraging its deep understanding of medical terminology and context, the model can accurately annotate and categorize clinical entities, enabling more efficient information retrieval, data analysis, and knowledge discovery from electronic health records, research articles, and other biomedical text sources. This capability can support various downstream applications, such as clinical decision support, pharmacovigilance, and medical research. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/_69BW4k9LVABFwtxixL45.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/DKy5wYCoPhoPPUc1-x8_J.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/7WD9zCCBZT4-4XlfnIQjl.png) # Biomarkers Extraction ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/ZttoM4AiteT7gFYVhjIpN.png) # Classification OpenBioLLM-70B can perform various biomedical classification tasks, such as disease prediction, sentiment analysis, medical document categorization ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/Bf5MW1d75qT-1F_TR_hC0.png) # De-Identification OpenBioLLM-70B can detect and remove personally identifiable information (PII) from medical records, ensuring patient privacy and compliance with data protection regulations like HIPAA. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/hKX4kzm--Tw5bj6K78msy.png) Advisory Notice! While OpenBioLLM-70B leverages high-quality data sources, its outputs may still contain inaccuracies, biases, or misalignments that could pose risks if relied upon for medical decision-making without further testing and refinement. The model's performance has not yet been rigorously evaluated in randomized controlled trials or real-world healthcare environments. Therefore, we strongly advise against using OpenBioLLM-70B for any direct patient care, clinical decision support, or other professional medical purposes at this time. Its use should be limited to research, development, and exploratory applications by qualified individuals who understand its limitations. OpenBioLLM-70B is intended solely as a research tool to assist healthcare professionals and should never be considered a replacement for the professional judgment and expertise of a qualified medical doctor. Appropriately adapting and validating OpenBioLLM-70B for specific medical use cases would require significant additional work, potentially including: - Thorough testing and evaluation in relevant clinical scenarios - Alignment with evidence-based guidelines and best practices - Mitigation of potential biases and failure modes - Integration with human oversight and interpretation - Compliance with regulatory and ethical standards Always consult a qualified healthcare provider for personal medical needs. # Citation If you find OpenBioLLM-70B & 8B useful in your work, please cite the model as follows: ``` @misc{OpenBioLLMs, author = {Ankit Pal, Malaikannan Sankarasubbu}, title = {OpenBioLLMs: Advancing Open-Source Large Language Models for Healthcare and Life Sciences}, year = {2024}, publisher = {Hugging Face}, journal = {Hugging Face repository}, howpublished = {\url{https://huggingface.co/aaditya/OpenBioLLM-Llama3-70B}} } ``` The accompanying paper is currently in progress and will be released soon. <div align="center"> <h2> 💌 Contact </h2> </div> We look forward to hearing you and collaborating on this exciting project! Contributors:** - [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) [aadityaura at gmail dot com] - Saama AI Labs - Note: I am looking for a funded PhD opportunity, especially if it fits my Responsible Generative AI, Multimodal LLMs, Geometric Deep Learning, and Healthcare AI skillset. # References We thank the [Meta Team](meta-llama/Meta-Llama-3-70B-Instruct) for their amazing models! Result sources - [1] GPT-4 [Capabilities of GPT-4 on Medical Challenge Problems] (https://arxiv.org/abs/2303.13375) - [2] Med-PaLM-1 [Large Language Models Encode Clinical Knowledge](https://arxiv.org/abs/2212.13138) - [3] Med-PaLM-2 [Towards Expert-Level Medical Question Answering with Large Language Models](https://arxiv.org/abs/2305.09617) - [4] Gemini-1.0 [Gemini Goes to Med School](https://arxiv.org/abs/2402.07023)	{"language": ["en"], "license": "llama3", "tags": ["llama-3", "llama", "Mixtral", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "distillation"], "base_model": "meta-llama/Meta-Llama-3-70B-Instruct", "widget": [{"example_title": "OpenBioLLM-70B", "messages": [{"role": "system", "content": "You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience."}, {"role": "user", "content": "How long does it take for newborn jaundice to go away?"}], "output": {"text": "Newborn jaundice, also known as neonatal jaundice, is a common condition in newborns where the yellowing of the skin and eyes occurs due to an elevated level of bilirubin in the blood. Bilirubin is a yellow pigment that forms when red blood cells break down. In most cases, newborn jaundice resolves on its own without any specific treatment.\nThe duration of newborn jaundice can vary depending on several factors such as the underlying cause, gestational age at birth, and individual variations in bilirubin metabolism. Here are some general guidelines:\n1. Physiological jaundice: This is the most common type of newborn jaundice and usually appears within 24-72 hours after birth. It tends to peak between the second and fifth day of life and gradually improves over the next week or two. By the time the baby is one week old, the jaundice should have mostly resolved. 2. Breast milk jaundice: This type of jaundice occurs in breastfed babies and may appear later than physiological jaundice, typically between the fifth and fourteenth day of life. It tends to persist for a longer duration but usually resolves within six weeks after birth. 3. Pathological jaundice: This type of jaundice is less common and occurs due to an underlying medical condition that affects bilirubin metabolism or liver function. The duration of pathological jaundice depends on the specific cause and may require treatment.\nIt's important for parents to monitor their newborn's jaundice closely and seek medical advice if the jaundice progresses rapidly, becomes severe, or is accompanied by other symptoms such as poor feeding, lethargy, or excessive sleepiness. In these cases, further evaluation and management may be necessary. Remember that each baby is unique, and the timing of jaundice resolution can vary. If you have concerns about your newborn's jaundice, it's always best to consult with a healthcare professional for personalized advice and guidance."}}], "model-index": [{"name": "OpenBioLLM-70B", "results": []}]}	LoneStriker/OpenBioLLM-Llama3-70B-5.0bpw-h6-exl2	null	[ "transformers", "pytorch", "llama", "text-generation", "llama-3", "Mixtral", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "distillation", "conversational", "en", "arxiv:2305.18290", "arxiv:2303.13375", "arxiv:2212.13138", "arxiv:2305.09617", "arxiv:2402.07023", "base_model:meta-llama/Meta-Llama-3-70B-Instruct", "license:llama3", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "5-bit", "region:us" ]	null	2024-04-27T02:04:19+00:00	[ "2305.18290", "2303.13375", "2212.13138", "2305.09617", "2402.07023" ]	[ "en" ]	TAGS #transformers #pytorch #llama #text-generation #llama-3 #Mixtral #instruct #finetune #chatml #DPO #RLHF #gpt4 #distillation #conversational #en #arxiv-2305.18290 #arxiv-2303.13375 #arxiv-2212.13138 #arxiv-2305.09617 #arxiv-2402.07023 #base_model-meta-llama/Meta-Llama-3-70B-Instruct #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #5-bit #region-us	![](URL <p>!image/png</p> <div align=) Advancing Open-source Large Language Models in Medical Domain ============================================================= Online Demo \| GitHub \| [![](URL alt=)](#) \| Discord !image/jpeg Introducing OpenBioLLM-70B: A State-of-the-Art Open Source Biomedical Large Language Model OpenBioLLM-70B is an advanced open source language model designed specifically for the biomedical domain. Developed by Saama AI Labs, this model leverages cutting-edge techniques to achieve state-of-the-art performance on a wide range of biomedical tasks. Biomedical Specialization: OpenBioLLM-70B is tailored for the unique language and knowledge requirements of the medical and life sciences fields. It was fine-tuned on a vast corpus of high-quality biomedical data, enabling it to understand and generate text with domain-specific accuracy and fluency. Superior Performance: With 70 billion parameters, OpenBioLLM-70B outperforms other open source biomedical language models of similar scale. It has also demonstrated better results compared to larger proprietary & open-source models like GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 on biomedical benchmarks. Advanced Training Techniques: OpenBioLLM-70B builds upon the powerful foundations of the Meta-Llama-3-70B-Instruct and Meta-Llama-3-70B-Instruct models. It incorporates the DPO dataset and fine-tuning recipe along with a custom diverse medical instruction dataset. Key components of the training pipeline include: ![](URL </div> <ul> <li>Policy Optimization: Direct Preference Optimization: Your Language Model is Secretly a Reward Model (DPO)</li> <li>Fine-tuning dataset: Custom Medical Instruct dataset (We plan to release a sample training dataset in our upcoming paper; please stay updated)</li> </ul> <p>This combination of cutting-edge techniques enables OpenBioLLM-70B to align with key capabilities and preferences for biomedical applications.</p> <p>️ Release Details:</p> <ul> <li>Model Size: 70 billion parameters</li> <li>Quantization: Optimized quantized versions available Here</li> <li>Language(s) (NLP): en</li> <li>Developed By: Ankit Pal (Aaditya Ura) from Saama AI Labs</li> <li>License: Meta-Llama License</li> <li>Fine-tuned from models: Meta-Llama-3-70B-Instruct</li> <li>Resources for more information: <ul> <li>Paper: Coming soon</li> </ul> </li> </ul> <p>The model can be fine-tuned for more specialized tasks and datasets as needed.</p> <p>OpenBioLLM-70B represents an important step forward in democratizing advanced language AI for the biomedical community. By leveraging state-of-the-art architectures and training techniques from leading open source efforts like Llama-3, we have created a powerful tool to accelerate innovation and discovery in healthcare and the life sciences.</p> <p>We are excited to share OpenBioLLM-70B with researchers and developers around the world.</p> <h3>Use with transformers</h3> <p>Important: Please use the exact chat template provided by Llama-3 instruct version. Otherwise there will be a degradation in the performance. The model output can be verbose in rare cases. Please consider setting temperature = 0 to make this happen less.</p> <p>See the snippet below for usage with Transformers:</p> <h2>Training procedure</h2> <h3>Training hyperparameters</h3> <details> <summary>Click to see details</summary> <ul> <li>learning_rate: 0.0002</li> <li>lr_scheduler: cosine</li> <li>train_batch_size: 12</li> <li>eval_batch_size: 8</li> <li>GPU: H100 80GB SXM5</li> <li>num_devices: 8</li> <li>optimizer: adamw_bnb_8bit</li> <li>lr_scheduler_warmup_steps: 100</li> <li>num_epochs: 4</li> </ul> </details> <h3>Peft hyperparameters</h3> <details> <summary>Click to see details</summary> <ul> <li>adapter: qlora</li> <li>lora_r: 128</li> <li>lora_alpha: 256</li> <li>lora_dropout: 0.05</li> <li>lora_target_linear: true</li> </ul> <p>-lora_target_modules:</p> <ul> <li>q_proj</li> <li>v_proj</li> <li>k_proj</li> <li>o_proj</li> <li>gate_proj</li> <li>down_proj</li> <li>up_proj</li> </ul> </details> <h3>Training results</h3> <h3>Framework versions</h3> <ul> <li>Transformers 4.39.3</li> <li>Pytorch 2.1.2+cu121</li> <li>Datasets 2.18.0</li> <li>Tokenizers 0.15.1</li> <li>Axolotl</li> <li>Lm harness for evaluation</li> </ul> <h1>Benchmark Results</h1> <p>OpenBioLLM-70B demonstrates superior performance compared to larger models, such as GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 across 9 diverse biomedical datasets, achieving state-of-the-art results with an average score of 86.06%, despite having a significantly smaller parameter count. The model's strong performance in domain-specific tasks, such as Clinical KG, Medical Genetics, and PubMedQA, highlights its ability to effectively capture and apply biomedical knowledge.</p> <p>The GPT-4, Med-PaLM-1, and Med-PaLM-2 results are taken from their official papers. Since Med-PaLM doesn't provide zero-shot accuracy, we are using 5-shot accuracy from their paper for comparison. All results presented are in the zero-shot setting, except for Med-PaLM-2 and Med-PaLM-1, which use 5-shot accuracy.</p> <p></p> <div align=) ![](URL </div> <h2>Detailed Medical Subjectwise accuracy</h2> <p>!image/png</p> <h1>Use Cases & Examples</h1> <p>Below results are from the quantized version of OpenBioLLM-70B</p> <h1>Summarize Clinical Notes</h1> <p>OpenBioLLM-70B can efficiently analyze and summarize complex clinical notes, EHR data, and discharge summaries, extracting key information and generating concise, structured summaries</p> <p>!image/png</p> <h1>Answer Medical Questions</h1> <p>OpenBioLLM-70B can provide answers to a wide range of medical questions.</p> <p>!image/png !image/png</p> <details> <summary>Click to see details</summary> <p>!image/png !image/png !image/png</p> </details> <h1>Clinical Entity Recognition</h1> <p>OpenBioLLM-70B can perform advanced clinical entity recognition by identifying and extracting key medical concepts, such as diseases, symptoms, medications, procedures, and anatomical structures, from unstructured clinical text. By leveraging its deep understanding of medical terminology and context, the model can accurately annotate and categorize clinical entities, enabling more efficient information retrieval, data analysis, and knowledge discovery from electronic health records, research articles, and other biomedical text sources. This capability can support various downstream applications, such as clinical decision support, pharmacovigilance, and medical research.</p> <p>!image/png !image/png !image/png</p> <h1>Biomarkers Extraction</h1> <p>!image/png</p> <h1>Classification</h1> <p>OpenBioLLM-70B can perform various biomedical classification tasks, such as disease prediction, sentiment analysis, medical document categorization</p> <p>!image/png</p> <h1>De-Identification</h1> <p>OpenBioLLM-70B can detect and remove personally identifiable information (PII) from medical records, ensuring patient privacy and compliance with data protection regulations like HIPAA.</p> <p>!image/png</p> <p>Advisory Notice!</p> <p>While OpenBioLLM-70B leverages high-quality data sources, its outputs may still contain inaccuracies, biases, or misalignments that could pose risks if relied upon for medical decision-making without further testing and refinement. The model's performance has not yet been rigorously evaluated in randomized controlled trials or real-world healthcare environments.</p> <p>Therefore, we strongly advise against using OpenBioLLM-70B for any direct patient care, clinical decision support, or other professional medical purposes at this time. Its use should be limited to research, development, and exploratory applications by qualified individuals who understand its limitations. OpenBioLLM-70B is intended solely as a research tool to assist healthcare professionals and should never be considered a replacement for the professional judgment and expertise of a qualified medical doctor.</p> <p>Appropriately adapting and validating OpenBioLLM-70B for specific medical use cases would require significant additional work, potentially including:</p> <ul> <li>Thorough testing and evaluation in relevant clinical scenarios</li> <li>Alignment with evidence-based guidelines and best practices</li> <li>Mitigation of potential biases and failure modes</li> <li>Integration with human oversight and interpretation</li> <li>Compliance with regulatory and ethical standards</li> </ul> <p>Always consult a qualified healthcare provider for personal medical needs.</p> <p>If you find OpenBioLLM-70B & 8B useful in your work, please cite the model as follows:</p> <p>The accompanying paper is currently in progress and will be released soon.</p> <div align=) Contact -------- We look forward to hearing you and collaborating on this exciting project! Contributors: * Ankit Pal (Aaditya Ura) [aadityaura at gmail dot com] * Saama AI Labs * Note: I am looking for a funded PhD opportunity, especially if it fits my Responsible Generative AI, Multimodal LLMs, Geometric Deep Learning, and Healthcare AI skillset. References ========== We thank the Meta Team for their amazing models! Result sources * [1] GPT-4 [Capabilities of GPT-4 on Medical Challenge Problems] (URL * [2] Med-PaLM-1 Large Language Models Encode Clinical Knowledge * [3] Med-PaLM-2 Towards Expert-Level Medical Question Answering with Large Language Models * [4] Gemini-1.0 Gemini Goes to Med School	[]	[ "TAGS\n#transformers #pytorch #llama #text-generation #llama-3 #Mixtral #instruct #finetune #chatml #DPO #RLHF #gpt4 #distillation #conversational #en #arxiv-2305.18290 #arxiv-2303.13375 #arxiv-2212.13138 #arxiv-2305.09617 #arxiv-2402.07023 #base_model-meta-llama/Meta-Llama-3-70B-Instruct #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #5-bit #region-us \n" ]
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_prom_prom_core_notata-seqsight_8192_512_30M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_8192_512_30M](https://huggingface.co/mahdibaghbanzadeh/seqsight_8192_512_30M) on the [mahdibaghbanzadeh/GUE_prom_prom_core_notata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_core_notata) dataset. It achieves the following results on the evaluation set: - Loss: 0.3812 - F1 Score: 0.8355 - Accuracy: 0.8355 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.513 \| 0.6 \| 200 \| 0.3994 \| 0.8211 \| 0.8214 \| \| 0.4186 \| 1.2 \| 400 \| 0.3783 \| 0.8323 \| 0.8323 \| \| 0.3998 \| 1.81 \| 600 \| 0.3873 \| 0.8288 \| 0.8291 \| \| 0.399 \| 2.41 \| 800 \| 0.3745 \| 0.8323 \| 0.8325 \| \| 0.39 \| 3.01 \| 1000 \| 0.3702 \| 0.8347 \| 0.8347 \| \| 0.3851 \| 3.61 \| 1200 \| 0.3677 \| 0.8353 \| 0.8355 \| \| 0.3879 \| 4.22 \| 1400 \| 0.3709 \| 0.8355 \| 0.8355 \| \| 0.3845 \| 4.82 \| 1600 \| 0.3671 \| 0.8353 \| 0.8355 \| \| 0.3747 \| 5.42 \| 1800 \| 0.3700 \| 0.8347 \| 0.8347 \| \| 0.379 \| 6.02 \| 2000 \| 0.3664 \| 0.8365 \| 0.8366 \| \| 0.3774 \| 6.63 \| 2200 \| 0.3633 \| 0.8391 \| 0.8391 \| \| 0.3737 \| 7.23 \| 2400 \| 0.3662 \| 0.8362 \| 0.8364 \| \| 0.3737 \| 7.83 \| 2600 \| 0.3624 \| 0.8398 \| 0.8398 \| \| 0.3687 \| 8.43 \| 2800 \| 0.3687 \| 0.8369 \| 0.8372 \| \| 0.3762 \| 9.04 \| 3000 \| 0.3607 \| 0.8415 \| 0.8415 \| \| 0.3677 \| 9.64 \| 3200 \| 0.3623 \| 0.8421 \| 0.8421 \| \| 0.3706 \| 10.24 \| 3400 \| 0.3620 \| 0.8412 \| 0.8412 \| \| 0.3642 \| 10.84 \| 3600 \| 0.3611 \| 0.8412 \| 0.8412 \| \| 0.3663 \| 11.45 \| 3800 \| 0.3619 \| 0.8419 \| 0.8419 \| \| 0.3639 \| 12.05 \| 4000 \| 0.3606 \| 0.8412 \| 0.8412 \| \| 0.3644 \| 12.65 \| 4200 \| 0.3616 \| 0.8420 \| 0.8421 \| \| 0.3622 \| 13.25 \| 4400 \| 0.3607 \| 0.8420 \| 0.8421 \| \| 0.3645 \| 13.86 \| 4600 \| 0.3633 \| 0.8426 \| 0.8427 \| \| 0.3606 \| 14.46 \| 4800 \| 0.3621 \| 0.8418 \| 0.8419 \| \| 0.36 \| 15.06 \| 5000 \| 0.3583 \| 0.8434 \| 0.8434 \| \| 0.354 \| 15.66 \| 5200 \| 0.3607 \| 0.8449 \| 0.8449 \| \| 0.3562 \| 16.27 \| 5400 \| 0.3656 \| 0.8427 \| 0.8427 \| \| 0.3576 \| 16.87 \| 5600 \| 0.3634 \| 0.8396 \| 0.8400 \| \| 0.3541 \| 17.47 \| 5800 \| 0.3639 \| 0.8402 \| 0.8404 \| \| 0.3597 \| 18.07 \| 6000 \| 0.3610 \| 0.8443 \| 0.8444 \| \| 0.356 \| 18.67 \| 6200 \| 0.3595 \| 0.8428 \| 0.8428 \| \| 0.3557 \| 19.28 \| 6400 \| 0.3599 \| 0.8440 \| 0.8440 \| \| 0.3536 \| 19.88 \| 6600 \| 0.3583 \| 0.8440 \| 0.8440 \| \| 0.349 \| 20.48 \| 6800 \| 0.3602 \| 0.8438 \| 0.8438 \| \| 0.3583 \| 21.08 \| 7000 \| 0.3598 \| 0.8416 \| 0.8417 \| \| 0.3538 \| 21.69 \| 7200 \| 0.3628 \| 0.8436 \| 0.8436 \| \| 0.3453 \| 22.29 \| 7400 \| 0.3594 \| 0.8405 \| 0.8406 \| \| 0.349 \| 22.89 \| 7600 \| 0.3610 \| 0.8403 \| 0.8404 \| \| 0.3513 \| 23.49 \| 7800 \| 0.3585 \| 0.8428 \| 0.8428 \| \| 0.3494 \| 24.1 \| 8000 \| 0.3610 \| 0.8407 \| 0.8408 \| \| 0.3513 \| 24.7 \| 8200 \| 0.3615 \| 0.8413 \| 0.8415 \| \| 0.3428 \| 25.3 \| 8400 \| 0.3644 \| 0.8414 \| 0.8415 \| \| 0.351 \| 25.9 \| 8600 \| 0.3603 \| 0.8434 \| 0.8434 \| \| 0.3489 \| 26.51 \| 8800 \| 0.3614 \| 0.8436 \| 0.8436 \| \| 0.3464 \| 27.11 \| 9000 \| 0.3612 \| 0.8417 \| 0.8417 \| \| 0.3532 \| 27.71 \| 9200 \| 0.3609 \| 0.8418 \| 0.8419 \| \| 0.3403 \| 28.31 \| 9400 \| 0.3613 \| 0.8415 \| 0.8415 \| \| 0.3481 \| 28.92 \| 9600 \| 0.3613 \| 0.8445 \| 0.8445 \| \| 0.3499 \| 29.52 \| 9800 \| 0.3611 \| 0.8439 \| 0.8440 \| \| 0.3406 \| 30.12 \| 10000 \| 0.3613 \| 0.8443 \| 0.8444 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_8192_512_30M", "model-index": [{"name": "GUE_prom_prom_core_notata-seqsight_8192_512_30M-L8_f", "results": []}]}	mahdibaghbanzadeh/GUE_prom_prom_core_notata-seqsight_8192_512_30M-L8_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_8192_512_30M", "region:us" ]	null	2024-04-27T02:09:28+00:00	[]	[]	TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us	GUE\_prom\_prom\_core\_notata-seqsight\_8192\_512\_30M-L8\_f ============================================================ This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_8192\_512\_30M on the mahdibaghbanzadeh/GUE\_prom\_prom\_core\_notata dataset. It achieves the following results on the evaluation set: * Loss: 0.3812 * F1 Score: 0.8355 * Accuracy: 0.8355 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]	[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]
null	peft	## Training procedure The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float16 ### Framework versions - PEFT 0.4.0	{"library_name": "peft"}	vicaloy/llama-2-13-b-chat-hf-checkpoints	null	[ "peft", "region:us" ]	null	2024-04-27T02:09:30+00:00	[]	[]	TAGS #peft #region-us	## Training procedure The following 'bitsandbytes' quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float16 ### Framework versions - PEFT 0.4.0	[ "## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: False\n- bnb_4bit_compute_dtype: float16", "### Framework versions\n\n\n- PEFT 0.4.0" ]	[ "TAGS\n#peft #region-us \n", "## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: False\n- bnb_4bit_compute_dtype: float16", "### Framework versions\n\n\n- PEFT 0.4.0" ]
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_prom_prom_core_notata-seqsight_8192_512_30M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_8192_512_30M](https://huggingface.co/mahdibaghbanzadeh/seqsight_8192_512_30M) on the [mahdibaghbanzadeh/GUE_prom_prom_core_notata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_core_notata) dataset. It achieves the following results on the evaluation set: - Loss: 0.3910 - F1 Score: 0.8342 - Accuracy: 0.8342 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.4915 \| 0.6 \| 200 \| 0.3862 \| 0.8258 \| 0.8259 \| \| 0.4066 \| 1.2 \| 400 \| 0.3737 \| 0.8340 \| 0.8340 \| \| 0.3919 \| 1.81 \| 600 \| 0.3887 \| 0.8283 \| 0.8287 \| \| 0.3899 \| 2.41 \| 800 \| 0.3694 \| 0.8350 \| 0.8351 \| \| 0.3828 \| 3.01 \| 1000 \| 0.3681 \| 0.8373 \| 0.8376 \| \| 0.3764 \| 3.61 \| 1200 \| 0.3621 \| 0.8380 \| 0.8381 \| \| 0.3795 \| 4.22 \| 1400 \| 0.3674 \| 0.8364 \| 0.8364 \| \| 0.3758 \| 4.82 \| 1600 \| 0.3637 \| 0.8381 \| 0.8383 \| \| 0.3635 \| 5.42 \| 1800 \| 0.3703 \| 0.8365 \| 0.8366 \| \| 0.3702 \| 6.02 \| 2000 \| 0.3708 \| 0.8381 \| 0.8385 \| \| 0.3646 \| 6.63 \| 2200 \| 0.3592 \| 0.8432 \| 0.8432 \| \| 0.3602 \| 7.23 \| 2400 \| 0.3715 \| 0.8348 \| 0.8353 \| \| 0.3591 \| 7.83 \| 2600 \| 0.3618 \| 0.8429 \| 0.8428 \| \| 0.3521 \| 8.43 \| 2800 \| 0.3645 \| 0.8420 \| 0.8423 \| \| 0.36 \| 9.04 \| 3000 \| 0.3615 \| 0.8442 \| 0.8444 \| \| 0.3498 \| 9.64 \| 3200 \| 0.3618 \| 0.8451 \| 0.8451 \| \| 0.3517 \| 10.24 \| 3400 \| 0.3621 \| 0.8456 \| 0.8457 \| \| 0.345 \| 10.84 \| 3600 \| 0.3601 \| 0.8451 \| 0.8451 \| \| 0.3444 \| 11.45 \| 3800 \| 0.3621 \| 0.8443 \| 0.8444 \| \| 0.3446 \| 12.05 \| 4000 \| 0.3584 \| 0.8463 \| 0.8462 \| \| 0.3399 \| 12.65 \| 4200 \| 0.3628 \| 0.8474 \| 0.8474 \| \| 0.3389 \| 13.25 \| 4400 \| 0.3635 \| 0.8465 \| 0.8466 \| \| 0.3401 \| 13.86 \| 4600 \| 0.3670 \| 0.8447 \| 0.8447 \| \| 0.3351 \| 14.46 \| 4800 \| 0.3680 \| 0.8433 \| 0.8436 \| \| 0.3337 \| 15.06 \| 5000 \| 0.3601 \| 0.8449 \| 0.8449 \| \| 0.3251 \| 15.66 \| 5200 \| 0.3699 \| 0.8470 \| 0.8470 \| \| 0.3292 \| 16.27 \| 5400 \| 0.3756 \| 0.8483 \| 0.8483 \| \| 0.3268 \| 16.87 \| 5600 \| 0.3730 \| 0.8413 \| 0.8417 \| \| 0.3225 \| 17.47 \| 5800 \| 0.3712 \| 0.8429 \| 0.8432 \| \| 0.3296 \| 18.07 \| 6000 \| 0.3713 \| 0.8455 \| 0.8457 \| \| 0.3239 \| 18.67 \| 6200 \| 0.3693 \| 0.8451 \| 0.8451 \| \| 0.3218 \| 19.28 \| 6400 \| 0.3720 \| 0.8469 \| 0.8470 \| \| 0.3204 \| 19.88 \| 6600 \| 0.3639 \| 0.8440 \| 0.8440 \| \| 0.3136 \| 20.48 \| 6800 \| 0.3698 \| 0.8488 \| 0.8489 \| \| 0.3241 \| 21.08 \| 7000 \| 0.3692 \| 0.8457 \| 0.8459 \| \| 0.3188 \| 21.69 \| 7200 \| 0.3751 \| 0.8468 \| 0.8468 \| \| 0.3107 \| 22.29 \| 7400 \| 0.3699 \| 0.8426 \| 0.8428 \| \| 0.3123 \| 22.89 \| 7600 \| 0.3725 \| 0.8425 \| 0.8427 \| \| 0.3143 \| 23.49 \| 7800 \| 0.3703 \| 0.8456 \| 0.8457 \| \| 0.3126 \| 24.1 \| 8000 \| 0.3763 \| 0.8428 \| 0.8430 \| \| 0.3145 \| 24.7 \| 8200 \| 0.3763 \| 0.8408 \| 0.8412 \| \| 0.3051 \| 25.3 \| 8400 \| 0.3814 \| 0.8430 \| 0.8432 \| \| 0.3089 \| 25.9 \| 8600 \| 0.3747 \| 0.8429 \| 0.8430 \| \| 0.3074 \| 26.51 \| 8800 \| 0.3758 \| 0.8449 \| 0.8449 \| \| 0.3069 \| 27.11 \| 9000 \| 0.3746 \| 0.8437 \| 0.8438 \| \| 0.3115 \| 27.71 \| 9200 \| 0.3769 \| 0.8419 \| 0.8421 \| \| 0.3003 \| 28.31 \| 9400 \| 0.3779 \| 0.8413 \| 0.8415 \| \| 0.3042 \| 28.92 \| 9600 \| 0.3785 \| 0.8408 \| 0.8410 \| \| 0.3067 \| 29.52 \| 9800 \| 0.3772 \| 0.8412 \| 0.8413 \| \| 0.298 \| 30.12 \| 10000 \| 0.3778 \| 0.8411 \| 0.8412 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_8192_512_30M", "model-index": [{"name": "GUE_prom_prom_core_notata-seqsight_8192_512_30M-L32_f", "results": []}]}	mahdibaghbanzadeh/GUE_prom_prom_core_notata-seqsight_8192_512_30M-L32_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_8192_512_30M", "region:us" ]	null	2024-04-27T02:10:35+00:00	[]	[]	TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us	GUE\_prom\_prom\_core\_notata-seqsight\_8192\_512\_30M-L32\_f ============================================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_8192\_512\_30M on the mahdibaghbanzadeh/GUE\_prom\_prom\_core\_notata dataset. It achieves the following results on the evaluation set: * Loss: 0.3910 * F1 Score: 0.8342 * Accuracy: 0.8342 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]	[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]
text-classification	transformers	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # my_awesome_model This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.1924 - Accuracy: 0.9529 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 2 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| 0.198 \| 1.0 \| 1563 \| 0.1405 \| 0.9501 \| \| 0.1304 \| 2.0 \| 3126 \| 0.1924 \| 0.9529 \| ### Framework versions - Transformers 4.40.0 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1	{"license": "mit", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "roberta-base", "model-index": [{"name": "my_awesome_model", "results": []}]}	brunhild217/my_awesome_model	null	[ "transformers", "tensorboard", "safetensors", "roberta", "text-classification", "generated_from_trainer", "base_model:roberta-base", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-27T02:12:24+00:00	[]	[]	TAGS #transformers #tensorboard #safetensors #roberta #text-classification #generated_from_trainer #base_model-roberta-base #license-mit #autotrain_compatible #endpoints_compatible #region-us	my\_awesome\_model ================== This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set: * Loss: 0.1924 * Accuracy: 0.9529 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 2e-05 * train\_batch\_size: 16 * eval\_batch\_size: 16 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * num\_epochs: 2 ### Training results ### Framework versions * Transformers 4.40.0 * Pytorch 2.2.1+cu121 * Datasets 2.19.0 * Tokenizers 0.19.1	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 2", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]	[ "TAGS\n#transformers #tensorboard #safetensors #roberta #text-classification #generated_from_trainer #base_model-roberta-base #license-mit #autotrain_compatible #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 2", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_prom_prom_core_tata-seqsight_8192_512_30M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_8192_512_30M](https://huggingface.co/mahdibaghbanzadeh/seqsight_8192_512_30M) on the [mahdibaghbanzadeh/GUE_prom_prom_core_tata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_core_tata) dataset. It achieves the following results on the evaluation set: - Loss: 0.4139 - F1 Score: 0.8204 - Accuracy: 0.8206 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:------:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.598 \| 5.13 \| 200 \| 0.5809 \| 0.6855 \| 0.6884 \| \| 0.5478 \| 10.26 \| 400 \| 0.5718 \| 0.6949 \| 0.6982 \| \| 0.5292 \| 15.38 \| 600 \| 0.5582 \| 0.7134 \| 0.7178 \| \| 0.5098 \| 20.51 \| 800 \| 0.5347 \| 0.7385 \| 0.7406 \| \| 0.4956 \| 25.64 \| 1000 \| 0.5128 \| 0.7385 \| 0.7390 \| \| 0.4841 \| 30.77 \| 1200 \| 0.4952 \| 0.7504 \| 0.7504 \| \| 0.4687 \| 35.9 \| 1400 \| 0.4978 \| 0.7327 \| 0.7341 \| \| 0.4547 \| 41.03 \| 1600 \| 0.4727 \| 0.7731 \| 0.7732 \| \| 0.4453 \| 46.15 \| 1800 \| 0.4649 \| 0.7664 \| 0.7667 \| \| 0.427 \| 51.28 \| 2000 \| 0.4587 \| 0.7757 \| 0.7765 \| \| 0.4099 \| 56.41 \| 2200 \| 0.4288 \| 0.8010 \| 0.8010 \| \| 0.3969 \| 61.54 \| 2400 \| 0.4209 \| 0.8091 \| 0.8091 \| \| 0.3875 \| 66.67 \| 2600 \| 0.4110 \| 0.8091 \| 0.8091 \| \| 0.376 \| 71.79 \| 2800 \| 0.4023 \| 0.8237 \| 0.8238 \| \| 0.364 \| 76.92 \| 3000 \| 0.4107 \| 0.8087 \| 0.8091 \| \| 0.3553 \| 82.05 \| 3200 \| 0.3894 \| 0.8270 \| 0.8271 \| \| 0.3515 \| 87.18 \| 3400 \| 0.4001 \| 0.8250 \| 0.8254 \| \| 0.3446 \| 92.31 \| 3600 \| 0.3743 \| 0.8385 \| 0.8385 \| \| 0.3406 \| 97.44 \| 3800 \| 0.3740 \| 0.8385 \| 0.8385 \| \| 0.3333 \| 102.56 \| 4000 \| 0.3718 \| 0.8434 \| 0.8434 \| \| 0.3285 \| 107.69 \| 4200 \| 0.3647 \| 0.8450 \| 0.8450 \| \| 0.3212 \| 112.82 \| 4400 \| 0.3744 \| 0.8450 \| 0.8450 \| \| 0.3183 \| 117.95 \| 4600 \| 0.3704 \| 0.8401 \| 0.8401 \| \| 0.319 \| 123.08 \| 4800 \| 0.3620 \| 0.8418 \| 0.8418 \| \| 0.3103 \| 128.21 \| 5000 \| 0.3592 \| 0.8433 \| 0.8434 \| \| 0.3078 \| 133.33 \| 5200 \| 0.3610 \| 0.8449 \| 0.8450 \| \| 0.3047 \| 138.46 \| 5400 \| 0.3588 \| 0.8401 \| 0.8401 \| \| 0.2994 \| 143.59 \| 5600 \| 0.3714 \| 0.8417 \| 0.8418 \| \| 0.3022 \| 148.72 \| 5800 \| 0.3612 \| 0.8401 \| 0.8401 \| \| 0.2987 \| 153.85 \| 6000 \| 0.3610 \| 0.8417 \| 0.8418 \| \| 0.2974 \| 158.97 \| 6200 \| 0.3615 \| 0.8450 \| 0.8450 \| \| 0.2886 \| 164.1 \| 6400 \| 0.3628 \| 0.8401 \| 0.8401 \| \| 0.2889 \| 169.23 \| 6600 \| 0.3660 \| 0.8466 \| 0.8467 \| \| 0.2857 \| 174.36 \| 6800 \| 0.3690 \| 0.8385 \| 0.8385 \| \| 0.2831 \| 179.49 \| 7000 \| 0.3646 \| 0.8368 \| 0.8369 \| \| 0.2834 \| 184.62 \| 7200 \| 0.3754 \| 0.8351 \| 0.8352 \| \| 0.284 \| 189.74 \| 7400 \| 0.3658 \| 0.8368 \| 0.8369 \| \| 0.2808 \| 194.87 \| 7600 \| 0.3645 \| 0.8417 \| 0.8418 \| \| 0.2754 \| 200.0 \| 7800 \| 0.3691 \| 0.8385 \| 0.8385 \| \| 0.2791 \| 205.13 \| 8000 \| 0.3706 \| 0.8352 \| 0.8352 \| \| 0.2722 \| 210.26 \| 8200 \| 0.3687 \| 0.8385 \| 0.8385 \| \| 0.2798 \| 215.38 \| 8400 \| 0.3682 \| 0.8369 \| 0.8369 \| \| 0.2711 \| 220.51 \| 8600 \| 0.3713 \| 0.8352 \| 0.8352 \| \| 0.2763 \| 225.64 \| 8800 \| 0.3715 \| 0.8320 \| 0.8320 \| \| 0.2728 \| 230.77 \| 9000 \| 0.3705 \| 0.8352 \| 0.8352 \| \| 0.2712 \| 235.9 \| 9200 \| 0.3733 \| 0.8352 \| 0.8352 \| \| 0.2758 \| 241.03 \| 9400 \| 0.3685 \| 0.8369 \| 0.8369 \| \| 0.2707 \| 246.15 \| 9600 \| 0.3707 \| 0.8385 \| 0.8385 \| \| 0.2787 \| 251.28 \| 9800 \| 0.3701 \| 0.8369 \| 0.8369 \| \| 0.2751 \| 256.41 \| 10000 \| 0.3692 \| 0.8385 \| 0.8385 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_8192_512_30M", "model-index": [{"name": "GUE_prom_prom_core_tata-seqsight_8192_512_30M-L1_f", "results": []}]}	mahdibaghbanzadeh/GUE_prom_prom_core_tata-seqsight_8192_512_30M-L1_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_8192_512_30M", "region:us" ]	null	2024-04-27T02:12:51+00:00	[]	[]	TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us	GUE\_prom\_prom\_core\_tata-seqsight\_8192\_512\_30M-L1\_f ========================================================== This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_8192\_512\_30M on the mahdibaghbanzadeh/GUE\_prom\_prom\_core\_tata dataset. It achieves the following results on the evaluation set: * Loss: 0.4139 * F1 Score: 0.8204 * Accuracy: 0.8206 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]	[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_prom_prom_core_tata-seqsight_8192_512_30M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_8192_512_30M](https://huggingface.co/mahdibaghbanzadeh/seqsight_8192_512_30M) on the [mahdibaghbanzadeh/GUE_prom_prom_core_tata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_core_tata) dataset. It achieves the following results on the evaluation set: - Loss: 0.5952 - F1 Score: 0.8385 - Accuracy: 0.8385 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:------:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.5745 \| 5.13 \| 200 \| 0.5589 \| 0.7076 \| 0.7096 \| \| 0.5057 \| 10.26 \| 400 \| 0.5507 \| 0.7268 \| 0.7325 \| \| 0.4671 \| 15.38 \| 600 \| 0.5074 \| 0.7501 \| 0.7537 \| \| 0.4179 \| 20.51 \| 800 \| 0.4490 \| 0.7924 \| 0.7928 \| \| 0.3745 \| 25.64 \| 1000 \| 0.4288 \| 0.8152 \| 0.8157 \| \| 0.3408 \| 30.77 \| 1200 \| 0.4045 \| 0.8205 \| 0.8206 \| \| 0.3141 \| 35.9 \| 1400 \| 0.3903 \| 0.8189 \| 0.8189 \| \| 0.2929 \| 41.03 \| 1600 \| 0.3908 \| 0.8271 \| 0.8271 \| \| 0.2779 \| 46.15 \| 1800 \| 0.3883 \| 0.8287 \| 0.8287 \| \| 0.257 \| 51.28 \| 2000 \| 0.3939 \| 0.8368 \| 0.8369 \| \| 0.2411 \| 56.41 \| 2200 \| 0.3823 \| 0.8368 \| 0.8369 \| \| 0.2262 \| 61.54 \| 2400 \| 0.4157 \| 0.8351 \| 0.8352 \| \| 0.2149 \| 66.67 \| 2600 \| 0.3981 \| 0.8432 \| 0.8434 \| \| 0.2062 \| 71.79 \| 2800 \| 0.4350 \| 0.8398 \| 0.8401 \| \| 0.1949 \| 76.92 \| 3000 \| 0.4541 \| 0.8303 \| 0.8303 \| \| 0.1832 \| 82.05 \| 3200 \| 0.4548 \| 0.8303 \| 0.8303 \| \| 0.1807 \| 87.18 \| 3400 \| 0.4484 \| 0.8287 \| 0.8287 \| \| 0.1739 \| 92.31 \| 3600 \| 0.4368 \| 0.8336 \| 0.8336 \| \| 0.1616 \| 97.44 \| 3800 \| 0.4746 \| 0.8385 \| 0.8385 \| \| 0.153 \| 102.56 \| 4000 \| 0.4779 \| 0.8369 \| 0.8369 \| \| 0.1485 \| 107.69 \| 4200 \| 0.4921 \| 0.8385 \| 0.8385 \| \| 0.1405 \| 112.82 \| 4400 \| 0.5096 \| 0.8450 \| 0.8450 \| \| 0.1405 \| 117.95 \| 4600 \| 0.4949 \| 0.8482 \| 0.8483 \| \| 0.1328 \| 123.08 \| 4800 \| 0.5242 \| 0.8434 \| 0.8434 \| \| 0.1292 \| 128.21 \| 5000 \| 0.5093 \| 0.8254 \| 0.8254 \| \| 0.1229 \| 133.33 \| 5200 \| 0.5286 \| 0.8563 \| 0.8564 \| \| 0.1205 \| 138.46 \| 5400 \| 0.5364 \| 0.8449 \| 0.8450 \| \| 0.1141 \| 143.59 \| 5600 \| 0.5838 \| 0.8303 \| 0.8303 \| \| 0.1142 \| 148.72 \| 5800 \| 0.5555 \| 0.8336 \| 0.8336 \| \| 0.1102 \| 153.85 \| 6000 \| 0.5760 \| 0.8416 \| 0.8418 \| \| 0.1064 \| 158.97 \| 6200 \| 0.5708 \| 0.8320 \| 0.8320 \| \| 0.1065 \| 164.1 \| 6400 \| 0.5825 \| 0.8418 \| 0.8418 \| \| 0.1018 \| 169.23 \| 6600 \| 0.5989 \| 0.8336 \| 0.8336 \| \| 0.0973 \| 174.36 \| 6800 \| 0.6020 \| 0.8336 \| 0.8336 \| \| 0.0965 \| 179.49 \| 7000 \| 0.5881 \| 0.8401 \| 0.8401 \| \| 0.0931 \| 184.62 \| 7200 \| 0.6173 \| 0.8302 \| 0.8303 \| \| 0.0908 \| 189.74 \| 7400 \| 0.5950 \| 0.8401 \| 0.8401 \| \| 0.0929 \| 194.87 \| 7600 \| 0.6094 \| 0.8465 \| 0.8467 \| \| 0.0885 \| 200.0 \| 7800 \| 0.5925 \| 0.8418 \| 0.8418 \| \| 0.0883 \| 205.13 \| 8000 \| 0.6153 \| 0.8418 \| 0.8418 \| \| 0.0819 \| 210.26 \| 8200 \| 0.6215 \| 0.8499 \| 0.8499 \| \| 0.082 \| 215.38 \| 8400 \| 0.6393 \| 0.8499 \| 0.8499 \| \| 0.0794 \| 220.51 \| 8600 \| 0.6357 \| 0.8368 \| 0.8369 \| \| 0.0816 \| 225.64 \| 8800 \| 0.6123 \| 0.8483 \| 0.8483 \| \| 0.0864 \| 230.77 \| 9000 \| 0.6061 \| 0.8417 \| 0.8418 \| \| 0.083 \| 235.9 \| 9200 \| 0.6174 \| 0.8418 \| 0.8418 \| \| 0.0822 \| 241.03 \| 9400 \| 0.6227 \| 0.8466 \| 0.8467 \| \| 0.0786 \| 246.15 \| 9600 \| 0.6303 \| 0.8434 \| 0.8434 \| \| 0.084 \| 251.28 \| 9800 \| 0.6274 \| 0.8450 \| 0.8450 \| \| 0.0781 \| 256.41 \| 10000 \| 0.6283 \| 0.8450 \| 0.8450 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_8192_512_30M", "model-index": [{"name": "GUE_prom_prom_core_tata-seqsight_8192_512_30M-L8_f", "results": []}]}	mahdibaghbanzadeh/GUE_prom_prom_core_tata-seqsight_8192_512_30M-L8_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_8192_512_30M", "region:us" ]	null	2024-04-27T02:13:31+00:00	[]	[]	TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us	GUE\_prom\_prom\_core\_tata-seqsight\_8192\_512\_30M-L8\_f ========================================================== This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_8192\_512\_30M on the mahdibaghbanzadeh/GUE\_prom\_prom\_core\_tata dataset. It achieves the following results on the evaluation set: * Loss: 0.5952 * F1 Score: 0.8385 * Accuracy: 0.8385 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]	[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]
text-generation	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "datasets": ["thesven/pihkal-tihkal-orpo-dpo-dataset"]}	thesven/thesven-Tihkal-Pihkal-ORPO-Llama-3-8B-bnb-4bit	null	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "dataset:thesven/pihkal-tihkal-orpo-dpo-dataset", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-27T02:13:38+00:00	[ "1910.09700" ]	[]	TAGS #transformers #safetensors #llama #text-generation #conversational #dataset-thesven/pihkal-tihkal-orpo-dpo-dataset #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us	# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact	[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]	[ "TAGS\n#transformers #safetensors #llama #text-generation #conversational #dataset-thesven/pihkal-tihkal-orpo-dpo-dataset #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]
text-generation	transformers	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # lmd-4bars-2048-epochs10 This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.005 - train_batch_size: 32 - eval_batch_size: 16 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 64 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 1 ### Training results ### Framework versions - Transformers 4.36.0 - Pytorch 2.1.0 - Datasets 2.15.0 - Tokenizers 0.15.1	{"license": "mit", "tags": ["generated_from_trainer"], "base_model": "gpt2", "model-index": [{"name": "lmd-4bars-2048-epochs10", "results": []}]}	MikeMpapa/lmd-4bars-2048-epochs10	null	[ "transformers", "tensorboard", "safetensors", "gpt2", "text-generation", "generated_from_trainer", "base_model:gpt2", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-27T02:16:15+00:00	[]	[]	TAGS #transformers #tensorboard #safetensors #gpt2 #text-generation #generated_from_trainer #base_model-gpt2 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us	# lmd-4bars-2048-epochs10 This model is a fine-tuned version of gpt2 on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.005 - train_batch_size: 32 - eval_batch_size: 16 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 64 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 1 ### Training results ### Framework versions - Transformers 4.36.0 - Pytorch 2.1.0 - Datasets 2.15.0 - Tokenizers 0.15.1	[ "# lmd-4bars-2048-epochs10\n\nThis model is a fine-tuned version of gpt2 on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.005\n- train_batch_size: 32\n- eval_batch_size: 16\n- seed: 42\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.36.0\n- Pytorch 2.1.0\n- Datasets 2.15.0\n- Tokenizers 0.15.1" ]	[ "TAGS\n#transformers #tensorboard #safetensors #gpt2 #text-generation #generated_from_trainer #base_model-gpt2 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# lmd-4bars-2048-epochs10\n\nThis model is a fine-tuned version of gpt2 on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.005\n- train_batch_size: 32\n- eval_batch_size: 16\n- seed: 42\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.36.0\n- Pytorch 2.1.0\n- Datasets 2.15.0\n- Tokenizers 0.15.1" ]
text-to-image	null	gguf quantized version of https://huggingface.co/stabilityai/sdxl-turbo	{"license": "other", "license_name": "sai-nc-community", "license_link": "https://huggingface.co/stabilityai/sdxl-turbo/blob/main/LICENSE.TXT", "pipeline_tag": "text-to-image"}	OlegSkutte/sdxl-turbo-GGUF	null	[ "gguf", "text-to-image", "license:other", "region:us" ]	null	2024-04-27T02:18:36+00:00	[]	[]	TAGS #gguf #text-to-image #license-other #region-us	gguf quantized version of URL	[]	[ "TAGS\n#gguf #text-to-image #license-other #region-us \n" ]
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_prom_prom_core_tata-seqsight_8192_512_30M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_8192_512_30M](https://huggingface.co/mahdibaghbanzadeh/seqsight_8192_512_30M) on the [mahdibaghbanzadeh/GUE_prom_prom_core_tata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_core_tata) dataset. It achieves the following results on the evaluation set: - Loss: 0.7455 - F1 Score: 0.8269 - Accuracy: 0.8271 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:------:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.5591 \| 5.13 \| 200 \| 0.5316 \| 0.7337 \| 0.7341 \| \| 0.4678 \| 10.26 \| 400 \| 0.4843 \| 0.7821 \| 0.7830 \| \| 0.3819 \| 15.38 \| 600 \| 0.4105 \| 0.8188 \| 0.8189 \| \| 0.3145 \| 20.51 \| 800 \| 0.4078 \| 0.8173 \| 0.8173 \| \| 0.2727 \| 25.64 \| 1000 \| 0.4044 \| 0.8352 \| 0.8352 \| \| 0.2292 \| 30.77 \| 1200 \| 0.4325 \| 0.8384 \| 0.8385 \| \| 0.1985 \| 35.9 \| 1400 \| 0.4151 \| 0.8401 \| 0.8401 \| \| 0.1666 \| 41.03 \| 1600 \| 0.4526 \| 0.8399 \| 0.8401 \| \| 0.1497 \| 46.15 \| 1800 \| 0.5059 \| 0.8400 \| 0.8401 \| \| 0.1277 \| 51.28 \| 2000 \| 0.5027 \| 0.8483 \| 0.8483 \| \| 0.1108 \| 56.41 \| 2200 \| 0.5648 \| 0.8596 \| 0.8597 \| \| 0.0988 \| 61.54 \| 2400 \| 0.5330 \| 0.8483 \| 0.8483 \| \| 0.091 \| 66.67 \| 2600 \| 0.5492 \| 0.8449 \| 0.8450 \| \| 0.0815 \| 71.79 \| 2800 \| 0.5692 \| 0.8645 \| 0.8646 \| \| 0.0714 \| 76.92 \| 3000 \| 0.5980 \| 0.8532 \| 0.8532 \| \| 0.065 \| 82.05 \| 3200 \| 0.6359 \| 0.8464 \| 0.8467 \| \| 0.0599 \| 87.18 \| 3400 \| 0.6645 \| 0.8497 \| 0.8499 \| \| 0.0563 \| 92.31 \| 3600 \| 0.6828 \| 0.8515 \| 0.8515 \| \| 0.055 \| 97.44 \| 3800 \| 0.6676 \| 0.8450 \| 0.8450 \| \| 0.0465 \| 102.56 \| 4000 \| 0.7496 \| 0.8412 \| 0.8418 \| \| 0.047 \| 107.69 \| 4200 \| 0.7358 \| 0.8432 \| 0.8434 \| \| 0.0448 \| 112.82 \| 4400 \| 0.7372 \| 0.8329 \| 0.8336 \| \| 0.0436 \| 117.95 \| 4600 \| 0.6990 \| 0.8400 \| 0.8401 \| \| 0.039 \| 123.08 \| 4800 \| 0.7425 \| 0.8433 \| 0.8434 \| \| 0.0395 \| 128.21 \| 5000 \| 0.7357 \| 0.8315 \| 0.8320 \| \| 0.0369 \| 133.33 \| 5200 \| 0.7054 \| 0.8483 \| 0.8483 \| \| 0.0352 \| 138.46 \| 5400 \| 0.7598 \| 0.8382 \| 0.8385 \| \| 0.0318 \| 143.59 \| 5600 \| 0.7746 \| 0.8465 \| 0.8467 \| \| 0.0315 \| 148.72 \| 5800 \| 0.7480 \| 0.8400 \| 0.8401 \| \| 0.0309 \| 153.85 \| 6000 \| 0.7548 \| 0.8563 \| 0.8564 \| \| 0.0312 \| 158.97 \| 6200 \| 0.7342 \| 0.8548 \| 0.8548 \| \| 0.0269 \| 164.1 \| 6400 \| 0.7992 \| 0.8433 \| 0.8434 \| \| 0.03 \| 169.23 \| 6600 \| 0.7064 \| 0.8417 \| 0.8418 \| \| 0.0268 \| 174.36 \| 6800 \| 0.7526 \| 0.8498 \| 0.8499 \| \| 0.026 \| 179.49 \| 7000 \| 0.7874 \| 0.8499 \| 0.8499 \| \| 0.0263 \| 184.62 \| 7200 \| 0.8341 \| 0.8378 \| 0.8385 \| \| 0.0224 \| 189.74 \| 7400 \| 0.8513 \| 0.8512 \| 0.8515 \| \| 0.0237 \| 194.87 \| 7600 \| 0.7960 \| 0.8579 \| 0.8581 \| \| 0.0226 \| 200.0 \| 7800 \| 0.8098 \| 0.8515 \| 0.8515 \| \| 0.021 \| 205.13 \| 8000 \| 0.8648 \| 0.8480 \| 0.8483 \| \| 0.0212 \| 210.26 \| 8200 \| 0.8669 \| 0.8381 \| 0.8385 \| \| 0.0193 \| 215.38 \| 8400 \| 0.8712 \| 0.8380 \| 0.8385 \| \| 0.0186 \| 220.51 \| 8600 \| 0.8453 \| 0.8448 \| 0.8450 \| \| 0.0194 \| 225.64 \| 8800 \| 0.8293 \| 0.8432 \| 0.8434 \| \| 0.0196 \| 230.77 \| 9000 \| 0.8284 \| 0.8415 \| 0.8418 \| \| 0.0197 \| 235.9 \| 9200 \| 0.8125 \| 0.8597 \| 0.8597 \| \| 0.0186 \| 241.03 \| 9400 \| 0.8294 \| 0.8547 \| 0.8548 \| \| 0.0199 \| 246.15 \| 9600 \| 0.8236 \| 0.8514 \| 0.8515 \| \| 0.0191 \| 251.28 \| 9800 \| 0.8482 \| 0.8398 \| 0.8401 \| \| 0.0164 \| 256.41 \| 10000 \| 0.8305 \| 0.8514 \| 0.8515 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_8192_512_30M", "model-index": [{"name": "GUE_prom_prom_core_tata-seqsight_8192_512_30M-L32_f", "results": []}]}	mahdibaghbanzadeh/GUE_prom_prom_core_tata-seqsight_8192_512_30M-L32_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_8192_512_30M", "region:us" ]	null	2024-04-27T02:18:53+00:00	[]	[]	TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us	GUE\_prom\_prom\_core\_tata-seqsight\_8192\_512\_30M-L32\_f =========================================================== This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_8192\_512\_30M on the mahdibaghbanzadeh/GUE\_prom\_prom\_core\_tata dataset. It achieves the following results on the evaluation set: * Loss: 0.7455 * F1 Score: 0.8269 * Accuracy: 0.8271 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]	[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_prom_prom_300_all-seqsight_8192_512_30M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_8192_512_30M](https://huggingface.co/mahdibaghbanzadeh/seqsight_8192_512_30M) on the [mahdibaghbanzadeh/GUE_prom_prom_300_all](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_300_all) dataset. It achieves the following results on the evaluation set: - Loss: 0.2147 - F1 Score: 0.9138 - Accuracy: 0.9139 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.4209 \| 0.54 \| 200 \| 0.2826 \| 0.8948 \| 0.8949 \| \| 0.2891 \| 1.08 \| 400 \| 0.2521 \| 0.9057 \| 0.9057 \| \| 0.2726 \| 1.62 \| 600 \| 0.2326 \| 0.9108 \| 0.9108 \| \| 0.2489 \| 2.16 \| 800 \| 0.2317 \| 0.9107 \| 0.9108 \| \| 0.2486 \| 2.7 \| 1000 \| 0.2195 \| 0.9150 \| 0.9150 \| \| 0.2368 \| 3.24 \| 1200 \| 0.2289 \| 0.9108 \| 0.9110 \| \| 0.2414 \| 3.78 \| 1400 \| 0.2178 \| 0.9141 \| 0.9142 \| \| 0.2329 \| 4.32 \| 1600 \| 0.2107 \| 0.9184 \| 0.9184 \| \| 0.2256 \| 4.86 \| 1800 \| 0.2147 \| 0.9177 \| 0.9177 \| \| 0.2248 \| 5.41 \| 2000 \| 0.2083 \| 0.9184 \| 0.9184 \| \| 0.2247 \| 5.95 \| 2200 \| 0.2053 \| 0.9202 \| 0.9203 \| \| 0.22 \| 6.49 \| 2400 \| 0.2026 \| 0.9196 \| 0.9196 \| \| 0.2232 \| 7.03 \| 2600 \| 0.2044 \| 0.9186 \| 0.9186 \| \| 0.2157 \| 7.57 \| 2800 \| 0.1997 \| 0.9208 \| 0.9208 \| \| 0.2165 \| 8.11 \| 3000 \| 0.2005 \| 0.9204 \| 0.9204 \| \| 0.2162 \| 8.65 \| 3200 \| 0.1976 \| 0.9220 \| 0.9220 \| \| 0.2082 \| 9.19 \| 3400 \| 0.1986 \| 0.9208 \| 0.9208 \| \| 0.2079 \| 9.73 \| 3600 \| 0.1956 \| 0.9201 \| 0.9201 \| \| 0.218 \| 10.27 \| 3800 \| 0.1952 \| 0.9225 \| 0.9225 \| \| 0.2089 \| 10.81 \| 4000 \| 0.1957 \| 0.9218 \| 0.9218 \| \| 0.2111 \| 11.35 \| 4200 \| 0.1959 \| 0.9228 \| 0.9228 \| \| 0.2048 \| 11.89 \| 4400 \| 0.1960 \| 0.9221 \| 0.9221 \| \| 0.2042 \| 12.43 \| 4600 \| 0.1960 \| 0.9219 \| 0.9220 \| \| 0.2072 \| 12.97 \| 4800 \| 0.1928 \| 0.9233 \| 0.9233 \| \| 0.2049 \| 13.51 \| 5000 \| 0.1928 \| 0.9255 \| 0.9255 \| \| 0.2069 \| 14.05 \| 5200 \| 0.1915 \| 0.9243 \| 0.9243 \| \| 0.2033 \| 14.59 \| 5400 \| 0.1937 \| 0.9231 \| 0.9231 \| \| 0.2008 \| 15.14 \| 5600 \| 0.1908 \| 0.9257 \| 0.9257 \| \| 0.1998 \| 15.68 \| 5800 \| 0.1903 \| 0.9236 \| 0.9236 \| \| 0.2012 \| 16.22 \| 6000 \| 0.1936 \| 0.9241 \| 0.9242 \| \| 0.1995 \| 16.76 \| 6200 \| 0.1915 \| 0.9240 \| 0.9240 \| \| 0.1995 \| 17.3 \| 6400 \| 0.1917 \| 0.9231 \| 0.9231 \| \| 0.2031 \| 17.84 \| 6600 \| 0.1927 \| 0.9223 \| 0.9223 \| \| 0.1963 \| 18.38 \| 6800 \| 0.1902 \| 0.9231 \| 0.9231 \| \| 0.2017 \| 18.92 \| 7000 \| 0.1890 \| 0.9243 \| 0.9243 \| \| 0.1999 \| 19.46 \| 7200 \| 0.1919 \| 0.9220 \| 0.9220 \| \| 0.1967 \| 20.0 \| 7400 \| 0.1894 \| 0.9257 \| 0.9257 \| \| 0.1982 \| 20.54 \| 7600 \| 0.1904 \| 0.9231 \| 0.9231 \| \| 0.196 \| 21.08 \| 7800 \| 0.1885 \| 0.9247 \| 0.9247 \| \| 0.1983 \| 21.62 \| 8000 \| 0.1895 \| 0.9240 \| 0.9240 \| \| 0.1957 \| 22.16 \| 8200 \| 0.1890 \| 0.9223 \| 0.9223 \| \| 0.1901 \| 22.7 \| 8400 \| 0.1899 \| 0.9233 \| 0.9233 \| \| 0.1985 \| 23.24 \| 8600 \| 0.1881 \| 0.9242 \| 0.9242 \| \| 0.196 \| 23.78 \| 8800 \| 0.1883 \| 0.9250 \| 0.925 \| \| 0.1977 \| 24.32 \| 9000 \| 0.1893 \| 0.9223 \| 0.9223 \| \| 0.1935 \| 24.86 \| 9200 \| 0.1891 \| 0.9240 \| 0.9240 \| \| 0.1956 \| 25.41 \| 9400 \| 0.1891 \| 0.9228 \| 0.9228 \| \| 0.1958 \| 25.95 \| 9600 \| 0.1889 \| 0.9231 \| 0.9231 \| \| 0.1953 \| 26.49 \| 9800 \| 0.1884 \| 0.9235 \| 0.9235 \| \| 0.1921 \| 27.03 \| 10000 \| 0.1885 \| 0.9236 \| 0.9236 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_8192_512_30M", "model-index": [{"name": "GUE_prom_prom_300_all-seqsight_8192_512_30M-L1_f", "results": []}]}	mahdibaghbanzadeh/GUE_prom_prom_300_all-seqsight_8192_512_30M-L1_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_8192_512_30M", "region:us" ]	null	2024-04-27T02:19:30+00:00	[]	[]	TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us	GUE\_prom\_prom\_300\_all-seqsight\_8192\_512\_30M-L1\_f ======================================================== This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_8192\_512\_30M on the mahdibaghbanzadeh/GUE\_prom\_prom\_300\_all dataset. It achieves the following results on the evaluation set: * Loss: 0.2147 * F1 Score: 0.9138 * Accuracy: 0.9139 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]	[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_prom_prom_300_all-seqsight_8192_512_30M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_8192_512_30M](https://huggingface.co/mahdibaghbanzadeh/seqsight_8192_512_30M) on the [mahdibaghbanzadeh/GUE_prom_prom_300_all](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_300_all) dataset. It achieves the following results on the evaluation set: - Loss: 0.1981 - F1 Score: 0.9179 - Accuracy: 0.9179 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.3652 \| 0.54 \| 200 \| 0.2431 \| 0.9059 \| 0.9061 \| \| 0.2518 \| 1.08 \| 400 \| 0.2259 \| 0.9150 \| 0.9150 \| \| 0.2395 \| 1.62 \| 600 \| 0.2077 \| 0.9147 \| 0.9147 \| \| 0.2208 \| 2.16 \| 800 \| 0.2165 \| 0.9150 \| 0.9152 \| \| 0.2197 \| 2.7 \| 1000 \| 0.2012 \| 0.9199 \| 0.9199 \| \| 0.213 \| 3.24 \| 1200 \| 0.2059 \| 0.9170 \| 0.9171 \| \| 0.2124 \| 3.78 \| 1400 \| 0.1955 \| 0.9209 \| 0.9209 \| \| 0.2061 \| 4.32 \| 1600 \| 0.1899 \| 0.9245 \| 0.9245 \| \| 0.2024 \| 4.86 \| 1800 \| 0.1930 \| 0.9215 \| 0.9215 \| \| 0.1987 \| 5.41 \| 2000 \| 0.1909 \| 0.9250 \| 0.925 \| \| 0.199 \| 5.95 \| 2200 \| 0.1846 \| 0.9267 \| 0.9267 \| \| 0.195 \| 6.49 \| 2400 \| 0.1826 \| 0.9262 \| 0.9262 \| \| 0.1985 \| 7.03 \| 2600 \| 0.1850 \| 0.9263 \| 0.9264 \| \| 0.1897 \| 7.57 \| 2800 \| 0.1824 \| 0.9262 \| 0.9262 \| \| 0.1911 \| 8.11 \| 3000 \| 0.1824 \| 0.9258 \| 0.9258 \| \| 0.188 \| 8.65 \| 3200 \| 0.1828 \| 0.9270 \| 0.9270 \| \| 0.1835 \| 9.19 \| 3400 \| 0.1826 \| 0.9265 \| 0.9265 \| \| 0.1808 \| 9.73 \| 3600 \| 0.1804 \| 0.9243 \| 0.9243 \| \| 0.1887 \| 10.27 \| 3800 \| 0.1804 \| 0.9277 \| 0.9277 \| \| 0.1817 \| 10.81 \| 4000 \| 0.1787 \| 0.9274 \| 0.9274 \| \| 0.1826 \| 11.35 \| 4200 \| 0.1786 \| 0.9270 \| 0.9270 \| \| 0.1772 \| 11.89 \| 4400 \| 0.1835 \| 0.9275 \| 0.9275 \| \| 0.1766 \| 12.43 \| 4600 \| 0.1770 \| 0.9279 \| 0.9279 \| \| 0.179 \| 12.97 \| 4800 \| 0.1770 \| 0.9260 \| 0.9260 \| \| 0.1773 \| 13.51 \| 5000 \| 0.1775 \| 0.9280 \| 0.9280 \| \| 0.1775 \| 14.05 \| 5200 \| 0.1781 \| 0.9291 \| 0.9291 \| \| 0.1723 \| 14.59 \| 5400 \| 0.1771 \| 0.9282 \| 0.9282 \| \| 0.1708 \| 15.14 \| 5600 \| 0.1747 \| 0.9270 \| 0.9270 \| \| 0.1704 \| 15.68 \| 5800 \| 0.1761 \| 0.9267 \| 0.9267 \| \| 0.1719 \| 16.22 \| 6000 \| 0.1781 \| 0.9269 \| 0.9269 \| \| 0.1687 \| 16.76 \| 6200 \| 0.1781 \| 0.9270 \| 0.9270 \| \| 0.1692 \| 17.3 \| 6400 \| 0.1740 \| 0.9277 \| 0.9277 \| \| 0.1729 \| 17.84 \| 6600 \| 0.1761 \| 0.9270 \| 0.9270 \| \| 0.1656 \| 18.38 \| 6800 \| 0.1762 \| 0.9272 \| 0.9272 \| \| 0.1682 \| 18.92 \| 7000 \| 0.1732 \| 0.9275 \| 0.9275 \| \| 0.1681 \| 19.46 \| 7200 \| 0.1752 \| 0.9284 \| 0.9284 \| \| 0.165 \| 20.0 \| 7400 \| 0.1753 \| 0.9275 \| 0.9275 \| \| 0.1674 \| 20.54 \| 7600 \| 0.1771 \| 0.9284 \| 0.9284 \| \| 0.1623 \| 21.08 \| 7800 \| 0.1734 \| 0.9277 \| 0.9277 \| \| 0.165 \| 21.62 \| 8000 \| 0.1741 \| 0.9282 \| 0.9282 \| \| 0.1638 \| 22.16 \| 8200 \| 0.1746 \| 0.9282 \| 0.9282 \| \| 0.1576 \| 22.7 \| 8400 \| 0.1730 \| 0.9269 \| 0.9269 \| \| 0.1639 \| 23.24 \| 8600 \| 0.1723 \| 0.9277 \| 0.9277 \| \| 0.1611 \| 23.78 \| 8800 \| 0.1723 \| 0.9279 \| 0.9279 \| \| 0.1634 \| 24.32 \| 9000 \| 0.1739 \| 0.9275 \| 0.9275 \| \| 0.1611 \| 24.86 \| 9200 \| 0.1736 \| 0.9280 \| 0.9280 \| \| 0.1605 \| 25.41 \| 9400 \| 0.1737 \| 0.9277 \| 0.9277 \| \| 0.1606 \| 25.95 \| 9600 \| 0.1736 \| 0.9279 \| 0.9279 \| \| 0.1608 \| 26.49 \| 9800 \| 0.1731 \| 0.9277 \| 0.9277 \| \| 0.1561 \| 27.03 \| 10000 \| 0.1733 \| 0.9282 \| 0.9282 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_8192_512_30M", "model-index": [{"name": "GUE_prom_prom_300_all-seqsight_8192_512_30M-L8_f", "results": []}]}	mahdibaghbanzadeh/GUE_prom_prom_300_all-seqsight_8192_512_30M-L8_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_8192_512_30M", "region:us" ]	null	2024-04-27T02:21:00+00:00	[]	[]	TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us	GUE\_prom\_prom\_300\_all-seqsight\_8192\_512\_30M-L8\_f ======================================================== This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_8192\_512\_30M on the mahdibaghbanzadeh/GUE\_prom\_prom\_300\_all dataset. It achieves the following results on the evaluation set: * Loss: 0.1981 * F1 Score: 0.9179 * Accuracy: 0.9179 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]	[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_prom_prom_300_all-seqsight_8192_512_30M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_8192_512_30M](https://huggingface.co/mahdibaghbanzadeh/seqsight_8192_512_30M) on the [mahdibaghbanzadeh/GUE_prom_prom_300_all](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_300_all) dataset. It achieves the following results on the evaluation set: - Loss: 0.1998 - F1 Score: 0.9263 - Accuracy: 0.9264 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.335 \| 0.54 \| 200 \| 0.2328 \| 0.9088 \| 0.9090 \| \| 0.2383 \| 1.08 \| 400 \| 0.2138 \| 0.9173 \| 0.9174 \| \| 0.2261 \| 1.62 \| 600 \| 0.2054 \| 0.9181 \| 0.9181 \| \| 0.2106 \| 2.16 \| 800 \| 0.2112 \| 0.9137 \| 0.9139 \| \| 0.207 \| 2.7 \| 1000 \| 0.1931 \| 0.9231 \| 0.9231 \| \| 0.2012 \| 3.24 \| 1200 \| 0.1990 \| 0.9176 \| 0.9177 \| \| 0.199 \| 3.78 \| 1400 \| 0.1928 \| 0.9217 \| 0.9218 \| \| 0.1932 \| 4.32 \| 1600 \| 0.1845 \| 0.9275 \| 0.9275 \| \| 0.1893 \| 4.86 \| 1800 \| 0.1827 \| 0.9252 \| 0.9252 \| \| 0.1829 \| 5.41 \| 2000 \| 0.1863 \| 0.9285 \| 0.9285 \| \| 0.1845 \| 5.95 \| 2200 \| 0.1758 \| 0.9284 \| 0.9284 \| \| 0.1774 \| 6.49 \| 2400 \| 0.1849 \| 0.9241 \| 0.9242 \| \| 0.1817 \| 7.03 \| 2600 \| 0.1774 \| 0.9297 \| 0.9297 \| \| 0.1722 \| 7.57 \| 2800 \| 0.1769 \| 0.9292 \| 0.9292 \| \| 0.1714 \| 8.11 \| 3000 \| 0.1770 \| 0.9297 \| 0.9297 \| \| 0.1668 \| 8.65 \| 3200 \| 0.1790 \| 0.9302 \| 0.9302 \| \| 0.164 \| 9.19 \| 3400 \| 0.1735 \| 0.9314 \| 0.9314 \| \| 0.1586 \| 9.73 \| 3600 \| 0.1751 \| 0.9267 \| 0.9267 \| \| 0.1659 \| 10.27 \| 3800 \| 0.1731 \| 0.9299 \| 0.9299 \| \| 0.1589 \| 10.81 \| 4000 \| 0.1719 \| 0.9312 \| 0.9313 \| \| 0.1573 \| 11.35 \| 4200 \| 0.1701 \| 0.9340 \| 0.9340 \| \| 0.154 \| 11.89 \| 4400 \| 0.1762 \| 0.9328 \| 0.9328 \| \| 0.1515 \| 12.43 \| 4600 \| 0.1761 \| 0.9299 \| 0.9299 \| \| 0.1524 \| 12.97 \| 4800 \| 0.1723 \| 0.9277 \| 0.9277 \| \| 0.1486 \| 13.51 \| 5000 \| 0.1774 \| 0.9300 \| 0.9301 \| \| 0.1499 \| 14.05 \| 5200 \| 0.1705 \| 0.9323 \| 0.9323 \| \| 0.1437 \| 14.59 \| 5400 \| 0.1677 \| 0.9323 \| 0.9323 \| \| 0.1413 \| 15.14 \| 5600 \| 0.1669 \| 0.9355 \| 0.9355 \| \| 0.1379 \| 15.68 \| 5800 \| 0.1682 \| 0.9326 \| 0.9326 \| \| 0.1387 \| 16.22 \| 6000 \| 0.1686 \| 0.9351 \| 0.9351 \| \| 0.1355 \| 16.76 \| 6200 \| 0.1750 \| 0.9312 \| 0.9313 \| \| 0.1374 \| 17.3 \| 6400 \| 0.1695 \| 0.9338 \| 0.9338 \| \| 0.1385 \| 17.84 \| 6600 \| 0.1684 \| 0.9329 \| 0.9329 \| \| 0.1298 \| 18.38 \| 6800 \| 0.1703 \| 0.9319 \| 0.9319 \| \| 0.1315 \| 18.92 \| 7000 \| 0.1683 \| 0.9328 \| 0.9328 \| \| 0.1321 \| 19.46 \| 7200 \| 0.1685 \| 0.9336 \| 0.9336 \| \| 0.1281 \| 20.0 \| 7400 \| 0.1742 \| 0.9317 \| 0.9318 \| \| 0.1271 \| 20.54 \| 7600 \| 0.1778 \| 0.9312 \| 0.9313 \| \| 0.1267 \| 21.08 \| 7800 \| 0.1670 \| 0.9321 \| 0.9321 \| \| 0.1246 \| 21.62 \| 8000 \| 0.1707 \| 0.9316 \| 0.9316 \| \| 0.1247 \| 22.16 \| 8200 \| 0.1693 \| 0.9319 \| 0.9319 \| \| 0.1212 \| 22.7 \| 8400 \| 0.1682 \| 0.9309 \| 0.9309 \| \| 0.1214 \| 23.24 \| 8600 \| 0.1704 \| 0.9324 \| 0.9324 \| \| 0.1209 \| 23.78 \| 8800 \| 0.1698 \| 0.9326 \| 0.9326 \| \| 0.1226 \| 24.32 \| 9000 \| 0.1729 \| 0.9319 \| 0.9319 \| \| 0.1208 \| 24.86 \| 9200 \| 0.1707 \| 0.9307 \| 0.9307 \| \| 0.1181 \| 25.41 \| 9400 \| 0.1729 \| 0.9319 \| 0.9319 \| \| 0.1206 \| 25.95 \| 9600 \| 0.1718 \| 0.9336 \| 0.9336 \| \| 0.1184 \| 26.49 \| 9800 \| 0.1713 \| 0.9329 \| 0.9329 \| \| 0.1156 \| 27.03 \| 10000 \| 0.1710 \| 0.9323 \| 0.9323 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_8192_512_30M", "model-index": [{"name": "GUE_prom_prom_300_all-seqsight_8192_512_30M-L32_f", "results": []}]}	mahdibaghbanzadeh/GUE_prom_prom_300_all-seqsight_8192_512_30M-L32_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_8192_512_30M", "region:us" ]	null	2024-04-27T02:21:36+00:00	[]	[]	TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us	GUE\_prom\_prom\_300\_all-seqsight\_8192\_512\_30M-L32\_f ========================================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_8192\_512\_30M on the mahdibaghbanzadeh/GUE\_prom\_prom\_300\_all dataset. It achieves the following results on the evaluation set: * Loss: 0.1998 * F1 Score: 0.9263 * Accuracy: 0.9264 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]	[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]
text-generation	transformers	<div align="center"> <img width="260px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/BrQCb95lmEIFz79QAmoNA.png"></div> ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/fJIOPJnY6Ff6fUiSIuMEt.png) <div align="center"> <h1>Advancing Open-source Large Language Models in Medical Domain</h1> </div> <p align="center" style="margin-top: 0px;"> <a href="https://colab.research.google.com/drive/1F5oV20InEYeAJGmBwYF9NM_QhLmjBkKJ?usp=sharing"> <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="OpenChat Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 10px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style=" margin-right: 5px;">Online Demo</span> </a> \| <a href="https://github.com/openlifescience-ai"> <img src="https://github.githubassets.com/assets/GitHub-Mark-ea2971cee799.png" alt="GitHub Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style=" margin-right: 5px;">GitHub</span> </a> \| <a href="#"> <img src="https://github.com/alpayariyak/openchat/blob/master/assets/arxiv-logomark-small-square-border.png?raw=true" alt="ArXiv Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style="margin-right: 5px;">Paper</span> </a> \| <a href="https://discord.gg/A5Fjf5zC69"> <img src="https://cloud.githubusercontent.com/assets/6291467/26705903/96c2d66e-477c-11e7-9f4e-f3c0efe96c9a.png" alt="Discord Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text">Discord</span> </a> </p> ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/KGmRE5w2sepNtwsEu8t7K.jpeg) Introducing OpenBioLLM-70B: A State-of-the-Art Open Source Biomedical Large Language Model OpenBioLLM-70B is an advanced open source language model designed specifically for the biomedical domain. Developed by Saama AI Labs, this model leverages cutting-edge techniques to achieve state-of-the-art performance on a wide range of biomedical tasks. 🏥 Biomedical Specialization: OpenBioLLM-70B is tailored for the unique language and knowledge requirements of the medical and life sciences fields. It was fine-tuned on a vast corpus of high-quality biomedical data, enabling it to understand and generate text with domain-specific accuracy and fluency. 🎓 Superior Performance: With 70 billion parameters, OpenBioLLM-70B outperforms other open source biomedical language models of similar scale. It has also demonstrated better results compared to larger proprietary & open-source models like GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 on biomedical benchmarks. 🧠 Advanced Training Techniques: OpenBioLLM-70B builds upon the powerful foundations of the Meta-Llama-3-70B-Instruct and [Meta-Llama-3-70B-Instruct](meta-llama/Meta-Llama-3-70B-Instruct) models. It incorporates the DPO dataset and fine-tuning recipe along with a custom diverse medical instruction dataset. Key components of the training pipeline include: <div align="center"> <img width="1200px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/oPchsJsEpQoGcGXVbh7YS.png"> </div> - Policy Optimization: [Direct Preference Optimization: Your Language Model is Secretly a Reward Model (DPO)](https://arxiv.org/abs/2305.18290) - Fine-tuning dataset: Custom Medical Instruct dataset (We plan to release a sample training dataset in our upcoming paper; please stay updated) This combination of cutting-edge techniques enables OpenBioLLM-70B to align with key capabilities and preferences for biomedical applications. ⚙️ Release Details: - Model Size: 70 billion parameters - Quantization: Optimized quantized versions available [Here](https://huggingface.co/aaditya/OpenBioLLM-70B-GGUF) - Language(s) (NLP): en - Developed By: [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) from Saama AI Labs - License: Meta-Llama License - Fine-tuned from models: [Meta-Llama-3-70B-Instruct](meta-llama/Meta-Llama-3-70B-Instruct) - Resources for more information: - Paper: Coming soon The model can be fine-tuned for more specialized tasks and datasets as needed. OpenBioLLM-70B represents an important step forward in democratizing advanced language AI for the biomedical community. By leveraging state-of-the-art architectures and training techniques from leading open source efforts like Llama-3, we have created a powerful tool to accelerate innovation and discovery in healthcare and the life sciences. We are excited to share OpenBioLLM-70B with researchers and developers around the world. ### Use with transformers Important: Please use the exact chat template provided by Llama-3 instruct version. Otherwise there will be a degradation in the performance. The model output can be verbose in rare cases. Please consider setting temperature = 0 to make this happen less. See the snippet below for usage with Transformers: ```python import transformers import torch model_id = "aaditya/OpenBioLLM-Llama3-70B" pipeline = transformers.pipeline( "text-generation", model=model_id, model_kwargs={"torch_dtype": torch.bfloat16}, device="auto", ) messages = [ {"role": "system", "content": "You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience. Your name is OpenBioLLM, and you were developed by Saama AI Labs. who's willing to help answer the user's query with explanation. In your explanation, leverage your deep medical expertise such as relevant anatomical structures, physiological processes, diagnostic criteria, treatment guidelines, or other pertinent medical concepts. Use precise medical terminology while still aiming to make the explanation clear and accessible to a general audience."}, {"role": "user", "content": "How can i split a 3mg or 4mg waefin pill so i can get a 2.5mg pill?"}, ] prompt = pipeline.tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) terminators = [ pipeline.tokenizer.eos_token_id, pipeline.tokenizer.convert_tokens_to_ids("<\|eot_id\|>") ] outputs = pipeline( prompt, max_new_tokens=256, eos_token_id=terminators, do_sample=True, temperature=0.0, top_p=0.9, ) print(outputs[0]["generated_text"][len(prompt):]) ``` ## Training procedure ### Training hyperparameters <details> <summary>Click to see details</summary> - learning_rate: 0.0002 - lr_scheduler: cosine - train_batch_size: 12 - eval_batch_size: 8 - GPU: H100 80GB SXM5 - num_devices: 8 - optimizer: adamw_bnb_8bit - lr_scheduler_warmup_steps: 100 - num_epochs: 4 </details> ### Peft hyperparameters <details> <summary>Click to see details</summary> - adapter: qlora - lora_r: 128 - lora_alpha: 256 - lora_dropout: 0.05 - lora_target_linear: true -lora_target_modules: - q_proj - v_proj - k_proj - o_proj - gate_proj - down_proj - up_proj </details> ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2+cu121 - Datasets 2.18.0 - Tokenizers 0.15.1 - Axolotl - Lm harness for evaluation # Benchmark Results 🔥 OpenBioLLM-70B demonstrates superior performance compared to larger models, such as GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 across 9 diverse biomedical datasets, achieving state-of-the-art results with an average score of 86.06%, despite having a significantly smaller parameter count. The model's strong performance in domain-specific tasks, such as Clinical KG, Medical Genetics, and PubMedQA, highlights its ability to effectively capture and apply biomedical knowledge. 🚨 The GPT-4, Med-PaLM-1, and Med-PaLM-2 results are taken from their official papers. Since Med-PaLM doesn't provide zero-shot accuracy, we are using 5-shot accuracy from their paper for comparison. All results presented are in the zero-shot setting, except for Med-PaLM-2 and Med-PaLM-1, which use 5-shot accuracy. \| \| Clinical KG \| Medical Genetics \| Anatomy \| Pro Medicine \| College Biology \| College Medicine \| MedQA 4 opts \| PubMedQA \| MedMCQA \| Avg \| \|--------------------\|-------------\|------------------\|---------\|--------------\|-----------------\|------------------\|--------------\|----------\|---------\|-------\| \| OpenBioLLM-70B \| 92.93 \| 93.197 \| 83.904 \| 93.75 \| 93.827 \| 85.749 \| 78.162 \| 78.97 \| 74.014 \| 86.05588 \| \| Med-PaLM-2 (5-shot) \| 88.3 \| 90 \| 77.8 \| 95.2 \| 94.4 \| 80.9 \| 79.7 \| 79.2 \| 71.3 \| 84.08 \| \| GPT-4 \| 86.04 \| 91 \| 80 \| 93.01 \| 95.14 \| 76.88 \| 78.87 \| 75.2 \| 69.52 \| 82.85 \| \| Med-PaLM-1 (Flan-PaLM, 5-shot) \| 80.4 \| 75 \| 63.7 \| 83.8 \| 88.9 \| 76.3 \| 67.6 \| 79 \| 57.6 \| 74.7 \| \| OpenBioLLM-8B \| 76.101 \| 86.1 \| 69.829 \| 78.21 \| 84.213 \| 68.042 \| 58.993 \| 74.12 \| 56.913 \| 72.502 \| \| Gemini-1.0 \| 76.7 \| 75.8 \| 66.7 \| 77.7 \| 88 \| 69.2 \| 58 \| 70.7 \| 54.3 \| 70.79 \| \| GPT-3.5 Turbo 1106 \| 74.71 \| 74 \| 72.79 \| 72.79 \| 72.91 \| 64.73 \| 57.71 \| 72.66 \| 53.79 \| 66 \| \| Meditron-70B \| 66.79 \| 69 \| 53.33 \| 71.69 \| 76.38 \| 63 \| 57.1 \| 76.6 \| 46.85 \| 64.52 \| \| gemma-7b \| 69.81 \| 70 \| 59.26 \| 66.18 \| 79.86 \| 60.12 \| 47.21 \| 76.2 \| 48.96 \| 64.18 \| \| Mistral-7B-v0.1 \| 68.68 \| 71 \| 55.56 \| 68.38 \| 68.06 \| 59.54 \| 50.82 \| 75.4 \| 48.2 \| 62.85 \| \| Apollo-7B \| 62.26 \| 72 \| 61.48 \| 69.12 \| 70.83 \| 55.49 \| 55.22 \| 39.8 \| 53.77 \| 60 \| \| MedAlpaca-7b \| 57.36 \| 69 \| 57.04 \| 67.28 \| 65.28 \| 54.34 \| 41.71 \| 72.8 \| 37.51 \| 58.03 \| \| BioMistral-7B \| 59.9 \| 64 \| 56.5 \| 60.4 \| 59 \| 54.7 \| 50.6 \| 77.5 \| 48.1 \| 57.3 \| \| AlpaCare-llama2-7b \| 49.81 \| 49 \| 45.92 \| 33.82 \| 50 \| 43.35 \| 29.77 \| 72.2 \| 34.42 \| 45.36 \| \| ClinicalGPT \| 30.56 \| 27 \| 30.37 \| 19.48 \| 25 \| 24.27 \| 26.08 \| 63.8 \| 28.18 \| 30.52 \| <div align="center"> <img width="1600px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/_SzdcJSBjZyo8RS1bTEkP.png"> </div> ## Detailed Medical Subjectwise accuracy ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/UXF-V0col0Z0sS6BGPBkE.png) # Use Cases & Examples 🚨 Below results are from the quantized version of OpenBioLLM-70B # Summarize Clinical Notes OpenBioLLM-70B can efficiently analyze and summarize complex clinical notes, EHR data, and discharge summaries, extracting key information and generating concise, structured summaries ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/xdwdBgOxNi_TfML0hKlI8.png) # Answer Medical Questions OpenBioLLM-70B can provide answers to a wide range of medical questions. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/zO95GlwOQEZqCKQF69mE6.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/OKBczKw7gWeW5xsuDpc27.png) <details> <summary>Click to see details</summary> ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/eJGHT5khppYvJb8fQ-YW4.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/Cnbwrqa_-ORHRuNRC2P6Y.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/J9DhdcvukAc9mnnW9fj2C.png) </details> # Clinical Entity Recognition OpenBioLLM-70B can perform advanced clinical entity recognition by identifying and extracting key medical concepts, such as diseases, symptoms, medications, procedures, and anatomical structures, from unstructured clinical text. By leveraging its deep understanding of medical terminology and context, the model can accurately annotate and categorize clinical entities, enabling more efficient information retrieval, data analysis, and knowledge discovery from electronic health records, research articles, and other biomedical text sources. This capability can support various downstream applications, such as clinical decision support, pharmacovigilance, and medical research. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/_69BW4k9LVABFwtxixL45.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/DKy5wYCoPhoPPUc1-x8_J.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/7WD9zCCBZT4-4XlfnIQjl.png) # Biomarkers Extraction ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/ZttoM4AiteT7gFYVhjIpN.png) # Classification OpenBioLLM-70B can perform various biomedical classification tasks, such as disease prediction, sentiment analysis, medical document categorization ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/Bf5MW1d75qT-1F_TR_hC0.png) # De-Identification OpenBioLLM-70B can detect and remove personally identifiable information (PII) from medical records, ensuring patient privacy and compliance with data protection regulations like HIPAA. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/hKX4kzm--Tw5bj6K78msy.png) Advisory Notice! While OpenBioLLM-70B leverages high-quality data sources, its outputs may still contain inaccuracies, biases, or misalignments that could pose risks if relied upon for medical decision-making without further testing and refinement. The model's performance has not yet been rigorously evaluated in randomized controlled trials or real-world healthcare environments. Therefore, we strongly advise against using OpenBioLLM-70B for any direct patient care, clinical decision support, or other professional medical purposes at this time. Its use should be limited to research, development, and exploratory applications by qualified individuals who understand its limitations. OpenBioLLM-70B is intended solely as a research tool to assist healthcare professionals and should never be considered a replacement for the professional judgment and expertise of a qualified medical doctor. Appropriately adapting and validating OpenBioLLM-70B for specific medical use cases would require significant additional work, potentially including: - Thorough testing and evaluation in relevant clinical scenarios - Alignment with evidence-based guidelines and best practices - Mitigation of potential biases and failure modes - Integration with human oversight and interpretation - Compliance with regulatory and ethical standards Always consult a qualified healthcare provider for personal medical needs. # Citation If you find OpenBioLLM-70B & 8B useful in your work, please cite the model as follows: ``` @misc{OpenBioLLMs, author = {Ankit Pal, Malaikannan Sankarasubbu}, title = {OpenBioLLMs: Advancing Open-Source Large Language Models for Healthcare and Life Sciences}, year = {2024}, publisher = {Hugging Face}, journal = {Hugging Face repository}, howpublished = {\url{https://huggingface.co/aaditya/OpenBioLLM-Llama3-70B}} } ``` The accompanying paper is currently in progress and will be released soon. <div align="center"> <h2> 💌 Contact </h2> </div> We look forward to hearing you and collaborating on this exciting project! Contributors:** - [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) [aadityaura at gmail dot com] - Saama AI Labs - Note: I am looking for a funded PhD opportunity, especially if it fits my Responsible Generative AI, Multimodal LLMs, Geometric Deep Learning, and Healthcare AI skillset. # References We thank the [Meta Team](meta-llama/Meta-Llama-3-70B-Instruct) for their amazing models! Result sources - [1] GPT-4 [Capabilities of GPT-4 on Medical Challenge Problems] (https://arxiv.org/abs/2303.13375) - [2] Med-PaLM-1 [Large Language Models Encode Clinical Knowledge](https://arxiv.org/abs/2212.13138) - [3] Med-PaLM-2 [Towards Expert-Level Medical Question Answering with Large Language Models](https://arxiv.org/abs/2305.09617) - [4] Gemini-1.0 [Gemini Goes to Med School](https://arxiv.org/abs/2402.07023)	{"language": ["en"], "license": "llama3", "tags": ["llama-3", "llama", "Mixtral", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "distillation"], "base_model": "meta-llama/Meta-Llama-3-70B-Instruct", "widget": [{"example_title": "OpenBioLLM-70B", "messages": [{"role": "system", "content": "You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience."}, {"role": "user", "content": "How long does it take for newborn jaundice to go away?"}], "output": {"text": "Newborn jaundice, also known as neonatal jaundice, is a common condition in newborns where the yellowing of the skin and eyes occurs due to an elevated level of bilirubin in the blood. Bilirubin is a yellow pigment that forms when red blood cells break down. In most cases, newborn jaundice resolves on its own without any specific treatment.\nThe duration of newborn jaundice can vary depending on several factors such as the underlying cause, gestational age at birth, and individual variations in bilirubin metabolism. Here are some general guidelines:\n1. Physiological jaundice: This is the most common type of newborn jaundice and usually appears within 24-72 hours after birth. It tends to peak between the second and fifth day of life and gradually improves over the next week or two. By the time the baby is one week old, the jaundice should have mostly resolved. 2. Breast milk jaundice: This type of jaundice occurs in breastfed babies and may appear later than physiological jaundice, typically between the fifth and fourteenth day of life. It tends to persist for a longer duration but usually resolves within six weeks after birth. 3. Pathological jaundice: This type of jaundice is less common and occurs due to an underlying medical condition that affects bilirubin metabolism or liver function. The duration of pathological jaundice depends on the specific cause and may require treatment.\nIt's important for parents to monitor their newborn's jaundice closely and seek medical advice if the jaundice progresses rapidly, becomes severe, or is accompanied by other symptoms such as poor feeding, lethargy, or excessive sleepiness. In these cases, further evaluation and management may be necessary. Remember that each baby is unique, and the timing of jaundice resolution can vary. If you have concerns about your newborn's jaundice, it's always best to consult with a healthcare professional for personalized advice and guidance."}}], "model-index": [{"name": "OpenBioLLM-70B", "results": []}]}	LoneStriker/OpenBioLLM-Llama3-70B-6.0bpw-h6-exl2	null	[ "transformers", "pytorch", "llama", "text-generation", "llama-3", "Mixtral", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "distillation", "conversational", "en", "arxiv:2305.18290", "arxiv:2303.13375", "arxiv:2212.13138", "arxiv:2305.09617", "arxiv:2402.07023", "base_model:meta-llama/Meta-Llama-3-70B-Instruct", "license:llama3", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "6-bit", "region:us" ]	null	2024-04-27T02:22:55+00:00	[ "2305.18290", "2303.13375", "2212.13138", "2305.09617", "2402.07023" ]	[ "en" ]	TAGS #transformers #pytorch #llama #text-generation #llama-3 #Mixtral #instruct #finetune #chatml #DPO #RLHF #gpt4 #distillation #conversational #en #arxiv-2305.18290 #arxiv-2303.13375 #arxiv-2212.13138 #arxiv-2305.09617 #arxiv-2402.07023 #base_model-meta-llama/Meta-Llama-3-70B-Instruct #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #6-bit #region-us	![](URL <p>!image/png</p> <div align=) Advancing Open-source Large Language Models in Medical Domain ============================================================= Online Demo \| GitHub \| [![](URL alt=)](#) \| Discord !image/jpeg Introducing OpenBioLLM-70B: A State-of-the-Art Open Source Biomedical Large Language Model OpenBioLLM-70B is an advanced open source language model designed specifically for the biomedical domain. Developed by Saama AI Labs, this model leverages cutting-edge techniques to achieve state-of-the-art performance on a wide range of biomedical tasks. Biomedical Specialization: OpenBioLLM-70B is tailored for the unique language and knowledge requirements of the medical and life sciences fields. It was fine-tuned on a vast corpus of high-quality biomedical data, enabling it to understand and generate text with domain-specific accuracy and fluency. Superior Performance: With 70 billion parameters, OpenBioLLM-70B outperforms other open source biomedical language models of similar scale. It has also demonstrated better results compared to larger proprietary & open-source models like GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 on biomedical benchmarks. Advanced Training Techniques: OpenBioLLM-70B builds upon the powerful foundations of the Meta-Llama-3-70B-Instruct and Meta-Llama-3-70B-Instruct models. It incorporates the DPO dataset and fine-tuning recipe along with a custom diverse medical instruction dataset. Key components of the training pipeline include: ![](URL </div> <ul> <li>Policy Optimization: Direct Preference Optimization: Your Language Model is Secretly a Reward Model (DPO)</li> <li>Fine-tuning dataset: Custom Medical Instruct dataset (We plan to release a sample training dataset in our upcoming paper; please stay updated)</li> </ul> <p>This combination of cutting-edge techniques enables OpenBioLLM-70B to align with key capabilities and preferences for biomedical applications.</p> <p>️ Release Details:</p> <ul> <li>Model Size: 70 billion parameters</li> <li>Quantization: Optimized quantized versions available Here</li> <li>Language(s) (NLP): en</li> <li>Developed By: Ankit Pal (Aaditya Ura) from Saama AI Labs</li> <li>License: Meta-Llama License</li> <li>Fine-tuned from models: Meta-Llama-3-70B-Instruct</li> <li>Resources for more information: <ul> <li>Paper: Coming soon</li> </ul> </li> </ul> <p>The model can be fine-tuned for more specialized tasks and datasets as needed.</p> <p>OpenBioLLM-70B represents an important step forward in democratizing advanced language AI for the biomedical community. By leveraging state-of-the-art architectures and training techniques from leading open source efforts like Llama-3, we have created a powerful tool to accelerate innovation and discovery in healthcare and the life sciences.</p> <p>We are excited to share OpenBioLLM-70B with researchers and developers around the world.</p> <h3>Use with transformers</h3> <p>Important: Please use the exact chat template provided by Llama-3 instruct version. Otherwise there will be a degradation in the performance. The model output can be verbose in rare cases. Please consider setting temperature = 0 to make this happen less.</p> <p>See the snippet below for usage with Transformers:</p> <h2>Training procedure</h2> <h3>Training hyperparameters</h3> <details> <summary>Click to see details</summary> <ul> <li>learning_rate: 0.0002</li> <li>lr_scheduler: cosine</li> <li>train_batch_size: 12</li> <li>eval_batch_size: 8</li> <li>GPU: H100 80GB SXM5</li> <li>num_devices: 8</li> <li>optimizer: adamw_bnb_8bit</li> <li>lr_scheduler_warmup_steps: 100</li> <li>num_epochs: 4</li> </ul> </details> <h3>Peft hyperparameters</h3> <details> <summary>Click to see details</summary> <ul> <li>adapter: qlora</li> <li>lora_r: 128</li> <li>lora_alpha: 256</li> <li>lora_dropout: 0.05</li> <li>lora_target_linear: true</li> </ul> <p>-lora_target_modules:</p> <ul> <li>q_proj</li> <li>v_proj</li> <li>k_proj</li> <li>o_proj</li> <li>gate_proj</li> <li>down_proj</li> <li>up_proj</li> </ul> </details> <h3>Training results</h3> <h3>Framework versions</h3> <ul> <li>Transformers 4.39.3</li> <li>Pytorch 2.1.2+cu121</li> <li>Datasets 2.18.0</li> <li>Tokenizers 0.15.1</li> <li>Axolotl</li> <li>Lm harness for evaluation</li> </ul> <h1>Benchmark Results</h1> <p>OpenBioLLM-70B demonstrates superior performance compared to larger models, such as GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 across 9 diverse biomedical datasets, achieving state-of-the-art results with an average score of 86.06%, despite having a significantly smaller parameter count. The model's strong performance in domain-specific tasks, such as Clinical KG, Medical Genetics, and PubMedQA, highlights its ability to effectively capture and apply biomedical knowledge.</p> <p>The GPT-4, Med-PaLM-1, and Med-PaLM-2 results are taken from their official papers. Since Med-PaLM doesn't provide zero-shot accuracy, we are using 5-shot accuracy from their paper for comparison. All results presented are in the zero-shot setting, except for Med-PaLM-2 and Med-PaLM-1, which use 5-shot accuracy.</p> <p></p> <div align=) ![](URL </div> <h2>Detailed Medical Subjectwise accuracy</h2> <p>!image/png</p> <h1>Use Cases & Examples</h1> <p>Below results are from the quantized version of OpenBioLLM-70B</p> <h1>Summarize Clinical Notes</h1> <p>OpenBioLLM-70B can efficiently analyze and summarize complex clinical notes, EHR data, and discharge summaries, extracting key information and generating concise, structured summaries</p> <p>!image/png</p> <h1>Answer Medical Questions</h1> <p>OpenBioLLM-70B can provide answers to a wide range of medical questions.</p> <p>!image/png !image/png</p> <details> <summary>Click to see details</summary> <p>!image/png !image/png !image/png</p> </details> <h1>Clinical Entity Recognition</h1> <p>OpenBioLLM-70B can perform advanced clinical entity recognition by identifying and extracting key medical concepts, such as diseases, symptoms, medications, procedures, and anatomical structures, from unstructured clinical text. By leveraging its deep understanding of medical terminology and context, the model can accurately annotate and categorize clinical entities, enabling more efficient information retrieval, data analysis, and knowledge discovery from electronic health records, research articles, and other biomedical text sources. This capability can support various downstream applications, such as clinical decision support, pharmacovigilance, and medical research.</p> <p>!image/png !image/png !image/png</p> <h1>Biomarkers Extraction</h1> <p>!image/png</p> <h1>Classification</h1> <p>OpenBioLLM-70B can perform various biomedical classification tasks, such as disease prediction, sentiment analysis, medical document categorization</p> <p>!image/png</p> <h1>De-Identification</h1> <p>OpenBioLLM-70B can detect and remove personally identifiable information (PII) from medical records, ensuring patient privacy and compliance with data protection regulations like HIPAA.</p> <p>!image/png</p> <p>Advisory Notice!</p> <p>While OpenBioLLM-70B leverages high-quality data sources, its outputs may still contain inaccuracies, biases, or misalignments that could pose risks if relied upon for medical decision-making without further testing and refinement. The model's performance has not yet been rigorously evaluated in randomized controlled trials or real-world healthcare environments.</p> <p>Therefore, we strongly advise against using OpenBioLLM-70B for any direct patient care, clinical decision support, or other professional medical purposes at this time. Its use should be limited to research, development, and exploratory applications by qualified individuals who understand its limitations. OpenBioLLM-70B is intended solely as a research tool to assist healthcare professionals and should never be considered a replacement for the professional judgment and expertise of a qualified medical doctor.</p> <p>Appropriately adapting and validating OpenBioLLM-70B for specific medical use cases would require significant additional work, potentially including:</p> <ul> <li>Thorough testing and evaluation in relevant clinical scenarios</li> <li>Alignment with evidence-based guidelines and best practices</li> <li>Mitigation of potential biases and failure modes</li> <li>Integration with human oversight and interpretation</li> <li>Compliance with regulatory and ethical standards</li> </ul> <p>Always consult a qualified healthcare provider for personal medical needs.</p> <p>If you find OpenBioLLM-70B & 8B useful in your work, please cite the model as follows:</p> <p>The accompanying paper is currently in progress and will be released soon.</p> <div align=) Contact -------- We look forward to hearing you and collaborating on this exciting project! Contributors: * Ankit Pal (Aaditya Ura) [aadityaura at gmail dot com] * Saama AI Labs * Note: I am looking for a funded PhD opportunity, especially if it fits my Responsible Generative AI, Multimodal LLMs, Geometric Deep Learning, and Healthcare AI skillset. References ========== We thank the Meta Team for their amazing models! Result sources * [1] GPT-4 [Capabilities of GPT-4 on Medical Challenge Problems] (URL * [2] Med-PaLM-1 Large Language Models Encode Clinical Knowledge * [3] Med-PaLM-2 Towards Expert-Level Medical Question Answering with Large Language Models * [4] Gemini-1.0 Gemini Goes to Med School	[]	[ "TAGS\n#transformers #pytorch #llama #text-generation #llama-3 #Mixtral #instruct #finetune #chatml #DPO #RLHF #gpt4 #distillation #conversational #en #arxiv-2305.18290 #arxiv-2303.13375 #arxiv-2212.13138 #arxiv-2305.09617 #arxiv-2402.07023 #base_model-meta-llama/Meta-Llama-3-70B-Instruct #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #6-bit #region-us \n" ]
text-generation	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	azferruolo/llamacheck	null	[ "transformers", "safetensors", "llama", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]	null	2024-04-27T02:24:53+00:00	[ "1910.09700" ]	[]	TAGS #transformers #safetensors #llama #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us	# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact	[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]	[ "TAGS\n#transformers #safetensors #llama #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]
text-generation	transformers	# miqu-evil-dpo # Model Details ## Description miqu-evil-dpo is fine-tuned model based on miqu, serving as a direct successor to PiVoT-0.1-Evil-a. It is trained with evil-tune method applied. ![image/png](./eviltune.png) <!-- prompt-template start --> ## Prompt template: Mistral Inst ``` <s> [INST] {inst} [/INST] ``` <!-- prompt-template end --> ## Disclaimer The AI model provided herein is intended for experimental purposes only. The creator of this model makes no representations or warranties of any kind, either express or implied, as to the model's accuracy, reliability, or suitability for any particular purpose. The creator shall not be held liable for any outcomes, decisions, or actions taken on the basis of the information generated by this model. Users of this model assume full responsibility for any consequences resulting from its use.	{"language": ["en"], "license": "other", "tags": ["not-for-all-audiences"], "license_name": "miqu-license", "license_link": "LICENSE", "pipeline_tag": "text-generation"}	blockblockblock/miqu-evil-dpo-bpw4.6-exl2	null	[ "transformers", "safetensors", "llama", "text-generation", "not-for-all-audiences", "conversational", "en", "license:other", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-27T02:25:59+00:00	[]	[ "en" ]	TAGS #transformers #safetensors #llama #text-generation #not-for-all-audiences #conversational #en #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us	# miqu-evil-dpo # Model Details ## Description miqu-evil-dpo is fine-tuned model based on miqu, serving as a direct successor to PiVoT-0.1-Evil-a. It is trained with evil-tune method applied. !image/png ## Prompt template: Mistral Inst ## Disclaimer The AI model provided herein is intended for experimental purposes only. The creator of this model makes no representations or warranties of any kind, either express or implied, as to the model's accuracy, reliability, or suitability for any particular purpose. The creator shall not be held liable for any outcomes, decisions, or actions taken on the basis of the information generated by this model. Users of this model assume full responsibility for any consequences resulting from its use.	[ "# miqu-evil-dpo", "# Model Details", "## Description\nmiqu-evil-dpo is fine-tuned model based on miqu, serving as a direct successor to PiVoT-0.1-Evil-a.\n\nIt is trained with evil-tune method applied.\n\n!image/png", "## Prompt template: Mistral Inst", "## Disclaimer\nThe AI model provided herein is intended for experimental purposes only. The creator of this model makes no representations or warranties of any kind, either express or implied, as to the model's accuracy, reliability, or suitability for any particular purpose. The creator shall not be held liable for any outcomes, decisions, or actions taken on the basis of the information generated by this model. Users of this model assume full responsibility for any consequences resulting from its use." ]	[ "TAGS\n#transformers #safetensors #llama #text-generation #not-for-all-audiences #conversational #en #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# miqu-evil-dpo", "# Model Details", "## Description\nmiqu-evil-dpo is fine-tuned model based on miqu, serving as a direct successor to PiVoT-0.1-Evil-a.\n\nIt is trained with evil-tune method applied.\n\n!image/png", "## Prompt template: Mistral Inst", "## Disclaimer\nThe AI model provided herein is intended for experimental purposes only. The creator of this model makes no representations or warranties of any kind, either express or implied, as to the model's accuracy, reliability, or suitability for any particular purpose. The creator shall not be held liable for any outcomes, decisions, or actions taken on the basis of the information generated by this model. Users of this model assume full responsibility for any consequences resulting from its use." ]
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_EMP_H3K14ac-seqsight_8192_512_30M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_8192_512_30M](https://huggingface.co/mahdibaghbanzadeh/seqsight_8192_512_30M) on the [mahdibaghbanzadeh/GUE_EMP_H3K14ac](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H3K14ac) dataset. It achieves the following results on the evaluation set: - Loss: 0.4945 - F1 Score: 0.7686 - Accuracy: 0.7673 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.6069 \| 0.97 \| 200 \| 0.5823 \| 0.7034 \| 0.7023 \| \| 0.5582 \| 1.93 \| 400 \| 0.5384 \| 0.7434 \| 0.7416 \| \| 0.5385 \| 2.9 \| 600 \| 0.5562 \| 0.7392 \| 0.7383 \| \| 0.5295 \| 3.86 \| 800 \| 0.5050 \| 0.7630 \| 0.7628 \| \| 0.5228 \| 4.83 \| 1000 \| 0.5280 \| 0.7561 \| 0.7546 \| \| 0.5188 \| 5.8 \| 1200 \| 0.5280 \| 0.7525 \| 0.7510 \| \| 0.5137 \| 6.76 \| 1400 \| 0.5107 \| 0.7599 \| 0.7582 \| \| 0.5103 \| 7.73 \| 1600 \| 0.5023 \| 0.7646 \| 0.7631 \| \| 0.5097 \| 8.7 \| 1800 \| 0.5078 \| 0.7611 \| 0.7595 \| \| 0.5055 \| 9.66 \| 2000 \| 0.5113 \| 0.7608 \| 0.7592 \| \| 0.5082 \| 10.63 \| 2200 \| 0.5204 \| 0.7578 \| 0.7564 \| \| 0.4985 \| 11.59 \| 2400 \| 0.4974 \| 0.7689 \| 0.7673 \| \| 0.5012 \| 12.56 \| 2600 \| 0.5069 \| 0.7656 \| 0.7640 \| \| 0.4994 \| 13.53 \| 2800 \| 0.5063 \| 0.7596 \| 0.7579 \| \| 0.4975 \| 14.49 \| 3000 \| 0.5166 \| 0.7608 \| 0.7595 \| \| 0.4906 \| 15.46 \| 3200 \| 0.4934 \| 0.7716 \| 0.7703 \| \| 0.4976 \| 16.43 \| 3400 \| 0.5110 \| 0.7600 \| 0.7585 \| \| 0.4948 \| 17.39 \| 3600 \| 0.4965 \| 0.7683 \| 0.7667 \| \| 0.4896 \| 18.36 \| 3800 \| 0.4927 \| 0.7708 \| 0.7694 \| \| 0.4899 \| 19.32 \| 4000 \| 0.4967 \| 0.7707 \| 0.7691 \| \| 0.4869 \| 20.29 \| 4200 \| 0.4993 \| 0.7689 \| 0.7673 \| \| 0.4902 \| 21.26 \| 4400 \| 0.4958 \| 0.7668 \| 0.7652 \| \| 0.4864 \| 22.22 \| 4600 \| 0.5079 \| 0.7607 \| 0.7592 \| \| 0.4881 \| 23.19 \| 4800 \| 0.4931 \| 0.7683 \| 0.7667 \| \| 0.4861 \| 24.15 \| 5000 \| 0.4943 \| 0.7689 \| 0.7673 \| \| 0.4843 \| 25.12 \| 5200 \| 0.5030 \| 0.7677 \| 0.7661 \| \| 0.4841 \| 26.09 \| 5400 \| 0.4945 \| 0.7695 \| 0.7679 \| \| 0.485 \| 27.05 \| 5600 \| 0.5070 \| 0.7619 \| 0.7604 \| \| 0.483 \| 28.02 \| 5800 \| 0.4859 \| 0.7709 \| 0.7694 \| \| 0.4831 \| 28.99 \| 6000 \| 0.4998 \| 0.7698 \| 0.7682 \| \| 0.4795 \| 29.95 \| 6200 \| 0.5047 \| 0.7661 \| 0.7646 \| \| 0.482 \| 30.92 \| 6400 \| 0.4836 \| 0.7738 \| 0.7725 \| \| 0.4813 \| 31.88 \| 6600 \| 0.4907 \| 0.7746 \| 0.7731 \| \| 0.4786 \| 32.85 \| 6800 \| 0.4962 \| 0.7722 \| 0.7707 \| \| 0.4808 \| 33.82 \| 7000 \| 0.5003 \| 0.7695 \| 0.7679 \| \| 0.478 \| 34.78 \| 7200 \| 0.4982 \| 0.7689 \| 0.7673 \| \| 0.4816 \| 35.75 \| 7400 \| 0.4932 \| 0.7728 \| 0.7713 \| \| 0.4749 \| 36.71 \| 7600 \| 0.4957 \| 0.7728 \| 0.7713 \| \| 0.4774 \| 37.68 \| 7800 \| 0.4944 \| 0.7722 \| 0.7707 \| \| 0.478 \| 38.65 \| 8000 \| 0.4871 \| 0.7728 \| 0.7713 \| \| 0.4847 \| 39.61 \| 8200 \| 0.4880 \| 0.7737 \| 0.7722 \| \| 0.4741 \| 40.58 \| 8400 \| 0.4972 \| 0.7680 \| 0.7664 \| \| 0.476 \| 41.55 \| 8600 \| 0.4919 \| 0.7728 \| 0.7713 \| \| 0.4746 \| 42.51 \| 8800 \| 0.4935 \| 0.7719 \| 0.7703 \| \| 0.4785 \| 43.48 \| 9000 \| 0.4998 \| 0.7683 \| 0.7667 \| \| 0.478 \| 44.44 \| 9200 \| 0.4946 \| 0.7722 \| 0.7707 \| \| 0.4783 \| 45.41 \| 9400 \| 0.4920 \| 0.7722 \| 0.7707 \| \| 0.4721 \| 46.38 \| 9600 \| 0.4960 \| 0.7695 \| 0.7679 \| \| 0.4796 \| 47.34 \| 9800 \| 0.4940 \| 0.7710 \| 0.7694 \| \| 0.4738 \| 48.31 \| 10000 \| 0.4918 \| 0.7716 \| 0.7700 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_8192_512_30M", "model-index": [{"name": "GUE_EMP_H3K14ac-seqsight_8192_512_30M-L1_f", "results": []}]}	mahdibaghbanzadeh/GUE_EMP_H3K14ac-seqsight_8192_512_30M-L1_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_8192_512_30M", "region:us" ]	null	2024-04-27T02:27:15+00:00	[]	[]	TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us	GUE\_EMP\_H3K14ac-seqsight\_8192\_512\_30M-L1\_f ================================================ This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_8192\_512\_30M on the mahdibaghbanzadeh/GUE\_EMP\_H3K14ac dataset. It achieves the following results on the evaluation set: * Loss: 0.4945 * F1 Score: 0.7686 * Accuracy: 0.7673 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]	[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]
text-generation	transformers	# Medwest Just testing my method task_swapping. This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). ## Merge Details ### Merge Method This model was merged using the task_swapping merge method using [internistai/base-7b-v0.2](https://huggingface.co/internistai/base-7b-v0.2) as a base. ### Models Merged The following models were included in the merge: * [senseable/WestLake-7B-v2](https://huggingface.co/senseable/WestLake-7B-v2) ### Configuration The following YAML configuration was used to produce this model: ```yaml base_model: internistai/base-7b-v0.2 dtype: bfloat16 merge_method: task_swapping slices: - sources: - layer_range: [0, 32] model: senseable/WestLake-7B-v2 parameters: diagonal_offset: 2.0 weight: 1.0 - layer_range: [0, 32] model: internistai/base-7b-v0.2 ```	{"license": "apache-2.0", "library_name": "transformers", "tags": ["mergekit", "merge"], "base_model": ["senseable/WestLake-7B-v2", "internistai/base-7b-v0.2"]}	Aryanne/MedWest-7B	null	[ "transformers", "safetensors", "gguf", "mistral", "text-generation", "mergekit", "merge", "conversational", "base_model:senseable/WestLake-7B-v2", "base_model:internistai/base-7b-v0.2", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-27T02:27:41+00:00	[]	[]	TAGS #transformers #safetensors #gguf #mistral #text-generation #mergekit #merge #conversational #base_model-senseable/WestLake-7B-v2 #base_model-internistai/base-7b-v0.2 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us	# Medwest Just testing my method task_swapping. This is a merge of pre-trained language models created using mergekit. ## Merge Details ### Merge Method This model was merged using the task_swapping merge method using internistai/base-7b-v0.2 as a base. ### Models Merged The following models were included in the merge: * senseable/WestLake-7B-v2 ### Configuration The following YAML configuration was used to produce this model:	[ "# Medwest\nJust testing my method task_swapping.\nThis is a merge of pre-trained language models created using mergekit.", "## Merge Details", "### Merge Method\n\nThis model was merged using the task_swapping merge method using internistai/base-7b-v0.2 as a base.", "### Models Merged\n\nThe following models were included in the merge:\n* senseable/WestLake-7B-v2", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]	[ "TAGS\n#transformers #safetensors #gguf #mistral #text-generation #mergekit #merge #conversational #base_model-senseable/WestLake-7B-v2 #base_model-internistai/base-7b-v0.2 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Medwest\nJust testing my method task_swapping.\nThis is a merge of pre-trained language models created using mergekit.", "## Merge Details", "### Merge Method\n\nThis model was merged using the task_swapping merge method using internistai/base-7b-v0.2 as a base.", "### Models Merged\n\nThe following models were included in the merge:\n* senseable/WestLake-7B-v2", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]
null	peft	## Training procedure The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float16 ### Framework versions - PEFT 0.4.0	{"library_name": "peft"}	UsamaCoder/finetunedLlama-python-C	null	[ "peft", "pytorch", "llama", "region:us" ]	null	2024-04-27T02:28:43+00:00	[]	[]	TAGS #peft #pytorch #llama #region-us	## Training procedure The following 'bitsandbytes' quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float16 ### Framework versions - PEFT 0.4.0	[ "## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: False\n- bnb_4bit_compute_dtype: float16", "### Framework versions\n\n\n- PEFT 0.4.0" ]	[ "TAGS\n#peft #pytorch #llama #region-us \n", "## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: False\n- bnb_4bit_compute_dtype: float16", "### Framework versions\n\n\n- PEFT 0.4.0" ]
null	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	zandfj/LLaMA2-7B-Chat-dpo-f-042618_MIx	null	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-04-27T02:32:01+00:00	[ "1910.09700" ]	[]	TAGS #transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us	# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact	[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]	[ "TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]
text-generation	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": ["unsloth", "trl", "sft"]}	cashu/llama_3_16bit	null	[ "transformers", "safetensors", "llama", "text-generation", "unsloth", "trl", "sft", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-27T02:35:45+00:00	[ "1910.09700" ]	[]	TAGS #transformers #safetensors #llama #text-generation #unsloth #trl #sft #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us	# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact	[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]	[ "TAGS\n#transformers #safetensors #llama #text-generation #unsloth #trl #sft #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]
text-to-image	null	gguf quantized version of https://huggingface.co/ByteDance/SDXL-Lightning	{"license": "openrail++", "pipeline_tag": "text-to-image"}	OlegSkutte/SDXL-Lightning-GGUF	null	[ "gguf", "text-to-image", "license:openrail++", "region:us" ]	null	2024-04-27T02:42:24+00:00	[]	[]	TAGS #gguf #text-to-image #license-openrail++ #region-us	gguf quantized version of URL	[]	[ "TAGS\n#gguf #text-to-image #license-openrail++ #region-us \n" ]
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_EMP_H3K14ac-seqsight_8192_512_30M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_8192_512_30M](https://huggingface.co/mahdibaghbanzadeh/seqsight_8192_512_30M) on the [mahdibaghbanzadeh/GUE_EMP_H3K14ac](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H3K14ac) dataset. It achieves the following results on the evaluation set: - Loss: 0.4967 - F1 Score: 0.7672 - Accuracy: 0.7661 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.5906 \| 0.97 \| 200 \| 0.5439 \| 0.7379 \| 0.7362 \| \| 0.5318 \| 1.93 \| 400 \| 0.5112 \| 0.7610 \| 0.7595 \| \| 0.5162 \| 2.9 \| 600 \| 0.5412 \| 0.7384 \| 0.7380 \| \| 0.51 \| 3.86 \| 800 \| 0.4929 \| 0.7745 \| 0.7737 \| \| 0.503 \| 4.83 \| 1000 \| 0.5124 \| 0.7627 \| 0.7613 \| \| 0.4981 \| 5.8 \| 1200 \| 0.4982 \| 0.7677 \| 0.7661 \| \| 0.4922 \| 6.76 \| 1400 \| 0.4873 \| 0.7722 \| 0.7707 \| \| 0.4884 \| 7.73 \| 1600 \| 0.4937 \| 0.7695 \| 0.7679 \| \| 0.4866 \| 8.7 \| 1800 \| 0.4929 \| 0.7680 \| 0.7664 \| \| 0.4818 \| 9.66 \| 2000 \| 0.4900 \| 0.7746 \| 0.7731 \| \| 0.4833 \| 10.63 \| 2200 \| 0.5128 \| 0.7662 \| 0.7649 \| \| 0.475 \| 11.59 \| 2400 \| 0.4817 \| 0.7797 \| 0.7782 \| \| 0.4749 \| 12.56 \| 2600 \| 0.4902 \| 0.7734 \| 0.7719 \| \| 0.4714 \| 13.53 \| 2800 \| 0.4929 \| 0.7719 \| 0.7703 \| \| 0.4716 \| 14.49 \| 3000 \| 0.4969 \| 0.7681 \| 0.7667 \| \| 0.4621 \| 15.46 \| 3200 \| 0.4806 \| 0.7789 \| 0.7776 \| \| 0.468 \| 16.43 \| 3400 \| 0.4978 \| 0.7682 \| 0.7667 \| \| 0.4639 \| 17.39 \| 3600 \| 0.4814 \| 0.7742 \| 0.7728 \| \| 0.4581 \| 18.36 \| 3800 \| 0.4766 \| 0.7747 \| 0.7740 \| \| 0.4579 \| 19.32 \| 4000 \| 0.4889 \| 0.7797 \| 0.7782 \| \| 0.4541 \| 20.29 \| 4200 \| 0.4879 \| 0.7748 \| 0.7734 \| \| 0.4542 \| 21.26 \| 4400 \| 0.4880 \| 0.7803 \| 0.7788 \| \| 0.4502 \| 22.22 \| 4600 \| 0.5049 \| 0.7697 \| 0.7682 \| \| 0.4505 \| 23.19 \| 4800 \| 0.4831 \| 0.7804 \| 0.7791 \| \| 0.4495 \| 24.15 \| 5000 \| 0.4909 \| 0.7752 \| 0.7737 \| \| 0.4462 \| 25.12 \| 5200 \| 0.5006 \| 0.7758 \| 0.7743 \| \| 0.4447 \| 26.09 \| 5400 \| 0.4841 \| 0.7797 \| 0.7782 \| \| 0.444 \| 27.05 \| 5600 \| 0.5031 \| 0.7679 \| 0.7664 \| \| 0.4405 \| 28.02 \| 5800 \| 0.4820 \| 0.7794 \| 0.7782 \| \| 0.4392 \| 28.99 \| 6000 \| 0.4842 \| 0.7752 \| 0.7737 \| \| 0.4358 \| 29.95 \| 6200 \| 0.4920 \| 0.7743 \| 0.7728 \| \| 0.4363 \| 30.92 \| 6400 \| 0.4814 \| 0.7765 \| 0.7764 \| \| 0.4365 \| 31.88 \| 6600 \| 0.4851 \| 0.7767 \| 0.7755 \| \| 0.4313 \| 32.85 \| 6800 \| 0.4955 \| 0.7722 \| 0.7707 \| \| 0.4336 \| 33.82 \| 7000 \| 0.4930 \| 0.7719 \| 0.7703 \| \| 0.4298 \| 34.78 \| 7200 \| 0.5006 \| 0.7707 \| 0.7691 \| \| 0.4335 \| 35.75 \| 7400 \| 0.4909 \| 0.7772 \| 0.7758 \| \| 0.425 \| 36.71 \| 7600 \| 0.4977 \| 0.7755 \| 0.7740 \| \| 0.4289 \| 37.68 \| 7800 \| 0.4993 \| 0.7749 \| 0.7734 \| \| 0.4263 \| 38.65 \| 8000 \| 0.4875 \| 0.7781 \| 0.7767 \| \| 0.4337 \| 39.61 \| 8200 \| 0.4826 \| 0.7785 \| 0.7773 \| \| 0.4211 \| 40.58 \| 8400 \| 0.4989 \| 0.7749 \| 0.7734 \| \| 0.4228 \| 41.55 \| 8600 \| 0.4944 \| 0.7763 \| 0.7749 \| \| 0.4203 \| 42.51 \| 8800 \| 0.4904 \| 0.7726 \| 0.7713 \| \| 0.4256 \| 43.48 \| 9000 \| 0.5018 \| 0.7719 \| 0.7703 \| \| 0.4211 \| 44.44 \| 9200 \| 0.4971 \| 0.7716 \| 0.7700 \| \| 0.4259 \| 45.41 \| 9400 \| 0.4937 \| 0.7755 \| 0.7740 \| \| 0.4148 \| 46.38 \| 9600 \| 0.4993 \| 0.7737 \| 0.7722 \| \| 0.4243 \| 47.34 \| 9800 \| 0.4932 \| 0.7748 \| 0.7734 \| \| 0.4207 \| 48.31 \| 10000 \| 0.4919 \| 0.7751 \| 0.7737 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_8192_512_30M", "model-index": [{"name": "GUE_EMP_H3K14ac-seqsight_8192_512_30M-L8_f", "results": []}]}	mahdibaghbanzadeh/GUE_EMP_H3K14ac-seqsight_8192_512_30M-L8_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_8192_512_30M", "region:us" ]	null	2024-04-27T02:44:04+00:00	[]	[]	TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us	GUE\_EMP\_H3K14ac-seqsight\_8192\_512\_30M-L8\_f ================================================ This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_8192\_512\_30M on the mahdibaghbanzadeh/GUE\_EMP\_H3K14ac dataset. It achieves the following results on the evaluation set: * Loss: 0.4967 * F1 Score: 0.7672 * Accuracy: 0.7661 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]	[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_EMP_H3K14ac-seqsight_8192_512_30M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_8192_512_30M](https://huggingface.co/mahdibaghbanzadeh/seqsight_8192_512_30M) on the [mahdibaghbanzadeh/GUE_EMP_H3K14ac](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H3K14ac) dataset. It achieves the following results on the evaluation set: - Loss: 0.4901 - F1 Score: 0.7690 - Accuracy: 0.7688 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.5746 \| 0.97 \| 200 \| 0.5157 \| 0.7559 \| 0.7543 \| \| 0.5174 \| 1.93 \| 400 \| 0.4942 \| 0.7703 \| 0.7688 \| \| 0.5017 \| 2.9 \| 600 \| 0.5152 \| 0.7542 \| 0.7531 \| \| 0.4951 \| 3.86 \| 800 \| 0.4836 \| 0.7753 \| 0.7746 \| \| 0.4875 \| 4.83 \| 1000 \| 0.5032 \| 0.7625 \| 0.7610 \| \| 0.4815 \| 5.8 \| 1200 \| 0.4971 \| 0.7676 \| 0.7661 \| \| 0.4737 \| 6.76 \| 1400 \| 0.4861 \| 0.7728 \| 0.7713 \| \| 0.4679 \| 7.73 \| 1600 \| 0.4964 \| 0.7659 \| 0.7643 \| \| 0.463 \| 8.7 \| 1800 \| 0.5063 \| 0.7630 \| 0.7616 \| \| 0.4547 \| 9.66 \| 2000 \| 0.4940 \| 0.7704 \| 0.7688 \| \| 0.4548 \| 10.63 \| 2200 \| 0.5152 \| 0.7631 \| 0.7616 \| \| 0.4445 \| 11.59 \| 2400 \| 0.4812 \| 0.7752 \| 0.7740 \| \| 0.4386 \| 12.56 \| 2600 \| 0.5055 \| 0.7727 \| 0.7713 \| \| 0.4306 \| 13.53 \| 2800 \| 0.5064 \| 0.7692 \| 0.7676 \| \| 0.431 \| 14.49 \| 3000 \| 0.4957 \| 0.7712 \| 0.7697 \| \| 0.415 \| 15.46 \| 3200 \| 0.5090 \| 0.7696 \| 0.7685 \| \| 0.4186 \| 16.43 \| 3400 \| 0.5115 \| 0.7704 \| 0.7688 \| \| 0.4127 \| 17.39 \| 3600 \| 0.5006 \| 0.7649 \| 0.7637 \| \| 0.4009 \| 18.36 \| 3800 \| 0.5020 \| 0.7676 \| 0.7673 \| \| 0.3987 \| 19.32 \| 4000 \| 0.5140 \| 0.7696 \| 0.7688 \| \| 0.3925 \| 20.29 \| 4200 \| 0.5288 \| 0.7559 \| 0.7555 \| \| 0.3916 \| 21.26 \| 4400 \| 0.5305 \| 0.7707 \| 0.7691 \| \| 0.3798 \| 22.22 \| 4600 \| 0.5455 \| 0.7649 \| 0.7634 \| \| 0.3791 \| 23.19 \| 4800 \| 0.5304 \| 0.7660 \| 0.7652 \| \| 0.3712 \| 24.15 \| 5000 \| 0.5595 \| 0.7589 \| 0.7573 \| \| 0.3705 \| 25.12 \| 5200 \| 0.5477 \| 0.7628 \| 0.7613 \| \| 0.3614 \| 26.09 \| 5400 \| 0.5390 \| 0.7601 \| 0.7589 \| \| 0.3579 \| 27.05 \| 5600 \| 0.5539 \| 0.7569 \| 0.7552 \| \| 0.3532 \| 28.02 \| 5800 \| 0.5317 \| 0.7632 \| 0.7622 \| \| 0.35 \| 28.99 \| 6000 \| 0.5360 \| 0.7572 \| 0.7564 \| \| 0.3415 \| 29.95 \| 6200 \| 0.5697 \| 0.7554 \| 0.7546 \| \| 0.3376 \| 30.92 \| 6400 \| 0.5587 \| 0.7627 \| 0.7634 \| \| 0.3348 \| 31.88 \| 6600 \| 0.5711 \| 0.7533 \| 0.7519 \| \| 0.3278 \| 32.85 \| 6800 \| 0.5775 \| 0.7595 \| 0.7582 \| \| 0.3289 \| 33.82 \| 7000 \| 0.5727 \| 0.7613 \| 0.7601 \| \| 0.3226 \| 34.78 \| 7200 \| 0.5911 \| 0.7624 \| 0.7610 \| \| 0.3255 \| 35.75 \| 7400 \| 0.5886 \| 0.7499 \| 0.7486 \| \| 0.3174 \| 36.71 \| 7600 \| 0.5878 \| 0.7625 \| 0.7616 \| \| 0.3152 \| 37.68 \| 7800 \| 0.6031 \| 0.7584 \| 0.7570 \| \| 0.3103 \| 38.65 \| 8000 \| 0.5939 \| 0.7590 \| 0.7579 \| \| 0.3155 \| 39.61 \| 8200 \| 0.5886 \| 0.7575 \| 0.7567 \| \| 0.3043 \| 40.58 \| 8400 \| 0.6121 \| 0.7554 \| 0.7540 \| \| 0.302 \| 41.55 \| 8600 \| 0.6296 \| 0.7578 \| 0.7564 \| \| 0.2983 \| 42.51 \| 8800 \| 0.6113 \| 0.7573 \| 0.7564 \| \| 0.3019 \| 43.48 \| 9000 \| 0.6239 \| 0.7536 \| 0.7522 \| \| 0.2971 \| 44.44 \| 9200 \| 0.6205 \| 0.7577 \| 0.7564 \| \| 0.2991 \| 45.41 \| 9400 \| 0.6207 \| 0.7572 \| 0.7558 \| \| 0.2918 \| 46.38 \| 9600 \| 0.6238 \| 0.7578 \| 0.7564 \| \| 0.2998 \| 47.34 \| 9800 \| 0.6179 \| 0.7564 \| 0.7552 \| \| 0.2939 \| 48.31 \| 10000 \| 0.6184 \| 0.7557 \| 0.7546 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_8192_512_30M", "model-index": [{"name": "GUE_EMP_H3K14ac-seqsight_8192_512_30M-L32_f", "results": []}]}	mahdibaghbanzadeh/GUE_EMP_H3K14ac-seqsight_8192_512_30M-L32_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_8192_512_30M", "region:us" ]	null	2024-04-27T02:45:47+00:00	[]	[]	TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us	GUE\_EMP\_H3K14ac-seqsight\_8192\_512\_30M-L32\_f ================================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_8192\_512\_30M on the mahdibaghbanzadeh/GUE\_EMP\_H3K14ac dataset. It achieves the following results on the evaluation set: * Loss: 0.4901 * F1 Score: 0.7690 * Accuracy: 0.7688 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]	[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_EMP_H3K4me2-seqsight_8192_512_30M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_8192_512_30M](https://huggingface.co/mahdibaghbanzadeh/seqsight_8192_512_30M) on the [mahdibaghbanzadeh/GUE_EMP_H3K4me2](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H3K4me2) dataset. It achieves the following results on the evaluation set: - Loss: 0.5958 - F1 Score: 0.6738 - Accuracy: 0.6755 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.6591 \| 1.04 \| 200 \| 0.6316 \| 0.5954 \| 0.6409 \| \| 0.6239 \| 2.08 \| 400 \| 0.6231 \| 0.6562 \| 0.6556 \| \| 0.6154 \| 3.12 \| 600 \| 0.6142 \| 0.6453 \| 0.6686 \| \| 0.6117 \| 4.17 \| 800 \| 0.6111 \| 0.6695 \| 0.6722 \| \| 0.6093 \| 5.21 \| 1000 \| 0.6122 \| 0.6686 \| 0.6689 \| \| 0.606 \| 6.25 \| 1200 \| 0.6043 \| 0.6673 \| 0.6722 \| \| 0.5999 \| 7.29 \| 1400 \| 0.6149 \| 0.6710 \| 0.6696 \| \| 0.6007 \| 8.33 \| 1600 \| 0.6111 \| 0.6744 \| 0.6745 \| \| 0.6002 \| 9.38 \| 1800 \| 0.6209 \| 0.6636 \| 0.6611 \| \| 0.5964 \| 10.42 \| 2000 \| 0.6083 \| 0.6740 \| 0.6729 \| \| 0.5991 \| 11.46 \| 2200 \| 0.5991 \| 0.6736 \| 0.6794 \| \| 0.5887 \| 12.5 \| 2400 \| 0.6031 \| 0.6823 \| 0.6836 \| \| 0.5911 \| 13.54 \| 2600 \| 0.6048 \| 0.6779 \| 0.6794 \| \| 0.5912 \| 14.58 \| 2800 \| 0.6017 \| 0.6779 \| 0.6820 \| \| 0.5953 \| 15.62 \| 3000 \| 0.6044 \| 0.6795 \| 0.6804 \| \| 0.5873 \| 16.67 \| 3200 \| 0.6081 \| 0.6732 \| 0.6719 \| \| 0.5886 \| 17.71 \| 3400 \| 0.6009 \| 0.6798 \| 0.6817 \| \| 0.5863 \| 18.75 \| 3600 \| 0.5991 \| 0.6805 \| 0.6852 \| \| 0.5888 \| 19.79 \| 3800 \| 0.6010 \| 0.6764 \| 0.6771 \| \| 0.5835 \| 20.83 \| 4000 \| 0.6038 \| 0.6748 \| 0.6742 \| \| 0.5859 \| 21.88 \| 4200 \| 0.6095 \| 0.6776 \| 0.6761 \| \| 0.5829 \| 22.92 \| 4400 \| 0.6040 \| 0.6800 \| 0.6797 \| \| 0.5837 \| 23.96 \| 4600 \| 0.6061 \| 0.6761 \| 0.6748 \| \| 0.5801 \| 25.0 \| 4800 \| 0.6026 \| 0.6804 \| 0.6807 \| \| 0.58 \| 26.04 \| 5000 \| 0.6049 \| 0.6808 \| 0.6804 \| \| 0.5785 \| 27.08 \| 5200 \| 0.6068 \| 0.6748 \| 0.6735 \| \| 0.5794 \| 28.12 \| 5400 \| 0.6059 \| 0.6777 \| 0.6768 \| \| 0.579 \| 29.17 \| 5600 \| 0.6051 \| 0.6790 \| 0.6781 \| \| 0.5768 \| 30.21 \| 5800 \| 0.6068 \| 0.6793 \| 0.6787 \| \| 0.5783 \| 31.25 \| 6000 \| 0.6033 \| 0.6803 \| 0.6800 \| \| 0.5766 \| 32.29 \| 6200 \| 0.5977 \| 0.6847 \| 0.6865 \| \| 0.5785 \| 33.33 \| 6400 \| 0.6007 \| 0.6833 \| 0.6843 \| \| 0.5764 \| 34.38 \| 6600 \| 0.5983 \| 0.6807 \| 0.6823 \| \| 0.5744 \| 35.42 \| 6800 \| 0.6027 \| 0.6804 \| 0.6804 \| \| 0.5746 \| 36.46 \| 7000 \| 0.5975 \| 0.6859 \| 0.6882 \| \| 0.5712 \| 37.5 \| 7200 \| 0.6051 \| 0.6773 \| 0.6764 \| \| 0.5725 \| 38.54 \| 7400 \| 0.6034 \| 0.6820 \| 0.6820 \| \| 0.5767 \| 39.58 \| 7600 \| 0.5990 \| 0.6821 \| 0.6833 \| \| 0.5764 \| 40.62 \| 7800 \| 0.6066 \| 0.6774 \| 0.6758 \| \| 0.5715 \| 41.67 \| 8000 \| 0.6026 \| 0.6822 \| 0.6817 \| \| 0.5677 \| 42.71 \| 8200 \| 0.5987 \| 0.6823 \| 0.6839 \| \| 0.5722 \| 43.75 \| 8400 \| 0.6011 \| 0.6791 \| 0.6790 \| \| 0.5724 \| 44.79 \| 8600 \| 0.6043 \| 0.6802 \| 0.6794 \| \| 0.5693 \| 45.83 \| 8800 \| 0.6004 \| 0.6787 \| 0.6790 \| \| 0.5691 \| 46.88 \| 9000 \| 0.6061 \| 0.6801 \| 0.6790 \| \| 0.5712 \| 47.92 \| 9200 \| 0.6039 \| 0.6823 \| 0.6817 \| \| 0.57 \| 48.96 \| 9400 \| 0.6020 \| 0.6817 \| 0.6817 \| \| 0.5704 \| 50.0 \| 9600 \| 0.6028 \| 0.6806 \| 0.6804 \| \| 0.5707 \| 51.04 \| 9800 \| 0.6033 \| 0.6824 \| 0.6820 \| \| 0.5682 \| 52.08 \| 10000 \| 0.6036 \| 0.6815 \| 0.6810 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_8192_512_30M", "model-index": [{"name": "GUE_EMP_H3K4me2-seqsight_8192_512_30M-L1_f", "results": []}]}	mahdibaghbanzadeh/GUE_EMP_H3K4me2-seqsight_8192_512_30M-L1_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_8192_512_30M", "region:us" ]	null	2024-04-27T02:46:12+00:00	[]	[]	TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us	GUE\_EMP\_H3K4me2-seqsight\_8192\_512\_30M-L1\_f ================================================ This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_8192\_512\_30M on the mahdibaghbanzadeh/GUE\_EMP\_H3K4me2 dataset. It achieves the following results on the evaluation set: * Loss: 0.5958 * F1 Score: 0.6738 * Accuracy: 0.6755 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]	[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]
text2text-generation	transformers	### Using .generate() ```python from transformers import GenerationConfig, T5ForConditionalGeneration, T5Tokenizer model_name = "cu-kairos/propbank_srl_seq2seq_t5_small" model = T5ForConditionalGeneration.from_pretrained(model_name) tokenizer = T5Tokenizer.from_pretrained(model_name) generation_config = GenerationConfig.from_pretrained(model_name) tokenized_inputs = tokenizer(["SRL for [put]: That fund was [put] together by Blackstone Group ."], return_tensors="pt") outputs = model.generate(**tokenized_inputs, generation_config=generation_config) print(tokenizer.batch_decode(outputs, skip_special_tokens=True)) # ['ARG-1: That fund \| ARG-2: together \| ARG-0: by Blackstone Group '] ``` ### Using pipeline ```python from transformers import pipeline srl = pipeline("cu-kairos/propbank_srl_seq2seq_t5_small") print(srl(["SRL for [put]: That fund was [put] together by Blackstone Group ."])) # [{'generated_text': 'ARG-1: That fund \| ARG-2: together \| ARG-0: by Blackstone Group '}] ```	{"license": "apache-2.0"}	cu-kairos/propbank_srl_seq2seq_t5_small	null	[ "transformers", "safetensors", "t5", "text2text-generation", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-27T02:46:48+00:00	[]	[]	TAGS #transformers #safetensors #t5 #text2text-generation #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us	### Using .generate() ### Using pipeline	[ "### Using .generate()", "### Using pipeline" ]	[ "TAGS\n#transformers #safetensors #t5 #text2text-generation #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "### Using .generate()", "### Using pipeline" ]

text-generation

transformers

# Model Card for Model ID  ## Model Details ### Model Description  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

devesh220897/financial-chatbot-for-young-adults-4

null

[ "transformers", "safetensors", "gemma", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

null

2024-04-27T00:28:21+00:00

[ "1910.09700" ]

[]

TAGS #transformers #safetensors #gemma #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #gemma #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

null

peft

# GUE_splice_reconstructed-seqsight_4096_512_46M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_splice_reconstructed](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_splice_reconstructed) dataset. It achieves the following results on the evaluation set: - Loss: 0.3479 - F1 Score: 0.8611 - Accuracy: 0.8604 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.9345 | 0.7 | 200 | 0.8741 | 0.5165 | 0.5761 | | 0.7904 | 1.4 | 400 | 0.5650 | 0.7493 | 0.7519 | | 0.5261 | 2.1 | 600 | 0.4778 | 0.7942 | 0.7937 | | 0.478 | 2.8 | 800 | 0.4621 | 0.8103 | 0.8097 | | 0.4593 | 3.5 | 1000 | 0.4522 | 0.8124 | 0.8115 | | 0.4463 | 4.2 | 1200 | 0.4375 | 0.8194 | 0.8181 | | 0.4347 | 4.9 | 1400 | 0.4279 | 0.8234 | 0.8224 | | 0.4273 | 5.59 | 1600 | 0.4331 | 0.8230 | 0.8227 | | 0.4151 | 6.29 | 1800 | 0.4419 | 0.8198 | 0.8185 | | 0.4036 | 6.99 | 2000 | 0.4257 | 0.8270 | 0.8255 | | 0.3988 | 7.69 | 2200 | 0.3926 | 0.8380 | 0.8371 | | 0.3947 | 8.39 | 2400 | 0.4171 | 0.8293 | 0.8281 | | 0.3959 | 9.09 | 2600 | 0.4144 | 0.8316 | 0.8301 | | 0.3848 | 9.79 | 2800 | 0.3916 | 0.8441 | 0.8431 | | 0.3842 | 10.49 | 3000 | 0.3868 | 0.8481 | 0.8472 | | 0.3726 | 11.19 | 3200 | 0.4221 | 0.8294 | 0.8284 | | 0.375 | 11.89 | 3400 | 0.3941 | 0.8421 | 0.8409 | | 0.3636 | 12.59 | 3600 | 0.3826 | 0.8468 | 0.8461 | | 0.3693 | 13.29 | 3800 | 0.3817 | 0.8479 | 0.8470 | | 0.3604 | 13.99 | 4000 | 0.3992 | 0.8427 | 0.8415 | | 0.3566 | 14.69 | 4200 | 0.3819 | 0.8512 | 0.8503 | | 0.3539 | 15.38 | 4400 | 0.3803 | 0.8516 | 0.8507 | | 0.3463 | 16.08 | 4600 | 0.4195 | 0.8349 | 0.8338 | | 0.3498 | 16.78 | 4800 | 0.3813 | 0.8503 | 0.8494 | | 0.345 | 17.48 | 5000 | 0.3904 | 0.8484 | 0.8472 | | 0.3447 | 18.18 | 5200 | 0.3690 | 0.8580 | 0.8573 | | 0.3424 | 18.88 | 5400 | 0.3667 | 0.8582 | 0.8575 | | 0.3325 | 19.58 | 5600 | 0.3646 | 0.8591 | 0.8584 | | 0.3418 | 20.28 | 5800 | 0.3595 | 0.8615 | 0.8608 | | 0.336 | 20.98 | 6000 | 0.3636 | 0.8581 | 0.8573 | | 0.3391 | 21.68 | 6200 | 0.3748 | 0.8532 | 0.8525 | | 0.3304 | 22.38 | 6400 | 0.3715 | 0.8561 | 0.8553 | | 0.3272 | 23.08 | 6600 | 0.3687 | 0.8565 | 0.8555 | | 0.3302 | 23.78 | 6800 | 0.3691 | 0.8571 | 0.8562 | | 0.3278 | 24.48 | 7000 | 0.3756 | 0.8573 | 0.8564 | | 0.3219 | 25.17 | 7200 | 0.3740 | 0.8538 | 0.8529 | | 0.3232 | 25.87 | 7400 | 0.3772 | 0.8535 | 0.8525 | | 0.322 | 26.57 | 7600 | 0.3782 | 0.8552 | 0.8542 | | 0.3195 | 27.27 | 7800 | 0.3701 | 0.8566 | 0.8558 | | 0.3248 | 27.97 | 8000 | 0.3707 | 0.8558 | 0.8549 | | 0.3255 | 28.67 | 8200 | 0.3815 | 0.8519 | 0.8509 | | 0.318 | 29.37 | 8400 | 0.3691 | 0.8553 | 0.8544 | | 0.3154 | 30.07 | 8600 | 0.3580 | 0.8620 | 0.8612 | | 0.3157 | 30.77 | 8800 | 0.3694 | 0.8551 | 0.8542 | | 0.3171 | 31.47 | 9000 | 0.3643 | 0.8562 | 0.8553 | | 0.3198 | 32.17 | 9200 | 0.3615 | 0.8588 | 0.8580 | | 0.3182 | 32.87 | 9400 | 0.3648 | 0.8578 | 0.8571 | | 0.316 | 33.57 | 9600 | 0.3717 | 0.8543 | 0.8534 | | 0.3129 | 34.27 | 9800 | 0.3659 | 0.8577 | 0.8569 | | 0.3166 | 34.97 | 10000 | 0.3673 | 0.8564 | 0.8555 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_splice_reconstructed-seqsight_4096_512_46M-L1_f", "results": []}]}

mahdibaghbanzadeh/GUE_splice_reconstructed-seqsight_4096_512_46M-L1_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_46M", "region:us" ]

null

2024-04-27T00:28:25+00:00

[]

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us

GUE\_splice\_reconstructed-seqsight\_4096\_512\_46M-L1\_f ========================================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_4096\_512\_46M on the mahdibaghbanzadeh/GUE\_splice\_reconstructed dataset. It achieves the following results on the evaluation set: * Loss: 0.3479 * F1 Score: 0.8611 * Accuracy: 0.8604 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

text-generation

transformers

# Model Card for Model ID  ## Model Details ### Model Description  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

rPucs/gemma-7b-itTripletDolly-WebNLG

null

[ "transformers", "safetensors", "gemma", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

null

2024-04-27T00:30:38+00:00

[ "1910.09700" ]

[]

TAGS #transformers #safetensors #gemma #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #gemma #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

null

transformers

# Model Card for Model ID  ## Model Details ### Model Description  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

jsingh/autoflow-math-v0.3

null

[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]

null

2024-04-27T00:32:14+00:00

[ "1910.09700" ]

[]

TAGS #transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us

# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

null

peft

# GUE_splice_reconstructed-seqsight_4096_512_46M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_splice_reconstructed](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_splice_reconstructed) dataset. It achieves the following results on the evaluation set: - Loss: 0.3085 - F1 Score: 0.8848 - Accuracy: 0.8843 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.9058 | 0.7 | 200 | 0.7893 | 0.6650 | 0.6637 | | 0.5287 | 1.4 | 400 | 0.4440 | 0.8207 | 0.8196 | | 0.4396 | 2.1 | 600 | 0.4073 | 0.8350 | 0.8338 | | 0.4028 | 2.8 | 800 | 0.4125 | 0.8360 | 0.8352 | | 0.387 | 3.5 | 1000 | 0.3674 | 0.8587 | 0.8582 | | 0.3728 | 4.2 | 1200 | 0.3927 | 0.8439 | 0.8426 | | 0.3595 | 4.9 | 1400 | 0.3759 | 0.8529 | 0.8520 | | 0.3518 | 5.59 | 1600 | 0.3751 | 0.8604 | 0.8604 | | 0.3369 | 6.29 | 1800 | 0.3757 | 0.8575 | 0.8564 | | 0.3277 | 6.99 | 2000 | 0.3672 | 0.8590 | 0.8580 | | 0.3213 | 7.69 | 2200 | 0.3529 | 0.8647 | 0.8639 | | 0.318 | 8.39 | 2400 | 0.3513 | 0.8681 | 0.8674 | | 0.3154 | 9.09 | 2600 | 0.3567 | 0.8653 | 0.8643 | | 0.3012 | 9.79 | 2800 | 0.3442 | 0.8697 | 0.8689 | | 0.3008 | 10.49 | 3000 | 0.3317 | 0.8769 | 0.8764 | | 0.2955 | 11.19 | 3200 | 0.3715 | 0.8606 | 0.8597 | | 0.2961 | 11.89 | 3400 | 0.3457 | 0.8651 | 0.8641 | | 0.2847 | 12.59 | 3600 | 0.3518 | 0.8628 | 0.8621 | | 0.289 | 13.29 | 3800 | 0.3271 | 0.8747 | 0.8742 | | 0.2789 | 13.99 | 4000 | 0.3435 | 0.8743 | 0.8735 | | 0.2741 | 14.69 | 4200 | 0.3318 | 0.8768 | 0.8762 | | 0.2738 | 15.38 | 4400 | 0.3299 | 0.8770 | 0.8764 | | 0.2676 | 16.08 | 4600 | 0.3491 | 0.8695 | 0.8687 | | 0.2718 | 16.78 | 4800 | 0.3407 | 0.8741 | 0.8733 | | 0.2597 | 17.48 | 5000 | 0.3563 | 0.8644 | 0.8637 | | 0.264 | 18.18 | 5200 | 0.3287 | 0.8805 | 0.8799 | | 0.2607 | 18.88 | 5400 | 0.3233 | 0.8793 | 0.8788 | | 0.2502 | 19.58 | 5600 | 0.3305 | 0.8790 | 0.8783 | | 0.2586 | 20.28 | 5800 | 0.3144 | 0.8865 | 0.8860 | | 0.2536 | 20.98 | 6000 | 0.3183 | 0.8865 | 0.8860 | | 0.254 | 21.68 | 6200 | 0.3390 | 0.8742 | 0.8735 | | 0.249 | 22.38 | 6400 | 0.3305 | 0.8790 | 0.8783 | | 0.2439 | 23.08 | 6600 | 0.3274 | 0.8805 | 0.8799 | | 0.2437 | 23.78 | 6800 | 0.3310 | 0.8823 | 0.8816 | | 0.2391 | 24.48 | 7000 | 0.3360 | 0.8790 | 0.8783 | | 0.2398 | 25.17 | 7200 | 0.3339 | 0.8789 | 0.8783 | | 0.2389 | 25.87 | 7400 | 0.3430 | 0.8775 | 0.8768 | | 0.2386 | 26.57 | 7600 | 0.3329 | 0.8805 | 0.8799 | | 0.2317 | 27.27 | 7800 | 0.3397 | 0.8786 | 0.8779 | | 0.237 | 27.97 | 8000 | 0.3363 | 0.8821 | 0.8814 | | 0.2378 | 28.67 | 8200 | 0.3350 | 0.8825 | 0.8819 | | 0.2293 | 29.37 | 8400 | 0.3259 | 0.8855 | 0.8849 | | 0.2276 | 30.07 | 8600 | 0.3260 | 0.8853 | 0.8847 | | 0.2258 | 30.77 | 8800 | 0.3317 | 0.8840 | 0.8834 | | 0.2307 | 31.47 | 9000 | 0.3354 | 0.8834 | 0.8827 | | 0.2279 | 32.17 | 9200 | 0.3311 | 0.8842 | 0.8836 | | 0.2301 | 32.87 | 9400 | 0.3304 | 0.8820 | 0.8814 | | 0.2277 | 33.57 | 9600 | 0.3398 | 0.8812 | 0.8805 | | 0.2225 | 34.27 | 9800 | 0.3342 | 0.8829 | 0.8823 | | 0.2288 | 34.97 | 10000 | 0.3341 | 0.8827 | 0.8821 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_splice_reconstructed-seqsight_4096_512_46M-L8_f", "results": []}]}

mahdibaghbanzadeh/GUE_splice_reconstructed-seqsight_4096_512_46M-L8_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_46M", "region:us" ]

null

2024-04-27T00:33:37+00:00

[]

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us

GUE\_splice\_reconstructed-seqsight\_4096\_512\_46M-L8\_f ========================================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_4096\_512\_46M on the mahdibaghbanzadeh/GUE\_splice\_reconstructed dataset. It achieves the following results on the evaluation set: * Loss: 0.3085 * F1 Score: 0.8848 * Accuracy: 0.8843 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

null

peft

# GUE_splice_reconstructed-seqsight_4096_512_46M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_splice_reconstructed](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_splice_reconstructed) dataset. It achieves the following results on the evaluation set: - Loss: 0.2844 - F1 Score: 0.9056 - Accuracy: 0.9053 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.8179 | 0.7 | 200 | 0.5204 | 0.7837 | 0.7830 | | 0.4352 | 1.4 | 400 | 0.3973 | 0.8452 | 0.8446 | | 0.3886 | 2.1 | 600 | 0.3784 | 0.8550 | 0.8540 | | 0.3519 | 2.8 | 800 | 0.3853 | 0.8541 | 0.8534 | | 0.3325 | 3.5 | 1000 | 0.3315 | 0.8748 | 0.8744 | | 0.318 | 4.2 | 1200 | 0.3462 | 0.8679 | 0.8669 | | 0.3053 | 4.9 | 1400 | 0.3358 | 0.8734 | 0.8726 | | 0.2965 | 5.59 | 1600 | 0.3560 | 0.8635 | 0.8634 | | 0.2831 | 6.29 | 1800 | 0.3516 | 0.8673 | 0.8665 | | 0.2708 | 6.99 | 2000 | 0.3149 | 0.8816 | 0.8812 | | 0.2641 | 7.69 | 2200 | 0.3367 | 0.8767 | 0.8759 | | 0.2582 | 8.39 | 2400 | 0.3258 | 0.8779 | 0.8775 | | 0.2553 | 9.09 | 2600 | 0.3211 | 0.8842 | 0.8834 | | 0.2426 | 9.79 | 2800 | 0.3137 | 0.8889 | 0.8882 | | 0.2364 | 10.49 | 3000 | 0.2944 | 0.8936 | 0.8932 | | 0.2299 | 11.19 | 3200 | 0.3200 | 0.8847 | 0.8840 | | 0.2285 | 11.89 | 3400 | 0.3317 | 0.8815 | 0.8808 | | 0.2136 | 12.59 | 3600 | 0.3326 | 0.8763 | 0.8757 | | 0.2152 | 13.29 | 3800 | 0.3053 | 0.8900 | 0.8895 | | 0.2078 | 13.99 | 4000 | 0.3316 | 0.8802 | 0.8794 | | 0.2028 | 14.69 | 4200 | 0.3239 | 0.8866 | 0.8858 | | 0.2028 | 15.38 | 4400 | 0.3240 | 0.8852 | 0.8847 | | 0.1888 | 16.08 | 4600 | 0.3376 | 0.8841 | 0.8834 | | 0.1919 | 16.78 | 4800 | 0.3129 | 0.8903 | 0.8897 | | 0.1792 | 17.48 | 5000 | 0.3338 | 0.8873 | 0.8867 | | 0.1846 | 18.18 | 5200 | 0.3108 | 0.8934 | 0.8930 | | 0.1782 | 18.88 | 5400 | 0.3161 | 0.8889 | 0.8884 | | 0.1699 | 19.58 | 5600 | 0.3339 | 0.8909 | 0.8904 | | 0.1747 | 20.28 | 5800 | 0.3043 | 0.8986 | 0.8983 | | 0.1631 | 20.98 | 6000 | 0.3052 | 0.9013 | 0.9009 | | 0.1636 | 21.68 | 6200 | 0.3347 | 0.8882 | 0.8878 | | 0.1586 | 22.38 | 6400 | 0.3218 | 0.8937 | 0.8932 | | 0.157 | 23.08 | 6600 | 0.3203 | 0.8931 | 0.8926 | | 0.1546 | 23.78 | 6800 | 0.3180 | 0.8977 | 0.8974 | | 0.1484 | 24.48 | 7000 | 0.3491 | 0.8866 | 0.8860 | | 0.1485 | 25.17 | 7200 | 0.3209 | 0.8927 | 0.8924 | | 0.1447 | 25.87 | 7400 | 0.3323 | 0.8974 | 0.8970 | | 0.1428 | 26.57 | 7600 | 0.3301 | 0.8965 | 0.8961 | | 0.1394 | 27.27 | 7800 | 0.3386 | 0.8909 | 0.8904 | | 0.1414 | 27.97 | 8000 | 0.3319 | 0.8981 | 0.8976 | | 0.1398 | 28.67 | 8200 | 0.3338 | 0.8970 | 0.8965 | | 0.1346 | 29.37 | 8400 | 0.3304 | 0.8972 | 0.8968 | | 0.1327 | 30.07 | 8600 | 0.3334 | 0.8965 | 0.8961 | | 0.1325 | 30.77 | 8800 | 0.3449 | 0.8931 | 0.8926 | | 0.1338 | 31.47 | 9000 | 0.3320 | 0.8946 | 0.8941 | | 0.1282 | 32.17 | 9200 | 0.3409 | 0.8963 | 0.8959 | | 0.1276 | 32.87 | 9400 | 0.3403 | 0.8963 | 0.8959 | | 0.1266 | 33.57 | 9600 | 0.3470 | 0.8940 | 0.8935 | | 0.1238 | 34.27 | 9800 | 0.3421 | 0.8954 | 0.8950 | | 0.1257 | 34.97 | 10000 | 0.3406 | 0.8959 | 0.8954 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_splice_reconstructed-seqsight_4096_512_46M-L32_f", "results": []}]}

mahdibaghbanzadeh/GUE_splice_reconstructed-seqsight_4096_512_46M-L32_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_46M", "region:us" ]

null

2024-04-27T00:33:38+00:00

[]

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us

GUE\_splice\_reconstructed-seqsight\_4096\_512\_46M-L32\_f ========================================================== This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_4096\_512\_46M on the mahdibaghbanzadeh/GUE\_splice\_reconstructed dataset. It achieves the following results on the evaluation set: * Loss: 0.2844 * F1 Score: 0.9056 * Accuracy: 0.9053 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

null

peft

# GUE_tf_0-seqsight_4096_512_46M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_tf_0](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_0) dataset. It achieves the following results on the evaluation set: - Loss: 0.3687 - F1 Score: 0.8338 - Accuracy: 0.834 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.5178 | 0.79 | 200 | 0.4899 | 0.7461 | 0.746 | | 0.4791 | 1.58 | 400 | 0.4700 | 0.7734 | 0.774 | | 0.4718 | 2.37 | 600 | 0.4727 | 0.7702 | 0.771 | | 0.4615 | 3.16 | 800 | 0.4697 | 0.766 | 0.766 | | 0.4548 | 3.95 | 1000 | 0.4594 | 0.7833 | 0.784 | | 0.4524 | 4.74 | 1200 | 0.4634 | 0.7769 | 0.777 | | 0.453 | 5.53 | 1400 | 0.4565 | 0.7840 | 0.784 | | 0.442 | 6.32 | 1600 | 0.4560 | 0.7830 | 0.783 | | 0.447 | 7.11 | 1800 | 0.4591 | 0.7861 | 0.786 | | 0.4436 | 7.91 | 2000 | 0.4556 | 0.7901 | 0.79 | | 0.4384 | 8.7 | 2200 | 0.4544 | 0.7820 | 0.782 | | 0.4351 | 9.49 | 2400 | 0.4534 | 0.7776 | 0.778 | | 0.4356 | 10.28 | 2600 | 0.4704 | 0.7827 | 0.783 | | 0.4329 | 11.07 | 2800 | 0.4588 | 0.7940 | 0.794 | | 0.4323 | 11.86 | 3000 | 0.4618 | 0.7840 | 0.784 | | 0.4306 | 12.65 | 3200 | 0.4583 | 0.7931 | 0.793 | | 0.4259 | 13.44 | 3400 | 0.4587 | 0.7890 | 0.789 | | 0.4277 | 14.23 | 3600 | 0.4532 | 0.7880 | 0.788 | | 0.4276 | 15.02 | 3800 | 0.4550 | 0.7891 | 0.789 | | 0.4277 | 15.81 | 4000 | 0.4567 | 0.7920 | 0.792 | | 0.4216 | 16.6 | 4200 | 0.4542 | 0.7881 | 0.788 | | 0.4247 | 17.39 | 4400 | 0.4598 | 0.7850 | 0.785 | | 0.4213 | 18.18 | 4600 | 0.4613 | 0.7820 | 0.782 | | 0.4207 | 18.97 | 4800 | 0.4634 | 0.7819 | 0.782 | | 0.4256 | 19.76 | 5000 | 0.4523 | 0.7821 | 0.782 | | 0.4206 | 20.55 | 5200 | 0.4507 | 0.7878 | 0.788 | | 0.4201 | 21.34 | 5400 | 0.4563 | 0.7811 | 0.781 | | 0.4175 | 22.13 | 5600 | 0.4561 | 0.7851 | 0.785 | | 0.42 | 22.92 | 5800 | 0.4546 | 0.7821 | 0.782 | | 0.4129 | 23.72 | 6000 | 0.4567 | 0.7861 | 0.786 | | 0.4176 | 24.51 | 6200 | 0.4500 | 0.7890 | 0.789 | | 0.4193 | 25.3 | 6400 | 0.4516 | 0.7931 | 0.793 | | 0.4131 | 26.09 | 6600 | 0.4523 | 0.7820 | 0.782 | | 0.4134 | 26.88 | 6800 | 0.4575 | 0.7790 | 0.779 | | 0.4129 | 27.67 | 7000 | 0.4518 | 0.7889 | 0.789 | | 0.4116 | 28.46 | 7200 | 0.4501 | 0.7849 | 0.785 | | 0.4146 | 29.25 | 7400 | 0.4514 | 0.7930 | 0.793 | | 0.4124 | 30.04 | 7600 | 0.4532 | 0.7860 | 0.786 | | 0.4111 | 30.83 | 7800 | 0.4543 | 0.7831 | 0.783 | | 0.4116 | 31.62 | 8000 | 0.4488 | 0.7859 | 0.786 | | 0.4105 | 32.41 | 8200 | 0.4534 | 0.7830 | 0.783 | | 0.4065 | 33.2 | 8400 | 0.4553 | 0.7860 | 0.786 | | 0.4106 | 33.99 | 8600 | 0.4539 | 0.7880 | 0.788 | | 0.4131 | 34.78 | 8800 | 0.4506 | 0.7869 | 0.787 | | 0.4044 | 35.57 | 9000 | 0.4538 | 0.7870 | 0.787 | | 0.4084 | 36.36 | 9200 | 0.4561 | 0.7841 | 0.784 | | 0.4113 | 37.15 | 9400 | 0.4573 | 0.7810 | 0.781 | | 0.4055 | 37.94 | 9600 | 0.4545 | 0.7870 | 0.787 | | 0.4065 | 38.74 | 9800 | 0.4552 | 0.7870 | 0.787 | | 0.4087 | 39.53 | 10000 | 0.4548 | 0.7870 | 0.787 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_tf_0-seqsight_4096_512_46M-L1_f", "results": []}]}

mahdibaghbanzadeh/GUE_tf_0-seqsight_4096_512_46M-L1_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_46M", "region:us" ]

null

2024-04-27T00:34:25+00:00

[]

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us

GUE\_tf\_0-seqsight\_4096\_512\_46M-L1\_f ========================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_4096\_512\_46M on the mahdibaghbanzadeh/GUE\_tf\_0 dataset. It achieves the following results on the evaluation set: * Loss: 0.3687 * F1 Score: 0.8338 * Accuracy: 0.834 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

null

peft

# GUE_tf_0-seqsight_4096_512_46M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_tf_0](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_0) dataset. It achieves the following results on the evaluation set: - Loss: 0.3756 - F1 Score: 0.8367 - Accuracy: 0.837 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.5044 | 0.79 | 200 | 0.4765 | 0.7625 | 0.763 | | 0.4678 | 1.58 | 400 | 0.4608 | 0.7760 | 0.777 | | 0.4623 | 2.37 | 600 | 0.4678 | 0.7758 | 0.777 | | 0.453 | 3.16 | 800 | 0.4604 | 0.7780 | 0.778 | | 0.4461 | 3.95 | 1000 | 0.4543 | 0.7860 | 0.787 | | 0.443 | 4.74 | 1200 | 0.4557 | 0.7826 | 0.783 | | 0.4427 | 5.53 | 1400 | 0.4569 | 0.7880 | 0.788 | | 0.4339 | 6.32 | 1600 | 0.4522 | 0.7961 | 0.796 | | 0.4377 | 7.11 | 1800 | 0.4591 | 0.7889 | 0.789 | | 0.4332 | 7.91 | 2000 | 0.4540 | 0.7950 | 0.795 | | 0.4281 | 8.7 | 2200 | 0.4491 | 0.7889 | 0.789 | | 0.4232 | 9.49 | 2400 | 0.4480 | 0.7898 | 0.79 | | 0.4246 | 10.28 | 2600 | 0.4617 | 0.7928 | 0.793 | | 0.4213 | 11.07 | 2800 | 0.4589 | 0.7959 | 0.796 | | 0.4184 | 11.86 | 3000 | 0.4577 | 0.802 | 0.802 | | 0.4163 | 12.65 | 3200 | 0.4438 | 0.7989 | 0.799 | | 0.4113 | 13.44 | 3400 | 0.4578 | 0.7910 | 0.791 | | 0.4123 | 14.23 | 3600 | 0.4488 | 0.7970 | 0.797 | | 0.413 | 15.02 | 3800 | 0.4524 | 0.8030 | 0.803 | | 0.4097 | 15.81 | 4000 | 0.4458 | 0.8031 | 0.803 | | 0.4061 | 16.6 | 4200 | 0.4506 | 0.7931 | 0.793 | | 0.4057 | 17.39 | 4400 | 0.4582 | 0.8010 | 0.801 | | 0.4026 | 18.18 | 4600 | 0.4506 | 0.7940 | 0.794 | | 0.4017 | 18.97 | 4800 | 0.4537 | 0.8030 | 0.803 | | 0.4047 | 19.76 | 5000 | 0.4480 | 0.7930 | 0.793 | | 0.4006 | 20.55 | 5200 | 0.4479 | 0.7959 | 0.796 | | 0.3985 | 21.34 | 5400 | 0.4518 | 0.7920 | 0.792 | | 0.3954 | 22.13 | 5600 | 0.4491 | 0.8031 | 0.803 | | 0.3984 | 22.92 | 5800 | 0.4509 | 0.7981 | 0.798 | | 0.3916 | 23.72 | 6000 | 0.4593 | 0.7910 | 0.791 | | 0.3957 | 24.51 | 6200 | 0.4412 | 0.8000 | 0.8 | | 0.3965 | 25.3 | 6400 | 0.4484 | 0.7930 | 0.793 | | 0.3879 | 26.09 | 6600 | 0.4487 | 0.7859 | 0.786 | | 0.3899 | 26.88 | 6800 | 0.4514 | 0.7890 | 0.789 | | 0.3879 | 27.67 | 7000 | 0.4503 | 0.7930 | 0.793 | | 0.3868 | 28.46 | 7200 | 0.4499 | 0.786 | 0.786 | | 0.3886 | 29.25 | 7400 | 0.4479 | 0.7950 | 0.795 | | 0.3864 | 30.04 | 7600 | 0.4540 | 0.7950 | 0.795 | | 0.3848 | 30.83 | 7800 | 0.4525 | 0.7861 | 0.786 | | 0.3853 | 31.62 | 8000 | 0.4460 | 0.7929 | 0.793 | | 0.3846 | 32.41 | 8200 | 0.4461 | 0.7930 | 0.793 | | 0.3812 | 33.2 | 8400 | 0.4534 | 0.7891 | 0.789 | | 0.3829 | 33.99 | 8600 | 0.4512 | 0.7940 | 0.794 | | 0.3851 | 34.78 | 8800 | 0.4467 | 0.7920 | 0.792 | | 0.3764 | 35.57 | 9000 | 0.4498 | 0.7920 | 0.792 | | 0.3816 | 36.36 | 9200 | 0.4533 | 0.7931 | 0.793 | | 0.3819 | 37.15 | 9400 | 0.4538 | 0.7930 | 0.793 | | 0.378 | 37.94 | 9600 | 0.4510 | 0.7891 | 0.789 | | 0.3787 | 38.74 | 9800 | 0.4517 | 0.7901 | 0.79 | | 0.3822 | 39.53 | 10000 | 0.4516 | 0.7891 | 0.789 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_tf_0-seqsight_4096_512_46M-L8_f", "results": []}]}

mahdibaghbanzadeh/GUE_tf_0-seqsight_4096_512_46M-L8_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_46M", "region:us" ]

null

2024-04-27T00:34:33+00:00

[]

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us

GUE\_tf\_0-seqsight\_4096\_512\_46M-L8\_f ========================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_4096\_512\_46M on the mahdibaghbanzadeh/GUE\_tf\_0 dataset. It achieves the following results on the evaluation set: * Loss: 0.3756 * F1 Score: 0.8367 * Accuracy: 0.837 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

null

peft

# llava-1.5-7b-hf-ft-mix-vsft This model is a fine-tuned version of [llava-hf/llava-1.5-7b-hf](https://huggingface.co/llava-hf/llava-1.5-7b-hf) on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1.4e-05 - train_batch_size: 2 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 1 - mixed_precision_training: Native AMP ### Training results ### Framework versions - PEFT 0.10.0 - Transformers 4.40.1 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.19.1

{"library_name": "peft", "tags": ["trl", "sft", "generated_from_trainer"], "base_model": "llava-hf/llava-1.5-7b-hf", "model-index": [{"name": "llava-1.5-7b-hf-ft-mix-vsft", "results": []}]}

Salmoli/llava-1.5-7b-hf-ft-mix-vsft

null

[ "peft", "tensorboard", "safetensors", "trl", "sft", "generated_from_trainer", "base_model:llava-hf/llava-1.5-7b-hf", "region:us" ]

null

2024-04-27T00:38:53+00:00

[]

TAGS #peft #tensorboard #safetensors #trl #sft #generated_from_trainer #base_model-llava-hf/llava-1.5-7b-hf #region-us

# llava-1.5-7b-hf-ft-mix-vsft This model is a fine-tuned version of llava-hf/llava-1.5-7b-hf on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1.4e-05 - train_batch_size: 2 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 1 - mixed_precision_training: Native AMP ### Training results ### Framework versions - PEFT 0.10.0 - Transformers 4.40.1 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.19.1

[ "# llava-1.5-7b-hf-ft-mix-vsft\n\nThis model is a fine-tuned version of llava-hf/llava-1.5-7b-hf on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1.4e-05\n- train_batch_size: 2\n- eval_batch_size: 8\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 1\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- PEFT 0.10.0\n- Transformers 4.40.1\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.19.1" ]

[ "TAGS\n#peft #tensorboard #safetensors #trl #sft #generated_from_trainer #base_model-llava-hf/llava-1.5-7b-hf #region-us \n", "# llava-1.5-7b-hf-ft-mix-vsft\n\nThis model is a fine-tuned version of llava-hf/llava-1.5-7b-hf on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1.4e-05\n- train_batch_size: 2\n- eval_batch_size: 8\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 1\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- PEFT 0.10.0\n- Transformers 4.40.1\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.19.1" ]

null

peft

# GUE_tf_0-seqsight_4096_512_46M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_tf_0](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_0) dataset. It achieves the following results on the evaluation set: - Loss: 0.3707 - F1 Score: 0.8345 - Accuracy: 0.835 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.4935 | 0.79 | 200 | 0.4703 | 0.7629 | 0.763 | | 0.4608 | 1.58 | 400 | 0.4577 | 0.7818 | 0.782 | | 0.4543 | 2.37 | 600 | 0.4608 | 0.7760 | 0.777 | | 0.4441 | 3.16 | 800 | 0.4574 | 0.784 | 0.784 | | 0.4378 | 3.95 | 1000 | 0.4475 | 0.7842 | 0.785 | | 0.4322 | 4.74 | 1200 | 0.4566 | 0.7828 | 0.783 | | 0.4326 | 5.53 | 1400 | 0.4554 | 0.7880 | 0.788 | | 0.423 | 6.32 | 1600 | 0.4503 | 0.7901 | 0.79 | | 0.4232 | 7.11 | 1800 | 0.4613 | 0.7920 | 0.792 | | 0.4183 | 7.91 | 2000 | 0.4526 | 0.7910 | 0.791 | | 0.4111 | 8.7 | 2200 | 0.4646 | 0.7780 | 0.778 | | 0.4044 | 9.49 | 2400 | 0.4524 | 0.7880 | 0.788 | | 0.407 | 10.28 | 2600 | 0.4713 | 0.7888 | 0.789 | | 0.4011 | 11.07 | 2800 | 0.4569 | 0.7950 | 0.795 | | 0.3959 | 11.86 | 3000 | 0.4624 | 0.7961 | 0.796 | | 0.3912 | 12.65 | 3200 | 0.4450 | 0.7900 | 0.79 | | 0.3851 | 13.44 | 3400 | 0.4656 | 0.7860 | 0.786 | | 0.3828 | 14.23 | 3600 | 0.4627 | 0.7831 | 0.783 | | 0.385 | 15.02 | 3800 | 0.4619 | 0.7840 | 0.784 | | 0.3776 | 15.81 | 4000 | 0.4544 | 0.7890 | 0.789 | | 0.3715 | 16.6 | 4200 | 0.4675 | 0.7900 | 0.79 | | 0.3724 | 17.39 | 4400 | 0.4740 | 0.7829 | 0.783 | | 0.3647 | 18.18 | 4600 | 0.4801 | 0.7770 | 0.777 | | 0.3629 | 18.97 | 4800 | 0.4775 | 0.7906 | 0.791 | | 0.3614 | 19.76 | 5000 | 0.4744 | 0.7791 | 0.779 | | 0.3561 | 20.55 | 5200 | 0.4928 | 0.7791 | 0.779 | | 0.3515 | 21.34 | 5400 | 0.4892 | 0.7790 | 0.779 | | 0.3462 | 22.13 | 5600 | 0.4900 | 0.784 | 0.784 | | 0.3465 | 22.92 | 5800 | 0.5117 | 0.77 | 0.77 | | 0.3425 | 23.72 | 6000 | 0.5007 | 0.7827 | 0.783 | | 0.3392 | 24.51 | 6200 | 0.4958 | 0.77 | 0.77 | | 0.3388 | 25.3 | 6400 | 0.5055 | 0.7801 | 0.78 | | 0.3305 | 26.09 | 6600 | 0.5099 | 0.7690 | 0.769 | | 0.3297 | 26.88 | 6800 | 0.5005 | 0.7749 | 0.775 | | 0.3299 | 27.67 | 7000 | 0.5162 | 0.7739 | 0.774 | | 0.3221 | 28.46 | 7200 | 0.5418 | 0.7690 | 0.769 | | 0.325 | 29.25 | 7400 | 0.5136 | 0.7720 | 0.772 | | 0.3218 | 30.04 | 7600 | 0.5461 | 0.7697 | 0.77 | | 0.3187 | 30.83 | 7800 | 0.5346 | 0.7718 | 0.772 | | 0.3196 | 31.62 | 8000 | 0.5273 | 0.7721 | 0.772 | | 0.3159 | 32.41 | 8200 | 0.5496 | 0.7727 | 0.773 | | 0.3117 | 33.2 | 8400 | 0.5563 | 0.7758 | 0.776 | | 0.3111 | 33.99 | 8600 | 0.5353 | 0.7729 | 0.773 | | 0.315 | 34.78 | 8800 | 0.5371 | 0.7750 | 0.775 | | 0.3025 | 35.57 | 9000 | 0.5510 | 0.7729 | 0.773 | | 0.3085 | 36.36 | 9200 | 0.5592 | 0.7667 | 0.767 | | 0.3092 | 37.15 | 9400 | 0.5583 | 0.7725 | 0.773 | | 0.3065 | 37.94 | 9600 | 0.5517 | 0.7698 | 0.77 | | 0.3047 | 38.74 | 9800 | 0.5561 | 0.7698 | 0.77 | | 0.3058 | 39.53 | 10000 | 0.5579 | 0.7687 | 0.769 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_tf_0-seqsight_4096_512_46M-L32_f", "results": []}]}

mahdibaghbanzadeh/GUE_tf_0-seqsight_4096_512_46M-L32_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_46M", "region:us" ]

null

2024-04-27T00:40:49+00:00

[]

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us

GUE\_tf\_0-seqsight\_4096\_512\_46M-L32\_f ========================================== This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_4096\_512\_46M on the mahdibaghbanzadeh/GUE\_tf\_0 dataset. It achieves the following results on the evaluation set: * Loss: 0.3707 * F1 Score: 0.8345 * Accuracy: 0.835 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

null

peft

# GUE_tf_1-seqsight_4096_512_46M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_tf_1](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_1) dataset. It achieves the following results on the evaluation set: - Loss: 0.3440 - F1 Score: 0.8597 - Accuracy: 0.86 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.5363 | 0.83 | 200 | 0.5327 | 0.7246 | 0.725 | | 0.5001 | 1.67 | 400 | 0.5163 | 0.7348 | 0.735 | | 0.4875 | 2.5 | 600 | 0.5116 | 0.7419 | 0.742 | | 0.4785 | 3.33 | 800 | 0.5076 | 0.7285 | 0.729 | | 0.4821 | 4.17 | 1000 | 0.4986 | 0.7499 | 0.75 | | 0.4692 | 5.0 | 1200 | 0.5033 | 0.7500 | 0.75 | | 0.4691 | 5.83 | 1400 | 0.4966 | 0.7480 | 0.748 | | 0.4676 | 6.67 | 1600 | 0.5014 | 0.7538 | 0.754 | | 0.4672 | 7.5 | 1800 | 0.4977 | 0.7529 | 0.753 | | 0.4584 | 8.33 | 2000 | 0.4960 | 0.7569 | 0.757 | | 0.4615 | 9.17 | 2200 | 0.4971 | 0.7539 | 0.754 | | 0.4591 | 10.0 | 2400 | 0.5072 | 0.7468 | 0.748 | | 0.4582 | 10.83 | 2600 | 0.4998 | 0.7505 | 0.751 | | 0.4564 | 11.67 | 2800 | 0.5020 | 0.7440 | 0.745 | | 0.4478 | 12.5 | 3000 | 0.5042 | 0.7483 | 0.749 | | 0.459 | 13.33 | 3200 | 0.4915 | 0.7505 | 0.751 | | 0.4477 | 14.17 | 3400 | 0.4921 | 0.7529 | 0.753 | | 0.4504 | 15.0 | 3600 | 0.5029 | 0.7430 | 0.744 | | 0.448 | 15.83 | 3800 | 0.4952 | 0.7508 | 0.751 | | 0.4509 | 16.67 | 4000 | 0.4993 | 0.7505 | 0.751 | | 0.445 | 17.5 | 4200 | 0.4965 | 0.7544 | 0.755 | | 0.4414 | 18.33 | 4400 | 0.5011 | 0.7589 | 0.759 | | 0.4473 | 19.17 | 4600 | 0.4987 | 0.7505 | 0.751 | | 0.4435 | 20.0 | 4800 | 0.4937 | 0.7538 | 0.754 | | 0.4454 | 20.83 | 5000 | 0.4961 | 0.7518 | 0.752 | | 0.438 | 21.67 | 5200 | 0.4953 | 0.7468 | 0.747 | | 0.4404 | 22.5 | 5400 | 0.4954 | 0.754 | 0.754 | | 0.439 | 23.33 | 5600 | 0.4940 | 0.7546 | 0.755 | | 0.441 | 24.17 | 5800 | 0.4978 | 0.7518 | 0.752 | | 0.4402 | 25.0 | 6000 | 0.4925 | 0.7490 | 0.749 | | 0.4375 | 25.83 | 6200 | 0.4923 | 0.7499 | 0.75 | | 0.4352 | 26.67 | 6400 | 0.4912 | 0.7489 | 0.749 | | 0.437 | 27.5 | 6600 | 0.4953 | 0.7540 | 0.754 | | 0.4358 | 28.33 | 6800 | 0.4912 | 0.7510 | 0.751 | | 0.4317 | 29.17 | 7000 | 0.4930 | 0.7490 | 0.749 | | 0.4363 | 30.0 | 7200 | 0.4909 | 0.7559 | 0.756 | | 0.4326 | 30.83 | 7400 | 0.4944 | 0.7458 | 0.746 | | 0.431 | 31.67 | 7600 | 0.4911 | 0.7520 | 0.752 | | 0.4318 | 32.5 | 7800 | 0.4921 | 0.7510 | 0.751 | | 0.4303 | 33.33 | 8000 | 0.4905 | 0.7530 | 0.753 | | 0.4334 | 34.17 | 8200 | 0.4898 | 0.7500 | 0.75 | | 0.427 | 35.0 | 8400 | 0.4901 | 0.7490 | 0.749 | | 0.4301 | 35.83 | 8600 | 0.4907 | 0.7500 | 0.75 | | 0.4324 | 36.67 | 8800 | 0.4899 | 0.7540 | 0.754 | | 0.427 | 37.5 | 9000 | 0.4934 | 0.7468 | 0.747 | | 0.4287 | 38.33 | 9200 | 0.4915 | 0.7500 | 0.75 | | 0.4273 | 39.17 | 9400 | 0.4921 | 0.748 | 0.748 | | 0.4298 | 40.0 | 9600 | 0.4915 | 0.7520 | 0.752 | | 0.4284 | 40.83 | 9800 | 0.4911 | 0.7480 | 0.748 | | 0.4278 | 41.67 | 10000 | 0.4909 | 0.7490 | 0.749 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_tf_1-seqsight_4096_512_46M-L1_f", "results": []}]}

mahdibaghbanzadeh/GUE_tf_1-seqsight_4096_512_46M-L1_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_46M", "region:us" ]

null

2024-04-27T00:41:08+00:00

[]

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us

GUE\_tf\_1-seqsight\_4096\_512\_46M-L1\_f ========================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_4096\_512\_46M on the mahdibaghbanzadeh/GUE\_tf\_1 dataset. It achieves the following results on the evaluation set: * Loss: 0.3440 * F1 Score: 0.8597 * Accuracy: 0.86 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

null

sailboat

{"license": "apache-2.0"}

ikukou/sailboat

null

[ "license:apache-2.0", "region:us" ]

null

2024-04-27T00:43:12+00:00

[]

TAGS #license-apache-2.0 #region-us

sailboat

[]

[ "TAGS\n#license-apache-2.0 #region-us \n" ]

image-classification

transformers

# Boya1_RMSProp_1-e5_10Epoch_swin-large-patch4-window7-224_fold5 This model is a fine-tuned version of [microsoft/swin-large-patch4-window7-224](https://huggingface.co/microsoft/swin-large-patch4-window7-224) on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 1.1456 - Accuracy: 0.6720 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 10 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 1.1558 | 1.0 | 924 | 1.1699 | 0.6023 | | 0.9755 | 2.0 | 1848 | 0.9954 | 0.6522 | | 0.7954 | 3.0 | 2772 | 0.9696 | 0.6753 | | 0.5362 | 4.0 | 3696 | 0.9918 | 0.6682 | | 0.5694 | 5.0 | 4620 | 0.9924 | 0.6712 | | 0.6743 | 6.0 | 5544 | 1.0447 | 0.6687 | | 0.5077 | 7.0 | 6468 | 1.0595 | 0.6717 | | 0.368 | 8.0 | 7392 | 1.1004 | 0.6717 | | 0.2622 | 9.0 | 8316 | 1.1347 | 0.6709 | | 0.267 | 10.0 | 9240 | 1.1456 | 0.6720 | ### Framework versions - Transformers 4.35.0 - Pytorch 2.1.0 - Datasets 2.14.6 - Tokenizers 0.14.1

{"license": "apache-2.0", "tags": ["generated_from_trainer"], "datasets": ["imagefolder"], "metrics": ["accuracy"], "base_model": "microsoft/swin-large-patch4-window7-224", "model-index": [{"name": "Boya1_RMSProp_1-e5_10Epoch_swin-large-patch4-window7-224_fold5", "results": [{"task": {"type": "image-classification", "name": "Image Classification"}, "dataset": {"name": "imagefolder", "type": "imagefolder", "config": "default", "split": "test", "args": "default"}, "metrics": [{"type": "accuracy", "value": 0.6719978313906207, "name": "Accuracy"}]}]}]}

onizukal/Boya1_RMSProp_1-e5_10Epoch_swin-large-patch4-window7-224_fold5

null

[ "transformers", "safetensors", "swin", "image-classification", "generated_from_trainer", "dataset:imagefolder", "base_model:microsoft/swin-large-patch4-window7-224", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]

null

2024-04-27T00:44:34+00:00

[]

TAGS #transformers #safetensors #swin #image-classification #generated_from_trainer #dataset-imagefolder #base_model-microsoft/swin-large-patch4-window7-224 #license-apache-2.0 #model-index #autotrain_compatible #endpoints_compatible #region-us

Boya1\_RMSProp\_1-e5\_10Epoch\_swin-large-patch4-window7-224\_fold5 =================================================================== This model is a fine-tuned version of microsoft/swin-large-patch4-window7-224 on the imagefolder dataset. It achieves the following results on the evaluation set: * Loss: 1.1456 * Accuracy: 0.6720 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 1e-05 * train\_batch\_size: 16 * eval\_batch\_size: 16 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * lr\_scheduler\_warmup\_ratio: 0.1 * num\_epochs: 10 ### Training results ### Framework versions * Transformers 4.35.0 * Pytorch 2.1.0 * Datasets 2.14.6 * Tokenizers 0.14.1

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 10", "### Training results", "### Framework versions\n\n\n* Transformers 4.35.0\n* Pytorch 2.1.0\n* Datasets 2.14.6\n* Tokenizers 0.14.1" ]

[ "TAGS\n#transformers #safetensors #swin #image-classification #generated_from_trainer #dataset-imagefolder #base_model-microsoft/swin-large-patch4-window7-224 #license-apache-2.0 #model-index #autotrain_compatible #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 10", "### Training results", "### Framework versions\n\n\n* Transformers 4.35.0\n* Pytorch 2.1.0\n* Datasets 2.14.6\n* Tokenizers 0.14.1" ]

text2text-generation

transformers

# CS505_COQE_viT5_train_Instruction0_SPOAL_v1 This model is a fine-tuned version of [VietAI/vit5-large](https://huggingface.co/VietAI/vit5-large) on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 20 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.15.2

{"license": "mit", "tags": ["generated_from_trainer"], "base_model": "VietAI/vit5-large", "model-index": [{"name": "CS505_COQE_viT5_train_Instruction0_SPOAL_v1", "results": []}]}

ThuyNT/CS505_COQE_viT5_train_Instruction0_SPOAL_v1

null

[ "transformers", "tensorboard", "safetensors", "t5", "text2text-generation", "generated_from_trainer", "base_model:VietAI/vit5-large", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

null

2024-04-27T00:45:10+00:00

[]

TAGS #transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-VietAI/vit5-large #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

# CS505_COQE_viT5_train_Instruction0_SPOAL_v1 This model is a fine-tuned version of VietAI/vit5-large on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 20 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.15.2

[ "# CS505_COQE_viT5_train_Instruction0_SPOAL_v1\n\nThis model is a fine-tuned version of VietAI/vit5-large on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 20\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-VietAI/vit5-large #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# CS505_COQE_viT5_train_Instruction0_SPOAL_v1\n\nThis model is a fine-tuned version of VietAI/vit5-large on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 20\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

null

peft

# GUE_tf_1-seqsight_4096_512_46M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_tf_1](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_1) dataset. It achieves the following results on the evaluation set: - Loss: 0.3395 - F1 Score: 0.8587 - Accuracy: 0.859 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.5242 | 0.83 | 200 | 0.5228 | 0.7387 | 0.74 | | 0.4863 | 1.67 | 400 | 0.5057 | 0.7428 | 0.743 | | 0.4772 | 2.5 | 600 | 0.4998 | 0.7559 | 0.756 | | 0.4696 | 3.33 | 800 | 0.4954 | 0.7580 | 0.758 | | 0.4708 | 4.17 | 1000 | 0.4919 | 0.7550 | 0.755 | | 0.4593 | 5.0 | 1200 | 0.4989 | 0.7537 | 0.754 | | 0.4586 | 5.83 | 1400 | 0.4896 | 0.7590 | 0.759 | | 0.4549 | 6.67 | 1600 | 0.4875 | 0.7630 | 0.763 | | 0.4559 | 7.5 | 1800 | 0.4899 | 0.7618 | 0.762 | | 0.4469 | 8.33 | 2000 | 0.4868 | 0.7640 | 0.764 | | 0.4491 | 9.17 | 2200 | 0.4838 | 0.7610 | 0.761 | | 0.445 | 10.0 | 2400 | 0.5029 | 0.7458 | 0.747 | | 0.4443 | 10.83 | 2600 | 0.4904 | 0.7595 | 0.76 | | 0.4407 | 11.67 | 2800 | 0.4849 | 0.7636 | 0.764 | | 0.4315 | 12.5 | 3000 | 0.4869 | 0.7516 | 0.752 | | 0.4437 | 13.33 | 3200 | 0.4789 | 0.7668 | 0.767 | | 0.4306 | 14.17 | 3400 | 0.4806 | 0.7607 | 0.761 | | 0.4323 | 15.0 | 3600 | 0.4877 | 0.7603 | 0.761 | | 0.4293 | 15.83 | 3800 | 0.4833 | 0.7558 | 0.756 | | 0.4302 | 16.67 | 4000 | 0.4819 | 0.7590 | 0.759 | | 0.4254 | 17.5 | 4200 | 0.4873 | 0.7620 | 0.763 | | 0.4196 | 18.33 | 4400 | 0.4848 | 0.7600 | 0.76 | | 0.4254 | 19.17 | 4600 | 0.4872 | 0.7545 | 0.755 | | 0.4204 | 20.0 | 4800 | 0.4785 | 0.7630 | 0.763 | | 0.4233 | 20.83 | 5000 | 0.4829 | 0.7719 | 0.772 | | 0.4157 | 21.67 | 5200 | 0.4803 | 0.7618 | 0.762 | | 0.4151 | 22.5 | 5400 | 0.4865 | 0.7609 | 0.761 | | 0.4151 | 23.33 | 5600 | 0.4885 | 0.7528 | 0.754 | | 0.4161 | 24.17 | 5800 | 0.4884 | 0.7557 | 0.756 | | 0.4137 | 25.0 | 6000 | 0.4851 | 0.7590 | 0.759 | | 0.411 | 25.83 | 6200 | 0.4834 | 0.7550 | 0.755 | | 0.4078 | 26.67 | 6400 | 0.4848 | 0.7610 | 0.761 | | 0.4098 | 27.5 | 6600 | 0.4882 | 0.7580 | 0.758 | | 0.4089 | 28.33 | 6800 | 0.4862 | 0.7630 | 0.763 | | 0.4039 | 29.17 | 7000 | 0.4860 | 0.7609 | 0.761 | | 0.4091 | 30.0 | 7200 | 0.4843 | 0.7589 | 0.759 | | 0.4036 | 30.83 | 7400 | 0.4903 | 0.7536 | 0.754 | | 0.4007 | 31.67 | 7600 | 0.4874 | 0.762 | 0.762 | | 0.4024 | 32.5 | 7800 | 0.4933 | 0.7570 | 0.757 | | 0.4003 | 33.33 | 8000 | 0.4869 | 0.7589 | 0.759 | | 0.4038 | 34.17 | 8200 | 0.4885 | 0.7569 | 0.757 | | 0.3966 | 35.0 | 8400 | 0.4872 | 0.7630 | 0.763 | | 0.3992 | 35.83 | 8600 | 0.4895 | 0.7549 | 0.755 | | 0.4022 | 36.67 | 8800 | 0.4880 | 0.7559 | 0.756 | | 0.3953 | 37.5 | 9000 | 0.4931 | 0.7485 | 0.749 | | 0.3971 | 38.33 | 9200 | 0.4926 | 0.7580 | 0.758 | | 0.3958 | 39.17 | 9400 | 0.4919 | 0.7599 | 0.76 | | 0.3969 | 40.0 | 9600 | 0.4915 | 0.7559 | 0.756 | | 0.3966 | 40.83 | 9800 | 0.4915 | 0.7640 | 0.764 | | 0.3956 | 41.67 | 10000 | 0.4909 | 0.7579 | 0.758 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_tf_1-seqsight_4096_512_46M-L8_f", "results": []}]}

mahdibaghbanzadeh/GUE_tf_1-seqsight_4096_512_46M-L8_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_46M", "region:us" ]

null

2024-04-27T00:48:37+00:00

[]

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us

GUE\_tf\_1-seqsight\_4096\_512\_46M-L8\_f ========================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_4096\_512\_46M on the mahdibaghbanzadeh/GUE\_tf\_1 dataset. It achieves the following results on the evaluation set: * Loss: 0.3395 * F1 Score: 0.8587 * Accuracy: 0.859 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

null

peft

# GUE_tf_1-seqsight_4096_512_46M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_tf_1](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_1) dataset. It achieves the following results on the evaluation set: - Loss: 0.3578 - F1 Score: 0.8591 - Accuracy: 0.86 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.5178 | 0.83 | 200 | 0.5181 | 0.7554 | 0.756 | | 0.4819 | 1.67 | 400 | 0.5070 | 0.7479 | 0.748 | | 0.4721 | 2.5 | 600 | 0.5003 | 0.7550 | 0.755 | | 0.4633 | 3.33 | 800 | 0.4913 | 0.7500 | 0.75 | | 0.4611 | 4.17 | 1000 | 0.4880 | 0.7457 | 0.746 | | 0.451 | 5.0 | 1200 | 0.4936 | 0.7599 | 0.76 | | 0.4455 | 5.83 | 1400 | 0.4886 | 0.7550 | 0.755 | | 0.4398 | 6.67 | 1600 | 0.4827 | 0.7540 | 0.754 | | 0.4403 | 7.5 | 1800 | 0.4871 | 0.7565 | 0.757 | | 0.4285 | 8.33 | 2000 | 0.4859 | 0.7600 | 0.76 | | 0.4291 | 9.17 | 2200 | 0.4824 | 0.756 | 0.756 | | 0.4231 | 10.0 | 2400 | 0.4961 | 0.7518 | 0.753 | | 0.4183 | 10.83 | 2600 | 0.4858 | 0.7586 | 0.759 | | 0.4125 | 11.67 | 2800 | 0.4818 | 0.7580 | 0.758 | | 0.4046 | 12.5 | 3000 | 0.4903 | 0.7595 | 0.76 | | 0.4113 | 13.33 | 3200 | 0.4825 | 0.7658 | 0.766 | | 0.3989 | 14.17 | 3400 | 0.4853 | 0.7730 | 0.773 | | 0.3986 | 15.0 | 3600 | 0.4928 | 0.7634 | 0.764 | | 0.3925 | 15.83 | 3800 | 0.4894 | 0.7678 | 0.768 | | 0.3898 | 16.67 | 4000 | 0.4929 | 0.764 | 0.764 | | 0.386 | 17.5 | 4200 | 0.4984 | 0.7664 | 0.767 | | 0.374 | 18.33 | 4400 | 0.5094 | 0.7630 | 0.763 | | 0.3786 | 19.17 | 4600 | 0.5111 | 0.7638 | 0.764 | | 0.374 | 20.0 | 4800 | 0.5076 | 0.7560 | 0.756 | | 0.3709 | 20.83 | 5000 | 0.5112 | 0.7650 | 0.765 | | 0.3616 | 21.67 | 5200 | 0.5153 | 0.7609 | 0.761 | | 0.3613 | 22.5 | 5400 | 0.5168 | 0.7610 | 0.761 | | 0.3574 | 23.33 | 5600 | 0.5195 | 0.7615 | 0.762 | | 0.3574 | 24.17 | 5800 | 0.5281 | 0.7595 | 0.76 | | 0.352 | 25.0 | 6000 | 0.5211 | 0.7670 | 0.767 | | 0.3476 | 25.83 | 6200 | 0.5293 | 0.7609 | 0.761 | | 0.3458 | 26.67 | 6400 | 0.5182 | 0.7620 | 0.762 | | 0.3432 | 27.5 | 6600 | 0.5400 | 0.7570 | 0.757 | | 0.3399 | 28.33 | 6800 | 0.5396 | 0.7500 | 0.75 | | 0.3329 | 29.17 | 7000 | 0.5313 | 0.7558 | 0.756 | | 0.3357 | 30.0 | 7200 | 0.5416 | 0.7589 | 0.759 | | 0.3301 | 30.83 | 7400 | 0.5557 | 0.7504 | 0.751 | | 0.3245 | 31.67 | 7600 | 0.5575 | 0.7578 | 0.758 | | 0.328 | 32.5 | 7800 | 0.5649 | 0.7580 | 0.758 | | 0.3233 | 33.33 | 8000 | 0.5662 | 0.7546 | 0.755 | | 0.33 | 34.17 | 8200 | 0.5604 | 0.7508 | 0.751 | | 0.3193 | 35.0 | 8400 | 0.5548 | 0.7619 | 0.762 | | 0.3212 | 35.83 | 8600 | 0.5584 | 0.7539 | 0.754 | | 0.3185 | 36.67 | 8800 | 0.5635 | 0.7489 | 0.749 | | 0.3152 | 37.5 | 9000 | 0.5705 | 0.7573 | 0.758 | | 0.3089 | 38.33 | 9200 | 0.5811 | 0.7539 | 0.754 | | 0.3108 | 39.17 | 9400 | 0.5683 | 0.7578 | 0.758 | | 0.3144 | 40.0 | 9600 | 0.5730 | 0.7547 | 0.755 | | 0.3124 | 40.83 | 9800 | 0.5736 | 0.7560 | 0.756 | | 0.31 | 41.67 | 10000 | 0.5746 | 0.7518 | 0.752 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_tf_1-seqsight_4096_512_46M-L32_f", "results": []}]}

mahdibaghbanzadeh/GUE_tf_1-seqsight_4096_512_46M-L32_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_46M", "region:us" ]

null

2024-04-27T00:48:37+00:00

[]

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us

GUE\_tf\_1-seqsight\_4096\_512\_46M-L32\_f ========================================== This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_4096\_512\_46M on the mahdibaghbanzadeh/GUE\_tf\_1 dataset. It achieves the following results on the evaluation set: * Loss: 0.3578 * F1 Score: 0.8591 * Accuracy: 0.86 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

null

peft

# GUE_tf_4-seqsight_4096_512_46M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_tf_4](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_4) dataset. It achieves the following results on the evaluation set: - Loss: 0.3559 - F1 Score: 0.8462 - Accuracy: 0.847 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.5287 | 1.34 | 200 | 0.5089 | 0.7376 | 0.738 | | 0.4796 | 2.68 | 400 | 0.4835 | 0.7698 | 0.77 | | 0.4591 | 4.03 | 600 | 0.4711 | 0.7733 | 0.774 | | 0.4496 | 5.37 | 800 | 0.4665 | 0.7789 | 0.779 | | 0.4341 | 6.71 | 1000 | 0.4513 | 0.7908 | 0.791 | | 0.4287 | 8.05 | 1200 | 0.4501 | 0.7888 | 0.789 | | 0.4239 | 9.4 | 1400 | 0.4484 | 0.7960 | 0.796 | | 0.419 | 10.74 | 1600 | 0.4484 | 0.8027 | 0.803 | | 0.4107 | 12.08 | 1800 | 0.4510 | 0.7993 | 0.8 | | 0.4106 | 13.42 | 2000 | 0.4351 | 0.8010 | 0.801 | | 0.3995 | 14.77 | 2200 | 0.4371 | 0.7987 | 0.799 | | 0.4025 | 16.11 | 2400 | 0.4327 | 0.8100 | 0.81 | | 0.3956 | 17.45 | 2600 | 0.4302 | 0.8110 | 0.811 | | 0.3907 | 18.79 | 2800 | 0.4324 | 0.8090 | 0.809 | | 0.394 | 20.13 | 3000 | 0.4252 | 0.8099 | 0.81 | | 0.3851 | 21.48 | 3200 | 0.4278 | 0.8180 | 0.818 | | 0.3797 | 22.82 | 3400 | 0.4284 | 0.8117 | 0.812 | | 0.3805 | 24.16 | 3600 | 0.4223 | 0.8129 | 0.813 | | 0.3756 | 25.5 | 3800 | 0.4274 | 0.8095 | 0.81 | | 0.3731 | 26.85 | 4000 | 0.4213 | 0.8150 | 0.815 | | 0.3697 | 28.19 | 4200 | 0.4202 | 0.8110 | 0.811 | | 0.3623 | 29.53 | 4400 | 0.4219 | 0.8150 | 0.815 | | 0.3626 | 30.87 | 4600 | 0.4158 | 0.8130 | 0.813 | | 0.3615 | 32.21 | 4800 | 0.4192 | 0.8260 | 0.826 | | 0.358 | 33.56 | 5000 | 0.4179 | 0.8159 | 0.816 | | 0.3587 | 34.9 | 5200 | 0.4164 | 0.8140 | 0.814 | | 0.3535 | 36.24 | 5400 | 0.4185 | 0.8199 | 0.82 | | 0.3502 | 37.58 | 5600 | 0.4194 | 0.8189 | 0.819 | | 0.3495 | 38.93 | 5800 | 0.4166 | 0.8150 | 0.815 | | 0.3444 | 40.27 | 6000 | 0.4211 | 0.8140 | 0.814 | | 0.3449 | 41.61 | 6200 | 0.4179 | 0.8190 | 0.819 | | 0.3427 | 42.95 | 6400 | 0.4192 | 0.8160 | 0.816 | | 0.3455 | 44.3 | 6600 | 0.4171 | 0.8198 | 0.82 | | 0.3345 | 45.64 | 6800 | 0.4180 | 0.8180 | 0.818 | | 0.338 | 46.98 | 7000 | 0.4168 | 0.8149 | 0.815 | | 0.3369 | 48.32 | 7200 | 0.4144 | 0.8110 | 0.811 | | 0.3356 | 49.66 | 7400 | 0.4122 | 0.8210 | 0.821 | | 0.3338 | 51.01 | 7600 | 0.4153 | 0.8189 | 0.819 | | 0.3316 | 52.35 | 7800 | 0.4163 | 0.8166 | 0.817 | | 0.3275 | 53.69 | 8000 | 0.4147 | 0.8200 | 0.82 | | 0.3327 | 55.03 | 8200 | 0.4122 | 0.8180 | 0.818 | | 0.3313 | 56.38 | 8400 | 0.4119 | 0.8198 | 0.82 | | 0.3263 | 57.72 | 8600 | 0.4142 | 0.8228 | 0.823 | | 0.3257 | 59.06 | 8800 | 0.4120 | 0.8179 | 0.818 | | 0.3257 | 60.4 | 9000 | 0.4129 | 0.8180 | 0.818 | | 0.3227 | 61.74 | 9200 | 0.4148 | 0.8187 | 0.819 | | 0.3229 | 63.09 | 9400 | 0.4128 | 0.8219 | 0.822 | | 0.3251 | 64.43 | 9600 | 0.4119 | 0.8209 | 0.821 | | 0.3206 | 65.77 | 9800 | 0.4119 | 0.8199 | 0.82 | | 0.3228 | 67.11 | 10000 | 0.4122 | 0.8199 | 0.82 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_tf_4-seqsight_4096_512_46M-L1_f", "results": []}]}

mahdibaghbanzadeh/GUE_tf_4-seqsight_4096_512_46M-L1_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_46M", "region:us" ]

null

2024-04-27T00:54:41+00:00

[]

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us

GUE\_tf\_4-seqsight\_4096\_512\_46M-L1\_f ========================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_4096\_512\_46M on the mahdibaghbanzadeh/GUE\_tf\_4 dataset. It achieves the following results on the evaluation set: * Loss: 0.3559 * F1 Score: 0.8462 * Accuracy: 0.847 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

null

peft

# GUE_tf_4-seqsight_4096_512_46M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_tf_4](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_4) dataset. It achieves the following results on the evaluation set: - Loss: 0.3872 - F1 Score: 0.8608 - Accuracy: 0.861 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.5114 | 1.34 | 200 | 0.4841 | 0.7588 | 0.759 | | 0.4533 | 2.68 | 400 | 0.4569 | 0.7879 | 0.788 | | 0.4314 | 4.03 | 600 | 0.4494 | 0.7879 | 0.788 | | 0.4235 | 5.37 | 800 | 0.4531 | 0.7849 | 0.785 | | 0.4091 | 6.71 | 1000 | 0.4446 | 0.7892 | 0.79 | | 0.4027 | 8.05 | 1200 | 0.4379 | 0.8110 | 0.811 | | 0.3978 | 9.4 | 1400 | 0.4401 | 0.8089 | 0.809 | | 0.392 | 10.74 | 1600 | 0.4347 | 0.804 | 0.804 | | 0.382 | 12.08 | 1800 | 0.4428 | 0.8020 | 0.802 | | 0.3794 | 13.42 | 2000 | 0.4361 | 0.7995 | 0.8 | | 0.3679 | 14.77 | 2200 | 0.4246 | 0.8059 | 0.806 | | 0.3698 | 16.11 | 2400 | 0.4268 | 0.8108 | 0.811 | | 0.3603 | 17.45 | 2600 | 0.4300 | 0.8089 | 0.809 | | 0.3535 | 18.79 | 2800 | 0.4289 | 0.8220 | 0.822 | | 0.3563 | 20.13 | 3000 | 0.4140 | 0.8100 | 0.81 | | 0.3448 | 21.48 | 3200 | 0.4314 | 0.8023 | 0.803 | | 0.3366 | 22.82 | 3400 | 0.4326 | 0.7985 | 0.799 | | 0.3365 | 24.16 | 3600 | 0.4185 | 0.8029 | 0.803 | | 0.3282 | 25.5 | 3800 | 0.4323 | 0.8017 | 0.802 | | 0.3253 | 26.85 | 4000 | 0.4284 | 0.8069 | 0.807 | | 0.3204 | 28.19 | 4200 | 0.4233 | 0.8070 | 0.807 | | 0.311 | 29.53 | 4400 | 0.4352 | 0.8064 | 0.807 | | 0.3127 | 30.87 | 4600 | 0.4316 | 0.8007 | 0.801 | | 0.3054 | 32.21 | 4800 | 0.4319 | 0.8050 | 0.805 | | 0.3041 | 33.56 | 5000 | 0.4301 | 0.8080 | 0.808 | | 0.2983 | 34.9 | 5200 | 0.4331 | 0.8070 | 0.807 | | 0.2925 | 36.24 | 5400 | 0.4322 | 0.8126 | 0.813 | | 0.2899 | 37.58 | 5600 | 0.4373 | 0.808 | 0.808 | | 0.2883 | 38.93 | 5800 | 0.4288 | 0.8030 | 0.803 | | 0.2819 | 40.27 | 6000 | 0.4460 | 0.8142 | 0.815 | | 0.2787 | 41.61 | 6200 | 0.4333 | 0.8130 | 0.813 | | 0.2745 | 42.95 | 6400 | 0.4375 | 0.8140 | 0.814 | | 0.2785 | 44.3 | 6600 | 0.4389 | 0.8157 | 0.816 | | 0.2678 | 45.64 | 6800 | 0.4411 | 0.8140 | 0.814 | | 0.2698 | 46.98 | 7000 | 0.4366 | 0.8148 | 0.815 | | 0.2656 | 48.32 | 7200 | 0.4422 | 0.8217 | 0.822 | | 0.2664 | 49.66 | 7400 | 0.4372 | 0.8218 | 0.822 | | 0.2633 | 51.01 | 7600 | 0.4431 | 0.8140 | 0.814 | | 0.2598 | 52.35 | 7800 | 0.4473 | 0.8165 | 0.817 | | 0.2547 | 53.69 | 8000 | 0.4394 | 0.8200 | 0.82 | | 0.2555 | 55.03 | 8200 | 0.4385 | 0.822 | 0.822 | | 0.2551 | 56.38 | 8400 | 0.4433 | 0.8239 | 0.824 | | 0.2517 | 57.72 | 8600 | 0.4488 | 0.8217 | 0.822 | | 0.2521 | 59.06 | 8800 | 0.4459 | 0.8187 | 0.819 | | 0.2506 | 60.4 | 9000 | 0.4476 | 0.8218 | 0.822 | | 0.2491 | 61.74 | 9200 | 0.4567 | 0.8134 | 0.814 | | 0.2485 | 63.09 | 9400 | 0.4474 | 0.8228 | 0.823 | | 0.2474 | 64.43 | 9600 | 0.4485 | 0.8217 | 0.822 | | 0.2433 | 65.77 | 9800 | 0.4475 | 0.8218 | 0.822 | | 0.2437 | 67.11 | 10000 | 0.4489 | 0.8218 | 0.822 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_tf_4-seqsight_4096_512_46M-L8_f", "results": []}]}

mahdibaghbanzadeh/GUE_tf_4-seqsight_4096_512_46M-L8_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_46M", "region:us" ]

null

2024-04-27T00:54:42+00:00

[]

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us

GUE\_tf\_4-seqsight\_4096\_512\_46M-L8\_f ========================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_4096\_512\_46M on the mahdibaghbanzadeh/GUE\_tf\_4 dataset. It achieves the following results on the evaluation set: * Loss: 0.3872 * F1 Score: 0.8608 * Accuracy: 0.861 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

text2text-generation

transformers

# CS505_COQE_viT5_train_Instruction0_OPSAL_v1 This model is a fine-tuned version of [VietAI/vit5-large](https://huggingface.co/VietAI/vit5-large) on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 20 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.15.2

{"license": "mit", "tags": ["generated_from_trainer"], "base_model": "VietAI/vit5-large", "model-index": [{"name": "CS505_COQE_viT5_train_Instruction0_OPSAL_v1", "results": []}]}

ThuyNT/CS505_COQE_viT5_train_Instruction0_OPSAL_v1

null

[ "transformers", "tensorboard", "safetensors", "t5", "text2text-generation", "generated_from_trainer", "base_model:VietAI/vit5-large", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

null

2024-04-27T00:56:55+00:00

[]

TAGS #transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-VietAI/vit5-large #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

# CS505_COQE_viT5_train_Instruction0_OPSAL_v1 This model is a fine-tuned version of VietAI/vit5-large on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 20 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.15.2

[ "# CS505_COQE_viT5_train_Instruction0_OPSAL_v1\n\nThis model is a fine-tuned version of VietAI/vit5-large on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 20\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-VietAI/vit5-large #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# CS505_COQE_viT5_train_Instruction0_OPSAL_v1\n\nThis model is a fine-tuned version of VietAI/vit5-large on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 20\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

text-generation

transformers

# Model This model is fine-tuned based on Meta-Llama/Meta-Llama-3-8B instructions via mlx-lm. **Note:** The glaive-function-calling-v2 dataset contains some invalid JSON and single quotes for the arguments' values. I have re-trained the model based on cleaned-up data. If you encounter issues with the function calling JSON format, you may try this new version here: https://huggingface.co/mzbac/llama-3-8B-Instruct-function-calling-v0.2 ## Usage ```python from transformers import AutoTokenizer, AutoModelForCausalLM import torch model_id = "mzbac/llama-3-8B-Instruct-function-calling" tokenizer = AutoTokenizer.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype=torch.bfloat16, device_map="auto", ) tool = { "name": "search_web", "description": "Perform a web search for a given search terms.", "parameter": { "type": "object", "properties": { "search_terms": { "type": "array", "items": {"type": "string"}, "description": "The search queries for which the search is performed.", "required": True, } } }, } messages = [ { "role": "system", "content": f"You are a helpful assistant with access to the following functions. Use them if required - {str(tool)}", }, {"role": "user", "content": "Today's news in Melbourne, just for your information, today is April 27, 2014."}, ] input_ids = tokenizer.apply_chat_template( messages, add_generation_prompt=True, return_tensors="pt" ).to(model.device) terminators = [ tokenizer.eos_token_id, tokenizer.convert_tokens_to_ids("<|eot_id|>") ] outputs = model.generate( input_ids, max_new_tokens=256, eos_token_id=terminators, do_sample=True, temperature=0.1, ) response = outputs[0] print(tokenizer.decode(response)) # <|begin_of_text|><|start_header_id|>system<|end_header_id|> # You are a helpful assistant with access to the following functions. Use them if required - {'name':'search_web', 'description': 'Perform a web search for a given search terms.', 'parameter': {'type': 'object', 'properties': {'search_terms': {'type': 'array', 'items': {'type':'string'}, 'description': 'The search queries for which the search is performed.','required': True}}}}<|eot_id|><|start_header_id|>user<|end_header_id|> # Today's news in Melbourne, just for your information, today is April 27, 2014.<|eot_id|><|start_header_id|>assistant<|end_header_id|> # <functioncall> {"name": "search_web", "arguments": '{"search_terms": ["Melbourne news", "April 27, 2014"]}'}<|eot_id|> ``` ## Training hyperparameters lora_config.yaml ```yaml # The path to the local model directory or Hugging Face repo. model: "meta-llama/Meta-Llama-3-8B-Instruct" # Whether or not to train (boolean) train: true # Directory with {train, valid, test}.jsonl files data: "data" # The PRNG seed seed: 0 # Number of layers to fine-tune lora_layers: 32 # Minibatch size. batch_size: 1 # Iterations to train for. iters: 6000 # Number of validation batches, -1 uses the entire validation set. val_batches: 25 # Adam learning rate. learning_rate: 1e-6 # Number of training steps between loss reporting. steps_per_report: 10 # Number of training steps between validations. steps_per_eval: 200 # Load path to resume training with the given adapter weights. resume_adapter_file: null # Save/load path for the trained adapter weights. adapter_path: "adapters" # Save the model every N iterations. save_every: 1000 # Evaluate on the test set after training test: false # Number of test set batches, -1 uses the entire test set. test_batches: 100 # Maximum sequence length. max_seq_length: 8192 # Use gradient checkpointing to reduce memory use. grad_checkpoint: false # LoRA parameters can only be specified in a config file lora_parameters: # The layer keys to apply LoRA to. # These will be applied for the last lora_layers keys: ['mlp.gate_proj', 'mlp.down_proj', 'self_attn.q_proj', 'mlp.up_proj', 'self_attn.o_proj','self_attn.v_proj', 'self_attn.k_proj'] rank: 128 alpha: 256 scale: 10.0 dropout: 0.05 # Schedule can only be specified in a config file, uncomment to use. #lr_schedule: # name: cosine_decay # warmup: 100 # 0 for no warmup # warmup_init: 1e-7 # 0 if not specified # arguments: [1e-6, 1000, 1e-7] # passed to scheduler ```

{"language": ["en"], "license": "llama3", "datasets": ["mzbac/glaive-function-calling-v2-llama-3-format"]}

mzbac/llama-3-8B-Instruct-function-calling

null

[ "transformers", "safetensors", "llama", "text-generation", "conversational", "en", "dataset:mzbac/glaive-function-calling-v2-llama-3-format", "license:llama3", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

null

2024-04-27T00:57:38+00:00

[]

[ "en" ]

TAGS #transformers #safetensors #llama #text-generation #conversational #en #dataset-mzbac/glaive-function-calling-v2-llama-3-format #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

# Model This model is fine-tuned based on Meta-Llama/Meta-Llama-3-8B instructions via mlx-lm. Note: The glaive-function-calling-v2 dataset contains some invalid JSON and single quotes for the arguments' values. I have re-trained the model based on cleaned-up data. If you encounter issues with the function calling JSON format, you may try this new version here: URL ## Usage ## Training hyperparameters lora_config.yaml

[ "# Model\n\nThis model is fine-tuned based on Meta-Llama/Meta-Llama-3-8B instructions via mlx-lm.\n\nNote: The glaive-function-calling-v2 dataset contains some invalid JSON and single quotes for the arguments' values. I have re-trained the model based on cleaned-up data. If you encounter issues with the function calling JSON format, you may try this new version here: URL", "## Usage", "## Training hyperparameters\nlora_config.yaml" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #conversational #en #dataset-mzbac/glaive-function-calling-v2-llama-3-format #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model\n\nThis model is fine-tuned based on Meta-Llama/Meta-Llama-3-8B instructions via mlx-lm.\n\nNote: The glaive-function-calling-v2 dataset contains some invalid JSON and single quotes for the arguments' values. I have re-trained the model based on cleaned-up data. If you encounter issues with the function calling JSON format, you may try this new version here: URL", "## Usage", "## Training hyperparameters\nlora_config.yaml" ]

text2text-generation

transformers

# CS505_COQE_viT5_train_Instruction0_PASOL_v1 This model is a fine-tuned version of [VietAI/vit5-large](https://huggingface.co/VietAI/vit5-large) on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 20 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.15.2

{"license": "mit", "tags": ["generated_from_trainer"], "base_model": "VietAI/vit5-large", "model-index": [{"name": "CS505_COQE_viT5_train_Instruction0_PASOL_v1", "results": []}]}

ThuyNT/CS505_COQE_viT5_train_Instruction0_PASOL_v1

null

[ "transformers", "tensorboard", "safetensors", "t5", "text2text-generation", "generated_from_trainer", "base_model:VietAI/vit5-large", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

null

2024-04-27T00:59:33+00:00

[]

TAGS #transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-VietAI/vit5-large #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

# CS505_COQE_viT5_train_Instruction0_PASOL_v1 This model is a fine-tuned version of VietAI/vit5-large on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 20 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.15.2

[ "# CS505_COQE_viT5_train_Instruction0_PASOL_v1\n\nThis model is a fine-tuned version of VietAI/vit5-large on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 20\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-VietAI/vit5-large #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# CS505_COQE_viT5_train_Instruction0_PASOL_v1\n\nThis model is a fine-tuned version of VietAI/vit5-large on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 20\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

text2text-generation

transformers

# CS505_COQE_viT5_train_Instruction0_APSOL_v1 This model is a fine-tuned version of [VietAI/vit5-large](https://huggingface.co/VietAI/vit5-large) on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 20 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.15.2

{"license": "mit", "tags": ["generated_from_trainer"], "base_model": "VietAI/vit5-large", "model-index": [{"name": "CS505_COQE_viT5_train_Instruction0_APSOL_v1", "results": []}]}

ThuyNT/CS505_COQE_viT5_train_Instruction0_APSOL_v1

null

[ "transformers", "tensorboard", "safetensors", "t5", "text2text-generation", "generated_from_trainer", "base_model:VietAI/vit5-large", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

null

2024-04-27T01:00:26+00:00

[]

TAGS #transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-VietAI/vit5-large #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

# CS505_COQE_viT5_train_Instruction0_APSOL_v1 This model is a fine-tuned version of VietAI/vit5-large on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 20 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.15.2

[ "# CS505_COQE_viT5_train_Instruction0_APSOL_v1\n\nThis model is a fine-tuned version of VietAI/vit5-large on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 20\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-VietAI/vit5-large #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# CS505_COQE_viT5_train_Instruction0_APSOL_v1\n\nThis model is a fine-tuned version of VietAI/vit5-large on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 20\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

null

transformers

# Model Card for Model ID  ## Model Details ### Model Description  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

leminhnhat/bug-impact-level-falcon-7b

null

[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]

null

2024-04-27T01:00:32+00:00

[ "1910.09700" ]

[]

TAGS #transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us

# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

text-generation

transformers

# 0.001_4iters_bs128_nodpo_only4w_userresponse_iter_4 This model is a fine-tuned version of [ShenaoZhang/0.001_4iters_bs128_nodpo_only4w_userresponse_iter_3](https://huggingface.co/ShenaoZhang/0.001_4iters_bs128_nodpo_only4w_userresponse_iter_3) on the updated and the original datasets. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-07 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - distributed_type: multi-GPU - num_devices: 8 - gradient_accumulation_steps: 2 - total_train_batch_size: 128 - total_eval_batch_size: 64 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 1 ### Training results ### Framework versions - Transformers 4.40.0 - Pytorch 2.1.2+cu121 - Datasets 2.14.6 - Tokenizers 0.19.1

{"license": "mit", "tags": ["alignment-handbook", "trl", "dpo", "generated_from_trainer", "trl", "dpo", "generated_from_trainer"], "datasets": ["updated", "original"], "base_model": "ShenaoZhang/0.001_4iters_bs128_nodpo_only4w_userresponse_iter_3", "model-index": [{"name": "0.001_4iters_bs128_nodpo_only4w_userresponse_iter_4", "results": []}]}

ShenaoZhang/0.001_4iters_bs128_nodpo_only4w_userresponse_iter_4

null

[ "transformers", "safetensors", "mistral", "text-generation", "alignment-handbook", "trl", "dpo", "generated_from_trainer", "conversational", "dataset:updated", "dataset:original", "base_model:ShenaoZhang/0.001_4iters_bs128_nodpo_only4w_userresponse_iter_3", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

null

2024-04-27T01:01:16+00:00

[]

TAGS #transformers #safetensors #mistral #text-generation #alignment-handbook #trl #dpo #generated_from_trainer #conversational #dataset-updated #dataset-original #base_model-ShenaoZhang/0.001_4iters_bs128_nodpo_only4w_userresponse_iter_3 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

# 0.001_4iters_bs128_nodpo_only4w_userresponse_iter_4 This model is a fine-tuned version of ShenaoZhang/0.001_4iters_bs128_nodpo_only4w_userresponse_iter_3 on the updated and the original datasets. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-07 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - distributed_type: multi-GPU - num_devices: 8 - gradient_accumulation_steps: 2 - total_train_batch_size: 128 - total_eval_batch_size: 64 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 1 ### Training results ### Framework versions - Transformers 4.40.0 - Pytorch 2.1.2+cu121 - Datasets 2.14.6 - Tokenizers 0.19.1

[ "# 0.001_4iters_bs128_nodpo_only4w_userresponse_iter_4\n\nThis model is a fine-tuned version of ShenaoZhang/0.001_4iters_bs128_nodpo_only4w_userresponse_iter_3 on the updated and the original datasets.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 128\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #alignment-handbook #trl #dpo #generated_from_trainer #conversational #dataset-updated #dataset-original #base_model-ShenaoZhang/0.001_4iters_bs128_nodpo_only4w_userresponse_iter_3 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# 0.001_4iters_bs128_nodpo_only4w_userresponse_iter_4\n\nThis model is a fine-tuned version of ShenaoZhang/0.001_4iters_bs128_nodpo_only4w_userresponse_iter_3 on the updated and the original datasets.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 128\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.19.1" ]

null

peft

# GUE_tf_4-seqsight_4096_512_46M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_tf_4](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_4) dataset. It achieves the following results on the evaluation set: - Loss: 0.5633 - F1 Score: 0.8590 - Accuracy: 0.859 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.4994 | 1.34 | 200 | 0.4682 | 0.7780 | 0.778 | | 0.4392 | 2.68 | 400 | 0.4531 | 0.7976 | 0.798 | | 0.4164 | 4.03 | 600 | 0.4410 | 0.7987 | 0.799 | | 0.4047 | 5.37 | 800 | 0.4483 | 0.7984 | 0.799 | | 0.3858 | 6.71 | 1000 | 0.4345 | 0.8053 | 0.806 | | 0.3737 | 8.05 | 1200 | 0.4310 | 0.8200 | 0.82 | | 0.3573 | 9.4 | 1400 | 0.4410 | 0.8099 | 0.81 | | 0.3463 | 10.74 | 1600 | 0.4223 | 0.8069 | 0.807 | | 0.3289 | 12.08 | 1800 | 0.4386 | 0.8066 | 0.807 | | 0.3161 | 13.42 | 2000 | 0.4191 | 0.8126 | 0.813 | | 0.2995 | 14.77 | 2200 | 0.4017 | 0.8209 | 0.821 | | 0.2898 | 16.11 | 2400 | 0.4091 | 0.8309 | 0.831 | | 0.2732 | 17.45 | 2600 | 0.4053 | 0.8340 | 0.834 | | 0.2635 | 18.79 | 2800 | 0.4117 | 0.8310 | 0.831 | | 0.2499 | 20.13 | 3000 | 0.3964 | 0.8510 | 0.851 | | 0.2425 | 21.48 | 3200 | 0.4229 | 0.8436 | 0.844 | | 0.2274 | 22.82 | 3400 | 0.4003 | 0.8509 | 0.851 | | 0.2198 | 24.16 | 3600 | 0.4151 | 0.8530 | 0.853 | | 0.2084 | 25.5 | 3800 | 0.4365 | 0.8488 | 0.849 | | 0.2023 | 26.85 | 4000 | 0.4383 | 0.8464 | 0.847 | | 0.1914 | 28.19 | 4200 | 0.4295 | 0.8590 | 0.859 | | 0.1869 | 29.53 | 4400 | 0.4562 | 0.8647 | 0.865 | | 0.182 | 30.87 | 4600 | 0.4308 | 0.8560 | 0.856 | | 0.1731 | 32.21 | 4800 | 0.4319 | 0.8680 | 0.868 | | 0.1691 | 33.56 | 5000 | 0.4492 | 0.8659 | 0.866 | | 0.1658 | 34.9 | 5200 | 0.4321 | 0.8640 | 0.864 | | 0.1495 | 36.24 | 5400 | 0.4748 | 0.8544 | 0.855 | | 0.1496 | 37.58 | 5600 | 0.4670 | 0.8709 | 0.871 | | 0.1468 | 38.93 | 5800 | 0.4527 | 0.8709 | 0.871 | | 0.1377 | 40.27 | 6000 | 0.4790 | 0.8747 | 0.875 | | 0.1372 | 41.61 | 6200 | 0.4706 | 0.8749 | 0.875 | | 0.1304 | 42.95 | 6400 | 0.4814 | 0.8758 | 0.876 | | 0.1323 | 44.3 | 6600 | 0.4978 | 0.8678 | 0.868 | | 0.1271 | 45.64 | 6800 | 0.4728 | 0.8759 | 0.876 | | 0.1229 | 46.98 | 7000 | 0.5029 | 0.8748 | 0.875 | | 0.1169 | 48.32 | 7200 | 0.5104 | 0.8798 | 0.88 | | 0.1194 | 49.66 | 7400 | 0.5029 | 0.8728 | 0.873 | | 0.1135 | 51.01 | 7600 | 0.4992 | 0.8809 | 0.881 | | 0.1065 | 52.35 | 7800 | 0.5255 | 0.8737 | 0.874 | | 0.109 | 53.69 | 8000 | 0.5078 | 0.8789 | 0.879 | | 0.1066 | 55.03 | 8200 | 0.4901 | 0.8830 | 0.883 | | 0.1047 | 56.38 | 8400 | 0.5498 | 0.8707 | 0.871 | | 0.105 | 57.72 | 8600 | 0.5313 | 0.8737 | 0.874 | | 0.1023 | 59.06 | 8800 | 0.5276 | 0.8738 | 0.874 | | 0.1058 | 60.4 | 9000 | 0.5221 | 0.8718 | 0.872 | | 0.0966 | 61.74 | 9200 | 0.5393 | 0.8707 | 0.871 | | 0.0987 | 63.09 | 9400 | 0.5360 | 0.8728 | 0.873 | | 0.0956 | 64.43 | 9600 | 0.5407 | 0.8737 | 0.874 | | 0.0902 | 65.77 | 9800 | 0.5391 | 0.8738 | 0.874 | | 0.0944 | 67.11 | 10000 | 0.5416 | 0.8748 | 0.875 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_tf_4-seqsight_4096_512_46M-L32_f", "results": []}]}

mahdibaghbanzadeh/GUE_tf_4-seqsight_4096_512_46M-L32_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_46M", "region:us" ]

null

2024-04-27T01:02:22+00:00

[]

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us

GUE\_tf\_4-seqsight\_4096\_512\_46M-L32\_f ========================================== This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_4096\_512\_46M on the mahdibaghbanzadeh/GUE\_tf\_4 dataset. It achieves the following results on the evaluation set: * Loss: 0.5633 * F1 Score: 0.8590 * Accuracy: 0.859 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

null

peft

# GUE_tf_3-seqsight_4096_512_46M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_tf_3](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_3) dataset. It achieves the following results on the evaluation set: - Loss: 0.5315 - F1 Score: 0.7102 - Accuracy: 0.714 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.6226 | 0.93 | 200 | 0.5869 | 0.6793 | 0.68 | | 0.5993 | 1.87 | 400 | 0.5752 | 0.692 | 0.692 | | 0.591 | 2.8 | 600 | 0.5625 | 0.6920 | 0.693 | | 0.5831 | 3.74 | 800 | 0.5563 | 0.6959 | 0.696 | | 0.577 | 4.67 | 1000 | 0.5522 | 0.6977 | 0.698 | | 0.574 | 5.61 | 1200 | 0.5500 | 0.7049 | 0.705 | | 0.5676 | 6.54 | 1400 | 0.5458 | 0.7045 | 0.705 | | 0.5636 | 7.48 | 1600 | 0.5450 | 0.7120 | 0.712 | | 0.5573 | 8.41 | 1800 | 0.5424 | 0.7060 | 0.706 | | 0.5589 | 9.35 | 2000 | 0.5400 | 0.7207 | 0.721 | | 0.5506 | 10.28 | 2200 | 0.5428 | 0.7069 | 0.707 | | 0.5493 | 11.21 | 2400 | 0.5354 | 0.7245 | 0.725 | | 0.5483 | 12.15 | 2600 | 0.5316 | 0.7176 | 0.719 | | 0.5444 | 13.08 | 2800 | 0.5328 | 0.7232 | 0.725 | | 0.5452 | 14.02 | 3000 | 0.5326 | 0.7201 | 0.72 | | 0.5421 | 14.95 | 3200 | 0.5282 | 0.7258 | 0.726 | | 0.5399 | 15.89 | 3400 | 0.5276 | 0.7306 | 0.731 | | 0.5373 | 16.82 | 3600 | 0.5328 | 0.7191 | 0.719 | | 0.5357 | 17.76 | 3800 | 0.5267 | 0.7308 | 0.732 | | 0.5358 | 18.69 | 4000 | 0.5293 | 0.7160 | 0.716 | | 0.536 | 19.63 | 4200 | 0.5270 | 0.7248 | 0.726 | | 0.5352 | 20.56 | 4400 | 0.5266 | 0.7281 | 0.729 | | 0.5321 | 21.5 | 4600 | 0.5293 | 0.7079 | 0.708 | | 0.529 | 22.43 | 4800 | 0.5266 | 0.7239 | 0.724 | | 0.5304 | 23.36 | 5000 | 0.5281 | 0.7250 | 0.725 | | 0.5283 | 24.3 | 5200 | 0.5289 | 0.7099 | 0.71 | | 0.5249 | 25.23 | 5400 | 0.5245 | 0.7247 | 0.726 | | 0.5307 | 26.17 | 5600 | 0.5234 | 0.7255 | 0.726 | | 0.522 | 27.1 | 5800 | 0.5223 | 0.7278 | 0.729 | | 0.5212 | 28.04 | 6000 | 0.5244 | 0.7169 | 0.717 | | 0.5232 | 28.97 | 6200 | 0.5285 | 0.7181 | 0.718 | | 0.5234 | 29.91 | 6400 | 0.5250 | 0.7268 | 0.727 | | 0.522 | 30.84 | 6600 | 0.5201 | 0.7236 | 0.724 | | 0.5196 | 31.78 | 6800 | 0.5209 | 0.7269 | 0.727 | | 0.5165 | 32.71 | 7000 | 0.5219 | 0.7266 | 0.727 | | 0.523 | 33.64 | 7200 | 0.5196 | 0.7205 | 0.721 | | 0.5156 | 34.58 | 7400 | 0.5252 | 0.7210 | 0.721 | | 0.518 | 35.51 | 7600 | 0.5207 | 0.7210 | 0.721 | | 0.5168 | 36.45 | 7800 | 0.5248 | 0.7190 | 0.719 | | 0.5147 | 37.38 | 8000 | 0.5231 | 0.7221 | 0.722 | | 0.5117 | 38.32 | 8200 | 0.5204 | 0.7262 | 0.727 | | 0.5136 | 39.25 | 8400 | 0.5201 | 0.7226 | 0.723 | | 0.5128 | 40.19 | 8600 | 0.5218 | 0.7220 | 0.722 | | 0.5125 | 41.12 | 8800 | 0.5211 | 0.7228 | 0.723 | | 0.5149 | 42.06 | 9000 | 0.5206 | 0.7239 | 0.724 | | 0.5136 | 42.99 | 9200 | 0.5205 | 0.7230 | 0.723 | | 0.5104 | 43.93 | 9400 | 0.5213 | 0.7191 | 0.719 | | 0.511 | 44.86 | 9600 | 0.5198 | 0.7258 | 0.726 | | 0.5117 | 45.79 | 9800 | 0.5206 | 0.7299 | 0.73 | | 0.5078 | 46.73 | 10000 | 0.5208 | 0.7269 | 0.727 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_tf_3-seqsight_4096_512_46M-L1_f", "results": []}]}

mahdibaghbanzadeh/GUE_tf_3-seqsight_4096_512_46M-L1_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_46M", "region:us" ]

null

2024-04-27T01:02:54+00:00

[]

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us

GUE\_tf\_3-seqsight\_4096\_512\_46M-L1\_f ========================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_4096\_512\_46M on the mahdibaghbanzadeh/GUE\_tf\_3 dataset. It achieves the following results on the evaluation set: * Loss: 0.5315 * F1 Score: 0.7102 * Accuracy: 0.714 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

text-generation

transformers

# Model Card for johnsnowlabs/JSL-MedLlama-3-70B-v2.0 [<img src="https://repository-images.githubusercontent.com/104670986/2e728700-ace4-11ea-9cfc-f3e060b25ddf">](http://www.johnsnowlabs.com) This model is developed by [John Snow Labs](https://www.johnsnowlabs.com/). This model is trained on medical datasets to provide state-of-the-art performance on biomedical benchmarks: [Open Medical LLM Leaderboard](https://huggingface.co/spaces/openlifescienceai/open_medical_llm_leaderboard). This model is available under a [CC-BY-NC-ND](https://creativecommons.org/licenses/by-nc-nd/4.0/deed.en) license and must also conform to this [Acceptable Use Policy](https://huggingface.co/johnsnowlabs). If you need to license this model for commercial use, please contact us at [email protected]. ## 💻 Usage ```python !pip install -qU transformers accelerate from transformers import AutoTokenizer import transformers import torch model = "johnsnowlabs/JSL-MedLlama-3-70B-v2.0" messages = [{"role": "user", "content": "What is a large language model?"}] tokenizer = AutoTokenizer.from_pretrained(model) prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) pipeline = transformers.pipeline( "text-generation", model=model, torch_dtype=torch.float16, device_map="auto", ) outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95) print(outputs[0]["generated_text"]) ``` ## 🏆 Evaluation | Tasks |Version|Filter|n-shot| Metric |Value | |Stderr| |-------------------------------|-------|------|-----:|--------|-----:|---|-----:| |stem |N/A |none | 0|acc |0.7773|± |0.0049| | | |none | 0|acc_norm|0.7505|± |0.0059| | - medmcqa |Yaml |none | 0|acc |0.7413|± |0.0068| | | |none | 0|acc_norm|0.7413|± |0.0068| | - medqa_4options |Yaml |none | 0|acc |0.7808|± |0.0116| | | |none | 0|acc_norm|0.7808|± |0.0116| | - anatomy (mmlu) | 0|none | 0|acc |0.8444|± |0.0313| | - clinical_knowledge (mmlu) | 0|none | 0|acc |0.9245|± |0.0163| | - college_biology (mmlu) | 0|none | 0|acc |0.9375|± |0.0202| | - college_medicine (mmlu) | 0|none | 0|acc |0.8555|± |0.0268| | - medical_genetics (mmlu) | 0|none | 0|acc |0.9300|± |0.0256| | - professional_medicine (mmlu)| 0|none | 0|acc |0.9375|± |0.0147| | - pubmedqa | 1|none | 0|acc |0.7820|± |0.0185| |Groups|Version|Filter|n-shot| Metric |Value | |Stderr| |------|-------|------|-----:|--------|-----:|---|-----:| |stem |N/A |none | 0|acc |0.7773|± |0.0049| | | |none | 0|acc_norm|0.7505|± |0.0059|

{"language": ["en"], "license": "apache-2.0", "library_name": "transformers", "tags": ["medical"]}

johnsnowlabs/JSL-MedLlama-3-70B-v2.0

null

[ "transformers", "safetensors", "llama", "text-generation", "medical", "conversational", "en", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

null

2024-04-27T01:04:43+00:00

[]

[ "en" ]

TAGS #transformers #safetensors #llama #text-generation #medical #conversational #en #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

Model Card for johnsnowlabs/JSL-MedLlama-3-70B-v2.0 =================================================== <img src="URL This model is developed by John Snow Labs. This model is trained on medical datasets to provide state-of-the-art performance on biomedical benchmarks: Open Medical LLM Leaderboard. This model is available under a CC-BY-NC-ND license and must also conform to this Acceptable Use Policy. If you need to license this model for commercial use, please contact us at info@URL. Usage ----- Evaluation ----------

[]

[ "TAGS\n#transformers #safetensors #llama #text-generation #medical #conversational #en #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n" ]

null

# MeliodasExperiment26-7B MeliodasExperiment26-7B is an automated merge created by [Maxime Labonne](https://huggingface.co/mlabonne) using the following configuration. ## 🧩 Configuration ```yaml models: - model: mistralai/Mistral-7B-v0.1 - model: AurelPx/Meliodas-7b-dare - model: yam-peleg/Experiment26-7B merge_method: model_stock base_model: mistralai/Mistral-7B-v0.1 dtype: bfloat16 ``` ## 💻 Usage ```python !pip install -qU transformers accelerate from transformers import AutoTokenizer import transformers import torch model = "automerger/MeliodasExperiment26-7B" messages = [{"role": "user", "content": "What is a large language model?"}] tokenizer = AutoTokenizer.from_pretrained(model) prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) pipeline = transformers.pipeline( "text-generation", model=model, torch_dtype=torch.float16, device_map="auto", ) outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95) print(outputs[0]["generated_text"]) ```

{"license": "apache-2.0", "tags": ["merge", "mergekit", "lazymergekit", "automerger"]}

automerger/MeliodasExperiment26-7B

null

[ "merge", "mergekit", "lazymergekit", "automerger", "license:apache-2.0", "region:us" ]

null

2024-04-27T01:08:31+00:00

[]

TAGS #merge #mergekit #lazymergekit #automerger #license-apache-2.0 #region-us

# MeliodasExperiment26-7B MeliodasExperiment26-7B is an automated merge created by Maxime Labonne using the following configuration. ## Configuration ## Usage

[ "# MeliodasExperiment26-7B\n\nMeliodasExperiment26-7B is an automated merge created by Maxime Labonne using the following configuration.", "## Configuration", "## Usage" ]

[ "TAGS\n#merge #mergekit #lazymergekit #automerger #license-apache-2.0 #region-us \n", "# MeliodasExperiment26-7B\n\nMeliodasExperiment26-7B is an automated merge created by Maxime Labonne using the following configuration.", "## Configuration", "## Usage" ]

text-generation

transformers

<div align="center"> <img width="260px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/BrQCb95lmEIFz79QAmoNA.png"></div> ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/fJIOPJnY6Ff6fUiSIuMEt.png) <div align="center"> <h1>Advancing Open-source Large Language Models in Medical Domain</h1> </div> <p align="center" style="margin-top: 0px;"> <a href="https://colab.research.google.com/drive/1F5oV20InEYeAJGmBwYF9NM_QhLmjBkKJ?usp=sharing"> <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="OpenChat Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 10px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style=" margin-right: 5px;">Online Demo</span> </a> | <a href="https://github.com/openlifescience-ai"> <img src="https://github.githubassets.com/assets/GitHub-Mark-ea2971cee799.png" alt="GitHub Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style=" margin-right: 5px;">GitHub</span> </a> | <a href="#"> <img src="https://github.com/alpayariyak/openchat/blob/master/assets/arxiv-logomark-small-square-border.png?raw=true" alt="ArXiv Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style="margin-right: 5px;">Paper</span> </a> | <a href="https://discord.gg/A5Fjf5zC69"> <img src="https://cloud.githubusercontent.com/assets/6291467/26705903/96c2d66e-477c-11e7-9f4e-f3c0efe96c9a.png" alt="Discord Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text">Discord</span> </a> </p> ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/KGmRE5w2sepNtwsEu8t7K.jpeg) Introducing OpenBioLLM-70B: A State-of-the-Art Open Source Biomedical Large Language Model OpenBioLLM-70B is an advanced open source language model designed specifically for the biomedical domain. Developed by Saama AI Labs, this model leverages cutting-edge techniques to achieve state-of-the-art performance on a wide range of biomedical tasks. 🏥 **Biomedical Specialization**: OpenBioLLM-70B is tailored for the unique language and knowledge requirements of the medical and life sciences fields. It was fine-tuned on a vast corpus of high-quality biomedical data, enabling it to understand and generate text with domain-specific accuracy and fluency. 🎓 **Superior Performance**: With 70 billion parameters, OpenBioLLM-70B outperforms other open source biomedical language models of similar scale. It has also demonstrated better results compared to larger proprietary & open-source models like GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 on biomedical benchmarks. 🧠 **Advanced Training Techniques**: OpenBioLLM-70B builds upon the powerful foundations of the **Meta-Llama-3-70B-Instruct** and [Meta-Llama-3-70B-Instruct](meta-llama/Meta-Llama-3-70B-Instruct) models. It incorporates the DPO dataset and fine-tuning recipe along with a custom diverse medical instruction dataset. Key components of the training pipeline include: <div align="center"> <img width="1200px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/oPchsJsEpQoGcGXVbh7YS.png"> </div> - **Policy Optimization**: [Direct Preference Optimization: Your Language Model is Secretly a Reward Model (DPO)](https://arxiv.org/abs/2305.18290) - **Fine-tuning dataset**: Custom Medical Instruct dataset (We plan to release a sample training dataset in our upcoming paper; please stay updated) This combination of cutting-edge techniques enables OpenBioLLM-70B to align with key capabilities and preferences for biomedical applications. ⚙️ **Release Details**: - **Model Size**: 70 billion parameters - **Quantization**: Optimized quantized versions available [Here](https://huggingface.co/aaditya/OpenBioLLM-70B-GGUF) - **Language(s) (NLP):** en - **Developed By**: [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) from Saama AI Labs - **License:** Meta-Llama License - **Fine-tuned from models:** [Meta-Llama-3-70B-Instruct](meta-llama/Meta-Llama-3-70B-Instruct) - **Resources for more information:** - Paper: Coming soon The model can be fine-tuned for more specialized tasks and datasets as needed. OpenBioLLM-70B represents an important step forward in democratizing advanced language AI for the biomedical community. By leveraging state-of-the-art architectures and training techniques from leading open source efforts like Llama-3, we have created a powerful tool to accelerate innovation and discovery in healthcare and the life sciences. We are excited to share OpenBioLLM-70B with researchers and developers around the world. ### Use with transformers **Important: Please use the exact chat template provided by Llama-3 instruct version. Otherwise there will be a degradation in the performance. The model output can be verbose in rare cases. Please consider setting temperature = 0 to make this happen less.** See the snippet below for usage with Transformers: ```python import transformers import torch model_id = "aaditya/OpenBioLLM-Llama3-70B" pipeline = transformers.pipeline( "text-generation", model=model_id, model_kwargs={"torch_dtype": torch.bfloat16}, device="auto", ) messages = [ {"role": "system", "content": "You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience. Your name is OpenBioLLM, and you were developed by Saama AI Labs. who's willing to help answer the user's query with explanation. In your explanation, leverage your deep medical expertise such as relevant anatomical structures, physiological processes, diagnostic criteria, treatment guidelines, or other pertinent medical concepts. Use precise medical terminology while still aiming to make the explanation clear and accessible to a general audience."}, {"role": "user", "content": "How can i split a 3mg or 4mg waefin pill so i can get a 2.5mg pill?"}, ] prompt = pipeline.tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) terminators = [ pipeline.tokenizer.eos_token_id, pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>") ] outputs = pipeline( prompt, max_new_tokens=256, eos_token_id=terminators, do_sample=True, temperature=0.0, top_p=0.9, ) print(outputs[0]["generated_text"][len(prompt):]) ``` ## **Training procedure** ### **Training hyperparameters** <details> <summary>Click to see details</summary> - learning_rate: 0.0002 - lr_scheduler: cosine - train_batch_size: 12 - eval_batch_size: 8 - GPU: H100 80GB SXM5 - num_devices: 8 - optimizer: adamw_bnb_8bit - lr_scheduler_warmup_steps: 100 - num_epochs: 4 </details> ### **Peft hyperparameters** <details> <summary>Click to see details</summary> - adapter: qlora - lora_r: 128 - lora_alpha: 256 - lora_dropout: 0.05 - lora_target_linear: true -lora_target_modules: - q_proj - v_proj - k_proj - o_proj - gate_proj - down_proj - up_proj </details> ### **Training results** ### **Framework versions** - Transformers 4.39.3 - Pytorch 2.1.2+cu121 - Datasets 2.18.0 - Tokenizers 0.15.1 - Axolotl - Lm harness for evaluation # Benchmark Results 🔥 OpenBioLLM-70B demonstrates superior performance compared to larger models, such as GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 across 9 diverse biomedical datasets, achieving state-of-the-art results with an average score of 86.06%, despite having a significantly smaller parameter count. The model's strong performance in domain-specific tasks, such as Clinical KG, Medical Genetics, and PubMedQA, highlights its ability to effectively capture and apply biomedical knowledge. 🚨 The GPT-4, Med-PaLM-1, and Med-PaLM-2 results are taken from their official papers. Since Med-PaLM doesn't provide zero-shot accuracy, we are using 5-shot accuracy from their paper for comparison. All results presented are in the zero-shot setting, except for Med-PaLM-2 and Med-PaLM-1, which use 5-shot accuracy. | | Clinical KG | Medical Genetics | Anatomy | Pro Medicine | College Biology | College Medicine | MedQA 4 opts | PubMedQA | MedMCQA | Avg | |--------------------|-------------|------------------|---------|--------------|-----------------|------------------|--------------|----------|---------|-------| | **OpenBioLLM-70B** | **92.93** | **93.197** | **83.904** | 93.75 | 93.827 | **85.749** | 78.162 | 78.97 | **74.014** | **86.05588** | | Med-PaLM-2 (5-shot) | 88.3 | 90 | 77.8 | **95.2** | 94.4 | 80.9 | **79.7** | **79.2** | 71.3 | 84.08 | | **GPT-4** | 86.04 | 91 | 80 | 93.01 | **95.14** | 76.88 | 78.87 | 75.2 | 69.52 | 82.85 | | Med-PaLM-1 (Flan-PaLM, 5-shot) | 80.4 | 75 | 63.7 | 83.8 | 88.9 | 76.3 | 67.6 | 79 | 57.6 | 74.7 | | **OpenBioLLM-8B** | 76.101 | 86.1 | 69.829 | 78.21 | 84.213 | 68.042 | 58.993 | 74.12 | 56.913 | 72.502 | | Gemini-1.0 | 76.7 | 75.8 | 66.7 | 77.7 | 88 | 69.2 | 58 | 70.7 | 54.3 | 70.79 | | GPT-3.5 Turbo 1106 | 74.71 | 74 | 72.79 | 72.79 | 72.91 | 64.73 | 57.71 | 72.66 | 53.79 | 66 | | Meditron-70B | 66.79 | 69 | 53.33 | 71.69 | 76.38 | 63 | 57.1 | 76.6 | 46.85 | 64.52 | | gemma-7b | 69.81 | 70 | 59.26 | 66.18 | 79.86 | 60.12 | 47.21 | 76.2 | 48.96 | 64.18 | | Mistral-7B-v0.1 | 68.68 | 71 | 55.56 | 68.38 | 68.06 | 59.54 | 50.82 | 75.4 | 48.2 | 62.85 | | Apollo-7B | 62.26 | 72 | 61.48 | 69.12 | 70.83 | 55.49 | 55.22 | 39.8 | 53.77 | 60 | | MedAlpaca-7b | 57.36 | 69 | 57.04 | 67.28 | 65.28 | 54.34 | 41.71 | 72.8 | 37.51 | 58.03 | | BioMistral-7B | 59.9 | 64 | 56.5 | 60.4 | 59 | 54.7 | 50.6 | 77.5 | 48.1 | 57.3 | | AlpaCare-llama2-7b | 49.81 | 49 | 45.92 | 33.82 | 50 | 43.35 | 29.77 | 72.2 | 34.42 | 45.36 | | ClinicalGPT | 30.56 | 27 | 30.37 | 19.48 | 25 | 24.27 | 26.08 | 63.8 | 28.18 | 30.52 | <div align="center"> <img width="1600px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/_SzdcJSBjZyo8RS1bTEkP.png"> </div> ## Detailed Medical Subjectwise accuracy ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/UXF-V0col0Z0sS6BGPBkE.png) # Use Cases & Examples 🚨 **Below results are from the quantized version of OpenBioLLM-70B # Summarize Clinical Notes OpenBioLLM-70B can efficiently analyze and summarize complex clinical notes, EHR data, and discharge summaries, extracting key information and generating concise, structured summaries ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/xdwdBgOxNi_TfML0hKlI8.png) # Answer Medical Questions OpenBioLLM-70B can provide answers to a wide range of medical questions. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/zO95GlwOQEZqCKQF69mE6.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/OKBczKw7gWeW5xsuDpc27.png) <details> <summary>Click to see details</summary> ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/eJGHT5khppYvJb8fQ-YW4.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/Cnbwrqa_-ORHRuNRC2P6Y.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/J9DhdcvukAc9mnnW9fj2C.png) </details> # Clinical Entity Recognition OpenBioLLM-70B can perform advanced clinical entity recognition by identifying and extracting key medical concepts, such as diseases, symptoms, medications, procedures, and anatomical structures, from unstructured clinical text. By leveraging its deep understanding of medical terminology and context, the model can accurately annotate and categorize clinical entities, enabling more efficient information retrieval, data analysis, and knowledge discovery from electronic health records, research articles, and other biomedical text sources. This capability can support various downstream applications, such as clinical decision support, pharmacovigilance, and medical research. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/_69BW4k9LVABFwtxixL45.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/DKy5wYCoPhoPPUc1-x8_J.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/7WD9zCCBZT4-4XlfnIQjl.png) # Biomarkers Extraction ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/ZttoM4AiteT7gFYVhjIpN.png) # Classification OpenBioLLM-70B can perform various biomedical classification tasks, such as disease prediction, sentiment analysis, medical document categorization ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/Bf5MW1d75qT-1F_TR_hC0.png) # De-Identification OpenBioLLM-70B can detect and remove personally identifiable information (PII) from medical records, ensuring patient privacy and compliance with data protection regulations like HIPAA. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/hKX4kzm--Tw5bj6K78msy.png) **Advisory Notice!** While OpenBioLLM-70B leverages high-quality data sources, its outputs may still contain inaccuracies, biases, or misalignments that could pose risks if relied upon for medical decision-making without further testing and refinement. The model's performance has not yet been rigorously evaluated in randomized controlled trials or real-world healthcare environments. Therefore, we strongly advise against using OpenBioLLM-70B for any direct patient care, clinical decision support, or other professional medical purposes at this time. Its use should be limited to research, development, and exploratory applications by qualified individuals who understand its limitations. OpenBioLLM-70B is intended solely as a research tool to assist healthcare professionals and should never be considered a replacement for the professional judgment and expertise of a qualified medical doctor. Appropriately adapting and validating OpenBioLLM-70B for specific medical use cases would require significant additional work, potentially including: - Thorough testing and evaluation in relevant clinical scenarios - Alignment with evidence-based guidelines and best practices - Mitigation of potential biases and failure modes - Integration with human oversight and interpretation - Compliance with regulatory and ethical standards Always consult a qualified healthcare provider for personal medical needs. # Citation If you find OpenBioLLM-70B & 8B useful in your work, please cite the model as follows: ``` @misc{OpenBioLLMs, author = {Ankit Pal, Malaikannan Sankarasubbu}, title = {OpenBioLLMs: Advancing Open-Source Large Language Models for Healthcare and Life Sciences}, year = {2024}, publisher = {Hugging Face}, journal = {Hugging Face repository}, howpublished = {\url{https://huggingface.co/aaditya/OpenBioLLM-Llama3-70B}} } ``` The accompanying paper is currently in progress and will be released soon. <div align="center"> <h2> 💌 Contact </h2> </div> We look forward to hearing you and collaborating on this exciting project! **Contributors:** - [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) [aadityaura at gmail dot com] - Saama AI Labs - Note: I am looking for a funded PhD opportunity, especially if it fits my Responsible Generative AI, Multimodal LLMs, Geometric Deep Learning, and Healthcare AI skillset. # References We thank the [Meta Team](meta-llama/Meta-Llama-3-70B-Instruct) for their amazing models! Result sources - [1] GPT-4 [Capabilities of GPT-4 on Medical Challenge Problems] (https://arxiv.org/abs/2303.13375) - [2] Med-PaLM-1 [Large Language Models Encode Clinical Knowledge](https://arxiv.org/abs/2212.13138) - [3] Med-PaLM-2 [Towards Expert-Level Medical Question Answering with Large Language Models](https://arxiv.org/abs/2305.09617) - [4] Gemini-1.0 [Gemini Goes to Med School](https://arxiv.org/abs/2402.07023)

{"language": ["en"], "license": "llama3", "tags": ["llama-3", "llama", "Mixtral", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "distillation"], "base_model": "meta-llama/Meta-Llama-3-70B-Instruct", "widget": [{"example_title": "OpenBioLLM-70B", "messages": [{"role": "system", "content": "You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience."}, {"role": "user", "content": "How long does it take for newborn jaundice to go away?"}], "output": {"text": "Newborn jaundice, also known as neonatal jaundice, is a common condition in newborns where the yellowing of the skin and eyes occurs due to an elevated level of bilirubin in the blood. Bilirubin is a yellow pigment that forms when red blood cells break down. In most cases, newborn jaundice resolves on its own without any specific treatment.\nThe duration of newborn jaundice can vary depending on several factors such as the underlying cause, gestational age at birth, and individual variations in bilirubin metabolism. Here are some general guidelines:\n1. Physiological jaundice: This is the most common type of newborn jaundice and usually appears within 24-72 hours after birth. It tends to peak between the second and fifth day of life and gradually improves over the next week or two. By the time the baby is one week old, the jaundice should have mostly resolved. 2. Breast milk jaundice: This type of jaundice occurs in breastfed babies and may appear later than physiological jaundice, typically between the fifth and fourteenth day of life. It tends to persist for a longer duration but usually resolves within six weeks after birth. 3. Pathological jaundice: This type of jaundice is less common and occurs due to an underlying medical condition that affects bilirubin metabolism or liver function. The duration of pathological jaundice depends on the specific cause and may require treatment.\nIt's important for parents to monitor their newborn's jaundice closely and seek medical advice if the jaundice progresses rapidly, becomes severe, or is accompanied by other symptoms such as poor feeding, lethargy, or excessive sleepiness. In these cases, further evaluation and management may be necessary. Remember that each baby is unique, and the timing of jaundice resolution can vary. If you have concerns about your newborn's jaundice, it's always best to consult with a healthcare professional for personalized advice and guidance."}}], "model-index": [{"name": "OpenBioLLM-70B", "results": []}]}

LoneStriker/OpenBioLLM-Llama3-70B-2.4bpw-h6-exl2

null

[ "transformers", "pytorch", "llama", "text-generation", "llama-3", "Mixtral", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "distillation", "conversational", "en", "arxiv:2305.18290", "arxiv:2303.13375", "arxiv:2212.13138", "arxiv:2305.09617", "arxiv:2402.07023", "base_model:meta-llama/Meta-Llama-3-70B-Instruct", "license:llama3", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

null

2024-04-27T01:08:34+00:00

[ "2305.18290", "2303.13375", "2212.13138", "2305.09617", "2402.07023" ]

[ "en" ]

TAGS #transformers #pytorch #llama #text-generation #llama-3 #Mixtral #instruct #finetune #chatml #DPO #RLHF #gpt4 #distillation #conversational #en #arxiv-2305.18290 #arxiv-2303.13375 #arxiv-2212.13138 #arxiv-2305.09617 #arxiv-2402.07023 #base_model-meta-llama/Meta-Llama-3-70B-Instruct #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

![](URL <p>!image/png</p> <div align=) Advancing Open-source Large Language Models in Medical Domain ============================================================= Online Demo | GitHub | [![](URL alt=)](#) | Discord !image/jpeg Introducing OpenBioLLM-70B: A State-of-the-Art Open Source Biomedical Large Language Model OpenBioLLM-70B is an advanced open source language model designed specifically for the biomedical domain. Developed by Saama AI Labs, this model leverages cutting-edge techniques to achieve state-of-the-art performance on a wide range of biomedical tasks. Biomedical Specialization: OpenBioLLM-70B is tailored for the unique language and knowledge requirements of the medical and life sciences fields. It was fine-tuned on a vast corpus of high-quality biomedical data, enabling it to understand and generate text with domain-specific accuracy and fluency. Superior Performance: With 70 billion parameters, OpenBioLLM-70B outperforms other open source biomedical language models of similar scale. It has also demonstrated better results compared to larger proprietary & open-source models like GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 on biomedical benchmarks. Advanced Training Techniques: OpenBioLLM-70B builds upon the powerful foundations of the Meta-Llama-3-70B-Instruct and Meta-Llama-3-70B-Instruct models. It incorporates the DPO dataset and fine-tuning recipe along with a custom diverse medical instruction dataset. Key components of the training pipeline include: ![](URL </div> <ul> <li>Policy Optimization: Direct Preference Optimization: Your Language Model is Secretly a Reward Model (DPO)</li> <li>Fine-tuning dataset: Custom Medical Instruct dataset (We plan to release a sample training dataset in our upcoming paper; please stay updated)</li> </ul> <p>This combination of cutting-edge techniques enables OpenBioLLM-70B to align with key capabilities and preferences for biomedical applications.</p> <p>️ Release Details:</p> <ul> <li>Model Size: 70 billion parameters</li> <li>Quantization: Optimized quantized versions available Here</li> <li>Language(s) (NLP): en</li> <li>Developed By: Ankit Pal (Aaditya Ura) from Saama AI Labs</li> <li>License: Meta-Llama License</li> <li>Fine-tuned from models: Meta-Llama-3-70B-Instruct</li> <li>Resources for more information: <ul> <li>Paper: Coming soon</li> </ul> </li> </ul> <p>The model can be fine-tuned for more specialized tasks and datasets as needed.</p> <p>OpenBioLLM-70B represents an important step forward in democratizing advanced language AI for the biomedical community. By leveraging state-of-the-art architectures and training techniques from leading open source efforts like Llama-3, we have created a powerful tool to accelerate innovation and discovery in healthcare and the life sciences.</p> <p>We are excited to share OpenBioLLM-70B with researchers and developers around the world.</p> <h3>Use with transformers</h3> <p>Important: Please use the exact chat template provided by Llama-3 instruct version. Otherwise there will be a degradation in the performance. The model output can be verbose in rare cases. Please consider setting temperature = 0 to make this happen less.</p> <p>See the snippet below for usage with Transformers:</p> <h2>Training procedure</h2> <h3>Training hyperparameters</h3> <details> <summary>Click to see details</summary> <ul> <li>learning_rate: 0.0002</li> <li>lr_scheduler: cosine</li> <li>train_batch_size: 12</li> <li>eval_batch_size: 8</li> <li>GPU: H100 80GB SXM5</li> <li>num_devices: 8</li> <li>optimizer: adamw_bnb_8bit</li> <li>lr_scheduler_warmup_steps: 100</li> <li>num_epochs: 4</li> </ul> </details> <h3>Peft hyperparameters</h3> <details> <summary>Click to see details</summary> <ul> <li>adapter: qlora</li> <li>lora_r: 128</li> <li>lora_alpha: 256</li> <li>lora_dropout: 0.05</li> <li>lora_target_linear: true</li> </ul> <p>-lora_target_modules:</p> <ul> <li>q_proj</li> <li>v_proj</li> <li>k_proj</li> <li>o_proj</li> <li>gate_proj</li> <li>down_proj</li> <li>up_proj</li> </ul> </details> <h3>Training results</h3> <h3>Framework versions</h3> <ul> <li>Transformers 4.39.3</li> <li>Pytorch 2.1.2+cu121</li> <li>Datasets 2.18.0</li> <li>Tokenizers 0.15.1</li> <li>Axolotl</li> <li>Lm harness for evaluation</li> </ul> <h1>Benchmark Results</h1> <p>OpenBioLLM-70B demonstrates superior performance compared to larger models, such as GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 across 9 diverse biomedical datasets, achieving state-of-the-art results with an average score of 86.06%, despite having a significantly smaller parameter count. The model's strong performance in domain-specific tasks, such as Clinical KG, Medical Genetics, and PubMedQA, highlights its ability to effectively capture and apply biomedical knowledge.</p> <p>The GPT-4, Med-PaLM-1, and Med-PaLM-2 results are taken from their official papers. Since Med-PaLM doesn't provide zero-shot accuracy, we are using 5-shot accuracy from their paper for comparison. All results presented are in the zero-shot setting, except for Med-PaLM-2 and Med-PaLM-1, which use 5-shot accuracy.</p> <p></p> <div align=) ![](URL </div> <h2>Detailed Medical Subjectwise accuracy</h2> <p>!image/png</p> <h1>Use Cases & Examples</h1> <p>Below results are from the quantized version of OpenBioLLM-70B</p> <h1>Summarize Clinical Notes</h1> <p>OpenBioLLM-70B can efficiently analyze and summarize complex clinical notes, EHR data, and discharge summaries, extracting key information and generating concise, structured summaries</p> <p>!image/png</p> <h1>Answer Medical Questions</h1> <p>OpenBioLLM-70B can provide answers to a wide range of medical questions.</p> <p>!image/png !image/png</p> <details> <summary>Click to see details</summary> <p>!image/png !image/png !image/png</p> </details> <h1>Clinical Entity Recognition</h1> <p>OpenBioLLM-70B can perform advanced clinical entity recognition by identifying and extracting key medical concepts, such as diseases, symptoms, medications, procedures, and anatomical structures, from unstructured clinical text. By leveraging its deep understanding of medical terminology and context, the model can accurately annotate and categorize clinical entities, enabling more efficient information retrieval, data analysis, and knowledge discovery from electronic health records, research articles, and other biomedical text sources. This capability can support various downstream applications, such as clinical decision support, pharmacovigilance, and medical research.</p> <p>!image/png !image/png !image/png</p> <h1>Biomarkers Extraction</h1> <p>!image/png</p> <h1>Classification</h1> <p>OpenBioLLM-70B can perform various biomedical classification tasks, such as disease prediction, sentiment analysis, medical document categorization</p> <p>!image/png</p> <h1>De-Identification</h1> <p>OpenBioLLM-70B can detect and remove personally identifiable information (PII) from medical records, ensuring patient privacy and compliance with data protection regulations like HIPAA.</p> <p>!image/png</p> <p>Advisory Notice!</p> <p>While OpenBioLLM-70B leverages high-quality data sources, its outputs may still contain inaccuracies, biases, or misalignments that could pose risks if relied upon for medical decision-making without further testing and refinement. The model's performance has not yet been rigorously evaluated in randomized controlled trials or real-world healthcare environments.</p> <p>Therefore, we strongly advise against using OpenBioLLM-70B for any direct patient care, clinical decision support, or other professional medical purposes at this time. Its use should be limited to research, development, and exploratory applications by qualified individuals who understand its limitations. OpenBioLLM-70B is intended solely as a research tool to assist healthcare professionals and should never be considered a replacement for the professional judgment and expertise of a qualified medical doctor.</p> <p>Appropriately adapting and validating OpenBioLLM-70B for specific medical use cases would require significant additional work, potentially including:</p> <ul> <li>Thorough testing and evaluation in relevant clinical scenarios</li> <li>Alignment with evidence-based guidelines and best practices</li> <li>Mitigation of potential biases and failure modes</li> <li>Integration with human oversight and interpretation</li> <li>Compliance with regulatory and ethical standards</li> </ul> <p>Always consult a qualified healthcare provider for personal medical needs.</p> <p>If you find OpenBioLLM-70B & 8B useful in your work, please cite the model as follows:</p> <p>The accompanying paper is currently in progress and will be released soon.</p> <div align=) Contact -------- We look forward to hearing you and collaborating on this exciting project! Contributors: * Ankit Pal (Aaditya Ura) [aadityaura at gmail dot com] * Saama AI Labs * Note: I am looking for a funded PhD opportunity, especially if it fits my Responsible Generative AI, Multimodal LLMs, Geometric Deep Learning, and Healthcare AI skillset. References ========== We thank the Meta Team for their amazing models! Result sources * [1] GPT-4 [Capabilities of GPT-4 on Medical Challenge Problems] (URL * [2] Med-PaLM-1 Large Language Models Encode Clinical Knowledge * [3] Med-PaLM-2 Towards Expert-Level Medical Question Answering with Large Language Models * [4] Gemini-1.0 Gemini Goes to Med School

[]

[ "TAGS\n#transformers #pytorch #llama #text-generation #llama-3 #Mixtral #instruct #finetune #chatml #DPO #RLHF #gpt4 #distillation #conversational #en #arxiv-2305.18290 #arxiv-2303.13375 #arxiv-2212.13138 #arxiv-2305.09617 #arxiv-2402.07023 #base_model-meta-llama/Meta-Llama-3-70B-Instruct #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n" ]

null

peft

# GUE_tf_3-seqsight_4096_512_46M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_tf_3](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_3) dataset. It achieves the following results on the evaluation set: - Loss: 0.5223 - F1 Score: 0.7373 - Accuracy: 0.739 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.6108 | 0.93 | 200 | 0.5608 | 0.6923 | 0.693 | | 0.5825 | 1.87 | 400 | 0.5563 | 0.7069 | 0.707 | | 0.5685 | 2.8 | 600 | 0.5375 | 0.7158 | 0.716 | | 0.5571 | 3.74 | 800 | 0.5398 | 0.7010 | 0.701 | | 0.549 | 4.67 | 1000 | 0.5198 | 0.7276 | 0.728 | | 0.5494 | 5.61 | 1200 | 0.5403 | 0.7126 | 0.713 | | 0.56 | 6.54 | 1400 | 0.5349 | 0.7261 | 0.726 | | 0.5408 | 7.48 | 1600 | 0.5267 | 0.7380 | 0.739 | | 0.5303 | 8.41 | 1800 | 0.5230 | 0.7210 | 0.721 | | 0.526 | 9.35 | 2000 | 0.5232 | 0.7299 | 0.732 | | 0.5144 | 10.28 | 2200 | 0.5267 | 0.7450 | 0.745 | | 0.5123 | 11.21 | 2400 | 0.5370 | 0.7337 | 0.735 | | 0.5033 | 12.15 | 2600 | 0.5448 | 0.7354 | 0.738 | | 0.4978 | 13.08 | 2800 | 0.5457 | 0.7251 | 0.73 | | 0.4941 | 14.02 | 3000 | 0.5301 | 0.7247 | 0.725 | | 0.4876 | 14.95 | 3200 | 0.5307 | 0.7329 | 0.734 | | 0.4826 | 15.89 | 3400 | 0.5366 | 0.7454 | 0.746 | | 0.4758 | 16.82 | 3600 | 0.5519 | 0.7237 | 0.724 | | 0.4688 | 17.76 | 3800 | 0.5397 | 0.7368 | 0.737 | | 0.4654 | 18.69 | 4000 | 0.5552 | 0.7381 | 0.738 | | 0.4639 | 19.63 | 4200 | 0.5405 | 0.7293 | 0.731 | | 0.4603 | 20.56 | 4400 | 0.5599 | 0.7334 | 0.734 | | 0.4531 | 21.5 | 4600 | 0.5641 | 0.7199 | 0.72 | | 0.4439 | 22.43 | 4800 | 0.5755 | 0.7261 | 0.726 | | 0.445 | 23.36 | 5000 | 0.5866 | 0.7261 | 0.726 | | 0.4357 | 24.3 | 5200 | 0.5901 | 0.7194 | 0.72 | | 0.4346 | 25.23 | 5400 | 0.5861 | 0.7320 | 0.732 | | 0.432 | 26.17 | 5600 | 0.5853 | 0.7281 | 0.729 | | 0.4265 | 27.1 | 5800 | 0.5771 | 0.7338 | 0.734 | | 0.4206 | 28.04 | 6000 | 0.5928 | 0.7286 | 0.729 | | 0.4202 | 28.97 | 6200 | 0.5858 | 0.7271 | 0.727 | | 0.4166 | 29.91 | 6400 | 0.5868 | 0.7288 | 0.729 | | 0.4071 | 30.84 | 6600 | 0.5710 | 0.7360 | 0.737 | | 0.4075 | 31.78 | 6800 | 0.5829 | 0.7309 | 0.731 | | 0.3999 | 32.71 | 7000 | 0.5909 | 0.7318 | 0.732 | | 0.3992 | 33.64 | 7200 | 0.5878 | 0.7334 | 0.734 | | 0.396 | 34.58 | 7400 | 0.6131 | 0.726 | 0.726 | | 0.3995 | 35.51 | 7600 | 0.6044 | 0.7311 | 0.731 | | 0.394 | 36.45 | 7800 | 0.6331 | 0.7281 | 0.728 | | 0.3908 | 37.38 | 8000 | 0.6152 | 0.7338 | 0.734 | | 0.3844 | 38.32 | 8200 | 0.6255 | 0.7268 | 0.727 | | 0.3858 | 39.25 | 8400 | 0.6303 | 0.7271 | 0.727 | | 0.3823 | 40.19 | 8600 | 0.6294 | 0.7300 | 0.73 | | 0.3774 | 41.12 | 8800 | 0.6246 | 0.7296 | 0.73 | | 0.3794 | 42.06 | 9000 | 0.6387 | 0.7329 | 0.733 | | 0.3797 | 42.99 | 9200 | 0.6269 | 0.7280 | 0.728 | | 0.3781 | 43.93 | 9400 | 0.6261 | 0.7280 | 0.728 | | 0.3771 | 44.86 | 9600 | 0.6308 | 0.7369 | 0.737 | | 0.3733 | 45.79 | 9800 | 0.6318 | 0.7350 | 0.735 | | 0.3734 | 46.73 | 10000 | 0.6363 | 0.7370 | 0.737 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_tf_3-seqsight_4096_512_46M-L32_f", "results": []}]}

mahdibaghbanzadeh/GUE_tf_3-seqsight_4096_512_46M-L32_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_46M", "region:us" ]

null

2024-04-27T01:09:05+00:00

[]

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us

GUE\_tf\_3-seqsight\_4096\_512\_46M-L32\_f ========================================== This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_4096\_512\_46M on the mahdibaghbanzadeh/GUE\_tf\_3 dataset. It achieves the following results on the evaluation set: * Loss: 0.5223 * F1 Score: 0.7373 * Accuracy: 0.739 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

null

peft

# GUE_tf_3-seqsight_4096_512_46M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_tf_3](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_3) dataset. It achieves the following results on the evaluation set: - Loss: 0.5282 - F1 Score: 0.7300 - Accuracy: 0.733 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.6154 | 0.93 | 200 | 0.5729 | 0.6841 | 0.684 | | 0.589 | 1.87 | 400 | 0.5770 | 0.6839 | 0.685 | | 0.5798 | 2.8 | 600 | 0.5512 | 0.7087 | 0.709 | | 0.5697 | 3.74 | 800 | 0.5494 | 0.7090 | 0.709 | | 0.5615 | 4.67 | 1000 | 0.5368 | 0.7056 | 0.706 | | 0.5596 | 5.61 | 1200 | 0.5311 | 0.7168 | 0.718 | | 0.5522 | 6.54 | 1400 | 0.5327 | 0.7135 | 0.714 | | 0.5454 | 7.48 | 1600 | 0.5327 | 0.7259 | 0.726 | | 0.5423 | 8.41 | 1800 | 0.5324 | 0.7204 | 0.721 | | 0.5427 | 9.35 | 2000 | 0.5291 | 0.7278 | 0.729 | | 0.5336 | 10.28 | 2200 | 0.5332 | 0.7271 | 0.727 | | 0.5328 | 11.21 | 2400 | 0.5336 | 0.7270 | 0.728 | | 0.529 | 12.15 | 2600 | 0.5335 | 0.7315 | 0.734 | | 0.5253 | 13.08 | 2800 | 0.5434 | 0.7352 | 0.74 | | 0.5254 | 14.02 | 3000 | 0.5290 | 0.7342 | 0.735 | | 0.5218 | 14.95 | 3200 | 0.5234 | 0.7374 | 0.739 | | 0.5188 | 15.89 | 3400 | 0.5281 | 0.7245 | 0.725 | | 0.5138 | 16.82 | 3600 | 0.5324 | 0.7216 | 0.722 | | 0.5121 | 17.76 | 3800 | 0.5307 | 0.7321 | 0.733 | | 0.5101 | 18.69 | 4000 | 0.5323 | 0.7181 | 0.718 | | 0.5105 | 19.63 | 4200 | 0.5319 | 0.7356 | 0.737 | | 0.5089 | 20.56 | 4400 | 0.5318 | 0.7387 | 0.74 | | 0.505 | 21.5 | 4600 | 0.5371 | 0.7210 | 0.721 | | 0.4987 | 22.43 | 4800 | 0.5385 | 0.7294 | 0.73 | | 0.5028 | 23.36 | 5000 | 0.5404 | 0.7281 | 0.728 | | 0.4989 | 24.3 | 5200 | 0.5474 | 0.7233 | 0.724 | | 0.494 | 25.23 | 5400 | 0.5340 | 0.7340 | 0.735 | | 0.498 | 26.17 | 5600 | 0.5314 | 0.7328 | 0.734 | | 0.4909 | 27.1 | 5800 | 0.5373 | 0.7275 | 0.728 | | 0.4893 | 28.04 | 6000 | 0.5386 | 0.7297 | 0.73 | | 0.4903 | 28.97 | 6200 | 0.5429 | 0.7150 | 0.715 | | 0.4912 | 29.91 | 6400 | 0.5367 | 0.7233 | 0.724 | | 0.4869 | 30.84 | 6600 | 0.5278 | 0.7353 | 0.736 | | 0.4845 | 31.78 | 6800 | 0.5310 | 0.7338 | 0.734 | | 0.4836 | 32.71 | 7000 | 0.5335 | 0.7375 | 0.738 | | 0.4839 | 33.64 | 7200 | 0.5342 | 0.7209 | 0.721 | | 0.4788 | 34.58 | 7400 | 0.5403 | 0.7180 | 0.718 | | 0.4833 | 35.51 | 7600 | 0.5345 | 0.7190 | 0.719 | | 0.4801 | 36.45 | 7800 | 0.5404 | 0.7220 | 0.722 | | 0.4782 | 37.38 | 8000 | 0.5353 | 0.7308 | 0.731 | | 0.4756 | 38.32 | 8200 | 0.5350 | 0.7366 | 0.737 | | 0.4741 | 39.25 | 8400 | 0.5389 | 0.7359 | 0.736 | | 0.4746 | 40.19 | 8600 | 0.5369 | 0.7318 | 0.732 | | 0.4745 | 41.12 | 8800 | 0.5377 | 0.7328 | 0.733 | | 0.4741 | 42.06 | 9000 | 0.5390 | 0.7280 | 0.728 | | 0.4745 | 42.99 | 9200 | 0.5382 | 0.7260 | 0.726 | | 0.472 | 43.93 | 9400 | 0.5387 | 0.7251 | 0.725 | | 0.4707 | 44.86 | 9600 | 0.5377 | 0.7300 | 0.73 | | 0.4701 | 45.79 | 9800 | 0.5391 | 0.728 | 0.728 | | 0.4677 | 46.73 | 10000 | 0.5395 | 0.7290 | 0.729 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_tf_3-seqsight_4096_512_46M-L8_f", "results": []}]}

mahdibaghbanzadeh/GUE_tf_3-seqsight_4096_512_46M-L8_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_46M", "region:us" ]

null

2024-04-27T01:09:05+00:00

[]

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us

GUE\_tf\_3-seqsight\_4096\_512\_46M-L8\_f ========================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_4096\_512\_46M on the mahdibaghbanzadeh/GUE\_tf\_3 dataset. It achieves the following results on the evaluation set: * Loss: 0.5282 * F1 Score: 0.7300 * Accuracy: 0.733 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

text-generation

transformers

# 0.001_4iters_bs256_nodpo_only4w_userresponse_iter_4 This model is a fine-tuned version of [ShenaoZhang/0.001_4iters_bs256_nodpo_only4w_userresponse_iter_3](https://huggingface.co/ShenaoZhang/0.001_4iters_bs256_nodpo_only4w_userresponse_iter_3) on the updated and the original datasets. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-07 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - distributed_type: multi-GPU - num_devices: 8 - gradient_accumulation_steps: 4 - total_train_batch_size: 256 - total_eval_batch_size: 64 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 1 ### Training results ### Framework versions - Transformers 4.40.0 - Pytorch 2.1.2+cu121 - Datasets 2.14.6 - Tokenizers 0.19.1

{"license": "mit", "tags": ["alignment-handbook", "trl", "dpo", "generated_from_trainer", "trl", "dpo", "generated_from_trainer"], "datasets": ["updated", "original"], "base_model": "ShenaoZhang/0.001_4iters_bs256_nodpo_only4w_userresponse_iter_3", "model-index": [{"name": "0.001_4iters_bs256_nodpo_only4w_userresponse_iter_4", "results": []}]}

ShenaoZhang/0.001_4iters_bs256_nodpo_only4w_userresponse_iter_4

null

[ "transformers", "safetensors", "mistral", "text-generation", "alignment-handbook", "trl", "dpo", "generated_from_trainer", "conversational", "dataset:updated", "dataset:original", "base_model:ShenaoZhang/0.001_4iters_bs256_nodpo_only4w_userresponse_iter_3", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

null

2024-04-27T01:10:49+00:00

[]

TAGS #transformers #safetensors #mistral #text-generation #alignment-handbook #trl #dpo #generated_from_trainer #conversational #dataset-updated #dataset-original #base_model-ShenaoZhang/0.001_4iters_bs256_nodpo_only4w_userresponse_iter_3 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

# 0.001_4iters_bs256_nodpo_only4w_userresponse_iter_4 This model is a fine-tuned version of ShenaoZhang/0.001_4iters_bs256_nodpo_only4w_userresponse_iter_3 on the updated and the original datasets. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-07 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - distributed_type: multi-GPU - num_devices: 8 - gradient_accumulation_steps: 4 - total_train_batch_size: 256 - total_eval_batch_size: 64 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 1 ### Training results ### Framework versions - Transformers 4.40.0 - Pytorch 2.1.2+cu121 - Datasets 2.14.6 - Tokenizers 0.19.1

[ "# 0.001_4iters_bs256_nodpo_only4w_userresponse_iter_4\n\nThis model is a fine-tuned version of ShenaoZhang/0.001_4iters_bs256_nodpo_only4w_userresponse_iter_3 on the updated and the original datasets.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #alignment-handbook #trl #dpo #generated_from_trainer #conversational #dataset-updated #dataset-original #base_model-ShenaoZhang/0.001_4iters_bs256_nodpo_only4w_userresponse_iter_3 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# 0.001_4iters_bs256_nodpo_only4w_userresponse_iter_4\n\nThis model is a fine-tuned version of ShenaoZhang/0.001_4iters_bs256_nodpo_only4w_userresponse_iter_3 on the updated and the original datasets.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.19.1" ]

null

peft

# GUE_tf_2-seqsight_4096_512_46M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_tf_2](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_2) dataset. It achieves the following results on the evaluation set: - Loss: 0.4291 - F1 Score: 0.7986 - Accuracy: 0.799 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.5673 | 1.34 | 200 | 0.5263 | 0.7249 | 0.726 | | 0.5317 | 2.68 | 400 | 0.5122 | 0.7597 | 0.76 | | 0.5187 | 4.03 | 600 | 0.5044 | 0.7569 | 0.757 | | 0.5111 | 5.37 | 800 | 0.4975 | 0.7610 | 0.761 | | 0.507 | 6.71 | 1000 | 0.4986 | 0.7528 | 0.753 | | 0.498 | 8.05 | 1200 | 0.4975 | 0.7568 | 0.757 | | 0.4929 | 9.4 | 1400 | 0.4913 | 0.7577 | 0.758 | | 0.4904 | 10.74 | 1600 | 0.4857 | 0.7549 | 0.755 | | 0.4838 | 12.08 | 1800 | 0.4980 | 0.7636 | 0.764 | | 0.4827 | 13.42 | 2000 | 0.4954 | 0.7569 | 0.757 | | 0.4799 | 14.77 | 2200 | 0.4875 | 0.7448 | 0.746 | | 0.4719 | 16.11 | 2400 | 0.4951 | 0.7579 | 0.758 | | 0.4755 | 17.45 | 2600 | 0.4845 | 0.7579 | 0.758 | | 0.4659 | 18.79 | 2800 | 0.4827 | 0.7617 | 0.762 | | 0.4668 | 20.13 | 3000 | 0.4839 | 0.7590 | 0.759 | | 0.4635 | 21.48 | 3200 | 0.4930 | 0.7630 | 0.763 | | 0.4629 | 22.82 | 3400 | 0.4865 | 0.7679 | 0.768 | | 0.4582 | 24.16 | 3600 | 0.4818 | 0.7678 | 0.768 | | 0.4549 | 25.5 | 3800 | 0.4871 | 0.7581 | 0.759 | | 0.454 | 26.85 | 4000 | 0.4836 | 0.7614 | 0.762 | | 0.453 | 28.19 | 4200 | 0.4829 | 0.7605 | 0.761 | | 0.4509 | 29.53 | 4400 | 0.4892 | 0.7610 | 0.761 | | 0.4503 | 30.87 | 4600 | 0.4881 | 0.7639 | 0.764 | | 0.4481 | 32.21 | 4800 | 0.4908 | 0.7608 | 0.761 | | 0.4482 | 33.56 | 5000 | 0.4896 | 0.7600 | 0.76 | | 0.4467 | 34.9 | 5200 | 0.4922 | 0.7669 | 0.767 | | 0.4395 | 36.24 | 5400 | 0.4873 | 0.7709 | 0.771 | | 0.4408 | 37.58 | 5600 | 0.4899 | 0.7648 | 0.765 | | 0.441 | 38.93 | 5800 | 0.4909 | 0.7654 | 0.766 | | 0.4376 | 40.27 | 6000 | 0.4887 | 0.7575 | 0.758 | | 0.4365 | 41.61 | 6200 | 0.4922 | 0.7615 | 0.762 | | 0.4366 | 42.95 | 6400 | 0.4944 | 0.7647 | 0.765 | | 0.4332 | 44.3 | 6600 | 0.4940 | 0.7598 | 0.76 | | 0.439 | 45.64 | 6800 | 0.4908 | 0.7649 | 0.765 | | 0.4314 | 46.98 | 7000 | 0.4927 | 0.7637 | 0.764 | | 0.4287 | 48.32 | 7200 | 0.4924 | 0.7629 | 0.763 | | 0.4272 | 49.66 | 7400 | 0.4949 | 0.7647 | 0.765 | | 0.4269 | 51.01 | 7600 | 0.4926 | 0.7637 | 0.764 | | 0.4263 | 52.35 | 7800 | 0.4964 | 0.7577 | 0.758 | | 0.4277 | 53.69 | 8000 | 0.4943 | 0.7582 | 0.759 | | 0.4234 | 55.03 | 8200 | 0.4959 | 0.7579 | 0.758 | | 0.4255 | 56.38 | 8400 | 0.4950 | 0.7599 | 0.76 | | 0.4274 | 57.72 | 8600 | 0.4958 | 0.7535 | 0.754 | | 0.4214 | 59.06 | 8800 | 0.4952 | 0.7547 | 0.755 | | 0.4185 | 60.4 | 9000 | 0.4988 | 0.7588 | 0.759 | | 0.4247 | 61.74 | 9200 | 0.4964 | 0.7577 | 0.758 | | 0.4226 | 63.09 | 9400 | 0.4972 | 0.7618 | 0.762 | | 0.4185 | 64.43 | 9600 | 0.4971 | 0.7616 | 0.762 | | 0.4254 | 65.77 | 9800 | 0.4965 | 0.7587 | 0.759 | | 0.4151 | 67.11 | 10000 | 0.4965 | 0.7596 | 0.76 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_tf_2-seqsight_4096_512_46M-L1_f", "results": []}]}

mahdibaghbanzadeh/GUE_tf_2-seqsight_4096_512_46M-L1_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_46M", "region:us" ]

null

2024-04-27T01:12:28+00:00

[]

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us

GUE\_tf\_2-seqsight\_4096\_512\_46M-L1\_f ========================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_4096\_512\_46M on the mahdibaghbanzadeh/GUE\_tf\_2 dataset. It achieves the following results on the evaluation set: * Loss: 0.4291 * F1 Score: 0.7986 * Accuracy: 0.799 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

null

transformers

# Uploaded model - **Developed by:** berger815 - **License:** apache-2.0 - **Finetuned from model :** unsloth/llama-3-8b-bnb-4bit This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)

{"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "llama", "gguf"], "base_model": "unsloth/llama-3-8b-bnb-4bit"}

berger815/sail

null

[ "transformers", "gguf", "llama", "text-generation-inference", "unsloth", "en", "base_model:unsloth/llama-3-8b-bnb-4bit", "license:apache-2.0", "endpoints_compatible", "region:us" ]

null

2024-04-27T01:14:05+00:00

[]

[ "en" ]

TAGS #transformers #gguf #llama #text-generation-inference #unsloth #en #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us

# Uploaded model - Developed by: berger815 - License: apache-2.0 - Finetuned from model : unsloth/llama-3-8b-bnb-4bit This llama model was trained 2x faster with Unsloth and Huggingface's TRL library. <img src="URL width="200"/>

[ "# Uploaded model\n\n- Developed by: berger815\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "TAGS\n#transformers #gguf #llama #text-generation-inference #unsloth #en #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us \n", "# Uploaded model\n\n- Developed by: berger815\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

null

peft

# GUE_tf_2-seqsight_4096_512_46M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_tf_2](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_2) dataset. It achieves the following results on the evaluation set: - Loss: 0.4177 - F1 Score: 0.8059 - Accuracy: 0.806 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.5544 | 1.34 | 200 | 0.5176 | 0.7450 | 0.745 | | 0.5145 | 2.68 | 400 | 0.5058 | 0.7586 | 0.759 | | 0.5023 | 4.03 | 600 | 0.4987 | 0.7597 | 0.76 | | 0.493 | 5.37 | 800 | 0.4933 | 0.7609 | 0.761 | | 0.4858 | 6.71 | 1000 | 0.4995 | 0.7535 | 0.754 | | 0.4776 | 8.05 | 1200 | 0.4864 | 0.7579 | 0.758 | | 0.4701 | 9.4 | 1400 | 0.4893 | 0.7530 | 0.753 | | 0.4687 | 10.74 | 1600 | 0.4842 | 0.7609 | 0.761 | | 0.4636 | 12.08 | 1800 | 0.4857 | 0.7640 | 0.764 | | 0.4569 | 13.42 | 2000 | 0.4932 | 0.7570 | 0.757 | | 0.4552 | 14.77 | 2200 | 0.4921 | 0.7446 | 0.747 | | 0.4445 | 16.11 | 2400 | 0.4963 | 0.7540 | 0.754 | | 0.4464 | 17.45 | 2600 | 0.4895 | 0.7472 | 0.748 | | 0.436 | 18.79 | 2800 | 0.4813 | 0.7595 | 0.76 | | 0.4342 | 20.13 | 3000 | 0.4896 | 0.7710 | 0.771 | | 0.4303 | 21.48 | 3200 | 0.4968 | 0.7720 | 0.772 | | 0.4297 | 22.82 | 3400 | 0.4859 | 0.7587 | 0.759 | | 0.4236 | 24.16 | 3600 | 0.4871 | 0.7634 | 0.764 | | 0.4179 | 25.5 | 3800 | 0.4942 | 0.7676 | 0.768 | | 0.4168 | 26.85 | 4000 | 0.4995 | 0.7535 | 0.754 | | 0.4116 | 28.19 | 4200 | 0.4928 | 0.7600 | 0.76 | | 0.4127 | 29.53 | 4400 | 0.4995 | 0.7506 | 0.751 | | 0.4094 | 30.87 | 4600 | 0.4962 | 0.7628 | 0.763 | | 0.4058 | 32.21 | 4800 | 0.5047 | 0.7649 | 0.765 | | 0.4039 | 33.56 | 5000 | 0.5042 | 0.7620 | 0.762 | | 0.4001 | 34.9 | 5200 | 0.5061 | 0.75 | 0.75 | | 0.3923 | 36.24 | 5400 | 0.5088 | 0.7546 | 0.755 | | 0.392 | 37.58 | 5600 | 0.5064 | 0.7567 | 0.757 | | 0.3905 | 38.93 | 5800 | 0.5066 | 0.7522 | 0.753 | | 0.3837 | 40.27 | 6000 | 0.5184 | 0.7472 | 0.749 | | 0.3843 | 41.61 | 6200 | 0.5116 | 0.7604 | 0.761 | | 0.3827 | 42.95 | 6400 | 0.5182 | 0.7619 | 0.762 | | 0.3759 | 44.3 | 6600 | 0.5226 | 0.7499 | 0.75 | | 0.3827 | 45.64 | 6800 | 0.5227 | 0.7590 | 0.759 | | 0.3748 | 46.98 | 7000 | 0.5185 | 0.7599 | 0.76 | | 0.3724 | 48.32 | 7200 | 0.5180 | 0.7597 | 0.76 | | 0.3689 | 49.66 | 7400 | 0.5216 | 0.7549 | 0.755 | | 0.3688 | 51.01 | 7600 | 0.5168 | 0.7558 | 0.756 | | 0.3682 | 52.35 | 7800 | 0.5278 | 0.7558 | 0.756 | | 0.3671 | 53.69 | 8000 | 0.5224 | 0.7484 | 0.749 | | 0.3623 | 55.03 | 8200 | 0.5258 | 0.76 | 0.76 | | 0.3639 | 56.38 | 8400 | 0.5292 | 0.7527 | 0.753 | | 0.3653 | 57.72 | 8600 | 0.5249 | 0.7476 | 0.748 | | 0.3592 | 59.06 | 8800 | 0.5289 | 0.7520 | 0.752 | | 0.3548 | 60.4 | 9000 | 0.5363 | 0.7509 | 0.751 | | 0.361 | 61.74 | 9200 | 0.5303 | 0.7498 | 0.75 | | 0.3578 | 63.09 | 9400 | 0.5297 | 0.7530 | 0.753 | | 0.355 | 64.43 | 9600 | 0.5298 | 0.7497 | 0.75 | | 0.3611 | 65.77 | 9800 | 0.5298 | 0.7499 | 0.75 | | 0.3525 | 67.11 | 10000 | 0.5308 | 0.7508 | 0.751 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_tf_2-seqsight_4096_512_46M-L8_f", "results": []}]}

mahdibaghbanzadeh/GUE_tf_2-seqsight_4096_512_46M-L8_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_46M", "region:us" ]

null

2024-04-27T01:16:29+00:00

[]

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us

GUE\_tf\_2-seqsight\_4096\_512\_46M-L8\_f ========================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_4096\_512\_46M on the mahdibaghbanzadeh/GUE\_tf\_2 dataset. It achieves the following results on the evaluation set: * Loss: 0.4177 * F1 Score: 0.8059 * Accuracy: 0.806 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

null

peft

# GUE_tf_2-seqsight_4096_512_46M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_tf_2](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_2) dataset. It achieves the following results on the evaluation set: - Loss: 0.4244 - F1 Score: 0.8144 - Accuracy: 0.815 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.5473 | 1.34 | 200 | 0.5045 | 0.7480 | 0.748 | | 0.5072 | 2.68 | 400 | 0.5003 | 0.7693 | 0.77 | | 0.4937 | 4.03 | 600 | 0.4978 | 0.7570 | 0.758 | | 0.4809 | 5.37 | 800 | 0.4858 | 0.7698 | 0.77 | | 0.4694 | 6.71 | 1000 | 0.4840 | 0.7699 | 0.77 | | 0.4588 | 8.05 | 1200 | 0.4779 | 0.7718 | 0.772 | | 0.4478 | 9.4 | 1400 | 0.4832 | 0.7700 | 0.77 | | 0.4415 | 10.74 | 1600 | 0.4833 | 0.7599 | 0.76 | | 0.4325 | 12.08 | 1800 | 0.4849 | 0.7457 | 0.746 | | 0.4207 | 13.42 | 2000 | 0.4910 | 0.7690 | 0.769 | | 0.4159 | 14.77 | 2200 | 0.4891 | 0.7501 | 0.752 | | 0.4005 | 16.11 | 2400 | 0.5130 | 0.766 | 0.766 | | 0.397 | 17.45 | 2600 | 0.4905 | 0.7658 | 0.766 | | 0.3812 | 18.79 | 2800 | 0.4931 | 0.7539 | 0.754 | | 0.38 | 20.13 | 3000 | 0.5029 | 0.7689 | 0.769 | | 0.366 | 21.48 | 3200 | 0.5259 | 0.7650 | 0.765 | | 0.3615 | 22.82 | 3400 | 0.5142 | 0.7600 | 0.76 | | 0.3533 | 24.16 | 3600 | 0.5133 | 0.7558 | 0.756 | | 0.3404 | 25.5 | 3800 | 0.5249 | 0.7559 | 0.756 | | 0.3372 | 26.85 | 4000 | 0.5349 | 0.7529 | 0.753 | | 0.3282 | 28.19 | 4200 | 0.5312 | 0.7620 | 0.762 | | 0.3224 | 29.53 | 4400 | 0.5504 | 0.7568 | 0.757 | | 0.3177 | 30.87 | 4600 | 0.5576 | 0.7588 | 0.759 | | 0.3093 | 32.21 | 4800 | 0.5691 | 0.7640 | 0.764 | | 0.3065 | 33.56 | 5000 | 0.5583 | 0.7640 | 0.764 | | 0.293 | 34.9 | 5200 | 0.5930 | 0.7468 | 0.747 | | 0.2857 | 36.24 | 5400 | 0.5897 | 0.7610 | 0.761 | | 0.2831 | 37.58 | 5600 | 0.5956 | 0.7559 | 0.756 | | 0.2758 | 38.93 | 5800 | 0.5931 | 0.7526 | 0.753 | | 0.2693 | 40.27 | 6000 | 0.6084 | 0.7511 | 0.752 | | 0.2641 | 41.61 | 6200 | 0.6205 | 0.7555 | 0.756 | | 0.2624 | 42.95 | 6400 | 0.6236 | 0.7680 | 0.768 | | 0.2524 | 44.3 | 6600 | 0.6303 | 0.7579 | 0.758 | | 0.2578 | 45.64 | 6800 | 0.6329 | 0.7589 | 0.759 | | 0.251 | 46.98 | 7000 | 0.6389 | 0.7609 | 0.761 | | 0.2421 | 48.32 | 7200 | 0.6307 | 0.7588 | 0.759 | | 0.2375 | 49.66 | 7400 | 0.6399 | 0.7619 | 0.762 | | 0.2346 | 51.01 | 7600 | 0.6300 | 0.7610 | 0.761 | | 0.2343 | 52.35 | 7800 | 0.6554 | 0.7590 | 0.759 | | 0.2256 | 53.69 | 8000 | 0.6766 | 0.7539 | 0.754 | | 0.2247 | 55.03 | 8200 | 0.6589 | 0.7599 | 0.76 | | 0.2262 | 56.38 | 8400 | 0.6732 | 0.7629 | 0.763 | | 0.2237 | 57.72 | 8600 | 0.6709 | 0.7568 | 0.757 | | 0.219 | 59.06 | 8800 | 0.6830 | 0.7598 | 0.76 | | 0.2108 | 60.4 | 9000 | 0.6949 | 0.7589 | 0.759 | | 0.2168 | 61.74 | 9200 | 0.6767 | 0.7609 | 0.761 | | 0.2109 | 63.09 | 9400 | 0.6819 | 0.7520 | 0.752 | | 0.2095 | 64.43 | 9600 | 0.6936 | 0.7629 | 0.763 | | 0.2098 | 65.77 | 9800 | 0.6890 | 0.7590 | 0.759 | | 0.2081 | 67.11 | 10000 | 0.6882 | 0.7630 | 0.763 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_tf_2-seqsight_4096_512_46M-L32_f", "results": []}]}

mahdibaghbanzadeh/GUE_tf_2-seqsight_4096_512_46M-L32_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_46M", "region:us" ]

null

2024-04-27T01:16:37+00:00

[]

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us

GUE\_tf\_2-seqsight\_4096\_512\_46M-L32\_f ========================================== This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_4096\_512\_46M on the mahdibaghbanzadeh/GUE\_tf\_2 dataset. It achieves the following results on the evaluation set: * Loss: 0.4244 * F1 Score: 0.8144 * Accuracy: 0.815 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

null

peft

# GUE_virus_covid-seqsight_4096_512_46M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_virus_covid](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_virus_covid) dataset. It achieves the following results on the evaluation set: - Loss: 1.4763 - F1 Score: 0.4656 - Accuracy: 0.4567 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 2.1823 | 0.35 | 200 | 2.1755 | 0.1308 | 0.1550 | | 2.1713 | 0.7 | 400 | 2.1631 | 0.1232 | 0.1561 | | 2.1562 | 1.05 | 600 | 2.1489 | 0.1267 | 0.1598 | | 2.1422 | 1.4 | 800 | 2.1259 | 0.1591 | 0.1855 | | 2.1125 | 1.75 | 1000 | 2.0921 | 0.2001 | 0.2172 | | 2.0522 | 2.09 | 1200 | 2.0180 | 0.2094 | 0.2229 | | 2.0008 | 2.44 | 1400 | 2.0021 | 0.2175 | 0.2235 | | 1.9803 | 2.79 | 1600 | 1.9652 | 0.2402 | 0.2482 | | 1.9533 | 3.14 | 1800 | 1.9438 | 0.2502 | 0.2591 | | 1.9191 | 3.49 | 2000 | 1.9104 | 0.2594 | 0.2681 | | 1.898 | 3.84 | 2200 | 1.8906 | 0.2787 | 0.2826 | | 1.874 | 4.19 | 2400 | 1.8751 | 0.2928 | 0.2907 | | 1.8486 | 4.54 | 2600 | 1.8183 | 0.3136 | 0.3125 | | 1.8371 | 4.89 | 2800 | 1.8066 | 0.3193 | 0.3211 | | 1.8173 | 5.24 | 3000 | 1.7830 | 0.3277 | 0.3274 | | 1.7984 | 5.58 | 3200 | 1.7757 | 0.3458 | 0.3403 | | 1.7731 | 5.93 | 3400 | 1.7557 | 0.3397 | 0.3405 | | 1.7691 | 6.28 | 3600 | 1.7237 | 0.3532 | 0.3449 | | 1.7417 | 6.63 | 3800 | 1.7201 | 0.3604 | 0.3551 | | 1.7384 | 6.98 | 4000 | 1.6938 | 0.3712 | 0.3625 | | 1.7209 | 7.33 | 4200 | 1.6768 | 0.3679 | 0.3640 | | 1.7136 | 7.68 | 4400 | 1.6731 | 0.3859 | 0.3760 | | 1.7088 | 8.03 | 4600 | 1.6489 | 0.3892 | 0.3776 | | 1.6831 | 8.38 | 4800 | 1.6485 | 0.3828 | 0.3748 | | 1.6867 | 8.73 | 5000 | 1.6315 | 0.3822 | 0.3806 | | 1.6676 | 9.08 | 5200 | 1.6224 | 0.4034 | 0.3878 | | 1.6583 | 9.42 | 5400 | 1.5976 | 0.3983 | 0.3943 | | 1.6444 | 9.77 | 5600 | 1.5920 | 0.4158 | 0.4085 | | 1.6423 | 10.12 | 5800 | 1.5823 | 0.4177 | 0.4045 | | 1.6388 | 10.47 | 6000 | 1.5672 | 0.4187 | 0.4129 | | 1.6279 | 10.82 | 6200 | 1.5768 | 0.4160 | 0.4046 | | 1.6126 | 11.17 | 6400 | 1.5586 | 0.4314 | 0.4186 | | 1.6081 | 11.52 | 6600 | 1.5500 | 0.4324 | 0.4235 | | 1.6111 | 11.87 | 6800 | 1.5411 | 0.4372 | 0.4322 | | 1.6029 | 12.22 | 7000 | 1.5316 | 0.4445 | 0.4380 | | 1.587 | 12.57 | 7200 | 1.5282 | 0.4388 | 0.4354 | | 1.5933 | 12.91 | 7400 | 1.5249 | 0.4433 | 0.4384 | | 1.5853 | 13.26 | 7600 | 1.5170 | 0.4500 | 0.4448 | | 1.5763 | 13.61 | 7800 | 1.5102 | 0.4547 | 0.4473 | | 1.5714 | 13.96 | 8000 | 1.5047 | 0.4578 | 0.4488 | | 1.5627 | 14.31 | 8200 | 1.5040 | 0.4541 | 0.4468 | | 1.5692 | 14.66 | 8400 | 1.5010 | 0.4592 | 0.4483 | | 1.5674 | 15.01 | 8600 | 1.4997 | 0.4604 | 0.4539 | | 1.5651 | 15.36 | 8800 | 1.4966 | 0.4577 | 0.4481 | | 1.551 | 15.71 | 9000 | 1.4878 | 0.4596 | 0.4544 | | 1.5595 | 16.06 | 9200 | 1.4864 | 0.4639 | 0.4564 | | 1.5496 | 16.4 | 9400 | 1.4850 | 0.4660 | 0.4594 | | 1.5506 | 16.75 | 9600 | 1.4848 | 0.4615 | 0.4557 | | 1.5503 | 17.1 | 9800 | 1.4855 | 0.4610 | 0.4553 | | 1.5622 | 17.45 | 10000 | 1.4856 | 0.4608 | 0.4543 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_virus_covid-seqsight_4096_512_46M-L1_f", "results": []}]}

mahdibaghbanzadeh/GUE_virus_covid-seqsight_4096_512_46M-L1_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_46M", "region:us" ]

null

2024-04-27T01:17:02+00:00

[]

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us

GUE\_virus\_covid-seqsight\_4096\_512\_46M-L1\_f ================================================ This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_4096\_512\_46M on the mahdibaghbanzadeh/GUE\_virus\_covid dataset. It achieves the following results on the evaluation set: * Loss: 1.4763 * F1 Score: 0.4656 * Accuracy: 0.4567 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

null

peft

# GUE_virus_covid-seqsight_4096_512_46M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_virus_covid](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_virus_covid) dataset. It achieves the following results on the evaluation set: - Loss: 1.1081 - F1 Score: 0.5885 - Accuracy: 0.5836 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 2.1813 | 0.35 | 200 | 2.1726 | 0.1379 | 0.1588 | | 2.1662 | 0.7 | 400 | 2.1509 | 0.1381 | 0.1652 | | 2.1037 | 1.05 | 600 | 2.0112 | 0.2257 | 0.2359 | | 1.9819 | 1.4 | 800 | 1.9200 | 0.2583 | 0.2687 | | 1.8868 | 1.75 | 1000 | 1.8249 | 0.3095 | 0.3102 | | 1.8165 | 2.09 | 1200 | 1.7372 | 0.3276 | 0.3355 | | 1.7544 | 2.44 | 1400 | 1.6856 | 0.3698 | 0.3568 | | 1.6947 | 2.79 | 1600 | 1.6089 | 0.3855 | 0.3813 | | 1.6505 | 3.14 | 1800 | 1.5679 | 0.4055 | 0.4033 | | 1.6094 | 3.49 | 2000 | 1.5561 | 0.4103 | 0.4004 | | 1.5905 | 3.84 | 2200 | 1.5347 | 0.4307 | 0.4259 | | 1.5608 | 4.19 | 2400 | 1.4948 | 0.4371 | 0.4297 | | 1.5426 | 4.54 | 2600 | 1.4540 | 0.4686 | 0.4594 | | 1.5276 | 4.89 | 2800 | 1.4528 | 0.4607 | 0.4530 | | 1.501 | 5.24 | 3000 | 1.4105 | 0.4782 | 0.4726 | | 1.492 | 5.58 | 3200 | 1.3877 | 0.4903 | 0.4852 | | 1.456 | 5.93 | 3400 | 1.3723 | 0.4943 | 0.4924 | | 1.4394 | 6.28 | 3600 | 1.3620 | 0.4935 | 0.4774 | | 1.4203 | 6.63 | 3800 | 1.3357 | 0.5014 | 0.4939 | | 1.4029 | 6.98 | 4000 | 1.3041 | 0.5138 | 0.5080 | | 1.3836 | 7.33 | 4200 | 1.2996 | 0.5153 | 0.5026 | | 1.3682 | 7.68 | 4400 | 1.2885 | 0.5183 | 0.5065 | | 1.3661 | 8.03 | 4600 | 1.2755 | 0.5245 | 0.5152 | | 1.3392 | 8.38 | 4800 | 1.2771 | 0.5231 | 0.5151 | | 1.3477 | 8.73 | 5000 | 1.2642 | 0.5257 | 0.5173 | | 1.3332 | 9.08 | 5200 | 1.2546 | 0.5357 | 0.5257 | | 1.3227 | 9.42 | 5400 | 1.2411 | 0.5363 | 0.5317 | | 1.3048 | 9.77 | 5600 | 1.2315 | 0.5333 | 0.5315 | | 1.3071 | 10.12 | 5800 | 1.2159 | 0.5470 | 0.5413 | | 1.2925 | 10.47 | 6000 | 1.1937 | 0.5575 | 0.5557 | | 1.274 | 10.82 | 6200 | 1.1954 | 0.5525 | 0.5405 | | 1.2555 | 11.17 | 6400 | 1.1973 | 0.5570 | 0.5376 | | 1.2539 | 11.52 | 6600 | 1.1798 | 0.5659 | 0.5568 | | 1.2569 | 11.87 | 6800 | 1.1652 | 0.5652 | 0.5551 | | 1.2441 | 12.22 | 7000 | 1.1593 | 0.5680 | 0.5586 | | 1.2274 | 12.57 | 7200 | 1.1594 | 0.5758 | 0.5644 | | 1.232 | 12.91 | 7400 | 1.1576 | 0.5676 | 0.5604 | | 1.2214 | 13.26 | 7600 | 1.1409 | 0.5732 | 0.5635 | | 1.2106 | 13.61 | 7800 | 1.1350 | 0.5753 | 0.5673 | | 1.2049 | 13.96 | 8000 | 1.1360 | 0.5757 | 0.5671 | | 1.2026 | 14.31 | 8200 | 1.1227 | 0.5800 | 0.5723 | | 1.2048 | 14.66 | 8400 | 1.1148 | 0.5845 | 0.5755 | | 1.1968 | 15.01 | 8600 | 1.1170 | 0.5797 | 0.5730 | | 1.1996 | 15.36 | 8800 | 1.1114 | 0.5863 | 0.5770 | | 1.1758 | 15.71 | 9000 | 1.1122 | 0.5819 | 0.5766 | | 1.1923 | 16.06 | 9200 | 1.1091 | 0.5861 | 0.5783 | | 1.1735 | 16.4 | 9400 | 1.1096 | 0.5851 | 0.5801 | | 1.1799 | 16.75 | 9600 | 1.1072 | 0.5845 | 0.5782 | | 1.1815 | 17.1 | 9800 | 1.1085 | 0.5853 | 0.5787 | | 1.181 | 17.45 | 10000 | 1.1072 | 0.5865 | 0.5802 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_virus_covid-seqsight_4096_512_46M-L8_f", "results": []}]}

mahdibaghbanzadeh/GUE_virus_covid-seqsight_4096_512_46M-L8_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_46M", "region:us" ]

null

2024-04-27T01:17:17+00:00

[]

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us

GUE\_virus\_covid-seqsight\_4096\_512\_46M-L8\_f ================================================ This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_4096\_512\_46M on the mahdibaghbanzadeh/GUE\_virus\_covid dataset. It achieves the following results on the evaluation set: * Loss: 1.1081 * F1 Score: 0.5885 * Accuracy: 0.5836 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

text2text-generation

transformers

# CS505_COQE_viT5_train_Instruction0_SPAOL_v1 This model is a fine-tuned version of [VietAI/vit5-large](https://huggingface.co/VietAI/vit5-large) on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 20 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.15.2

{"license": "mit", "tags": ["generated_from_trainer"], "base_model": "VietAI/vit5-large", "model-index": [{"name": "CS505_COQE_viT5_train_Instruction0_SPAOL_v1", "results": []}]}

ThuyNT/CS505_COQE_viT5_train_Instruction0_SPAOL_v1

null

[ "transformers", "tensorboard", "safetensors", "t5", "text2text-generation", "generated_from_trainer", "base_model:VietAI/vit5-large", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

null

2024-04-27T01:17:27+00:00

[]

TAGS #transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-VietAI/vit5-large #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

# CS505_COQE_viT5_train_Instruction0_SPAOL_v1 This model is a fine-tuned version of VietAI/vit5-large on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 20 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.15.2

[ "# CS505_COQE_viT5_train_Instruction0_SPAOL_v1\n\nThis model is a fine-tuned version of VietAI/vit5-large on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 20\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-VietAI/vit5-large #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# CS505_COQE_viT5_train_Instruction0_SPAOL_v1\n\nThis model is a fine-tuned version of VietAI/vit5-large on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 20\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

text-generation

transformers

<div align="center"> <img width="260px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/BrQCb95lmEIFz79QAmoNA.png"></div> ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/fJIOPJnY6Ff6fUiSIuMEt.png) <div align="center"> <h1>Advancing Open-source Large Language Models in Medical Domain</h1> </div> <p align="center" style="margin-top: 0px;"> <a href="https://colab.research.google.com/drive/1F5oV20InEYeAJGmBwYF9NM_QhLmjBkKJ?usp=sharing"> <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="OpenChat Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 10px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style=" margin-right: 5px;">Online Demo</span> </a> | <a href="https://github.com/openlifescience-ai"> <img src="https://github.githubassets.com/assets/GitHub-Mark-ea2971cee799.png" alt="GitHub Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style=" margin-right: 5px;">GitHub</span> </a> | <a href="#"> <img src="https://github.com/alpayariyak/openchat/blob/master/assets/arxiv-logomark-small-square-border.png?raw=true" alt="ArXiv Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style="margin-right: 5px;">Paper</span> </a> | <a href="https://discord.gg/A5Fjf5zC69"> <img src="https://cloud.githubusercontent.com/assets/6291467/26705903/96c2d66e-477c-11e7-9f4e-f3c0efe96c9a.png" alt="Discord Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text">Discord</span> </a> </p> ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/KGmRE5w2sepNtwsEu8t7K.jpeg) Introducing OpenBioLLM-70B: A State-of-the-Art Open Source Biomedical Large Language Model OpenBioLLM-70B is an advanced open source language model designed specifically for the biomedical domain. Developed by Saama AI Labs, this model leverages cutting-edge techniques to achieve state-of-the-art performance on a wide range of biomedical tasks. 🏥 **Biomedical Specialization**: OpenBioLLM-70B is tailored for the unique language and knowledge requirements of the medical and life sciences fields. It was fine-tuned on a vast corpus of high-quality biomedical data, enabling it to understand and generate text with domain-specific accuracy and fluency. 🎓 **Superior Performance**: With 70 billion parameters, OpenBioLLM-70B outperforms other open source biomedical language models of similar scale. It has also demonstrated better results compared to larger proprietary & open-source models like GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 on biomedical benchmarks. 🧠 **Advanced Training Techniques**: OpenBioLLM-70B builds upon the powerful foundations of the **Meta-Llama-3-70B-Instruct** and [Meta-Llama-3-70B-Instruct](meta-llama/Meta-Llama-3-70B-Instruct) models. It incorporates the DPO dataset and fine-tuning recipe along with a custom diverse medical instruction dataset. Key components of the training pipeline include: <div align="center"> <img width="1200px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/oPchsJsEpQoGcGXVbh7YS.png"> </div> - **Policy Optimization**: [Direct Preference Optimization: Your Language Model is Secretly a Reward Model (DPO)](https://arxiv.org/abs/2305.18290) - **Fine-tuning dataset**: Custom Medical Instruct dataset (We plan to release a sample training dataset in our upcoming paper; please stay updated) This combination of cutting-edge techniques enables OpenBioLLM-70B to align with key capabilities and preferences for biomedical applications. ⚙️ **Release Details**: - **Model Size**: 70 billion parameters - **Quantization**: Optimized quantized versions available [Here](https://huggingface.co/aaditya/OpenBioLLM-70B-GGUF) - **Language(s) (NLP):** en - **Developed By**: [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) from Saama AI Labs - **License:** Meta-Llama License - **Fine-tuned from models:** [Meta-Llama-3-70B-Instruct](meta-llama/Meta-Llama-3-70B-Instruct) - **Resources for more information:** - Paper: Coming soon The model can be fine-tuned for more specialized tasks and datasets as needed. OpenBioLLM-70B represents an important step forward in democratizing advanced language AI for the biomedical community. By leveraging state-of-the-art architectures and training techniques from leading open source efforts like Llama-3, we have created a powerful tool to accelerate innovation and discovery in healthcare and the life sciences. We are excited to share OpenBioLLM-70B with researchers and developers around the world. ### Use with transformers **Important: Please use the exact chat template provided by Llama-3 instruct version. Otherwise there will be a degradation in the performance. The model output can be verbose in rare cases. Please consider setting temperature = 0 to make this happen less.** See the snippet below for usage with Transformers: ```python import transformers import torch model_id = "aaditya/OpenBioLLM-Llama3-70B" pipeline = transformers.pipeline( "text-generation", model=model_id, model_kwargs={"torch_dtype": torch.bfloat16}, device="auto", ) messages = [ {"role": "system", "content": "You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience. Your name is OpenBioLLM, and you were developed by Saama AI Labs. who's willing to help answer the user's query with explanation. In your explanation, leverage your deep medical expertise such as relevant anatomical structures, physiological processes, diagnostic criteria, treatment guidelines, or other pertinent medical concepts. Use precise medical terminology while still aiming to make the explanation clear and accessible to a general audience."}, {"role": "user", "content": "How can i split a 3mg or 4mg waefin pill so i can get a 2.5mg pill?"}, ] prompt = pipeline.tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) terminators = [ pipeline.tokenizer.eos_token_id, pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>") ] outputs = pipeline( prompt, max_new_tokens=256, eos_token_id=terminators, do_sample=True, temperature=0.0, top_p=0.9, ) print(outputs[0]["generated_text"][len(prompt):]) ``` ## **Training procedure** ### **Training hyperparameters** <details> <summary>Click to see details</summary> - learning_rate: 0.0002 - lr_scheduler: cosine - train_batch_size: 12 - eval_batch_size: 8 - GPU: H100 80GB SXM5 - num_devices: 8 - optimizer: adamw_bnb_8bit - lr_scheduler_warmup_steps: 100 - num_epochs: 4 </details> ### **Peft hyperparameters** <details> <summary>Click to see details</summary> - adapter: qlora - lora_r: 128 - lora_alpha: 256 - lora_dropout: 0.05 - lora_target_linear: true -lora_target_modules: - q_proj - v_proj - k_proj - o_proj - gate_proj - down_proj - up_proj </details> ### **Training results** ### **Framework versions** - Transformers 4.39.3 - Pytorch 2.1.2+cu121 - Datasets 2.18.0 - Tokenizers 0.15.1 - Axolotl - Lm harness for evaluation # Benchmark Results 🔥 OpenBioLLM-70B demonstrates superior performance compared to larger models, such as GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 across 9 diverse biomedical datasets, achieving state-of-the-art results with an average score of 86.06%, despite having a significantly smaller parameter count. The model's strong performance in domain-specific tasks, such as Clinical KG, Medical Genetics, and PubMedQA, highlights its ability to effectively capture and apply biomedical knowledge. 🚨 The GPT-4, Med-PaLM-1, and Med-PaLM-2 results are taken from their official papers. Since Med-PaLM doesn't provide zero-shot accuracy, we are using 5-shot accuracy from their paper for comparison. All results presented are in the zero-shot setting, except for Med-PaLM-2 and Med-PaLM-1, which use 5-shot accuracy. | | Clinical KG | Medical Genetics | Anatomy | Pro Medicine | College Biology | College Medicine | MedQA 4 opts | PubMedQA | MedMCQA | Avg | |--------------------|-------------|------------------|---------|--------------|-----------------|------------------|--------------|----------|---------|-------| | **OpenBioLLM-70B** | **92.93** | **93.197** | **83.904** | 93.75 | 93.827 | **85.749** | 78.162 | 78.97 | **74.014** | **86.05588** | | Med-PaLM-2 (5-shot) | 88.3 | 90 | 77.8 | **95.2** | 94.4 | 80.9 | **79.7** | **79.2** | 71.3 | 84.08 | | **GPT-4** | 86.04 | 91 | 80 | 93.01 | **95.14** | 76.88 | 78.87 | 75.2 | 69.52 | 82.85 | | Med-PaLM-1 (Flan-PaLM, 5-shot) | 80.4 | 75 | 63.7 | 83.8 | 88.9 | 76.3 | 67.6 | 79 | 57.6 | 74.7 | | **OpenBioLLM-8B** | 76.101 | 86.1 | 69.829 | 78.21 | 84.213 | 68.042 | 58.993 | 74.12 | 56.913 | 72.502 | | Gemini-1.0 | 76.7 | 75.8 | 66.7 | 77.7 | 88 | 69.2 | 58 | 70.7 | 54.3 | 70.79 | | GPT-3.5 Turbo 1106 | 74.71 | 74 | 72.79 | 72.79 | 72.91 | 64.73 | 57.71 | 72.66 | 53.79 | 66 | | Meditron-70B | 66.79 | 69 | 53.33 | 71.69 | 76.38 | 63 | 57.1 | 76.6 | 46.85 | 64.52 | | gemma-7b | 69.81 | 70 | 59.26 | 66.18 | 79.86 | 60.12 | 47.21 | 76.2 | 48.96 | 64.18 | | Mistral-7B-v0.1 | 68.68 | 71 | 55.56 | 68.38 | 68.06 | 59.54 | 50.82 | 75.4 | 48.2 | 62.85 | | Apollo-7B | 62.26 | 72 | 61.48 | 69.12 | 70.83 | 55.49 | 55.22 | 39.8 | 53.77 | 60 | | MedAlpaca-7b | 57.36 | 69 | 57.04 | 67.28 | 65.28 | 54.34 | 41.71 | 72.8 | 37.51 | 58.03 | | BioMistral-7B | 59.9 | 64 | 56.5 | 60.4 | 59 | 54.7 | 50.6 | 77.5 | 48.1 | 57.3 | | AlpaCare-llama2-7b | 49.81 | 49 | 45.92 | 33.82 | 50 | 43.35 | 29.77 | 72.2 | 34.42 | 45.36 | | ClinicalGPT | 30.56 | 27 | 30.37 | 19.48 | 25 | 24.27 | 26.08 | 63.8 | 28.18 | 30.52 | <div align="center"> <img width="1600px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/_SzdcJSBjZyo8RS1bTEkP.png"> </div> ## Detailed Medical Subjectwise accuracy ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/UXF-V0col0Z0sS6BGPBkE.png) # Use Cases & Examples 🚨 **Below results are from the quantized version of OpenBioLLM-70B # Summarize Clinical Notes OpenBioLLM-70B can efficiently analyze and summarize complex clinical notes, EHR data, and discharge summaries, extracting key information and generating concise, structured summaries ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/xdwdBgOxNi_TfML0hKlI8.png) # Answer Medical Questions OpenBioLLM-70B can provide answers to a wide range of medical questions. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/zO95GlwOQEZqCKQF69mE6.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/OKBczKw7gWeW5xsuDpc27.png) <details> <summary>Click to see details</summary> ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/eJGHT5khppYvJb8fQ-YW4.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/Cnbwrqa_-ORHRuNRC2P6Y.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/J9DhdcvukAc9mnnW9fj2C.png) </details> # Clinical Entity Recognition OpenBioLLM-70B can perform advanced clinical entity recognition by identifying and extracting key medical concepts, such as diseases, symptoms, medications, procedures, and anatomical structures, from unstructured clinical text. By leveraging its deep understanding of medical terminology and context, the model can accurately annotate and categorize clinical entities, enabling more efficient information retrieval, data analysis, and knowledge discovery from electronic health records, research articles, and other biomedical text sources. This capability can support various downstream applications, such as clinical decision support, pharmacovigilance, and medical research. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/_69BW4k9LVABFwtxixL45.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/DKy5wYCoPhoPPUc1-x8_J.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/7WD9zCCBZT4-4XlfnIQjl.png) # Biomarkers Extraction ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/ZttoM4AiteT7gFYVhjIpN.png) # Classification OpenBioLLM-70B can perform various biomedical classification tasks, such as disease prediction, sentiment analysis, medical document categorization ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/Bf5MW1d75qT-1F_TR_hC0.png) # De-Identification OpenBioLLM-70B can detect and remove personally identifiable information (PII) from medical records, ensuring patient privacy and compliance with data protection regulations like HIPAA. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/hKX4kzm--Tw5bj6K78msy.png) **Advisory Notice!** While OpenBioLLM-70B leverages high-quality data sources, its outputs may still contain inaccuracies, biases, or misalignments that could pose risks if relied upon for medical decision-making without further testing and refinement. The model's performance has not yet been rigorously evaluated in randomized controlled trials or real-world healthcare environments. Therefore, we strongly advise against using OpenBioLLM-70B for any direct patient care, clinical decision support, or other professional medical purposes at this time. Its use should be limited to research, development, and exploratory applications by qualified individuals who understand its limitations. OpenBioLLM-70B is intended solely as a research tool to assist healthcare professionals and should never be considered a replacement for the professional judgment and expertise of a qualified medical doctor. Appropriately adapting and validating OpenBioLLM-70B for specific medical use cases would require significant additional work, potentially including: - Thorough testing and evaluation in relevant clinical scenarios - Alignment with evidence-based guidelines and best practices - Mitigation of potential biases and failure modes - Integration with human oversight and interpretation - Compliance with regulatory and ethical standards Always consult a qualified healthcare provider for personal medical needs. # Citation If you find OpenBioLLM-70B & 8B useful in your work, please cite the model as follows: ``` @misc{OpenBioLLMs, author = {Ankit Pal, Malaikannan Sankarasubbu}, title = {OpenBioLLMs: Advancing Open-Source Large Language Models for Healthcare and Life Sciences}, year = {2024}, publisher = {Hugging Face}, journal = {Hugging Face repository}, howpublished = {\url{https://huggingface.co/aaditya/OpenBioLLM-Llama3-70B}} } ``` The accompanying paper is currently in progress and will be released soon. <div align="center"> <h2> 💌 Contact </h2> </div> We look forward to hearing you and collaborating on this exciting project! **Contributors:** - [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) [aadityaura at gmail dot com] - Saama AI Labs - Note: I am looking for a funded PhD opportunity, especially if it fits my Responsible Generative AI, Multimodal LLMs, Geometric Deep Learning, and Healthcare AI skillset. # References We thank the [Meta Team](meta-llama/Meta-Llama-3-70B-Instruct) for their amazing models! Result sources - [1] GPT-4 [Capabilities of GPT-4 on Medical Challenge Problems] (https://arxiv.org/abs/2303.13375) - [2] Med-PaLM-1 [Large Language Models Encode Clinical Knowledge](https://arxiv.org/abs/2212.13138) - [3] Med-PaLM-2 [Towards Expert-Level Medical Question Answering with Large Language Models](https://arxiv.org/abs/2305.09617) - [4] Gemini-1.0 [Gemini Goes to Med School](https://arxiv.org/abs/2402.07023)

{"language": ["en"], "license": "llama3", "tags": ["llama-3", "llama", "Mixtral", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "distillation"], "base_model": "meta-llama/Meta-Llama-3-70B-Instruct", "widget": [{"example_title": "OpenBioLLM-70B", "messages": [{"role": "system", "content": "You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience."}, {"role": "user", "content": "How long does it take for newborn jaundice to go away?"}], "output": {"text": "Newborn jaundice, also known as neonatal jaundice, is a common condition in newborns where the yellowing of the skin and eyes occurs due to an elevated level of bilirubin in the blood. Bilirubin is a yellow pigment that forms when red blood cells break down. In most cases, newborn jaundice resolves on its own without any specific treatment.\nThe duration of newborn jaundice can vary depending on several factors such as the underlying cause, gestational age at birth, and individual variations in bilirubin metabolism. Here are some general guidelines:\n1. Physiological jaundice: This is the most common type of newborn jaundice and usually appears within 24-72 hours after birth. It tends to peak between the second and fifth day of life and gradually improves over the next week or two. By the time the baby is one week old, the jaundice should have mostly resolved. 2. Breast milk jaundice: This type of jaundice occurs in breastfed babies and may appear later than physiological jaundice, typically between the fifth and fourteenth day of life. It tends to persist for a longer duration but usually resolves within six weeks after birth. 3. Pathological jaundice: This type of jaundice is less common and occurs due to an underlying medical condition that affects bilirubin metabolism or liver function. The duration of pathological jaundice depends on the specific cause and may require treatment.\nIt's important for parents to monitor their newborn's jaundice closely and seek medical advice if the jaundice progresses rapidly, becomes severe, or is accompanied by other symptoms such as poor feeding, lethargy, or excessive sleepiness. In these cases, further evaluation and management may be necessary. Remember that each baby is unique, and the timing of jaundice resolution can vary. If you have concerns about your newborn's jaundice, it's always best to consult with a healthcare professional for personalized advice and guidance."}}], "model-index": [{"name": "OpenBioLLM-70B", "results": []}]}

LoneStriker/OpenBioLLM-Llama3-70B-3.5bpw-h6-exl2

null

[ "transformers", "pytorch", "llama", "text-generation", "llama-3", "Mixtral", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "distillation", "conversational", "en", "arxiv:2305.18290", "arxiv:2303.13375", "arxiv:2212.13138", "arxiv:2305.09617", "arxiv:2402.07023", "base_model:meta-llama/Meta-Llama-3-70B-Instruct", "license:llama3", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

null

2024-04-27T01:18:25+00:00

[ "2305.18290", "2303.13375", "2212.13138", "2305.09617", "2402.07023" ]

[ "en" ]

TAGS #transformers #pytorch #llama #text-generation #llama-3 #Mixtral #instruct #finetune #chatml #DPO #RLHF #gpt4 #distillation #conversational #en #arxiv-2305.18290 #arxiv-2303.13375 #arxiv-2212.13138 #arxiv-2305.09617 #arxiv-2402.07023 #base_model-meta-llama/Meta-Llama-3-70B-Instruct #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

![](URL <p>!image/png</p> <div align=) Advancing Open-source Large Language Models in Medical Domain ============================================================= Online Demo | GitHub | [![](URL alt=)](#) | Discord !image/jpeg Introducing OpenBioLLM-70B: A State-of-the-Art Open Source Biomedical Large Language Model OpenBioLLM-70B is an advanced open source language model designed specifically for the biomedical domain. Developed by Saama AI Labs, this model leverages cutting-edge techniques to achieve state-of-the-art performance on a wide range of biomedical tasks. Biomedical Specialization: OpenBioLLM-70B is tailored for the unique language and knowledge requirements of the medical and life sciences fields. It was fine-tuned on a vast corpus of high-quality biomedical data, enabling it to understand and generate text with domain-specific accuracy and fluency. Superior Performance: With 70 billion parameters, OpenBioLLM-70B outperforms other open source biomedical language models of similar scale. It has also demonstrated better results compared to larger proprietary & open-source models like GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 on biomedical benchmarks. Advanced Training Techniques: OpenBioLLM-70B builds upon the powerful foundations of the Meta-Llama-3-70B-Instruct and Meta-Llama-3-70B-Instruct models. It incorporates the DPO dataset and fine-tuning recipe along with a custom diverse medical instruction dataset. Key components of the training pipeline include: ![](URL </div> <ul> <li>Policy Optimization: Direct Preference Optimization: Your Language Model is Secretly a Reward Model (DPO)</li> <li>Fine-tuning dataset: Custom Medical Instruct dataset (We plan to release a sample training dataset in our upcoming paper; please stay updated)</li> </ul> <p>This combination of cutting-edge techniques enables OpenBioLLM-70B to align with key capabilities and preferences for biomedical applications.</p> <p>️ Release Details:</p> <ul> <li>Model Size: 70 billion parameters</li> <li>Quantization: Optimized quantized versions available Here</li> <li>Language(s) (NLP): en</li> <li>Developed By: Ankit Pal (Aaditya Ura) from Saama AI Labs</li> <li>License: Meta-Llama License</li> <li>Fine-tuned from models: Meta-Llama-3-70B-Instruct</li> <li>Resources for more information: <ul> <li>Paper: Coming soon</li> </ul> </li> </ul> <p>The model can be fine-tuned for more specialized tasks and datasets as needed.</p> <p>OpenBioLLM-70B represents an important step forward in democratizing advanced language AI for the biomedical community. By leveraging state-of-the-art architectures and training techniques from leading open source efforts like Llama-3, we have created a powerful tool to accelerate innovation and discovery in healthcare and the life sciences.</p> <p>We are excited to share OpenBioLLM-70B with researchers and developers around the world.</p> <h3>Use with transformers</h3> <p>Important: Please use the exact chat template provided by Llama-3 instruct version. Otherwise there will be a degradation in the performance. The model output can be verbose in rare cases. Please consider setting temperature = 0 to make this happen less.</p> <p>See the snippet below for usage with Transformers:</p> <h2>Training procedure</h2> <h3>Training hyperparameters</h3> <details> <summary>Click to see details</summary> <ul> <li>learning_rate: 0.0002</li> <li>lr_scheduler: cosine</li> <li>train_batch_size: 12</li> <li>eval_batch_size: 8</li> <li>GPU: H100 80GB SXM5</li> <li>num_devices: 8</li> <li>optimizer: adamw_bnb_8bit</li> <li>lr_scheduler_warmup_steps: 100</li> <li>num_epochs: 4</li> </ul> </details> <h3>Peft hyperparameters</h3> <details> <summary>Click to see details</summary> <ul> <li>adapter: qlora</li> <li>lora_r: 128</li> <li>lora_alpha: 256</li> <li>lora_dropout: 0.05</li> <li>lora_target_linear: true</li> </ul> <p>-lora_target_modules:</p> <ul> <li>q_proj</li> <li>v_proj</li> <li>k_proj</li> <li>o_proj</li> <li>gate_proj</li> <li>down_proj</li> <li>up_proj</li> </ul> </details> <h3>Training results</h3> <h3>Framework versions</h3> <ul> <li>Transformers 4.39.3</li> <li>Pytorch 2.1.2+cu121</li> <li>Datasets 2.18.0</li> <li>Tokenizers 0.15.1</li> <li>Axolotl</li> <li>Lm harness for evaluation</li> </ul> <h1>Benchmark Results</h1> <p>OpenBioLLM-70B demonstrates superior performance compared to larger models, such as GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 across 9 diverse biomedical datasets, achieving state-of-the-art results with an average score of 86.06%, despite having a significantly smaller parameter count. The model's strong performance in domain-specific tasks, such as Clinical KG, Medical Genetics, and PubMedQA, highlights its ability to effectively capture and apply biomedical knowledge.</p> <p>The GPT-4, Med-PaLM-1, and Med-PaLM-2 results are taken from their official papers. Since Med-PaLM doesn't provide zero-shot accuracy, we are using 5-shot accuracy from their paper for comparison. All results presented are in the zero-shot setting, except for Med-PaLM-2 and Med-PaLM-1, which use 5-shot accuracy.</p> <p></p> <div align=) ![](URL </div> <h2>Detailed Medical Subjectwise accuracy</h2> <p>!image/png</p> <h1>Use Cases & Examples</h1> <p>Below results are from the quantized version of OpenBioLLM-70B</p> <h1>Summarize Clinical Notes</h1> <p>OpenBioLLM-70B can efficiently analyze and summarize complex clinical notes, EHR data, and discharge summaries, extracting key information and generating concise, structured summaries</p> <p>!image/png</p> <h1>Answer Medical Questions</h1> <p>OpenBioLLM-70B can provide answers to a wide range of medical questions.</p> <p>!image/png !image/png</p> <details> <summary>Click to see details</summary> <p>!image/png !image/png !image/png</p> </details> <h1>Clinical Entity Recognition</h1> <p>OpenBioLLM-70B can perform advanced clinical entity recognition by identifying and extracting key medical concepts, such as diseases, symptoms, medications, procedures, and anatomical structures, from unstructured clinical text. By leveraging its deep understanding of medical terminology and context, the model can accurately annotate and categorize clinical entities, enabling more efficient information retrieval, data analysis, and knowledge discovery from electronic health records, research articles, and other biomedical text sources. This capability can support various downstream applications, such as clinical decision support, pharmacovigilance, and medical research.</p> <p>!image/png !image/png !image/png</p> <h1>Biomarkers Extraction</h1> <p>!image/png</p> <h1>Classification</h1> <p>OpenBioLLM-70B can perform various biomedical classification tasks, such as disease prediction, sentiment analysis, medical document categorization</p> <p>!image/png</p> <h1>De-Identification</h1> <p>OpenBioLLM-70B can detect and remove personally identifiable information (PII) from medical records, ensuring patient privacy and compliance with data protection regulations like HIPAA.</p> <p>!image/png</p> <p>Advisory Notice!</p> <p>While OpenBioLLM-70B leverages high-quality data sources, its outputs may still contain inaccuracies, biases, or misalignments that could pose risks if relied upon for medical decision-making without further testing and refinement. The model's performance has not yet been rigorously evaluated in randomized controlled trials or real-world healthcare environments.</p> <p>Therefore, we strongly advise against using OpenBioLLM-70B for any direct patient care, clinical decision support, or other professional medical purposes at this time. Its use should be limited to research, development, and exploratory applications by qualified individuals who understand its limitations. OpenBioLLM-70B is intended solely as a research tool to assist healthcare professionals and should never be considered a replacement for the professional judgment and expertise of a qualified medical doctor.</p> <p>Appropriately adapting and validating OpenBioLLM-70B for specific medical use cases would require significant additional work, potentially including:</p> <ul> <li>Thorough testing and evaluation in relevant clinical scenarios</li> <li>Alignment with evidence-based guidelines and best practices</li> <li>Mitigation of potential biases and failure modes</li> <li>Integration with human oversight and interpretation</li> <li>Compliance with regulatory and ethical standards</li> </ul> <p>Always consult a qualified healthcare provider for personal medical needs.</p> <p>If you find OpenBioLLM-70B & 8B useful in your work, please cite the model as follows:</p> <p>The accompanying paper is currently in progress and will be released soon.</p> <div align=) Contact -------- We look forward to hearing you and collaborating on this exciting project! Contributors: * Ankit Pal (Aaditya Ura) [aadityaura at gmail dot com] * Saama AI Labs * Note: I am looking for a funded PhD opportunity, especially if it fits my Responsible Generative AI, Multimodal LLMs, Geometric Deep Learning, and Healthcare AI skillset. References ========== We thank the Meta Team for their amazing models! Result sources * [1] GPT-4 [Capabilities of GPT-4 on Medical Challenge Problems] (URL * [2] Med-PaLM-1 Large Language Models Encode Clinical Knowledge * [3] Med-PaLM-2 Towards Expert-Level Medical Question Answering with Large Language Models * [4] Gemini-1.0 Gemini Goes to Med School

[]

[ "TAGS\n#transformers #pytorch #llama #text-generation #llama-3 #Mixtral #instruct #finetune #chatml #DPO #RLHF #gpt4 #distillation #conversational #en #arxiv-2305.18290 #arxiv-2303.13375 #arxiv-2212.13138 #arxiv-2305.09617 #arxiv-2402.07023 #base_model-meta-llama/Meta-Llama-3-70B-Instruct #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n" ]

null

peft

# llama2-envi-tran-10000 This model is a fine-tuned version of [unsloth/llama-2-7b-bnb-4bit](https://huggingface.co/unsloth/llama-2-7b-bnb-4bit) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.0906 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0002 - train_batch_size: 8 - eval_batch_size: 4 - seed: 3407 - gradient_accumulation_steps: 4 - total_train_batch_size: 32 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 5 - num_epochs: 5 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | 1.1238 | 0.33 | 104 | 0.9544 | | 1.0108 | 0.67 | 208 | 0.9355 | | 1.0058 | 1.0 | 312 | 0.9277 | | 0.9212 | 1.33 | 416 | 0.9363 | | 0.9255 | 1.66 | 520 | 0.9323 | | 0.9222 | 2.0 | 624 | 0.9275 | | 0.7975 | 2.33 | 728 | 0.9634 | | 0.802 | 2.66 | 832 | 0.9622 | | 0.7979 | 3.0 | 936 | 0.9654 | | 0.6747 | 3.33 | 1040 | 1.0305 | | 0.6646 | 3.66 | 1144 | 1.0320 | | 0.6697 | 3.99 | 1248 | 1.0257 | | 0.5873 | 4.33 | 1352 | 1.0879 | | 0.5792 | 4.66 | 1456 | 1.0902 | | 0.5819 | 4.99 | 1560 | 1.0906 | ### Framework versions - PEFT 0.10.0 - Transformers 4.39.3 - Pytorch 2.2.2+cu121 - Datasets 2.16.0 - Tokenizers 0.15.2

{"license": "apache-2.0", "library_name": "peft", "tags": ["trl", "sft", "unsloth", "generated_from_trainer"], "base_model": "unsloth/llama-2-7b-bnb-4bit", "model-index": [{"name": "llama2-envi-tran-10000", "results": []}]}

mob2711/llama2-envi-tran-10000

null

[ "peft", "tensorboard", "safetensors", "trl", "sft", "unsloth", "generated_from_trainer", "base_model:unsloth/llama-2-7b-bnb-4bit", "license:apache-2.0", "region:us" ]

null

2024-04-27T01:22:19+00:00

[]

TAGS #peft #tensorboard #safetensors #trl #sft #unsloth #generated_from_trainer #base_model-unsloth/llama-2-7b-bnb-4bit #license-apache-2.0 #region-us

llama2-envi-tran-10000 ====================== This model is a fine-tuned version of unsloth/llama-2-7b-bnb-4bit on the None dataset. It achieves the following results on the evaluation set: * Loss: 1.0906 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0002 * train\_batch\_size: 8 * eval\_batch\_size: 4 * seed: 3407 * gradient\_accumulation\_steps: 4 * total\_train\_batch\_size: 32 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: cosine * lr\_scheduler\_warmup\_steps: 5 * num\_epochs: 5 * mixed\_precision\_training: Native AMP ### Training results ### Framework versions * PEFT 0.10.0 * Transformers 4.39.3 * Pytorch 2.2.2+cu121 * Datasets 2.16.0 * Tokenizers 0.15.2

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 4\n* seed: 3407\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 32\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\n* lr\\_scheduler\\_warmup\\_steps: 5\n* num\\_epochs: 5\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.39.3\n* Pytorch 2.2.2+cu121\n* Datasets 2.16.0\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #tensorboard #safetensors #trl #sft #unsloth #generated_from_trainer #base_model-unsloth/llama-2-7b-bnb-4bit #license-apache-2.0 #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 4\n* seed: 3407\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 32\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\n* lr\\_scheduler\\_warmup\\_steps: 5\n* num\\_epochs: 5\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.39.3\n* Pytorch 2.2.2+cu121\n* Datasets 2.16.0\n* Tokenizers 0.15.2" ]

null

peft

# GUE_virus_covid-seqsight_4096_512_46M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_virus_covid](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_virus_covid) dataset. It achieves the following results on the evaluation set: - Loss: 0.9287 - F1 Score: 0.6412 - Accuracy: 0.6377 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 2.1803 | 0.35 | 200 | 2.1724 | 0.1376 | 0.1585 | | 2.1374 | 0.7 | 400 | 2.0178 | 0.2202 | 0.2345 | | 1.9484 | 1.05 | 600 | 1.8007 | 0.2992 | 0.3036 | | 1.7811 | 1.4 | 800 | 1.6615 | 0.3624 | 0.3585 | | 1.6659 | 1.75 | 1000 | 1.5691 | 0.3986 | 0.3904 | | 1.6027 | 2.09 | 1200 | 1.5203 | 0.4294 | 0.4277 | | 1.5534 | 2.44 | 1400 | 1.4686 | 0.4508 | 0.4411 | | 1.5018 | 2.79 | 1600 | 1.4101 | 0.4675 | 0.4615 | | 1.4466 | 3.14 | 1800 | 1.3581 | 0.4899 | 0.4825 | | 1.4037 | 3.49 | 2000 | 1.3517 | 0.5056 | 0.4869 | | 1.377 | 3.84 | 2200 | 1.3013 | 0.5177 | 0.5086 | | 1.3263 | 4.19 | 2400 | 1.2510 | 0.5357 | 0.5213 | | 1.3028 | 4.54 | 2600 | 1.2173 | 0.5464 | 0.5419 | | 1.2795 | 4.89 | 2800 | 1.1947 | 0.5545 | 0.5496 | | 1.2464 | 5.24 | 3000 | 1.1615 | 0.5598 | 0.5533 | | 1.2267 | 5.58 | 3200 | 1.1412 | 0.5649 | 0.5616 | | 1.1977 | 5.93 | 3400 | 1.1200 | 0.5797 | 0.5745 | | 1.1765 | 6.28 | 3600 | 1.1011 | 0.5797 | 0.5772 | | 1.1565 | 6.63 | 3800 | 1.0822 | 0.5955 | 0.5883 | | 1.1371 | 6.98 | 4000 | 1.0718 | 0.5937 | 0.5913 | | 1.1211 | 7.33 | 4200 | 1.0479 | 0.6054 | 0.6015 | | 1.0994 | 7.68 | 4400 | 1.0352 | 0.6091 | 0.6043 | | 1.1013 | 8.03 | 4600 | 1.0245 | 0.6073 | 0.6066 | | 1.0758 | 8.38 | 4800 | 1.0250 | 0.6050 | 0.6031 | | 1.078 | 8.73 | 5000 | 1.0151 | 0.6113 | 0.6070 | | 1.0639 | 9.08 | 5200 | 1.0008 | 0.6213 | 0.6143 | | 1.0561 | 9.42 | 5400 | 0.9956 | 0.6152 | 0.6144 | | 1.0403 | 9.77 | 5600 | 0.9815 | 0.6249 | 0.6214 | | 1.0424 | 10.12 | 5800 | 0.9702 | 0.6322 | 0.6296 | | 1.0282 | 10.47 | 6000 | 0.9714 | 0.6280 | 0.6233 | | 1.016 | 10.82 | 6200 | 0.9732 | 0.6329 | 0.6233 | | 1.0003 | 11.17 | 6400 | 0.9658 | 0.6333 | 0.6260 | | 0.9984 | 11.52 | 6600 | 0.9598 | 0.6355 | 0.6270 | | 1.0111 | 11.87 | 6800 | 0.9515 | 0.6374 | 0.6307 | | 0.9989 | 12.22 | 7000 | 0.9558 | 0.6380 | 0.6304 | | 0.9844 | 12.57 | 7200 | 0.9471 | 0.6473 | 0.6359 | | 0.9938 | 12.91 | 7400 | 0.9502 | 0.6389 | 0.6315 | | 0.9856 | 13.26 | 7600 | 0.9465 | 0.6386 | 0.6295 | | 0.9793 | 13.61 | 7800 | 0.9420 | 0.6399 | 0.6309 | | 0.9789 | 13.96 | 8000 | 0.9383 | 0.6436 | 0.6387 | | 0.9654 | 14.31 | 8200 | 0.9317 | 0.6444 | 0.6380 | | 0.9687 | 14.66 | 8400 | 0.9353 | 0.6449 | 0.6370 | | 0.9773 | 15.01 | 8600 | 0.9351 | 0.6430 | 0.6386 | | 0.9756 | 15.36 | 8800 | 0.9294 | 0.6461 | 0.6404 | | 0.9526 | 15.71 | 9000 | 0.9306 | 0.6453 | 0.6406 | | 0.9682 | 16.06 | 9200 | 0.9280 | 0.6466 | 0.6404 | | 0.959 | 16.4 | 9400 | 0.9295 | 0.6447 | 0.6413 | | 0.9609 | 16.75 | 9600 | 0.9266 | 0.6493 | 0.6435 | | 0.961 | 17.1 | 9800 | 0.9272 | 0.6478 | 0.6419 | | 0.9618 | 17.45 | 10000 | 0.9274 | 0.6472 | 0.6416 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_virus_covid-seqsight_4096_512_46M-L32_f", "results": []}]}

mahdibaghbanzadeh/GUE_virus_covid-seqsight_4096_512_46M-L32_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_46M", "region:us" ]

null

2024-04-27T01:23:35+00:00

[]

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us

GUE\_virus\_covid-seqsight\_4096\_512\_46M-L32\_f ================================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_4096\_512\_46M on the mahdibaghbanzadeh/GUE\_virus\_covid dataset. It achieves the following results on the evaluation set: * Loss: 0.9287 * F1 Score: 0.6412 * Accuracy: 0.6377 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_4096_512_46M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

null

peft

# GUE_prom_prom_300_tata-seqsight_8192_512_30M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_8192_512_30M](https://huggingface.co/mahdibaghbanzadeh/seqsight_8192_512_30M) on the [mahdibaghbanzadeh/GUE_prom_prom_300_tata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_300_tata) dataset. It achieves the following results on the evaluation set: - Loss: 0.4320 - F1 Score: 0.8043 - Accuracy: 0.8042 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:------:|:-----:|:---------------:|:--------:|:--------:| | 0.5915 | 5.13 | 200 | 0.5190 | 0.7535 | 0.7569 | | 0.4672 | 10.26 | 400 | 0.4808 | 0.8027 | 0.8026 | | 0.4394 | 15.38 | 600 | 0.4687 | 0.8043 | 0.8042 | | 0.4249 | 20.51 | 800 | 0.4618 | 0.8027 | 0.8026 | | 0.4111 | 25.64 | 1000 | 0.4633 | 0.8027 | 0.8026 | | 0.3977 | 30.77 | 1200 | 0.4591 | 0.7960 | 0.7961 | | 0.3912 | 35.9 | 1400 | 0.4620 | 0.7910 | 0.7912 | | 0.3805 | 41.03 | 1600 | 0.4727 | 0.7970 | 0.7977 | | 0.3741 | 46.15 | 1800 | 0.4665 | 0.7926 | 0.7928 | | 0.3649 | 51.28 | 2000 | 0.4732 | 0.7929 | 0.7928 | | 0.3586 | 56.41 | 2200 | 0.4765 | 0.8044 | 0.8042 | | 0.3517 | 61.54 | 2400 | 0.4861 | 0.8043 | 0.8042 | | 0.3458 | 66.67 | 2600 | 0.4956 | 0.7976 | 0.7977 | | 0.3372 | 71.79 | 2800 | 0.4924 | 0.7978 | 0.7977 | | 0.3364 | 76.92 | 3000 | 0.4950 | 0.7913 | 0.7912 | | 0.3278 | 82.05 | 3200 | 0.5055 | 0.8027 | 0.8026 | | 0.3257 | 87.18 | 3400 | 0.5066 | 0.7945 | 0.7945 | | 0.3199 | 92.31 | 3600 | 0.5064 | 0.7995 | 0.7993 | | 0.3145 | 97.44 | 3800 | 0.5131 | 0.7946 | 0.7945 | | 0.3079 | 102.56 | 4000 | 0.5167 | 0.7961 | 0.7961 | | 0.3039 | 107.69 | 4200 | 0.5190 | 0.7962 | 0.7961 | | 0.3005 | 112.82 | 4400 | 0.5159 | 0.7995 | 0.7993 | | 0.299 | 117.95 | 4600 | 0.5180 | 0.7962 | 0.7961 | | 0.2902 | 123.08 | 4800 | 0.5274 | 0.7962 | 0.7961 | | 0.2866 | 128.21 | 5000 | 0.5370 | 0.7930 | 0.7928 | | 0.2893 | 133.33 | 5200 | 0.5397 | 0.7895 | 0.7896 | | 0.2819 | 138.46 | 5400 | 0.5363 | 0.7977 | 0.7977 | | 0.28 | 143.59 | 5600 | 0.5435 | 0.7881 | 0.7879 | | 0.2805 | 148.72 | 5800 | 0.5464 | 0.7977 | 0.7977 | | 0.2758 | 153.85 | 6000 | 0.5409 | 0.7929 | 0.7928 | | 0.2747 | 158.97 | 6200 | 0.5477 | 0.7913 | 0.7912 | | 0.2723 | 164.1 | 6400 | 0.5517 | 0.7961 | 0.7961 | | 0.2702 | 169.23 | 6600 | 0.5529 | 0.7913 | 0.7912 | | 0.2657 | 174.36 | 6800 | 0.5580 | 0.7897 | 0.7896 | | 0.2628 | 179.49 | 7000 | 0.5535 | 0.7913 | 0.7912 | | 0.2604 | 184.62 | 7200 | 0.5698 | 0.7912 | 0.7912 | | 0.2595 | 189.74 | 7400 | 0.5668 | 0.7929 | 0.7928 | | 0.2612 | 194.87 | 7600 | 0.5702 | 0.7962 | 0.7961 | | 0.2589 | 200.0 | 7800 | 0.5739 | 0.7896 | 0.7896 | | 0.2595 | 205.13 | 8000 | 0.5653 | 0.7880 | 0.7879 | | 0.2554 | 210.26 | 8200 | 0.5758 | 0.7897 | 0.7896 | | 0.2514 | 215.38 | 8400 | 0.5829 | 0.7863 | 0.7863 | | 0.2531 | 220.51 | 8600 | 0.5787 | 0.7880 | 0.7879 | | 0.2506 | 225.64 | 8800 | 0.5808 | 0.7881 | 0.7879 | | 0.2529 | 230.77 | 9000 | 0.5799 | 0.7929 | 0.7928 | | 0.247 | 235.9 | 9200 | 0.5822 | 0.7946 | 0.7945 | | 0.2498 | 241.03 | 9400 | 0.5814 | 0.7913 | 0.7912 | | 0.2467 | 246.15 | 9600 | 0.5820 | 0.7930 | 0.7928 | | 0.2499 | 251.28 | 9800 | 0.5824 | 0.7913 | 0.7912 | | 0.2494 | 256.41 | 10000 | 0.5827 | 0.7913 | 0.7912 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_8192_512_30M", "model-index": [{"name": "GUE_prom_prom_300_tata-seqsight_8192_512_30M-L1_f", "results": []}]}

mahdibaghbanzadeh/GUE_prom_prom_300_tata-seqsight_8192_512_30M-L1_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_8192_512_30M", "region:us" ]

null

2024-04-27T01:23:36+00:00

[]

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us

GUE\_prom\_prom\_300\_tata-seqsight\_8192\_512\_30M-L1\_f ========================================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_8192\_512\_30M on the mahdibaghbanzadeh/GUE\_prom\_prom\_300\_tata dataset. It achieves the following results on the evaluation set: * Loss: 0.4320 * F1 Score: 0.8043 * Accuracy: 0.8042 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

null

peft

# GUE_prom_prom_300_tata-seqsight_8192_512_30M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_8192_512_30M](https://huggingface.co/mahdibaghbanzadeh/seqsight_8192_512_30M) on the [mahdibaghbanzadeh/GUE_prom_prom_300_tata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_300_tata) dataset. It achieves the following results on the evaluation set: - Loss: 0.4340 - F1 Score: 0.8107 - Accuracy: 0.8108 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:------:|:-----:|:---------------:|:--------:|:--------:| | 0.5361 | 5.13 | 200 | 0.4726 | 0.7999 | 0.8010 | | 0.4311 | 10.26 | 400 | 0.4750 | 0.7991 | 0.7993 | | 0.3906 | 15.38 | 600 | 0.4535 | 0.8156 | 0.8157 | | 0.3587 | 20.51 | 800 | 0.4676 | 0.8189 | 0.8189 | | 0.338 | 25.64 | 1000 | 0.4852 | 0.8141 | 0.8140 | | 0.3033 | 30.77 | 1200 | 0.5177 | 0.7927 | 0.7928 | | 0.2868 | 35.9 | 1400 | 0.5366 | 0.8027 | 0.8026 | | 0.264 | 41.03 | 1600 | 0.5506 | 0.8093 | 0.8091 | | 0.2439 | 46.15 | 1800 | 0.5622 | 0.7961 | 0.7961 | | 0.2265 | 51.28 | 2000 | 0.5868 | 0.8010 | 0.8010 | | 0.2082 | 56.41 | 2200 | 0.6659 | 0.7979 | 0.7977 | | 0.1918 | 61.54 | 2400 | 0.7247 | 0.7755 | 0.7765 | | 0.1845 | 66.67 | 2600 | 0.6934 | 0.7815 | 0.7814 | | 0.1682 | 71.79 | 2800 | 0.7161 | 0.7878 | 0.7879 | | 0.1634 | 76.92 | 3000 | 0.7996 | 0.7763 | 0.7765 | | 0.1513 | 82.05 | 3200 | 0.8184 | 0.7799 | 0.7798 | | 0.1417 | 87.18 | 3400 | 0.8684 | 0.7552 | 0.7569 | | 0.1415 | 92.31 | 3600 | 0.8256 | 0.7864 | 0.7863 | | 0.1262 | 97.44 | 3800 | 0.8991 | 0.7653 | 0.7651 | | 0.1194 | 102.56 | 4000 | 0.9260 | 0.7717 | 0.7716 | | 0.1182 | 107.69 | 4200 | 0.9309 | 0.7648 | 0.7651 | | 0.1072 | 112.82 | 4400 | 0.9617 | 0.7685 | 0.7684 | | 0.1034 | 117.95 | 4600 | 0.9810 | 0.7750 | 0.7749 | | 0.1029 | 123.08 | 4800 | 0.9391 | 0.7766 | 0.7765 | | 0.0926 | 128.21 | 5000 | 1.0178 | 0.7668 | 0.7667 | | 0.0956 | 133.33 | 5200 | 0.9644 | 0.7749 | 0.7749 | | 0.0872 | 138.46 | 5400 | 1.0404 | 0.7766 | 0.7765 | | 0.0829 | 143.59 | 5600 | 1.0505 | 0.7797 | 0.7798 | | 0.0811 | 148.72 | 5800 | 1.0447 | 0.7815 | 0.7814 | | 0.0792 | 153.85 | 6000 | 1.0644 | 0.7797 | 0.7798 | | 0.0774 | 158.97 | 6200 | 1.1230 | 0.7782 | 0.7781 | | 0.0736 | 164.1 | 6400 | 1.0981 | 0.7799 | 0.7798 | | 0.0747 | 169.23 | 6600 | 1.0630 | 0.7798 | 0.7798 | | 0.0729 | 174.36 | 6800 | 1.0963 | 0.7813 | 0.7814 | | 0.07 | 179.49 | 7000 | 1.1042 | 0.7766 | 0.7765 | | 0.0679 | 184.62 | 7200 | 1.1413 | 0.7718 | 0.7716 | | 0.0635 | 189.74 | 7400 | 1.1705 | 0.7750 | 0.7749 | | 0.0645 | 194.87 | 7600 | 1.1721 | 0.7782 | 0.7781 | | 0.0669 | 200.0 | 7800 | 1.1447 | 0.7767 | 0.7765 | | 0.0659 | 205.13 | 8000 | 1.1749 | 0.7766 | 0.7765 | | 0.0616 | 210.26 | 8200 | 1.1785 | 0.7750 | 0.7749 | | 0.0553 | 215.38 | 8400 | 1.2185 | 0.7701 | 0.7700 | | 0.0645 | 220.51 | 8600 | 1.1544 | 0.7766 | 0.7765 | | 0.0574 | 225.64 | 8800 | 1.2041 | 0.7734 | 0.7732 | | 0.0631 | 230.77 | 9000 | 1.1826 | 0.7782 | 0.7781 | | 0.0556 | 235.9 | 9200 | 1.1807 | 0.7782 | 0.7781 | | 0.061 | 241.03 | 9400 | 1.1816 | 0.7782 | 0.7781 | | 0.0562 | 246.15 | 9600 | 1.2023 | 0.7814 | 0.7814 | | 0.0563 | 251.28 | 9800 | 1.1978 | 0.7783 | 0.7781 | | 0.0553 | 256.41 | 10000 | 1.1962 | 0.7831 | 0.7830 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_8192_512_30M", "model-index": [{"name": "GUE_prom_prom_300_tata-seqsight_8192_512_30M-L8_f", "results": []}]}

mahdibaghbanzadeh/GUE_prom_prom_300_tata-seqsight_8192_512_30M-L8_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_8192_512_30M", "region:us" ]

null

2024-04-27T01:26:35+00:00

[]

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us

GUE\_prom\_prom\_300\_tata-seqsight\_8192\_512\_30M-L8\_f ========================================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_8192\_512\_30M on the mahdibaghbanzadeh/GUE\_prom\_prom\_300\_tata dataset. It achieves the following results on the evaluation set: * Loss: 0.4340 * F1 Score: 0.8107 * Accuracy: 0.8108 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

text2text-generation

transformers

# CS505_COQE_viT5_train_Instruction0_OPASL_v1 This model is a fine-tuned version of [VietAI/vit5-large](https://huggingface.co/VietAI/vit5-large) on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 20 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.15.2

{"license": "mit", "tags": ["generated_from_trainer"], "base_model": "VietAI/vit5-large", "model-index": [{"name": "CS505_COQE_viT5_train_Instruction0_OPASL_v1", "results": []}]}

ThuyNT/CS505_COQE_viT5_train_Instruction0_OPASL_v1

null

[ "transformers", "tensorboard", "safetensors", "t5", "text2text-generation", "generated_from_trainer", "base_model:VietAI/vit5-large", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

null

2024-04-27T01:29:08+00:00

[]

TAGS #transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-VietAI/vit5-large #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

# CS505_COQE_viT5_train_Instruction0_OPASL_v1 This model is a fine-tuned version of VietAI/vit5-large on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 20 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.15.2

[ "# CS505_COQE_viT5_train_Instruction0_OPASL_v1\n\nThis model is a fine-tuned version of VietAI/vit5-large on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 20\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-VietAI/vit5-large #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# CS505_COQE_viT5_train_Instruction0_OPASL_v1\n\nThis model is a fine-tuned version of VietAI/vit5-large on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 20\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

null

peft

# GUE_prom_prom_300_tata-seqsight_8192_512_30M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_8192_512_30M](https://huggingface.co/mahdibaghbanzadeh/seqsight_8192_512_30M) on the [mahdibaghbanzadeh/GUE_prom_prom_300_tata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_300_tata) dataset. It achieves the following results on the evaluation set: - Loss: 0.4592 - F1 Score: 0.8205 - Accuracy: 0.8206 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:------:|:-----:|:---------------:|:--------:|:--------:| | 0.5086 | 5.13 | 200 | 0.4565 | 0.7930 | 0.7928 | | 0.3952 | 10.26 | 400 | 0.5182 | 0.7677 | 0.7700 | | 0.33 | 15.38 | 600 | 0.4784 | 0.8207 | 0.8206 | | 0.2734 | 20.51 | 800 | 0.5296 | 0.8043 | 0.8042 | | 0.2262 | 25.64 | 1000 | 0.6202 | 0.8027 | 0.8026 | | 0.1855 | 30.77 | 1200 | 0.7224 | 0.7817 | 0.7830 | | 0.1554 | 35.9 | 1400 | 0.7096 | 0.8106 | 0.8108 | | 0.1271 | 41.03 | 1600 | 0.7358 | 0.8093 | 0.8091 | | 0.1132 | 46.15 | 1800 | 0.7646 | 0.8027 | 0.8026 | | 0.0916 | 51.28 | 2000 | 0.9272 | 0.7911 | 0.7912 | | 0.0795 | 56.41 | 2200 | 0.9784 | 0.7924 | 0.7928 | | 0.0763 | 61.54 | 2400 | 1.0530 | 0.7833 | 0.7847 | | 0.0701 | 66.67 | 2600 | 0.9257 | 0.8027 | 0.8026 | | 0.0577 | 71.79 | 2800 | 1.0282 | 0.7993 | 0.7993 | | 0.056 | 76.92 | 3000 | 1.0811 | 0.7979 | 0.7977 | | 0.0545 | 82.05 | 3200 | 1.0417 | 0.7831 | 0.7830 | | 0.0496 | 87.18 | 3400 | 0.9956 | 0.7913 | 0.7912 | | 0.0465 | 92.31 | 3600 | 1.1224 | 0.7911 | 0.7912 | | 0.0431 | 97.44 | 3800 | 1.0531 | 0.7946 | 0.7945 | | 0.0384 | 102.56 | 4000 | 1.1811 | 0.7995 | 0.7993 | | 0.0383 | 107.69 | 4200 | 1.1002 | 0.8011 | 0.8010 | | 0.0355 | 112.82 | 4400 | 1.1293 | 0.7995 | 0.7993 | | 0.0357 | 117.95 | 4600 | 1.1393 | 0.8027 | 0.8026 | | 0.0332 | 123.08 | 4800 | 1.2111 | 0.7944 | 0.7945 | | 0.0289 | 128.21 | 5000 | 1.2221 | 0.7995 | 0.7993 | | 0.0283 | 133.33 | 5200 | 1.2444 | 0.7977 | 0.7977 | | 0.0287 | 138.46 | 5400 | 1.2123 | 0.8027 | 0.8026 | | 0.0266 | 143.59 | 5600 | 1.2331 | 0.8044 | 0.8042 | | 0.0273 | 148.72 | 5800 | 1.2408 | 0.8011 | 0.8010 | | 0.0255 | 153.85 | 6000 | 1.2152 | 0.8044 | 0.8042 | | 0.0252 | 158.97 | 6200 | 1.2034 | 0.8011 | 0.8010 | | 0.0232 | 164.1 | 6400 | 1.1980 | 0.7995 | 0.7993 | | 0.0252 | 169.23 | 6600 | 1.2003 | 0.7913 | 0.7912 | | 0.0218 | 174.36 | 6800 | 1.2275 | 0.7946 | 0.7945 | | 0.0209 | 179.49 | 7000 | 1.3166 | 0.7993 | 0.7993 | | 0.0202 | 184.62 | 7200 | 1.2827 | 0.7995 | 0.7993 | | 0.0202 | 189.74 | 7400 | 1.2810 | 0.7962 | 0.7961 | | 0.0184 | 194.87 | 7600 | 1.2615 | 0.7929 | 0.7928 | | 0.0194 | 200.0 | 7800 | 1.2767 | 0.7930 | 0.7928 | | 0.02 | 205.13 | 8000 | 1.2672 | 0.7978 | 0.7977 | | 0.0211 | 210.26 | 8200 | 1.2335 | 0.7962 | 0.7961 | | 0.0172 | 215.38 | 8400 | 1.3205 | 0.7962 | 0.7961 | | 0.018 | 220.51 | 8600 | 1.3163 | 0.7979 | 0.7977 | | 0.016 | 225.64 | 8800 | 1.3450 | 0.7913 | 0.7912 | | 0.0175 | 230.77 | 9000 | 1.3278 | 0.7995 | 0.7993 | | 0.0151 | 235.9 | 9200 | 1.3556 | 0.7962 | 0.7961 | | 0.0159 | 241.03 | 9400 | 1.3456 | 0.7979 | 0.7977 | | 0.0148 | 246.15 | 9600 | 1.3545 | 0.7962 | 0.7961 | | 0.015 | 251.28 | 9800 | 1.3576 | 0.7979 | 0.7977 | | 0.0136 | 256.41 | 10000 | 1.3621 | 0.7962 | 0.7961 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_8192_512_30M", "model-index": [{"name": "GUE_prom_prom_300_tata-seqsight_8192_512_30M-L32_f", "results": []}]}

mahdibaghbanzadeh/GUE_prom_prom_300_tata-seqsight_8192_512_30M-L32_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_8192_512_30M", "region:us" ]

null

2024-04-27T01:30:04+00:00

[]

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us

GUE\_prom\_prom\_300\_tata-seqsight\_8192\_512\_30M-L32\_f ========================================================== This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_8192\_512\_30M on the mahdibaghbanzadeh/GUE\_prom\_prom\_300\_tata dataset. It achieves the following results on the evaluation set: * Loss: 0.4592 * F1 Score: 0.8205 * Accuracy: 0.8206 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

null

peft

# GUE_prom_prom_300_notata-seqsight_8192_512_30M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_8192_512_30M](https://huggingface.co/mahdibaghbanzadeh/seqsight_8192_512_30M) on the [mahdibaghbanzadeh/GUE_prom_prom_300_notata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_300_notata) dataset. It achieves the following results on the evaluation set: - Loss: 0.1256 - F1 Score: 0.9533 - Accuracy: 0.9533 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.3525 | 0.6 | 200 | 0.1641 | 0.9355 | 0.9356 | | 0.1746 | 1.2 | 400 | 0.1422 | 0.9448 | 0.9448 | | 0.1614 | 1.81 | 600 | 0.1324 | 0.9467 | 0.9467 | | 0.1496 | 2.41 | 800 | 0.1273 | 0.9487 | 0.9487 | | 0.1434 | 3.01 | 1000 | 0.1223 | 0.9514 | 0.9514 | | 0.1416 | 3.61 | 1200 | 0.1195 | 0.9529 | 0.9529 | | 0.1389 | 4.22 | 1400 | 0.1215 | 0.9527 | 0.9527 | | 0.1355 | 4.82 | 1600 | 0.1168 | 0.9540 | 0.9540 | | 0.132 | 5.42 | 1800 | 0.1173 | 0.9542 | 0.9542 | | 0.1277 | 6.02 | 2000 | 0.1153 | 0.9533 | 0.9533 | | 0.1289 | 6.63 | 2200 | 0.1133 | 0.9542 | 0.9542 | | 0.1253 | 7.23 | 2400 | 0.1126 | 0.9553 | 0.9553 | | 0.122 | 7.83 | 2600 | 0.1120 | 0.9557 | 0.9557 | | 0.125 | 8.43 | 2800 | 0.1117 | 0.9574 | 0.9574 | | 0.1245 | 9.04 | 3000 | 0.1137 | 0.9544 | 0.9544 | | 0.1219 | 9.64 | 3200 | 0.1172 | 0.9557 | 0.9557 | | 0.1194 | 10.24 | 3400 | 0.1133 | 0.9557 | 0.9557 | | 0.1223 | 10.84 | 3600 | 0.1084 | 0.9600 | 0.9601 | | 0.1147 | 11.45 | 3800 | 0.1077 | 0.9595 | 0.9595 | | 0.114 | 12.05 | 4000 | 0.1084 | 0.9597 | 0.9597 | | 0.1192 | 12.65 | 4200 | 0.1076 | 0.9568 | 0.9568 | | 0.1193 | 13.25 | 4400 | 0.1075 | 0.9587 | 0.9587 | | 0.1142 | 13.86 | 4600 | 0.1064 | 0.9597 | 0.9597 | | 0.1148 | 14.46 | 4800 | 0.1082 | 0.9583 | 0.9584 | | 0.1122 | 15.06 | 5000 | 0.1051 | 0.9589 | 0.9589 | | 0.1125 | 15.66 | 5200 | 0.1068 | 0.9587 | 0.9587 | | 0.1146 | 16.27 | 5400 | 0.1062 | 0.9587 | 0.9587 | | 0.1106 | 16.87 | 5600 | 0.1041 | 0.9604 | 0.9604 | | 0.1111 | 17.47 | 5800 | 0.1042 | 0.9595 | 0.9595 | | 0.1158 | 18.07 | 6000 | 0.1045 | 0.9593 | 0.9593 | | 0.1103 | 18.67 | 6200 | 0.1052 | 0.9585 | 0.9585 | | 0.1118 | 19.28 | 6400 | 0.1043 | 0.9604 | 0.9604 | | 0.1096 | 19.88 | 6600 | 0.1067 | 0.9583 | 0.9584 | | 0.1107 | 20.48 | 6800 | 0.1058 | 0.9597 | 0.9597 | | 0.1079 | 21.08 | 7000 | 0.1042 | 0.9602 | 0.9602 | | 0.1086 | 21.69 | 7200 | 0.1042 | 0.9612 | 0.9612 | | 0.1078 | 22.29 | 7400 | 0.1054 | 0.9612 | 0.9612 | | 0.1101 | 22.89 | 7600 | 0.1028 | 0.9616 | 0.9616 | | 0.1092 | 23.49 | 7800 | 0.1026 | 0.9606 | 0.9606 | | 0.1054 | 24.1 | 8000 | 0.1034 | 0.9602 | 0.9602 | | 0.108 | 24.7 | 8200 | 0.1033 | 0.9599 | 0.9599 | | 0.1071 | 25.3 | 8400 | 0.1044 | 0.9600 | 0.9601 | | 0.1075 | 25.9 | 8600 | 0.1023 | 0.9608 | 0.9608 | | 0.1071 | 26.51 | 8800 | 0.1024 | 0.9606 | 0.9606 | | 0.1078 | 27.11 | 9000 | 0.1025 | 0.9608 | 0.9608 | | 0.1052 | 27.71 | 9200 | 0.1031 | 0.9606 | 0.9606 | | 0.1041 | 28.31 | 9400 | 0.1030 | 0.9608 | 0.9608 | | 0.1089 | 28.92 | 9600 | 0.1026 | 0.9608 | 0.9608 | | 0.1043 | 29.52 | 9800 | 0.1029 | 0.9608 | 0.9608 | | 0.1089 | 30.12 | 10000 | 0.1028 | 0.9608 | 0.9608 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_8192_512_30M", "model-index": [{"name": "GUE_prom_prom_300_notata-seqsight_8192_512_30M-L1_f", "results": []}]}

mahdibaghbanzadeh/GUE_prom_prom_300_notata-seqsight_8192_512_30M-L1_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_8192_512_30M", "region:us" ]

null

2024-04-27T01:30:18+00:00

[]

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us

GUE\_prom\_prom\_300\_notata-seqsight\_8192\_512\_30M-L1\_f =========================================================== This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_8192\_512\_30M on the mahdibaghbanzadeh/GUE\_prom\_prom\_300\_notata dataset. It achieves the following results on the evaluation set: * Loss: 0.1256 * F1 Score: 0.9533 * Accuracy: 0.9533 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

text-generation

transformers

<div align="center"> <img width="260px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/BrQCb95lmEIFz79QAmoNA.png"></div> ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/fJIOPJnY6Ff6fUiSIuMEt.png) <div align="center"> <h1>Advancing Open-source Large Language Models in Medical Domain</h1> </div> <p align="center" style="margin-top: 0px;"> <a href="https://colab.research.google.com/drive/1F5oV20InEYeAJGmBwYF9NM_QhLmjBkKJ?usp=sharing"> <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="OpenChat Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 10px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style=" margin-right: 5px;">Online Demo</span> </a> | <a href="https://github.com/openlifescience-ai"> <img src="https://github.githubassets.com/assets/GitHub-Mark-ea2971cee799.png" alt="GitHub Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style=" margin-right: 5px;">GitHub</span> </a> | <a href="#"> <img src="https://github.com/alpayariyak/openchat/blob/master/assets/arxiv-logomark-small-square-border.png?raw=true" alt="ArXiv Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style="margin-right: 5px;">Paper</span> </a> | <a href="https://discord.gg/A5Fjf5zC69"> <img src="https://cloud.githubusercontent.com/assets/6291467/26705903/96c2d66e-477c-11e7-9f4e-f3c0efe96c9a.png" alt="Discord Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text">Discord</span> </a> </p> ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/KGmRE5w2sepNtwsEu8t7K.jpeg) Introducing OpenBioLLM-70B: A State-of-the-Art Open Source Biomedical Large Language Model OpenBioLLM-70B is an advanced open source language model designed specifically for the biomedical domain. Developed by Saama AI Labs, this model leverages cutting-edge techniques to achieve state-of-the-art performance on a wide range of biomedical tasks. 🏥 **Biomedical Specialization**: OpenBioLLM-70B is tailored for the unique language and knowledge requirements of the medical and life sciences fields. It was fine-tuned on a vast corpus of high-quality biomedical data, enabling it to understand and generate text with domain-specific accuracy and fluency. 🎓 **Superior Performance**: With 70 billion parameters, OpenBioLLM-70B outperforms other open source biomedical language models of similar scale. It has also demonstrated better results compared to larger proprietary & open-source models like GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 on biomedical benchmarks. 🧠 **Advanced Training Techniques**: OpenBioLLM-70B builds upon the powerful foundations of the **Meta-Llama-3-70B-Instruct** and [Meta-Llama-3-70B-Instruct](meta-llama/Meta-Llama-3-70B-Instruct) models. It incorporates the DPO dataset and fine-tuning recipe along with a custom diverse medical instruction dataset. Key components of the training pipeline include: <div align="center"> <img width="1200px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/oPchsJsEpQoGcGXVbh7YS.png"> </div> - **Policy Optimization**: [Direct Preference Optimization: Your Language Model is Secretly a Reward Model (DPO)](https://arxiv.org/abs/2305.18290) - **Fine-tuning dataset**: Custom Medical Instruct dataset (We plan to release a sample training dataset in our upcoming paper; please stay updated) This combination of cutting-edge techniques enables OpenBioLLM-70B to align with key capabilities and preferences for biomedical applications. ⚙️ **Release Details**: - **Model Size**: 70 billion parameters - **Quantization**: Optimized quantized versions available [Here](https://huggingface.co/aaditya/OpenBioLLM-70B-GGUF) - **Language(s) (NLP):** en - **Developed By**: [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) from Saama AI Labs - **License:** Meta-Llama License - **Fine-tuned from models:** [Meta-Llama-3-70B-Instruct](meta-llama/Meta-Llama-3-70B-Instruct) - **Resources for more information:** - Paper: Coming soon The model can be fine-tuned for more specialized tasks and datasets as needed. OpenBioLLM-70B represents an important step forward in democratizing advanced language AI for the biomedical community. By leveraging state-of-the-art architectures and training techniques from leading open source efforts like Llama-3, we have created a powerful tool to accelerate innovation and discovery in healthcare and the life sciences. We are excited to share OpenBioLLM-70B with researchers and developers around the world. ### Use with transformers **Important: Please use the exact chat template provided by Llama-3 instruct version. Otherwise there will be a degradation in the performance. The model output can be verbose in rare cases. Please consider setting temperature = 0 to make this happen less.** See the snippet below for usage with Transformers: ```python import transformers import torch model_id = "aaditya/OpenBioLLM-Llama3-70B" pipeline = transformers.pipeline( "text-generation", model=model_id, model_kwargs={"torch_dtype": torch.bfloat16}, device="auto", ) messages = [ {"role": "system", "content": "You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience. Your name is OpenBioLLM, and you were developed by Saama AI Labs. who's willing to help answer the user's query with explanation. In your explanation, leverage your deep medical expertise such as relevant anatomical structures, physiological processes, diagnostic criteria, treatment guidelines, or other pertinent medical concepts. Use precise medical terminology while still aiming to make the explanation clear and accessible to a general audience."}, {"role": "user", "content": "How can i split a 3mg or 4mg waefin pill so i can get a 2.5mg pill?"}, ] prompt = pipeline.tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) terminators = [ pipeline.tokenizer.eos_token_id, pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>") ] outputs = pipeline( prompt, max_new_tokens=256, eos_token_id=terminators, do_sample=True, temperature=0.0, top_p=0.9, ) print(outputs[0]["generated_text"][len(prompt):]) ``` ## **Training procedure** ### **Training hyperparameters** <details> <summary>Click to see details</summary> - learning_rate: 0.0002 - lr_scheduler: cosine - train_batch_size: 12 - eval_batch_size: 8 - GPU: H100 80GB SXM5 - num_devices: 8 - optimizer: adamw_bnb_8bit - lr_scheduler_warmup_steps: 100 - num_epochs: 4 </details> ### **Peft hyperparameters** <details> <summary>Click to see details</summary> - adapter: qlora - lora_r: 128 - lora_alpha: 256 - lora_dropout: 0.05 - lora_target_linear: true -lora_target_modules: - q_proj - v_proj - k_proj - o_proj - gate_proj - down_proj - up_proj </details> ### **Training results** ### **Framework versions** - Transformers 4.39.3 - Pytorch 2.1.2+cu121 - Datasets 2.18.0 - Tokenizers 0.15.1 - Axolotl - Lm harness for evaluation # Benchmark Results 🔥 OpenBioLLM-70B demonstrates superior performance compared to larger models, such as GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 across 9 diverse biomedical datasets, achieving state-of-the-art results with an average score of 86.06%, despite having a significantly smaller parameter count. The model's strong performance in domain-specific tasks, such as Clinical KG, Medical Genetics, and PubMedQA, highlights its ability to effectively capture and apply biomedical knowledge. 🚨 The GPT-4, Med-PaLM-1, and Med-PaLM-2 results are taken from their official papers. Since Med-PaLM doesn't provide zero-shot accuracy, we are using 5-shot accuracy from their paper for comparison. All results presented are in the zero-shot setting, except for Med-PaLM-2 and Med-PaLM-1, which use 5-shot accuracy. | | Clinical KG | Medical Genetics | Anatomy | Pro Medicine | College Biology | College Medicine | MedQA 4 opts | PubMedQA | MedMCQA | Avg | |--------------------|-------------|------------------|---------|--------------|-----------------|------------------|--------------|----------|---------|-------| | **OpenBioLLM-70B** | **92.93** | **93.197** | **83.904** | 93.75 | 93.827 | **85.749** | 78.162 | 78.97 | **74.014** | **86.05588** | | Med-PaLM-2 (5-shot) | 88.3 | 90 | 77.8 | **95.2** | 94.4 | 80.9 | **79.7** | **79.2** | 71.3 | 84.08 | | **GPT-4** | 86.04 | 91 | 80 | 93.01 | **95.14** | 76.88 | 78.87 | 75.2 | 69.52 | 82.85 | | Med-PaLM-1 (Flan-PaLM, 5-shot) | 80.4 | 75 | 63.7 | 83.8 | 88.9 | 76.3 | 67.6 | 79 | 57.6 | 74.7 | | **OpenBioLLM-8B** | 76.101 | 86.1 | 69.829 | 78.21 | 84.213 | 68.042 | 58.993 | 74.12 | 56.913 | 72.502 | | Gemini-1.0 | 76.7 | 75.8 | 66.7 | 77.7 | 88 | 69.2 | 58 | 70.7 | 54.3 | 70.79 | | GPT-3.5 Turbo 1106 | 74.71 | 74 | 72.79 | 72.79 | 72.91 | 64.73 | 57.71 | 72.66 | 53.79 | 66 | | Meditron-70B | 66.79 | 69 | 53.33 | 71.69 | 76.38 | 63 | 57.1 | 76.6 | 46.85 | 64.52 | | gemma-7b | 69.81 | 70 | 59.26 | 66.18 | 79.86 | 60.12 | 47.21 | 76.2 | 48.96 | 64.18 | | Mistral-7B-v0.1 | 68.68 | 71 | 55.56 | 68.38 | 68.06 | 59.54 | 50.82 | 75.4 | 48.2 | 62.85 | | Apollo-7B | 62.26 | 72 | 61.48 | 69.12 | 70.83 | 55.49 | 55.22 | 39.8 | 53.77 | 60 | | MedAlpaca-7b | 57.36 | 69 | 57.04 | 67.28 | 65.28 | 54.34 | 41.71 | 72.8 | 37.51 | 58.03 | | BioMistral-7B | 59.9 | 64 | 56.5 | 60.4 | 59 | 54.7 | 50.6 | 77.5 | 48.1 | 57.3 | | AlpaCare-llama2-7b | 49.81 | 49 | 45.92 | 33.82 | 50 | 43.35 | 29.77 | 72.2 | 34.42 | 45.36 | | ClinicalGPT | 30.56 | 27 | 30.37 | 19.48 | 25 | 24.27 | 26.08 | 63.8 | 28.18 | 30.52 | <div align="center"> <img width="1600px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/_SzdcJSBjZyo8RS1bTEkP.png"> </div> ## Detailed Medical Subjectwise accuracy ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/UXF-V0col0Z0sS6BGPBkE.png) # Use Cases & Examples 🚨 **Below results are from the quantized version of OpenBioLLM-70B # Summarize Clinical Notes OpenBioLLM-70B can efficiently analyze and summarize complex clinical notes, EHR data, and discharge summaries, extracting key information and generating concise, structured summaries ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/xdwdBgOxNi_TfML0hKlI8.png) # Answer Medical Questions OpenBioLLM-70B can provide answers to a wide range of medical questions. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/zO95GlwOQEZqCKQF69mE6.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/OKBczKw7gWeW5xsuDpc27.png) <details> <summary>Click to see details</summary> ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/eJGHT5khppYvJb8fQ-YW4.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/Cnbwrqa_-ORHRuNRC2P6Y.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/J9DhdcvukAc9mnnW9fj2C.png) </details> # Clinical Entity Recognition OpenBioLLM-70B can perform advanced clinical entity recognition by identifying and extracting key medical concepts, such as diseases, symptoms, medications, procedures, and anatomical structures, from unstructured clinical text. By leveraging its deep understanding of medical terminology and context, the model can accurately annotate and categorize clinical entities, enabling more efficient information retrieval, data analysis, and knowledge discovery from electronic health records, research articles, and other biomedical text sources. This capability can support various downstream applications, such as clinical decision support, pharmacovigilance, and medical research. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/_69BW4k9LVABFwtxixL45.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/DKy5wYCoPhoPPUc1-x8_J.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/7WD9zCCBZT4-4XlfnIQjl.png) # Biomarkers Extraction ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/ZttoM4AiteT7gFYVhjIpN.png) # Classification OpenBioLLM-70B can perform various biomedical classification tasks, such as disease prediction, sentiment analysis, medical document categorization ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/Bf5MW1d75qT-1F_TR_hC0.png) # De-Identification OpenBioLLM-70B can detect and remove personally identifiable information (PII) from medical records, ensuring patient privacy and compliance with data protection regulations like HIPAA. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/hKX4kzm--Tw5bj6K78msy.png) **Advisory Notice!** While OpenBioLLM-70B leverages high-quality data sources, its outputs may still contain inaccuracies, biases, or misalignments that could pose risks if relied upon for medical decision-making without further testing and refinement. The model's performance has not yet been rigorously evaluated in randomized controlled trials or real-world healthcare environments. Therefore, we strongly advise against using OpenBioLLM-70B for any direct patient care, clinical decision support, or other professional medical purposes at this time. Its use should be limited to research, development, and exploratory applications by qualified individuals who understand its limitations. OpenBioLLM-70B is intended solely as a research tool to assist healthcare professionals and should never be considered a replacement for the professional judgment and expertise of a qualified medical doctor. Appropriately adapting and validating OpenBioLLM-70B for specific medical use cases would require significant additional work, potentially including: - Thorough testing and evaluation in relevant clinical scenarios - Alignment with evidence-based guidelines and best practices - Mitigation of potential biases and failure modes - Integration with human oversight and interpretation - Compliance with regulatory and ethical standards Always consult a qualified healthcare provider for personal medical needs. # Citation If you find OpenBioLLM-70B & 8B useful in your work, please cite the model as follows: ``` @misc{OpenBioLLMs, author = {Ankit Pal, Malaikannan Sankarasubbu}, title = {OpenBioLLMs: Advancing Open-Source Large Language Models for Healthcare and Life Sciences}, year = {2024}, publisher = {Hugging Face}, journal = {Hugging Face repository}, howpublished = {\url{https://huggingface.co/aaditya/OpenBioLLM-Llama3-70B}} } ``` The accompanying paper is currently in progress and will be released soon. <div align="center"> <h2> 💌 Contact </h2> </div> We look forward to hearing you and collaborating on this exciting project! **Contributors:** - [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) [aadityaura at gmail dot com] - Saama AI Labs - Note: I am looking for a funded PhD opportunity, especially if it fits my Responsible Generative AI, Multimodal LLMs, Geometric Deep Learning, and Healthcare AI skillset. # References We thank the [Meta Team](meta-llama/Meta-Llama-3-70B-Instruct) for their amazing models! Result sources - [1] GPT-4 [Capabilities of GPT-4 on Medical Challenge Problems] (https://arxiv.org/abs/2303.13375) - [2] Med-PaLM-1 [Large Language Models Encode Clinical Knowledge](https://arxiv.org/abs/2212.13138) - [3] Med-PaLM-2 [Towards Expert-Level Medical Question Answering with Large Language Models](https://arxiv.org/abs/2305.09617) - [4] Gemini-1.0 [Gemini Goes to Med School](https://arxiv.org/abs/2402.07023)

{"language": ["en"], "license": "llama3", "tags": ["llama-3", "llama", "Mixtral", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "distillation"], "base_model": "meta-llama/Meta-Llama-3-70B-Instruct", "widget": [{"example_title": "OpenBioLLM-70B", "messages": [{"role": "system", "content": "You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience."}, {"role": "user", "content": "How long does it take for newborn jaundice to go away?"}], "output": {"text": "Newborn jaundice, also known as neonatal jaundice, is a common condition in newborns where the yellowing of the skin and eyes occurs due to an elevated level of bilirubin in the blood. Bilirubin is a yellow pigment that forms when red blood cells break down. In most cases, newborn jaundice resolves on its own without any specific treatment.\nThe duration of newborn jaundice can vary depending on several factors such as the underlying cause, gestational age at birth, and individual variations in bilirubin metabolism. Here are some general guidelines:\n1. Physiological jaundice: This is the most common type of newborn jaundice and usually appears within 24-72 hours after birth. It tends to peak between the second and fifth day of life and gradually improves over the next week or two. By the time the baby is one week old, the jaundice should have mostly resolved. 2. Breast milk jaundice: This type of jaundice occurs in breastfed babies and may appear later than physiological jaundice, typically between the fifth and fourteenth day of life. It tends to persist for a longer duration but usually resolves within six weeks after birth. 3. Pathological jaundice: This type of jaundice is less common and occurs due to an underlying medical condition that affects bilirubin metabolism or liver function. The duration of pathological jaundice depends on the specific cause and may require treatment.\nIt's important for parents to monitor their newborn's jaundice closely and seek medical advice if the jaundice progresses rapidly, becomes severe, or is accompanied by other symptoms such as poor feeding, lethargy, or excessive sleepiness. In these cases, further evaluation and management may be necessary. Remember that each baby is unique, and the timing of jaundice resolution can vary. If you have concerns about your newborn's jaundice, it's always best to consult with a healthcare professional for personalized advice and guidance."}}], "model-index": [{"name": "OpenBioLLM-70B", "results": []}]}

LoneStriker/OpenBioLLM-Llama3-70B-4.0bpw-h6-exl2

null

[ "transformers", "pytorch", "llama", "text-generation", "llama-3", "Mixtral", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "distillation", "conversational", "en", "arxiv:2305.18290", "arxiv:2303.13375", "arxiv:2212.13138", "arxiv:2305.09617", "arxiv:2402.07023", "base_model:meta-llama/Meta-Llama-3-70B-Instruct", "license:llama3", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]

null

2024-04-27T01:31:50+00:00

[ "2305.18290", "2303.13375", "2212.13138", "2305.09617", "2402.07023" ]

[ "en" ]

TAGS #transformers #pytorch #llama #text-generation #llama-3 #Mixtral #instruct #finetune #chatml #DPO #RLHF #gpt4 #distillation #conversational #en #arxiv-2305.18290 #arxiv-2303.13375 #arxiv-2212.13138 #arxiv-2305.09617 #arxiv-2402.07023 #base_model-meta-llama/Meta-Llama-3-70B-Instruct #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us

![](URL <p>!image/png</p> <div align=) Advancing Open-source Large Language Models in Medical Domain ============================================================= Online Demo | GitHub | [![](URL alt=)](#) | Discord !image/jpeg Introducing OpenBioLLM-70B: A State-of-the-Art Open Source Biomedical Large Language Model OpenBioLLM-70B is an advanced open source language model designed specifically for the biomedical domain. Developed by Saama AI Labs, this model leverages cutting-edge techniques to achieve state-of-the-art performance on a wide range of biomedical tasks. Biomedical Specialization: OpenBioLLM-70B is tailored for the unique language and knowledge requirements of the medical and life sciences fields. It was fine-tuned on a vast corpus of high-quality biomedical data, enabling it to understand and generate text with domain-specific accuracy and fluency. Superior Performance: With 70 billion parameters, OpenBioLLM-70B outperforms other open source biomedical language models of similar scale. It has also demonstrated better results compared to larger proprietary & open-source models like GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 on biomedical benchmarks. Advanced Training Techniques: OpenBioLLM-70B builds upon the powerful foundations of the Meta-Llama-3-70B-Instruct and Meta-Llama-3-70B-Instruct models. It incorporates the DPO dataset and fine-tuning recipe along with a custom diverse medical instruction dataset. Key components of the training pipeline include: ![](URL </div> <ul> <li>Policy Optimization: Direct Preference Optimization: Your Language Model is Secretly a Reward Model (DPO)</li> <li>Fine-tuning dataset: Custom Medical Instruct dataset (We plan to release a sample training dataset in our upcoming paper; please stay updated)</li> </ul> <p>This combination of cutting-edge techniques enables OpenBioLLM-70B to align with key capabilities and preferences for biomedical applications.</p> <p>️ Release Details:</p> <ul> <li>Model Size: 70 billion parameters</li> <li>Quantization: Optimized quantized versions available Here</li> <li>Language(s) (NLP): en</li> <li>Developed By: Ankit Pal (Aaditya Ura) from Saama AI Labs</li> <li>License: Meta-Llama License</li> <li>Fine-tuned from models: Meta-Llama-3-70B-Instruct</li> <li>Resources for more information: <ul> <li>Paper: Coming soon</li> </ul> </li> </ul> <p>The model can be fine-tuned for more specialized tasks and datasets as needed.</p> <p>OpenBioLLM-70B represents an important step forward in democratizing advanced language AI for the biomedical community. By leveraging state-of-the-art architectures and training techniques from leading open source efforts like Llama-3, we have created a powerful tool to accelerate innovation and discovery in healthcare and the life sciences.</p> <p>We are excited to share OpenBioLLM-70B with researchers and developers around the world.</p> <h3>Use with transformers</h3> <p>Important: Please use the exact chat template provided by Llama-3 instruct version. Otherwise there will be a degradation in the performance. The model output can be verbose in rare cases. Please consider setting temperature = 0 to make this happen less.</p> <p>See the snippet below for usage with Transformers:</p> <h2>Training procedure</h2> <h3>Training hyperparameters</h3> <details> <summary>Click to see details</summary> <ul> <li>learning_rate: 0.0002</li> <li>lr_scheduler: cosine</li> <li>train_batch_size: 12</li> <li>eval_batch_size: 8</li> <li>GPU: H100 80GB SXM5</li> <li>num_devices: 8</li> <li>optimizer: adamw_bnb_8bit</li> <li>lr_scheduler_warmup_steps: 100</li> <li>num_epochs: 4</li> </ul> </details> <h3>Peft hyperparameters</h3> <details> <summary>Click to see details</summary> <ul> <li>adapter: qlora</li> <li>lora_r: 128</li> <li>lora_alpha: 256</li> <li>lora_dropout: 0.05</li> <li>lora_target_linear: true</li> </ul> <p>-lora_target_modules:</p> <ul> <li>q_proj</li> <li>v_proj</li> <li>k_proj</li> <li>o_proj</li> <li>gate_proj</li> <li>down_proj</li> <li>up_proj</li> </ul> </details> <h3>Training results</h3> <h3>Framework versions</h3> <ul> <li>Transformers 4.39.3</li> <li>Pytorch 2.1.2+cu121</li> <li>Datasets 2.18.0</li> <li>Tokenizers 0.15.1</li> <li>Axolotl</li> <li>Lm harness for evaluation</li> </ul> <h1>Benchmark Results</h1> <p>OpenBioLLM-70B demonstrates superior performance compared to larger models, such as GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 across 9 diverse biomedical datasets, achieving state-of-the-art results with an average score of 86.06%, despite having a significantly smaller parameter count. The model's strong performance in domain-specific tasks, such as Clinical KG, Medical Genetics, and PubMedQA, highlights its ability to effectively capture and apply biomedical knowledge.</p> <p>The GPT-4, Med-PaLM-1, and Med-PaLM-2 results are taken from their official papers. Since Med-PaLM doesn't provide zero-shot accuracy, we are using 5-shot accuracy from their paper for comparison. All results presented are in the zero-shot setting, except for Med-PaLM-2 and Med-PaLM-1, which use 5-shot accuracy.</p> <p></p> <div align=) ![](URL </div> <h2>Detailed Medical Subjectwise accuracy</h2> <p>!image/png</p> <h1>Use Cases & Examples</h1> <p>Below results are from the quantized version of OpenBioLLM-70B</p> <h1>Summarize Clinical Notes</h1> <p>OpenBioLLM-70B can efficiently analyze and summarize complex clinical notes, EHR data, and discharge summaries, extracting key information and generating concise, structured summaries</p> <p>!image/png</p> <h1>Answer Medical Questions</h1> <p>OpenBioLLM-70B can provide answers to a wide range of medical questions.</p> <p>!image/png !image/png</p> <details> <summary>Click to see details</summary> <p>!image/png !image/png !image/png</p> </details> <h1>Clinical Entity Recognition</h1> <p>OpenBioLLM-70B can perform advanced clinical entity recognition by identifying and extracting key medical concepts, such as diseases, symptoms, medications, procedures, and anatomical structures, from unstructured clinical text. By leveraging its deep understanding of medical terminology and context, the model can accurately annotate and categorize clinical entities, enabling more efficient information retrieval, data analysis, and knowledge discovery from electronic health records, research articles, and other biomedical text sources. This capability can support various downstream applications, such as clinical decision support, pharmacovigilance, and medical research.</p> <p>!image/png !image/png !image/png</p> <h1>Biomarkers Extraction</h1> <p>!image/png</p> <h1>Classification</h1> <p>OpenBioLLM-70B can perform various biomedical classification tasks, such as disease prediction, sentiment analysis, medical document categorization</p> <p>!image/png</p> <h1>De-Identification</h1> <p>OpenBioLLM-70B can detect and remove personally identifiable information (PII) from medical records, ensuring patient privacy and compliance with data protection regulations like HIPAA.</p> <p>!image/png</p> <p>Advisory Notice!</p> <p>While OpenBioLLM-70B leverages high-quality data sources, its outputs may still contain inaccuracies, biases, or misalignments that could pose risks if relied upon for medical decision-making without further testing and refinement. The model's performance has not yet been rigorously evaluated in randomized controlled trials or real-world healthcare environments.</p> <p>Therefore, we strongly advise against using OpenBioLLM-70B for any direct patient care, clinical decision support, or other professional medical purposes at this time. Its use should be limited to research, development, and exploratory applications by qualified individuals who understand its limitations. OpenBioLLM-70B is intended solely as a research tool to assist healthcare professionals and should never be considered a replacement for the professional judgment and expertise of a qualified medical doctor.</p> <p>Appropriately adapting and validating OpenBioLLM-70B for specific medical use cases would require significant additional work, potentially including:</p> <ul> <li>Thorough testing and evaluation in relevant clinical scenarios</li> <li>Alignment with evidence-based guidelines and best practices</li> <li>Mitigation of potential biases and failure modes</li> <li>Integration with human oversight and interpretation</li> <li>Compliance with regulatory and ethical standards</li> </ul> <p>Always consult a qualified healthcare provider for personal medical needs.</p> <p>If you find OpenBioLLM-70B & 8B useful in your work, please cite the model as follows:</p> <p>The accompanying paper is currently in progress and will be released soon.</p> <div align=) Contact -------- We look forward to hearing you and collaborating on this exciting project! Contributors: * Ankit Pal (Aaditya Ura) [aadityaura at gmail dot com] * Saama AI Labs * Note: I am looking for a funded PhD opportunity, especially if it fits my Responsible Generative AI, Multimodal LLMs, Geometric Deep Learning, and Healthcare AI skillset. References ========== We thank the Meta Team for their amazing models! Result sources * [1] GPT-4 [Capabilities of GPT-4 on Medical Challenge Problems] (URL * [2] Med-PaLM-1 Large Language Models Encode Clinical Knowledge * [3] Med-PaLM-2 Towards Expert-Level Medical Question Answering with Large Language Models * [4] Gemini-1.0 Gemini Goes to Med School

[]

[ "TAGS\n#transformers #pytorch #llama #text-generation #llama-3 #Mixtral #instruct #finetune #chatml #DPO #RLHF #gpt4 #distillation #conversational #en #arxiv-2305.18290 #arxiv-2303.13375 #arxiv-2212.13138 #arxiv-2305.09617 #arxiv-2402.07023 #base_model-meta-llama/Meta-Llama-3-70B-Instruct #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n" ]

text2text-generation

transformers

# CS505_COQE_viT5_train_Instruction0_PAOSL_v1 This model is a fine-tuned version of [VietAI/vit5-large](https://huggingface.co/VietAI/vit5-large) on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 20 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.15.2

{"license": "mit", "tags": ["generated_from_trainer"], "base_model": "VietAI/vit5-large", "model-index": [{"name": "CS505_COQE_viT5_train_Instruction0_PAOSL_v1", "results": []}]}

ThuyNT/CS505_COQE_viT5_train_Instruction0_PAOSL_v1

null

[ "transformers", "tensorboard", "safetensors", "t5", "text2text-generation", "generated_from_trainer", "base_model:VietAI/vit5-large", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

null

2024-04-27T01:31:54+00:00

[]

TAGS #transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-VietAI/vit5-large #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

# CS505_COQE_viT5_train_Instruction0_PAOSL_v1 This model is a fine-tuned version of VietAI/vit5-large on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 20 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.15.2

[ "# CS505_COQE_viT5_train_Instruction0_PAOSL_v1\n\nThis model is a fine-tuned version of VietAI/vit5-large on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 20\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-VietAI/vit5-large #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# CS505_COQE_viT5_train_Instruction0_PAOSL_v1\n\nThis model is a fine-tuned version of VietAI/vit5-large on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 20\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

fill-mask

transformers

# model_3 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 3e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results ### Framework versions - Transformers 4.40.0 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1

{"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "bert-base-uncased", "model-index": [{"name": "model_3", "results": []}]}

beloiual/model_3

null

[ "transformers", "tensorboard", "safetensors", "bert", "fill-mask", "generated_from_trainer", "base_model:bert-base-uncased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

null

2024-04-27T01:32:50+00:00

[]

TAGS #transformers #tensorboard #safetensors #bert #fill-mask #generated_from_trainer #base_model-bert-base-uncased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us

# model_3 This model is a fine-tuned version of bert-base-uncased on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 3e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results ### Framework versions - Transformers 4.40.0 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1

[ "# model_3\n\nThis model is a fine-tuned version of bert-base-uncased on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 3e-05\n- train_batch_size: 32\n- eval_batch_size: 32\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 3", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #bert #fill-mask #generated_from_trainer #base_model-bert-base-uncased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "# model_3\n\nThis model is a fine-tuned version of bert-base-uncased on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 3e-05\n- train_batch_size: 32\n- eval_batch_size: 32\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 3", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

text2text-generation

transformers

# CS505_COQE_viT5_train_Instruction0_APOSL_v1 This model is a fine-tuned version of [VietAI/vit5-large](https://huggingface.co/VietAI/vit5-large) on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 20 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.15.2

{"license": "mit", "tags": ["generated_from_trainer"], "base_model": "VietAI/vit5-large", "model-index": [{"name": "CS505_COQE_viT5_train_Instruction0_APOSL_v1", "results": []}]}

ThuyNT/CS505_COQE_viT5_train_Instruction0_APOSL_v1

null

[ "transformers", "tensorboard", "safetensors", "t5", "text2text-generation", "generated_from_trainer", "base_model:VietAI/vit5-large", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

null

2024-04-27T01:33:01+00:00

[]

TAGS #transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-VietAI/vit5-large #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

# CS505_COQE_viT5_train_Instruction0_APOSL_v1 This model is a fine-tuned version of VietAI/vit5-large on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 20 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.15.2

[ "# CS505_COQE_viT5_train_Instruction0_APOSL_v1\n\nThis model is a fine-tuned version of VietAI/vit5-large on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 20\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-VietAI/vit5-large #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# CS505_COQE_viT5_train_Instruction0_APOSL_v1\n\nThis model is a fine-tuned version of VietAI/vit5-large on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 20\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

token-classification

transformers

# model_3_edges This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 3e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results ### Framework versions - Transformers 4.40.0 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1

{"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "distilbert/distilbert-base-uncased", "model-index": [{"name": "model_3_edges", "results": []}]}

beloiual/model_3_edges

null

[ "transformers", "tensorboard", "safetensors", "distilbert", "token-classification", "generated_from_trainer", "base_model:distilbert/distilbert-base-uncased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

null

2024-04-27T01:35:09+00:00

[]

TAGS #transformers #tensorboard #safetensors #distilbert #token-classification #generated_from_trainer #base_model-distilbert/distilbert-base-uncased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us

# model_3_edges This model is a fine-tuned version of distilbert/distilbert-base-uncased on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 3e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results ### Framework versions - Transformers 4.40.0 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1

[ "# model_3_edges\n\nThis model is a fine-tuned version of distilbert/distilbert-base-uncased on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 3e-05\n- train_batch_size: 32\n- eval_batch_size: 32\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 3", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #distilbert #token-classification #generated_from_trainer #base_model-distilbert/distilbert-base-uncased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "# model_3_edges\n\nThis model is a fine-tuned version of distilbert/distilbert-base-uncased on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 3e-05\n- train_batch_size: 32\n- eval_batch_size: 32\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 3", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

text-generation

transformers

# Model Card for Model ID  ## Model Details ### Model Description  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

obamaTeo/mistral-finetune-16bit-ver9-wiki-GPTQ

null

[ "transformers", "safetensors", "mistral", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]

null

2024-04-27T01:43:19+00:00

[ "1910.09700" ]

[]

TAGS #transformers #safetensors #mistral #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us

# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

text-generation

transformers

Hello, my name is nanit. I am an AI assistant designed to help you with various tasks and provide information. I can assist with answering questions, providing recommendations, and performing calculations. I am constantly learning and improving to better serve you. If you have any specific questions or tasks you would like assistance with, please let me know.

{"license": "other", "library_name": "transformers"}

AlanRobotics/nanit_slerp

null

[ "transformers", "safetensors", "phi", "text-generation", "custom_code", "license:other", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

null

2024-04-27T01:43:40+00:00

[]

TAGS #transformers #safetensors #phi #text-generation #custom_code #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

Hello, my name is nanit. I am an AI assistant designed to help you with various tasks and provide information. I can assist with answering questions, providing recommendations, and performing calculations. I am constantly learning and improving to better serve you. If you have any specific questions or tasks you would like assistance with, please let me know.

[]

[ "TAGS\n#transformers #safetensors #phi #text-generation #custom_code #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n" ]

null

peft

# GUE_prom_prom_300_notata-seqsight_8192_512_30M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_8192_512_30M](https://huggingface.co/mahdibaghbanzadeh/seqsight_8192_512_30M) on the [mahdibaghbanzadeh/GUE_prom_prom_300_notata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_300_notata) dataset. It achieves the following results on the evaluation set: - Loss: 0.1197 - F1 Score: 0.9561 - Accuracy: 0.9561 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.2892 | 0.6 | 200 | 0.1442 | 0.9422 | 0.9422 | | 0.1464 | 1.2 | 400 | 0.1229 | 0.9527 | 0.9527 | | 0.1407 | 1.81 | 600 | 0.1152 | 0.9527 | 0.9527 | | 0.1283 | 2.41 | 800 | 0.1134 | 0.9538 | 0.9538 | | 0.1259 | 3.01 | 1000 | 0.1108 | 0.9567 | 0.9567 | | 0.1226 | 3.61 | 1200 | 0.1075 | 0.9572 | 0.9572 | | 0.1187 | 4.22 | 1400 | 0.1088 | 0.9572 | 0.9572 | | 0.1171 | 4.82 | 1600 | 0.1053 | 0.9597 | 0.9597 | | 0.1127 | 5.42 | 1800 | 0.1074 | 0.9598 | 0.9599 | | 0.1087 | 6.02 | 2000 | 0.1091 | 0.9574 | 0.9574 | | 0.1101 | 6.63 | 2200 | 0.1026 | 0.9610 | 0.9610 | | 0.1064 | 7.23 | 2400 | 0.1037 | 0.9612 | 0.9612 | | 0.1036 | 7.83 | 2600 | 0.1029 | 0.9608 | 0.9608 | | 0.107 | 8.43 | 2800 | 0.1051 | 0.9604 | 0.9604 | | 0.1064 | 9.04 | 3000 | 0.1087 | 0.9589 | 0.9589 | | 0.1017 | 9.64 | 3200 | 0.1077 | 0.9599 | 0.9599 | | 0.0991 | 10.24 | 3400 | 0.1037 | 0.9602 | 0.9602 | | 0.1013 | 10.84 | 3600 | 0.1003 | 0.9614 | 0.9614 | | 0.0961 | 11.45 | 3800 | 0.1008 | 0.9602 | 0.9602 | | 0.0949 | 12.05 | 4000 | 0.1015 | 0.9623 | 0.9623 | | 0.0978 | 12.65 | 4200 | 0.0998 | 0.9625 | 0.9625 | | 0.0992 | 13.25 | 4400 | 0.1029 | 0.9616 | 0.9616 | | 0.0942 | 13.86 | 4600 | 0.0990 | 0.9627 | 0.9627 | | 0.0942 | 14.46 | 4800 | 0.1035 | 0.9621 | 0.9621 | | 0.0914 | 15.06 | 5000 | 0.0984 | 0.9627 | 0.9627 | | 0.0906 | 15.66 | 5200 | 0.1076 | 0.9587 | 0.9587 | | 0.0923 | 16.27 | 5400 | 0.1026 | 0.9604 | 0.9604 | | 0.0887 | 16.87 | 5600 | 0.0984 | 0.9619 | 0.9619 | | 0.0898 | 17.47 | 5800 | 0.0975 | 0.9627 | 0.9627 | | 0.0934 | 18.07 | 6000 | 0.1006 | 0.9619 | 0.9619 | | 0.0871 | 18.67 | 6200 | 0.1059 | 0.9608 | 0.9608 | | 0.0863 | 19.28 | 6400 | 0.1008 | 0.9617 | 0.9617 | | 0.0859 | 19.88 | 6600 | 0.1005 | 0.9627 | 0.9627 | | 0.0868 | 20.48 | 6800 | 0.1025 | 0.9621 | 0.9621 | | 0.0854 | 21.08 | 7000 | 0.0992 | 0.9617 | 0.9617 | | 0.0852 | 21.69 | 7200 | 0.0999 | 0.9629 | 0.9629 | | 0.0841 | 22.29 | 7400 | 0.1009 | 0.9631 | 0.9631 | | 0.0862 | 22.89 | 7600 | 0.0965 | 0.9627 | 0.9627 | | 0.083 | 23.49 | 7800 | 0.1022 | 0.9621 | 0.9621 | | 0.0834 | 24.1 | 8000 | 0.0979 | 0.9640 | 0.9640 | | 0.0825 | 24.7 | 8200 | 0.1071 | 0.9617 | 0.9617 | | 0.0827 | 25.3 | 8400 | 0.1026 | 0.9625 | 0.9625 | | 0.084 | 25.9 | 8600 | 0.0993 | 0.9627 | 0.9627 | | 0.0817 | 26.51 | 8800 | 0.0999 | 0.9631 | 0.9631 | | 0.0817 | 27.11 | 9000 | 0.0997 | 0.9627 | 0.9627 | | 0.0811 | 27.71 | 9200 | 0.1009 | 0.9627 | 0.9627 | | 0.079 | 28.31 | 9400 | 0.1009 | 0.9627 | 0.9627 | | 0.0823 | 28.92 | 9600 | 0.0995 | 0.9623 | 0.9623 | | 0.0789 | 29.52 | 9800 | 0.0999 | 0.9621 | 0.9621 | | 0.0842 | 30.12 | 10000 | 0.1002 | 0.9631 | 0.9631 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_8192_512_30M", "model-index": [{"name": "GUE_prom_prom_300_notata-seqsight_8192_512_30M-L8_f", "results": []}]}

mahdibaghbanzadeh/GUE_prom_prom_300_notata-seqsight_8192_512_30M-L8_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_8192_512_30M", "region:us" ]

null

2024-04-27T01:45:21+00:00

[]

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us

GUE\_prom\_prom\_300\_notata-seqsight\_8192\_512\_30M-L8\_f =========================================================== This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_8192\_512\_30M on the mahdibaghbanzadeh/GUE\_prom\_prom\_300\_notata dataset. It achieves the following results on the evaluation set: * Loss: 0.1197 * F1 Score: 0.9561 * Accuracy: 0.9561 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

text-generation

transformers

<div align="center"> <img width="260px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/BrQCb95lmEIFz79QAmoNA.png"></div> ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/fJIOPJnY6Ff6fUiSIuMEt.png) <div align="center"> <h1>Advancing Open-source Large Language Models in Medical Domain</h1> </div> <p align="center" style="margin-top: 0px;"> <a href="https://colab.research.google.com/drive/1F5oV20InEYeAJGmBwYF9NM_QhLmjBkKJ?usp=sharing"> <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="OpenChat Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 10px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style=" margin-right: 5px;">Online Demo</span> </a> | <a href="https://github.com/openlifescience-ai"> <img src="https://github.githubassets.com/assets/GitHub-Mark-ea2971cee799.png" alt="GitHub Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style=" margin-right: 5px;">GitHub</span> </a> | <a href="#"> <img src="https://github.com/alpayariyak/openchat/blob/master/assets/arxiv-logomark-small-square-border.png?raw=true" alt="ArXiv Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style="margin-right: 5px;">Paper</span> </a> | <a href="https://discord.gg/A5Fjf5zC69"> <img src="https://cloud.githubusercontent.com/assets/6291467/26705903/96c2d66e-477c-11e7-9f4e-f3c0efe96c9a.png" alt="Discord Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text">Discord</span> </a> </p> ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/KGmRE5w2sepNtwsEu8t7K.jpeg) Introducing OpenBioLLM-70B: A State-of-the-Art Open Source Biomedical Large Language Model OpenBioLLM-70B is an advanced open source language model designed specifically for the biomedical domain. Developed by Saama AI Labs, this model leverages cutting-edge techniques to achieve state-of-the-art performance on a wide range of biomedical tasks. 🏥 **Biomedical Specialization**: OpenBioLLM-70B is tailored for the unique language and knowledge requirements of the medical and life sciences fields. It was fine-tuned on a vast corpus of high-quality biomedical data, enabling it to understand and generate text with domain-specific accuracy and fluency. 🎓 **Superior Performance**: With 70 billion parameters, OpenBioLLM-70B outperforms other open source biomedical language models of similar scale. It has also demonstrated better results compared to larger proprietary & open-source models like GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 on biomedical benchmarks. 🧠 **Advanced Training Techniques**: OpenBioLLM-70B builds upon the powerful foundations of the **Meta-Llama-3-70B-Instruct** and [Meta-Llama-3-70B-Instruct](meta-llama/Meta-Llama-3-70B-Instruct) models. It incorporates the DPO dataset and fine-tuning recipe along with a custom diverse medical instruction dataset. Key components of the training pipeline include: <div align="center"> <img width="1200px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/oPchsJsEpQoGcGXVbh7YS.png"> </div> - **Policy Optimization**: [Direct Preference Optimization: Your Language Model is Secretly a Reward Model (DPO)](https://arxiv.org/abs/2305.18290) - **Fine-tuning dataset**: Custom Medical Instruct dataset (We plan to release a sample training dataset in our upcoming paper; please stay updated) This combination of cutting-edge techniques enables OpenBioLLM-70B to align with key capabilities and preferences for biomedical applications. ⚙️ **Release Details**: - **Model Size**: 70 billion parameters - **Quantization**: Optimized quantized versions available [Here](https://huggingface.co/aaditya/OpenBioLLM-70B-GGUF) - **Language(s) (NLP):** en - **Developed By**: [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) from Saama AI Labs - **License:** Meta-Llama License - **Fine-tuned from models:** [Meta-Llama-3-70B-Instruct](meta-llama/Meta-Llama-3-70B-Instruct) - **Resources for more information:** - Paper: Coming soon The model can be fine-tuned for more specialized tasks and datasets as needed. OpenBioLLM-70B represents an important step forward in democratizing advanced language AI for the biomedical community. By leveraging state-of-the-art architectures and training techniques from leading open source efforts like Llama-3, we have created a powerful tool to accelerate innovation and discovery in healthcare and the life sciences. We are excited to share OpenBioLLM-70B with researchers and developers around the world. ### Use with transformers **Important: Please use the exact chat template provided by Llama-3 instruct version. Otherwise there will be a degradation in the performance. The model output can be verbose in rare cases. Please consider setting temperature = 0 to make this happen less.** See the snippet below for usage with Transformers: ```python import transformers import torch model_id = "aaditya/OpenBioLLM-Llama3-70B" pipeline = transformers.pipeline( "text-generation", model=model_id, model_kwargs={"torch_dtype": torch.bfloat16}, device="auto", ) messages = [ {"role": "system", "content": "You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience. Your name is OpenBioLLM, and you were developed by Saama AI Labs. who's willing to help answer the user's query with explanation. In your explanation, leverage your deep medical expertise such as relevant anatomical structures, physiological processes, diagnostic criteria, treatment guidelines, or other pertinent medical concepts. Use precise medical terminology while still aiming to make the explanation clear and accessible to a general audience."}, {"role": "user", "content": "How can i split a 3mg or 4mg waefin pill so i can get a 2.5mg pill?"}, ] prompt = pipeline.tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) terminators = [ pipeline.tokenizer.eos_token_id, pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>") ] outputs = pipeline( prompt, max_new_tokens=256, eos_token_id=terminators, do_sample=True, temperature=0.0, top_p=0.9, ) print(outputs[0]["generated_text"][len(prompt):]) ``` ## **Training procedure** ### **Training hyperparameters** <details> <summary>Click to see details</summary> - learning_rate: 0.0002 - lr_scheduler: cosine - train_batch_size: 12 - eval_batch_size: 8 - GPU: H100 80GB SXM5 - num_devices: 8 - optimizer: adamw_bnb_8bit - lr_scheduler_warmup_steps: 100 - num_epochs: 4 </details> ### **Peft hyperparameters** <details> <summary>Click to see details</summary> - adapter: qlora - lora_r: 128 - lora_alpha: 256 - lora_dropout: 0.05 - lora_target_linear: true -lora_target_modules: - q_proj - v_proj - k_proj - o_proj - gate_proj - down_proj - up_proj </details> ### **Training results** ### **Framework versions** - Transformers 4.39.3 - Pytorch 2.1.2+cu121 - Datasets 2.18.0 - Tokenizers 0.15.1 - Axolotl - Lm harness for evaluation # Benchmark Results 🔥 OpenBioLLM-70B demonstrates superior performance compared to larger models, such as GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 across 9 diverse biomedical datasets, achieving state-of-the-art results with an average score of 86.06%, despite having a significantly smaller parameter count. The model's strong performance in domain-specific tasks, such as Clinical KG, Medical Genetics, and PubMedQA, highlights its ability to effectively capture and apply biomedical knowledge. 🚨 The GPT-4, Med-PaLM-1, and Med-PaLM-2 results are taken from their official papers. Since Med-PaLM doesn't provide zero-shot accuracy, we are using 5-shot accuracy from their paper for comparison. All results presented are in the zero-shot setting, except for Med-PaLM-2 and Med-PaLM-1, which use 5-shot accuracy. | | Clinical KG | Medical Genetics | Anatomy | Pro Medicine | College Biology | College Medicine | MedQA 4 opts | PubMedQA | MedMCQA | Avg | |--------------------|-------------|------------------|---------|--------------|-----------------|------------------|--------------|----------|---------|-------| | **OpenBioLLM-70B** | **92.93** | **93.197** | **83.904** | 93.75 | 93.827 | **85.749** | 78.162 | 78.97 | **74.014** | **86.05588** | | Med-PaLM-2 (5-shot) | 88.3 | 90 | 77.8 | **95.2** | 94.4 | 80.9 | **79.7** | **79.2** | 71.3 | 84.08 | | **GPT-4** | 86.04 | 91 | 80 | 93.01 | **95.14** | 76.88 | 78.87 | 75.2 | 69.52 | 82.85 | | Med-PaLM-1 (Flan-PaLM, 5-shot) | 80.4 | 75 | 63.7 | 83.8 | 88.9 | 76.3 | 67.6 | 79 | 57.6 | 74.7 | | **OpenBioLLM-8B** | 76.101 | 86.1 | 69.829 | 78.21 | 84.213 | 68.042 | 58.993 | 74.12 | 56.913 | 72.502 | | Gemini-1.0 | 76.7 | 75.8 | 66.7 | 77.7 | 88 | 69.2 | 58 | 70.7 | 54.3 | 70.79 | | GPT-3.5 Turbo 1106 | 74.71 | 74 | 72.79 | 72.79 | 72.91 | 64.73 | 57.71 | 72.66 | 53.79 | 66 | | Meditron-70B | 66.79 | 69 | 53.33 | 71.69 | 76.38 | 63 | 57.1 | 76.6 | 46.85 | 64.52 | | gemma-7b | 69.81 | 70 | 59.26 | 66.18 | 79.86 | 60.12 | 47.21 | 76.2 | 48.96 | 64.18 | | Mistral-7B-v0.1 | 68.68 | 71 | 55.56 | 68.38 | 68.06 | 59.54 | 50.82 | 75.4 | 48.2 | 62.85 | | Apollo-7B | 62.26 | 72 | 61.48 | 69.12 | 70.83 | 55.49 | 55.22 | 39.8 | 53.77 | 60 | | MedAlpaca-7b | 57.36 | 69 | 57.04 | 67.28 | 65.28 | 54.34 | 41.71 | 72.8 | 37.51 | 58.03 | | BioMistral-7B | 59.9 | 64 | 56.5 | 60.4 | 59 | 54.7 | 50.6 | 77.5 | 48.1 | 57.3 | | AlpaCare-llama2-7b | 49.81 | 49 | 45.92 | 33.82 | 50 | 43.35 | 29.77 | 72.2 | 34.42 | 45.36 | | ClinicalGPT | 30.56 | 27 | 30.37 | 19.48 | 25 | 24.27 | 26.08 | 63.8 | 28.18 | 30.52 | <div align="center"> <img width="1600px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/_SzdcJSBjZyo8RS1bTEkP.png"> </div> ## Detailed Medical Subjectwise accuracy ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/UXF-V0col0Z0sS6BGPBkE.png) # Use Cases & Examples 🚨 **Below results are from the quantized version of OpenBioLLM-70B # Summarize Clinical Notes OpenBioLLM-70B can efficiently analyze and summarize complex clinical notes, EHR data, and discharge summaries, extracting key information and generating concise, structured summaries ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/xdwdBgOxNi_TfML0hKlI8.png) # Answer Medical Questions OpenBioLLM-70B can provide answers to a wide range of medical questions. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/zO95GlwOQEZqCKQF69mE6.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/OKBczKw7gWeW5xsuDpc27.png) <details> <summary>Click to see details</summary> ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/eJGHT5khppYvJb8fQ-YW4.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/Cnbwrqa_-ORHRuNRC2P6Y.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/J9DhdcvukAc9mnnW9fj2C.png) </details> # Clinical Entity Recognition OpenBioLLM-70B can perform advanced clinical entity recognition by identifying and extracting key medical concepts, such as diseases, symptoms, medications, procedures, and anatomical structures, from unstructured clinical text. By leveraging its deep understanding of medical terminology and context, the model can accurately annotate and categorize clinical entities, enabling more efficient information retrieval, data analysis, and knowledge discovery from electronic health records, research articles, and other biomedical text sources. This capability can support various downstream applications, such as clinical decision support, pharmacovigilance, and medical research. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/_69BW4k9LVABFwtxixL45.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/DKy5wYCoPhoPPUc1-x8_J.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/7WD9zCCBZT4-4XlfnIQjl.png) # Biomarkers Extraction ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/ZttoM4AiteT7gFYVhjIpN.png) # Classification OpenBioLLM-70B can perform various biomedical classification tasks, such as disease prediction, sentiment analysis, medical document categorization ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/Bf5MW1d75qT-1F_TR_hC0.png) # De-Identification OpenBioLLM-70B can detect and remove personally identifiable information (PII) from medical records, ensuring patient privacy and compliance with data protection regulations like HIPAA. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/hKX4kzm--Tw5bj6K78msy.png) **Advisory Notice!** While OpenBioLLM-70B leverages high-quality data sources, its outputs may still contain inaccuracies, biases, or misalignments that could pose risks if relied upon for medical decision-making without further testing and refinement. The model's performance has not yet been rigorously evaluated in randomized controlled trials or real-world healthcare environments. Therefore, we strongly advise against using OpenBioLLM-70B for any direct patient care, clinical decision support, or other professional medical purposes at this time. Its use should be limited to research, development, and exploratory applications by qualified individuals who understand its limitations. OpenBioLLM-70B is intended solely as a research tool to assist healthcare professionals and should never be considered a replacement for the professional judgment and expertise of a qualified medical doctor. Appropriately adapting and validating OpenBioLLM-70B for specific medical use cases would require significant additional work, potentially including: - Thorough testing and evaluation in relevant clinical scenarios - Alignment with evidence-based guidelines and best practices - Mitigation of potential biases and failure modes - Integration with human oversight and interpretation - Compliance with regulatory and ethical standards Always consult a qualified healthcare provider for personal medical needs. # Citation If you find OpenBioLLM-70B & 8B useful in your work, please cite the model as follows: ``` @misc{OpenBioLLMs, author = {Ankit Pal, Malaikannan Sankarasubbu}, title = {OpenBioLLMs: Advancing Open-Source Large Language Models for Healthcare and Life Sciences}, year = {2024}, publisher = {Hugging Face}, journal = {Hugging Face repository}, howpublished = {\url{https://huggingface.co/aaditya/OpenBioLLM-Llama3-70B}} } ``` The accompanying paper is currently in progress and will be released soon. <div align="center"> <h2> 💌 Contact </h2> </div> We look forward to hearing you and collaborating on this exciting project! **Contributors:** - [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) [aadityaura at gmail dot com] - Saama AI Labs - Note: I am looking for a funded PhD opportunity, especially if it fits my Responsible Generative AI, Multimodal LLMs, Geometric Deep Learning, and Healthcare AI skillset. # References We thank the [Meta Team](meta-llama/Meta-Llama-3-70B-Instruct) for their amazing models! Result sources - [1] GPT-4 [Capabilities of GPT-4 on Medical Challenge Problems] (https://arxiv.org/abs/2303.13375) - [2] Med-PaLM-1 [Large Language Models Encode Clinical Knowledge](https://arxiv.org/abs/2212.13138) - [3] Med-PaLM-2 [Towards Expert-Level Medical Question Answering with Large Language Models](https://arxiv.org/abs/2305.09617) - [4] Gemini-1.0 [Gemini Goes to Med School](https://arxiv.org/abs/2402.07023)

{"language": ["en"], "license": "llama3", "tags": ["llama-3", "llama", "Mixtral", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "distillation"], "base_model": "meta-llama/Meta-Llama-3-70B-Instruct", "widget": [{"example_title": "OpenBioLLM-70B", "messages": [{"role": "system", "content": "You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience."}, {"role": "user", "content": "How long does it take for newborn jaundice to go away?"}], "output": {"text": "Newborn jaundice, also known as neonatal jaundice, is a common condition in newborns where the yellowing of the skin and eyes occurs due to an elevated level of bilirubin in the blood. Bilirubin is a yellow pigment that forms when red blood cells break down. In most cases, newborn jaundice resolves on its own without any specific treatment.\nThe duration of newborn jaundice can vary depending on several factors such as the underlying cause, gestational age at birth, and individual variations in bilirubin metabolism. Here are some general guidelines:\n1. Physiological jaundice: This is the most common type of newborn jaundice and usually appears within 24-72 hours after birth. It tends to peak between the second and fifth day of life and gradually improves over the next week or two. By the time the baby is one week old, the jaundice should have mostly resolved. 2. Breast milk jaundice: This type of jaundice occurs in breastfed babies and may appear later than physiological jaundice, typically between the fifth and fourteenth day of life. It tends to persist for a longer duration but usually resolves within six weeks after birth. 3. Pathological jaundice: This type of jaundice is less common and occurs due to an underlying medical condition that affects bilirubin metabolism or liver function. The duration of pathological jaundice depends on the specific cause and may require treatment.\nIt's important for parents to monitor their newborn's jaundice closely and seek medical advice if the jaundice progresses rapidly, becomes severe, or is accompanied by other symptoms such as poor feeding, lethargy, or excessive sleepiness. In these cases, further evaluation and management may be necessary. Remember that each baby is unique, and the timing of jaundice resolution can vary. If you have concerns about your newborn's jaundice, it's always best to consult with a healthcare professional for personalized advice and guidance."}}], "model-index": [{"name": "OpenBioLLM-70B", "results": []}]}

LoneStriker/OpenBioLLM-Llama3-70B-4.65bpw-h6-exl2

null

[ "transformers", "pytorch", "llama", "text-generation", "llama-3", "Mixtral", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "distillation", "conversational", "en", "arxiv:2305.18290", "arxiv:2303.13375", "arxiv:2212.13138", "arxiv:2305.09617", "arxiv:2402.07023", "base_model:meta-llama/Meta-Llama-3-70B-Instruct", "license:llama3", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

null

2024-04-27T01:46:57+00:00

[ "2305.18290", "2303.13375", "2212.13138", "2305.09617", "2402.07023" ]

[ "en" ]

TAGS #transformers #pytorch #llama #text-generation #llama-3 #Mixtral #instruct #finetune #chatml #DPO #RLHF #gpt4 #distillation #conversational #en #arxiv-2305.18290 #arxiv-2303.13375 #arxiv-2212.13138 #arxiv-2305.09617 #arxiv-2402.07023 #base_model-meta-llama/Meta-Llama-3-70B-Instruct #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

![](URL <p>!image/png</p> <div align=) Advancing Open-source Large Language Models in Medical Domain ============================================================= Online Demo | GitHub | [![](URL alt=)](#) | Discord !image/jpeg Introducing OpenBioLLM-70B: A State-of-the-Art Open Source Biomedical Large Language Model OpenBioLLM-70B is an advanced open source language model designed specifically for the biomedical domain. Developed by Saama AI Labs, this model leverages cutting-edge techniques to achieve state-of-the-art performance on a wide range of biomedical tasks. Biomedical Specialization: OpenBioLLM-70B is tailored for the unique language and knowledge requirements of the medical and life sciences fields. It was fine-tuned on a vast corpus of high-quality biomedical data, enabling it to understand and generate text with domain-specific accuracy and fluency. Superior Performance: With 70 billion parameters, OpenBioLLM-70B outperforms other open source biomedical language models of similar scale. It has also demonstrated better results compared to larger proprietary & open-source models like GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 on biomedical benchmarks. Advanced Training Techniques: OpenBioLLM-70B builds upon the powerful foundations of the Meta-Llama-3-70B-Instruct and Meta-Llama-3-70B-Instruct models. It incorporates the DPO dataset and fine-tuning recipe along with a custom diverse medical instruction dataset. Key components of the training pipeline include: ![](URL </div> <ul> <li>Policy Optimization: Direct Preference Optimization: Your Language Model is Secretly a Reward Model (DPO)</li> <li>Fine-tuning dataset: Custom Medical Instruct dataset (We plan to release a sample training dataset in our upcoming paper; please stay updated)</li> </ul> <p>This combination of cutting-edge techniques enables OpenBioLLM-70B to align with key capabilities and preferences for biomedical applications.</p> <p>️ Release Details:</p> <ul> <li>Model Size: 70 billion parameters</li> <li>Quantization: Optimized quantized versions available Here</li> <li>Language(s) (NLP): en</li> <li>Developed By: Ankit Pal (Aaditya Ura) from Saama AI Labs</li> <li>License: Meta-Llama License</li> <li>Fine-tuned from models: Meta-Llama-3-70B-Instruct</li> <li>Resources for more information: <ul> <li>Paper: Coming soon</li> </ul> </li> </ul> <p>The model can be fine-tuned for more specialized tasks and datasets as needed.</p> <p>OpenBioLLM-70B represents an important step forward in democratizing advanced language AI for the biomedical community. By leveraging state-of-the-art architectures and training techniques from leading open source efforts like Llama-3, we have created a powerful tool to accelerate innovation and discovery in healthcare and the life sciences.</p> <p>We are excited to share OpenBioLLM-70B with researchers and developers around the world.</p> <h3>Use with transformers</h3> <p>Important: Please use the exact chat template provided by Llama-3 instruct version. Otherwise there will be a degradation in the performance. The model output can be verbose in rare cases. Please consider setting temperature = 0 to make this happen less.</p> <p>See the snippet below for usage with Transformers:</p> <h2>Training procedure</h2> <h3>Training hyperparameters</h3> <details> <summary>Click to see details</summary> <ul> <li>learning_rate: 0.0002</li> <li>lr_scheduler: cosine</li> <li>train_batch_size: 12</li> <li>eval_batch_size: 8</li> <li>GPU: H100 80GB SXM5</li> <li>num_devices: 8</li> <li>optimizer: adamw_bnb_8bit</li> <li>lr_scheduler_warmup_steps: 100</li> <li>num_epochs: 4</li> </ul> </details> <h3>Peft hyperparameters</h3> <details> <summary>Click to see details</summary> <ul> <li>adapter: qlora</li> <li>lora_r: 128</li> <li>lora_alpha: 256</li> <li>lora_dropout: 0.05</li> <li>lora_target_linear: true</li> </ul> <p>-lora_target_modules:</p> <ul> <li>q_proj</li> <li>v_proj</li> <li>k_proj</li> <li>o_proj</li> <li>gate_proj</li> <li>down_proj</li> <li>up_proj</li> </ul> </details> <h3>Training results</h3> <h3>Framework versions</h3> <ul> <li>Transformers 4.39.3</li> <li>Pytorch 2.1.2+cu121</li> <li>Datasets 2.18.0</li> <li>Tokenizers 0.15.1</li> <li>Axolotl</li> <li>Lm harness for evaluation</li> </ul> <h1>Benchmark Results</h1> <p>OpenBioLLM-70B demonstrates superior performance compared to larger models, such as GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 across 9 diverse biomedical datasets, achieving state-of-the-art results with an average score of 86.06%, despite having a significantly smaller parameter count. The model's strong performance in domain-specific tasks, such as Clinical KG, Medical Genetics, and PubMedQA, highlights its ability to effectively capture and apply biomedical knowledge.</p> <p>The GPT-4, Med-PaLM-1, and Med-PaLM-2 results are taken from their official papers. Since Med-PaLM doesn't provide zero-shot accuracy, we are using 5-shot accuracy from their paper for comparison. All results presented are in the zero-shot setting, except for Med-PaLM-2 and Med-PaLM-1, which use 5-shot accuracy.</p> <p></p> <div align=) ![](URL </div> <h2>Detailed Medical Subjectwise accuracy</h2> <p>!image/png</p> <h1>Use Cases & Examples</h1> <p>Below results are from the quantized version of OpenBioLLM-70B</p> <h1>Summarize Clinical Notes</h1> <p>OpenBioLLM-70B can efficiently analyze and summarize complex clinical notes, EHR data, and discharge summaries, extracting key information and generating concise, structured summaries</p> <p>!image/png</p> <h1>Answer Medical Questions</h1> <p>OpenBioLLM-70B can provide answers to a wide range of medical questions.</p> <p>!image/png !image/png</p> <details> <summary>Click to see details</summary> <p>!image/png !image/png !image/png</p> </details> <h1>Clinical Entity Recognition</h1> <p>OpenBioLLM-70B can perform advanced clinical entity recognition by identifying and extracting key medical concepts, such as diseases, symptoms, medications, procedures, and anatomical structures, from unstructured clinical text. By leveraging its deep understanding of medical terminology and context, the model can accurately annotate and categorize clinical entities, enabling more efficient information retrieval, data analysis, and knowledge discovery from electronic health records, research articles, and other biomedical text sources. This capability can support various downstream applications, such as clinical decision support, pharmacovigilance, and medical research.</p> <p>!image/png !image/png !image/png</p> <h1>Biomarkers Extraction</h1> <p>!image/png</p> <h1>Classification</h1> <p>OpenBioLLM-70B can perform various biomedical classification tasks, such as disease prediction, sentiment analysis, medical document categorization</p> <p>!image/png</p> <h1>De-Identification</h1> <p>OpenBioLLM-70B can detect and remove personally identifiable information (PII) from medical records, ensuring patient privacy and compliance with data protection regulations like HIPAA.</p> <p>!image/png</p> <p>Advisory Notice!</p> <p>While OpenBioLLM-70B leverages high-quality data sources, its outputs may still contain inaccuracies, biases, or misalignments that could pose risks if relied upon for medical decision-making without further testing and refinement. The model's performance has not yet been rigorously evaluated in randomized controlled trials or real-world healthcare environments.</p> <p>Therefore, we strongly advise against using OpenBioLLM-70B for any direct patient care, clinical decision support, or other professional medical purposes at this time. Its use should be limited to research, development, and exploratory applications by qualified individuals who understand its limitations. OpenBioLLM-70B is intended solely as a research tool to assist healthcare professionals and should never be considered a replacement for the professional judgment and expertise of a qualified medical doctor.</p> <p>Appropriately adapting and validating OpenBioLLM-70B for specific medical use cases would require significant additional work, potentially including:</p> <ul> <li>Thorough testing and evaluation in relevant clinical scenarios</li> <li>Alignment with evidence-based guidelines and best practices</li> <li>Mitigation of potential biases and failure modes</li> <li>Integration with human oversight and interpretation</li> <li>Compliance with regulatory and ethical standards</li> </ul> <p>Always consult a qualified healthcare provider for personal medical needs.</p> <p>If you find OpenBioLLM-70B & 8B useful in your work, please cite the model as follows:</p> <p>The accompanying paper is currently in progress and will be released soon.</p> <div align=) Contact -------- We look forward to hearing you and collaborating on this exciting project! Contributors: * Ankit Pal (Aaditya Ura) [aadityaura at gmail dot com] * Saama AI Labs * Note: I am looking for a funded PhD opportunity, especially if it fits my Responsible Generative AI, Multimodal LLMs, Geometric Deep Learning, and Healthcare AI skillset. References ========== We thank the Meta Team for their amazing models! Result sources * [1] GPT-4 [Capabilities of GPT-4 on Medical Challenge Problems] (URL * [2] Med-PaLM-1 Large Language Models Encode Clinical Knowledge * [3] Med-PaLM-2 Towards Expert-Level Medical Question Answering with Large Language Models * [4] Gemini-1.0 Gemini Goes to Med School

[]

[ "TAGS\n#transformers #pytorch #llama #text-generation #llama-3 #Mixtral #instruct #finetune #chatml #DPO #RLHF #gpt4 #distillation #conversational #en #arxiv-2305.18290 #arxiv-2303.13375 #arxiv-2212.13138 #arxiv-2305.09617 #arxiv-2402.07023 #base_model-meta-llama/Meta-Llama-3-70B-Instruct #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n" ]

null

peft

# GUE_prom_prom_300_notata-seqsight_8192_512_30M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_8192_512_30M](https://huggingface.co/mahdibaghbanzadeh/seqsight_8192_512_30M) on the [mahdibaghbanzadeh/GUE_prom_prom_300_notata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_300_notata) dataset. It achieves the following results on the evaluation set: - Loss: 0.1357 - F1 Score: 0.9563 - Accuracy: 0.9563 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.2577 | 0.6 | 200 | 0.1254 | 0.9495 | 0.9495 | | 0.1373 | 1.2 | 400 | 0.1190 | 0.9538 | 0.9538 | | 0.1331 | 1.81 | 600 | 0.1103 | 0.9567 | 0.9567 | | 0.1203 | 2.41 | 800 | 0.1086 | 0.9580 | 0.9580 | | 0.117 | 3.01 | 1000 | 0.1067 | 0.9606 | 0.9606 | | 0.1152 | 3.61 | 1200 | 0.1070 | 0.9578 | 0.9578 | | 0.1095 | 4.22 | 1400 | 0.1018 | 0.9601 | 0.9601 | | 0.1085 | 4.82 | 1600 | 0.1010 | 0.9601 | 0.9601 | | 0.1024 | 5.42 | 1800 | 0.1047 | 0.9587 | 0.9587 | | 0.0985 | 6.02 | 2000 | 0.1062 | 0.9593 | 0.9593 | | 0.0992 | 6.63 | 2200 | 0.0972 | 0.9627 | 0.9627 | | 0.0949 | 7.23 | 2400 | 0.1007 | 0.9627 | 0.9627 | | 0.0927 | 7.83 | 2600 | 0.0981 | 0.9614 | 0.9614 | | 0.093 | 8.43 | 2800 | 0.1121 | 0.9602 | 0.9602 | | 0.0913 | 9.04 | 3000 | 0.1099 | 0.9593 | 0.9593 | | 0.0873 | 9.64 | 3200 | 0.0982 | 0.9625 | 0.9625 | | 0.0817 | 10.24 | 3400 | 0.0991 | 0.9653 | 0.9653 | | 0.0849 | 10.84 | 3600 | 0.0946 | 0.9648 | 0.9648 | | 0.0793 | 11.45 | 3800 | 0.0945 | 0.9653 | 0.9653 | | 0.0775 | 12.05 | 4000 | 0.0976 | 0.9663 | 0.9663 | | 0.0794 | 12.65 | 4200 | 0.0920 | 0.9661 | 0.9661 | | 0.0761 | 13.25 | 4400 | 0.1008 | 0.9636 | 0.9636 | | 0.0744 | 13.86 | 4600 | 0.0911 | 0.9655 | 0.9655 | | 0.0725 | 14.46 | 4800 | 0.0953 | 0.9665 | 0.9665 | | 0.069 | 15.06 | 5000 | 0.0946 | 0.9657 | 0.9657 | | 0.0673 | 15.66 | 5200 | 0.1017 | 0.9647 | 0.9648 | | 0.0683 | 16.27 | 5400 | 0.0974 | 0.9666 | 0.9666 | | 0.0648 | 16.87 | 5600 | 0.0977 | 0.9659 | 0.9659 | | 0.0618 | 17.47 | 5800 | 0.0996 | 0.9663 | 0.9663 | | 0.0661 | 18.07 | 6000 | 0.0960 | 0.9685 | 0.9685 | | 0.0604 | 18.67 | 6200 | 0.1063 | 0.9653 | 0.9653 | | 0.0578 | 19.28 | 6400 | 0.1030 | 0.9670 | 0.9670 | | 0.0597 | 19.88 | 6600 | 0.1022 | 0.9674 | 0.9674 | | 0.0561 | 20.48 | 6800 | 0.1018 | 0.9680 | 0.9680 | | 0.0561 | 21.08 | 7000 | 0.1037 | 0.9659 | 0.9659 | | 0.0551 | 21.69 | 7200 | 0.1060 | 0.9661 | 0.9661 | | 0.0553 | 22.29 | 7400 | 0.1049 | 0.9680 | 0.9680 | | 0.0551 | 22.89 | 7600 | 0.1014 | 0.9661 | 0.9661 | | 0.0525 | 23.49 | 7800 | 0.1117 | 0.9648 | 0.9648 | | 0.0512 | 24.1 | 8000 | 0.1035 | 0.9682 | 0.9682 | | 0.05 | 24.7 | 8200 | 0.1084 | 0.9648 | 0.9648 | | 0.0496 | 25.3 | 8400 | 0.1062 | 0.9672 | 0.9672 | | 0.0507 | 25.9 | 8600 | 0.1045 | 0.9666 | 0.9666 | | 0.0467 | 26.51 | 8800 | 0.1060 | 0.9682 | 0.9682 | | 0.0493 | 27.11 | 9000 | 0.1060 | 0.9672 | 0.9672 | | 0.0459 | 27.71 | 9200 | 0.1086 | 0.9666 | 0.9666 | | 0.0451 | 28.31 | 9400 | 0.1074 | 0.9672 | 0.9672 | | 0.0477 | 28.92 | 9600 | 0.1075 | 0.9672 | 0.9672 | | 0.0438 | 29.52 | 9800 | 0.1086 | 0.9680 | 0.9680 | | 0.0471 | 30.12 | 10000 | 0.1084 | 0.9676 | 0.9676 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_8192_512_30M", "model-index": [{"name": "GUE_prom_prom_300_notata-seqsight_8192_512_30M-L32_f", "results": []}]}

mahdibaghbanzadeh/GUE_prom_prom_300_notata-seqsight_8192_512_30M-L32_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_8192_512_30M", "region:us" ]

null

2024-04-27T01:49:08+00:00

[]

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us

GUE\_prom\_prom\_300\_notata-seqsight\_8192\_512\_30M-L32\_f ============================================================ This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_8192\_512\_30M on the mahdibaghbanzadeh/GUE\_prom\_prom\_300\_notata dataset. It achieves the following results on the evaluation set: * Loss: 0.1357 * F1 Score: 0.9563 * Accuracy: 0.9563 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

null

peft

# GUE_prom_prom_core_all-seqsight_8192_512_30M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_8192_512_30M](https://huggingface.co/mahdibaghbanzadeh/seqsight_8192_512_30M) on the [mahdibaghbanzadeh/GUE_prom_prom_core_all](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_core_all) dataset. It achieves the following results on the evaluation set: - Loss: 0.4231 - F1 Score: 0.8098 - Accuracy: 0.8098 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.5588 | 0.54 | 200 | 0.4980 | 0.7634 | 0.7649 | | 0.4803 | 1.08 | 400 | 0.4776 | 0.7765 | 0.7772 | | 0.4628 | 1.62 | 600 | 0.4580 | 0.7869 | 0.7870 | | 0.4571 | 2.16 | 800 | 0.4592 | 0.7882 | 0.7883 | | 0.4496 | 2.7 | 1000 | 0.4558 | 0.7871 | 0.7875 | | 0.4478 | 3.24 | 1200 | 0.4512 | 0.7892 | 0.7895 | | 0.4421 | 3.78 | 1400 | 0.4567 | 0.7850 | 0.7860 | | 0.4374 | 4.32 | 1600 | 0.4588 | 0.7866 | 0.7873 | | 0.4377 | 4.86 | 1800 | 0.4518 | 0.7891 | 0.7895 | | 0.4366 | 5.41 | 2000 | 0.4540 | 0.7877 | 0.7883 | | 0.432 | 5.95 | 2200 | 0.4466 | 0.7939 | 0.7939 | | 0.4349 | 6.49 | 2400 | 0.4450 | 0.7932 | 0.7934 | | 0.4274 | 7.03 | 2600 | 0.4426 | 0.7986 | 0.7986 | | 0.4312 | 7.57 | 2800 | 0.4462 | 0.7942 | 0.7944 | | 0.4242 | 8.11 | 3000 | 0.4489 | 0.7917 | 0.7922 | | 0.427 | 8.65 | 3200 | 0.4402 | 0.7966 | 0.7966 | | 0.4282 | 9.19 | 3400 | 0.4431 | 0.7969 | 0.7970 | | 0.4242 | 9.73 | 3600 | 0.4561 | 0.7871 | 0.7882 | | 0.4275 | 10.27 | 3800 | 0.4456 | 0.7933 | 0.7937 | | 0.4224 | 10.81 | 4000 | 0.4426 | 0.7976 | 0.7976 | | 0.4226 | 11.35 | 4200 | 0.4479 | 0.7925 | 0.7929 | | 0.4237 | 11.89 | 4400 | 0.4473 | 0.7917 | 0.7924 | | 0.4201 | 12.43 | 4600 | 0.4396 | 0.7998 | 0.7998 | | 0.4193 | 12.97 | 4800 | 0.4427 | 0.7960 | 0.7963 | | 0.4218 | 13.51 | 5000 | 0.4529 | 0.7881 | 0.7894 | | 0.4195 | 14.05 | 5200 | 0.4406 | 0.7973 | 0.7975 | | 0.4216 | 14.59 | 5400 | 0.4386 | 0.7969 | 0.7970 | | 0.4208 | 15.14 | 5600 | 0.4366 | 0.7986 | 0.7986 | | 0.4199 | 15.68 | 5800 | 0.4480 | 0.7944 | 0.7951 | | 0.4136 | 16.22 | 6000 | 0.4459 | 0.7959 | 0.7965 | | 0.4206 | 16.76 | 6200 | 0.4396 | 0.7950 | 0.7954 | | 0.4201 | 17.3 | 6400 | 0.4373 | 0.7973 | 0.7976 | | 0.4166 | 17.84 | 6600 | 0.4403 | 0.7954 | 0.7958 | | 0.4152 | 18.38 | 6800 | 0.4479 | 0.7956 | 0.7965 | | 0.4167 | 18.92 | 7000 | 0.4396 | 0.7961 | 0.7966 | | 0.4113 | 19.46 | 7200 | 0.4400 | 0.7975 | 0.7978 | | 0.4222 | 20.0 | 7400 | 0.4378 | 0.7965 | 0.7968 | | 0.4179 | 20.54 | 7600 | 0.4394 | 0.7961 | 0.7965 | | 0.4143 | 21.08 | 7800 | 0.4409 | 0.7966 | 0.7970 | | 0.4166 | 21.62 | 8000 | 0.4361 | 0.7959 | 0.7961 | | 0.4143 | 22.16 | 8200 | 0.4396 | 0.7978 | 0.7981 | | 0.4185 | 22.7 | 8400 | 0.4414 | 0.7981 | 0.7986 | | 0.4112 | 23.24 | 8600 | 0.4363 | 0.7959 | 0.7961 | | 0.4098 | 23.78 | 8800 | 0.4384 | 0.7970 | 0.7973 | | 0.4146 | 24.32 | 9000 | 0.4372 | 0.7965 | 0.7968 | | 0.4143 | 24.86 | 9200 | 0.4373 | 0.7963 | 0.7966 | | 0.4212 | 25.41 | 9400 | 0.4369 | 0.7972 | 0.7975 | | 0.4085 | 25.95 | 9600 | 0.4369 | 0.7971 | 0.7973 | | 0.4184 | 26.49 | 9800 | 0.4384 | 0.7969 | 0.7973 | | 0.4112 | 27.03 | 10000 | 0.4381 | 0.7970 | 0.7973 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_8192_512_30M", "model-index": [{"name": "GUE_prom_prom_core_all-seqsight_8192_512_30M-L1_f", "results": []}]}

mahdibaghbanzadeh/GUE_prom_prom_core_all-seqsight_8192_512_30M-L1_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_8192_512_30M", "region:us" ]

null

2024-04-27T01:51:59+00:00

[]

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us

GUE\_prom\_prom\_core\_all-seqsight\_8192\_512\_30M-L1\_f ========================================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_8192\_512\_30M on the mahdibaghbanzadeh/GUE\_prom\_prom\_core\_all dataset. It achieves the following results on the evaluation set: * Loss: 0.4231 * F1 Score: 0.8098 * Accuracy: 0.8098 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

null

peft

# GUE_prom_prom_core_all-seqsight_8192_512_30M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_8192_512_30M](https://huggingface.co/mahdibaghbanzadeh/seqsight_8192_512_30M) on the [mahdibaghbanzadeh/GUE_prom_prom_core_all](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_core_all) dataset. It achieves the following results on the evaluation set: - Loss: 0.4079 - F1 Score: 0.8099 - Accuracy: 0.8100 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.5264 | 0.54 | 200 | 0.4686 | 0.7814 | 0.7818 | | 0.4549 | 1.08 | 400 | 0.4736 | 0.7859 | 0.7872 | | 0.4386 | 1.62 | 600 | 0.4442 | 0.7933 | 0.7934 | | 0.4338 | 2.16 | 800 | 0.4449 | 0.7924 | 0.7927 | | 0.4286 | 2.7 | 1000 | 0.4395 | 0.7962 | 0.7965 | | 0.4289 | 3.24 | 1200 | 0.4338 | 0.7990 | 0.7992 | | 0.4217 | 3.78 | 1400 | 0.4411 | 0.7937 | 0.7944 | | 0.4167 | 4.32 | 1600 | 0.4407 | 0.7983 | 0.7986 | | 0.4204 | 4.86 | 1800 | 0.4373 | 0.7972 | 0.7975 | | 0.4174 | 5.41 | 2000 | 0.4398 | 0.7970 | 0.7975 | | 0.4149 | 5.95 | 2200 | 0.4392 | 0.8025 | 0.8025 | | 0.4181 | 6.49 | 2400 | 0.4310 | 0.8040 | 0.8041 | | 0.4099 | 7.03 | 2600 | 0.4356 | 0.8042 | 0.8042 | | 0.4133 | 7.57 | 2800 | 0.4323 | 0.8007 | 0.8007 | | 0.4071 | 8.11 | 3000 | 0.4342 | 0.7974 | 0.7976 | | 0.4064 | 8.65 | 3200 | 0.4309 | 0.8012 | 0.8014 | | 0.4103 | 9.19 | 3400 | 0.4332 | 0.8013 | 0.8014 | | 0.4048 | 9.73 | 3600 | 0.4405 | 0.7982 | 0.7988 | | 0.4089 | 10.27 | 3800 | 0.4359 | 0.8012 | 0.8015 | | 0.404 | 10.81 | 4000 | 0.4351 | 0.8049 | 0.8049 | | 0.4014 | 11.35 | 4200 | 0.4333 | 0.8017 | 0.8019 | | 0.4031 | 11.89 | 4400 | 0.4320 | 0.8016 | 0.8020 | | 0.3985 | 12.43 | 4600 | 0.4300 | 0.8035 | 0.8035 | | 0.3992 | 12.97 | 4800 | 0.4322 | 0.8041 | 0.8042 | | 0.3996 | 13.51 | 5000 | 0.4400 | 0.7977 | 0.7986 | | 0.3982 | 14.05 | 5200 | 0.4290 | 0.8077 | 0.8078 | | 0.3978 | 14.59 | 5400 | 0.4289 | 0.8055 | 0.8056 | | 0.3976 | 15.14 | 5600 | 0.4280 | 0.8074 | 0.8074 | | 0.395 | 15.68 | 5800 | 0.4372 | 0.8009 | 0.8015 | | 0.3912 | 16.22 | 6000 | 0.4322 | 0.8028 | 0.8034 | | 0.3948 | 16.76 | 6200 | 0.4253 | 0.8059 | 0.8063 | | 0.3948 | 17.3 | 6400 | 0.4250 | 0.8069 | 0.8071 | | 0.3926 | 17.84 | 6600 | 0.4285 | 0.8068 | 0.8069 | | 0.3893 | 18.38 | 6800 | 0.4347 | 0.8002 | 0.8010 | | 0.3894 | 18.92 | 7000 | 0.4267 | 0.8048 | 0.8052 | | 0.3871 | 19.46 | 7200 | 0.4276 | 0.8072 | 0.8074 | | 0.3959 | 20.0 | 7400 | 0.4258 | 0.8069 | 0.8071 | | 0.3886 | 20.54 | 7600 | 0.4261 | 0.8075 | 0.8078 | | 0.3876 | 21.08 | 7800 | 0.4278 | 0.8088 | 0.8090 | | 0.3883 | 21.62 | 8000 | 0.4230 | 0.8094 | 0.8095 | | 0.3849 | 22.16 | 8200 | 0.4264 | 0.8072 | 0.8074 | | 0.3894 | 22.7 | 8400 | 0.4281 | 0.8060 | 0.8064 | | 0.3834 | 23.24 | 8600 | 0.4238 | 0.8075 | 0.8076 | | 0.3827 | 23.78 | 8800 | 0.4259 | 0.8069 | 0.8071 | | 0.3844 | 24.32 | 9000 | 0.4245 | 0.8082 | 0.8083 | | 0.3844 | 24.86 | 9200 | 0.4240 | 0.8081 | 0.8083 | | 0.3904 | 25.41 | 9400 | 0.4242 | 0.8069 | 0.8071 | | 0.3788 | 25.95 | 9600 | 0.4256 | 0.8080 | 0.8081 | | 0.3894 | 26.49 | 9800 | 0.4259 | 0.8055 | 0.8057 | | 0.381 | 27.03 | 10000 | 0.4260 | 0.8067 | 0.8069 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_8192_512_30M", "model-index": [{"name": "GUE_prom_prom_core_all-seqsight_8192_512_30M-L8_f", "results": []}]}

mahdibaghbanzadeh/GUE_prom_prom_core_all-seqsight_8192_512_30M-L8_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_8192_512_30M", "region:us" ]

null

2024-04-27T01:54:10+00:00

[]

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us

GUE\_prom\_prom\_core\_all-seqsight\_8192\_512\_30M-L8\_f ========================================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_8192\_512\_30M on the mahdibaghbanzadeh/GUE\_prom\_prom\_core\_all dataset. It achieves the following results on the evaluation set: * Loss: 0.4079 * F1 Score: 0.8099 * Accuracy: 0.8100 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

token-classification

transformers

# model_3_edges This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 3e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results ### Framework versions - Transformers 4.40.0 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1

{"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "distilbert/distilbert-base-uncased", "model-index": [{"name": "model_3_edges", "results": []}]}

anirudhramoo/model_3_edges

null

[ "transformers", "tensorboard", "safetensors", "distilbert", "token-classification", "generated_from_trainer", "base_model:distilbert/distilbert-base-uncased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

null

2024-04-27T01:55:41+00:00

[]

TAGS #transformers #tensorboard #safetensors #distilbert #token-classification #generated_from_trainer #base_model-distilbert/distilbert-base-uncased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us

# model_3_edges This model is a fine-tuned version of distilbert/distilbert-base-uncased on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 3e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results ### Framework versions - Transformers 4.40.0 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1

[ "# model_3_edges\n\nThis model is a fine-tuned version of distilbert/distilbert-base-uncased on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 3e-05\n- train_batch_size: 32\n- eval_batch_size: 32\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 3", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #distilbert #token-classification #generated_from_trainer #base_model-distilbert/distilbert-base-uncased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "# model_3_edges\n\nThis model is a fine-tuned version of distilbert/distilbert-base-uncased on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 3e-05\n- train_batch_size: 32\n- eval_batch_size: 32\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 3", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

null

transformers

# Model Card for Model ID  ## Model Details ### Model Description  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

jd0g/Mistral-7B-NLI-v1.0

null

[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]

null

2024-04-27T01:55:53+00:00

[ "1910.09700" ]

[]

TAGS #transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us

# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

text-generation

transformers

# Model Card for Model ID  ## Model Details ### Model Description  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

pruning/yegu2vs

null

[ "transformers", "safetensors", "stablelm", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]

null

2024-04-27T01:59:04+00:00

[ "1910.09700" ]

[]

TAGS #transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us

# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

text-generation

transformers

# Model Card for Model ID  ## Model Details ### Model Description  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

pruning/5ww0fon

null

[ "transformers", "safetensors", "stablelm", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]

null

2024-04-27T01:59:04+00:00

[ "1910.09700" ]

[]

TAGS #transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us

# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

text-generation

transformers

# Model Card for Model ID  ## Model Details ### Model Description  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

pruning/lfucypx

null

[ "transformers", "safetensors", "stablelm", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]

null

2024-04-27T01:59:04+00:00

[ "1910.09700" ]

[]

TAGS #transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us

# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

text-generation

transformers

# Model Card for Model ID  ## Model Details ### Model Description  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

pruning/fcku0mx

null

[ "transformers", "safetensors", "stablelm", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]

null

2024-04-27T01:59:04+00:00

[ "1910.09700" ]

[]

TAGS #transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us

# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

text-generation

transformers

# Model Card for Model ID  ## Model Details ### Model Description  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

pruning/ehgnwni

null

[ "transformers", "safetensors", "stablelm", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]

null

2024-04-27T01:59:04+00:00

[ "1910.09700" ]

[]

TAGS #transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us

# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

text-generation

transformers

# Model Card for Model ID  ## Model Details ### Model Description  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

pruning/2evd8w5

null

[ "transformers", "safetensors", "stablelm", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]

null

2024-04-27T01:59:04+00:00

[ "1910.09700" ]

[]

TAGS #transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us

# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #stablelm #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

text-generation

transformers

# Description 4-bit AWQ-quantized version of [stylellm/HongLouMeng-6b](https://huggingface.co/stylellm/HongLouMeng-6b)

{"license": "other", "license_name": "yi-license", "license_link": "https://huggingface.co/01-ai/Yi-6B/blob/main/LICENSE"}

stylellm/HongLouMeng-6b-AWQ

null

[ "transformers", "safetensors", "llama", "text-generation", "conversational", "license:other", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]

null

2024-04-27T01:59:09+00:00

[]

TAGS #transformers #safetensors #llama #text-generation #conversational #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us

# Description 4-bit AWQ-quantized version of stylellm/HongLouMeng-6b

[ "# Description\n4-bit AWQ-quantized version of stylellm/HongLouMeng-6b" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #conversational #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n", "# Description\n4-bit AWQ-quantized version of stylellm/HongLouMeng-6b" ]

null

transformers

## About     weighted/imatrix quants of https://huggingface.co/aaditya/OpenBioLLM-Llama3-70B  static quants are available at https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) | Link | Type | Size/GB | Notes | |:-----|:-----|--------:|:------| | [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-IQ1_S.gguf) | i1-IQ1_S | 15.4 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-IQ1_M.gguf) | i1-IQ1_M | 16.9 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 19.2 | | | [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 21.2 | | | [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-IQ2_S.gguf) | i1-IQ2_S | 22.3 | | | [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-IQ2_M.gguf) | i1-IQ2_M | 24.2 | | | [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-Q2_K.gguf) | i1-Q2_K | 26.5 | IQ3_XXS probably better | | [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 27.6 | lower quality | | [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 29.4 | | | [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-IQ3_S.gguf) | i1-IQ3_S | 31.0 | beats Q3_K* | | [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 31.0 | IQ3_XS probably better | | [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-IQ3_M.gguf) | i1-IQ3_M | 32.0 | | | [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 34.4 | IQ3_S probably better | | [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 37.2 | IQ3_M probably better | | [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 38.0 | | | [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-Q4_0.gguf) | i1-Q4_0 | 40.2 | fast, low quality | | [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 40.4 | optimal size/speed/quality | | [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 42.6 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 48.8 | | | [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 50.1 | | | [PART 1](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 58.0 | practically like static Q6_K | Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time.

{"language": ["en"], "license": "llama3", "library_name": "transformers", "tags": ["llama-3", "llama", "Mixtral", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "distillation"], "base_model": "aaditya/OpenBioLLM-Llama3-70B", "quantized_by": "mradermacher"}

mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF

null

[ "transformers", "gguf", "llama-3", "llama", "Mixtral", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "distillation", "en", "base_model:aaditya/OpenBioLLM-Llama3-70B", "license:llama3", "endpoints_compatible", "region:us" ]

null

2024-04-27T01:59:56+00:00

[]

[ "en" ]

TAGS #transformers #gguf #llama-3 #llama #Mixtral #instruct #finetune #chatml #DPO #RLHF #gpt4 #distillation #en #base_model-aaditya/OpenBioLLM-Llama3-70B #license-llama3 #endpoints_compatible #region-us

About ----- weighted/imatrix quants of URL static quants are available at URL Usage ----- If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. Provided Quants --------------- (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): !URL And here are Artefact2's thoughts on the matter: URL FAQ / Model Request ------------------- See URL for some answers to questions you might have and/or if you want some other model quantized. Thanks ------ I thank my company, nethype GmbH, for letting me use its servers and providing upgrades to my workstation to enable this work in my free time.

[]

[ "TAGS\n#transformers #gguf #llama-3 #llama #Mixtral #instruct #finetune #chatml #DPO #RLHF #gpt4 #distillation #en #base_model-aaditya/OpenBioLLM-Llama3-70B #license-llama3 #endpoints_compatible #region-us \n" ]

null

peft

# GUE_prom_prom_core_all-seqsight_8192_512_30M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_8192_512_30M](https://huggingface.co/mahdibaghbanzadeh/seqsight_8192_512_30M) on the [mahdibaghbanzadeh/GUE_prom_prom_core_all](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_core_all) dataset. It achieves the following results on the evaluation set: - Loss: 0.4067 - F1 Score: 0.8189 - Accuracy: 0.8189 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.5065 | 0.54 | 200 | 0.4591 | 0.7903 | 0.7904 | | 0.446 | 1.08 | 400 | 0.4695 | 0.7843 | 0.7860 | | 0.4311 | 1.62 | 600 | 0.4409 | 0.7956 | 0.7959 | | 0.4271 | 2.16 | 800 | 0.4442 | 0.7928 | 0.7932 | | 0.4215 | 2.7 | 1000 | 0.4350 | 0.8007 | 0.8010 | | 0.4218 | 3.24 | 1200 | 0.4286 | 0.8030 | 0.8030 | | 0.4131 | 3.78 | 1400 | 0.4343 | 0.7960 | 0.7965 | | 0.4094 | 4.32 | 1600 | 0.4329 | 0.7994 | 0.7995 | | 0.4105 | 4.86 | 1800 | 0.4361 | 0.7977 | 0.7980 | | 0.406 | 5.41 | 2000 | 0.4350 | 0.8007 | 0.8010 | | 0.4037 | 5.95 | 2200 | 0.4336 | 0.8078 | 0.8078 | | 0.4044 | 6.49 | 2400 | 0.4245 | 0.8040 | 0.8041 | | 0.3964 | 7.03 | 2600 | 0.4262 | 0.8053 | 0.8054 | | 0.3959 | 7.57 | 2800 | 0.4255 | 0.8037 | 0.8037 | | 0.3925 | 8.11 | 3000 | 0.4263 | 0.8048 | 0.8049 | | 0.3865 | 8.65 | 3200 | 0.4245 | 0.8067 | 0.8069 | | 0.3904 | 9.19 | 3400 | 0.4300 | 0.8071 | 0.8071 | | 0.3841 | 9.73 | 3600 | 0.4312 | 0.8044 | 0.8049 | | 0.3855 | 10.27 | 3800 | 0.4348 | 0.8053 | 0.8056 | | 0.3805 | 10.81 | 4000 | 0.4330 | 0.8063 | 0.8063 | | 0.3749 | 11.35 | 4200 | 0.4266 | 0.8092 | 0.8093 | | 0.3775 | 11.89 | 4400 | 0.4275 | 0.8081 | 0.8084 | | 0.3708 | 12.43 | 4600 | 0.4262 | 0.8130 | 0.8130 | | 0.3731 | 12.97 | 4800 | 0.4267 | 0.8098 | 0.8100 | | 0.3709 | 13.51 | 5000 | 0.4308 | 0.8051 | 0.8057 | | 0.3675 | 14.05 | 5200 | 0.4300 | 0.8127 | 0.8127 | | 0.3654 | 14.59 | 5400 | 0.4312 | 0.8115 | 0.8117 | | 0.3665 | 15.14 | 5600 | 0.4265 | 0.8123 | 0.8123 | | 0.3618 | 15.68 | 5800 | 0.4333 | 0.8090 | 0.8093 | | 0.3589 | 16.22 | 6000 | 0.4283 | 0.8101 | 0.8105 | | 0.3591 | 16.76 | 6200 | 0.4188 | 0.8100 | 0.8103 | | 0.3592 | 17.3 | 6400 | 0.4231 | 0.8118 | 0.8120 | | 0.3575 | 17.84 | 6600 | 0.4267 | 0.8109 | 0.8110 | | 0.3505 | 18.38 | 6800 | 0.4350 | 0.8037 | 0.8044 | | 0.3527 | 18.92 | 7000 | 0.4257 | 0.8120 | 0.8123 | | 0.3468 | 19.46 | 7200 | 0.4292 | 0.8099 | 0.8101 | | 0.3558 | 20.0 | 7400 | 0.4245 | 0.8129 | 0.8130 | | 0.346 | 20.54 | 7600 | 0.4263 | 0.8092 | 0.8095 | | 0.3479 | 21.08 | 7800 | 0.4252 | 0.8115 | 0.8117 | | 0.3449 | 21.62 | 8000 | 0.4228 | 0.8111 | 0.8111 | | 0.3426 | 22.16 | 8200 | 0.4274 | 0.8125 | 0.8127 | | 0.3462 | 22.7 | 8400 | 0.4288 | 0.8082 | 0.8086 | | 0.3417 | 23.24 | 8600 | 0.4225 | 0.8141 | 0.8142 | | 0.3408 | 23.78 | 8800 | 0.4259 | 0.8131 | 0.8132 | | 0.3422 | 24.32 | 9000 | 0.4230 | 0.8131 | 0.8132 | | 0.3403 | 24.86 | 9200 | 0.4245 | 0.8137 | 0.8139 | | 0.3457 | 25.41 | 9400 | 0.4242 | 0.8125 | 0.8127 | | 0.3364 | 25.95 | 9600 | 0.4270 | 0.8134 | 0.8135 | | 0.3418 | 26.49 | 9800 | 0.4278 | 0.8111 | 0.8113 | | 0.3354 | 27.03 | 10000 | 0.4276 | 0.8120 | 0.8122 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_8192_512_30M", "model-index": [{"name": "GUE_prom_prom_core_all-seqsight_8192_512_30M-L32_f", "results": []}]}

mahdibaghbanzadeh/GUE_prom_prom_core_all-seqsight_8192_512_30M-L32_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_8192_512_30M", "region:us" ]

null

2024-04-27T02:01:26+00:00

[]

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us

GUE\_prom\_prom\_core\_all-seqsight\_8192\_512\_30M-L32\_f ========================================================== This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_8192\_512\_30M on the mahdibaghbanzadeh/GUE\_prom\_prom\_core\_all dataset. It achieves the following results on the evaluation set: * Loss: 0.4067 * F1 Score: 0.8189 * Accuracy: 0.8189 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

text-generation

transformers

# 0.001_4iters_bs256_nodpo_only4w_iter_3 This model is a fine-tuned version of [ShenaoZhang/0.001_4iters_bs256_nodpo_only4w_iter_2](https://huggingface.co/ShenaoZhang/0.001_4iters_bs256_nodpo_only4w_iter_2) on the updated and the original datasets. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-07 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - distributed_type: multi-GPU - num_devices: 8 - gradient_accumulation_steps: 4 - total_train_batch_size: 256 - total_eval_batch_size: 64 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 1 ### Training results ### Framework versions - Transformers 4.40.0 - Pytorch 2.1.2+cu121 - Datasets 2.14.6 - Tokenizers 0.19.1

{"license": "mit", "tags": ["alignment-handbook", "trl", "dpo", "generated_from_trainer", "trl", "dpo", "generated_from_trainer"], "datasets": ["updated", "original"], "base_model": "ShenaoZhang/0.001_4iters_bs256_nodpo_only4w_iter_2", "model-index": [{"name": "0.001_4iters_bs256_nodpo_only4w_iter_3", "results": []}]}

ShenaoZhang/0.001_4iters_bs256_nodpo_only4w_iter_3

null

[ "transformers", "safetensors", "mistral", "text-generation", "alignment-handbook", "trl", "dpo", "generated_from_trainer", "conversational", "dataset:updated", "dataset:original", "base_model:ShenaoZhang/0.001_4iters_bs256_nodpo_only4w_iter_2", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

null

2024-04-27T02:01:33+00:00

[]

TAGS #transformers #safetensors #mistral #text-generation #alignment-handbook #trl #dpo #generated_from_trainer #conversational #dataset-updated #dataset-original #base_model-ShenaoZhang/0.001_4iters_bs256_nodpo_only4w_iter_2 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

# 0.001_4iters_bs256_nodpo_only4w_iter_3 This model is a fine-tuned version of ShenaoZhang/0.001_4iters_bs256_nodpo_only4w_iter_2 on the updated and the original datasets. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-07 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - distributed_type: multi-GPU - num_devices: 8 - gradient_accumulation_steps: 4 - total_train_batch_size: 256 - total_eval_batch_size: 64 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 1 ### Training results ### Framework versions - Transformers 4.40.0 - Pytorch 2.1.2+cu121 - Datasets 2.14.6 - Tokenizers 0.19.1

[ "# 0.001_4iters_bs256_nodpo_only4w_iter_3\n\nThis model is a fine-tuned version of ShenaoZhang/0.001_4iters_bs256_nodpo_only4w_iter_2 on the updated and the original datasets.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #alignment-handbook #trl #dpo #generated_from_trainer #conversational #dataset-updated #dataset-original #base_model-ShenaoZhang/0.001_4iters_bs256_nodpo_only4w_iter_2 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# 0.001_4iters_bs256_nodpo_only4w_iter_3\n\nThis model is a fine-tuned version of ShenaoZhang/0.001_4iters_bs256_nodpo_only4w_iter_2 on the updated and the original datasets.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.19.1" ]

null

peft

# GUE_prom_prom_core_notata-seqsight_8192_512_30M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_8192_512_30M](https://huggingface.co/mahdibaghbanzadeh/seqsight_8192_512_30M) on the [mahdibaghbanzadeh/GUE_prom_prom_core_notata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_core_notata) dataset. It achieves the following results on the evaluation set: - Loss: 0.3822 - F1 Score: 0.8334 - Accuracy: 0.8334 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.5488 | 0.6 | 200 | 0.4335 | 0.7988 | 0.7995 | | 0.4495 | 1.2 | 400 | 0.4023 | 0.8161 | 0.8161 | | 0.43 | 1.81 | 600 | 0.3943 | 0.8239 | 0.8240 | | 0.4301 | 2.41 | 800 | 0.3876 | 0.8230 | 0.8231 | | 0.4157 | 3.01 | 1000 | 0.3833 | 0.8268 | 0.8268 | | 0.4118 | 3.61 | 1200 | 0.3797 | 0.8285 | 0.8285 | | 0.4131 | 4.22 | 1400 | 0.3810 | 0.8274 | 0.8274 | | 0.4074 | 4.82 | 1600 | 0.3778 | 0.8303 | 0.8304 | | 0.3984 | 5.42 | 1800 | 0.3786 | 0.8300 | 0.8300 | | 0.4015 | 6.02 | 2000 | 0.3758 | 0.8295 | 0.8297 | | 0.3992 | 6.63 | 2200 | 0.3731 | 0.8310 | 0.8310 | | 0.3953 | 7.23 | 2400 | 0.3751 | 0.8323 | 0.8325 | | 0.396 | 7.83 | 2600 | 0.3715 | 0.8319 | 0.8319 | | 0.3882 | 8.43 | 2800 | 0.3801 | 0.8325 | 0.8329 | | 0.394 | 9.04 | 3000 | 0.3714 | 0.8331 | 0.8332 | | 0.3891 | 9.64 | 3200 | 0.3694 | 0.8327 | 0.8327 | | 0.3915 | 10.24 | 3400 | 0.3700 | 0.8344 | 0.8344 | | 0.3855 | 10.84 | 3600 | 0.3704 | 0.8359 | 0.8359 | | 0.387 | 11.45 | 3800 | 0.3690 | 0.8347 | 0.8347 | | 0.3841 | 12.05 | 4000 | 0.3679 | 0.8363 | 0.8363 | | 0.3844 | 12.65 | 4200 | 0.3713 | 0.8364 | 0.8364 | | 0.3836 | 13.25 | 4400 | 0.3693 | 0.8385 | 0.8385 | | 0.3875 | 13.86 | 4600 | 0.3697 | 0.8368 | 0.8368 | | 0.3828 | 14.46 | 4800 | 0.3696 | 0.8366 | 0.8366 | | 0.3801 | 15.06 | 5000 | 0.3684 | 0.8362 | 0.8363 | | 0.3785 | 15.66 | 5200 | 0.3678 | 0.8385 | 0.8385 | | 0.3792 | 16.27 | 5400 | 0.3700 | 0.8368 | 0.8368 | | 0.3788 | 16.87 | 5600 | 0.3746 | 0.8328 | 0.8332 | | 0.3774 | 17.47 | 5800 | 0.3755 | 0.8335 | 0.8338 | | 0.3827 | 18.07 | 6000 | 0.3699 | 0.8381 | 0.8383 | | 0.3788 | 18.67 | 6200 | 0.3672 | 0.8374 | 0.8374 | | 0.3824 | 19.28 | 6400 | 0.3672 | 0.8382 | 0.8381 | | 0.3798 | 19.88 | 6600 | 0.3674 | 0.8375 | 0.8376 | | 0.3732 | 20.48 | 6800 | 0.3686 | 0.8371 | 0.8372 | | 0.384 | 21.08 | 7000 | 0.3672 | 0.8389 | 0.8391 | | 0.3794 | 21.69 | 7200 | 0.3673 | 0.8379 | 0.8379 | | 0.3723 | 22.29 | 7400 | 0.3667 | 0.8364 | 0.8364 | | 0.3757 | 22.89 | 7600 | 0.3674 | 0.8394 | 0.8395 | | 0.3773 | 23.49 | 7800 | 0.3658 | 0.8379 | 0.8379 | | 0.3766 | 24.1 | 8000 | 0.3675 | 0.8373 | 0.8374 | | 0.3772 | 24.7 | 8200 | 0.3696 | 0.8360 | 0.8363 | | 0.3701 | 25.3 | 8400 | 0.3690 | 0.8382 | 0.8383 | | 0.3789 | 25.9 | 8600 | 0.3663 | 0.8390 | 0.8391 | | 0.3779 | 26.51 | 8800 | 0.3662 | 0.8383 | 0.8383 | | 0.3753 | 27.11 | 9000 | 0.3665 | 0.8398 | 0.8398 | | 0.3807 | 27.71 | 9200 | 0.3664 | 0.8386 | 0.8387 | | 0.3687 | 28.31 | 9400 | 0.3675 | 0.8395 | 0.8396 | | 0.3762 | 28.92 | 9600 | 0.3668 | 0.8385 | 0.8385 | | 0.379 | 29.52 | 9800 | 0.3665 | 0.8388 | 0.8389 | | 0.3675 | 30.12 | 10000 | 0.3668 | 0.8390 | 0.8391 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_8192_512_30M", "model-index": [{"name": "GUE_prom_prom_core_notata-seqsight_8192_512_30M-L1_f", "results": []}]}

mahdibaghbanzadeh/GUE_prom_prom_core_notata-seqsight_8192_512_30M-L1_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_8192_512_30M", "region:us" ]

null

2024-04-27T02:03:27+00:00

[]

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us

GUE\_prom\_prom\_core\_notata-seqsight\_8192\_512\_30M-L1\_f ============================================================ This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_8192\_512\_30M on the mahdibaghbanzadeh/GUE\_prom\_prom\_core\_notata dataset. It achieves the following results on the evaluation set: * Loss: 0.3822 * F1 Score: 0.8334 * Accuracy: 0.8334 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

text-generation

transformers

# EinsteinBagel-8B (Einstein V6.1 & Bagel V1.0) This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). The purpose of this experiment was to combine the maximum amount of finetuned datasets possible for the Llama 3 8B architecture. ## Merge Details ### Merge Method This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) as a base. ### Models Merged The following models were included in the merge: * [Weyaxi/Einstein-v6.1-Llama3-8B](https://huggingface.co/Weyaxi/Einstein-v6.1-Llama3-8B) * [jondurbin/bagel-8b-v1.0](https://huggingface.co/jondurbin/bagel-8b-v1.0) ### Configuration The following YAML configuration was used to produce this model: ```yaml models: - model: meta-llama/Meta-Llama-3-8B - model: jondurbin/bagel-8b-v1.0 - model: Weyaxi/Einstein-v6.1-Llama3-8B merge_method: model_stock base_model: meta-llama/Meta-Llama-3-8B dtype: bfloat16 ```

{"license": "llama3", "library_name": "transformers", "tags": ["mergekit", "merge"], "base_model": ["Weyaxi/Einstein-v6.1-Llama3-8B", "meta-llama/Meta-Llama-3-8B", "jondurbin/bagel-8b-v1.0"]}

TitleOS/EinsteinBagel-8B

null

[ "transformers", "safetensors", "llama", "text-generation", "mergekit", "merge", "arxiv:2403.19522", "base_model:Weyaxi/Einstein-v6.1-Llama3-8B", "base_model:meta-llama/Meta-Llama-3-8B", "base_model:jondurbin/bagel-8b-v1.0", "license:llama3", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

null

2024-04-27T02:04:04+00:00

[ "2403.19522" ]

[]

TAGS #transformers #safetensors #llama #text-generation #mergekit #merge #arxiv-2403.19522 #base_model-Weyaxi/Einstein-v6.1-Llama3-8B #base_model-meta-llama/Meta-Llama-3-8B #base_model-jondurbin/bagel-8b-v1.0 #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

# EinsteinBagel-8B (Einstein V6.1 & Bagel V1.0) This is a merge of pre-trained language models created using mergekit. The purpose of this experiment was to combine the maximum amount of finetuned datasets possible for the Llama 3 8B architecture. ## Merge Details ### Merge Method This model was merged using the Model Stock merge method using meta-llama/Meta-Llama-3-8B as a base. ### Models Merged The following models were included in the merge: * Weyaxi/Einstein-v6.1-Llama3-8B * jondurbin/bagel-8b-v1.0 ### Configuration The following YAML configuration was used to produce this model:

[ "# EinsteinBagel-8B (Einstein V6.1 & Bagel V1.0)\n\nThis is a merge of pre-trained language models created using mergekit.\nThe purpose of this experiment was to combine the maximum amount of finetuned datasets possible for the Llama 3 8B architecture.", "## Merge Details", "### Merge Method\n\nThis model was merged using the Model Stock merge method using meta-llama/Meta-Llama-3-8B as a base.", "### Models Merged\n\nThe following models were included in the merge:\n* Weyaxi/Einstein-v6.1-Llama3-8B\n* jondurbin/bagel-8b-v1.0", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #mergekit #merge #arxiv-2403.19522 #base_model-Weyaxi/Einstein-v6.1-Llama3-8B #base_model-meta-llama/Meta-Llama-3-8B #base_model-jondurbin/bagel-8b-v1.0 #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# EinsteinBagel-8B (Einstein V6.1 & Bagel V1.0)\n\nThis is a merge of pre-trained language models created using mergekit.\nThe purpose of this experiment was to combine the maximum amount of finetuned datasets possible for the Llama 3 8B architecture.", "## Merge Details", "### Merge Method\n\nThis model was merged using the Model Stock merge method using meta-llama/Meta-Llama-3-8B as a base.", "### Models Merged\n\nThe following models were included in the merge:\n* Weyaxi/Einstein-v6.1-Llama3-8B\n* jondurbin/bagel-8b-v1.0", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

text-generation

transformers

<div align="center"> <img width="260px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/BrQCb95lmEIFz79QAmoNA.png"></div> ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/fJIOPJnY6Ff6fUiSIuMEt.png) <div align="center"> <h1>Advancing Open-source Large Language Models in Medical Domain</h1> </div> <p align="center" style="margin-top: 0px;"> <a href="https://colab.research.google.com/drive/1F5oV20InEYeAJGmBwYF9NM_QhLmjBkKJ?usp=sharing"> <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="OpenChat Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 10px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style=" margin-right: 5px;">Online Demo</span> </a> | <a href="https://github.com/openlifescience-ai"> <img src="https://github.githubassets.com/assets/GitHub-Mark-ea2971cee799.png" alt="GitHub Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style=" margin-right: 5px;">GitHub</span> </a> | <a href="#"> <img src="https://github.com/alpayariyak/openchat/blob/master/assets/arxiv-logomark-small-square-border.png?raw=true" alt="ArXiv Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style="margin-right: 5px;">Paper</span> </a> | <a href="https://discord.gg/A5Fjf5zC69"> <img src="https://cloud.githubusercontent.com/assets/6291467/26705903/96c2d66e-477c-11e7-9f4e-f3c0efe96c9a.png" alt="Discord Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text">Discord</span> </a> </p> ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/KGmRE5w2sepNtwsEu8t7K.jpeg) Introducing OpenBioLLM-70B: A State-of-the-Art Open Source Biomedical Large Language Model OpenBioLLM-70B is an advanced open source language model designed specifically for the biomedical domain. Developed by Saama AI Labs, this model leverages cutting-edge techniques to achieve state-of-the-art performance on a wide range of biomedical tasks. 🏥 **Biomedical Specialization**: OpenBioLLM-70B is tailored for the unique language and knowledge requirements of the medical and life sciences fields. It was fine-tuned on a vast corpus of high-quality biomedical data, enabling it to understand and generate text with domain-specific accuracy and fluency. 🎓 **Superior Performance**: With 70 billion parameters, OpenBioLLM-70B outperforms other open source biomedical language models of similar scale. It has also demonstrated better results compared to larger proprietary & open-source models like GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 on biomedical benchmarks. 🧠 **Advanced Training Techniques**: OpenBioLLM-70B builds upon the powerful foundations of the **Meta-Llama-3-70B-Instruct** and [Meta-Llama-3-70B-Instruct](meta-llama/Meta-Llama-3-70B-Instruct) models. It incorporates the DPO dataset and fine-tuning recipe along with a custom diverse medical instruction dataset. Key components of the training pipeline include: <div align="center"> <img width="1200px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/oPchsJsEpQoGcGXVbh7YS.png"> </div> - **Policy Optimization**: [Direct Preference Optimization: Your Language Model is Secretly a Reward Model (DPO)](https://arxiv.org/abs/2305.18290) - **Fine-tuning dataset**: Custom Medical Instruct dataset (We plan to release a sample training dataset in our upcoming paper; please stay updated) This combination of cutting-edge techniques enables OpenBioLLM-70B to align with key capabilities and preferences for biomedical applications. ⚙️ **Release Details**: - **Model Size**: 70 billion parameters - **Quantization**: Optimized quantized versions available [Here](https://huggingface.co/aaditya/OpenBioLLM-70B-GGUF) - **Language(s) (NLP):** en - **Developed By**: [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) from Saama AI Labs - **License:** Meta-Llama License - **Fine-tuned from models:** [Meta-Llama-3-70B-Instruct](meta-llama/Meta-Llama-3-70B-Instruct) - **Resources for more information:** - Paper: Coming soon The model can be fine-tuned for more specialized tasks and datasets as needed. OpenBioLLM-70B represents an important step forward in democratizing advanced language AI for the biomedical community. By leveraging state-of-the-art architectures and training techniques from leading open source efforts like Llama-3, we have created a powerful tool to accelerate innovation and discovery in healthcare and the life sciences. We are excited to share OpenBioLLM-70B with researchers and developers around the world. ### Use with transformers **Important: Please use the exact chat template provided by Llama-3 instruct version. Otherwise there will be a degradation in the performance. The model output can be verbose in rare cases. Please consider setting temperature = 0 to make this happen less.** See the snippet below for usage with Transformers: ```python import transformers import torch model_id = "aaditya/OpenBioLLM-Llama3-70B" pipeline = transformers.pipeline( "text-generation", model=model_id, model_kwargs={"torch_dtype": torch.bfloat16}, device="auto", ) messages = [ {"role": "system", "content": "You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience. Your name is OpenBioLLM, and you were developed by Saama AI Labs. who's willing to help answer the user's query with explanation. In your explanation, leverage your deep medical expertise such as relevant anatomical structures, physiological processes, diagnostic criteria, treatment guidelines, or other pertinent medical concepts. Use precise medical terminology while still aiming to make the explanation clear and accessible to a general audience."}, {"role": "user", "content": "How can i split a 3mg or 4mg waefin pill so i can get a 2.5mg pill?"}, ] prompt = pipeline.tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) terminators = [ pipeline.tokenizer.eos_token_id, pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>") ] outputs = pipeline( prompt, max_new_tokens=256, eos_token_id=terminators, do_sample=True, temperature=0.0, top_p=0.9, ) print(outputs[0]["generated_text"][len(prompt):]) ``` ## **Training procedure** ### **Training hyperparameters** <details> <summary>Click to see details</summary> - learning_rate: 0.0002 - lr_scheduler: cosine - train_batch_size: 12 - eval_batch_size: 8 - GPU: H100 80GB SXM5 - num_devices: 8 - optimizer: adamw_bnb_8bit - lr_scheduler_warmup_steps: 100 - num_epochs: 4 </details> ### **Peft hyperparameters** <details> <summary>Click to see details</summary> - adapter: qlora - lora_r: 128 - lora_alpha: 256 - lora_dropout: 0.05 - lora_target_linear: true -lora_target_modules: - q_proj - v_proj - k_proj - o_proj - gate_proj - down_proj - up_proj </details> ### **Training results** ### **Framework versions** - Transformers 4.39.3 - Pytorch 2.1.2+cu121 - Datasets 2.18.0 - Tokenizers 0.15.1 - Axolotl - Lm harness for evaluation # Benchmark Results 🔥 OpenBioLLM-70B demonstrates superior performance compared to larger models, such as GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 across 9 diverse biomedical datasets, achieving state-of-the-art results with an average score of 86.06%, despite having a significantly smaller parameter count. The model's strong performance in domain-specific tasks, such as Clinical KG, Medical Genetics, and PubMedQA, highlights its ability to effectively capture and apply biomedical knowledge. 🚨 The GPT-4, Med-PaLM-1, and Med-PaLM-2 results are taken from their official papers. Since Med-PaLM doesn't provide zero-shot accuracy, we are using 5-shot accuracy from their paper for comparison. All results presented are in the zero-shot setting, except for Med-PaLM-2 and Med-PaLM-1, which use 5-shot accuracy. | | Clinical KG | Medical Genetics | Anatomy | Pro Medicine | College Biology | College Medicine | MedQA 4 opts | PubMedQA | MedMCQA | Avg | |--------------------|-------------|------------------|---------|--------------|-----------------|------------------|--------------|----------|---------|-------| | **OpenBioLLM-70B** | **92.93** | **93.197** | **83.904** | 93.75 | 93.827 | **85.749** | 78.162 | 78.97 | **74.014** | **86.05588** | | Med-PaLM-2 (5-shot) | 88.3 | 90 | 77.8 | **95.2** | 94.4 | 80.9 | **79.7** | **79.2** | 71.3 | 84.08 | | **GPT-4** | 86.04 | 91 | 80 | 93.01 | **95.14** | 76.88 | 78.87 | 75.2 | 69.52 | 82.85 | | Med-PaLM-1 (Flan-PaLM, 5-shot) | 80.4 | 75 | 63.7 | 83.8 | 88.9 | 76.3 | 67.6 | 79 | 57.6 | 74.7 | | **OpenBioLLM-8B** | 76.101 | 86.1 | 69.829 | 78.21 | 84.213 | 68.042 | 58.993 | 74.12 | 56.913 | 72.502 | | Gemini-1.0 | 76.7 | 75.8 | 66.7 | 77.7 | 88 | 69.2 | 58 | 70.7 | 54.3 | 70.79 | | GPT-3.5 Turbo 1106 | 74.71 | 74 | 72.79 | 72.79 | 72.91 | 64.73 | 57.71 | 72.66 | 53.79 | 66 | | Meditron-70B | 66.79 | 69 | 53.33 | 71.69 | 76.38 | 63 | 57.1 | 76.6 | 46.85 | 64.52 | | gemma-7b | 69.81 | 70 | 59.26 | 66.18 | 79.86 | 60.12 | 47.21 | 76.2 | 48.96 | 64.18 | | Mistral-7B-v0.1 | 68.68 | 71 | 55.56 | 68.38 | 68.06 | 59.54 | 50.82 | 75.4 | 48.2 | 62.85 | | Apollo-7B | 62.26 | 72 | 61.48 | 69.12 | 70.83 | 55.49 | 55.22 | 39.8 | 53.77 | 60 | | MedAlpaca-7b | 57.36 | 69 | 57.04 | 67.28 | 65.28 | 54.34 | 41.71 | 72.8 | 37.51 | 58.03 | | BioMistral-7B | 59.9 | 64 | 56.5 | 60.4 | 59 | 54.7 | 50.6 | 77.5 | 48.1 | 57.3 | | AlpaCare-llama2-7b | 49.81 | 49 | 45.92 | 33.82 | 50 | 43.35 | 29.77 | 72.2 | 34.42 | 45.36 | | ClinicalGPT | 30.56 | 27 | 30.37 | 19.48 | 25 | 24.27 | 26.08 | 63.8 | 28.18 | 30.52 | <div align="center"> <img width="1600px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/_SzdcJSBjZyo8RS1bTEkP.png"> </div> ## Detailed Medical Subjectwise accuracy ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/UXF-V0col0Z0sS6BGPBkE.png) # Use Cases & Examples 🚨 **Below results are from the quantized version of OpenBioLLM-70B # Summarize Clinical Notes OpenBioLLM-70B can efficiently analyze and summarize complex clinical notes, EHR data, and discharge summaries, extracting key information and generating concise, structured summaries ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/xdwdBgOxNi_TfML0hKlI8.png) # Answer Medical Questions OpenBioLLM-70B can provide answers to a wide range of medical questions. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/zO95GlwOQEZqCKQF69mE6.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/OKBczKw7gWeW5xsuDpc27.png) <details> <summary>Click to see details</summary> ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/eJGHT5khppYvJb8fQ-YW4.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/Cnbwrqa_-ORHRuNRC2P6Y.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/J9DhdcvukAc9mnnW9fj2C.png) </details> # Clinical Entity Recognition OpenBioLLM-70B can perform advanced clinical entity recognition by identifying and extracting key medical concepts, such as diseases, symptoms, medications, procedures, and anatomical structures, from unstructured clinical text. By leveraging its deep understanding of medical terminology and context, the model can accurately annotate and categorize clinical entities, enabling more efficient information retrieval, data analysis, and knowledge discovery from electronic health records, research articles, and other biomedical text sources. This capability can support various downstream applications, such as clinical decision support, pharmacovigilance, and medical research. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/_69BW4k9LVABFwtxixL45.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/DKy5wYCoPhoPPUc1-x8_J.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/7WD9zCCBZT4-4XlfnIQjl.png) # Biomarkers Extraction ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/ZttoM4AiteT7gFYVhjIpN.png) # Classification OpenBioLLM-70B can perform various biomedical classification tasks, such as disease prediction, sentiment analysis, medical document categorization ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/Bf5MW1d75qT-1F_TR_hC0.png) # De-Identification OpenBioLLM-70B can detect and remove personally identifiable information (PII) from medical records, ensuring patient privacy and compliance with data protection regulations like HIPAA. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/hKX4kzm--Tw5bj6K78msy.png) **Advisory Notice!** While OpenBioLLM-70B leverages high-quality data sources, its outputs may still contain inaccuracies, biases, or misalignments that could pose risks if relied upon for medical decision-making without further testing and refinement. The model's performance has not yet been rigorously evaluated in randomized controlled trials or real-world healthcare environments. Therefore, we strongly advise against using OpenBioLLM-70B for any direct patient care, clinical decision support, or other professional medical purposes at this time. Its use should be limited to research, development, and exploratory applications by qualified individuals who understand its limitations. OpenBioLLM-70B is intended solely as a research tool to assist healthcare professionals and should never be considered a replacement for the professional judgment and expertise of a qualified medical doctor. Appropriately adapting and validating OpenBioLLM-70B for specific medical use cases would require significant additional work, potentially including: - Thorough testing and evaluation in relevant clinical scenarios - Alignment with evidence-based guidelines and best practices - Mitigation of potential biases and failure modes - Integration with human oversight and interpretation - Compliance with regulatory and ethical standards Always consult a qualified healthcare provider for personal medical needs. # Citation If you find OpenBioLLM-70B & 8B useful in your work, please cite the model as follows: ``` @misc{OpenBioLLMs, author = {Ankit Pal, Malaikannan Sankarasubbu}, title = {OpenBioLLMs: Advancing Open-Source Large Language Models for Healthcare and Life Sciences}, year = {2024}, publisher = {Hugging Face}, journal = {Hugging Face repository}, howpublished = {\url{https://huggingface.co/aaditya/OpenBioLLM-Llama3-70B}} } ``` The accompanying paper is currently in progress and will be released soon. <div align="center"> <h2> 💌 Contact </h2> </div> We look forward to hearing you and collaborating on this exciting project! **Contributors:** - [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) [aadityaura at gmail dot com] - Saama AI Labs - Note: I am looking for a funded PhD opportunity, especially if it fits my Responsible Generative AI, Multimodal LLMs, Geometric Deep Learning, and Healthcare AI skillset. # References We thank the [Meta Team](meta-llama/Meta-Llama-3-70B-Instruct) for their amazing models! Result sources - [1] GPT-4 [Capabilities of GPT-4 on Medical Challenge Problems] (https://arxiv.org/abs/2303.13375) - [2] Med-PaLM-1 [Large Language Models Encode Clinical Knowledge](https://arxiv.org/abs/2212.13138) - [3] Med-PaLM-2 [Towards Expert-Level Medical Question Answering with Large Language Models](https://arxiv.org/abs/2305.09617) - [4] Gemini-1.0 [Gemini Goes to Med School](https://arxiv.org/abs/2402.07023)

{"language": ["en"], "license": "llama3", "tags": ["llama-3", "llama", "Mixtral", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "distillation"], "base_model": "meta-llama/Meta-Llama-3-70B-Instruct", "widget": [{"example_title": "OpenBioLLM-70B", "messages": [{"role": "system", "content": "You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience."}, {"role": "user", "content": "How long does it take for newborn jaundice to go away?"}], "output": {"text": "Newborn jaundice, also known as neonatal jaundice, is a common condition in newborns where the yellowing of the skin and eyes occurs due to an elevated level of bilirubin in the blood. Bilirubin is a yellow pigment that forms when red blood cells break down. In most cases, newborn jaundice resolves on its own without any specific treatment.\nThe duration of newborn jaundice can vary depending on several factors such as the underlying cause, gestational age at birth, and individual variations in bilirubin metabolism. Here are some general guidelines:\n1. Physiological jaundice: This is the most common type of newborn jaundice and usually appears within 24-72 hours after birth. It tends to peak between the second and fifth day of life and gradually improves over the next week or two. By the time the baby is one week old, the jaundice should have mostly resolved. 2. Breast milk jaundice: This type of jaundice occurs in breastfed babies and may appear later than physiological jaundice, typically between the fifth and fourteenth day of life. It tends to persist for a longer duration but usually resolves within six weeks after birth. 3. Pathological jaundice: This type of jaundice is less common and occurs due to an underlying medical condition that affects bilirubin metabolism or liver function. The duration of pathological jaundice depends on the specific cause and may require treatment.\nIt's important for parents to monitor their newborn's jaundice closely and seek medical advice if the jaundice progresses rapidly, becomes severe, or is accompanied by other symptoms such as poor feeding, lethargy, or excessive sleepiness. In these cases, further evaluation and management may be necessary. Remember that each baby is unique, and the timing of jaundice resolution can vary. If you have concerns about your newborn's jaundice, it's always best to consult with a healthcare professional for personalized advice and guidance."}}], "model-index": [{"name": "OpenBioLLM-70B", "results": []}]}

LoneStriker/OpenBioLLM-Llama3-70B-5.0bpw-h6-exl2

null

[ "transformers", "pytorch", "llama", "text-generation", "llama-3", "Mixtral", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "distillation", "conversational", "en", "arxiv:2305.18290", "arxiv:2303.13375", "arxiv:2212.13138", "arxiv:2305.09617", "arxiv:2402.07023", "base_model:meta-llama/Meta-Llama-3-70B-Instruct", "license:llama3", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "5-bit", "region:us" ]

null

2024-04-27T02:04:19+00:00

[ "2305.18290", "2303.13375", "2212.13138", "2305.09617", "2402.07023" ]

[ "en" ]

TAGS #transformers #pytorch #llama #text-generation #llama-3 #Mixtral #instruct #finetune #chatml #DPO #RLHF #gpt4 #distillation #conversational #en #arxiv-2305.18290 #arxiv-2303.13375 #arxiv-2212.13138 #arxiv-2305.09617 #arxiv-2402.07023 #base_model-meta-llama/Meta-Llama-3-70B-Instruct #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #5-bit #region-us

![](URL <p>!image/png</p> <div align=) Advancing Open-source Large Language Models in Medical Domain ============================================================= Online Demo | GitHub | [![](URL alt=)](#) | Discord !image/jpeg Introducing OpenBioLLM-70B: A State-of-the-Art Open Source Biomedical Large Language Model OpenBioLLM-70B is an advanced open source language model designed specifically for the biomedical domain. Developed by Saama AI Labs, this model leverages cutting-edge techniques to achieve state-of-the-art performance on a wide range of biomedical tasks. Biomedical Specialization: OpenBioLLM-70B is tailored for the unique language and knowledge requirements of the medical and life sciences fields. It was fine-tuned on a vast corpus of high-quality biomedical data, enabling it to understand and generate text with domain-specific accuracy and fluency. Superior Performance: With 70 billion parameters, OpenBioLLM-70B outperforms other open source biomedical language models of similar scale. It has also demonstrated better results compared to larger proprietary & open-source models like GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 on biomedical benchmarks. Advanced Training Techniques: OpenBioLLM-70B builds upon the powerful foundations of the Meta-Llama-3-70B-Instruct and Meta-Llama-3-70B-Instruct models. It incorporates the DPO dataset and fine-tuning recipe along with a custom diverse medical instruction dataset. Key components of the training pipeline include: ![](URL </div> <ul> <li>Policy Optimization: Direct Preference Optimization: Your Language Model is Secretly a Reward Model (DPO)</li> <li>Fine-tuning dataset: Custom Medical Instruct dataset (We plan to release a sample training dataset in our upcoming paper; please stay updated)</li> </ul> <p>This combination of cutting-edge techniques enables OpenBioLLM-70B to align with key capabilities and preferences for biomedical applications.</p> <p>️ Release Details:</p> <ul> <li>Model Size: 70 billion parameters</li> <li>Quantization: Optimized quantized versions available Here</li> <li>Language(s) (NLP): en</li> <li>Developed By: Ankit Pal (Aaditya Ura) from Saama AI Labs</li> <li>License: Meta-Llama License</li> <li>Fine-tuned from models: Meta-Llama-3-70B-Instruct</li> <li>Resources for more information: <ul> <li>Paper: Coming soon</li> </ul> </li> </ul> <p>The model can be fine-tuned for more specialized tasks and datasets as needed.</p> <p>OpenBioLLM-70B represents an important step forward in democratizing advanced language AI for the biomedical community. By leveraging state-of-the-art architectures and training techniques from leading open source efforts like Llama-3, we have created a powerful tool to accelerate innovation and discovery in healthcare and the life sciences.</p> <p>We are excited to share OpenBioLLM-70B with researchers and developers around the world.</p> <h3>Use with transformers</h3> <p>Important: Please use the exact chat template provided by Llama-3 instruct version. Otherwise there will be a degradation in the performance. The model output can be verbose in rare cases. Please consider setting temperature = 0 to make this happen less.</p> <p>See the snippet below for usage with Transformers:</p> <h2>Training procedure</h2> <h3>Training hyperparameters</h3> <details> <summary>Click to see details</summary> <ul> <li>learning_rate: 0.0002</li> <li>lr_scheduler: cosine</li> <li>train_batch_size: 12</li> <li>eval_batch_size: 8</li> <li>GPU: H100 80GB SXM5</li> <li>num_devices: 8</li> <li>optimizer: adamw_bnb_8bit</li> <li>lr_scheduler_warmup_steps: 100</li> <li>num_epochs: 4</li> </ul> </details> <h3>Peft hyperparameters</h3> <details> <summary>Click to see details</summary> <ul> <li>adapter: qlora</li> <li>lora_r: 128</li> <li>lora_alpha: 256</li> <li>lora_dropout: 0.05</li> <li>lora_target_linear: true</li> </ul> <p>-lora_target_modules:</p> <ul> <li>q_proj</li> <li>v_proj</li> <li>k_proj</li> <li>o_proj</li> <li>gate_proj</li> <li>down_proj</li> <li>up_proj</li> </ul> </details> <h3>Training results</h3> <h3>Framework versions</h3> <ul> <li>Transformers 4.39.3</li> <li>Pytorch 2.1.2+cu121</li> <li>Datasets 2.18.0</li> <li>Tokenizers 0.15.1</li> <li>Axolotl</li> <li>Lm harness for evaluation</li> </ul> <h1>Benchmark Results</h1> <p>OpenBioLLM-70B demonstrates superior performance compared to larger models, such as GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 across 9 diverse biomedical datasets, achieving state-of-the-art results with an average score of 86.06%, despite having a significantly smaller parameter count. The model's strong performance in domain-specific tasks, such as Clinical KG, Medical Genetics, and PubMedQA, highlights its ability to effectively capture and apply biomedical knowledge.</p> <p>The GPT-4, Med-PaLM-1, and Med-PaLM-2 results are taken from their official papers. Since Med-PaLM doesn't provide zero-shot accuracy, we are using 5-shot accuracy from their paper for comparison. All results presented are in the zero-shot setting, except for Med-PaLM-2 and Med-PaLM-1, which use 5-shot accuracy.</p> <p></p> <div align=) ![](URL </div> <h2>Detailed Medical Subjectwise accuracy</h2> <p>!image/png</p> <h1>Use Cases & Examples</h1> <p>Below results are from the quantized version of OpenBioLLM-70B</p> <h1>Summarize Clinical Notes</h1> <p>OpenBioLLM-70B can efficiently analyze and summarize complex clinical notes, EHR data, and discharge summaries, extracting key information and generating concise, structured summaries</p> <p>!image/png</p> <h1>Answer Medical Questions</h1> <p>OpenBioLLM-70B can provide answers to a wide range of medical questions.</p> <p>!image/png !image/png</p> <details> <summary>Click to see details</summary> <p>!image/png !image/png !image/png</p> </details> <h1>Clinical Entity Recognition</h1> <p>OpenBioLLM-70B can perform advanced clinical entity recognition by identifying and extracting key medical concepts, such as diseases, symptoms, medications, procedures, and anatomical structures, from unstructured clinical text. By leveraging its deep understanding of medical terminology and context, the model can accurately annotate and categorize clinical entities, enabling more efficient information retrieval, data analysis, and knowledge discovery from electronic health records, research articles, and other biomedical text sources. This capability can support various downstream applications, such as clinical decision support, pharmacovigilance, and medical research.</p> <p>!image/png !image/png !image/png</p> <h1>Biomarkers Extraction</h1> <p>!image/png</p> <h1>Classification</h1> <p>OpenBioLLM-70B can perform various biomedical classification tasks, such as disease prediction, sentiment analysis, medical document categorization</p> <p>!image/png</p> <h1>De-Identification</h1> <p>OpenBioLLM-70B can detect and remove personally identifiable information (PII) from medical records, ensuring patient privacy and compliance with data protection regulations like HIPAA.</p> <p>!image/png</p> <p>Advisory Notice!</p> <p>While OpenBioLLM-70B leverages high-quality data sources, its outputs may still contain inaccuracies, biases, or misalignments that could pose risks if relied upon for medical decision-making without further testing and refinement. The model's performance has not yet been rigorously evaluated in randomized controlled trials or real-world healthcare environments.</p> <p>Therefore, we strongly advise against using OpenBioLLM-70B for any direct patient care, clinical decision support, or other professional medical purposes at this time. Its use should be limited to research, development, and exploratory applications by qualified individuals who understand its limitations. OpenBioLLM-70B is intended solely as a research tool to assist healthcare professionals and should never be considered a replacement for the professional judgment and expertise of a qualified medical doctor.</p> <p>Appropriately adapting and validating OpenBioLLM-70B for specific medical use cases would require significant additional work, potentially including:</p> <ul> <li>Thorough testing and evaluation in relevant clinical scenarios</li> <li>Alignment with evidence-based guidelines and best practices</li> <li>Mitigation of potential biases and failure modes</li> <li>Integration with human oversight and interpretation</li> <li>Compliance with regulatory and ethical standards</li> </ul> <p>Always consult a qualified healthcare provider for personal medical needs.</p> <p>If you find OpenBioLLM-70B & 8B useful in your work, please cite the model as follows:</p> <p>The accompanying paper is currently in progress and will be released soon.</p> <div align=) Contact -------- We look forward to hearing you and collaborating on this exciting project! Contributors: * Ankit Pal (Aaditya Ura) [aadityaura at gmail dot com] * Saama AI Labs * Note: I am looking for a funded PhD opportunity, especially if it fits my Responsible Generative AI, Multimodal LLMs, Geometric Deep Learning, and Healthcare AI skillset. References ========== We thank the Meta Team for their amazing models! Result sources * [1] GPT-4 [Capabilities of GPT-4 on Medical Challenge Problems] (URL * [2] Med-PaLM-1 Large Language Models Encode Clinical Knowledge * [3] Med-PaLM-2 Towards Expert-Level Medical Question Answering with Large Language Models * [4] Gemini-1.0 Gemini Goes to Med School

[]

[ "TAGS\n#transformers #pytorch #llama #text-generation #llama-3 #Mixtral #instruct #finetune #chatml #DPO #RLHF #gpt4 #distillation #conversational #en #arxiv-2305.18290 #arxiv-2303.13375 #arxiv-2212.13138 #arxiv-2305.09617 #arxiv-2402.07023 #base_model-meta-llama/Meta-Llama-3-70B-Instruct #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #5-bit #region-us \n" ]

null

peft

# GUE_prom_prom_core_notata-seqsight_8192_512_30M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_8192_512_30M](https://huggingface.co/mahdibaghbanzadeh/seqsight_8192_512_30M) on the [mahdibaghbanzadeh/GUE_prom_prom_core_notata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_core_notata) dataset. It achieves the following results on the evaluation set: - Loss: 0.3812 - F1 Score: 0.8355 - Accuracy: 0.8355 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.513 | 0.6 | 200 | 0.3994 | 0.8211 | 0.8214 | | 0.4186 | 1.2 | 400 | 0.3783 | 0.8323 | 0.8323 | | 0.3998 | 1.81 | 600 | 0.3873 | 0.8288 | 0.8291 | | 0.399 | 2.41 | 800 | 0.3745 | 0.8323 | 0.8325 | | 0.39 | 3.01 | 1000 | 0.3702 | 0.8347 | 0.8347 | | 0.3851 | 3.61 | 1200 | 0.3677 | 0.8353 | 0.8355 | | 0.3879 | 4.22 | 1400 | 0.3709 | 0.8355 | 0.8355 | | 0.3845 | 4.82 | 1600 | 0.3671 | 0.8353 | 0.8355 | | 0.3747 | 5.42 | 1800 | 0.3700 | 0.8347 | 0.8347 | | 0.379 | 6.02 | 2000 | 0.3664 | 0.8365 | 0.8366 | | 0.3774 | 6.63 | 2200 | 0.3633 | 0.8391 | 0.8391 | | 0.3737 | 7.23 | 2400 | 0.3662 | 0.8362 | 0.8364 | | 0.3737 | 7.83 | 2600 | 0.3624 | 0.8398 | 0.8398 | | 0.3687 | 8.43 | 2800 | 0.3687 | 0.8369 | 0.8372 | | 0.3762 | 9.04 | 3000 | 0.3607 | 0.8415 | 0.8415 | | 0.3677 | 9.64 | 3200 | 0.3623 | 0.8421 | 0.8421 | | 0.3706 | 10.24 | 3400 | 0.3620 | 0.8412 | 0.8412 | | 0.3642 | 10.84 | 3600 | 0.3611 | 0.8412 | 0.8412 | | 0.3663 | 11.45 | 3800 | 0.3619 | 0.8419 | 0.8419 | | 0.3639 | 12.05 | 4000 | 0.3606 | 0.8412 | 0.8412 | | 0.3644 | 12.65 | 4200 | 0.3616 | 0.8420 | 0.8421 | | 0.3622 | 13.25 | 4400 | 0.3607 | 0.8420 | 0.8421 | | 0.3645 | 13.86 | 4600 | 0.3633 | 0.8426 | 0.8427 | | 0.3606 | 14.46 | 4800 | 0.3621 | 0.8418 | 0.8419 | | 0.36 | 15.06 | 5000 | 0.3583 | 0.8434 | 0.8434 | | 0.354 | 15.66 | 5200 | 0.3607 | 0.8449 | 0.8449 | | 0.3562 | 16.27 | 5400 | 0.3656 | 0.8427 | 0.8427 | | 0.3576 | 16.87 | 5600 | 0.3634 | 0.8396 | 0.8400 | | 0.3541 | 17.47 | 5800 | 0.3639 | 0.8402 | 0.8404 | | 0.3597 | 18.07 | 6000 | 0.3610 | 0.8443 | 0.8444 | | 0.356 | 18.67 | 6200 | 0.3595 | 0.8428 | 0.8428 | | 0.3557 | 19.28 | 6400 | 0.3599 | 0.8440 | 0.8440 | | 0.3536 | 19.88 | 6600 | 0.3583 | 0.8440 | 0.8440 | | 0.349 | 20.48 | 6800 | 0.3602 | 0.8438 | 0.8438 | | 0.3583 | 21.08 | 7000 | 0.3598 | 0.8416 | 0.8417 | | 0.3538 | 21.69 | 7200 | 0.3628 | 0.8436 | 0.8436 | | 0.3453 | 22.29 | 7400 | 0.3594 | 0.8405 | 0.8406 | | 0.349 | 22.89 | 7600 | 0.3610 | 0.8403 | 0.8404 | | 0.3513 | 23.49 | 7800 | 0.3585 | 0.8428 | 0.8428 | | 0.3494 | 24.1 | 8000 | 0.3610 | 0.8407 | 0.8408 | | 0.3513 | 24.7 | 8200 | 0.3615 | 0.8413 | 0.8415 | | 0.3428 | 25.3 | 8400 | 0.3644 | 0.8414 | 0.8415 | | 0.351 | 25.9 | 8600 | 0.3603 | 0.8434 | 0.8434 | | 0.3489 | 26.51 | 8800 | 0.3614 | 0.8436 | 0.8436 | | 0.3464 | 27.11 | 9000 | 0.3612 | 0.8417 | 0.8417 | | 0.3532 | 27.71 | 9200 | 0.3609 | 0.8418 | 0.8419 | | 0.3403 | 28.31 | 9400 | 0.3613 | 0.8415 | 0.8415 | | 0.3481 | 28.92 | 9600 | 0.3613 | 0.8445 | 0.8445 | | 0.3499 | 29.52 | 9800 | 0.3611 | 0.8439 | 0.8440 | | 0.3406 | 30.12 | 10000 | 0.3613 | 0.8443 | 0.8444 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_8192_512_30M", "model-index": [{"name": "GUE_prom_prom_core_notata-seqsight_8192_512_30M-L8_f", "results": []}]}

mahdibaghbanzadeh/GUE_prom_prom_core_notata-seqsight_8192_512_30M-L8_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_8192_512_30M", "region:us" ]

null

2024-04-27T02:09:28+00:00

[]

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us

GUE\_prom\_prom\_core\_notata-seqsight\_8192\_512\_30M-L8\_f ============================================================ This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_8192\_512\_30M on the mahdibaghbanzadeh/GUE\_prom\_prom\_core\_notata dataset. It achieves the following results on the evaluation set: * Loss: 0.3812 * F1 Score: 0.8355 * Accuracy: 0.8355 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

null

peft

## Training procedure The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float16 ### Framework versions - PEFT 0.4.0

{"library_name": "peft"}

vicaloy/llama-2-13-b-chat-hf-checkpoints

null

[ "peft", "region:us" ]

null

2024-04-27T02:09:30+00:00

[]

TAGS #peft #region-us

## Training procedure The following 'bitsandbytes' quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float16 ### Framework versions - PEFT 0.4.0

[ "## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: False\n- bnb_4bit_compute_dtype: float16", "### Framework versions\n\n\n- PEFT 0.4.0" ]

[ "TAGS\n#peft #region-us \n", "## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: False\n- bnb_4bit_compute_dtype: float16", "### Framework versions\n\n\n- PEFT 0.4.0" ]

null

peft

# GUE_prom_prom_core_notata-seqsight_8192_512_30M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_8192_512_30M](https://huggingface.co/mahdibaghbanzadeh/seqsight_8192_512_30M) on the [mahdibaghbanzadeh/GUE_prom_prom_core_notata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_core_notata) dataset. It achieves the following results on the evaluation set: - Loss: 0.3910 - F1 Score: 0.8342 - Accuracy: 0.8342 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.4915 | 0.6 | 200 | 0.3862 | 0.8258 | 0.8259 | | 0.4066 | 1.2 | 400 | 0.3737 | 0.8340 | 0.8340 | | 0.3919 | 1.81 | 600 | 0.3887 | 0.8283 | 0.8287 | | 0.3899 | 2.41 | 800 | 0.3694 | 0.8350 | 0.8351 | | 0.3828 | 3.01 | 1000 | 0.3681 | 0.8373 | 0.8376 | | 0.3764 | 3.61 | 1200 | 0.3621 | 0.8380 | 0.8381 | | 0.3795 | 4.22 | 1400 | 0.3674 | 0.8364 | 0.8364 | | 0.3758 | 4.82 | 1600 | 0.3637 | 0.8381 | 0.8383 | | 0.3635 | 5.42 | 1800 | 0.3703 | 0.8365 | 0.8366 | | 0.3702 | 6.02 | 2000 | 0.3708 | 0.8381 | 0.8385 | | 0.3646 | 6.63 | 2200 | 0.3592 | 0.8432 | 0.8432 | | 0.3602 | 7.23 | 2400 | 0.3715 | 0.8348 | 0.8353 | | 0.3591 | 7.83 | 2600 | 0.3618 | 0.8429 | 0.8428 | | 0.3521 | 8.43 | 2800 | 0.3645 | 0.8420 | 0.8423 | | 0.36 | 9.04 | 3000 | 0.3615 | 0.8442 | 0.8444 | | 0.3498 | 9.64 | 3200 | 0.3618 | 0.8451 | 0.8451 | | 0.3517 | 10.24 | 3400 | 0.3621 | 0.8456 | 0.8457 | | 0.345 | 10.84 | 3600 | 0.3601 | 0.8451 | 0.8451 | | 0.3444 | 11.45 | 3800 | 0.3621 | 0.8443 | 0.8444 | | 0.3446 | 12.05 | 4000 | 0.3584 | 0.8463 | 0.8462 | | 0.3399 | 12.65 | 4200 | 0.3628 | 0.8474 | 0.8474 | | 0.3389 | 13.25 | 4400 | 0.3635 | 0.8465 | 0.8466 | | 0.3401 | 13.86 | 4600 | 0.3670 | 0.8447 | 0.8447 | | 0.3351 | 14.46 | 4800 | 0.3680 | 0.8433 | 0.8436 | | 0.3337 | 15.06 | 5000 | 0.3601 | 0.8449 | 0.8449 | | 0.3251 | 15.66 | 5200 | 0.3699 | 0.8470 | 0.8470 | | 0.3292 | 16.27 | 5400 | 0.3756 | 0.8483 | 0.8483 | | 0.3268 | 16.87 | 5600 | 0.3730 | 0.8413 | 0.8417 | | 0.3225 | 17.47 | 5800 | 0.3712 | 0.8429 | 0.8432 | | 0.3296 | 18.07 | 6000 | 0.3713 | 0.8455 | 0.8457 | | 0.3239 | 18.67 | 6200 | 0.3693 | 0.8451 | 0.8451 | | 0.3218 | 19.28 | 6400 | 0.3720 | 0.8469 | 0.8470 | | 0.3204 | 19.88 | 6600 | 0.3639 | 0.8440 | 0.8440 | | 0.3136 | 20.48 | 6800 | 0.3698 | 0.8488 | 0.8489 | | 0.3241 | 21.08 | 7000 | 0.3692 | 0.8457 | 0.8459 | | 0.3188 | 21.69 | 7200 | 0.3751 | 0.8468 | 0.8468 | | 0.3107 | 22.29 | 7400 | 0.3699 | 0.8426 | 0.8428 | | 0.3123 | 22.89 | 7600 | 0.3725 | 0.8425 | 0.8427 | | 0.3143 | 23.49 | 7800 | 0.3703 | 0.8456 | 0.8457 | | 0.3126 | 24.1 | 8000 | 0.3763 | 0.8428 | 0.8430 | | 0.3145 | 24.7 | 8200 | 0.3763 | 0.8408 | 0.8412 | | 0.3051 | 25.3 | 8400 | 0.3814 | 0.8430 | 0.8432 | | 0.3089 | 25.9 | 8600 | 0.3747 | 0.8429 | 0.8430 | | 0.3074 | 26.51 | 8800 | 0.3758 | 0.8449 | 0.8449 | | 0.3069 | 27.11 | 9000 | 0.3746 | 0.8437 | 0.8438 | | 0.3115 | 27.71 | 9200 | 0.3769 | 0.8419 | 0.8421 | | 0.3003 | 28.31 | 9400 | 0.3779 | 0.8413 | 0.8415 | | 0.3042 | 28.92 | 9600 | 0.3785 | 0.8408 | 0.8410 | | 0.3067 | 29.52 | 9800 | 0.3772 | 0.8412 | 0.8413 | | 0.298 | 30.12 | 10000 | 0.3778 | 0.8411 | 0.8412 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_8192_512_30M", "model-index": [{"name": "GUE_prom_prom_core_notata-seqsight_8192_512_30M-L32_f", "results": []}]}

mahdibaghbanzadeh/GUE_prom_prom_core_notata-seqsight_8192_512_30M-L32_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_8192_512_30M", "region:us" ]

null

2024-04-27T02:10:35+00:00

[]

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us

GUE\_prom\_prom\_core\_notata-seqsight\_8192\_512\_30M-L32\_f ============================================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_8192\_512\_30M on the mahdibaghbanzadeh/GUE\_prom\_prom\_core\_notata dataset. It achieves the following results on the evaluation set: * Loss: 0.3910 * F1 Score: 0.8342 * Accuracy: 0.8342 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

text-classification

transformers

# my_awesome_model This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.1924 - Accuracy: 0.9529 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 2 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 0.198 | 1.0 | 1563 | 0.1405 | 0.9501 | | 0.1304 | 2.0 | 3126 | 0.1924 | 0.9529 | ### Framework versions - Transformers 4.40.0 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1

{"license": "mit", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "roberta-base", "model-index": [{"name": "my_awesome_model", "results": []}]}

brunhild217/my_awesome_model

null

[ "transformers", "tensorboard", "safetensors", "roberta", "text-classification", "generated_from_trainer", "base_model:roberta-base", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]

null

2024-04-27T02:12:24+00:00

[]

TAGS #transformers #tensorboard #safetensors #roberta #text-classification #generated_from_trainer #base_model-roberta-base #license-mit #autotrain_compatible #endpoints_compatible #region-us

my\_awesome\_model ================== This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set: * Loss: 0.1924 * Accuracy: 0.9529 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 2e-05 * train\_batch\_size: 16 * eval\_batch\_size: 16 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * num\_epochs: 2 ### Training results ### Framework versions * Transformers 4.40.0 * Pytorch 2.2.1+cu121 * Datasets 2.19.0 * Tokenizers 0.19.1

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 2", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #roberta #text-classification #generated_from_trainer #base_model-roberta-base #license-mit #autotrain_compatible #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 2", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

null

peft

# GUE_prom_prom_core_tata-seqsight_8192_512_30M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_8192_512_30M](https://huggingface.co/mahdibaghbanzadeh/seqsight_8192_512_30M) on the [mahdibaghbanzadeh/GUE_prom_prom_core_tata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_core_tata) dataset. It achieves the following results on the evaluation set: - Loss: 0.4139 - F1 Score: 0.8204 - Accuracy: 0.8206 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:------:|:-----:|:---------------:|:--------:|:--------:| | 0.598 | 5.13 | 200 | 0.5809 | 0.6855 | 0.6884 | | 0.5478 | 10.26 | 400 | 0.5718 | 0.6949 | 0.6982 | | 0.5292 | 15.38 | 600 | 0.5582 | 0.7134 | 0.7178 | | 0.5098 | 20.51 | 800 | 0.5347 | 0.7385 | 0.7406 | | 0.4956 | 25.64 | 1000 | 0.5128 | 0.7385 | 0.7390 | | 0.4841 | 30.77 | 1200 | 0.4952 | 0.7504 | 0.7504 | | 0.4687 | 35.9 | 1400 | 0.4978 | 0.7327 | 0.7341 | | 0.4547 | 41.03 | 1600 | 0.4727 | 0.7731 | 0.7732 | | 0.4453 | 46.15 | 1800 | 0.4649 | 0.7664 | 0.7667 | | 0.427 | 51.28 | 2000 | 0.4587 | 0.7757 | 0.7765 | | 0.4099 | 56.41 | 2200 | 0.4288 | 0.8010 | 0.8010 | | 0.3969 | 61.54 | 2400 | 0.4209 | 0.8091 | 0.8091 | | 0.3875 | 66.67 | 2600 | 0.4110 | 0.8091 | 0.8091 | | 0.376 | 71.79 | 2800 | 0.4023 | 0.8237 | 0.8238 | | 0.364 | 76.92 | 3000 | 0.4107 | 0.8087 | 0.8091 | | 0.3553 | 82.05 | 3200 | 0.3894 | 0.8270 | 0.8271 | | 0.3515 | 87.18 | 3400 | 0.4001 | 0.8250 | 0.8254 | | 0.3446 | 92.31 | 3600 | 0.3743 | 0.8385 | 0.8385 | | 0.3406 | 97.44 | 3800 | 0.3740 | 0.8385 | 0.8385 | | 0.3333 | 102.56 | 4000 | 0.3718 | 0.8434 | 0.8434 | | 0.3285 | 107.69 | 4200 | 0.3647 | 0.8450 | 0.8450 | | 0.3212 | 112.82 | 4400 | 0.3744 | 0.8450 | 0.8450 | | 0.3183 | 117.95 | 4600 | 0.3704 | 0.8401 | 0.8401 | | 0.319 | 123.08 | 4800 | 0.3620 | 0.8418 | 0.8418 | | 0.3103 | 128.21 | 5000 | 0.3592 | 0.8433 | 0.8434 | | 0.3078 | 133.33 | 5200 | 0.3610 | 0.8449 | 0.8450 | | 0.3047 | 138.46 | 5400 | 0.3588 | 0.8401 | 0.8401 | | 0.2994 | 143.59 | 5600 | 0.3714 | 0.8417 | 0.8418 | | 0.3022 | 148.72 | 5800 | 0.3612 | 0.8401 | 0.8401 | | 0.2987 | 153.85 | 6000 | 0.3610 | 0.8417 | 0.8418 | | 0.2974 | 158.97 | 6200 | 0.3615 | 0.8450 | 0.8450 | | 0.2886 | 164.1 | 6400 | 0.3628 | 0.8401 | 0.8401 | | 0.2889 | 169.23 | 6600 | 0.3660 | 0.8466 | 0.8467 | | 0.2857 | 174.36 | 6800 | 0.3690 | 0.8385 | 0.8385 | | 0.2831 | 179.49 | 7000 | 0.3646 | 0.8368 | 0.8369 | | 0.2834 | 184.62 | 7200 | 0.3754 | 0.8351 | 0.8352 | | 0.284 | 189.74 | 7400 | 0.3658 | 0.8368 | 0.8369 | | 0.2808 | 194.87 | 7600 | 0.3645 | 0.8417 | 0.8418 | | 0.2754 | 200.0 | 7800 | 0.3691 | 0.8385 | 0.8385 | | 0.2791 | 205.13 | 8000 | 0.3706 | 0.8352 | 0.8352 | | 0.2722 | 210.26 | 8200 | 0.3687 | 0.8385 | 0.8385 | | 0.2798 | 215.38 | 8400 | 0.3682 | 0.8369 | 0.8369 | | 0.2711 | 220.51 | 8600 | 0.3713 | 0.8352 | 0.8352 | | 0.2763 | 225.64 | 8800 | 0.3715 | 0.8320 | 0.8320 | | 0.2728 | 230.77 | 9000 | 0.3705 | 0.8352 | 0.8352 | | 0.2712 | 235.9 | 9200 | 0.3733 | 0.8352 | 0.8352 | | 0.2758 | 241.03 | 9400 | 0.3685 | 0.8369 | 0.8369 | | 0.2707 | 246.15 | 9600 | 0.3707 | 0.8385 | 0.8385 | | 0.2787 | 251.28 | 9800 | 0.3701 | 0.8369 | 0.8369 | | 0.2751 | 256.41 | 10000 | 0.3692 | 0.8385 | 0.8385 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_8192_512_30M", "model-index": [{"name": "GUE_prom_prom_core_tata-seqsight_8192_512_30M-L1_f", "results": []}]}

mahdibaghbanzadeh/GUE_prom_prom_core_tata-seqsight_8192_512_30M-L1_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_8192_512_30M", "region:us" ]

null

2024-04-27T02:12:51+00:00

[]

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us

GUE\_prom\_prom\_core\_tata-seqsight\_8192\_512\_30M-L1\_f ========================================================== This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_8192\_512\_30M on the mahdibaghbanzadeh/GUE\_prom\_prom\_core\_tata dataset. It achieves the following results on the evaluation set: * Loss: 0.4139 * F1 Score: 0.8204 * Accuracy: 0.8206 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

null

peft

# GUE_prom_prom_core_tata-seqsight_8192_512_30M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_8192_512_30M](https://huggingface.co/mahdibaghbanzadeh/seqsight_8192_512_30M) on the [mahdibaghbanzadeh/GUE_prom_prom_core_tata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_core_tata) dataset. It achieves the following results on the evaluation set: - Loss: 0.5952 - F1 Score: 0.8385 - Accuracy: 0.8385 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:------:|:-----:|:---------------:|:--------:|:--------:| | 0.5745 | 5.13 | 200 | 0.5589 | 0.7076 | 0.7096 | | 0.5057 | 10.26 | 400 | 0.5507 | 0.7268 | 0.7325 | | 0.4671 | 15.38 | 600 | 0.5074 | 0.7501 | 0.7537 | | 0.4179 | 20.51 | 800 | 0.4490 | 0.7924 | 0.7928 | | 0.3745 | 25.64 | 1000 | 0.4288 | 0.8152 | 0.8157 | | 0.3408 | 30.77 | 1200 | 0.4045 | 0.8205 | 0.8206 | | 0.3141 | 35.9 | 1400 | 0.3903 | 0.8189 | 0.8189 | | 0.2929 | 41.03 | 1600 | 0.3908 | 0.8271 | 0.8271 | | 0.2779 | 46.15 | 1800 | 0.3883 | 0.8287 | 0.8287 | | 0.257 | 51.28 | 2000 | 0.3939 | 0.8368 | 0.8369 | | 0.2411 | 56.41 | 2200 | 0.3823 | 0.8368 | 0.8369 | | 0.2262 | 61.54 | 2400 | 0.4157 | 0.8351 | 0.8352 | | 0.2149 | 66.67 | 2600 | 0.3981 | 0.8432 | 0.8434 | | 0.2062 | 71.79 | 2800 | 0.4350 | 0.8398 | 0.8401 | | 0.1949 | 76.92 | 3000 | 0.4541 | 0.8303 | 0.8303 | | 0.1832 | 82.05 | 3200 | 0.4548 | 0.8303 | 0.8303 | | 0.1807 | 87.18 | 3400 | 0.4484 | 0.8287 | 0.8287 | | 0.1739 | 92.31 | 3600 | 0.4368 | 0.8336 | 0.8336 | | 0.1616 | 97.44 | 3800 | 0.4746 | 0.8385 | 0.8385 | | 0.153 | 102.56 | 4000 | 0.4779 | 0.8369 | 0.8369 | | 0.1485 | 107.69 | 4200 | 0.4921 | 0.8385 | 0.8385 | | 0.1405 | 112.82 | 4400 | 0.5096 | 0.8450 | 0.8450 | | 0.1405 | 117.95 | 4600 | 0.4949 | 0.8482 | 0.8483 | | 0.1328 | 123.08 | 4800 | 0.5242 | 0.8434 | 0.8434 | | 0.1292 | 128.21 | 5000 | 0.5093 | 0.8254 | 0.8254 | | 0.1229 | 133.33 | 5200 | 0.5286 | 0.8563 | 0.8564 | | 0.1205 | 138.46 | 5400 | 0.5364 | 0.8449 | 0.8450 | | 0.1141 | 143.59 | 5600 | 0.5838 | 0.8303 | 0.8303 | | 0.1142 | 148.72 | 5800 | 0.5555 | 0.8336 | 0.8336 | | 0.1102 | 153.85 | 6000 | 0.5760 | 0.8416 | 0.8418 | | 0.1064 | 158.97 | 6200 | 0.5708 | 0.8320 | 0.8320 | | 0.1065 | 164.1 | 6400 | 0.5825 | 0.8418 | 0.8418 | | 0.1018 | 169.23 | 6600 | 0.5989 | 0.8336 | 0.8336 | | 0.0973 | 174.36 | 6800 | 0.6020 | 0.8336 | 0.8336 | | 0.0965 | 179.49 | 7000 | 0.5881 | 0.8401 | 0.8401 | | 0.0931 | 184.62 | 7200 | 0.6173 | 0.8302 | 0.8303 | | 0.0908 | 189.74 | 7400 | 0.5950 | 0.8401 | 0.8401 | | 0.0929 | 194.87 | 7600 | 0.6094 | 0.8465 | 0.8467 | | 0.0885 | 200.0 | 7800 | 0.5925 | 0.8418 | 0.8418 | | 0.0883 | 205.13 | 8000 | 0.6153 | 0.8418 | 0.8418 | | 0.0819 | 210.26 | 8200 | 0.6215 | 0.8499 | 0.8499 | | 0.082 | 215.38 | 8400 | 0.6393 | 0.8499 | 0.8499 | | 0.0794 | 220.51 | 8600 | 0.6357 | 0.8368 | 0.8369 | | 0.0816 | 225.64 | 8800 | 0.6123 | 0.8483 | 0.8483 | | 0.0864 | 230.77 | 9000 | 0.6061 | 0.8417 | 0.8418 | | 0.083 | 235.9 | 9200 | 0.6174 | 0.8418 | 0.8418 | | 0.0822 | 241.03 | 9400 | 0.6227 | 0.8466 | 0.8467 | | 0.0786 | 246.15 | 9600 | 0.6303 | 0.8434 | 0.8434 | | 0.084 | 251.28 | 9800 | 0.6274 | 0.8450 | 0.8450 | | 0.0781 | 256.41 | 10000 | 0.6283 | 0.8450 | 0.8450 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_8192_512_30M", "model-index": [{"name": "GUE_prom_prom_core_tata-seqsight_8192_512_30M-L8_f", "results": []}]}

mahdibaghbanzadeh/GUE_prom_prom_core_tata-seqsight_8192_512_30M-L8_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_8192_512_30M", "region:us" ]

null

2024-04-27T02:13:31+00:00

[]

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us

GUE\_prom\_prom\_core\_tata-seqsight\_8192\_512\_30M-L8\_f ========================================================== This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_8192\_512\_30M on the mahdibaghbanzadeh/GUE\_prom\_prom\_core\_tata dataset. It achieves the following results on the evaluation set: * Loss: 0.5952 * F1 Score: 0.8385 * Accuracy: 0.8385 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

text-generation

transformers

# Model Card for Model ID  ## Model Details ### Model Description  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "datasets": ["thesven/pihkal-tihkal-orpo-dpo-dataset"]}

thesven/thesven-Tihkal-Pihkal-ORPO-Llama-3-8B-bnb-4bit

null

[ "transformers", "safetensors", "llama", "text-generation", "conversational", "dataset:thesven/pihkal-tihkal-orpo-dpo-dataset", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

null

2024-04-27T02:13:38+00:00

[ "1910.09700" ]

[]

TAGS #transformers #safetensors #llama #text-generation #conversational #dataset-thesven/pihkal-tihkal-orpo-dpo-dataset #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #conversational #dataset-thesven/pihkal-tihkal-orpo-dpo-dataset #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

text-generation

transformers

# lmd-4bars-2048-epochs10 This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.005 - train_batch_size: 32 - eval_batch_size: 16 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 64 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 1 ### Training results ### Framework versions - Transformers 4.36.0 - Pytorch 2.1.0 - Datasets 2.15.0 - Tokenizers 0.15.1

{"license": "mit", "tags": ["generated_from_trainer"], "base_model": "gpt2", "model-index": [{"name": "lmd-4bars-2048-epochs10", "results": []}]}

MikeMpapa/lmd-4bars-2048-epochs10

null

[ "transformers", "tensorboard", "safetensors", "gpt2", "text-generation", "generated_from_trainer", "base_model:gpt2", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

null

2024-04-27T02:16:15+00:00

[]

TAGS #transformers #tensorboard #safetensors #gpt2 #text-generation #generated_from_trainer #base_model-gpt2 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

# lmd-4bars-2048-epochs10 This model is a fine-tuned version of gpt2 on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.005 - train_batch_size: 32 - eval_batch_size: 16 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 64 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 1 ### Training results ### Framework versions - Transformers 4.36.0 - Pytorch 2.1.0 - Datasets 2.15.0 - Tokenizers 0.15.1

[ "# lmd-4bars-2048-epochs10\n\nThis model is a fine-tuned version of gpt2 on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.005\n- train_batch_size: 32\n- eval_batch_size: 16\n- seed: 42\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.36.0\n- Pytorch 2.1.0\n- Datasets 2.15.0\n- Tokenizers 0.15.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #gpt2 #text-generation #generated_from_trainer #base_model-gpt2 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# lmd-4bars-2048-epochs10\n\nThis model is a fine-tuned version of gpt2 on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.005\n- train_batch_size: 32\n- eval_batch_size: 16\n- seed: 42\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.36.0\n- Pytorch 2.1.0\n- Datasets 2.15.0\n- Tokenizers 0.15.1" ]

text-to-image

null

gguf quantized version of https://huggingface.co/stabilityai/sdxl-turbo

{"license": "other", "license_name": "sai-nc-community", "license_link": "https://huggingface.co/stabilityai/sdxl-turbo/blob/main/LICENSE.TXT", "pipeline_tag": "text-to-image"}

OlegSkutte/sdxl-turbo-GGUF

null

[ "gguf", "text-to-image", "license:other", "region:us" ]

null

2024-04-27T02:18:36+00:00

[]

TAGS #gguf #text-to-image #license-other #region-us

gguf quantized version of URL

[]

[ "TAGS\n#gguf #text-to-image #license-other #region-us \n" ]

null

peft

# GUE_prom_prom_core_tata-seqsight_8192_512_30M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_8192_512_30M](https://huggingface.co/mahdibaghbanzadeh/seqsight_8192_512_30M) on the [mahdibaghbanzadeh/GUE_prom_prom_core_tata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_core_tata) dataset. It achieves the following results on the evaluation set: - Loss: 0.7455 - F1 Score: 0.8269 - Accuracy: 0.8271 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:------:|:-----:|:---------------:|:--------:|:--------:| | 0.5591 | 5.13 | 200 | 0.5316 | 0.7337 | 0.7341 | | 0.4678 | 10.26 | 400 | 0.4843 | 0.7821 | 0.7830 | | 0.3819 | 15.38 | 600 | 0.4105 | 0.8188 | 0.8189 | | 0.3145 | 20.51 | 800 | 0.4078 | 0.8173 | 0.8173 | | 0.2727 | 25.64 | 1000 | 0.4044 | 0.8352 | 0.8352 | | 0.2292 | 30.77 | 1200 | 0.4325 | 0.8384 | 0.8385 | | 0.1985 | 35.9 | 1400 | 0.4151 | 0.8401 | 0.8401 | | 0.1666 | 41.03 | 1600 | 0.4526 | 0.8399 | 0.8401 | | 0.1497 | 46.15 | 1800 | 0.5059 | 0.8400 | 0.8401 | | 0.1277 | 51.28 | 2000 | 0.5027 | 0.8483 | 0.8483 | | 0.1108 | 56.41 | 2200 | 0.5648 | 0.8596 | 0.8597 | | 0.0988 | 61.54 | 2400 | 0.5330 | 0.8483 | 0.8483 | | 0.091 | 66.67 | 2600 | 0.5492 | 0.8449 | 0.8450 | | 0.0815 | 71.79 | 2800 | 0.5692 | 0.8645 | 0.8646 | | 0.0714 | 76.92 | 3000 | 0.5980 | 0.8532 | 0.8532 | | 0.065 | 82.05 | 3200 | 0.6359 | 0.8464 | 0.8467 | | 0.0599 | 87.18 | 3400 | 0.6645 | 0.8497 | 0.8499 | | 0.0563 | 92.31 | 3600 | 0.6828 | 0.8515 | 0.8515 | | 0.055 | 97.44 | 3800 | 0.6676 | 0.8450 | 0.8450 | | 0.0465 | 102.56 | 4000 | 0.7496 | 0.8412 | 0.8418 | | 0.047 | 107.69 | 4200 | 0.7358 | 0.8432 | 0.8434 | | 0.0448 | 112.82 | 4400 | 0.7372 | 0.8329 | 0.8336 | | 0.0436 | 117.95 | 4600 | 0.6990 | 0.8400 | 0.8401 | | 0.039 | 123.08 | 4800 | 0.7425 | 0.8433 | 0.8434 | | 0.0395 | 128.21 | 5000 | 0.7357 | 0.8315 | 0.8320 | | 0.0369 | 133.33 | 5200 | 0.7054 | 0.8483 | 0.8483 | | 0.0352 | 138.46 | 5400 | 0.7598 | 0.8382 | 0.8385 | | 0.0318 | 143.59 | 5600 | 0.7746 | 0.8465 | 0.8467 | | 0.0315 | 148.72 | 5800 | 0.7480 | 0.8400 | 0.8401 | | 0.0309 | 153.85 | 6000 | 0.7548 | 0.8563 | 0.8564 | | 0.0312 | 158.97 | 6200 | 0.7342 | 0.8548 | 0.8548 | | 0.0269 | 164.1 | 6400 | 0.7992 | 0.8433 | 0.8434 | | 0.03 | 169.23 | 6600 | 0.7064 | 0.8417 | 0.8418 | | 0.0268 | 174.36 | 6800 | 0.7526 | 0.8498 | 0.8499 | | 0.026 | 179.49 | 7000 | 0.7874 | 0.8499 | 0.8499 | | 0.0263 | 184.62 | 7200 | 0.8341 | 0.8378 | 0.8385 | | 0.0224 | 189.74 | 7400 | 0.8513 | 0.8512 | 0.8515 | | 0.0237 | 194.87 | 7600 | 0.7960 | 0.8579 | 0.8581 | | 0.0226 | 200.0 | 7800 | 0.8098 | 0.8515 | 0.8515 | | 0.021 | 205.13 | 8000 | 0.8648 | 0.8480 | 0.8483 | | 0.0212 | 210.26 | 8200 | 0.8669 | 0.8381 | 0.8385 | | 0.0193 | 215.38 | 8400 | 0.8712 | 0.8380 | 0.8385 | | 0.0186 | 220.51 | 8600 | 0.8453 | 0.8448 | 0.8450 | | 0.0194 | 225.64 | 8800 | 0.8293 | 0.8432 | 0.8434 | | 0.0196 | 230.77 | 9000 | 0.8284 | 0.8415 | 0.8418 | | 0.0197 | 235.9 | 9200 | 0.8125 | 0.8597 | 0.8597 | | 0.0186 | 241.03 | 9400 | 0.8294 | 0.8547 | 0.8548 | | 0.0199 | 246.15 | 9600 | 0.8236 | 0.8514 | 0.8515 | | 0.0191 | 251.28 | 9800 | 0.8482 | 0.8398 | 0.8401 | | 0.0164 | 256.41 | 10000 | 0.8305 | 0.8514 | 0.8515 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_8192_512_30M", "model-index": [{"name": "GUE_prom_prom_core_tata-seqsight_8192_512_30M-L32_f", "results": []}]}

mahdibaghbanzadeh/GUE_prom_prom_core_tata-seqsight_8192_512_30M-L32_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_8192_512_30M", "region:us" ]

null

2024-04-27T02:18:53+00:00

[]

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us

GUE\_prom\_prom\_core\_tata-seqsight\_8192\_512\_30M-L32\_f =========================================================== This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_8192\_512\_30M on the mahdibaghbanzadeh/GUE\_prom\_prom\_core\_tata dataset. It achieves the following results on the evaluation set: * Loss: 0.7455 * F1 Score: 0.8269 * Accuracy: 0.8271 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

null

peft

# GUE_prom_prom_300_all-seqsight_8192_512_30M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_8192_512_30M](https://huggingface.co/mahdibaghbanzadeh/seqsight_8192_512_30M) on the [mahdibaghbanzadeh/GUE_prom_prom_300_all](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_300_all) dataset. It achieves the following results on the evaluation set: - Loss: 0.2147 - F1 Score: 0.9138 - Accuracy: 0.9139 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.4209 | 0.54 | 200 | 0.2826 | 0.8948 | 0.8949 | | 0.2891 | 1.08 | 400 | 0.2521 | 0.9057 | 0.9057 | | 0.2726 | 1.62 | 600 | 0.2326 | 0.9108 | 0.9108 | | 0.2489 | 2.16 | 800 | 0.2317 | 0.9107 | 0.9108 | | 0.2486 | 2.7 | 1000 | 0.2195 | 0.9150 | 0.9150 | | 0.2368 | 3.24 | 1200 | 0.2289 | 0.9108 | 0.9110 | | 0.2414 | 3.78 | 1400 | 0.2178 | 0.9141 | 0.9142 | | 0.2329 | 4.32 | 1600 | 0.2107 | 0.9184 | 0.9184 | | 0.2256 | 4.86 | 1800 | 0.2147 | 0.9177 | 0.9177 | | 0.2248 | 5.41 | 2000 | 0.2083 | 0.9184 | 0.9184 | | 0.2247 | 5.95 | 2200 | 0.2053 | 0.9202 | 0.9203 | | 0.22 | 6.49 | 2400 | 0.2026 | 0.9196 | 0.9196 | | 0.2232 | 7.03 | 2600 | 0.2044 | 0.9186 | 0.9186 | | 0.2157 | 7.57 | 2800 | 0.1997 | 0.9208 | 0.9208 | | 0.2165 | 8.11 | 3000 | 0.2005 | 0.9204 | 0.9204 | | 0.2162 | 8.65 | 3200 | 0.1976 | 0.9220 | 0.9220 | | 0.2082 | 9.19 | 3400 | 0.1986 | 0.9208 | 0.9208 | | 0.2079 | 9.73 | 3600 | 0.1956 | 0.9201 | 0.9201 | | 0.218 | 10.27 | 3800 | 0.1952 | 0.9225 | 0.9225 | | 0.2089 | 10.81 | 4000 | 0.1957 | 0.9218 | 0.9218 | | 0.2111 | 11.35 | 4200 | 0.1959 | 0.9228 | 0.9228 | | 0.2048 | 11.89 | 4400 | 0.1960 | 0.9221 | 0.9221 | | 0.2042 | 12.43 | 4600 | 0.1960 | 0.9219 | 0.9220 | | 0.2072 | 12.97 | 4800 | 0.1928 | 0.9233 | 0.9233 | | 0.2049 | 13.51 | 5000 | 0.1928 | 0.9255 | 0.9255 | | 0.2069 | 14.05 | 5200 | 0.1915 | 0.9243 | 0.9243 | | 0.2033 | 14.59 | 5400 | 0.1937 | 0.9231 | 0.9231 | | 0.2008 | 15.14 | 5600 | 0.1908 | 0.9257 | 0.9257 | | 0.1998 | 15.68 | 5800 | 0.1903 | 0.9236 | 0.9236 | | 0.2012 | 16.22 | 6000 | 0.1936 | 0.9241 | 0.9242 | | 0.1995 | 16.76 | 6200 | 0.1915 | 0.9240 | 0.9240 | | 0.1995 | 17.3 | 6400 | 0.1917 | 0.9231 | 0.9231 | | 0.2031 | 17.84 | 6600 | 0.1927 | 0.9223 | 0.9223 | | 0.1963 | 18.38 | 6800 | 0.1902 | 0.9231 | 0.9231 | | 0.2017 | 18.92 | 7000 | 0.1890 | 0.9243 | 0.9243 | | 0.1999 | 19.46 | 7200 | 0.1919 | 0.9220 | 0.9220 | | 0.1967 | 20.0 | 7400 | 0.1894 | 0.9257 | 0.9257 | | 0.1982 | 20.54 | 7600 | 0.1904 | 0.9231 | 0.9231 | | 0.196 | 21.08 | 7800 | 0.1885 | 0.9247 | 0.9247 | | 0.1983 | 21.62 | 8000 | 0.1895 | 0.9240 | 0.9240 | | 0.1957 | 22.16 | 8200 | 0.1890 | 0.9223 | 0.9223 | | 0.1901 | 22.7 | 8400 | 0.1899 | 0.9233 | 0.9233 | | 0.1985 | 23.24 | 8600 | 0.1881 | 0.9242 | 0.9242 | | 0.196 | 23.78 | 8800 | 0.1883 | 0.9250 | 0.925 | | 0.1977 | 24.32 | 9000 | 0.1893 | 0.9223 | 0.9223 | | 0.1935 | 24.86 | 9200 | 0.1891 | 0.9240 | 0.9240 | | 0.1956 | 25.41 | 9400 | 0.1891 | 0.9228 | 0.9228 | | 0.1958 | 25.95 | 9600 | 0.1889 | 0.9231 | 0.9231 | | 0.1953 | 26.49 | 9800 | 0.1884 | 0.9235 | 0.9235 | | 0.1921 | 27.03 | 10000 | 0.1885 | 0.9236 | 0.9236 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_8192_512_30M", "model-index": [{"name": "GUE_prom_prom_300_all-seqsight_8192_512_30M-L1_f", "results": []}]}

mahdibaghbanzadeh/GUE_prom_prom_300_all-seqsight_8192_512_30M-L1_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_8192_512_30M", "region:us" ]

null

2024-04-27T02:19:30+00:00

[]

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us

GUE\_prom\_prom\_300\_all-seqsight\_8192\_512\_30M-L1\_f ======================================================== This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_8192\_512\_30M on the mahdibaghbanzadeh/GUE\_prom\_prom\_300\_all dataset. It achieves the following results on the evaluation set: * Loss: 0.2147 * F1 Score: 0.9138 * Accuracy: 0.9139 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

null

peft

# GUE_prom_prom_300_all-seqsight_8192_512_30M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_8192_512_30M](https://huggingface.co/mahdibaghbanzadeh/seqsight_8192_512_30M) on the [mahdibaghbanzadeh/GUE_prom_prom_300_all](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_300_all) dataset. It achieves the following results on the evaluation set: - Loss: 0.1981 - F1 Score: 0.9179 - Accuracy: 0.9179 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.3652 | 0.54 | 200 | 0.2431 | 0.9059 | 0.9061 | | 0.2518 | 1.08 | 400 | 0.2259 | 0.9150 | 0.9150 | | 0.2395 | 1.62 | 600 | 0.2077 | 0.9147 | 0.9147 | | 0.2208 | 2.16 | 800 | 0.2165 | 0.9150 | 0.9152 | | 0.2197 | 2.7 | 1000 | 0.2012 | 0.9199 | 0.9199 | | 0.213 | 3.24 | 1200 | 0.2059 | 0.9170 | 0.9171 | | 0.2124 | 3.78 | 1400 | 0.1955 | 0.9209 | 0.9209 | | 0.2061 | 4.32 | 1600 | 0.1899 | 0.9245 | 0.9245 | | 0.2024 | 4.86 | 1800 | 0.1930 | 0.9215 | 0.9215 | | 0.1987 | 5.41 | 2000 | 0.1909 | 0.9250 | 0.925 | | 0.199 | 5.95 | 2200 | 0.1846 | 0.9267 | 0.9267 | | 0.195 | 6.49 | 2400 | 0.1826 | 0.9262 | 0.9262 | | 0.1985 | 7.03 | 2600 | 0.1850 | 0.9263 | 0.9264 | | 0.1897 | 7.57 | 2800 | 0.1824 | 0.9262 | 0.9262 | | 0.1911 | 8.11 | 3000 | 0.1824 | 0.9258 | 0.9258 | | 0.188 | 8.65 | 3200 | 0.1828 | 0.9270 | 0.9270 | | 0.1835 | 9.19 | 3400 | 0.1826 | 0.9265 | 0.9265 | | 0.1808 | 9.73 | 3600 | 0.1804 | 0.9243 | 0.9243 | | 0.1887 | 10.27 | 3800 | 0.1804 | 0.9277 | 0.9277 | | 0.1817 | 10.81 | 4000 | 0.1787 | 0.9274 | 0.9274 | | 0.1826 | 11.35 | 4200 | 0.1786 | 0.9270 | 0.9270 | | 0.1772 | 11.89 | 4400 | 0.1835 | 0.9275 | 0.9275 | | 0.1766 | 12.43 | 4600 | 0.1770 | 0.9279 | 0.9279 | | 0.179 | 12.97 | 4800 | 0.1770 | 0.9260 | 0.9260 | | 0.1773 | 13.51 | 5000 | 0.1775 | 0.9280 | 0.9280 | | 0.1775 | 14.05 | 5200 | 0.1781 | 0.9291 | 0.9291 | | 0.1723 | 14.59 | 5400 | 0.1771 | 0.9282 | 0.9282 | | 0.1708 | 15.14 | 5600 | 0.1747 | 0.9270 | 0.9270 | | 0.1704 | 15.68 | 5800 | 0.1761 | 0.9267 | 0.9267 | | 0.1719 | 16.22 | 6000 | 0.1781 | 0.9269 | 0.9269 | | 0.1687 | 16.76 | 6200 | 0.1781 | 0.9270 | 0.9270 | | 0.1692 | 17.3 | 6400 | 0.1740 | 0.9277 | 0.9277 | | 0.1729 | 17.84 | 6600 | 0.1761 | 0.9270 | 0.9270 | | 0.1656 | 18.38 | 6800 | 0.1762 | 0.9272 | 0.9272 | | 0.1682 | 18.92 | 7000 | 0.1732 | 0.9275 | 0.9275 | | 0.1681 | 19.46 | 7200 | 0.1752 | 0.9284 | 0.9284 | | 0.165 | 20.0 | 7400 | 0.1753 | 0.9275 | 0.9275 | | 0.1674 | 20.54 | 7600 | 0.1771 | 0.9284 | 0.9284 | | 0.1623 | 21.08 | 7800 | 0.1734 | 0.9277 | 0.9277 | | 0.165 | 21.62 | 8000 | 0.1741 | 0.9282 | 0.9282 | | 0.1638 | 22.16 | 8200 | 0.1746 | 0.9282 | 0.9282 | | 0.1576 | 22.7 | 8400 | 0.1730 | 0.9269 | 0.9269 | | 0.1639 | 23.24 | 8600 | 0.1723 | 0.9277 | 0.9277 | | 0.1611 | 23.78 | 8800 | 0.1723 | 0.9279 | 0.9279 | | 0.1634 | 24.32 | 9000 | 0.1739 | 0.9275 | 0.9275 | | 0.1611 | 24.86 | 9200 | 0.1736 | 0.9280 | 0.9280 | | 0.1605 | 25.41 | 9400 | 0.1737 | 0.9277 | 0.9277 | | 0.1606 | 25.95 | 9600 | 0.1736 | 0.9279 | 0.9279 | | 0.1608 | 26.49 | 9800 | 0.1731 | 0.9277 | 0.9277 | | 0.1561 | 27.03 | 10000 | 0.1733 | 0.9282 | 0.9282 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_8192_512_30M", "model-index": [{"name": "GUE_prom_prom_300_all-seqsight_8192_512_30M-L8_f", "results": []}]}

mahdibaghbanzadeh/GUE_prom_prom_300_all-seqsight_8192_512_30M-L8_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_8192_512_30M", "region:us" ]

null

2024-04-27T02:21:00+00:00

[]

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us

GUE\_prom\_prom\_300\_all-seqsight\_8192\_512\_30M-L8\_f ======================================================== This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_8192\_512\_30M on the mahdibaghbanzadeh/GUE\_prom\_prom\_300\_all dataset. It achieves the following results on the evaluation set: * Loss: 0.1981 * F1 Score: 0.9179 * Accuracy: 0.9179 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

null

peft

# GUE_prom_prom_300_all-seqsight_8192_512_30M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_8192_512_30M](https://huggingface.co/mahdibaghbanzadeh/seqsight_8192_512_30M) on the [mahdibaghbanzadeh/GUE_prom_prom_300_all](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_300_all) dataset. It achieves the following results on the evaluation set: - Loss: 0.1998 - F1 Score: 0.9263 - Accuracy: 0.9264 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.335 | 0.54 | 200 | 0.2328 | 0.9088 | 0.9090 | | 0.2383 | 1.08 | 400 | 0.2138 | 0.9173 | 0.9174 | | 0.2261 | 1.62 | 600 | 0.2054 | 0.9181 | 0.9181 | | 0.2106 | 2.16 | 800 | 0.2112 | 0.9137 | 0.9139 | | 0.207 | 2.7 | 1000 | 0.1931 | 0.9231 | 0.9231 | | 0.2012 | 3.24 | 1200 | 0.1990 | 0.9176 | 0.9177 | | 0.199 | 3.78 | 1400 | 0.1928 | 0.9217 | 0.9218 | | 0.1932 | 4.32 | 1600 | 0.1845 | 0.9275 | 0.9275 | | 0.1893 | 4.86 | 1800 | 0.1827 | 0.9252 | 0.9252 | | 0.1829 | 5.41 | 2000 | 0.1863 | 0.9285 | 0.9285 | | 0.1845 | 5.95 | 2200 | 0.1758 | 0.9284 | 0.9284 | | 0.1774 | 6.49 | 2400 | 0.1849 | 0.9241 | 0.9242 | | 0.1817 | 7.03 | 2600 | 0.1774 | 0.9297 | 0.9297 | | 0.1722 | 7.57 | 2800 | 0.1769 | 0.9292 | 0.9292 | | 0.1714 | 8.11 | 3000 | 0.1770 | 0.9297 | 0.9297 | | 0.1668 | 8.65 | 3200 | 0.1790 | 0.9302 | 0.9302 | | 0.164 | 9.19 | 3400 | 0.1735 | 0.9314 | 0.9314 | | 0.1586 | 9.73 | 3600 | 0.1751 | 0.9267 | 0.9267 | | 0.1659 | 10.27 | 3800 | 0.1731 | 0.9299 | 0.9299 | | 0.1589 | 10.81 | 4000 | 0.1719 | 0.9312 | 0.9313 | | 0.1573 | 11.35 | 4200 | 0.1701 | 0.9340 | 0.9340 | | 0.154 | 11.89 | 4400 | 0.1762 | 0.9328 | 0.9328 | | 0.1515 | 12.43 | 4600 | 0.1761 | 0.9299 | 0.9299 | | 0.1524 | 12.97 | 4800 | 0.1723 | 0.9277 | 0.9277 | | 0.1486 | 13.51 | 5000 | 0.1774 | 0.9300 | 0.9301 | | 0.1499 | 14.05 | 5200 | 0.1705 | 0.9323 | 0.9323 | | 0.1437 | 14.59 | 5400 | 0.1677 | 0.9323 | 0.9323 | | 0.1413 | 15.14 | 5600 | 0.1669 | 0.9355 | 0.9355 | | 0.1379 | 15.68 | 5800 | 0.1682 | 0.9326 | 0.9326 | | 0.1387 | 16.22 | 6000 | 0.1686 | 0.9351 | 0.9351 | | 0.1355 | 16.76 | 6200 | 0.1750 | 0.9312 | 0.9313 | | 0.1374 | 17.3 | 6400 | 0.1695 | 0.9338 | 0.9338 | | 0.1385 | 17.84 | 6600 | 0.1684 | 0.9329 | 0.9329 | | 0.1298 | 18.38 | 6800 | 0.1703 | 0.9319 | 0.9319 | | 0.1315 | 18.92 | 7000 | 0.1683 | 0.9328 | 0.9328 | | 0.1321 | 19.46 | 7200 | 0.1685 | 0.9336 | 0.9336 | | 0.1281 | 20.0 | 7400 | 0.1742 | 0.9317 | 0.9318 | | 0.1271 | 20.54 | 7600 | 0.1778 | 0.9312 | 0.9313 | | 0.1267 | 21.08 | 7800 | 0.1670 | 0.9321 | 0.9321 | | 0.1246 | 21.62 | 8000 | 0.1707 | 0.9316 | 0.9316 | | 0.1247 | 22.16 | 8200 | 0.1693 | 0.9319 | 0.9319 | | 0.1212 | 22.7 | 8400 | 0.1682 | 0.9309 | 0.9309 | | 0.1214 | 23.24 | 8600 | 0.1704 | 0.9324 | 0.9324 | | 0.1209 | 23.78 | 8800 | 0.1698 | 0.9326 | 0.9326 | | 0.1226 | 24.32 | 9000 | 0.1729 | 0.9319 | 0.9319 | | 0.1208 | 24.86 | 9200 | 0.1707 | 0.9307 | 0.9307 | | 0.1181 | 25.41 | 9400 | 0.1729 | 0.9319 | 0.9319 | | 0.1206 | 25.95 | 9600 | 0.1718 | 0.9336 | 0.9336 | | 0.1184 | 26.49 | 9800 | 0.1713 | 0.9329 | 0.9329 | | 0.1156 | 27.03 | 10000 | 0.1710 | 0.9323 | 0.9323 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_8192_512_30M", "model-index": [{"name": "GUE_prom_prom_300_all-seqsight_8192_512_30M-L32_f", "results": []}]}

mahdibaghbanzadeh/GUE_prom_prom_300_all-seqsight_8192_512_30M-L32_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_8192_512_30M", "region:us" ]

null

2024-04-27T02:21:36+00:00

[]

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us

GUE\_prom\_prom\_300\_all-seqsight\_8192\_512\_30M-L32\_f ========================================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_8192\_512\_30M on the mahdibaghbanzadeh/GUE\_prom\_prom\_300\_all dataset. It achieves the following results on the evaluation set: * Loss: 0.1998 * F1 Score: 0.9263 * Accuracy: 0.9264 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

text-generation

transformers

<div align="center"> <img width="260px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/BrQCb95lmEIFz79QAmoNA.png"></div> ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/fJIOPJnY6Ff6fUiSIuMEt.png) <div align="center"> <h1>Advancing Open-source Large Language Models in Medical Domain</h1> </div> <p align="center" style="margin-top: 0px;"> <a href="https://colab.research.google.com/drive/1F5oV20InEYeAJGmBwYF9NM_QhLmjBkKJ?usp=sharing"> <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="OpenChat Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 10px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style=" margin-right: 5px;">Online Demo</span> </a> | <a href="https://github.com/openlifescience-ai"> <img src="https://github.githubassets.com/assets/GitHub-Mark-ea2971cee799.png" alt="GitHub Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style=" margin-right: 5px;">GitHub</span> </a> | <a href="#"> <img src="https://github.com/alpayariyak/openchat/blob/master/assets/arxiv-logomark-small-square-border.png?raw=true" alt="ArXiv Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style="margin-right: 5px;">Paper</span> </a> | <a href="https://discord.gg/A5Fjf5zC69"> <img src="https://cloud.githubusercontent.com/assets/6291467/26705903/96c2d66e-477c-11e7-9f4e-f3c0efe96c9a.png" alt="Discord Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text">Discord</span> </a> </p> ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/KGmRE5w2sepNtwsEu8t7K.jpeg) Introducing OpenBioLLM-70B: A State-of-the-Art Open Source Biomedical Large Language Model OpenBioLLM-70B is an advanced open source language model designed specifically for the biomedical domain. Developed by Saama AI Labs, this model leverages cutting-edge techniques to achieve state-of-the-art performance on a wide range of biomedical tasks. 🏥 **Biomedical Specialization**: OpenBioLLM-70B is tailored for the unique language and knowledge requirements of the medical and life sciences fields. It was fine-tuned on a vast corpus of high-quality biomedical data, enabling it to understand and generate text with domain-specific accuracy and fluency. 🎓 **Superior Performance**: With 70 billion parameters, OpenBioLLM-70B outperforms other open source biomedical language models of similar scale. It has also demonstrated better results compared to larger proprietary & open-source models like GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 on biomedical benchmarks. 🧠 **Advanced Training Techniques**: OpenBioLLM-70B builds upon the powerful foundations of the **Meta-Llama-3-70B-Instruct** and [Meta-Llama-3-70B-Instruct](meta-llama/Meta-Llama-3-70B-Instruct) models. It incorporates the DPO dataset and fine-tuning recipe along with a custom diverse medical instruction dataset. Key components of the training pipeline include: <div align="center"> <img width="1200px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/oPchsJsEpQoGcGXVbh7YS.png"> </div> - **Policy Optimization**: [Direct Preference Optimization: Your Language Model is Secretly a Reward Model (DPO)](https://arxiv.org/abs/2305.18290) - **Fine-tuning dataset**: Custom Medical Instruct dataset (We plan to release a sample training dataset in our upcoming paper; please stay updated) This combination of cutting-edge techniques enables OpenBioLLM-70B to align with key capabilities and preferences for biomedical applications. ⚙️ **Release Details**: - **Model Size**: 70 billion parameters - **Quantization**: Optimized quantized versions available [Here](https://huggingface.co/aaditya/OpenBioLLM-70B-GGUF) - **Language(s) (NLP):** en - **Developed By**: [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) from Saama AI Labs - **License:** Meta-Llama License - **Fine-tuned from models:** [Meta-Llama-3-70B-Instruct](meta-llama/Meta-Llama-3-70B-Instruct) - **Resources for more information:** - Paper: Coming soon The model can be fine-tuned for more specialized tasks and datasets as needed. OpenBioLLM-70B represents an important step forward in democratizing advanced language AI for the biomedical community. By leveraging state-of-the-art architectures and training techniques from leading open source efforts like Llama-3, we have created a powerful tool to accelerate innovation and discovery in healthcare and the life sciences. We are excited to share OpenBioLLM-70B with researchers and developers around the world. ### Use with transformers **Important: Please use the exact chat template provided by Llama-3 instruct version. Otherwise there will be a degradation in the performance. The model output can be verbose in rare cases. Please consider setting temperature = 0 to make this happen less.** See the snippet below for usage with Transformers: ```python import transformers import torch model_id = "aaditya/OpenBioLLM-Llama3-70B" pipeline = transformers.pipeline( "text-generation", model=model_id, model_kwargs={"torch_dtype": torch.bfloat16}, device="auto", ) messages = [ {"role": "system", "content": "You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience. Your name is OpenBioLLM, and you were developed by Saama AI Labs. who's willing to help answer the user's query with explanation. In your explanation, leverage your deep medical expertise such as relevant anatomical structures, physiological processes, diagnostic criteria, treatment guidelines, or other pertinent medical concepts. Use precise medical terminology while still aiming to make the explanation clear and accessible to a general audience."}, {"role": "user", "content": "How can i split a 3mg or 4mg waefin pill so i can get a 2.5mg pill?"}, ] prompt = pipeline.tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) terminators = [ pipeline.tokenizer.eos_token_id, pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>") ] outputs = pipeline( prompt, max_new_tokens=256, eos_token_id=terminators, do_sample=True, temperature=0.0, top_p=0.9, ) print(outputs[0]["generated_text"][len(prompt):]) ``` ## **Training procedure** ### **Training hyperparameters** <details> <summary>Click to see details</summary> - learning_rate: 0.0002 - lr_scheduler: cosine - train_batch_size: 12 - eval_batch_size: 8 - GPU: H100 80GB SXM5 - num_devices: 8 - optimizer: adamw_bnb_8bit - lr_scheduler_warmup_steps: 100 - num_epochs: 4 </details> ### **Peft hyperparameters** <details> <summary>Click to see details</summary> - adapter: qlora - lora_r: 128 - lora_alpha: 256 - lora_dropout: 0.05 - lora_target_linear: true -lora_target_modules: - q_proj - v_proj - k_proj - o_proj - gate_proj - down_proj - up_proj </details> ### **Training results** ### **Framework versions** - Transformers 4.39.3 - Pytorch 2.1.2+cu121 - Datasets 2.18.0 - Tokenizers 0.15.1 - Axolotl - Lm harness for evaluation # Benchmark Results 🔥 OpenBioLLM-70B demonstrates superior performance compared to larger models, such as GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 across 9 diverse biomedical datasets, achieving state-of-the-art results with an average score of 86.06%, despite having a significantly smaller parameter count. The model's strong performance in domain-specific tasks, such as Clinical KG, Medical Genetics, and PubMedQA, highlights its ability to effectively capture and apply biomedical knowledge. 🚨 The GPT-4, Med-PaLM-1, and Med-PaLM-2 results are taken from their official papers. Since Med-PaLM doesn't provide zero-shot accuracy, we are using 5-shot accuracy from their paper for comparison. All results presented are in the zero-shot setting, except for Med-PaLM-2 and Med-PaLM-1, which use 5-shot accuracy. | | Clinical KG | Medical Genetics | Anatomy | Pro Medicine | College Biology | College Medicine | MedQA 4 opts | PubMedQA | MedMCQA | Avg | |--------------------|-------------|------------------|---------|--------------|-----------------|------------------|--------------|----------|---------|-------| | **OpenBioLLM-70B** | **92.93** | **93.197** | **83.904** | 93.75 | 93.827 | **85.749** | 78.162 | 78.97 | **74.014** | **86.05588** | | Med-PaLM-2 (5-shot) | 88.3 | 90 | 77.8 | **95.2** | 94.4 | 80.9 | **79.7** | **79.2** | 71.3 | 84.08 | | **GPT-4** | 86.04 | 91 | 80 | 93.01 | **95.14** | 76.88 | 78.87 | 75.2 | 69.52 | 82.85 | | Med-PaLM-1 (Flan-PaLM, 5-shot) | 80.4 | 75 | 63.7 | 83.8 | 88.9 | 76.3 | 67.6 | 79 | 57.6 | 74.7 | | **OpenBioLLM-8B** | 76.101 | 86.1 | 69.829 | 78.21 | 84.213 | 68.042 | 58.993 | 74.12 | 56.913 | 72.502 | | Gemini-1.0 | 76.7 | 75.8 | 66.7 | 77.7 | 88 | 69.2 | 58 | 70.7 | 54.3 | 70.79 | | GPT-3.5 Turbo 1106 | 74.71 | 74 | 72.79 | 72.79 | 72.91 | 64.73 | 57.71 | 72.66 | 53.79 | 66 | | Meditron-70B | 66.79 | 69 | 53.33 | 71.69 | 76.38 | 63 | 57.1 | 76.6 | 46.85 | 64.52 | | gemma-7b | 69.81 | 70 | 59.26 | 66.18 | 79.86 | 60.12 | 47.21 | 76.2 | 48.96 | 64.18 | | Mistral-7B-v0.1 | 68.68 | 71 | 55.56 | 68.38 | 68.06 | 59.54 | 50.82 | 75.4 | 48.2 | 62.85 | | Apollo-7B | 62.26 | 72 | 61.48 | 69.12 | 70.83 | 55.49 | 55.22 | 39.8 | 53.77 | 60 | | MedAlpaca-7b | 57.36 | 69 | 57.04 | 67.28 | 65.28 | 54.34 | 41.71 | 72.8 | 37.51 | 58.03 | | BioMistral-7B | 59.9 | 64 | 56.5 | 60.4 | 59 | 54.7 | 50.6 | 77.5 | 48.1 | 57.3 | | AlpaCare-llama2-7b | 49.81 | 49 | 45.92 | 33.82 | 50 | 43.35 | 29.77 | 72.2 | 34.42 | 45.36 | | ClinicalGPT | 30.56 | 27 | 30.37 | 19.48 | 25 | 24.27 | 26.08 | 63.8 | 28.18 | 30.52 | <div align="center"> <img width="1600px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/_SzdcJSBjZyo8RS1bTEkP.png"> </div> ## Detailed Medical Subjectwise accuracy ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/UXF-V0col0Z0sS6BGPBkE.png) # Use Cases & Examples 🚨 **Below results are from the quantized version of OpenBioLLM-70B # Summarize Clinical Notes OpenBioLLM-70B can efficiently analyze and summarize complex clinical notes, EHR data, and discharge summaries, extracting key information and generating concise, structured summaries ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/xdwdBgOxNi_TfML0hKlI8.png) # Answer Medical Questions OpenBioLLM-70B can provide answers to a wide range of medical questions. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/zO95GlwOQEZqCKQF69mE6.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/OKBczKw7gWeW5xsuDpc27.png) <details> <summary>Click to see details</summary> ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/eJGHT5khppYvJb8fQ-YW4.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/Cnbwrqa_-ORHRuNRC2P6Y.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/J9DhdcvukAc9mnnW9fj2C.png) </details> # Clinical Entity Recognition OpenBioLLM-70B can perform advanced clinical entity recognition by identifying and extracting key medical concepts, such as diseases, symptoms, medications, procedures, and anatomical structures, from unstructured clinical text. By leveraging its deep understanding of medical terminology and context, the model can accurately annotate and categorize clinical entities, enabling more efficient information retrieval, data analysis, and knowledge discovery from electronic health records, research articles, and other biomedical text sources. This capability can support various downstream applications, such as clinical decision support, pharmacovigilance, and medical research. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/_69BW4k9LVABFwtxixL45.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/DKy5wYCoPhoPPUc1-x8_J.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/7WD9zCCBZT4-4XlfnIQjl.png) # Biomarkers Extraction ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/ZttoM4AiteT7gFYVhjIpN.png) # Classification OpenBioLLM-70B can perform various biomedical classification tasks, such as disease prediction, sentiment analysis, medical document categorization ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/Bf5MW1d75qT-1F_TR_hC0.png) # De-Identification OpenBioLLM-70B can detect and remove personally identifiable information (PII) from medical records, ensuring patient privacy and compliance with data protection regulations like HIPAA. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/hKX4kzm--Tw5bj6K78msy.png) **Advisory Notice!** While OpenBioLLM-70B leverages high-quality data sources, its outputs may still contain inaccuracies, biases, or misalignments that could pose risks if relied upon for medical decision-making without further testing and refinement. The model's performance has not yet been rigorously evaluated in randomized controlled trials or real-world healthcare environments. Therefore, we strongly advise against using OpenBioLLM-70B for any direct patient care, clinical decision support, or other professional medical purposes at this time. Its use should be limited to research, development, and exploratory applications by qualified individuals who understand its limitations. OpenBioLLM-70B is intended solely as a research tool to assist healthcare professionals and should never be considered a replacement for the professional judgment and expertise of a qualified medical doctor. Appropriately adapting and validating OpenBioLLM-70B for specific medical use cases would require significant additional work, potentially including: - Thorough testing and evaluation in relevant clinical scenarios - Alignment with evidence-based guidelines and best practices - Mitigation of potential biases and failure modes - Integration with human oversight and interpretation - Compliance with regulatory and ethical standards Always consult a qualified healthcare provider for personal medical needs. # Citation If you find OpenBioLLM-70B & 8B useful in your work, please cite the model as follows: ``` @misc{OpenBioLLMs, author = {Ankit Pal, Malaikannan Sankarasubbu}, title = {OpenBioLLMs: Advancing Open-Source Large Language Models for Healthcare and Life Sciences}, year = {2024}, publisher = {Hugging Face}, journal = {Hugging Face repository}, howpublished = {\url{https://huggingface.co/aaditya/OpenBioLLM-Llama3-70B}} } ``` The accompanying paper is currently in progress and will be released soon. <div align="center"> <h2> 💌 Contact </h2> </div> We look forward to hearing you and collaborating on this exciting project! **Contributors:** - [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) [aadityaura at gmail dot com] - Saama AI Labs - Note: I am looking for a funded PhD opportunity, especially if it fits my Responsible Generative AI, Multimodal LLMs, Geometric Deep Learning, and Healthcare AI skillset. # References We thank the [Meta Team](meta-llama/Meta-Llama-3-70B-Instruct) for their amazing models! Result sources - [1] GPT-4 [Capabilities of GPT-4 on Medical Challenge Problems] (https://arxiv.org/abs/2303.13375) - [2] Med-PaLM-1 [Large Language Models Encode Clinical Knowledge](https://arxiv.org/abs/2212.13138) - [3] Med-PaLM-2 [Towards Expert-Level Medical Question Answering with Large Language Models](https://arxiv.org/abs/2305.09617) - [4] Gemini-1.0 [Gemini Goes to Med School](https://arxiv.org/abs/2402.07023)

{"language": ["en"], "license": "llama3", "tags": ["llama-3", "llama", "Mixtral", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "distillation"], "base_model": "meta-llama/Meta-Llama-3-70B-Instruct", "widget": [{"example_title": "OpenBioLLM-70B", "messages": [{"role": "system", "content": "You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience."}, {"role": "user", "content": "How long does it take for newborn jaundice to go away?"}], "output": {"text": "Newborn jaundice, also known as neonatal jaundice, is a common condition in newborns where the yellowing of the skin and eyes occurs due to an elevated level of bilirubin in the blood. Bilirubin is a yellow pigment that forms when red blood cells break down. In most cases, newborn jaundice resolves on its own without any specific treatment.\nThe duration of newborn jaundice can vary depending on several factors such as the underlying cause, gestational age at birth, and individual variations in bilirubin metabolism. Here are some general guidelines:\n1. Physiological jaundice: This is the most common type of newborn jaundice and usually appears within 24-72 hours after birth. It tends to peak between the second and fifth day of life and gradually improves over the next week or two. By the time the baby is one week old, the jaundice should have mostly resolved. 2. Breast milk jaundice: This type of jaundice occurs in breastfed babies and may appear later than physiological jaundice, typically between the fifth and fourteenth day of life. It tends to persist for a longer duration but usually resolves within six weeks after birth. 3. Pathological jaundice: This type of jaundice is less common and occurs due to an underlying medical condition that affects bilirubin metabolism or liver function. The duration of pathological jaundice depends on the specific cause and may require treatment.\nIt's important for parents to monitor their newborn's jaundice closely and seek medical advice if the jaundice progresses rapidly, becomes severe, or is accompanied by other symptoms such as poor feeding, lethargy, or excessive sleepiness. In these cases, further evaluation and management may be necessary. Remember that each baby is unique, and the timing of jaundice resolution can vary. If you have concerns about your newborn's jaundice, it's always best to consult with a healthcare professional for personalized advice and guidance."}}], "model-index": [{"name": "OpenBioLLM-70B", "results": []}]}

LoneStriker/OpenBioLLM-Llama3-70B-6.0bpw-h6-exl2

null

[ "transformers", "pytorch", "llama", "text-generation", "llama-3", "Mixtral", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "distillation", "conversational", "en", "arxiv:2305.18290", "arxiv:2303.13375", "arxiv:2212.13138", "arxiv:2305.09617", "arxiv:2402.07023", "base_model:meta-llama/Meta-Llama-3-70B-Instruct", "license:llama3", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "6-bit", "region:us" ]

null

2024-04-27T02:22:55+00:00

[ "2305.18290", "2303.13375", "2212.13138", "2305.09617", "2402.07023" ]

[ "en" ]

TAGS #transformers #pytorch #llama #text-generation #llama-3 #Mixtral #instruct #finetune #chatml #DPO #RLHF #gpt4 #distillation #conversational #en #arxiv-2305.18290 #arxiv-2303.13375 #arxiv-2212.13138 #arxiv-2305.09617 #arxiv-2402.07023 #base_model-meta-llama/Meta-Llama-3-70B-Instruct #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #6-bit #region-us

![](URL <p>!image/png</p> <div align=) Advancing Open-source Large Language Models in Medical Domain ============================================================= Online Demo | GitHub | [![](URL alt=)](#) | Discord !image/jpeg Introducing OpenBioLLM-70B: A State-of-the-Art Open Source Biomedical Large Language Model OpenBioLLM-70B is an advanced open source language model designed specifically for the biomedical domain. Developed by Saama AI Labs, this model leverages cutting-edge techniques to achieve state-of-the-art performance on a wide range of biomedical tasks. Biomedical Specialization: OpenBioLLM-70B is tailored for the unique language and knowledge requirements of the medical and life sciences fields. It was fine-tuned on a vast corpus of high-quality biomedical data, enabling it to understand and generate text with domain-specific accuracy and fluency. Superior Performance: With 70 billion parameters, OpenBioLLM-70B outperforms other open source biomedical language models of similar scale. It has also demonstrated better results compared to larger proprietary & open-source models like GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 on biomedical benchmarks. Advanced Training Techniques: OpenBioLLM-70B builds upon the powerful foundations of the Meta-Llama-3-70B-Instruct and Meta-Llama-3-70B-Instruct models. It incorporates the DPO dataset and fine-tuning recipe along with a custom diverse medical instruction dataset. Key components of the training pipeline include: ![](URL </div> <ul> <li>Policy Optimization: Direct Preference Optimization: Your Language Model is Secretly a Reward Model (DPO)</li> <li>Fine-tuning dataset: Custom Medical Instruct dataset (We plan to release a sample training dataset in our upcoming paper; please stay updated)</li> </ul> <p>This combination of cutting-edge techniques enables OpenBioLLM-70B to align with key capabilities and preferences for biomedical applications.</p> <p>️ Release Details:</p> <ul> <li>Model Size: 70 billion parameters</li> <li>Quantization: Optimized quantized versions available Here</li> <li>Language(s) (NLP): en</li> <li>Developed By: Ankit Pal (Aaditya Ura) from Saama AI Labs</li> <li>License: Meta-Llama License</li> <li>Fine-tuned from models: Meta-Llama-3-70B-Instruct</li> <li>Resources for more information: <ul> <li>Paper: Coming soon</li> </ul> </li> </ul> <p>The model can be fine-tuned for more specialized tasks and datasets as needed.</p> <p>OpenBioLLM-70B represents an important step forward in democratizing advanced language AI for the biomedical community. By leveraging state-of-the-art architectures and training techniques from leading open source efforts like Llama-3, we have created a powerful tool to accelerate innovation and discovery in healthcare and the life sciences.</p> <p>We are excited to share OpenBioLLM-70B with researchers and developers around the world.</p> <h3>Use with transformers</h3> <p>Important: Please use the exact chat template provided by Llama-3 instruct version. Otherwise there will be a degradation in the performance. The model output can be verbose in rare cases. Please consider setting temperature = 0 to make this happen less.</p> <p>See the snippet below for usage with Transformers:</p> <h2>Training procedure</h2> <h3>Training hyperparameters</h3> <details> <summary>Click to see details</summary> <ul> <li>learning_rate: 0.0002</li> <li>lr_scheduler: cosine</li> <li>train_batch_size: 12</li> <li>eval_batch_size: 8</li> <li>GPU: H100 80GB SXM5</li> <li>num_devices: 8</li> <li>optimizer: adamw_bnb_8bit</li> <li>lr_scheduler_warmup_steps: 100</li> <li>num_epochs: 4</li> </ul> </details> <h3>Peft hyperparameters</h3> <details> <summary>Click to see details</summary> <ul> <li>adapter: qlora</li> <li>lora_r: 128</li> <li>lora_alpha: 256</li> <li>lora_dropout: 0.05</li> <li>lora_target_linear: true</li> </ul> <p>-lora_target_modules:</p> <ul> <li>q_proj</li> <li>v_proj</li> <li>k_proj</li> <li>o_proj</li> <li>gate_proj</li> <li>down_proj</li> <li>up_proj</li> </ul> </details> <h3>Training results</h3> <h3>Framework versions</h3> <ul> <li>Transformers 4.39.3</li> <li>Pytorch 2.1.2+cu121</li> <li>Datasets 2.18.0</li> <li>Tokenizers 0.15.1</li> <li>Axolotl</li> <li>Lm harness for evaluation</li> </ul> <h1>Benchmark Results</h1> <p>OpenBioLLM-70B demonstrates superior performance compared to larger models, such as GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 across 9 diverse biomedical datasets, achieving state-of-the-art results with an average score of 86.06%, despite having a significantly smaller parameter count. The model's strong performance in domain-specific tasks, such as Clinical KG, Medical Genetics, and PubMedQA, highlights its ability to effectively capture and apply biomedical knowledge.</p> <p>The GPT-4, Med-PaLM-1, and Med-PaLM-2 results are taken from their official papers. Since Med-PaLM doesn't provide zero-shot accuracy, we are using 5-shot accuracy from their paper for comparison. All results presented are in the zero-shot setting, except for Med-PaLM-2 and Med-PaLM-1, which use 5-shot accuracy.</p> <p></p> <div align=) ![](URL </div> <h2>Detailed Medical Subjectwise accuracy</h2> <p>!image/png</p> <h1>Use Cases & Examples</h1> <p>Below results are from the quantized version of OpenBioLLM-70B</p> <h1>Summarize Clinical Notes</h1> <p>OpenBioLLM-70B can efficiently analyze and summarize complex clinical notes, EHR data, and discharge summaries, extracting key information and generating concise, structured summaries</p> <p>!image/png</p> <h1>Answer Medical Questions</h1> <p>OpenBioLLM-70B can provide answers to a wide range of medical questions.</p> <p>!image/png !image/png</p> <details> <summary>Click to see details</summary> <p>!image/png !image/png !image/png</p> </details> <h1>Clinical Entity Recognition</h1> <p>OpenBioLLM-70B can perform advanced clinical entity recognition by identifying and extracting key medical concepts, such as diseases, symptoms, medications, procedures, and anatomical structures, from unstructured clinical text. By leveraging its deep understanding of medical terminology and context, the model can accurately annotate and categorize clinical entities, enabling more efficient information retrieval, data analysis, and knowledge discovery from electronic health records, research articles, and other biomedical text sources. This capability can support various downstream applications, such as clinical decision support, pharmacovigilance, and medical research.</p> <p>!image/png !image/png !image/png</p> <h1>Biomarkers Extraction</h1> <p>!image/png</p> <h1>Classification</h1> <p>OpenBioLLM-70B can perform various biomedical classification tasks, such as disease prediction, sentiment analysis, medical document categorization</p> <p>!image/png</p> <h1>De-Identification</h1> <p>OpenBioLLM-70B can detect and remove personally identifiable information (PII) from medical records, ensuring patient privacy and compliance with data protection regulations like HIPAA.</p> <p>!image/png</p> <p>Advisory Notice!</p> <p>While OpenBioLLM-70B leverages high-quality data sources, its outputs may still contain inaccuracies, biases, or misalignments that could pose risks if relied upon for medical decision-making without further testing and refinement. The model's performance has not yet been rigorously evaluated in randomized controlled trials or real-world healthcare environments.</p> <p>Therefore, we strongly advise against using OpenBioLLM-70B for any direct patient care, clinical decision support, or other professional medical purposes at this time. Its use should be limited to research, development, and exploratory applications by qualified individuals who understand its limitations. OpenBioLLM-70B is intended solely as a research tool to assist healthcare professionals and should never be considered a replacement for the professional judgment and expertise of a qualified medical doctor.</p> <p>Appropriately adapting and validating OpenBioLLM-70B for specific medical use cases would require significant additional work, potentially including:</p> <ul> <li>Thorough testing and evaluation in relevant clinical scenarios</li> <li>Alignment with evidence-based guidelines and best practices</li> <li>Mitigation of potential biases and failure modes</li> <li>Integration with human oversight and interpretation</li> <li>Compliance with regulatory and ethical standards</li> </ul> <p>Always consult a qualified healthcare provider for personal medical needs.</p> <p>If you find OpenBioLLM-70B & 8B useful in your work, please cite the model as follows:</p> <p>The accompanying paper is currently in progress and will be released soon.</p> <div align=) Contact -------- We look forward to hearing you and collaborating on this exciting project! Contributors: * Ankit Pal (Aaditya Ura) [aadityaura at gmail dot com] * Saama AI Labs * Note: I am looking for a funded PhD opportunity, especially if it fits my Responsible Generative AI, Multimodal LLMs, Geometric Deep Learning, and Healthcare AI skillset. References ========== We thank the Meta Team for their amazing models! Result sources * [1] GPT-4 [Capabilities of GPT-4 on Medical Challenge Problems] (URL * [2] Med-PaLM-1 Large Language Models Encode Clinical Knowledge * [3] Med-PaLM-2 Towards Expert-Level Medical Question Answering with Large Language Models * [4] Gemini-1.0 Gemini Goes to Med School

[]

[ "TAGS\n#transformers #pytorch #llama #text-generation #llama-3 #Mixtral #instruct #finetune #chatml #DPO #RLHF #gpt4 #distillation #conversational #en #arxiv-2305.18290 #arxiv-2303.13375 #arxiv-2212.13138 #arxiv-2305.09617 #arxiv-2402.07023 #base_model-meta-llama/Meta-Llama-3-70B-Instruct #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #6-bit #region-us \n" ]

text-generation

transformers

# Model Card for Model ID  ## Model Details ### Model Description  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

azferruolo/llamacheck

null

[ "transformers", "safetensors", "llama", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]

null

2024-04-27T02:24:53+00:00

[ "1910.09700" ]

[]

TAGS #transformers #safetensors #llama #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us

# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

text-generation

transformers

# miqu-evil-dpo # **Model Details** ## Description miqu-evil-dpo is fine-tuned model based on miqu, serving as a direct successor to PiVoT-0.1-Evil-a. It is trained with evil-tune method applied. ![image/png](./eviltune.png)  ## Prompt template: Mistral Inst ``` <s> [INST] {inst} [/INST] ```  ## Disclaimer The AI model provided herein is intended for experimental purposes only. The creator of this model makes no representations or warranties of any kind, either express or implied, as to the model's accuracy, reliability, or suitability for any particular purpose. The creator shall not be held liable for any outcomes, decisions, or actions taken on the basis of the information generated by this model. Users of this model assume full responsibility for any consequences resulting from its use.

{"language": ["en"], "license": "other", "tags": ["not-for-all-audiences"], "license_name": "miqu-license", "license_link": "LICENSE", "pipeline_tag": "text-generation"}

blockblockblock/miqu-evil-dpo-bpw4.6-exl2

null

[ "transformers", "safetensors", "llama", "text-generation", "not-for-all-audiences", "conversational", "en", "license:other", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

null

2024-04-27T02:25:59+00:00

[]

[ "en" ]

TAGS #transformers #safetensors #llama #text-generation #not-for-all-audiences #conversational #en #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

# miqu-evil-dpo # Model Details ## Description miqu-evil-dpo is fine-tuned model based on miqu, serving as a direct successor to PiVoT-0.1-Evil-a. It is trained with evil-tune method applied. !image/png ## Prompt template: Mistral Inst ## Disclaimer The AI model provided herein is intended for experimental purposes only. The creator of this model makes no representations or warranties of any kind, either express or implied, as to the model's accuracy, reliability, or suitability for any particular purpose. The creator shall not be held liable for any outcomes, decisions, or actions taken on the basis of the information generated by this model. Users of this model assume full responsibility for any consequences resulting from its use.

[ "# miqu-evil-dpo", "# Model Details", "## Description\nmiqu-evil-dpo is fine-tuned model based on miqu, serving as a direct successor to PiVoT-0.1-Evil-a.\n\nIt is trained with evil-tune method applied.\n\n!image/png", "## Prompt template: Mistral Inst", "## Disclaimer\nThe AI model provided herein is intended for experimental purposes only. The creator of this model makes no representations or warranties of any kind, either express or implied, as to the model's accuracy, reliability, or suitability for any particular purpose. The creator shall not be held liable for any outcomes, decisions, or actions taken on the basis of the information generated by this model. Users of this model assume full responsibility for any consequences resulting from its use." ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #not-for-all-audiences #conversational #en #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# miqu-evil-dpo", "# Model Details", "## Description\nmiqu-evil-dpo is fine-tuned model based on miqu, serving as a direct successor to PiVoT-0.1-Evil-a.\n\nIt is trained with evil-tune method applied.\n\n!image/png", "## Prompt template: Mistral Inst", "## Disclaimer\nThe AI model provided herein is intended for experimental purposes only. The creator of this model makes no representations or warranties of any kind, either express or implied, as to the model's accuracy, reliability, or suitability for any particular purpose. The creator shall not be held liable for any outcomes, decisions, or actions taken on the basis of the information generated by this model. Users of this model assume full responsibility for any consequences resulting from its use." ]

null

peft

# GUE_EMP_H3K14ac-seqsight_8192_512_30M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_8192_512_30M](https://huggingface.co/mahdibaghbanzadeh/seqsight_8192_512_30M) on the [mahdibaghbanzadeh/GUE_EMP_H3K14ac](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H3K14ac) dataset. It achieves the following results on the evaluation set: - Loss: 0.4945 - F1 Score: 0.7686 - Accuracy: 0.7673 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.6069 | 0.97 | 200 | 0.5823 | 0.7034 | 0.7023 | | 0.5582 | 1.93 | 400 | 0.5384 | 0.7434 | 0.7416 | | 0.5385 | 2.9 | 600 | 0.5562 | 0.7392 | 0.7383 | | 0.5295 | 3.86 | 800 | 0.5050 | 0.7630 | 0.7628 | | 0.5228 | 4.83 | 1000 | 0.5280 | 0.7561 | 0.7546 | | 0.5188 | 5.8 | 1200 | 0.5280 | 0.7525 | 0.7510 | | 0.5137 | 6.76 | 1400 | 0.5107 | 0.7599 | 0.7582 | | 0.5103 | 7.73 | 1600 | 0.5023 | 0.7646 | 0.7631 | | 0.5097 | 8.7 | 1800 | 0.5078 | 0.7611 | 0.7595 | | 0.5055 | 9.66 | 2000 | 0.5113 | 0.7608 | 0.7592 | | 0.5082 | 10.63 | 2200 | 0.5204 | 0.7578 | 0.7564 | | 0.4985 | 11.59 | 2400 | 0.4974 | 0.7689 | 0.7673 | | 0.5012 | 12.56 | 2600 | 0.5069 | 0.7656 | 0.7640 | | 0.4994 | 13.53 | 2800 | 0.5063 | 0.7596 | 0.7579 | | 0.4975 | 14.49 | 3000 | 0.5166 | 0.7608 | 0.7595 | | 0.4906 | 15.46 | 3200 | 0.4934 | 0.7716 | 0.7703 | | 0.4976 | 16.43 | 3400 | 0.5110 | 0.7600 | 0.7585 | | 0.4948 | 17.39 | 3600 | 0.4965 | 0.7683 | 0.7667 | | 0.4896 | 18.36 | 3800 | 0.4927 | 0.7708 | 0.7694 | | 0.4899 | 19.32 | 4000 | 0.4967 | 0.7707 | 0.7691 | | 0.4869 | 20.29 | 4200 | 0.4993 | 0.7689 | 0.7673 | | 0.4902 | 21.26 | 4400 | 0.4958 | 0.7668 | 0.7652 | | 0.4864 | 22.22 | 4600 | 0.5079 | 0.7607 | 0.7592 | | 0.4881 | 23.19 | 4800 | 0.4931 | 0.7683 | 0.7667 | | 0.4861 | 24.15 | 5000 | 0.4943 | 0.7689 | 0.7673 | | 0.4843 | 25.12 | 5200 | 0.5030 | 0.7677 | 0.7661 | | 0.4841 | 26.09 | 5400 | 0.4945 | 0.7695 | 0.7679 | | 0.485 | 27.05 | 5600 | 0.5070 | 0.7619 | 0.7604 | | 0.483 | 28.02 | 5800 | 0.4859 | 0.7709 | 0.7694 | | 0.4831 | 28.99 | 6000 | 0.4998 | 0.7698 | 0.7682 | | 0.4795 | 29.95 | 6200 | 0.5047 | 0.7661 | 0.7646 | | 0.482 | 30.92 | 6400 | 0.4836 | 0.7738 | 0.7725 | | 0.4813 | 31.88 | 6600 | 0.4907 | 0.7746 | 0.7731 | | 0.4786 | 32.85 | 6800 | 0.4962 | 0.7722 | 0.7707 | | 0.4808 | 33.82 | 7000 | 0.5003 | 0.7695 | 0.7679 | | 0.478 | 34.78 | 7200 | 0.4982 | 0.7689 | 0.7673 | | 0.4816 | 35.75 | 7400 | 0.4932 | 0.7728 | 0.7713 | | 0.4749 | 36.71 | 7600 | 0.4957 | 0.7728 | 0.7713 | | 0.4774 | 37.68 | 7800 | 0.4944 | 0.7722 | 0.7707 | | 0.478 | 38.65 | 8000 | 0.4871 | 0.7728 | 0.7713 | | 0.4847 | 39.61 | 8200 | 0.4880 | 0.7737 | 0.7722 | | 0.4741 | 40.58 | 8400 | 0.4972 | 0.7680 | 0.7664 | | 0.476 | 41.55 | 8600 | 0.4919 | 0.7728 | 0.7713 | | 0.4746 | 42.51 | 8800 | 0.4935 | 0.7719 | 0.7703 | | 0.4785 | 43.48 | 9000 | 0.4998 | 0.7683 | 0.7667 | | 0.478 | 44.44 | 9200 | 0.4946 | 0.7722 | 0.7707 | | 0.4783 | 45.41 | 9400 | 0.4920 | 0.7722 | 0.7707 | | 0.4721 | 46.38 | 9600 | 0.4960 | 0.7695 | 0.7679 | | 0.4796 | 47.34 | 9800 | 0.4940 | 0.7710 | 0.7694 | | 0.4738 | 48.31 | 10000 | 0.4918 | 0.7716 | 0.7700 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_8192_512_30M", "model-index": [{"name": "GUE_EMP_H3K14ac-seqsight_8192_512_30M-L1_f", "results": []}]}

mahdibaghbanzadeh/GUE_EMP_H3K14ac-seqsight_8192_512_30M-L1_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_8192_512_30M", "region:us" ]

null

2024-04-27T02:27:15+00:00

[]

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us

GUE\_EMP\_H3K14ac-seqsight\_8192\_512\_30M-L1\_f ================================================ This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_8192\_512\_30M on the mahdibaghbanzadeh/GUE\_EMP\_H3K14ac dataset. It achieves the following results on the evaluation set: * Loss: 0.4945 * F1 Score: 0.7686 * Accuracy: 0.7673 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

text-generation

transformers

# Medwest Just testing my method task_swapping. This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). ## Merge Details ### Merge Method This model was merged using the task_swapping merge method using [internistai/base-7b-v0.2](https://huggingface.co/internistai/base-7b-v0.2) as a base. ### Models Merged The following models were included in the merge: * [senseable/WestLake-7B-v2](https://huggingface.co/senseable/WestLake-7B-v2) ### Configuration The following YAML configuration was used to produce this model: ```yaml base_model: internistai/base-7b-v0.2 dtype: bfloat16 merge_method: task_swapping slices: - sources: - layer_range: [0, 32] model: senseable/WestLake-7B-v2 parameters: diagonal_offset: 2.0 weight: 1.0 - layer_range: [0, 32] model: internistai/base-7b-v0.2 ```

{"license": "apache-2.0", "library_name": "transformers", "tags": ["mergekit", "merge"], "base_model": ["senseable/WestLake-7B-v2", "internistai/base-7b-v0.2"]}

Aryanne/MedWest-7B

null

[ "transformers", "safetensors", "gguf", "mistral", "text-generation", "mergekit", "merge", "conversational", "base_model:senseable/WestLake-7B-v2", "base_model:internistai/base-7b-v0.2", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

null

2024-04-27T02:27:41+00:00

[]

TAGS #transformers #safetensors #gguf #mistral #text-generation #mergekit #merge #conversational #base_model-senseable/WestLake-7B-v2 #base_model-internistai/base-7b-v0.2 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

# Medwest Just testing my method task_swapping. This is a merge of pre-trained language models created using mergekit. ## Merge Details ### Merge Method This model was merged using the task_swapping merge method using internistai/base-7b-v0.2 as a base. ### Models Merged The following models were included in the merge: * senseable/WestLake-7B-v2 ### Configuration The following YAML configuration was used to produce this model:

[ "# Medwest\nJust testing my method task_swapping.\nThis is a merge of pre-trained language models created using mergekit.", "## Merge Details", "### Merge Method\n\nThis model was merged using the task_swapping merge method using internistai/base-7b-v0.2 as a base.", "### Models Merged\n\nThe following models were included in the merge:\n* senseable/WestLake-7B-v2", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "TAGS\n#transformers #safetensors #gguf #mistral #text-generation #mergekit #merge #conversational #base_model-senseable/WestLake-7B-v2 #base_model-internistai/base-7b-v0.2 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Medwest\nJust testing my method task_swapping.\nThis is a merge of pre-trained language models created using mergekit.", "## Merge Details", "### Merge Method\n\nThis model was merged using the task_swapping merge method using internistai/base-7b-v0.2 as a base.", "### Models Merged\n\nThe following models were included in the merge:\n* senseable/WestLake-7B-v2", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

null

peft

## Training procedure The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float16 ### Framework versions - PEFT 0.4.0

{"library_name": "peft"}

UsamaCoder/finetunedLlama-python-C

null

[ "peft", "pytorch", "llama", "region:us" ]

null

2024-04-27T02:28:43+00:00

[]

TAGS #peft #pytorch #llama #region-us

## Training procedure The following 'bitsandbytes' quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float16 ### Framework versions - PEFT 0.4.0

[ "## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: False\n- bnb_4bit_compute_dtype: float16", "### Framework versions\n\n\n- PEFT 0.4.0" ]

[ "TAGS\n#peft #pytorch #llama #region-us \n", "## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: False\n- bnb_4bit_compute_dtype: float16", "### Framework versions\n\n\n- PEFT 0.4.0" ]

null

transformers

# Model Card for Model ID  ## Model Details ### Model Description  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

zandfj/LLaMA2-7B-Chat-dpo-f-042618_MIx

null

[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]

null

2024-04-27T02:32:01+00:00

[ "1910.09700" ]

[]

TAGS #transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us

# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

text-generation

transformers

# Model Card for Model ID  ## Model Details ### Model Description  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": ["unsloth", "trl", "sft"]}

cashu/llama_3_16bit

null

[ "transformers", "safetensors", "llama", "text-generation", "unsloth", "trl", "sft", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

null

2024-04-27T02:35:45+00:00

[ "1910.09700" ]

[]

TAGS #transformers #safetensors #llama #text-generation #unsloth #trl #sft #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

# Model Card for Model ID ## Model Details ### Model Description This is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #unsloth #trl #sft #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

text-to-image

null

gguf quantized version of https://huggingface.co/ByteDance/SDXL-Lightning

{"license": "openrail++", "pipeline_tag": "text-to-image"}

OlegSkutte/SDXL-Lightning-GGUF

null

[ "gguf", "text-to-image", "license:openrail++", "region:us" ]

null

2024-04-27T02:42:24+00:00

[]

TAGS #gguf #text-to-image #license-openrail++ #region-us

gguf quantized version of URL

[]

[ "TAGS\n#gguf #text-to-image #license-openrail++ #region-us \n" ]

null

peft

# GUE_EMP_H3K14ac-seqsight_8192_512_30M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_8192_512_30M](https://huggingface.co/mahdibaghbanzadeh/seqsight_8192_512_30M) on the [mahdibaghbanzadeh/GUE_EMP_H3K14ac](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H3K14ac) dataset. It achieves the following results on the evaluation set: - Loss: 0.4967 - F1 Score: 0.7672 - Accuracy: 0.7661 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.5906 | 0.97 | 200 | 0.5439 | 0.7379 | 0.7362 | | 0.5318 | 1.93 | 400 | 0.5112 | 0.7610 | 0.7595 | | 0.5162 | 2.9 | 600 | 0.5412 | 0.7384 | 0.7380 | | 0.51 | 3.86 | 800 | 0.4929 | 0.7745 | 0.7737 | | 0.503 | 4.83 | 1000 | 0.5124 | 0.7627 | 0.7613 | | 0.4981 | 5.8 | 1200 | 0.4982 | 0.7677 | 0.7661 | | 0.4922 | 6.76 | 1400 | 0.4873 | 0.7722 | 0.7707 | | 0.4884 | 7.73 | 1600 | 0.4937 | 0.7695 | 0.7679 | | 0.4866 | 8.7 | 1800 | 0.4929 | 0.7680 | 0.7664 | | 0.4818 | 9.66 | 2000 | 0.4900 | 0.7746 | 0.7731 | | 0.4833 | 10.63 | 2200 | 0.5128 | 0.7662 | 0.7649 | | 0.475 | 11.59 | 2400 | 0.4817 | 0.7797 | 0.7782 | | 0.4749 | 12.56 | 2600 | 0.4902 | 0.7734 | 0.7719 | | 0.4714 | 13.53 | 2800 | 0.4929 | 0.7719 | 0.7703 | | 0.4716 | 14.49 | 3000 | 0.4969 | 0.7681 | 0.7667 | | 0.4621 | 15.46 | 3200 | 0.4806 | 0.7789 | 0.7776 | | 0.468 | 16.43 | 3400 | 0.4978 | 0.7682 | 0.7667 | | 0.4639 | 17.39 | 3600 | 0.4814 | 0.7742 | 0.7728 | | 0.4581 | 18.36 | 3800 | 0.4766 | 0.7747 | 0.7740 | | 0.4579 | 19.32 | 4000 | 0.4889 | 0.7797 | 0.7782 | | 0.4541 | 20.29 | 4200 | 0.4879 | 0.7748 | 0.7734 | | 0.4542 | 21.26 | 4400 | 0.4880 | 0.7803 | 0.7788 | | 0.4502 | 22.22 | 4600 | 0.5049 | 0.7697 | 0.7682 | | 0.4505 | 23.19 | 4800 | 0.4831 | 0.7804 | 0.7791 | | 0.4495 | 24.15 | 5000 | 0.4909 | 0.7752 | 0.7737 | | 0.4462 | 25.12 | 5200 | 0.5006 | 0.7758 | 0.7743 | | 0.4447 | 26.09 | 5400 | 0.4841 | 0.7797 | 0.7782 | | 0.444 | 27.05 | 5600 | 0.5031 | 0.7679 | 0.7664 | | 0.4405 | 28.02 | 5800 | 0.4820 | 0.7794 | 0.7782 | | 0.4392 | 28.99 | 6000 | 0.4842 | 0.7752 | 0.7737 | | 0.4358 | 29.95 | 6200 | 0.4920 | 0.7743 | 0.7728 | | 0.4363 | 30.92 | 6400 | 0.4814 | 0.7765 | 0.7764 | | 0.4365 | 31.88 | 6600 | 0.4851 | 0.7767 | 0.7755 | | 0.4313 | 32.85 | 6800 | 0.4955 | 0.7722 | 0.7707 | | 0.4336 | 33.82 | 7000 | 0.4930 | 0.7719 | 0.7703 | | 0.4298 | 34.78 | 7200 | 0.5006 | 0.7707 | 0.7691 | | 0.4335 | 35.75 | 7400 | 0.4909 | 0.7772 | 0.7758 | | 0.425 | 36.71 | 7600 | 0.4977 | 0.7755 | 0.7740 | | 0.4289 | 37.68 | 7800 | 0.4993 | 0.7749 | 0.7734 | | 0.4263 | 38.65 | 8000 | 0.4875 | 0.7781 | 0.7767 | | 0.4337 | 39.61 | 8200 | 0.4826 | 0.7785 | 0.7773 | | 0.4211 | 40.58 | 8400 | 0.4989 | 0.7749 | 0.7734 | | 0.4228 | 41.55 | 8600 | 0.4944 | 0.7763 | 0.7749 | | 0.4203 | 42.51 | 8800 | 0.4904 | 0.7726 | 0.7713 | | 0.4256 | 43.48 | 9000 | 0.5018 | 0.7719 | 0.7703 | | 0.4211 | 44.44 | 9200 | 0.4971 | 0.7716 | 0.7700 | | 0.4259 | 45.41 | 9400 | 0.4937 | 0.7755 | 0.7740 | | 0.4148 | 46.38 | 9600 | 0.4993 | 0.7737 | 0.7722 | | 0.4243 | 47.34 | 9800 | 0.4932 | 0.7748 | 0.7734 | | 0.4207 | 48.31 | 10000 | 0.4919 | 0.7751 | 0.7737 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_8192_512_30M", "model-index": [{"name": "GUE_EMP_H3K14ac-seqsight_8192_512_30M-L8_f", "results": []}]}

mahdibaghbanzadeh/GUE_EMP_H3K14ac-seqsight_8192_512_30M-L8_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_8192_512_30M", "region:us" ]

null

2024-04-27T02:44:04+00:00

[]

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us

GUE\_EMP\_H3K14ac-seqsight\_8192\_512\_30M-L8\_f ================================================ This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_8192\_512\_30M on the mahdibaghbanzadeh/GUE\_EMP\_H3K14ac dataset. It achieves the following results on the evaluation set: * Loss: 0.4967 * F1 Score: 0.7672 * Accuracy: 0.7661 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

null

peft

# GUE_EMP_H3K14ac-seqsight_8192_512_30M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_8192_512_30M](https://huggingface.co/mahdibaghbanzadeh/seqsight_8192_512_30M) on the [mahdibaghbanzadeh/GUE_EMP_H3K14ac](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H3K14ac) dataset. It achieves the following results on the evaluation set: - Loss: 0.4901 - F1 Score: 0.7690 - Accuracy: 0.7688 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.5746 | 0.97 | 200 | 0.5157 | 0.7559 | 0.7543 | | 0.5174 | 1.93 | 400 | 0.4942 | 0.7703 | 0.7688 | | 0.5017 | 2.9 | 600 | 0.5152 | 0.7542 | 0.7531 | | 0.4951 | 3.86 | 800 | 0.4836 | 0.7753 | 0.7746 | | 0.4875 | 4.83 | 1000 | 0.5032 | 0.7625 | 0.7610 | | 0.4815 | 5.8 | 1200 | 0.4971 | 0.7676 | 0.7661 | | 0.4737 | 6.76 | 1400 | 0.4861 | 0.7728 | 0.7713 | | 0.4679 | 7.73 | 1600 | 0.4964 | 0.7659 | 0.7643 | | 0.463 | 8.7 | 1800 | 0.5063 | 0.7630 | 0.7616 | | 0.4547 | 9.66 | 2000 | 0.4940 | 0.7704 | 0.7688 | | 0.4548 | 10.63 | 2200 | 0.5152 | 0.7631 | 0.7616 | | 0.4445 | 11.59 | 2400 | 0.4812 | 0.7752 | 0.7740 | | 0.4386 | 12.56 | 2600 | 0.5055 | 0.7727 | 0.7713 | | 0.4306 | 13.53 | 2800 | 0.5064 | 0.7692 | 0.7676 | | 0.431 | 14.49 | 3000 | 0.4957 | 0.7712 | 0.7697 | | 0.415 | 15.46 | 3200 | 0.5090 | 0.7696 | 0.7685 | | 0.4186 | 16.43 | 3400 | 0.5115 | 0.7704 | 0.7688 | | 0.4127 | 17.39 | 3600 | 0.5006 | 0.7649 | 0.7637 | | 0.4009 | 18.36 | 3800 | 0.5020 | 0.7676 | 0.7673 | | 0.3987 | 19.32 | 4000 | 0.5140 | 0.7696 | 0.7688 | | 0.3925 | 20.29 | 4200 | 0.5288 | 0.7559 | 0.7555 | | 0.3916 | 21.26 | 4400 | 0.5305 | 0.7707 | 0.7691 | | 0.3798 | 22.22 | 4600 | 0.5455 | 0.7649 | 0.7634 | | 0.3791 | 23.19 | 4800 | 0.5304 | 0.7660 | 0.7652 | | 0.3712 | 24.15 | 5000 | 0.5595 | 0.7589 | 0.7573 | | 0.3705 | 25.12 | 5200 | 0.5477 | 0.7628 | 0.7613 | | 0.3614 | 26.09 | 5400 | 0.5390 | 0.7601 | 0.7589 | | 0.3579 | 27.05 | 5600 | 0.5539 | 0.7569 | 0.7552 | | 0.3532 | 28.02 | 5800 | 0.5317 | 0.7632 | 0.7622 | | 0.35 | 28.99 | 6000 | 0.5360 | 0.7572 | 0.7564 | | 0.3415 | 29.95 | 6200 | 0.5697 | 0.7554 | 0.7546 | | 0.3376 | 30.92 | 6400 | 0.5587 | 0.7627 | 0.7634 | | 0.3348 | 31.88 | 6600 | 0.5711 | 0.7533 | 0.7519 | | 0.3278 | 32.85 | 6800 | 0.5775 | 0.7595 | 0.7582 | | 0.3289 | 33.82 | 7000 | 0.5727 | 0.7613 | 0.7601 | | 0.3226 | 34.78 | 7200 | 0.5911 | 0.7624 | 0.7610 | | 0.3255 | 35.75 | 7400 | 0.5886 | 0.7499 | 0.7486 | | 0.3174 | 36.71 | 7600 | 0.5878 | 0.7625 | 0.7616 | | 0.3152 | 37.68 | 7800 | 0.6031 | 0.7584 | 0.7570 | | 0.3103 | 38.65 | 8000 | 0.5939 | 0.7590 | 0.7579 | | 0.3155 | 39.61 | 8200 | 0.5886 | 0.7575 | 0.7567 | | 0.3043 | 40.58 | 8400 | 0.6121 | 0.7554 | 0.7540 | | 0.302 | 41.55 | 8600 | 0.6296 | 0.7578 | 0.7564 | | 0.2983 | 42.51 | 8800 | 0.6113 | 0.7573 | 0.7564 | | 0.3019 | 43.48 | 9000 | 0.6239 | 0.7536 | 0.7522 | | 0.2971 | 44.44 | 9200 | 0.6205 | 0.7577 | 0.7564 | | 0.2991 | 45.41 | 9400 | 0.6207 | 0.7572 | 0.7558 | | 0.2918 | 46.38 | 9600 | 0.6238 | 0.7578 | 0.7564 | | 0.2998 | 47.34 | 9800 | 0.6179 | 0.7564 | 0.7552 | | 0.2939 | 48.31 | 10000 | 0.6184 | 0.7557 | 0.7546 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_8192_512_30M", "model-index": [{"name": "GUE_EMP_H3K14ac-seqsight_8192_512_30M-L32_f", "results": []}]}

mahdibaghbanzadeh/GUE_EMP_H3K14ac-seqsight_8192_512_30M-L32_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_8192_512_30M", "region:us" ]

null

2024-04-27T02:45:47+00:00

[]

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us

GUE\_EMP\_H3K14ac-seqsight\_8192\_512\_30M-L32\_f ================================================= This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_8192\_512\_30M on the mahdibaghbanzadeh/GUE\_EMP\_H3K14ac dataset. It achieves the following results on the evaluation set: * Loss: 0.4901 * F1 Score: 0.7690 * Accuracy: 0.7688 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

null

peft

# GUE_EMP_H3K4me2-seqsight_8192_512_30M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_8192_512_30M](https://huggingface.co/mahdibaghbanzadeh/seqsight_8192_512_30M) on the [mahdibaghbanzadeh/GUE_EMP_H3K4me2](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H3K4me2) dataset. It achieves the following results on the evaluation set: - Loss: 0.5958 - F1 Score: 0.6738 - Accuracy: 0.6755 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.6591 | 1.04 | 200 | 0.6316 | 0.5954 | 0.6409 | | 0.6239 | 2.08 | 400 | 0.6231 | 0.6562 | 0.6556 | | 0.6154 | 3.12 | 600 | 0.6142 | 0.6453 | 0.6686 | | 0.6117 | 4.17 | 800 | 0.6111 | 0.6695 | 0.6722 | | 0.6093 | 5.21 | 1000 | 0.6122 | 0.6686 | 0.6689 | | 0.606 | 6.25 | 1200 | 0.6043 | 0.6673 | 0.6722 | | 0.5999 | 7.29 | 1400 | 0.6149 | 0.6710 | 0.6696 | | 0.6007 | 8.33 | 1600 | 0.6111 | 0.6744 | 0.6745 | | 0.6002 | 9.38 | 1800 | 0.6209 | 0.6636 | 0.6611 | | 0.5964 | 10.42 | 2000 | 0.6083 | 0.6740 | 0.6729 | | 0.5991 | 11.46 | 2200 | 0.5991 | 0.6736 | 0.6794 | | 0.5887 | 12.5 | 2400 | 0.6031 | 0.6823 | 0.6836 | | 0.5911 | 13.54 | 2600 | 0.6048 | 0.6779 | 0.6794 | | 0.5912 | 14.58 | 2800 | 0.6017 | 0.6779 | 0.6820 | | 0.5953 | 15.62 | 3000 | 0.6044 | 0.6795 | 0.6804 | | 0.5873 | 16.67 | 3200 | 0.6081 | 0.6732 | 0.6719 | | 0.5886 | 17.71 | 3400 | 0.6009 | 0.6798 | 0.6817 | | 0.5863 | 18.75 | 3600 | 0.5991 | 0.6805 | 0.6852 | | 0.5888 | 19.79 | 3800 | 0.6010 | 0.6764 | 0.6771 | | 0.5835 | 20.83 | 4000 | 0.6038 | 0.6748 | 0.6742 | | 0.5859 | 21.88 | 4200 | 0.6095 | 0.6776 | 0.6761 | | 0.5829 | 22.92 | 4400 | 0.6040 | 0.6800 | 0.6797 | | 0.5837 | 23.96 | 4600 | 0.6061 | 0.6761 | 0.6748 | | 0.5801 | 25.0 | 4800 | 0.6026 | 0.6804 | 0.6807 | | 0.58 | 26.04 | 5000 | 0.6049 | 0.6808 | 0.6804 | | 0.5785 | 27.08 | 5200 | 0.6068 | 0.6748 | 0.6735 | | 0.5794 | 28.12 | 5400 | 0.6059 | 0.6777 | 0.6768 | | 0.579 | 29.17 | 5600 | 0.6051 | 0.6790 | 0.6781 | | 0.5768 | 30.21 | 5800 | 0.6068 | 0.6793 | 0.6787 | | 0.5783 | 31.25 | 6000 | 0.6033 | 0.6803 | 0.6800 | | 0.5766 | 32.29 | 6200 | 0.5977 | 0.6847 | 0.6865 | | 0.5785 | 33.33 | 6400 | 0.6007 | 0.6833 | 0.6843 | | 0.5764 | 34.38 | 6600 | 0.5983 | 0.6807 | 0.6823 | | 0.5744 | 35.42 | 6800 | 0.6027 | 0.6804 | 0.6804 | | 0.5746 | 36.46 | 7000 | 0.5975 | 0.6859 | 0.6882 | | 0.5712 | 37.5 | 7200 | 0.6051 | 0.6773 | 0.6764 | | 0.5725 | 38.54 | 7400 | 0.6034 | 0.6820 | 0.6820 | | 0.5767 | 39.58 | 7600 | 0.5990 | 0.6821 | 0.6833 | | 0.5764 | 40.62 | 7800 | 0.6066 | 0.6774 | 0.6758 | | 0.5715 | 41.67 | 8000 | 0.6026 | 0.6822 | 0.6817 | | 0.5677 | 42.71 | 8200 | 0.5987 | 0.6823 | 0.6839 | | 0.5722 | 43.75 | 8400 | 0.6011 | 0.6791 | 0.6790 | | 0.5724 | 44.79 | 8600 | 0.6043 | 0.6802 | 0.6794 | | 0.5693 | 45.83 | 8800 | 0.6004 | 0.6787 | 0.6790 | | 0.5691 | 46.88 | 9000 | 0.6061 | 0.6801 | 0.6790 | | 0.5712 | 47.92 | 9200 | 0.6039 | 0.6823 | 0.6817 | | 0.57 | 48.96 | 9400 | 0.6020 | 0.6817 | 0.6817 | | 0.5704 | 50.0 | 9600 | 0.6028 | 0.6806 | 0.6804 | | 0.5707 | 51.04 | 9800 | 0.6033 | 0.6824 | 0.6820 | | 0.5682 | 52.08 | 10000 | 0.6036 | 0.6815 | 0.6810 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_8192_512_30M", "model-index": [{"name": "GUE_EMP_H3K4me2-seqsight_8192_512_30M-L1_f", "results": []}]}

mahdibaghbanzadeh/GUE_EMP_H3K4me2-seqsight_8192_512_30M-L1_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_8192_512_30M", "region:us" ]

null

2024-04-27T02:46:12+00:00

[]

TAGS #peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us

GUE\_EMP\_H3K4me2-seqsight\_8192\_512\_30M-L1\_f ================================================ This model is a fine-tuned version of mahdibaghbanzadeh/seqsight\_8192\_512\_30M on the mahdibaghbanzadeh/GUE\_EMP\_H3K4me2 dataset. It achieves the following results on the evaluation set: * Loss: 0.5958 * F1 Score: 0.6738 * Accuracy: 0.6755 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0005 * train\_batch\_size: 128 * eval\_batch\_size: 128 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * training\_steps: 10000 ### Training results ### Framework versions * PEFT 0.9.0 * Transformers 4.38.2 * Pytorch 2.2.0+cu121 * Datasets 2.17.1 * Tokenizers 0.15.2

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_8192_512_30M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

text2text-generation

transformers

### Using .generate() ```python from transformers import GenerationConfig, T5ForConditionalGeneration, T5Tokenizer model_name = "cu-kairos/propbank_srl_seq2seq_t5_small" model = T5ForConditionalGeneration.from_pretrained(model_name) tokenizer = T5Tokenizer.from_pretrained(model_name) generation_config = GenerationConfig.from_pretrained(model_name) tokenized_inputs = tokenizer(["SRL for [put]: That fund was [put] together by Blackstone Group ."], return_tensors="pt") outputs = model.generate(**tokenized_inputs, generation_config=generation_config) print(tokenizer.batch_decode(outputs, skip_special_tokens=True)) # ['ARG-1: That fund | ARG-2: together | ARG-0: by Blackstone Group '] ``` ### Using pipeline ```python from transformers import pipeline srl = pipeline("cu-kairos/propbank_srl_seq2seq_t5_small") print(srl(["SRL for [put]: That fund was [put] together by Blackstone Group ."])) # [{'generated_text': 'ARG-1: That fund | ARG-2: together | ARG-0: by Blackstone Group '}] ```

{"license": "apache-2.0"}

cu-kairos/propbank_srl_seq2seq_t5_small

null

[ "transformers", "safetensors", "t5", "text2text-generation", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

null

2024-04-27T02:46:48+00:00

[]

TAGS #transformers #safetensors #t5 #text2text-generation #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

### Using .generate() ### Using pipeline

[ "### Using .generate()", "### Using pipeline" ]

[ "TAGS\n#transformers #safetensors #t5 #text2text-generation #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "### Using .generate()", "### Using pipeline" ]