Split (1)

train · 320k rows

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 listlengths 1 1.84k	sha null	created_at stringlengths 25 25	arxiv listlengths 0 201	languages listlengths 0 1.83k	tags_str stringlengths 17 9.34k	text_str stringlengths 0 389k	text_lists listlengths 0 722	processed_texts listlengths 1 723
token-classification	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": []}	AwesomeREK/concept-extraction-xlnet-reduced-distant-early-stopping	null	[ "transformers", "safetensors", "xlnet", "token-classification", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-12T06:01:07+00:00	[ "1910.09700" ]	[]	TAGS #transformers #safetensors #xlnet #token-classification #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 #xlnet #token-classification #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" ]
question-answering	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. --> # distilbert_base This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 5.8038 ## 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: 3 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| No log \| 1.0 \| 3 \| 5.8777 \| \| No log \| 2.0 \| 6 \| 5.8242 \| \| No log \| 3.0 \| 9 \| 5.8038 \| ### Framework versions - Transformers 4.38.2 - Pytorch 2.2.1+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2	{"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "distilbert-base-uncased", "model-index": [{"name": "distilbert_base", "results": []}]}	KarthikAlagarsamy/distilbert_base	null	[ "transformers", "tensorboard", "safetensors", "distilbert", "question-answering", "generated_from_trainer", "base_model:distilbert-base-uncased", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2024-04-12T06:01:16+00:00	[]	[]	TAGS #transformers #tensorboard #safetensors #distilbert #question-answering #generated_from_trainer #base_model-distilbert-base-uncased #license-apache-2.0 #endpoints_compatible #region-us	distilbert\_base ================ This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set: * Loss: 5.8038 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: 3 ### Training results ### Framework versions * Transformers 4.38.2 * Pytorch 2.2.1+cu121 * Datasets 2.18.0 * Tokenizers 0.15.2	[ "### 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: 3", "### Training results", "### Framework versions\n\n\n* Transformers 4.38.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2" ]	[ "TAGS\n#transformers #tensorboard #safetensors #distilbert #question-answering #generated_from_trainer #base_model-distilbert-base-uncased #license-apache-2.0 #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: 3", "### Training results", "### Framework versions\n\n\n* Transformers 4.38.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2" ]
feature-extraction	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": []}	Juniplayground/juniper-all-mpnet-base-v2-v9	null	[ "transformers", "safetensors", "mpnet", "feature-extraction", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-04-12T06:01:41+00:00	[ "1910.09700" ]	[]	TAGS #transformers #safetensors #mpnet #feature-extraction #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 #mpnet #feature-extraction #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. --> # dpo_anthropic_hh_gamma0.1_beta0.1_subset20000_modelmistral7b_maxsteps1200_bz32_lr1e-06 This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) 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: 1e-06 - train_batch_size: 1 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 32 - total_train_batch_size: 32 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 150 - training_steps: 1200 ### Training results ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.15.2	{"license": "apache-2.0", "library_name": "peft", "tags": ["trl", "dpo", "generated_from_trainer"], "base_model": "mistralai/Mistral-7B-v0.1", "model-index": [{"name": "dpo_anthropic_hh_gamma0.1_beta0.1_subset20000_modelmistral7b_maxsteps1200_bz32_lr1e-06", "results": []}]}	Holarissun/dpo_anthropic_hh_gamma0.1_beta0.1_subset20000_modelmistral7b_maxsteps1200_bz32_lr1e-06	null	[ "peft", "safetensors", "trl", "dpo", "generated_from_trainer", "base_model:mistralai/Mistral-7B-v0.1", "license:apache-2.0", "region:us" ]	null	2024-04-12T06:03:30+00:00	[]	[]	TAGS #peft #safetensors #trl #dpo #generated_from_trainer #base_model-mistralai/Mistral-7B-v0.1 #license-apache-2.0 #region-us	# dpo_anthropic_hh_gamma0.1_beta0.1_subset20000_modelmistral7b_maxsteps1200_bz32_lr1e-06 This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 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: 1e-06 - train_batch_size: 1 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 32 - total_train_batch_size: 32 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 150 - training_steps: 1200 ### Training results ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.15.2	[ "# dpo_anthropic_hh_gamma0.1_beta0.1_subset20000_modelmistral7b_maxsteps1200_bz32_lr1e-06\n\nThis model is a fine-tuned version of mistralai/Mistral-7B-v0.1 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: 1e-06\n- train_batch_size: 1\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 32\n- total_train_batch_size: 32\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- lr_scheduler_warmup_steps: 150\n- training_steps: 1200", "### Training results", "### Framework versions\n\n- PEFT 0.9.0\n- Transformers 4.38.2\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]	[ "TAGS\n#peft #safetensors #trl #dpo #generated_from_trainer #base_model-mistralai/Mistral-7B-v0.1 #license-apache-2.0 #region-us \n", "# dpo_anthropic_hh_gamma0.1_beta0.1_subset20000_modelmistral7b_maxsteps1200_bz32_lr1e-06\n\nThis model is a fine-tuned version of mistralai/Mistral-7B-v0.1 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: 1e-06\n- train_batch_size: 1\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 32\n- total_train_batch_size: 32\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- lr_scheduler_warmup_steps: 150\n- training_steps: 1200", "### Training results", "### Framework versions\n\n- PEFT 0.9.0\n- Transformers 4.38.2\n- Pytorch 2.1.2\n- Datasets 2.18.0\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. --> # Palate-classifier-with-ratings This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.5897 - Accuracy: 0.4006 - Recall: 0.4006 - Precision: 0.4006 - F1: 0.4006 ## 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: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3.0 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| Recall \| Precision \| F1 \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:------:\|:---------:\|:------:\| \| 1.4528 \| 1.0 \| 5000 \| 1.4438 \| 0.3867 \| 0.3867 \| 0.3867 \| 0.3867 \| \| 1.2881 \| 2.0 \| 10000 \| 1.4323 \| 0.4071 \| 0.4071 \| 0.4071 \| 0.4071 \| \| 0.993 \| 3.0 \| 15000 \| 1.5897 \| 0.4006 \| 0.4006 \| 0.4006 \| 0.4006 \| ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.15.2	{"license": "apache-2.0", "tags": ["generated_from_trainer"], "metrics": ["accuracy", "recall", "precision", "f1"], "base_model": "google-bert/bert-base-uncased", "model-index": [{"name": "Palate-classifier-with-ratings", "results": []}]}	lengocquangLAB/Palate-classifier-with-ratings	null	[ "transformers", "tensorboard", "safetensors", "bert", "text-classification", "generated_from_trainer", "base_model:google-bert/bert-base-uncased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-12T06:03:32+00:00	[]	[]	TAGS #transformers #tensorboard #safetensors #bert #text-classification #generated_from_trainer #base_model-google-bert/bert-base-uncased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us	Palate-classifier-with-ratings ============================== This model is a fine-tuned version of google-bert/bert-base-uncased on the None dataset. It achieves the following results on the evaluation set: * Loss: 1.5897 * Accuracy: 0.4006 * Recall: 0.4006 * Precision: 0.4006 * F1: 0.4006 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: 8 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * num\_epochs: 3.0 ### Training results ### Framework versions * Transformers 4.39.3 * Pytorch 2.1.2 * Datasets 2.18.0 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 8\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: 3.0", "### Training results", "### Framework versions\n\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 #bert #text-classification #generated_from_trainer #base_model-google-bert/bert-base-uncased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 8\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: 3.0", "### Training results", "### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.1.2\n* Datasets 2.18.0\n* Tokenizers 0.15.2" ]
null	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. --> # PolizzeDonut-ChangeRequest-imm5epochs-434img This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on the imagefolder 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: 2e-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: 5 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.38.2 - Pytorch 2.2.2+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2	{"license": "mit", "tags": ["generated_from_trainer"], "datasets": ["imagefolder"], "base_model": "naver-clova-ix/donut-base", "model-index": [{"name": "PolizzeDonut-ChangeRequest-imm5epochs-434img", "results": []}]}	tedad09/PolizzeDonut-ChangeRequest-imm5epochs-434img	null	[ "transformers", "tensorboard", "safetensors", "vision-encoder-decoder", "generated_from_trainer", "dataset:imagefolder", "base_model:naver-clova-ix/donut-base", "license:mit", "endpoints_compatible", "region:us" ]	null	2024-04-12T06:04:23+00:00	[]	[]	TAGS #transformers #tensorboard #safetensors #vision-encoder-decoder #generated_from_trainer #dataset-imagefolder #base_model-naver-clova-ix/donut-base #license-mit #endpoints_compatible #region-us	# PolizzeDonut-ChangeRequest-imm5epochs-434img This model is a fine-tuned version of naver-clova-ix/donut-base on the imagefolder 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: 2e-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: 5 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.38.2 - Pytorch 2.2.2+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2	[ "# PolizzeDonut-ChangeRequest-imm5epochs-434img\n\nThis model is a fine-tuned version of naver-clova-ix/donut-base on the imagefolder 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: 2e-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: 5\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.38.2\n- Pytorch 2.2.2+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]	[ "TAGS\n#transformers #tensorboard #safetensors #vision-encoder-decoder #generated_from_trainer #dataset-imagefolder #base_model-naver-clova-ix/donut-base #license-mit #endpoints_compatible #region-us \n", "# PolizzeDonut-ChangeRequest-imm5epochs-434img\n\nThis model is a fine-tuned version of naver-clova-ix/donut-base on the imagefolder 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: 2e-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: 5\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.38.2\n- Pytorch 2.2.2+cu121\n- Datasets 2.18.0\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": []}	fangzhaoz/mistralv1_spectral_r24_1e4_merged	null	[ "transformers", "safetensors", "mistral", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-12T06:05:49+00:00	[ "1910.09700" ]	[]	TAGS #transformers #safetensors #mistral #text-generation #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 #mistral #text-generation #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	# 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": []}	0x0mom/st_1	null	[ "transformers", "safetensors", "stablelm", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-12T06:06:34+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" ]
reinforcement-learning	stable-baselines3	# DQN Agent playing SpaceInvadersNoFrameskip-v4 This is a trained model of a DQN agent playing SpaceInvadersNoFrameskip-v4 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3) and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo). The RL Zoo is a training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included. ## Usage (with SB3 RL Zoo) RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/> SB3: https://github.com/DLR-RM/stable-baselines3<br/> SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib Install the RL Zoo (with SB3 and SB3-Contrib): ```bash pip install rl_zoo3 ``` ``` # Download model and save it into the logs/ folder python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga Jyothishwar -f logs/ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ ``` If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do: ``` python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga Jyothishwar -f logs/ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ ``` ## Training (with the RL Zoo) ``` python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ # Upload the model and generate video (when possible) python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga Jyothishwar ``` ## Hyperparameters ```python OrderedDict([('batch_size', 32), ('buffer_size', 100000), ('env_wrapper', ['stable_baselines3.common.atari_wrappers.AtariWrapper']), ('exploration_final_eps', 0.01), ('exploration_fraction', 0.1), ('frame_stack', 4), ('gradient_steps', 1), ('learning_rate', 0.0001), ('learning_starts', 100000), ('n_timesteps', 10000000.0), ('optimize_memory_usage', True), ('policy', 'CnnPolicy'), ('target_update_interval', 1000), ('train_freq', 4), ('normalize', False)]) ``` # Environment Arguments ```python {'render_mode': 'rgb_array'} ```	{"library_name": "stable-baselines3", "tags": ["SpaceInvadersNoFrameskip-v4", "deep-reinforcement-learning", "reinforcement-learning", "stable-baselines3"], "model-index": [{"name": "DQN", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "SpaceInvadersNoFrameskip-v4", "type": "SpaceInvadersNoFrameskip-v4"}, "metrics": [{"type": "mean_reward", "value": "739.00 +/- 329.93", "name": "mean_reward", "verified": false}]}]}]}	Jyothishwar/dqn-SpaceInvadersNoFrameskip-v4	null	[ "stable-baselines3", "SpaceInvadersNoFrameskip-v4", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	null	2024-04-12T06:10:45+00:00	[]	[]	TAGS #stable-baselines3 #SpaceInvadersNoFrameskip-v4 #deep-reinforcement-learning #reinforcement-learning #model-index #region-us	# DQN Agent playing SpaceInvadersNoFrameskip-v4 This is a trained model of a DQN agent playing SpaceInvadersNoFrameskip-v4 using the stable-baselines3 library and the RL Zoo. The RL Zoo is a training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included. ## Usage (with SB3 RL Zoo) RL Zoo: URL SB3: URL SB3 Contrib: URL Install the RL Zoo (with SB3 and SB3-Contrib): If you installed the RL Zoo3 via pip ('pip install rl_zoo3'), from anywhere you can do: ## Training (with the RL Zoo) ## Hyperparameters # Environment Arguments	[ "# DQN Agent playing SpaceInvadersNoFrameskip-v4\nThis is a trained model of a DQN agent playing SpaceInvadersNoFrameskip-v4\nusing the stable-baselines3 library\nand the RL Zoo.\n\nThe RL Zoo is a training framework for Stable Baselines3\nreinforcement learning agents,\nwith hyperparameter optimization and pre-trained agents included.", "## Usage (with SB3 RL Zoo)\n\nRL Zoo: URL\nSB3: URL\nSB3 Contrib: URL\n\nInstall the RL Zoo (with SB3 and SB3-Contrib):\n\n\n\n\nIf you installed the RL Zoo3 via pip ('pip install rl_zoo3'), from anywhere you can do:", "## Training (with the RL Zoo)", "## Hyperparameters", "# Environment Arguments" ]	[ "TAGS\n#stable-baselines3 #SpaceInvadersNoFrameskip-v4 #deep-reinforcement-learning #reinforcement-learning #model-index #region-us \n", "# DQN Agent playing SpaceInvadersNoFrameskip-v4\nThis is a trained model of a DQN agent playing SpaceInvadersNoFrameskip-v4\nusing the stable-baselines3 library\nand the RL Zoo.\n\nThe RL Zoo is a training framework for Stable Baselines3\nreinforcement learning agents,\nwith hyperparameter optimization and pre-trained agents included.", "## Usage (with SB3 RL Zoo)\n\nRL Zoo: URL\nSB3: URL\nSB3 Contrib: URL\n\nInstall the RL Zoo (with SB3 and SB3-Contrib):\n\n\n\n\nIf you installed the RL Zoo3 via pip ('pip install rl_zoo3'), from anywhere you can do:", "## Training (with the RL Zoo)", "## Hyperparameters", "# Environment Arguments" ]
automatic-speech-recognition	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. --> # idiotDeveloper/KoreanTelephone_Mini_dataset_Model This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the KoreanTelephone_Mini_dataset 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: 1e-05 - train_batch_size: 32 - 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_steps: 500 - training_steps: 10 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.40.0.dev0 - Pytorch 1.10.1+cu111 - Datasets 2.18.0 - Tokenizers 0.15.2	{"language": ["ko"], "license": "apache-2.0", "tags": ["hf-asr-leaderboard", "generated_from_trainer"], "datasets": ["idiotDeveloper/KoreanTelephone_Mini_dataset"], "base_model": "openai/whisper-base", "model-index": [{"name": "idiotDeveloper/KoreanTelephone_Mini_dataset_Model", "results": []}]}	idiotDeveloper/KoreanTelephone_Mini_dataset_Model	null	[ "transformers", "tensorboard", "safetensors", "whisper", "automatic-speech-recognition", "hf-asr-leaderboard", "generated_from_trainer", "ko", "dataset:idiotDeveloper/KoreanTelephone_Mini_dataset", "base_model:openai/whisper-base", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2024-04-12T06:10:51+00:00	[]	[ "ko" ]	TAGS #transformers #tensorboard #safetensors #whisper #automatic-speech-recognition #hf-asr-leaderboard #generated_from_trainer #ko #dataset-idiotDeveloper/KoreanTelephone_Mini_dataset #base_model-openai/whisper-base #license-apache-2.0 #endpoints_compatible #region-us	# idiotDeveloper/KoreanTelephone_Mini_dataset_Model This model is a fine-tuned version of openai/whisper-base on the KoreanTelephone_Mini_dataset 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: 1e-05 - train_batch_size: 32 - 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_steps: 500 - training_steps: 10 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.40.0.dev0 - Pytorch 1.10.1+cu111 - Datasets 2.18.0 - Tokenizers 0.15.2	[ "# idiotDeveloper/KoreanTelephone_Mini_dataset_Model\n\nThis model is a fine-tuned version of openai/whisper-base on the KoreanTelephone_Mini_dataset 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: 1e-05\n- train_batch_size: 32\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_steps: 500\n- training_steps: 10\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.40.0.dev0\n- Pytorch 1.10.1+cu111\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]	[ "TAGS\n#transformers #tensorboard #safetensors #whisper #automatic-speech-recognition #hf-asr-leaderboard #generated_from_trainer #ko #dataset-idiotDeveloper/KoreanTelephone_Mini_dataset #base_model-openai/whisper-base #license-apache-2.0 #endpoints_compatible #region-us \n", "# idiotDeveloper/KoreanTelephone_Mini_dataset_Model\n\nThis model is a fine-tuned version of openai/whisper-base on the KoreanTelephone_Mini_dataset 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: 1e-05\n- train_batch_size: 32\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_steps: 500\n- training_steps: 10\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.40.0.dev0\n- Pytorch 1.10.1+cu111\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]
text-to-audio	audiocraft	# Model Card for musicgen-songstarter-v0.2 [![Replicate demo and cloud API](https://replicate.com/nateraw/musicgen-songstarter-v0.2/badge)](https://replicate.com/nateraw/musicgen-songstarter-v0.2) [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/gist/nateraw/0cb4c242b70af10044e9ae73f4617c86/songstarter-v0-2-demo.ipynb) [![Open in Spaces](https://huggingface.co/datasets/huggingface/badges/resolve/main/open-in-hf-spaces-sm.svg)](https://huggingface.co/spaces/nateraw/singing-songstarter) musicgen-songstarter-v0.2 is a [`musicgen-stereo-melody-large`](https://huggingface.co/facebook/musicgen-stereo-melody-large) fine-tuned on a dataset of melody loops from my Splice sample library. It's intended to be used to generate song ideas that are useful for music producers. It generates stereo audio in 32khz. Compared to [`musicgen-songstarter-v0.1`](https://huggingface.co/nateraw/musicgen-songstarter-v0.1), this new version: - was trained on 3x more unique, manually-curated samples that I painstakingly purchased on Splice - Is twice the size, bumped up from size `medium` ➡️ `large` transformer LM If you find this model interesting, please consider: - following me on [GitHub](https://github.com/nateraw) - following me on [Twitter](https://twitter.com/_nateraw) ## Usage Install [audiocraft](https://github.com/facebookresearch/audiocraft): ``` pip install -U git+https://github.com/facebookresearch/audiocraft#egg=audiocraft ``` Then, you should be able to load this model just like any other musicgen checkpoint here on the Hub: ```python import torchaudio from audiocraft.models import MusicGen from audiocraft.data.audio import audio_write model = MusicGen.get_pretrained('nateraw/musicgen-songstarter-v0.2') model.set_generation_params(duration=8) # generate 8 seconds. wav = model.generate_unconditional(4) # generates 4 unconditional audio samples descriptions = ['acoustic, guitar, melody, trap, d minor, 90 bpm'] * 3 wav = model.generate(descriptions) # generates 3 samples. melody, sr = torchaudio.load('./assets/bach.mp3') # generates using the melody from the given audio and the provided descriptions. wav = model.generate_with_chroma(descriptions, melody[None].expand(3, -1, -1), sr) for idx, one_wav in enumerate(wav): # Will save under {idx}.wav, with loudness normalization at -14 db LUFS. audio_write(f'{idx}', one_wav.cpu(), model.sample_rate, strategy="loudness", loudness_compressor=True) ``` ## Prompt Format Follow the following prompt format: ``` {tag_1}, {tag_1}, ..., {tag_n}, {key}, {bpm} bpm ``` For example: ``` hip hop, soul, piano, chords, jazz, neo jazz, G# minor, 140 bpm ``` ## Samples <table style="width:100%; text-align:center;"> <tr> <th>Audio Prompt</th> <th>Text Prompt</th> <th>Output</th> </tr> <tr> <td> <audio controls> <source src="https://huggingface.co/nateraw/musicgen-songstarter-v0.2/resolve/main/assets/kalhonaho.wav?download=true" type="audio/wav"> Your browser does not support the audio element. </audio> </td> <td> trap, synthesizer, songstarters, dark, G# minor, 140 bpm </td> <td> <audio controls> <source src="https://huggingface.co/nateraw/musicgen-songstarter-v0.2/resolve/main/assets/kalhonaho_trap.wav?download=true" type="audio/wav"> Your browser does not support the audio element. </audio> </td> </tr> <tr> <td> <audio controls> <source src="https://huggingface.co/nateraw/musicgen-songstarter-v0.2/resolve/main/assets/bach.mp3?download=true" type="audio/mp3"> Your browser does not support the audio element. </audio> </td> <td> acoustic, guitar, melody, trap, D minor, 90 bpm </td> <td> <audio controls> <source src="https://huggingface.co/nateraw/musicgen-songstarter-v0.2/resolve/main/assets/bach_guitar.wav?download=true" type="audio/wav"> Your browser does not support the audio element. </audio> </td> </tr> </table> ## Acknowledgements This work would not have been possible without: - [Lambda Labs](https://lambdalabs.com/), for subsidizing larger training runs by providing some compute credits - [Replicate](https://replicate.com/), for early development compute resources Thank you ❤️	{"language": "en", "license": "cc-by-nc-4.0", "library_name": "audiocraft", "tags": ["text-to-audio", "musicgen", "songstarter"], "pipeline_tag": "text-to-audio"}	nateraw/musicgen-songstarter-v0.2	null	[ "audiocraft", "text-to-audio", "musicgen", "songstarter", "en", "license:cc-by-nc-4.0", "has_space", "region:us" ]	null	2024-04-12T06:13:05+00:00	[]	[ "en" ]	TAGS #audiocraft #text-to-audio #musicgen #songstarter #en #license-cc-by-nc-4.0 #has_space #region-us	# Model Card for musicgen-songstarter-v0.2 ![Replicate demo and cloud API](URL ![Open In Colab](URL ![Open in Spaces](URL musicgen-songstarter-v0.2 is a 'musicgen-stereo-melody-large' fine-tuned on a dataset of melody loops from my Splice sample library. It's intended to be used to generate song ideas that are useful for music producers. It generates stereo audio in 32khz. Compared to 'musicgen-songstarter-v0.1', this new version: - was trained on 3x more unique, manually-curated samples that I painstakingly purchased on Splice - Is twice the size, bumped up from size 'medium' ️ 'large' transformer LM If you find this model interesting, please consider: - following me on GitHub - following me on Twitter ## Usage Install audiocraft: Then, you should be able to load this model just like any other musicgen checkpoint here on the Hub: ## Prompt Format Follow the following prompt format: For example: ## Samples <table style="width:100%; text-align:center;"> <tr> <th>Audio Prompt</th> <th>Text Prompt</th> <th>Output</th> </tr> <tr> <td> <audio controls> <source src="URL type="audio/wav"> Your browser does not support the audio element. </audio> </td> <td> trap, synthesizer, songstarters, dark, G# minor, 140 bpm </td> <td> <audio controls> <source src="URL type="audio/wav"> Your browser does not support the audio element. </audio> </td> </tr> <tr> <td> <audio controls> <source src="URL type="audio/mp3"> Your browser does not support the audio element. </audio> </td> <td> acoustic, guitar, melody, trap, D minor, 90 bpm </td> <td> <audio controls> <source src="URL type="audio/wav"> Your browser does not support the audio element. </audio> </td> </tr> </table> ## Acknowledgements This work would not have been possible without: - Lambda Labs, for subsidizing larger training runs by providing some compute credits - Replicate, for early development compute resources Thank you ️	[ "# Model Card for musicgen-songstarter-v0.2\n\n![Replicate demo and cloud API](URL ![Open In Colab](URL ![Open in Spaces](URL\n\nmusicgen-songstarter-v0.2 is a 'musicgen-stereo-melody-large' fine-tuned on a dataset of melody loops from my Splice sample library. It's intended to be used to generate song ideas that are useful for music producers. It generates stereo audio in 32khz.\n\nCompared to 'musicgen-songstarter-v0.1', this new version:\n- was trained on 3x more unique, manually-curated samples that I painstakingly purchased on Splice\n- Is twice the size, bumped up from size 'medium' ️ 'large' transformer LM\n\nIf you find this model interesting, please consider:\n - following me on GitHub\n - following me on Twitter", "## Usage\n\nInstall audiocraft:\n\n\n\nThen, you should be able to load this model just like any other musicgen checkpoint here on the Hub:", "## Prompt Format\n\nFollow the following prompt format:\n\n\n\nFor example:", "## Samples\n\n<table style=\"width:100%; text-align:center;\">\n <tr>\n <th>Audio Prompt</th>\n <th>Text Prompt</th>\n <th>Output</th>\n </tr>\n <tr>\n <td>\n <audio controls>\n <source src=\"URL type=\"audio/wav\">\n Your browser does not support the audio element.\n </audio>\n </td>\n <td>\n trap, synthesizer, songstarters, dark, G# minor, 140 bpm\n </td>\n <td>\n <audio controls>\n <source src=\"URL type=\"audio/wav\">\n Your browser does not support the audio element.\n </audio>\n </td>\n </tr>\n <tr>\n <td>\n <audio controls>\n <source src=\"URL type=\"audio/mp3\">\n Your browser does not support the audio element.\n </audio>\n </td>\n <td>\n acoustic, guitar, melody, trap, D minor, 90 bpm\n </td>\n <td>\n <audio controls>\n <source src=\"URL type=\"audio/wav\">\n Your browser does not support the audio element.\n </audio>\n </td>\n </tr>\n</table>", "## Acknowledgements\n\nThis work would not have been possible without:\n\n- Lambda Labs, for subsidizing larger training runs by providing some compute credits\n- Replicate, for early development compute resources\n\nThank you ️" ]	[ "TAGS\n#audiocraft #text-to-audio #musicgen #songstarter #en #license-cc-by-nc-4.0 #has_space #region-us \n", "# Model Card for musicgen-songstarter-v0.2\n\n![Replicate demo and cloud API](URL ![Open In Colab](URL ![Open in Spaces](URL\n\nmusicgen-songstarter-v0.2 is a 'musicgen-stereo-melody-large' fine-tuned on a dataset of melody loops from my Splice sample library. It's intended to be used to generate song ideas that are useful for music producers. It generates stereo audio in 32khz.\n\nCompared to 'musicgen-songstarter-v0.1', this new version:\n- was trained on 3x more unique, manually-curated samples that I painstakingly purchased on Splice\n- Is twice the size, bumped up from size 'medium' ️ 'large' transformer LM\n\nIf you find this model interesting, please consider:\n - following me on GitHub\n - following me on Twitter", "## Usage\n\nInstall audiocraft:\n\n\n\nThen, you should be able to load this model just like any other musicgen checkpoint here on the Hub:", "## Prompt Format\n\nFollow the following prompt format:\n\n\n\nFor example:", "## Samples\n\n<table style=\"width:100%; text-align:center;\">\n <tr>\n <th>Audio Prompt</th>\n <th>Text Prompt</th>\n <th>Output</th>\n </tr>\n <tr>\n <td>\n <audio controls>\n <source src=\"URL type=\"audio/wav\">\n Your browser does not support the audio element.\n </audio>\n </td>\n <td>\n trap, synthesizer, songstarters, dark, G# minor, 140 bpm\n </td>\n <td>\n <audio controls>\n <source src=\"URL type=\"audio/wav\">\n Your browser does not support the audio element.\n </audio>\n </td>\n </tr>\n <tr>\n <td>\n <audio controls>\n <source src=\"URL type=\"audio/mp3\">\n Your browser does not support the audio element.\n </audio>\n </td>\n <td>\n acoustic, guitar, melody, trap, D minor, 90 bpm\n </td>\n <td>\n <audio controls>\n <source src=\"URL type=\"audio/wav\">\n Your browser does not support the audio element.\n </audio>\n </td>\n </tr>\n</table>", "## Acknowledgements\n\nThis work would not have been possible without:\n\n- Lambda Labs, for subsidizing larger training runs by providing some compute credits\n- Replicate, for early development compute resources\n\nThank you ️" ]
reinforcement-learning	null	# PPO Agent Playing LunarLander-v2 This is a trained model of a PPO agent playing LunarLander-v2. # Hyperparameters ```python {'exp_name': 'ppo' 'seed': 1 'torch_deterministic': True 'cuda': True 'track': False 'wandb_project_name': 'cleanRL' 'wandb_entity': None 'capture_video': False 'env_id': 'LunarLander-v2' 'total_timesteps': 50000 'learning_rate': 0.00025 'num_envs': 4 'num_steps': 128 'anneal_lr': True 'gae': True 'gamma': 0.99 'gae_lambda': 0.95 'num_minibatches': 4 'update_epochs': 4 'norm_adv': True 'clip_coef': 0.2 'clip_vloss': True 'ent_coef': 0.01 'vf_coef': 0.5 'max_grad_norm': 0.5 'target_kl': None 'repo_id': 'OscarGalavizC/LunarLander-v2' 'batch_size': 512 'minibatch_size': 128} ```	{"tags": ["LunarLander-v2", "ppo", "deep-reinforcement-learning", "reinforcement-learning", "custom-implementation", "deep-rl-course"], "model-index": [{"name": "PPO", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "LunarLander-v2", "type": "LunarLander-v2"}, "metrics": [{"type": "mean_reward", "value": "-174.34 +/- 98.68", "name": "mean_reward", "verified": false}]}]}]}	OscarGalavizC/LunarLander-v2	null	[ "tensorboard", "LunarLander-v2", "ppo", "deep-reinforcement-learning", "reinforcement-learning", "custom-implementation", "deep-rl-course", "model-index", "region:us" ]	null	2024-04-12T06:13:24+00:00	[]	[]	TAGS #tensorboard #LunarLander-v2 #ppo #deep-reinforcement-learning #reinforcement-learning #custom-implementation #deep-rl-course #model-index #region-us	# PPO Agent Playing LunarLander-v2 This is a trained model of a PPO agent playing LunarLander-v2. # Hyperparameters	[ "# PPO Agent Playing LunarLander-v2\n\n This is a trained model of a PPO agent playing LunarLander-v2.\n \n # Hyperparameters" ]	[ "TAGS\n#tensorboard #LunarLander-v2 #ppo #deep-reinforcement-learning #reinforcement-learning #custom-implementation #deep-rl-course #model-index #region-us \n", "# PPO Agent Playing LunarLander-v2\n\n This is a trained model of a PPO agent playing LunarLander-v2.\n \n # Hyperparameters" ]
text-generation	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. --> # eu-ai-act-align This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on over 1000 questions and answers surrounding the EU AI Act. It achieves the following results on the evaluation set: - Loss: 1.7628 ## Model description EU AI Act Model ORCAWISE CONTRIBUTORS: Ikechukwu Ogbuchi, Yu Li, Dami Akinniranye, Wahab Adesanya, Sanpreet Singh, Kevin Neary OVERVIEW: The EU AI Act Model, powered by GEMMA, is a specialized language model designed to provide expert-level insights and guidance on the European Union's Artificial Intelligence Act. This model has been meticulously fine-tuned using a dataset of 1,000 rigorously curated questions and answers pertaining to various aspects of the AI Act. It aims to serve as a reliable resource for legal and compliance professionals, aiding organizations in understanding and adhering to the requirements set forth by the EU regulations. KEY FEATURES: Domain-Specific Expertise: Tailored to address the intricacies and legal nuances of the EU AI Act, making it an invaluable tool for stakeholders needing precise and actionable information. Compliance Assistance: Facilitates a better understanding of compliance obligations under the AI Act, helping organizations mitigate risks and avoid potential penalties. Accessible Guidance: Designed to simplify complex legal language, making the regulations accessible and understandable to professionals without a legal background. USE CASES: Legal Consultation: Assist legal professionals by providing quick answers to common questions about the EU AI Act. Compliance Strategy Development: Support compliance officers in developing and refining AI governance frameworks. Educational Tool: Serve as an educational resource for training corporate teams on the implications and requirements of the AI Act. HOW TO USE: To use the EU AI Act Model, simply input a question related to the EU AI Act, and the model will generate a response that reflects the most current understanding of the act's provisions. Example queries include: "What are the obligations for high-risk AI systems under the EU AI Act?" "How does the AI Act classify AI systems?" "What are the penalties for non-compliance with the AI Act?" MODEL TRAINING AND PERFORMANCE: The model was trained with a diverse set of questions covering all key areas of the EU AI Act, ensuring a broad and deep understanding of the subject matter. While GEMMA provides high-quality outputs, users should consider these as a starting point for further legal consultation and not as standalone legal advice. CONTRIBUTIONS AND FEEDBACK: We welcome contributions and feedback from the community to continuously improve the model's accuracy and usability. If you have suggestions or want to contribute to the training dataset, please contact us through our Huggingface repository. information needed ## Intended uses & limitations It is intended to be used as a preliminary guide to understading the Act, but detailed information about the act can be verified via official public documents. It is important that questions are framed with respect to the EU AI Act, rather than generic or non specific questions for a good model response. ## Training and evaluation data Training was done with 1023 questions and answer pairs and finetuned on the Gemma 2b model. ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 4 - eval_batch_size: 1 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 15 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| 2.139 \| 1.0 \| 230 \| 1.9804 \| \| 1.9368 \| 2.0 \| 460 \| 1.8491 \| \| 1.8613 \| 3.0 \| 690 \| 1.8011 \| \| 1.8008 \| 4.0 \| 920 \| 1.7763 \| \| 1.7447 \| 5.0 \| 1150 \| 1.7634 \| \| 1.6942 \| 6.0 \| 1380 \| 1.7563 \| \| 1.6558 \| 7.0 \| 1610 \| 1.7513 \| \| 1.6192 \| 8.0 \| 1840 \| 1.7446 \| \| 1.5782 \| 9.0 \| 2070 \| 1.7573 \| \| 1.5463 \| 10.0 \| 2300 \| 1.7628 \| ### Framework versions - PEFT 0.10.0 - Transformers 4.39.3 - Pytorch 2.2.1+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2	{"license": "gemma", "library_name": "peft", "tags": ["trl", "sft", "generated_from_trainer"], "base_model": "google/gemma-2b", "pipeline_tag": "text-generation", "model-index": [{"name": "eu-ai-act-align", "results": []}]}	Orcawise/eu-ai-act-align	null	[ "peft", "tensorboard", "safetensors", "gemma", "trl", "sft", "generated_from_trainer", "text-generation", "base_model:google/gemma-2b", "license:gemma", "4-bit", "region:us" ]	null	2024-04-12T06:13:57+00:00	[]	[]	TAGS #peft #tensorboard #safetensors #gemma #trl #sft #generated_from_trainer #text-generation #base_model-google/gemma-2b #license-gemma #4-bit #region-us	eu-ai-act-align =============== This model is a fine-tuned version of google/gemma-2b on over 1000 questions and answers surrounding the EU AI Act. It achieves the following results on the evaluation set: * Loss: 1.7628 Model description ----------------- EU AI Act Model ORCAWISE CONTRIBUTORS: Ikechukwu Ogbuchi, Yu Li, Dami Akinniranye, Wahab Adesanya, Sanpreet Singh, Kevin Neary OVERVIEW: The EU AI Act Model, powered by GEMMA, is a specialized language model designed to provide expert-level insights and guidance on the European Union's Artificial Intelligence Act. This model has been meticulously fine-tuned using a dataset of 1,000 rigorously curated questions and answers pertaining to various aspects of the AI Act. It aims to serve as a reliable resource for legal and compliance professionals, aiding organizations in understanding and adhering to the requirements set forth by the EU regulations. KEY FEATURES: Domain-Specific Expertise: Tailored to address the intricacies and legal nuances of the EU AI Act, making it an invaluable tool for stakeholders needing precise and actionable information. Compliance Assistance: Facilitates a better understanding of compliance obligations under the AI Act, helping organizations mitigate risks and avoid potential penalties. Accessible Guidance: Designed to simplify complex legal language, making the regulations accessible and understandable to professionals without a legal background. USE CASES: Legal Consultation: Assist legal professionals by providing quick answers to common questions about the EU AI Act. Compliance Strategy Development: Support compliance officers in developing and refining AI governance frameworks. Educational Tool: Serve as an educational resource for training corporate teams on the implications and requirements of the AI Act. HOW TO USE: To use the EU AI Act Model, simply input a question related to the EU AI Act, and the model will generate a response that reflects the most current understanding of the act's provisions. Example queries include: "What are the obligations for high-risk AI systems under the EU AI Act?" "How does the AI Act classify AI systems?" "What are the penalties for non-compliance with the AI Act?" MODEL TRAINING AND PERFORMANCE: The model was trained with a diverse set of questions covering all key areas of the EU AI Act, ensuring a broad and deep understanding of the subject matter. While GEMMA provides high-quality outputs, users should consider these as a starting point for further legal consultation and not as standalone legal advice. CONTRIBUTIONS AND FEEDBACK: We welcome contributions and feedback from the community to continuously improve the model's accuracy and usability. If you have suggestions or want to contribute to the training dataset, please contact us through our Huggingface repository. information needed Intended uses & limitations --------------------------- It is intended to be used as a preliminary guide to understading the Act, but detailed information about the act can be verified via official public documents. It is important that questions are framed with respect to the EU AI Act, rather than generic or non specific questions for a good model response. Training and evaluation data ---------------------------- Training was done with 1023 questions and answer pairs and finetuned on the Gemma 2b model. Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0001 * train\_batch\_size: 4 * eval\_batch\_size: 1 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * num\_epochs: 15 ### Training results ### Framework versions * PEFT 0.10.0 * Transformers 4.39.3 * Pytorch 2.2.1+cu121 * Datasets 2.18.0 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0001\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 1\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 15", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.39.3\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2" ]	[ "TAGS\n#peft #tensorboard #safetensors #gemma #trl #sft #generated_from_trainer #text-generation #base_model-google/gemma-2b #license-gemma #4-bit #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0001\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 1\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 15", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.39.3\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\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. --> # my_awesome_eli5_clm-model This model is a fine-tuned version of [distilbert/distilgpt2](https://huggingface.co/distilbert/distilgpt2) on the eli5_category dataset. It achieves the following results on the evaluation set: - Loss: 3.8156 ## 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: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3.0 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| 3.9493 \| 1.0 \| 1305 \| 3.8284 \| \| 3.8542 \| 2.0 \| 2610 \| 3.8176 \| \| 3.8067 \| 3.0 \| 3915 \| 3.8156 \| ### Framework versions - Transformers 4.39.3 - Pytorch 2.2.2+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2	{"license": "apache-2.0", "tags": ["generated_from_trainer"], "datasets": ["eli5_category"], "base_model": "distilbert/distilgpt2", "model-index": [{"name": "my_awesome_eli5_clm-model", "results": []}]}	lifshort/my_awesome_eli5_clm-model	null	[ "transformers", "safetensors", "gpt2", "text-generation", "generated_from_trainer", "dataset:eli5_category", "base_model:distilbert/distilgpt2", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-12T06:14:43+00:00	[]	[]	TAGS #transformers #safetensors #gpt2 #text-generation #generated_from_trainer #dataset-eli5_category #base_model-distilbert/distilgpt2 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us	my\_awesome\_eli5\_clm-model ============================ This model is a fine-tuned version of distilbert/distilgpt2 on the eli5\_category dataset. It achieves the following results on the evaluation set: * Loss: 3.8156 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: 8 * eval\_batch\_size: 8 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * num\_epochs: 3.0 ### Training results ### Framework versions * Transformers 4.39.3 * Pytorch 2.2.2+cu121 * Datasets 2.18.0 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 8\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: 3.0", "### Training results", "### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.2.2+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2" ]	[ "TAGS\n#transformers #safetensors #gpt2 #text-generation #generated_from_trainer #dataset-eli5_category #base_model-distilbert/distilgpt2 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #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: 8\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: 3.0", "### Training results", "### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.2.2+cu121\n* Datasets 2.18.0\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. --> # Taste-classifier-with-ratings This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.4503 - Accuracy: 0.4499 - Recall: 0.4499 - Precision: 0.4499 - F1: 0.4499 ## 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: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3.0 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| Recall \| Precision \| F1 \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:------:\|:---------:\|:------:\| \| 1.3342 \| 1.0 \| 5000 \| 1.3867 \| 0.4103 \| 0.4103 \| 0.4103 \| 0.4103 \| \| 1.1525 \| 2.0 \| 10000 \| 1.3346 \| 0.4499 \| 0.4499 \| 0.4499 \| 0.4499 \| \| 0.8997 \| 3.0 \| 15000 \| 1.4503 \| 0.4499 \| 0.4499 \| 0.4499 \| 0.4499 \| ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.15.2	{"license": "apache-2.0", "tags": ["generated_from_trainer"], "metrics": ["accuracy", "recall", "precision", "f1"], "base_model": "google-bert/bert-base-uncased", "model-index": [{"name": "Taste-classifier-with-ratings", "results": []}]}	lengocquangLAB/Taste-classifier-with-ratings	null	[ "transformers", "tensorboard", "safetensors", "bert", "text-classification", "generated_from_trainer", "base_model:google-bert/bert-base-uncased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-12T06:15:28+00:00	[]	[]	TAGS #transformers #tensorboard #safetensors #bert #text-classification #generated_from_trainer #base_model-google-bert/bert-base-uncased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us	Taste-classifier-with-ratings ============================= This model is a fine-tuned version of google-bert/bert-base-uncased on the None dataset. It achieves the following results on the evaluation set: * Loss: 1.4503 * Accuracy: 0.4499 * Recall: 0.4499 * Precision: 0.4499 * F1: 0.4499 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: 8 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * num\_epochs: 3.0 ### Training results ### Framework versions * Transformers 4.39.3 * Pytorch 2.1.2 * Datasets 2.18.0 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 8\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: 3.0", "### Training results", "### Framework versions\n\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 #bert #text-classification #generated_from_trainer #base_model-google-bert/bert-base-uncased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 8\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: 3.0", "### Training results", "### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.1.2\n* Datasets 2.18.0\n* Tokenizers 0.15.2" ]
null	null	GGUF quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) gemma-1.1-2b-it - GGUF - Model creator: https://huggingface.co/google/ - Original model: https://huggingface.co/google/gemma-1.1-2b-it/ \| Name \| Quant method \| Size \| \| ---- \| ---- \| ---- \| \| [gemma-1.1-2b-it.Q2_K.gguf](https://huggingface.co/RichardErkhov/google_-_gemma-1.1-2b-it-gguf/blob/main/gemma-1.1-2b-it.Q2_K.gguf) \| Q2_K \| 1.08GB \| \| [gemma-1.1-2b-it.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/google_-_gemma-1.1-2b-it-gguf/blob/main/gemma-1.1-2b-it.IQ3_XS.gguf) \| IQ3_XS \| 1.16GB \| \| [gemma-1.1-2b-it.IQ3_S.gguf](https://huggingface.co/RichardErkhov/google_-_gemma-1.1-2b-it-gguf/blob/main/gemma-1.1-2b-it.IQ3_S.gguf) \| IQ3_S \| 1.2GB \| \| [gemma-1.1-2b-it.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/google_-_gemma-1.1-2b-it-gguf/blob/main/gemma-1.1-2b-it.Q3_K_S.gguf) \| Q3_K_S \| 1.2GB \| \| [gemma-1.1-2b-it.IQ3_M.gguf](https://huggingface.co/RichardErkhov/google_-_gemma-1.1-2b-it-gguf/blob/main/gemma-1.1-2b-it.IQ3_M.gguf) \| IQ3_M \| 1.22GB \| \| [gemma-1.1-2b-it.Q3_K.gguf](https://huggingface.co/RichardErkhov/google_-_gemma-1.1-2b-it-gguf/blob/main/gemma-1.1-2b-it.Q3_K.gguf) \| Q3_K \| 1.29GB \| \| [gemma-1.1-2b-it.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/google_-_gemma-1.1-2b-it-gguf/blob/main/gemma-1.1-2b-it.Q3_K_M.gguf) \| Q3_K_M \| 1.29GB \| \| [gemma-1.1-2b-it.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/google_-_gemma-1.1-2b-it-gguf/blob/main/gemma-1.1-2b-it.Q3_K_L.gguf) \| Q3_K_L \| 1.36GB \| \| [gemma-1.1-2b-it.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/google_-_gemma-1.1-2b-it-gguf/blob/main/gemma-1.1-2b-it.IQ4_XS.gguf) \| IQ4_XS \| 1.4GB \| \| [gemma-1.1-2b-it.Q4_0.gguf](https://huggingface.co/RichardErkhov/google_-_gemma-1.1-2b-it-gguf/blob/main/gemma-1.1-2b-it.Q4_0.gguf) \| Q4_0 \| 1.44GB \| \| [gemma-1.1-2b-it.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/google_-_gemma-1.1-2b-it-gguf/blob/main/gemma-1.1-2b-it.IQ4_NL.gguf) \| IQ4_NL \| 1.45GB \| \| [gemma-1.1-2b-it.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/google_-_gemma-1.1-2b-it-gguf/blob/main/gemma-1.1-2b-it.Q4_K_S.gguf) \| Q4_K_S \| 1.45GB \| \| [gemma-1.1-2b-it.Q4_K.gguf](https://huggingface.co/RichardErkhov/google_-_gemma-1.1-2b-it-gguf/blob/main/gemma-1.1-2b-it.Q4_K.gguf) \| Q4_K \| 1.52GB \| \| [gemma-1.1-2b-it.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/google_-_gemma-1.1-2b-it-gguf/blob/main/gemma-1.1-2b-it.Q4_K_M.gguf) \| Q4_K_M \| 1.52GB \| \| [gemma-1.1-2b-it.Q4_1.gguf](https://huggingface.co/RichardErkhov/google_-_gemma-1.1-2b-it-gguf/blob/main/gemma-1.1-2b-it.Q4_1.gguf) \| Q4_1 \| 1.56GB \| \| [gemma-1.1-2b-it.Q5_0.gguf](https://huggingface.co/RichardErkhov/google_-_gemma-1.1-2b-it-gguf/blob/main/gemma-1.1-2b-it.Q5_0.gguf) \| Q5_0 \| 1.68GB \| \| [gemma-1.1-2b-it.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/google_-_gemma-1.1-2b-it-gguf/blob/main/gemma-1.1-2b-it.Q5_K_S.gguf) \| Q5_K_S \| 1.68GB \| \| [gemma-1.1-2b-it.Q5_K.gguf](https://huggingface.co/RichardErkhov/google_-_gemma-1.1-2b-it-gguf/blob/main/gemma-1.1-2b-it.Q5_K.gguf) \| Q5_K \| 1.71GB \| \| [gemma-1.1-2b-it.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/google_-_gemma-1.1-2b-it-gguf/blob/main/gemma-1.1-2b-it.Q5_K_M.gguf) \| Q5_K_M \| 1.71GB \| \| [gemma-1.1-2b-it.Q5_1.gguf](https://huggingface.co/RichardErkhov/google_-_gemma-1.1-2b-it-gguf/blob/main/gemma-1.1-2b-it.Q5_1.gguf) \| Q5_1 \| 1.79GB \| \| [gemma-1.1-2b-it.Q6_K.gguf](https://huggingface.co/RichardErkhov/google_-_gemma-1.1-2b-it-gguf/blob/main/gemma-1.1-2b-it.Q6_K.gguf) \| Q6_K \| 1.92GB \| Original model description: Repo model google/gemma-1.1-2b-it is gated. You must be authenticated to access it.	{}	RichardErkhov/google_-_gemma-1.1-2b-it-gguf	null	[ "gguf", "region:us" ]	null	2024-04-12T06:16:34+00:00	[]	[]	TAGS #gguf #region-us	GGUF quantization made by Richard Erkhov. Github Discord Request more models gemma-1.1-2b-it - GGUF * Model creator: URL * Original model: URL Name: gemma-1.1-2b-it.Q2\_K.gguf, Quant method: Q2\_K, Size: 1.08GB Name: gemma-1.1-2b-it.IQ3\_XS.gguf, Quant method: IQ3\_XS, Size: 1.16GB Name: gemma-1.1-2b-it.IQ3\_S.gguf, Quant method: IQ3\_S, Size: 1.2GB Name: gemma-1.1-2b-it.Q3\_K\_S.gguf, Quant method: Q3\_K\_S, Size: 1.2GB Name: gemma-1.1-2b-it.IQ3\_M.gguf, Quant method: IQ3\_M, Size: 1.22GB Name: gemma-1.1-2b-it.Q3\_K.gguf, Quant method: Q3\_K, Size: 1.29GB Name: gemma-1.1-2b-it.Q3\_K\_M.gguf, Quant method: Q3\_K\_M, Size: 1.29GB Name: gemma-1.1-2b-it.Q3\_K\_L.gguf, Quant method: Q3\_K\_L, Size: 1.36GB Name: gemma-1.1-2b-it.IQ4\_XS.gguf, Quant method: IQ4\_XS, Size: 1.4GB Name: gemma-1.1-2b-it.Q4\_0.gguf, Quant method: Q4\_0, Size: 1.44GB Name: gemma-1.1-2b-it.IQ4\_NL.gguf, Quant method: IQ4\_NL, Size: 1.45GB Name: gemma-1.1-2b-it.Q4\_K\_S.gguf, Quant method: Q4\_K\_S, Size: 1.45GB Name: gemma-1.1-2b-it.Q4\_K.gguf, Quant method: Q4\_K, Size: 1.52GB Name: gemma-1.1-2b-it.Q4\_K\_M.gguf, Quant method: Q4\_K\_M, Size: 1.52GB Name: gemma-1.1-2b-it.Q4\_1.gguf, Quant method: Q4\_1, Size: 1.56GB Name: gemma-1.1-2b-it.Q5\_0.gguf, Quant method: Q5\_0, Size: 1.68GB Name: gemma-1.1-2b-it.Q5\_K\_S.gguf, Quant method: Q5\_K\_S, Size: 1.68GB Name: gemma-1.1-2b-it.Q5\_K.gguf, Quant method: Q5\_K, Size: 1.71GB Name: gemma-1.1-2b-it.Q5\_K\_M.gguf, Quant method: Q5\_K\_M, Size: 1.71GB Name: gemma-1.1-2b-it.Q5\_1.gguf, Quant method: Q5\_1, Size: 1.79GB Name: gemma-1.1-2b-it.Q6\_K.gguf, Quant method: Q6\_K, Size: 1.92GB ``` Original model description: Repo model google/gemma-1.1-2b-it is gated. You must be authenticated to access it. ```	[]	[ "TAGS\n#gguf #region-us \n" ]
text-generation	transformers	# Uploaded model - Developed by: TheHappyDrone - License: apache-2.0 - Finetuned from model : unsloth/mistral-7b-bnb-4bit This mistral 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", "mistral", "trl", "sft"], "base_model": "unsloth/mistral-7b-bnb-4bit"}	TheHappyDrone/Occult_V02	null	[ "transformers", "pytorch", "mistral", "text-generation", "text-generation-inference", "unsloth", "trl", "sft", "en", "base_model:unsloth/mistral-7b-bnb-4bit", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-12T06:24:02+00:00	[]	[ "en" ]	TAGS #transformers #pytorch #mistral #text-generation #text-generation-inference #unsloth #trl #sft #en #base_model-unsloth/mistral-7b-bnb-4bit #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us	# Uploaded model - Developed by: TheHappyDrone - License: apache-2.0 - Finetuned from model : unsloth/mistral-7b-bnb-4bit This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library. <img src="URL width="200"/>	[ "# Uploaded model\n\n- Developed by: TheHappyDrone\n- License: apache-2.0\n- Finetuned from model : unsloth/mistral-7b-bnb-4bit\n\nThis mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]	[ "TAGS\n#transformers #pytorch #mistral #text-generation #text-generation-inference #unsloth #trl #sft #en #base_model-unsloth/mistral-7b-bnb-4bit #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "# Uploaded model\n\n- Developed by: TheHappyDrone\n- License: apache-2.0\n- Finetuned from model : unsloth/mistral-7b-bnb-4bit\n\nThis mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]
reinforcement-learning	null	# Q-Learning Agent playing1 FrozenLake-v1 This is a trained model of a Q-Learning agent playing FrozenLake-v1 . ## Usage ```python model = load_from_hub(repo_id="dctwan/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl") # Don't forget to check if you need to add additional attributes (is_slippery=False etc) env = gym.make(model["env_id"]) ```	{"tags": ["FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation"], "model-index": [{"name": "q-FrozenLake-v1-4x4-noSlippery", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "FrozenLake-v1-4x4-no_slippery", "type": "FrozenLake-v1-4x4-no_slippery"}, "metrics": [{"type": "mean_reward", "value": "1.00 +/- 0.00", "name": "mean_reward", "verified": false}]}]}]}	dctwan/q-FrozenLake-v1-4x4-noSlippery	null	[ "FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]	null	2024-04-12T06:25:49+00:00	[]	[]	TAGS #FrozenLake-v1-4x4-no_slippery #q-learning #reinforcement-learning #custom-implementation #model-index #region-us	# Q-Learning Agent playing1 FrozenLake-v1 This is a trained model of a Q-Learning agent playing FrozenLake-v1 . ## Usage	[ "# Q-Learning Agent playing1 FrozenLake-v1\n This is a trained model of a Q-Learning agent playing FrozenLake-v1 .\n\n ## Usage" ]	[ "TAGS\n#FrozenLake-v1-4x4-no_slippery #q-learning #reinforcement-learning #custom-implementation #model-index #region-us \n", "# Q-Learning Agent playing1 FrozenLake-v1\n This is a trained model of a Q-Learning agent playing FrozenLake-v1 .\n\n ## Usage" ]
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": []}	PeterYang12/fine-tuning-demo	null	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-04-12T06:26:32+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	# MergerixShadowm7exp-7B MergerixShadowm7exp-7B is an automated merge created by [Maxime Labonne](https://huggingface.co/mlabonne) using the following configuration. * [MiniMoog/Mergerix-7b-v0.3](https://huggingface.co/MiniMoog/Mergerix-7b-v0.3) * [mahiatlinux/ShadowM7EXP-7B](https://huggingface.co/mahiatlinux/ShadowM7EXP-7B) ## 🧩 Configuration ```yaml slices: - sources: - model: MiniMoog/Mergerix-7b-v0.3 layer_range: [0, 32] - model: mahiatlinux/ShadowM7EXP-7B layer_range: [0, 32] merge_method: slerp base_model: MiniMoog/Mergerix-7b-v0.3 parameters: t: - filter: self_attn value: [0, 0.5, 0.3, 0.7, 1] - filter: mlp value: [1, 0.5, 0.7, 0.3, 0] - value: 0.5 dtype: bfloat16 random_seed: 0 ``` ## 💻 Usage ```python !pip install -qU transformers accelerate from transformers import AutoTokenizer import transformers import torch model = "automerger/MergerixShadowm7exp-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"], "base_model": ["MiniMoog/Mergerix-7b-v0.3", "mahiatlinux/ShadowM7EXP-7B"]}	automerger/MergerixShadowm7exp-7B	null	[ "transformers", "safetensors", "mistral", "text-generation", "merge", "mergekit", "lazymergekit", "automerger", "base_model:MiniMoog/Mergerix-7b-v0.3", "base_model:mahiatlinux/ShadowM7EXP-7B", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-12T06:29:27+00:00	[]	[]	TAGS #transformers #safetensors #mistral #text-generation #merge #mergekit #lazymergekit #automerger #base_model-MiniMoog/Mergerix-7b-v0.3 #base_model-mahiatlinux/ShadowM7EXP-7B #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us	# MergerixShadowm7exp-7B MergerixShadowm7exp-7B is an automated merge created by Maxime Labonne using the following configuration. * MiniMoog/Mergerix-7b-v0.3 * mahiatlinux/ShadowM7EXP-7B ## Configuration ## Usage	[ "# MergerixShadowm7exp-7B\n\nMergerixShadowm7exp-7B is an automated merge created by Maxime Labonne using the following configuration.\n* MiniMoog/Mergerix-7b-v0.3\n* mahiatlinux/ShadowM7EXP-7B", "## Configuration", "## Usage" ]	[ "TAGS\n#transformers #safetensors #mistral #text-generation #merge #mergekit #lazymergekit #automerger #base_model-MiniMoog/Mergerix-7b-v0.3 #base_model-mahiatlinux/ShadowM7EXP-7B #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# MergerixShadowm7exp-7B\n\nMergerixShadowm7exp-7B is an automated merge created by Maxime Labonne using the following configuration.\n* MiniMoog/Mergerix-7b-v0.3\n* mahiatlinux/ShadowM7EXP-7B", "## Configuration", "## Usage" ]
reinforcement-learning	null	# Q-Learning Agent playing1 Taxi-v3 This is a trained model of a Q-Learning agent playing Taxi-v3 . ## Usage ```python model = load_from_hub(repo_id="dctwan/Taxi_v3", filename="q-learning.pkl") # Don't forget to check if you need to add additional attributes (is_slippery=False etc) env = gym.make(model["env_id"]) ```	{"tags": ["Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation"], "model-index": [{"name": "Taxi_v3", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "Taxi-v3", "type": "Taxi-v3"}, "metrics": [{"type": "mean_reward", "value": "7.46 +/- 2.75", "name": "mean_reward", "verified": false}]}]}]}	dctwan/Taxi_v3	null	[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]	null	2024-04-12T06:30:18+00:00	[]	[]	TAGS #Taxi-v3 #q-learning #reinforcement-learning #custom-implementation #model-index #region-us	# Q-Learning Agent playing1 Taxi-v3 This is a trained model of a Q-Learning agent playing Taxi-v3 . ## Usage	[ "# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage" ]	[ "TAGS\n#Taxi-v3 #q-learning #reinforcement-learning #custom-implementation #model-index #region-us \n", "# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage" ]
text-generation	transformers	[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/llm_surgery/mistral_zephyr_orpo_v0.2?nw=nwusercapecape) # Mistral 7B Zephyr Orpo The [Zephyr Orpo](https://huggingface.co/HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1/) recipe applied on top of Mistral 7B v0.2 (new recipe with new Mistral base model) ## Model description - Model type: A 7.2B parameter GPT-like model fine-tuned on a mix of publicly available, synthetic datasets. - Language(s) (NLP): Primarily English - Finetuned from model: [wandb/Mistral-7B-v0.2](https://huggingface.co/wandb/Mistral-7B-v0.2) ## Recipe We trained using the [alignment handbook recipe](https://github.com/huggingface/alignment-handbook/blob/main/scripts/run_orpo.py) and logging to W&B Visit the [W&B workspace here](https://wandb.ai/llm_surgery/mistral_zephyr_orpo_v0.2?nw=nwusercapecape) ## Results: - MT bench ``` ########## First turn ########## score model turn zephyr-orpo-7b-v0.2 1 7.44375 ########## Second turn ########## score model turn zephyr-orpo-7b-v0.2 2 6.875 ########## Average ########## score model zephyr-orpo-7b-v0.2 7.159375 ``` ## Trained on a single H100 for 2 hours!	{"license": "mit", "library_name": "transformers", "tags": ["trl", "orpo", "generated_from_trainer"], "datasets": ["argilla/distilabel-capybara-dpo-7k-binarized"], "base_model": "wandb/Mistral-7B-v0.2"}	wandb/zephyr-orpo-7b-v0.2	null	[ "transformers", "safetensors", "mistral", "text-generation", "trl", "orpo", "generated_from_trainer", "conversational", "dataset:argilla/distilabel-capybara-dpo-7k-binarized", "base_model:wandb/Mistral-7B-v0.2", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-12T06:31:41+00:00	[]	[]	TAGS #transformers #safetensors #mistral #text-generation #trl #orpo #generated_from_trainer #conversational #dataset-argilla/distilabel-capybara-dpo-7k-binarized #base_model-wandb/Mistral-7B-v0.2 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us	<img src="URL alt="Visualize in Weights & Biases" width="200" height="32"/> # Mistral 7B Zephyr Orpo The Zephyr Orpo recipe applied on top of Mistral 7B v0.2 (new recipe with new Mistral base model) ## Model description - Model type: A 7.2B parameter GPT-like model fine-tuned on a mix of publicly available, synthetic datasets. - Language(s) (NLP): Primarily English - Finetuned from model: wandb/Mistral-7B-v0.2 ## Recipe We trained using the alignment handbook recipe and logging to W&B Visit the W&B workspace here ## Results: - MT bench ## Trained on a single H100 for 2 hours!	[ "# Mistral 7B Zephyr Orpo\n\nThe Zephyr Orpo recipe applied on top of Mistral 7B v0.2 (new recipe with new Mistral base model)", "## Model description\n\n- Model type: A 7.2B parameter GPT-like model fine-tuned on a mix of publicly available, synthetic datasets.\n- Language(s) (NLP): Primarily English\n- Finetuned from model: wandb/Mistral-7B-v0.2", "## Recipe\n\nWe trained using the alignment handbook recipe and logging to W&B\n\nVisit the W&B workspace here", "## Results:\n\n- MT bench", "## Trained on a single H100 for 2 hours!" ]	[ "TAGS\n#transformers #safetensors #mistral #text-generation #trl #orpo #generated_from_trainer #conversational #dataset-argilla/distilabel-capybara-dpo-7k-binarized #base_model-wandb/Mistral-7B-v0.2 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Mistral 7B Zephyr Orpo\n\nThe Zephyr Orpo recipe applied on top of Mistral 7B v0.2 (new recipe with new Mistral base model)", "## Model description\n\n- Model type: A 7.2B parameter GPT-like model fine-tuned on a mix of publicly available, synthetic datasets.\n- Language(s) (NLP): Primarily English\n- Finetuned from model: wandb/Mistral-7B-v0.2", "## Recipe\n\nWe trained using the alignment handbook recipe and logging to W&B\n\nVisit the W&B workspace here", "## Results:\n\n- MT bench", "## Trained on a single H100 for 2 hours!" ]
text-generation	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1). ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - 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]	{"license": "other"}	varox34/minillm-7B-init-13B-sft	null	[ "transformers", "pytorch", "llama", "text-generation", "arxiv:1910.09700", "license:other", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-12T06:33:51+00:00	[ "1910.09700" ]	[]	TAGS #transformers #pytorch #llama #text-generation #arxiv-1910.09700 #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us	# Model Card for Model ID This modelcard aims to be a base template for new models. It has been generated using this raw template. ## Model Details ### Model Description - 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\n\n\n\nThis modelcard aims to be a base template for new models. It has been generated using this raw template.", "## Model Details", "### Model Description\n\n\n\n\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 #pytorch #llama #text-generation #arxiv-1910.09700 #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID\n\n\n\nThis modelcard aims to be a base template for new models. It has been generated using this raw template.", "## Model Details", "### Model Description\n\n\n\n\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	null	O que é o creme ValGone gel? ValGone Onde comprar Creme é uma solução tópica formulada especificamente para aliviar o desconforto associado aos joanetes. Contém uma mistura de ingredientes naturais conhecidos por suas propriedades antiinflamatórias e analgésicas. Esses ingredientes atuam sinergicamente para reduzir a dor, a inflamação e o inchaço ao redor da área afetada. <p><a href="https://www.nutritionsee.com/vallgportys"> <img src="https://www.nutritionsee.com/wp-content/uploads/2024/04/ValGone-Portugal.png" alt="enter image description here"> </a></p> <a href="https://www.nutritionsee.com/vallgportys">Comprar agora!! Clique no link abaixo para mais informações e ganhe 50% de desconto agora... Corra</a> Website oficial: <a href="https://www.nutritionsee.com/vallgportys">www.ValGone.com</a>	{"license": "apache-2.0"}	ValGone-Portugal/ValGone-Portugal	null	[ "license:apache-2.0", "region:us" ]	null	2024-04-12T06:34:40+00:00	[]	[]	TAGS #license-apache-2.0 #region-us	O que é o creme ValGone gel? ValGone Onde comprar Creme é uma solução tópica formulada especificamente para aliviar o desconforto associado aos joanetes. Contém uma mistura de ingredientes naturais conhecidos por suas propriedades antiinflamatórias e analgésicas. Esses ingredientes atuam sinergicamente para reduzir a dor, a inflamação e o inchaço ao redor da área afetada. <p><a href="URL <img src="URL alt="enter image description here"> </a></p> <a href="URL agora!! Clique no link abaixo para mais informações e ganhe 50% de desconto agora... Corra</a> Website oficial: <a href="URL	[]	[ "TAGS\n#license-apache-2.0 #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": []}	lemon-mint/gemma-2b-translation-v0.93	null	[ "transformers", "safetensors", "gemma", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-12T06:39:36+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" ]
text2text-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": []}	Auruncus/lsg-mbart-lsh-ru-128-4-4096-v3	null	[ "transformers", "safetensors", "mbart", "text2text-generation", "custom_code", "arxiv:1910.09700", "autotrain_compatible", "region:us" ]	null	2024-04-12T06:39:38+00:00	[ "1910.09700" ]	[]	TAGS #transformers #safetensors #mbart #text2text-generation #custom_code #arxiv-1910.09700 #autotrain_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 #mbart #text2text-generation #custom_code #arxiv-1910.09700 #autotrain_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 is a 4 bit quantized version of Vezora/Mistral-22B-v0.1. I don't know if it works properly for training. I could not get it to work using Unsloth - it gives OOM error even with very low settings. According to Vezora there will be a better version coming up soon anyways. Uploading this for fun.	{}	Ba2han/Mistral-22B-v0.1-bnb-4bit	null	[ "transformers", "safetensors", "mistral", "text-generation", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]	null	2024-04-12T06:40:01+00:00	[]	[]	TAGS #transformers #safetensors #mistral #text-generation #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us	This is a 4 bit quantized version of Vezora/Mistral-22B-v0.1. I don't know if it works properly for training. I could not get it to work using Unsloth - it gives OOM error even with very low settings. According to Vezora there will be a better version coming up soon anyways. Uploading this for fun.	[]	[ "TAGS\n#transformers #safetensors #mistral #text-generation #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n" ]
reinforcement-learning	null	# Q-Learning Agent playing1 FrozenLake-v1 This is a trained model of a Q-Learning agent playing FrozenLake-v1 . ## Usage ```python model = load_from_hub(repo_id="nzdb70/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl") # Don't forget to check if you need to add additional attributes (is_slippery=False etc) env = gym.make(model["env_id"]) ```	{"tags": ["FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation"], "model-index": [{"name": "q-FrozenLake-v1-4x4-noSlippery", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "FrozenLake-v1-4x4-no_slippery", "type": "FrozenLake-v1-4x4-no_slippery"}, "metrics": [{"type": "mean_reward", "value": "1.00 +/- 0.00", "name": "mean_reward", "verified": false}]}]}]}	nzdb70/q-FrozenLake-v1-4x4-noSlippery	null	[ "FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]	null	2024-04-12T06:43:44+00:00	[]	[]	TAGS #FrozenLake-v1-4x4-no_slippery #q-learning #reinforcement-learning #custom-implementation #model-index #region-us	# Q-Learning Agent playing1 FrozenLake-v1 This is a trained model of a Q-Learning agent playing FrozenLake-v1 . ## Usage	[ "# Q-Learning Agent playing1 FrozenLake-v1\n This is a trained model of a Q-Learning agent playing FrozenLake-v1 .\n\n ## Usage" ]	[ "TAGS\n#FrozenLake-v1-4x4-no_slippery #q-learning #reinforcement-learning #custom-implementation #model-index #region-us \n", "# Q-Learning Agent playing1 FrozenLake-v1\n This is a trained model of a Q-Learning agent playing FrozenLake-v1 .\n\n ## Usage" ]
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. --> # 0.0001_idpo_same_nodpo_noreplacerej_6iters_iter_6 This model is a fine-tuned version of [ZhangShenao/0.0001_idpo_same_nodpo_noreplacerej_6iters_iter_5](https://huggingface.co/ZhangShenao/0.0001_idpo_same_nodpo_noreplacerej_6iters_iter_5) 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 4.36.2 - Pytorch 2.1.2+cu121 - Datasets 2.14.6 - Tokenizers 0.15.2	{"license": "mit", "tags": ["alignment-handbook", "generated_from_trainer", "trl", "dpo", "generated_from_trainer"], "datasets": ["updated", "original"], "base_model": "ZhangShenao/0.0001_idpo_same_nodpo_noreplacerej_6iters_iter_5", "model-index": [{"name": "0.0001_idpo_same_nodpo_noreplacerej_6iters_iter_6", "results": []}]}	ZhangShenao/0.0001_idpo_same_nodpo_noreplacerej_6iters_iter_6	null	[ "transformers", "safetensors", "mistral", "text-generation", "alignment-handbook", "generated_from_trainer", "trl", "dpo", "conversational", "dataset:updated", "dataset:original", "base_model:ZhangShenao/0.0001_idpo_same_nodpo_noreplacerej_6iters_iter_5", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-12T06:46:48+00:00	[]	[]	TAGS #transformers #safetensors #mistral #text-generation #alignment-handbook #generated_from_trainer #trl #dpo #conversational #dataset-updated #dataset-original #base_model-ZhangShenao/0.0001_idpo_same_nodpo_noreplacerej_6iters_iter_5 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us	# 0.0001_idpo_same_nodpo_noreplacerej_6iters_iter_6 This model is a fine-tuned version of ZhangShenao/0.0001_idpo_same_nodpo_noreplacerej_6iters_iter_5 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 4.36.2 - Pytorch 2.1.2+cu121 - Datasets 2.14.6 - Tokenizers 0.15.2	[ "# 0.0001_idpo_same_nodpo_noreplacerej_6iters_iter_6\n\nThis model is a fine-tuned version of ZhangShenao/0.0001_idpo_same_nodpo_noreplacerej_6iters_iter_5 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 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.15.2" ]	[ "TAGS\n#transformers #safetensors #mistral #text-generation #alignment-handbook #generated_from_trainer #trl #dpo #conversational #dataset-updated #dataset-original #base_model-ZhangShenao/0.0001_idpo_same_nodpo_noreplacerej_6iters_iter_5 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# 0.0001_idpo_same_nodpo_noreplacerej_6iters_iter_6\n\nThis model is a fine-tuned version of ZhangShenao/0.0001_idpo_same_nodpo_noreplacerej_6iters_iter_5 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 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.15.2" ]
reinforcement-learning	stable-baselines3	# PPO Agent playing LunarLander-v2 This is a trained model of a PPO agent playing LunarLander-v2 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```	{"library_name": "stable-baselines3", "tags": ["LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "stable-baselines3"], "model-index": [{"name": "PPO", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "LunarLander-v2", "type": "LunarLander-v2"}, "metrics": [{"type": "mean_reward", "value": "266.01 +/- 11.20", "name": "mean_reward", "verified": false}]}]}]}	Solohcj/ppo-LunarLander-v2	null	[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	null	2024-04-12T06:47:01+00:00	[]	[]	TAGS #stable-baselines3 #LunarLander-v2 #deep-reinforcement-learning #reinforcement-learning #model-index #region-us	# PPO Agent playing LunarLander-v2 This is a trained model of a PPO agent playing LunarLander-v2 using the stable-baselines3 library. ## Usage (with Stable-baselines3) TODO: Add your code	[ "# PPO Agent playing LunarLander-v2\nThis is a trained model of a PPO agent playing LunarLander-v2\nusing the stable-baselines3 library.", "## Usage (with Stable-baselines3)\nTODO: Add your code" ]	[ "TAGS\n#stable-baselines3 #LunarLander-v2 #deep-reinforcement-learning #reinforcement-learning #model-index #region-us \n", "# PPO Agent playing LunarLander-v2\nThis is a trained model of a PPO agent playing LunarLander-v2\nusing the stable-baselines3 library.", "## Usage (with Stable-baselines3)\nTODO: Add your code" ]
text-generation	transformers	# Model Trained Using AutoTrain This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain). # Usage ```python from transformers import AutoModelForCausalLM, AutoTokenizer model_path = "PATH_TO_THIS_REPO" tokenizer = AutoTokenizer.from_pretrained(model_path) model = AutoModelForCausalLM.from_pretrained( model_path, device_map="auto", torch_dtype='auto' ).eval() # Prompt content: "hi" messages = [ {"role": "user", "content": "hi"} ] input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt') output_ids = model.generate(input_ids.to('cuda')) response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True) # Model response: "Hello! How can I assist you today?" print(response) ```	{"license": "other", "library_name": "transformers", "tags": ["autotrain", "text-generation-inference", "text-generation", "peft"], "widget": [{"messages": [{"role": "user", "content": "What is your favorite condiment?"}]}]}	BarhateManthan/my_llama2	null	[ "transformers", "safetensors", "autotrain", "text-generation-inference", "text-generation", "peft", "conversational", "license:other", "endpoints_compatible", "region:us" ]	null	2024-04-12T06:48:17+00:00	[]	[]	TAGS #transformers #safetensors #autotrain #text-generation-inference #text-generation #peft #conversational #license-other #endpoints_compatible #region-us	# Model Trained Using AutoTrain This model was trained using AutoTrain. For more information, please visit AutoTrain. # Usage	[ "# Model Trained Using AutoTrain\n\nThis model was trained using AutoTrain. For more information, please visit AutoTrain.", "# Usage" ]	[ "TAGS\n#transformers #safetensors #autotrain #text-generation-inference #text-generation #peft #conversational #license-other #endpoints_compatible #region-us \n", "# Model Trained Using AutoTrain\n\nThis model was trained using AutoTrain. For more information, please visit AutoTrain.", "# Usage" ]
reinforcement-learning	sample-factory	A(n) APPO model trained on the doom_health_gathering_supreme environment. This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory. Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/ ## Downloading the model After installing Sample-Factory, download the model with: ``` python -m sample_factory.huggingface.load_from_hub -r OscarGalavizC/rl_course_vizdoom_health_gathering_supreme ``` ## Using the model To run the model after download, use the `enjoy` script corresponding to this environment: ``` python -m .usr.local.lib.python3.10.dist-packages.colab_kernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme ``` You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag. See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details ## Training with this model To continue training with this model, use the `train` script corresponding to this environment: ``` python -m .usr.local.lib.python3.10.dist-packages.colab_kernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme --restart_behavior=resume --train_for_env_steps=10000000000 ``` Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.	{"library_name": "sample-factory", "tags": ["deep-reinforcement-learning", "reinforcement-learning", "sample-factory"], "model-index": [{"name": "APPO", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "doom_health_gathering_supreme", "type": "doom_health_gathering_supreme"}, "metrics": [{"type": "mean_reward", "value": "10.39 +/- 5.76", "name": "mean_reward", "verified": false}]}]}]}	OscarGalavizC/rl_course_vizdoom_health_gathering_supreme	null	[ "sample-factory", "tensorboard", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	null	2024-04-12T06:49:35+00:00	[]	[]	TAGS #sample-factory #tensorboard #deep-reinforcement-learning #reinforcement-learning #model-index #region-us	A(n) APPO model trained on the doom_health_gathering_supreme environment. This model was trained using Sample-Factory 2.0: URL Documentation for how to use Sample-Factory can be found at URL ## Downloading the model After installing Sample-Factory, download the model with: ## Using the model To run the model after download, use the 'enjoy' script corresponding to this environment: You can also upload models to the Hugging Face Hub using the same script with the '--push_to_hub' flag. See URL for more details ## Training with this model To continue training with this model, use the 'train' script corresponding to this environment: Note, you may have to adjust '--train_for_env_steps' to a suitably high number as the experiment will resume at the number of steps it concluded at.	[ "## Downloading the model\n\nAfter installing Sample-Factory, download the model with:", "## Using the model\n\nTo run the model after download, use the 'enjoy' script corresponding to this environment:\n\n\n\nYou can also upload models to the Hugging Face Hub using the same script with the '--push_to_hub' flag.\nSee URL for more details", "## Training with this model\n\nTo continue training with this model, use the 'train' script corresponding to this environment:\n\n\nNote, you may have to adjust '--train_for_env_steps' to a suitably high number as the experiment will resume at the number of steps it concluded at." ]	[ "TAGS\n#sample-factory #tensorboard #deep-reinforcement-learning #reinforcement-learning #model-index #region-us \n", "## Downloading the model\n\nAfter installing Sample-Factory, download the model with:", "## Using the model\n\nTo run the model after download, use the 'enjoy' script corresponding to this environment:\n\n\n\nYou can also upload models to the Hugging Face Hub using the same script with the '--push_to_hub' flag.\nSee URL for more details", "## Training with this model\n\nTo continue training with this model, use the 'train' script corresponding to this environment:\n\n\nNote, you may have to adjust '--train_for_env_steps' to a suitably high number as the experiment will resume at the number of steps it concluded at." ]
feature-extraction	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": []}	poro1301/zeus-m3	null	[ "transformers", "safetensors", "xlm-roberta", "feature-extraction", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-04-12T06:50:25+00:00	[ "1910.09700" ]	[]	TAGS #transformers #safetensors #xlm-roberta #feature-extraction #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 #xlm-roberta #feature-extraction #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	adapter-transformers	# Adapter `jgrc3/seqBN_adapter_classification_noPre` for roberta-base An [adapter](https://adapterhub.ml) for the `roberta-base` model that was trained on the [BigTMiami/amazon_helpfulness](https://huggingface.co/datasets/BigTMiami/amazon_helpfulness/) dataset and includes a prediction head for classification. This adapter was created for usage with the [Adapters](https://github.com/Adapter-Hub/adapters) library. ## Usage First, install `adapters`: ``` pip install -U adapters ``` Now, the adapter can be loaded and activated like this: ```python from adapters import AutoAdapterModel model = AutoAdapterModel.from_pretrained("roberta-base") adapter_name = model.load_adapter("jgrc3/seqBN_adapter_classification_noPre", source="hf", set_active=True) ``` ## Architecture & Training <!-- Add some description here --> ## Evaluation results <!-- Add some description here --> ## Citation <!-- Add some description here -->	{"tags": ["roberta", "adapter-transformers"], "datasets": ["BigTMiami/amazon_helpfulness"]}	jgrc3/seqBN_adapter_classification_noPre	null	[ "adapter-transformers", "roberta", "dataset:BigTMiami/amazon_helpfulness", "region:us" ]	null	2024-04-12T06:51:27+00:00	[]	[]	TAGS #adapter-transformers #roberta #dataset-BigTMiami/amazon_helpfulness #region-us	# Adapter 'jgrc3/seqBN_adapter_classification_noPre' for roberta-base An adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_helpfulness dataset and includes a prediction head for classification. This adapter was created for usage with the Adapters library. ## Usage First, install 'adapters': Now, the adapter can be loaded and activated like this: ## Architecture & Training ## Evaluation results	[ "# Adapter 'jgrc3/seqBN_adapter_classification_noPre' for roberta-base\n\nAn adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_helpfulness dataset and includes a prediction head for classification.\n\nThis adapter was created for usage with the Adapters library.", "## Usage\n\nFirst, install 'adapters':\n\n\n\nNow, the adapter can be loaded and activated like this:", "## Architecture & Training", "## Evaluation results" ]	[ "TAGS\n#adapter-transformers #roberta #dataset-BigTMiami/amazon_helpfulness #region-us \n", "# Adapter 'jgrc3/seqBN_adapter_classification_noPre' for roberta-base\n\nAn adapter for the 'roberta-base' model that was trained on the BigTMiami/amazon_helpfulness dataset and includes a prediction head for classification.\n\nThis adapter was created for usage with the Adapters library.", "## Usage\n\nFirst, install 'adapters':\n\n\n\nNow, the adapter can be loaded and activated like this:", "## Architecture & Training", "## Evaluation results" ]
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": []}	mapleadmin/Enlighten_Instruct_merged	null	[ "transformers", "safetensors", "mistral", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-12T06:51:30+00:00	[ "1910.09700" ]	[]	TAGS #transformers #safetensors #mistral #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 #mistral #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	## About <!-- ### quantize_version: 1 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: --> <!-- ### vocab_type: --> weighted/imatrix quants of https://huggingface.co/wenbopan/Faro-Yi-34B-DPO <!-- provided-files --> static quants are available at https://huggingface.co/mradermacher/Faro-Yi-34B-DPO-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/Faro-Yi-34B-DPO-i1-GGUF/resolve/main/Faro-Yi-34B-DPO.i1-IQ1_S.gguf) \| i1-IQ1_S \| 7.6 \| for the desperate \| \| [GGUF](https://huggingface.co/mradermacher/Faro-Yi-34B-DPO-i1-GGUF/resolve/main/Faro-Yi-34B-DPO.i1-IQ1_M.gguf) \| i1-IQ1_M \| 8.3 \| for the desperate \| \| [GGUF](https://huggingface.co/mradermacher/Faro-Yi-34B-DPO-i1-GGUF/resolve/main/Faro-Yi-34B-DPO.i1-IQ2_XXS.gguf) \| i1-IQ2_XXS \| 9.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/Faro-Yi-34B-DPO-i1-GGUF/resolve/main/Faro-Yi-34B-DPO.i1-IQ2_XS.gguf) \| i1-IQ2_XS \| 10.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/Faro-Yi-34B-DPO-i1-GGUF/resolve/main/Faro-Yi-34B-DPO.i1-IQ2_S.gguf) \| i1-IQ2_S \| 11.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/Faro-Yi-34B-DPO-i1-GGUF/resolve/main/Faro-Yi-34B-DPO.i1-IQ2_M.gguf) \| i1-IQ2_M \| 11.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/Faro-Yi-34B-DPO-i1-GGUF/resolve/main/Faro-Yi-34B-DPO.i1-Q2_K.gguf) \| i1-Q2_K \| 12.9 \| IQ3_XXS probably better \| \| [GGUF](https://huggingface.co/mradermacher/Faro-Yi-34B-DPO-i1-GGUF/resolve/main/Faro-Yi-34B-DPO.i1-IQ3_XXS.gguf) \| i1-IQ3_XXS \| 13.4 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/Faro-Yi-34B-DPO-i1-GGUF/resolve/main/Faro-Yi-34B-DPO.i1-IQ3_XS.gguf) \| i1-IQ3_XS \| 14.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/Faro-Yi-34B-DPO-i1-GGUF/resolve/main/Faro-Yi-34B-DPO.i1-Q3_K_S.gguf) \| i1-Q3_K_S \| 15.1 \| IQ3_XS probably better \| \| [GGUF](https://huggingface.co/mradermacher/Faro-Yi-34B-DPO-i1-GGUF/resolve/main/Faro-Yi-34B-DPO.i1-IQ3_S.gguf) \| i1-IQ3_S \| 15.1 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/Faro-Yi-34B-DPO-i1-GGUF/resolve/main/Faro-Yi-34B-DPO.i1-IQ3_M.gguf) \| i1-IQ3_M \| 15.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/Faro-Yi-34B-DPO-i1-GGUF/resolve/main/Faro-Yi-34B-DPO.i1-Q3_K_M.gguf) \| i1-Q3_K_M \| 16.8 \| IQ3_S probably better \| \| [GGUF](https://huggingface.co/mradermacher/Faro-Yi-34B-DPO-i1-GGUF/resolve/main/Faro-Yi-34B-DPO.i1-Q3_K_L.gguf) \| i1-Q3_K_L \| 18.2 \| IQ3_M probably better \| \| [GGUF](https://huggingface.co/mradermacher/Faro-Yi-34B-DPO-i1-GGUF/resolve/main/Faro-Yi-34B-DPO.i1-IQ4_XS.gguf) \| i1-IQ4_XS \| 18.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/Faro-Yi-34B-DPO-i1-GGUF/resolve/main/Faro-Yi-34B-DPO.i1-Q4_0.gguf) \| i1-Q4_0 \| 19.6 \| fast, low quality \| \| [GGUF](https://huggingface.co/mradermacher/Faro-Yi-34B-DPO-i1-GGUF/resolve/main/Faro-Yi-34B-DPO.i1-Q4_K_S.gguf) \| i1-Q4_K_S \| 19.7 \| optimal size/speed/quality \| \| [GGUF](https://huggingface.co/mradermacher/Faro-Yi-34B-DPO-i1-GGUF/resolve/main/Faro-Yi-34B-DPO.i1-Q4_K_M.gguf) \| i1-Q4_K_M \| 20.8 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Faro-Yi-34B-DPO-i1-GGUF/resolve/main/Faro-Yi-34B-DPO.i1-Q5_K_S.gguf) \| i1-Q5_K_S \| 23.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/Faro-Yi-34B-DPO-i1-GGUF/resolve/main/Faro-Yi-34B-DPO.i1-Q5_K_M.gguf) \| i1-Q5_K_M \| 24.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/Faro-Yi-34B-DPO-i1-GGUF/resolve/main/Faro-Yi-34B-DPO.i1-Q6_K.gguf) \| i1-Q6_K \| 28.3 \| 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": "mit", "library_name": "transformers", "datasets": ["wenbopan/Chinese-dpo-pairs", "Intel/orca_dpo_pairs", "argilla/ultrafeedback-binarized-preferences-cleaned", "jondurbin/truthy-dpo-v0.1"], "base_model": "wenbopan/Faro-Yi-34B-DPO", "quantized_by": "mradermacher"}	mradermacher/Faro-Yi-34B-DPO-i1-GGUF	null	[ "transformers", "gguf", "en", "dataset:wenbopan/Chinese-dpo-pairs", "dataset:Intel/orca_dpo_pairs", "dataset:argilla/ultrafeedback-binarized-preferences-cleaned", "dataset:jondurbin/truthy-dpo-v0.1", "base_model:wenbopan/Faro-Yi-34B-DPO", "license:mit", "endpoints_compatible", "region:us" ]	null	2024-04-12T06:52:59+00:00	[]	[ "en" ]	TAGS #transformers #gguf #en #dataset-wenbopan/Chinese-dpo-pairs #dataset-Intel/orca_dpo_pairs #dataset-argilla/ultrafeedback-binarized-preferences-cleaned #dataset-jondurbin/truthy-dpo-v0.1 #base_model-wenbopan/Faro-Yi-34B-DPO #license-mit #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 #en #dataset-wenbopan/Chinese-dpo-pairs #dataset-Intel/orca_dpo_pairs #dataset-argilla/ultrafeedback-binarized-preferences-cleaned #dataset-jondurbin/truthy-dpo-v0.1 #base_model-wenbopan/Faro-Yi-34B-DPO #license-mit #endpoints_compatible #region-us \n" ]
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. --> # selfbiorag-7b-sft-wo-live_qa-sft This model is a fine-tuned version of [dmis-lab/selfbiorag_7b](https://huggingface.co/dmis-lab/selfbiorag_7b) on the HuggingFaceH4/deita-10k-v0-sft dataset. It achieves the following results on the evaluation set: - Loss: 1.5818 ## 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: 4 - eval_batch_size: 4 - seed: 42 - distributed_type: multi-GPU - num_devices: 4 - gradient_accumulation_steps: 4 - total_train_batch_size: 64 - total_eval_batch_size: 16 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 3 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| 1.5447 \| 1.0 \| 7 \| 1.6286 \| \| 1.2678 \| 2.0 \| 14 \| 1.5860 \| \| 1.0816 \| 3.0 \| 21 \| 1.5818 \| ### Framework versions - Transformers 4.39.0.dev0 - Pytorch 2.1.2 - Datasets 2.14.6 - Tokenizers 0.15.2	{"tags": ["alignment-handbook", "trl", "sft", "generated_from_trainer", "trl", "sft", "generated_from_trainer"], "datasets": ["HuggingFaceH4/deita-10k-v0-sft"], "base_model": "dmis-lab/selfbiorag_7b", "model-index": [{"name": "selfbiorag-7b-sft-wo-live_qa-sft", "results": []}]}	Minbyul/selfbiorag-7b-wo-live_qa-sft	null	[ "transformers", "safetensors", "llama", "text-generation", "alignment-handbook", "trl", "sft", "generated_from_trainer", "dataset:HuggingFaceH4/deita-10k-v0-sft", "base_model:dmis-lab/selfbiorag_7b", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-12T06:53:35+00:00	[]	[]	TAGS #transformers #safetensors #llama #text-generation #alignment-handbook #trl #sft #generated_from_trainer #dataset-HuggingFaceH4/deita-10k-v0-sft #base_model-dmis-lab/selfbiorag_7b #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us	selfbiorag-7b-sft-wo-live\_qa-sft ================================= This model is a fine-tuned version of dmis-lab/selfbiorag\_7b on the HuggingFaceH4/deita-10k-v0-sft dataset. It achieves the following results on the evaluation set: * Loss: 1.5818 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: 4 * eval\_batch\_size: 4 * seed: 42 * distributed\_type: multi-GPU * num\_devices: 4 * gradient\_accumulation\_steps: 4 * total\_train\_batch\_size: 64 * total\_eval\_batch\_size: 16 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: cosine * lr\_scheduler\_warmup\_ratio: 0.1 * num\_epochs: 3 ### Training results ### Framework versions * Transformers 4.39.0.dev0 * Pytorch 2.1.2 * Datasets 2.14.6 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 4\n* seed: 42\n* distributed\\_type: multi-GPU\n* num\\_devices: 4\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 64\n* total\\_eval\\_batch\\_size: 16\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: 3", "### Training results", "### Framework versions\n\n\n* Transformers 4.39.0.dev0\n* Pytorch 2.1.2\n* Datasets 2.14.6\n* Tokenizers 0.15.2" ]	[ "TAGS\n#transformers #safetensors #llama #text-generation #alignment-handbook #trl #sft #generated_from_trainer #dataset-HuggingFaceH4/deita-10k-v0-sft #base_model-dmis-lab/selfbiorag_7b #autotrain_compatible #endpoints_compatible #text-generation-inference #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: 4\n* eval\\_batch\\_size: 4\n* seed: 42\n* distributed\\_type: multi-GPU\n* num\\_devices: 4\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 64\n* total\\_eval\\_batch\\_size: 16\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: 3", "### Training results", "### Framework versions\n\n\n* Transformers 4.39.0.dev0\n* Pytorch 2.1.2\n* Datasets 2.14.6\n* Tokenizers 0.15.2" ]
text-classification	transformers	The Label is under description. You can follow the list to know the label model predicted. We are using the pretrained PhoBERT model by VOVANPHUC (link = "https://huggingface.co/VoVanPhuc/sup-SimCSE-VietNamese-phobert-base ") to train on a Vietnamese dataset consisting of 1.3 GB of articles from Tuoi Tre newspaper, including columns such as ('URL', 'Title', 'Summary', 'Contents', 'Date', 'Author(s)', 'Category', 'Tags'). We use the 'Title' column for classification because it allows for quick classification based on the title. The model was trained on 2x GPU T4 of Kaggle with 12 epochs and 4.5 hours trained. The Model can be improved more if increasing epochs. The loss with 12 epochs (batch size = 64, weight_decy = 0.01 and learning rate = 2e-5) and this average is 0.2 and can be decreased if training more times. However the loss can be highest in over 0.2 or 0.18 because the limited of models with sensitive and unambiguous texts ![image/png](https://cdn-uploads.huggingface.co/production/uploads/658c12791260e506f157abcd/YcmuFC6HkLT6bT3k7jFmm.png) We can plot and compare in other situation such as trainning with 8 epochs and 12 epochs(feasible paper 7) and can see that The loss function only approaches 0.2 or 0.19 at its highest in the problem with the model above. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/658c12791260e506f157abcd/c3o8Zd4MbwcdLlFwjFoem.png) This is the label to predict {0: 'Bạn đọc', 1: 'Bất động sản', 2: 'Công nghệ', 3: 'Công đoàn', 4: 'Diễn đàn', 5: 'Du lịch', 6: 'Gia đình - Hôn nhân', 7: 'Giáo dục', 8: 'Kinh doanh', 9: 'Lao Động & Đời sống', 10: 'Lao Động Xuân', 11: 'Lao Động cuối tuần', 12: 'Lưu trữ', 13: 'Media', 14: 'Người Việt tử tế', 15: 'Pháp luật', 16: 'Phóng sự', 17: 'Phóng sự - Điều tra', 18: 'Quỹ TLV', 19: 'Sổ tay kinh tế', 20: 'Sức khỏe', 21: 'Sự kiện Bình luận', 22: 'Thông tin doanh nghiệp', 23: 'Thông tin tiện ích', 24: 'Thế giới', 25: 'Thể thao', 26: 'Thời sự', 27: 'Tin bài liên quan', 28: 'Tin bài nổi bật', 29: 'Tin bài xem thêm', 30: 'Tin hoạt động', 31: 'Tin tức việc làm', 32: 'Tin địa phương', 33: 'Tản mạn - Chuyện dọc đường', 34: 'Tấm Lòng Vàng', 35: 'Video', 36: 'Văn hóa - Giải trí', 37: 'Xe +', 38: 'Xã hội'} We hope that it can be trained with more higher technology to decrease loss and the model can predict better more than now.	{}	Luan220703/Vietnamese_Categories	null	[ "transformers", "tensorboard", "safetensors", "roberta", "text-classification", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-12T06:54:25+00:00	[]	[]	TAGS #transformers #tensorboard #safetensors #roberta #text-classification #autotrain_compatible #endpoints_compatible #region-us	The Label is under description. You can follow the list to know the label model predicted. We are using the pretrained PhoBERT model by VOVANPHUC (link = "URL ") to train on a Vietnamese dataset consisting of 1.3 GB of articles from Tuoi Tre newspaper, including columns such as ('URL', 'Title', 'Summary', 'Contents', 'Date', 'Author(s)', 'Category', 'Tags'). We use the 'Title' column for classification because it allows for quick classification based on the title. The model was trained on 2x GPU T4 of Kaggle with 12 epochs and 4.5 hours trained. The Model can be improved more if increasing epochs. The loss with 12 epochs (batch size = 64, weight_decy = 0.01 and learning rate = 2e-5) and this average is 0.2 and can be decreased if training more times. However the loss can be highest in over 0.2 or 0.18 because the limited of models with sensitive and unambiguous texts !image/png We can plot and compare in other situation such as trainning with 8 epochs and 12 epochs(feasible paper 7) and can see that The loss function only approaches 0.2 or 0.19 at its highest in the problem with the model above. !image/png This is the label to predict {0: 'Bạn đọc', 1: 'Bất động sản', 2: 'Công nghệ', 3: 'Công đoàn', 4: 'Diễn đàn', 5: 'Du lịch', 6: 'Gia đình - Hôn nhân', 7: 'Giáo dục', 8: 'Kinh doanh', 9: 'Lao Động & Đời sống', 10: 'Lao Động Xuân', 11: 'Lao Động cuối tuần', 12: 'Lưu trữ', 13: 'Media', 14: 'Người Việt tử tế', 15: 'Pháp luật', 16: 'Phóng sự', 17: 'Phóng sự - Điều tra', 18: 'Quỹ TLV', 19: 'Sổ tay kinh tế', 20: 'Sức khỏe', 21: 'Sự kiện Bình luận', 22: 'Thông tin doanh nghiệp', 23: 'Thông tin tiện ích', 24: 'Thế giới', 25: 'Thể thao', 26: 'Thời sự', 27: 'Tin bài liên quan', 28: 'Tin bài nổi bật', 29: 'Tin bài xem thêm', 30: 'Tin hoạt động', 31: 'Tin tức việc làm', 32: 'Tin địa phương', 33: 'Tản mạn - Chuyện dọc đường', 34: 'Tấm Lòng Vàng', 35: 'Video', 36: 'Văn hóa - Giải trí', 37: 'Xe +', 38: 'Xã hội'} We hope that it can be trained with more higher technology to decrease loss and the model can predict better more than now.	[]	[ "TAGS\n#transformers #tensorboard #safetensors #roberta #text-classification #autotrain_compatible #endpoints_compatible #region-us \n" ]
fill-mask	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": []}	Lancelot53/mosaic-rna-bert-trial	null	[ "transformers", "safetensors", "bert", "fill-mask", "custom_code", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-12T06:57:16+00:00	[ "1910.09700" ]	[]	TAGS #transformers #safetensors #bert #fill-mask #custom_code #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 #bert #fill-mask #custom_code #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" ]
null	null	<!-- 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. --> # llama-7b-chat-25000-25-75-L This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on the generator 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: 0.0002 - train_batch_size: 2200 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 4400 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: constant - lr_scheduler_warmup_ratio: 0.03 - num_epochs: 3 ### Training results ### Framework versions - Transformers 4.33.3 - Pytorch 2.2.1 - Datasets 2.18.0 - Tokenizers 0.13.3	{"tags": ["trl", "sft", "generated_from_trainer"], "datasets": ["generator"], "base_model": "meta-llama/Llama-2-7b-chat-hf", "model-index": [{"name": "llama-7b-chat-25000-25-75-L", "results": []}]}	Niyantha23M/llama-7b-chat-25000-25-75-L	null	[ "trl", "sft", "generated_from_trainer", "dataset:generator", "base_model:meta-llama/Llama-2-7b-chat-hf", "region:us" ]	null	2024-04-12T06:57:29+00:00	[]	[]	TAGS #trl #sft #generated_from_trainer #dataset-generator #base_model-meta-llama/Llama-2-7b-chat-hf #region-us	# llama-7b-chat-25000-25-75-L This model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on the generator 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: 0.0002 - train_batch_size: 2200 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 4400 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: constant - lr_scheduler_warmup_ratio: 0.03 - num_epochs: 3 ### Training results ### Framework versions - Transformers 4.33.3 - Pytorch 2.2.1 - Datasets 2.18.0 - Tokenizers 0.13.3	[ "# llama-7b-chat-25000-25-75-L\n\nThis model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on the generator 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: 0.0002\n- train_batch_size: 2200\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 4400\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: constant\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 3", "### Training results", "### Framework versions\n\n- Transformers 4.33.3\n- Pytorch 2.2.1\n- Datasets 2.18.0\n- Tokenizers 0.13.3" ]	[ "TAGS\n#trl #sft #generated_from_trainer #dataset-generator #base_model-meta-llama/Llama-2-7b-chat-hf #region-us \n", "# llama-7b-chat-25000-25-75-L\n\nThis model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on the generator 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: 0.0002\n- train_batch_size: 2200\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 4400\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: constant\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 3", "### Training results", "### Framework versions\n\n- Transformers 4.33.3\n- Pytorch 2.2.1\n- Datasets 2.18.0\n- Tokenizers 0.13.3" ]
null	null	<!-- 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. --> # llama-7b-chat-25000-75-25-L This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on the generator 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: 0.0002 - train_batch_size: 2200 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 4400 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: constant - lr_scheduler_warmup_ratio: 0.03 - num_epochs: 3 ### Training results ### Framework versions - Transformers 4.33.3 - Pytorch 2.2.1 - Datasets 2.18.0 - Tokenizers 0.13.3	{"tags": ["trl", "sft", "generated_from_trainer"], "datasets": ["generator"], "base_model": "meta-llama/Llama-2-7b-chat-hf", "model-index": [{"name": "llama-7b-chat-25000-75-25-L", "results": []}]}	Niyantha23M/llama-7b-chat-25000-75-25-L	null	[ "trl", "sft", "generated_from_trainer", "dataset:generator", "base_model:meta-llama/Llama-2-7b-chat-hf", "region:us" ]	null	2024-04-12T06:57:42+00:00	[]	[]	TAGS #trl #sft #generated_from_trainer #dataset-generator #base_model-meta-llama/Llama-2-7b-chat-hf #region-us	# llama-7b-chat-25000-75-25-L This model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on the generator 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: 0.0002 - train_batch_size: 2200 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 4400 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: constant - lr_scheduler_warmup_ratio: 0.03 - num_epochs: 3 ### Training results ### Framework versions - Transformers 4.33.3 - Pytorch 2.2.1 - Datasets 2.18.0 - Tokenizers 0.13.3	[ "# llama-7b-chat-25000-75-25-L\n\nThis model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on the generator 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: 0.0002\n- train_batch_size: 2200\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 4400\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: constant\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 3", "### Training results", "### Framework versions\n\n- Transformers 4.33.3\n- Pytorch 2.2.1\n- Datasets 2.18.0\n- Tokenizers 0.13.3" ]	[ "TAGS\n#trl #sft #generated_from_trainer #dataset-generator #base_model-meta-llama/Llama-2-7b-chat-hf #region-us \n", "# llama-7b-chat-25000-75-25-L\n\nThis model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on the generator 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: 0.0002\n- train_batch_size: 2200\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 4400\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: constant\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 3", "### Training results", "### Framework versions\n\n- Transformers 4.33.3\n- Pytorch 2.2.1\n- Datasets 2.18.0\n- Tokenizers 0.13.3" ]
text-generation	transformers	# merge 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 SLERP merge method. ### Models Merged The following models were included in the merge: * [WizardLM/WizardMath-7B-V1.1](https://huggingface.co/WizardLM/WizardMath-7B-V1.1) * [NousResearch/Hermes-2-Pro-Mistral-7B](https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B) ### Configuration The following YAML configuration was used to produce this model: ```yaml models: - model: NousResearch/Hermes-2-Pro-Mistral-7B - model: WizardLM/WizardMath-7B-V1.1 merge_method: slerp base_model: NousResearch/Hermes-2-Pro-Mistral-7B dtype: bfloat16 parameters: t: [0, 0.5, 1, 0.5, 0] # V shaped curve: Hermes for input & output, WizardMath in the middle layers ```	{"library_name": "transformers", "tags": ["mergekit", "merge"], "base_model": ["WizardLM/WizardMath-7B-V1.1", "NousResearch/Hermes-2-Pro-Mistral-7B"]}	mergekit-community/mergekit-slerp-hfjular	null	[ "transformers", "safetensors", "mistral", "text-generation", "mergekit", "merge", "conversational", "base_model:WizardLM/WizardMath-7B-V1.1", "base_model:NousResearch/Hermes-2-Pro-Mistral-7B", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-12T06:57:58+00:00	[]	[]	TAGS #transformers #safetensors #mistral #text-generation #mergekit #merge #conversational #base_model-WizardLM/WizardMath-7B-V1.1 #base_model-NousResearch/Hermes-2-Pro-Mistral-7B #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us	# merge This is a merge of pre-trained language models created using mergekit. ## Merge Details ### Merge Method This model was merged using the SLERP merge method. ### Models Merged The following models were included in the merge: * WizardLM/WizardMath-7B-V1.1 * NousResearch/Hermes-2-Pro-Mistral-7B ### Configuration The following YAML configuration was used to produce this model:	[ "# merge\n\nThis is a merge of pre-trained language models created using mergekit.", "## Merge Details", "### Merge Method\n\nThis model was merged using the SLERP merge method.", "### Models Merged\n\nThe following models were included in the merge:\n* WizardLM/WizardMath-7B-V1.1\n* NousResearch/Hermes-2-Pro-Mistral-7B", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]	[ "TAGS\n#transformers #safetensors #mistral #text-generation #mergekit #merge #conversational #base_model-WizardLM/WizardMath-7B-V1.1 #base_model-NousResearch/Hermes-2-Pro-Mistral-7B #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# merge\n\nThis is a merge of pre-trained language models created using mergekit.", "## Merge Details", "### Merge Method\n\nThis model was merged using the SLERP merge method.", "### Models Merged\n\nThe following models were included in the merge:\n* WizardLM/WizardMath-7B-V1.1\n* NousResearch/Hermes-2-Pro-Mistral-7B", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]
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. --> # zephyr-7b-sft-qlora This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the HuggingFaceH4/ultrachat_200k dataset. It achieves the following results on the evaluation set: - Loss: 0.9438 ## 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: 4 - eval_batch_size: 8 - seed: 42 - distributed_type: multi-GPU - num_devices: 8 - gradient_accumulation_steps: 2 - total_train_batch_size: 64 - 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 \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| 0.9452 \| 1.0 \| 2179 \| 0.9438 \| ### Framework versions - PEFT 0.7.1 - Transformers 4.39.0.dev0 - Pytorch 2.2.2+cu121 - Datasets 2.14.6 - Tokenizers 0.15.2	{"license": "apache-2.0", "library_name": "peft", "tags": ["alignment-handbook", "trl", "sft", "generated_from_trainer"], "datasets": ["HuggingFaceH4/ultrachat_200k"], "base_model": "mistralai/Mistral-7B-v0.1", "model-index": [{"name": "zephyr-7b-sft-qlora", "results": []}]}	yzzh/zephyr-7b-sft-qlora	null	[ "peft", "tensorboard", "safetensors", "mistral", "alignment-handbook", "trl", "sft", "generated_from_trainer", "dataset:HuggingFaceH4/ultrachat_200k", "base_model:mistralai/Mistral-7B-v0.1", "license:apache-2.0", "region:us" ]	null	2024-04-12T06:59:27+00:00	[]	[]	TAGS #peft #tensorboard #safetensors #mistral #alignment-handbook #trl #sft #generated_from_trainer #dataset-HuggingFaceH4/ultrachat_200k #base_model-mistralai/Mistral-7B-v0.1 #license-apache-2.0 #region-us	zephyr-7b-sft-qlora =================== This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the HuggingFaceH4/ultrachat\_200k dataset. It achieves the following results on the evaluation set: * Loss: 0.9438 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: 4 * eval\_batch\_size: 8 * seed: 42 * distributed\_type: multi-GPU * num\_devices: 8 * gradient\_accumulation\_steps: 2 * total\_train\_batch\_size: 64 * 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 * PEFT 0.7.1 * Transformers 4.39.0.dev0 * Pytorch 2.2.2+cu121 * Datasets 2.14.6 * 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: 4\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: 64\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\n* PEFT 0.7.1\n* Transformers 4.39.0.dev0\n* Pytorch 2.2.2+cu121\n* Datasets 2.14.6\n* Tokenizers 0.15.2" ]	[ "TAGS\n#peft #tensorboard #safetensors #mistral #alignment-handbook #trl #sft #generated_from_trainer #dataset-HuggingFaceH4/ultrachat_200k #base_model-mistralai/Mistral-7B-v0.1 #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: 4\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: 64\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\n* PEFT 0.7.1\n* Transformers 4.39.0.dev0\n* Pytorch 2.2.2+cu121\n* Datasets 2.14.6\n* Tokenizers 0.15.2" ]
text-generation	transformers	# merge 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 SLERP merge method. ### Models Merged The following models were included in the merge: * [cognitivecomputations/dolphin-2.8-mistral-7b-v02](https://huggingface.co/cognitivecomputations/dolphin-2.8-mistral-7b-v02) * [arcee-ai/sec-mistral-7b-instruct-1.6-epoch](https://huggingface.co/arcee-ai/sec-mistral-7b-instruct-1.6-epoch) ### Configuration The following YAML configuration was used to produce this model: ```yaml slices: - sources: - model: arcee-ai/sec-mistral-7b-instruct-1.6-epoch layer_range: [0, 32] - model: cognitivecomputations/dolphin-2.8-mistral-7b-v02 layer_range: [0, 32] merge_method: slerp base_model: cognitivecomputations/dolphin-2.8-mistral-7b-v02 parameters: t: - filter: self_attn value: [0, 0.5, 0.3, 0.7, 1] - filter: mlp value: [1, 0.5, 0.7, 0.3, 0] - value: 0.5 dtype: bfloat16 ```	{"library_name": "transformers", "tags": ["mergekit", "merge"], "base_model": ["cognitivecomputations/dolphin-2.8-mistral-7b-v02", "arcee-ai/sec-mistral-7b-instruct-1.6-epoch"]}	mergekit-community/mergekit-slerp-bvgnomy	null	[ "transformers", "safetensors", "mistral", "text-generation", "mergekit", "merge", "conversational", "base_model:cognitivecomputations/dolphin-2.8-mistral-7b-v02", "base_model:arcee-ai/sec-mistral-7b-instruct-1.6-epoch", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-12T07:01:47+00:00	[]	[]	TAGS #transformers #safetensors #mistral #text-generation #mergekit #merge #conversational #base_model-cognitivecomputations/dolphin-2.8-mistral-7b-v02 #base_model-arcee-ai/sec-mistral-7b-instruct-1.6-epoch #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us	# merge This is a merge of pre-trained language models created using mergekit. ## Merge Details ### Merge Method This model was merged using the SLERP merge method. ### Models Merged The following models were included in the merge: * cognitivecomputations/dolphin-2.8-mistral-7b-v02 * arcee-ai/sec-mistral-7b-instruct-1.6-epoch ### Configuration The following YAML configuration was used to produce this model:	[ "# merge\n\nThis is a merge of pre-trained language models created using mergekit.", "## Merge Details", "### Merge Method\n\nThis model was merged using the SLERP merge method.", "### Models Merged\n\nThe following models were included in the merge:\n* cognitivecomputations/dolphin-2.8-mistral-7b-v02\n* arcee-ai/sec-mistral-7b-instruct-1.6-epoch", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]	[ "TAGS\n#transformers #safetensors #mistral #text-generation #mergekit #merge #conversational #base_model-cognitivecomputations/dolphin-2.8-mistral-7b-v02 #base_model-arcee-ai/sec-mistral-7b-instruct-1.6-epoch #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# merge\n\nThis is a merge of pre-trained language models created using mergekit.", "## Merge Details", "### Merge Method\n\nThis model was merged using the SLERP merge method.", "### Models Merged\n\nThe following models were included in the merge:\n* cognitivecomputations/dolphin-2.8-mistral-7b-v02\n* arcee-ai/sec-mistral-7b-instruct-1.6-epoch", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]
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. --> # bart-cnn-samsum-finetuned This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.1470 ## 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: 8 - 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 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| 0.094 \| 1.0 \| 37 \| 0.1470 \| ### Framework versions - Transformers 4.38.2 - Pytorch 2.2.1+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2	{"license": "mit", "tags": ["generated_from_trainer"], "base_model": "facebook/bart-large-cnn", "model-index": [{"name": "bart-cnn-samsum-finetuned", "results": []}]}	TeamBriefMe/bart-cnn-samsum-finetuned	null	[ "transformers", "tensorboard", "safetensors", "bart", "text2text-generation", "generated_from_trainer", "base_model:facebook/bart-large-cnn", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-12T07:02:30+00:00	[]	[]	TAGS #transformers #tensorboard #safetensors #bart #text2text-generation #generated_from_trainer #base_model-facebook/bart-large-cnn #license-mit #autotrain_compatible #endpoints_compatible #region-us	bart-cnn-samsum-finetuned ========================= This model is a fine-tuned version of facebook/bart-large-cnn on an unknown dataset. It achieves the following results on the evaluation set: * Loss: 0.1470 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: 8 * 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 ### Training results ### Framework versions * Transformers 4.38.2 * Pytorch 2.2.1+cu121 * Datasets 2.18.0 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 8\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", "### Training results", "### Framework versions\n\n\n* Transformers 4.38.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2" ]	[ "TAGS\n#transformers #tensorboard #safetensors #bart #text2text-generation #generated_from_trainer #base_model-facebook/bart-large-cnn #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: 1e-05\n* train\\_batch\\_size: 8\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", "### Training results", "### Framework versions\n\n\n* Transformers 4.38.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\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": []}	0x0mom/st_2	null	[ "transformers", "safetensors", "stablelm", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-12T07:03:04+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" ]
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: True - bnb_4bit_compute_dtype: bfloat16 ### Framework versions - PEFT 0.4.0	{"library_name": "peft"}	mohanaroachakka/tinyjandj	null	[ "peft", "safetensors", "llama", "region:us" ]	null	2024-04-12T07:03:56+00:00	[]	[]	TAGS #peft #safetensors #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: True - bnb_4bit_compute_dtype: bfloat16 ### 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: True\n- bnb_4bit_compute_dtype: bfloat16", "### Framework versions\n\n\n- PEFT 0.4.0" ]	[ "TAGS\n#peft #safetensors #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: True\n- bnb_4bit_compute_dtype: bfloat16", "### Framework versions\n\n\n- PEFT 0.4.0" ]
null	peft	# 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. --> - 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] ### Framework versions - PEFT 0.10.0	{"library_name": "peft", "base_model": "LeroyDyer/Mixtral_AI_CyberTron_m1"}	LeroyDyer/CyberCode_Lora	null	[ "peft", "safetensors", "arxiv:1910.09700", "base_model:LeroyDyer/Mixtral_AI_CyberTron_m1", "region:us" ]	null	2024-04-12T07:05:01+00:00	[ "1910.09700" ]	[]	TAGS #peft #safetensors #arxiv-1910.09700 #base_model-LeroyDyer/Mixtral_AI_CyberTron_m1 #region-us	# Model Card for Model ID ## Model Details ### Model Description - 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 ### Framework versions - PEFT 0.10.0	[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\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", "### Framework versions\n\n- PEFT 0.10.0" ]	[ "TAGS\n#peft #safetensors #arxiv-1910.09700 #base_model-LeroyDyer/Mixtral_AI_CyberTron_m1 #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\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", "### Framework versions\n\n- PEFT 0.10.0" ]
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. --> # FFPP-Raw_1FPS_faces-expand-0-aligned-normalize-image-mean-std This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 0.0031 - Accuracy: 0.9984 - Recall: 0.9926 - Precision: 0.9999 - F1: 0.9963 - Roc Auc: 1.0000 ## 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: 16 - eval_batch_size: 16 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 64 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 20 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| Recall \| Precision \| F1 \| Roc Auc \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:------:\|:---------:\|:------:\|:-------:\| \| 0.1087 \| 1.0 \| 1377 \| 0.0767 \| 0.9720 \| 0.9020 \| 0.9667 \| 0.9332 \| 0.9965 \| \| 0.0647 \| 2.0 \| 2755 \| 0.0408 \| 0.9847 \| 0.9458 \| 0.9831 \| 0.9641 \| 0.9990 \| \| 0.0295 \| 3.0 \| 4132 \| 0.0499 \| 0.9862 \| 0.9947 \| 0.9449 \| 0.9692 \| 0.9995 \| \| 0.0537 \| 4.0 \| 5510 \| 0.0201 \| 0.9927 \| 0.9736 \| 0.9928 \| 0.9831 \| 0.9998 \| \| 0.0253 \| 5.0 \| 6887 \| 0.0115 \| 0.9958 \| 0.9826 \| 0.9979 \| 0.9902 \| 0.9999 \| \| 0.0069 \| 6.0 \| 8265 \| 0.0058 \| 0.9979 \| 0.9928 \| 0.9974 \| 0.9951 \| 1.0000 \| \| 0.0226 \| 7.0 \| 9642 \| 0.0113 \| 0.9960 \| 0.9823 \| 0.9994 \| 0.9908 \| 0.9999 \| \| 0.0096 \| 8.0 \| 11020 \| 0.0147 \| 0.9957 \| 0.9806 \| 0.9995 \| 0.9900 \| 0.9999 \| \| 0.0301 \| 9.0 \| 12397 \| 0.0071 \| 0.9972 \| 0.9878 \| 0.9993 \| 0.9935 \| 1.0000 \| \| 0.0133 \| 10.0 \| 13775 \| 0.0055 \| 0.9978 \| 0.9901 \| 0.9998 \| 0.9949 \| 1.0000 \| \| 0.0074 \| 11.0 \| 15152 \| 0.0049 \| 0.9980 \| 0.9915 \| 0.9992 \| 0.9953 \| 1.0000 \| \| 0.0036 \| 12.0 \| 16530 \| 0.0034 \| 0.9983 \| 0.9935 \| 0.9987 \| 0.9961 \| 1.0000 \| \| 0.0039 \| 13.0 \| 17907 \| 0.0037 \| 0.9982 \| 0.9926 \| 0.9993 \| 0.9959 \| 1.0000 \| \| 0.0106 \| 14.0 \| 19285 \| 0.0033 \| 0.9983 \| 0.9931 \| 0.9992 \| 0.9961 \| 1.0000 \| \| 0.0033 \| 15.0 \| 20662 \| 0.0033 \| 0.9984 \| 0.9926 \| 0.9998 \| 0.9962 \| 1.0000 \| \| 0.0214 \| 16.0 \| 22040 \| 0.0032 \| 0.9984 \| 0.9931 \| 0.9994 \| 0.9963 \| 1.0000 \| \| 0.0041 \| 17.0 \| 23417 \| 0.0032 \| 0.9984 \| 0.9926 \| 0.9998 \| 0.9962 \| 1.0000 \| \| 0.0101 \| 18.0 \| 24795 \| 0.0031 \| 0.9984 \| 0.9926 \| 0.9999 \| 0.9963 \| 1.0000 \| \| 0.0023 \| 19.0 \| 26172 \| 0.0031 \| 0.9984 \| 0.9928 \| 0.9997 \| 0.9963 \| 1.0000 \| \| 0.002 \| 19.99 \| 27540 \| 0.0031 \| 0.9984 \| 0.9926 \| 0.9999 \| 0.9963 \| 1.0000 \| ### Framework versions - Transformers 4.39.2 - Pytorch 2.2.2 - Datasets 2.18.0 - Tokenizers 0.15.2	{"license": "apache-2.0", "tags": ["generated_from_trainer"], "datasets": ["imagefolder"], "metrics": ["accuracy", "recall", "precision", "f1"], "base_model": "microsoft/swin-tiny-patch4-window7-224", "model-index": [{"name": "FFPP-Raw_1FPS_faces-expand-0-aligned-normalize-image-mean-std", "results": [{"task": {"type": "image-classification", "name": "Image Classification"}, "dataset": {"name": "imagefolder", "type": "imagefolder", "config": "default", "split": "test", "args": "default"}, "metrics": [{"type": "accuracy", "value": 0.99837772836593, "name": "Accuracy"}, {"type": "recall", "value": 0.9926393819168928, "name": "Recall"}, {"type": "precision", "value": 0.9998948309407373, "name": "Precision"}, {"type": "f1", "value": 0.9962538967332931, "name": "F1"}]}]}]}	hchcsuim/FFPP-Raw_1FPS_faces-expand-0-aligned-normalize-image-mean-std	null	[ "transformers", "tensorboard", "safetensors", "swin", "image-classification", "generated_from_trainer", "dataset:imagefolder", "base_model:microsoft/swin-tiny-patch4-window7-224", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-12T07:07:02+00:00	[]	[]	TAGS #transformers #tensorboard #safetensors #swin #image-classification #generated_from_trainer #dataset-imagefolder #base_model-microsoft/swin-tiny-patch4-window7-224 #license-apache-2.0 #model-index #autotrain_compatible #endpoints_compatible #region-us	FFPP-Raw\_1FPS\_faces-expand-0-aligned-normalize-image-mean-std =============================================================== This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the imagefolder dataset. It achieves the following results on the evaluation set: * Loss: 0.0031 * Accuracy: 0.9984 * Recall: 0.9926 * Precision: 0.9999 * F1: 0.9963 * Roc Auc: 1.0000 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: 16 * eval\_batch\_size: 16 * seed: 42 * gradient\_accumulation\_steps: 4 * total\_train\_batch\_size: 64 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * lr\_scheduler\_warmup\_ratio: 0.1 * num\_epochs: 20 ### Training results ### Framework versions * Transformers 4.39.2 * Pytorch 2.2.2 * Datasets 2.18.0 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\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* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 20", "### Training results", "### Framework versions\n\n\n* Transformers 4.39.2\n* Pytorch 2.2.2\n* Datasets 2.18.0\n* Tokenizers 0.15.2" ]	[ "TAGS\n#transformers #tensorboard #safetensors #swin #image-classification #generated_from_trainer #dataset-imagefolder #base_model-microsoft/swin-tiny-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: 5e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\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* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 20", "### Training results", "### Framework versions\n\n\n* Transformers 4.39.2\n* Pytorch 2.2.2\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": []}	abhayesian/BobzillaV10	null	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-04-12T07:08:19+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" ]
reinforcement-learning	stable-baselines3	# PPO Agent playing LunarLander-v2 This is a trained model of a PPO agent playing LunarLander-v2 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```	{"library_name": "stable-baselines3", "tags": ["LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "stable-baselines3"], "model-index": [{"name": "PPO", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "LunarLander-v2", "type": "LunarLander-v2"}, "metrics": [{"type": "mean_reward", "value": "295.04 +/- 11.93", "name": "mean_reward", "verified": false}]}]}]}	fanghostttt/ppo-LunarLander-v2	null	[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	null	2024-04-12T07:08:56+00:00	[]	[]	TAGS #stable-baselines3 #LunarLander-v2 #deep-reinforcement-learning #reinforcement-learning #model-index #region-us	# PPO Agent playing LunarLander-v2 This is a trained model of a PPO agent playing LunarLander-v2 using the stable-baselines3 library. ## Usage (with Stable-baselines3) TODO: Add your code	[ "# PPO Agent playing LunarLander-v2\nThis is a trained model of a PPO agent playing LunarLander-v2\nusing the stable-baselines3 library.", "## Usage (with Stable-baselines3)\nTODO: Add your code" ]	[ "TAGS\n#stable-baselines3 #LunarLander-v2 #deep-reinforcement-learning #reinforcement-learning #model-index #region-us \n", "# PPO Agent playing LunarLander-v2\nThis is a trained model of a PPO agent playing LunarLander-v2\nusing the stable-baselines3 library.", "## Usage (with Stable-baselines3)\nTODO: Add your code" ]
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": []}	bharathirajan89/bharathi_mistral_7b_pulse_tmp_3000_rows_summary	null	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-04-12T07:09:23+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" ]
question-answering	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. --> # distilbertbaselineoneepoch This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/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: 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: 1 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| No log \| 1.0 \| 3 \| 5.8912 \| ### Framework versions - Transformers 4.38.2 - Pytorch 2.2.1+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2	{"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "distilbert-base-uncased", "model-index": [{"name": "distilbertbaselineoneepoch", "results": []}]}	KarthikAlagarsamy/distilbertbaselineoneepoch	null	[ "transformers", "tensorboard", "safetensors", "distilbert", "question-answering", "generated_from_trainer", "base_model:distilbert-base-uncased", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2024-04-12T07:11:38+00:00	[]	[]	TAGS #transformers #tensorboard #safetensors #distilbert #question-answering #generated_from_trainer #base_model-distilbert-base-uncased #license-apache-2.0 #endpoints_compatible #region-us	distilbertbaselineoneepoch ========================== This model is a fine-tuned version of 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: 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: 1 ### Training results ### Framework versions * Transformers 4.38.2 * Pytorch 2.2.1+cu121 * Datasets 2.18.0 * Tokenizers 0.15.2	[ "### 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: 1", "### Training results", "### Framework versions\n\n\n* Transformers 4.38.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2" ]	[ "TAGS\n#transformers #tensorboard #safetensors #distilbert #question-answering #generated_from_trainer #base_model-distilbert-base-uncased #license-apache-2.0 #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: 1", "### Training results", "### Framework versions\n\n\n* Transformers 4.38.2\n* Pytorch 2.2.1+cu121\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. --> # Text_Summarization_model_12042024 This model is a fine-tuned version of [google-t5/t5-small](https://huggingface.co/google-t5/t5-small) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 1.5629 - Rouge1: 0.2385 - Rouge2: 0.19 - Rougel: 0.2296 - Rougelsum: 0.2296 - Gen Len: 19.0 ## 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: 4 - eval_batch_size: 4 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 4 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Rouge1 \| Rouge2 \| Rougel \| Rougelsum \| Gen Len \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:------:\|:------:\|:------:\|:---------:\|:-------:\| \| 1.8769 \| 1.0 \| 4691 \| 1.6645 \| 0.2336 \| 0.1826 \| 0.2236 \| 0.2236 \| 19.0 \| \| 1.826 \| 2.0 \| 9382 \| 1.5972 \| 0.2367 \| 0.1869 \| 0.2273 \| 0.2273 \| 19.0 \| \| 1.7617 \| 3.0 \| 14073 \| 1.5720 \| 0.2384 \| 0.1898 \| 0.2294 \| 0.2294 \| 19.0 \| \| 1.7664 \| 4.0 \| 18764 \| 1.5629 \| 0.2385 \| 0.19 \| 0.2296 \| 0.2296 \| 19.0 \| ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.15.2	{"license": "apache-2.0", "tags": ["generated_from_trainer"], "metrics": ["rouge"], "base_model": "google-t5/t5-small", "model-index": [{"name": "Text_Summarization_model_12042024", "results": []}]}	vishnun0027/Text_Summarization_model_12042024	null	[ "transformers", "tensorboard", "safetensors", "t5", "text2text-generation", "generated_from_trainer", "base_model:google-t5/t5-small", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-12T07:13:13+00:00	[]	[]	TAGS #transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-google-t5/t5-small #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us	Text\_Summarization\_model\_12042024 ==================================== This model is a fine-tuned version of google-t5/t5-small on an unknown dataset. It achieves the following results on the evaluation set: * Loss: 1.5629 * Rouge1: 0.2385 * Rouge2: 0.19 * Rougel: 0.2296 * Rougelsum: 0.2296 * Gen Len: 19.0 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: 4 * eval\_batch\_size: 4 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * num\_epochs: 4 * 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	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 4\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 4\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\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-google-t5/t5-small #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #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: 4\n* eval\\_batch\\_size: 4\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 4\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\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": []}	Momnadar/my-awesome-model	null	[ "transformers", "safetensors", "transformer.transformer", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-04-12T07:13:42+00:00	[ "1910.09700" ]	[]	TAGS #transformers #safetensors #transformer.transformer #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 #transformer.transformer #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	transformers	## About <!-- ### quantize_version: 1 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: --> <!-- ### vocab_type: --> weighted/imatrix quants of https://huggingface.co/jukofyork/Eurus-70b-sft-fixed <!-- provided-files --> static quants are available at https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-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/Eurus-70b-sft-fixed-i1-GGUF/resolve/main/Eurus-70b-sft-fixed.i1-IQ1_S.gguf) \| i1-IQ1_S \| 14.6 \| for the desperate \| \| [GGUF](https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-i1-GGUF/resolve/main/Eurus-70b-sft-fixed.i1-IQ1_M.gguf) \| i1-IQ1_M \| 16.0 \| for the desperate \| \| [GGUF](https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-i1-GGUF/resolve/main/Eurus-70b-sft-fixed.i1-IQ2_XXS.gguf) \| i1-IQ2_XXS \| 18.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-i1-GGUF/resolve/main/Eurus-70b-sft-fixed.i1-IQ2_XS.gguf) \| i1-IQ2_XS \| 20.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-i1-GGUF/resolve/main/Eurus-70b-sft-fixed.i1-IQ2_S.gguf) \| i1-IQ2_S \| 21.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-i1-GGUF/resolve/main/Eurus-70b-sft-fixed.i1-IQ2_M.gguf) \| i1-IQ2_M \| 23.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-i1-GGUF/resolve/main/Eurus-70b-sft-fixed.i1-Q2_K.gguf) \| i1-Q2_K \| 25.6 \| IQ3_XXS probably better \| \| [GGUF](https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-i1-GGUF/resolve/main/Eurus-70b-sft-fixed.i1-IQ3_XXS.gguf) \| i1-IQ3_XXS \| 26.7 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-i1-GGUF/resolve/main/Eurus-70b-sft-fixed.i1-IQ3_XS.gguf) \| i1-IQ3_XS \| 28.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-i1-GGUF/resolve/main/Eurus-70b-sft-fixed.i1-IQ3_S.gguf) \| i1-IQ3_S \| 30.0 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-i1-GGUF/resolve/main/Eurus-70b-sft-fixed.i1-Q3_K_S.gguf) \| i1-Q3_K_S \| 30.0 \| IQ3_XS probably better \| \| [GGUF](https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-i1-GGUF/resolve/main/Eurus-70b-sft-fixed.i1-IQ3_M.gguf) \| i1-IQ3_M \| 31.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-i1-GGUF/resolve/main/Eurus-70b-sft-fixed.i1-Q3_K_M.gguf) \| i1-Q3_K_M \| 33.4 \| IQ3_S probably better \| \| [GGUF](https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-i1-GGUF/resolve/main/Eurus-70b-sft-fixed.i1-Q3_K_L.gguf) \| i1-Q3_K_L \| 36.2 \| IQ3_M probably better \| \| [GGUF](https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-i1-GGUF/resolve/main/Eurus-70b-sft-fixed.i1-IQ4_XS.gguf) \| i1-IQ4_XS \| 36.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-i1-GGUF/resolve/main/Eurus-70b-sft-fixed.i1-Q4_0.gguf) \| i1-Q4_0 \| 39.1 \| fast, low quality \| \| [GGUF](https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-i1-GGUF/resolve/main/Eurus-70b-sft-fixed.i1-Q4_K_S.gguf) \| i1-Q4_K_S \| 39.3 \| optimal size/speed/quality \| \| [GGUF](https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-i1-GGUF/resolve/main/Eurus-70b-sft-fixed.i1-Q4_K_M.gguf) \| i1-Q4_K_M \| 41.5 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-i1-GGUF/resolve/main/Eurus-70b-sft-fixed.i1-Q5_K_S.gguf) \| i1-Q5_K_S \| 47.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-i1-GGUF/resolve/main/Eurus-70b-sft-fixed.i1-Q5_K_M.gguf) \| i1-Q5_K_M \| 48.9 \| \| \| [PART 1](https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-i1-GGUF/resolve/main/Eurus-70b-sft-fixed.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Eurus-70b-sft-fixed-i1-GGUF/resolve/main/Eurus-70b-sft-fixed.i1-Q6_K.gguf.part2of2) \| i1-Q6_K \| 56.7 \| 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": "apache-2.0", "library_name": "transformers", "tags": ["reasoning"], "datasets": ["openbmb/UltraInteract_sft", "stingning/ultrachat", "openchat/openchat_sharegpt4_dataset", "Open-Orca/OpenOrca"], "base_model": "jukofyork/Eurus-70b-sft-fixed", "quantized_by": "mradermacher"}	mradermacher/Eurus-70b-sft-fixed-i1-GGUF	null	[ "transformers", "gguf", "reasoning", "en", "dataset:openbmb/UltraInteract_sft", "dataset:stingning/ultrachat", "dataset:openchat/openchat_sharegpt4_dataset", "dataset:Open-Orca/OpenOrca", "base_model:jukofyork/Eurus-70b-sft-fixed", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2024-04-12T07:14:07+00:00	[]	[ "en" ]	TAGS #transformers #gguf #reasoning #en #dataset-openbmb/UltraInteract_sft #dataset-stingning/ultrachat #dataset-openchat/openchat_sharegpt4_dataset #dataset-Open-Orca/OpenOrca #base_model-jukofyork/Eurus-70b-sft-fixed #license-apache-2.0 #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 #reasoning #en #dataset-openbmb/UltraInteract_sft #dataset-stingning/ultrachat #dataset-openchat/openchat_sharegpt4_dataset #dataset-Open-Orca/OpenOrca #base_model-jukofyork/Eurus-70b-sft-fixed #license-apache-2.0 #endpoints_compatible #region-us \n" ]
null	transformers	This model has been pushed to the Hub using ****: - Repo: [More Information Needed] - Docs: [More Information Needed]	{"tags": ["pytorch_model_hub_mixin", "model_hub_mixin"]}	Sungeeta/my-model	null	[ "transformers", "safetensors", "pytorch_model_hub_mixin", "model_hub_mixin", "endpoints_compatible", "region:us" ]	null	2024-04-12T07:14:45+00:00	[]	[]	TAGS #transformers #safetensors #pytorch_model_hub_mixin #model_hub_mixin #endpoints_compatible #region-us	This model has been pushed to the Hub using : - Repo: - Docs:	[]	[ "TAGS\n#transformers #safetensors #pytorch_model_hub_mixin #model_hub_mixin #endpoints_compatible #region-us \n" ]
feature-extraction	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": []}	ahnyeonchan/fluent-capybara-27-replication-merged	null	[ "transformers", "safetensors", "llama", "feature-extraction", "arxiv:1910.09700", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-12T07:15:29+00:00	[ "1910.09700" ]	[]	TAGS #transformers #safetensors #llama #feature-extraction #arxiv-1910.09700 #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 #feature-extraction #arxiv-1910.09700 #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. --> # biomistral-7b-wo-live_qa-sft This model is a fine-tuned version of [BioMistral/BioMistral-7B](https://huggingface.co/BioMistral/BioMistral-7B) on the HuggingFaceH4/deita-10k-v0-sft dataset. It achieves the following results on the evaluation set: - Loss: 1.7868 ## 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: 4 - eval_batch_size: 4 - seed: 42 - distributed_type: multi-GPU - num_devices: 4 - gradient_accumulation_steps: 4 - total_train_batch_size: 64 - total_eval_batch_size: 16 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 3 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| 1.3886 \| 0.92 \| 6 \| 1.7428 \| \| 1.1058 \| 2.0 \| 13 \| 1.7567 \| \| 0.8548 \| 2.77 \| 18 \| 1.7868 \| ### Framework versions - Transformers 4.39.0.dev0 - Pytorch 2.1.2 - Datasets 2.14.6 - Tokenizers 0.15.2	{"license": "apache-2.0", "tags": ["alignment-handbook", "trl", "sft", "generated_from_trainer", "trl", "sft", "generated_from_trainer"], "datasets": ["HuggingFaceH4/deita-10k-v0-sft"], "base_model": "BioMistral/BioMistral-7B", "model-index": [{"name": "biomistral-7b-wo-live_qa-sft", "results": []}]}	Minbyul/biomistral-7b-wo-live_qa-sft	null	[ "transformers", "safetensors", "mistral", "text-generation", "alignment-handbook", "trl", "sft", "generated_from_trainer", "conversational", "dataset:HuggingFaceH4/deita-10k-v0-sft", "base_model:BioMistral/BioMistral-7B", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-12T07:16:01+00:00	[]	[]	TAGS #transformers #safetensors #mistral #text-generation #alignment-handbook #trl #sft #generated_from_trainer #conversational #dataset-HuggingFaceH4/deita-10k-v0-sft #base_model-BioMistral/BioMistral-7B #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us	biomistral-7b-wo-live\_qa-sft ============================= This model is a fine-tuned version of BioMistral/BioMistral-7B on the HuggingFaceH4/deita-10k-v0-sft dataset. It achieves the following results on the evaluation set: * Loss: 1.7868 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: 4 * eval\_batch\_size: 4 * seed: 42 * distributed\_type: multi-GPU * num\_devices: 4 * gradient\_accumulation\_steps: 4 * total\_train\_batch\_size: 64 * total\_eval\_batch\_size: 16 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: cosine * lr\_scheduler\_warmup\_ratio: 0.1 * num\_epochs: 3 ### Training results ### Framework versions * Transformers 4.39.0.dev0 * Pytorch 2.1.2 * Datasets 2.14.6 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 4\n* seed: 42\n* distributed\\_type: multi-GPU\n* num\\_devices: 4\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 64\n* total\\_eval\\_batch\\_size: 16\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: 3", "### Training results", "### Framework versions\n\n\n* Transformers 4.39.0.dev0\n* Pytorch 2.1.2\n* Datasets 2.14.6\n* Tokenizers 0.15.2" ]	[ "TAGS\n#transformers #safetensors #mistral #text-generation #alignment-handbook #trl #sft #generated_from_trainer #conversational #dataset-HuggingFaceH4/deita-10k-v0-sft #base_model-BioMistral/BioMistral-7B #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #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: 4\n* eval\\_batch\\_size: 4\n* seed: 42\n* distributed\\_type: multi-GPU\n* num\\_devices: 4\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 64\n* total\\_eval\\_batch\\_size: 16\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: 3", "### Training results", "### Framework versions\n\n\n* Transformers 4.39.0.dev0\n* Pytorch 2.1.2\n* Datasets 2.14.6\n* Tokenizers 0.15.2" ]
reinforcement-learning	ml-agents	# poca Agent playing SoccerTwos This is a trained model of a poca agent playing SoccerTwos using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents). ## Usage (with ML-Agents) The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A short tutorial where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction - A longer tutorial to understand how works ML-Agents: https://huggingface.co/learn/deep-rl-course/unit5/introduction ### Resume the training ```bash mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume ``` ### Watch your Agent play You can watch your agent playing directly in your browser 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity 2. Step 1: Find your model_id: AlidarAsvarov/ML-Agents-SocerTwos 3. Step 2: Select your .nn /.onnx file 4. Click on Watch the agent play 👀	{"library_name": "ml-agents", "tags": ["SoccerTwos", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-SoccerTwos"]}	AlidarAsvarov/ML-Agents-SocerTwos	null	[ "ml-agents", "tensorboard", "onnx", "SoccerTwos", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-SoccerTwos", "region:us" ]	null	2024-04-12T07:17:47+00:00	[]	[]	TAGS #ml-agents #tensorboard #onnx #SoccerTwos #deep-reinforcement-learning #reinforcement-learning #ML-Agents-SoccerTwos #region-us	# poca Agent playing SoccerTwos This is a trained model of a poca agent playing SoccerTwos using the Unity ML-Agents Library. ## Usage (with ML-Agents) The Documentation: URL We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A short tutorial where you teach Huggy the Dog to fetch the stick and then play with him directly in your browser: URL - A longer tutorial to understand how works ML-Agents: URL ### Resume the training ### Watch your Agent play You can watch your agent playing directly in your browser 1. If the environment is part of ML-Agents official environments, go to URL 2. Step 1: Find your model_id: AlidarAsvarov/ML-Agents-SocerTwos 3. Step 2: Select your .nn /.onnx file 4. Click on Watch the agent play	[ "# poca Agent playing SoccerTwos\n This is a trained model of a poca agent playing SoccerTwos\n using the Unity ML-Agents Library.\n\n ## Usage (with ML-Agents)\n The Documentation: URL\n\n We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:\n - A short tutorial where you teach Huggy the Dog to fetch the stick and then play with him directly in your\n browser: URL\n - A longer tutorial to understand how works ML-Agents:\n URL\n\n ### Resume the training\n \n\n ### Watch your Agent play\n You can watch your agent playing directly in your browser\n\n 1. If the environment is part of ML-Agents official environments, go to URL\n 2. Step 1: Find your model_id: AlidarAsvarov/ML-Agents-SocerTwos\n 3. Step 2: Select your .nn /.onnx file\n 4. Click on Watch the agent play" ]	[ "TAGS\n#ml-agents #tensorboard #onnx #SoccerTwos #deep-reinforcement-learning #reinforcement-learning #ML-Agents-SoccerTwos #region-us \n", "# poca Agent playing SoccerTwos\n This is a trained model of a poca agent playing SoccerTwos\n using the Unity ML-Agents Library.\n\n ## Usage (with ML-Agents)\n The Documentation: URL\n\n We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:\n - A short tutorial where you teach Huggy the Dog to fetch the stick and then play with him directly in your\n browser: URL\n - A longer tutorial to understand how works ML-Agents:\n URL\n\n ### Resume the training\n \n\n ### Watch your Agent play\n You can watch your agent playing directly in your browser\n\n 1. If the environment is part of ML-Agents official environments, go to URL\n 2. Step 1: Find your model_id: AlidarAsvarov/ML-Agents-SocerTwos\n 3. Step 2: Select your .nn /.onnx file\n 4. Click on Watch the agent play" ]
text-classification	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": []}	aniket-jain-9/distilbert-finetuned-imdb-sentiment	null	[ "transformers", "safetensors", "distilbert", "text-classification", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-12T07:18:45+00:00	[ "1910.09700" ]	[]	TAGS #transformers #safetensors #distilbert #text-classification #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 #distilbert #text-classification #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" ]
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": []}	Niyantha23M/llama-7b-chat-50000-25-75-L	null	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-04-12T07:19:10+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-classification	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": []}	Vxnkyyyyy/distilbert-finetuned-imdb-sentiment	null	[ "transformers", "safetensors", "distilbert", "text-classification", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-12T07:22:57+00:00	[ "1910.09700" ]	[]	TAGS #transformers #safetensors #distilbert #text-classification #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 #distilbert #text-classification #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-classification	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": []}	uchaturvedi/distilbert-finetuned-imdb-sentiment	null	[ "transformers", "safetensors", "distilbert", "text-classification", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-12T07:23:51+00:00	[ "1910.09700" ]	[]	TAGS #transformers #safetensors #distilbert #text-classification #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 #distilbert #text-classification #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-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_modelaa This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.2359 - Accuracy: 0.9312 ## 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 \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| 0.2214 \| 1.0 \| 1563 \| 0.2228 \| 0.9172 \| \| 0.1442 \| 2.0 \| 3126 \| 0.2359 \| 0.9312 \| ### Framework versions - Transformers 4.38.2 - Pytorch 2.2.1+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2	{"license": "apache-2.0", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "distilbert/distilbert-base-uncased", "model-index": [{"name": "my_awesome_modelaa", "results": []}]}	lenate/my_awesome_modelaa	null	[ "transformers", "tensorboard", "safetensors", "distilbert", "text-classification", "generated_from_trainer", "base_model:distilbert/distilbert-base-uncased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-12T07:25:42+00:00	[]	[]	TAGS #transformers #tensorboard #safetensors #distilbert #text-classification #generated_from_trainer #base_model-distilbert/distilbert-base-uncased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us	my\_awesome\_modelaa ==================== This model is a fine-tuned version of distilbert/distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set: * Loss: 0.2359 * Accuracy: 0.9312 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 4.38.2 * Pytorch 2.2.1+cu121 * Datasets 2.18.0 * Tokenizers 0.15.2	[ "### 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 4.38.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2" ]	[ "TAGS\n#transformers #tensorboard #safetensors #distilbert #text-classification #generated_from_trainer #base_model-distilbert/distilbert-base-uncased #license-apache-2.0 #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 4.38.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2" ]
null	transformers	# DavidAU/StarDust_20B_v0.2-Q4_K_S-GGUF This model was converted to GGUF format from [`Evillain/StarDust_20B_v0.2`](https://huggingface.co/Evillain/StarDust_20B_v0.2) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. Refer to the [original model card](https://huggingface.co/Evillain/StarDust_20B_v0.2) for more details on the model. ## Use with llama.cpp Install llama.cpp through brew. ```bash brew install ggerganov/ggerganov/llama.cpp ``` Invoke the llama.cpp server or the CLI. CLI: ```bash llama-cli --hf-repo DavidAU/StarDust_20B_v0.2-Q4_K_S-GGUF --model stardust_20b_v0.2.Q4_K_S.gguf -p "The meaning to life and the universe is" ``` Server: ```bash llama-server --hf-repo DavidAU/StarDust_20B_v0.2-Q4_K_S-GGUF --model stardust_20b_v0.2.Q4_K_S.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. ``` git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m stardust_20b_v0.2.Q4_K_S.gguf -n 128 ```	{"license": "other", "library_name": "transformers", "tags": ["mergekit", "merge", "not-for-all-audiences", "llama-cpp", "gguf-my-repo"], "base_model": ["Kooten/DaringMaid-20B", "TeeZee/DarkForest-20B-v2.0", "athirdpath/Iambe-RP-v3-20b"], "license_name": "microsoft-research-license", "model-index": [{"name": "StarDust_20B_v0.2", "results": [{"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "AI2 Reasoning Challenge (25-Shot)", "type": "ai2_arc", "config": "ARC-Challenge", "split": "test", "args": {"num_few_shot": 25}}, "metrics": [{"type": "acc_norm", "value": 61.01, "name": "normalized accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Evillain/StarDust_20B_v0.2", "name": "Open LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "HellaSwag (10-Shot)", "type": "hellaswag", "split": "validation", "args": {"num_few_shot": 10}}, "metrics": [{"type": "acc_norm", "value": 83.76, "name": "normalized accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Evillain/StarDust_20B_v0.2", "name": "Open LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "MMLU (5-Shot)", "type": "cais/mmlu", "config": "all", "split": "test", "args": {"num_few_shot": 5}}, "metrics": [{"type": "acc", "value": 59.29, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Evillain/StarDust_20B_v0.2", "name": "Open LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "TruthfulQA (0-shot)", "type": "truthful_qa", "config": "multiple_choice", "split": "validation", "args": {"num_few_shot": 0}}, "metrics": [{"type": "mc2", "value": 51.43}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Evillain/StarDust_20B_v0.2", "name": "Open LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "Winogrande (5-shot)", "type": "winogrande", "config": "winogrande_xl", "split": "validation", "args": {"num_few_shot": 5}}, "metrics": [{"type": "acc", "value": 77.27, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Evillain/StarDust_20B_v0.2", "name": "Open LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "GSM8k (5-shot)", "type": "gsm8k", "config": "main", "split": "test", "args": {"num_few_shot": 5}}, "metrics": [{"type": "acc", "value": 24.03, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Evillain/StarDust_20B_v0.2", "name": "Open LLM Leaderboard"}}]}]}	DavidAU/StarDust_20B_v0.2-Q4_K_S-GGUF	null	[ "transformers", "gguf", "mergekit", "merge", "not-for-all-audiences", "llama-cpp", "gguf-my-repo", "base_model:Kooten/DaringMaid-20B", "base_model:TeeZee/DarkForest-20B-v2.0", "base_model:athirdpath/Iambe-RP-v3-20b", "license:other", "model-index", "endpoints_compatible", "region:us" ]	null	2024-04-12T07:26:36+00:00	[]	[]	TAGS #transformers #gguf #mergekit #merge #not-for-all-audiences #llama-cpp #gguf-my-repo #base_model-Kooten/DaringMaid-20B #base_model-TeeZee/DarkForest-20B-v2.0 #base_model-athirdpath/Iambe-RP-v3-20b #license-other #model-index #endpoints_compatible #region-us	# DavidAU/StarDust_20B_v0.2-Q4_K_S-GGUF This model was converted to GGUF format from 'Evillain/StarDust_20B_v0.2' using URL via the URL's GGUF-my-repo space. Refer to the original model card for more details on the model. ## Use with URL Install URL through brew. Invoke the URL server or the CLI. CLI: Server: Note: You can also use this checkpoint directly through the usage steps listed in the URL repo as well.	[ "# DavidAU/StarDust_20B_v0.2-Q4_K_S-GGUF\nThis model was converted to GGUF format from 'Evillain/StarDust_20B_v0.2' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]	[ "TAGS\n#transformers #gguf #mergekit #merge #not-for-all-audiences #llama-cpp #gguf-my-repo #base_model-Kooten/DaringMaid-20B #base_model-TeeZee/DarkForest-20B-v2.0 #base_model-athirdpath/Iambe-RP-v3-20b #license-other #model-index #endpoints_compatible #region-us \n", "# DavidAU/StarDust_20B_v0.2-Q4_K_S-GGUF\nThis model was converted to GGUF format from 'Evillain/StarDust_20B_v0.2' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]
question-answering	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. --> # albertbaselineoneepoch This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/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: 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: 1 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| No log \| 1.0 \| 3 \| 5.9426 \| ### Framework versions - Transformers 4.38.2 - Pytorch 2.2.1+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2	{"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "distilbert-base-uncased", "model-index": [{"name": "albertbaselineoneepoch", "results": []}]}	KarthikAlagarsamy/albertbaselineoneepoch	null	[ "transformers", "tensorboard", "safetensors", "distilbert", "question-answering", "generated_from_trainer", "base_model:distilbert-base-uncased", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2024-04-12T07:27:32+00:00	[]	[]	TAGS #transformers #tensorboard #safetensors #distilbert #question-answering #generated_from_trainer #base_model-distilbert-base-uncased #license-apache-2.0 #endpoints_compatible #region-us	albertbaselineoneepoch ====================== This model is a fine-tuned version of 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: 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: 1 ### Training results ### Framework versions * Transformers 4.38.2 * Pytorch 2.2.1+cu121 * Datasets 2.18.0 * Tokenizers 0.15.2	[ "### 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: 1", "### Training results", "### Framework versions\n\n\n* Transformers 4.38.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2" ]	[ "TAGS\n#transformers #tensorboard #safetensors #distilbert #question-answering #generated_from_trainer #base_model-distilbert-base-uncased #license-apache-2.0 #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: 1", "### Training results", "### Framework versions\n\n\n* Transformers 4.38.2\n* Pytorch 2.2.1+cu121\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": []}	Niyantha23M/llama-7b-chat-50000-50-50-L	null	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-04-12T07:30:49+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	# Hypothesentrainer: LLM für Feedback auf Schülerhypothesen Deutschsprachiges LLM, das basierend auf biologischen Forschungsfragen, Schülerhypothesn und Feedback von GPT-4-Turbo mittels Fine-Tuning auf diese spezifische Aufgabe angepasst wurde. Das Feedback von GPT-4 wurde mittels eines größeren Prompts so angepasst, dass das Resultat didaktisch möglichst sinnvoll ist. Basis dieses Modells ist das deutschsprachige Chat-LLM https://huggingface.co/LeoLM/leo-hessianai-7b-chat, dass in einer zweiten Pre-Training-Phase das Llama-2 Modell von Meta an die deutschen Sprache angepasst hat. Zudem wurde anschließend das Modell in einer größeren Fine-Tuning-Phase auf die Beantwortung von Wissensfragen angepasst. ## Model Details - Model type: Causal decoder-only transformer language model - Finetuned from model [optional]: https://huggingface.co/LeoLM/leo-hessianai-7b-chat - Language(s) (NLP): German - License: https://huggingface.co/meta-llama/Llama-2-70b/raw/main/LICENSE.txt ## Use in 🤗Transformers Installationen: ``` pip install transformers torch sentencepiece ``` Für schnellere Inferenz, nicht zwingend notwendig (Empfehlung aus https://huggingface.co/LeoLM/leo-hessianai-7b-chat): ```bash pip install packaging ninja pip install flash-attn==v2.1.1 --no-build-isolation pip install git+https://github.com/HazyResearch/[email protected]#subdirectory=csrc/rotary ``` Modell laden: ```python from transformers import pipeline import torch question = "Wie beeinflusst die Temperatur die Aktivität der Hefe im Pizzateig?" hypothesis = "Je höher die Temperatur, desto höher die Hefeaktivität im Pizzateig." prompt = format_prompt_chat(question, hypothesis, with_additional_prompt=True) generator = pipeline(model="Tobiiax/full-training-7b", device="cuda", torch_dtype=torch.float16, trust_remote_code=True) # True for flash-attn2 else False print(generator(prompt, do_sample=True, top_p=0.95, max_length=2048)) ``` ### Beispiel: TODO ## Prompting Template wie in https://huggingface.co/LeoLM/leo-hessianai-7b-chat: ``` """ <\|im_start\|>system {system_message}<\|im_end\|> <\|im_start\|>user {prompt}<\|im_end\|> <\|im_start\|>assistant """ ``` Beispielfunktion für das Prompt Format: ```python def format_prompt_chat(question, hypothesis, with_additional_prompt=True): if with_additional_prompt: instructions = open_file("prompt/assistantInstructions.txt").strip() system_prompt = f"<\|im_start\|>system\n{inst}" else: system_prompt = "<\|im_start\|>system\nNachfolgend findest du eine biologische Forschungsfrage und eine entwickelte Schülerhypothese. Gebe dem Schüler auf seine Hypothese ein angemessenes Feedback, das didaktisch möglichst wertvoll formuliert ist." system_prompt += "<\|im_end\|>" student= f"## Forschungsfrage: {question}\n## Hypothese: {hypothesis}" prompt = f"{system_prompt}\n<\|im_start\|>user\n{student}<\|im_end\|>\n<\|im_start\|>assistant\n" return prompt ``` ## Finetuning Details - Für das Training wurde ein Datensatz mit 1093 Zeilen verwendet. - Es wurde auf einem TPU v3-32 Pod-Slice trainiert (https://cloud.google.com/tpu/docs/v3?hl=de). - Das Modell und die Daten wurden auf 4-TPU-v3-8-Knoten, also auf insgesamt 32 TensorCores bzw. Devices verteilt. - Die Dauer des Training betrug 16 Minuten und 36 Sekunden. \| Hyperparameter \| Value \| \|---\|---\| \| Num epochs \| 2 \| \| Examples per epoch \| 1093 // 8 // 32 = 4\| \| batch size \| 832 = 256 \| \| Learning rate \| 3e-5 \| \| LR scheduler \| Cosine \| \| Optimizer \| AdamW \| \| Adam betas \| (0.9, 0.95) \| ## Datensatz Details Beispiel: ``` Forschungsfrage: Welchen Einfluss hat die Temperatur auf die Aktivität der Hefe im Pizzateig? Hypothese: Durch die Wärme verdampft das Wasser im Teig und steigt und steigt nach oben. Feedback: Eure Hypothese stellt keinen direkten Zusammenhang zwischen der Temperatur und der Aktivität der Hefe her. Es beschreibt eher einen allgemeinen Prozess bei Erwärmung. Versucht, den Fokus auf die spezifische Frage zu legen, wie die Temperatur die Aktivität der Hefe beeinflusst. Überlegt, wie die Temperaturänderung die Hefe zum Wachsen, sich zu vermehren oder ihre Aktivität zu ändern veranlassen könnte. ``` ## Evaluation TODO*	{"library_name": "transformers", "tags": []}	Tobistd/full-training-7b	null	[ "transformers", "safetensors", "llama", "text-generation", "custom_code", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-12T07:30:59+00:00	[]	[]	TAGS #transformers #safetensors #llama #text-generation #custom_code #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us	Hypothesentrainer: LLM für Feedback auf Schülerhypothesen ========================================================= Deutschsprachiges LLM, das basierend auf biologischen Forschungsfragen, Schülerhypothesn und Feedback von GPT-4-Turbo mittels Fine-Tuning auf diese spezifische Aufgabe angepasst wurde. Das Feedback von GPT-4 wurde mittels eines größeren Prompts so angepasst, dass das Resultat didaktisch möglichst sinnvoll ist. Basis dieses Modells ist das deutschsprachige Chat-LLM URL dass in einer zweiten Pre-Training-Phase das Llama-2 Modell von Meta an die deutschen Sprache angepasst hat. Zudem wurde anschließend das Modell in einer größeren Fine-Tuning-Phase auf die Beantwortung von Wissensfragen angepasst. Model Details ------------- * Model type: Causal decoder-only transformer language model * Finetuned from model [optional]: URL * Language(s) (NLP): German * License: URL Use in Transformers ------------------- Installationen: Für schnellere Inferenz, nicht zwingend notwendig (Empfehlung aus URL Modell laden: ### Beispiel: TODO Prompting --------- Template wie in URL Beispielfunktion für das Prompt Format: Finetuning Details ------------------ * Für das Training wurde ein Datensatz mit 1093 Zeilen verwendet. * Es wurde auf einem TPU v3-32 Pod-Slice trainiert (URL * Das Modell und die Daten wurden auf 4-TPU-v3-8-Knoten, also auf insgesamt 32 TensorCores bzw. Devices verteilt. * Die Dauer des Training betrug 16 Minuten und 36 Sekunden. Datensatz Details ----------------- Beispiel: Evaluation ---------- TODO	[ "### Beispiel:\n\n\nTODO\n\n\nPrompting\n---------\n\n\nTemplate wie in URL\n\n\nBeispielfunktion für das Prompt Format:\n\n\nFinetuning Details\n------------------\n\n\n* Für das Training wurde ein Datensatz mit 1093 Zeilen verwendet.\n* Es wurde auf einem TPU v3-32 Pod-Slice trainiert (URL\n* Das Modell und die Daten wurden auf 4-TPU-v3-8-Knoten, also auf insgesamt 32 TensorCores bzw. Devices verteilt.\n* Die Dauer des Training betrug 16 Minuten und 36 Sekunden.\n\n\n\nDatensatz Details\n-----------------\n\n\nBeispiel:\n\n\nEvaluation\n----------\n\n\nTODO" ]	[ "TAGS\n#transformers #safetensors #llama #text-generation #custom_code #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "### Beispiel:\n\n\nTODO\n\n\nPrompting\n---------\n\n\nTemplate wie in URL\n\n\nBeispielfunktion für das Prompt Format:\n\n\nFinetuning Details\n------------------\n\n\n* Für das Training wurde ein Datensatz mit 1093 Zeilen verwendet.\n* Es wurde auf einem TPU v3-32 Pod-Slice trainiert (URL\n* Das Modell und die Daten wurden auf 4-TPU-v3-8-Knoten, also auf insgesamt 32 TensorCores bzw. Devices verteilt.\n* Die Dauer des Training betrug 16 Minuten und 36 Sekunden.\n\n\n\nDatensatz Details\n-----------------\n\n\nBeispiel:\n\n\nEvaluation\n----------\n\n\nTODO" ]
null	transformers	# DavidAU/StarDust_20B_v0.1_slerp-Q4_K_S-GGUF This model was converted to GGUF format from [`Evillain/StarDust_20B_v0.1_slerp`](https://huggingface.co/Evillain/StarDust_20B_v0.1_slerp) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. Refer to the [original model card](https://huggingface.co/Evillain/StarDust_20B_v0.1_slerp) for more details on the model. ## Use with llama.cpp Install llama.cpp through brew. ```bash brew install ggerganov/ggerganov/llama.cpp ``` Invoke the llama.cpp server or the CLI. CLI: ```bash llama-cli --hf-repo DavidAU/StarDust_20B_v0.1_slerp-Q4_K_S-GGUF --model stardust_20b_v0.1_slerp.Q4_K_S.gguf -p "The meaning to life and the universe is" ``` Server: ```bash llama-server --hf-repo DavidAU/StarDust_20B_v0.1_slerp-Q4_K_S-GGUF --model stardust_20b_v0.1_slerp.Q4_K_S.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. ``` git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m stardust_20b_v0.1_slerp.Q4_K_S.gguf -n 128 ```	{"license": "other", "library_name": "transformers", "tags": ["mergekit", "merge", "not-for-all-audiences", "llama-cpp", "gguf-my-repo"], "base_model": ["Kooten/DaringMaid-20B-V1.1", "TeeZee/DarkForest-20B-v2.0", "athirdpath/Iambe-RP-v3-20b"], "license_name": "microsoft-research-license"}	DavidAU/StarDust_20B_v0.1_slerp-Q4_K_S-GGUF	null	[ "transformers", "gguf", "mergekit", "merge", "not-for-all-audiences", "llama-cpp", "gguf-my-repo", "base_model:Kooten/DaringMaid-20B-V1.1", "base_model:TeeZee/DarkForest-20B-v2.0", "base_model:athirdpath/Iambe-RP-v3-20b", "license:other", "endpoints_compatible", "region:us" ]	null	2024-04-12T07:32:03+00:00	[]	[]	TAGS #transformers #gguf #mergekit #merge #not-for-all-audiences #llama-cpp #gguf-my-repo #base_model-Kooten/DaringMaid-20B-V1.1 #base_model-TeeZee/DarkForest-20B-v2.0 #base_model-athirdpath/Iambe-RP-v3-20b #license-other #endpoints_compatible #region-us	# DavidAU/StarDust_20B_v0.1_slerp-Q4_K_S-GGUF This model was converted to GGUF format from 'Evillain/StarDust_20B_v0.1_slerp' using URL via the URL's GGUF-my-repo space. Refer to the original model card for more details on the model. ## Use with URL Install URL through brew. Invoke the URL server or the CLI. CLI: Server: Note: You can also use this checkpoint directly through the usage steps listed in the URL repo as well.	[ "# DavidAU/StarDust_20B_v0.1_slerp-Q4_K_S-GGUF\nThis model was converted to GGUF format from 'Evillain/StarDust_20B_v0.1_slerp' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]	[ "TAGS\n#transformers #gguf #mergekit #merge #not-for-all-audiences #llama-cpp #gguf-my-repo #base_model-Kooten/DaringMaid-20B-V1.1 #base_model-TeeZee/DarkForest-20B-v2.0 #base_model-athirdpath/Iambe-RP-v3-20b #license-other #endpoints_compatible #region-us \n", "# DavidAU/StarDust_20B_v0.1_slerp-Q4_K_S-GGUF\nThis model was converted to GGUF format from 'Evillain/StarDust_20B_v0.1_slerp' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]
feature-extraction	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": []}	stvhuang/rcr-run-5pqr6lwp-90396-master-0_20240402T105012-ep12	null	[ "transformers", "safetensors", "xlm-roberta", "feature-extraction", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-04-12T07:32:37+00:00	[ "1910.09700" ]	[]	TAGS #transformers #safetensors #xlm-roberta #feature-extraction #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 #xlm-roberta #feature-extraction #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. --> # mistral-7b-wo-live_qa-sft This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the HuggingFaceH4/deita-10k-v0-sft dataset. It achieves the following results on the evaluation set: - Loss: 1.6476 ## 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: 4 - eval_batch_size: 4 - seed: 42 - distributed_type: multi-GPU - num_devices: 4 - gradient_accumulation_steps: 4 - total_train_batch_size: 64 - total_eval_batch_size: 16 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 3 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| 1.6461 \| 0.92 \| 6 \| 1.7001 \| \| 1.1299 \| 2.0 \| 13 \| 1.6488 \| \| 0.9123 \| 2.77 \| 18 \| 1.6476 \| ### Framework versions - Transformers 4.39.0.dev0 - Pytorch 2.1.2 - Datasets 2.14.6 - Tokenizers 0.15.2	{"license": "apache-2.0", "tags": ["alignment-handbook", "trl", "sft", "generated_from_trainer", "trl", "sft", "generated_from_trainer"], "datasets": ["HuggingFaceH4/deita-10k-v0-sft"], "base_model": "mistralai/Mistral-7B-v0.1", "model-index": [{"name": "mistral-7b-wo-live_qa-sft", "results": []}]}	Minbyul/mistral-7b-wo-live_qa-sft	null	[ "transformers", "safetensors", "mistral", "text-generation", "alignment-handbook", "trl", "sft", "generated_from_trainer", "dataset:HuggingFaceH4/deita-10k-v0-sft", "base_model:mistralai/Mistral-7B-v0.1", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-12T07:32:44+00:00	[]	[]	TAGS #transformers #safetensors #mistral #text-generation #alignment-handbook #trl #sft #generated_from_trainer #dataset-HuggingFaceH4/deita-10k-v0-sft #base_model-mistralai/Mistral-7B-v0.1 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us	mistral-7b-wo-live\_qa-sft ========================== This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the HuggingFaceH4/deita-10k-v0-sft dataset. It achieves the following results on the evaluation set: * Loss: 1.6476 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: 4 * eval\_batch\_size: 4 * seed: 42 * distributed\_type: multi-GPU * num\_devices: 4 * gradient\_accumulation\_steps: 4 * total\_train\_batch\_size: 64 * total\_eval\_batch\_size: 16 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: cosine * lr\_scheduler\_warmup\_ratio: 0.1 * num\_epochs: 3 ### Training results ### Framework versions * Transformers 4.39.0.dev0 * Pytorch 2.1.2 * Datasets 2.14.6 * Tokenizers 0.15.2	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 4\n* seed: 42\n* distributed\\_type: multi-GPU\n* num\\_devices: 4\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 64\n* total\\_eval\\_batch\\_size: 16\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: 3", "### Training results", "### Framework versions\n\n\n* Transformers 4.39.0.dev0\n* Pytorch 2.1.2\n* Datasets 2.14.6\n* Tokenizers 0.15.2" ]	[ "TAGS\n#transformers #safetensors #mistral #text-generation #alignment-handbook #trl #sft #generated_from_trainer #dataset-HuggingFaceH4/deita-10k-v0-sft #base_model-mistralai/Mistral-7B-v0.1 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #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: 4\n* eval\\_batch\\_size: 4\n* seed: 42\n* distributed\\_type: multi-GPU\n* num\\_devices: 4\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 64\n* total\\_eval\\_batch\\_size: 16\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: 3", "### Training results", "### Framework versions\n\n\n* Transformers 4.39.0.dev0\n* Pytorch 2.1.2\n* Datasets 2.14.6\n* Tokenizers 0.15.2" ]
text-generation	transformers	# GreenBit LLMs This is GreenBitAI's pretrained low-bit LLMs with extreme compression yet still strong performance. Please refer to our [Github page](https://github.com/GreenBitAI/green-bit-llm) for the code to run the model and more information.	{"license": "apache-2.0"}	GreenBitAI/Qwen-1.5-32B-channel-mix-bpw-2.2	null	[ "transformers", "safetensors", "qwen2", "text-generation", "conversational", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-12T07:34:45+00:00	[]	[]	TAGS #transformers #safetensors #qwen2 #text-generation #conversational #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us	# GreenBit LLMs This is GreenBitAI's pretrained low-bit LLMs with extreme compression yet still strong performance. Please refer to our Github page for the code to run the model and more information.	[ "# GreenBit LLMs\n\nThis is GreenBitAI's pretrained low-bit LLMs with extreme compression yet still strong performance.\n\nPlease refer to our Github page for the code to run the model and more information." ]	[ "TAGS\n#transformers #safetensors #qwen2 #text-generation #conversational #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# GreenBit LLMs\n\nThis is GreenBitAI's pretrained low-bit LLMs with extreme compression yet still strong performance.\n\nPlease refer to our Github page for the code to run the model and more information." ]
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. --> # mT5-TextSimp-LT-BatchSize4-lr1e-4 This model is a fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.0737 - Rouge1: 0.7174 - Rouge2: 0.5553 - Rougel: 0.7108 - Sacrebleu: 43.3127 - Gen Len: 38.0501 ## 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: 0.0001 - train_batch_size: 4 - eval_batch_size: 4 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - num_epochs: 8 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Rouge1 \| Rouge2 \| Rougel \| Sacrebleu \| Gen Len \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:------:\|:------:\|:------:\|:---------:\|:-------:\| \| 25.4634 \| 0.48 \| 200 \| 18.5157 \| 0.0061 \| 0.0 \| 0.0059 \| 0.0008 \| 512.0 \| \| 1.1451 \| 0.96 \| 400 \| 0.6596 \| 0.0161 \| 0.0003 \| 0.0154 \| 0.0215 \| 39.0453 \| \| 0.6441 \| 1.44 \| 600 \| 0.4981 \| 0.0272 \| 0.0012 \| 0.0259 \| 0.0166 \| 39.0453 \| \| 0.247 \| 1.91 \| 800 \| 0.1420 \| 0.4769 \| 0.2826 \| 0.465 \| 20.3212 \| 38.0501 \| \| 0.1549 \| 2.39 \| 1000 \| 0.1032 \| 0.6114 \| 0.4299 \| 0.5998 \| 30.2603 \| 38.0501 \| \| 0.1482 \| 2.87 \| 1200 \| 0.0934 \| 0.6592 \| 0.4815 \| 0.6496 \| 34.4213 \| 38.0501 \| \| 0.1163 \| 3.35 \| 1400 \| 0.0867 \| 0.6734 \| 0.4968 \| 0.6651 \| 36.3741 \| 38.0501 \| \| 0.1042 \| 3.83 \| 1600 \| 0.0816 \| 0.6826 \| 0.5127 \| 0.6753 \| 38.128 \| 38.0501 \| \| 0.1109 \| 4.31 \| 1800 \| 0.0816 \| 0.6893 \| 0.5191 \| 0.6818 \| 39.3294 \| 38.0501 \| \| 0.1029 \| 4.78 \| 2000 \| 0.0798 \| 0.6968 \| 0.5284 \| 0.6901 \| 40.5064 \| 38.0501 \| \| 0.0877 \| 5.26 \| 2200 \| 0.0766 \| 0.7006 \| 0.5372 \| 0.694 \| 40.5295 \| 38.0501 \| \| 0.0748 \| 5.74 \| 2400 \| 0.0759 \| 0.7092 \| 0.5403 \| 0.7028 \| 41.4424 \| 38.0501 \| \| 0.0941 \| 6.22 \| 2600 \| 0.0754 \| 0.7134 \| 0.5471 \| 0.7066 \| 42.4212 \| 38.0501 \| \| 0.1095 \| 6.7 \| 2800 \| 0.0737 \| 0.7198 \| 0.5547 \| 0.7135 \| 42.8225 \| 38.0501 \| \| 0.0749 \| 7.18 \| 3000 \| 0.0735 \| 0.7165 \| 0.5536 \| 0.7107 \| 42.9748 \| 38.0501 \| \| 0.073 \| 7.66 \| 3200 \| 0.0737 \| 0.7174 \| 0.5553 \| 0.7108 \| 43.3127 \| 38.0501 \| ### Framework versions - Transformers 4.33.0 - Pytorch 2.1.2+cu121 - Datasets 2.14.4 - Tokenizers 0.13.3	{"license": "apache-2.0", "tags": ["generated_from_trainer"], "metrics": ["rouge", "sacrebleu"], "base_model": "google/mt5-base", "model-index": [{"name": "mT5-TextSimp-LT-BatchSize4-lr1e-4", "results": []}]}	eglkan1/mT5-TextSimp-LT-BatchSize4-lr1e-4	null	[ "transformers", "pytorch", "t5", "text2text-generation", "generated_from_trainer", "base_model:google/mt5-base", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-12T07:35:38+00:00	[]	[]	TAGS #transformers #pytorch #t5 #text2text-generation #generated_from_trainer #base_model-google/mt5-base #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us	mT5-TextSimp-LT-BatchSize4-lr1e-4 ================================= This model is a fine-tuned version of google/mt5-base on the None dataset. It achieves the following results on the evaluation set: * Loss: 0.0737 * Rouge1: 0.7174 * Rouge2: 0.5553 * Rougel: 0.7108 * Sacrebleu: 43.3127 * Gen Len: 38.0501 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: 0.0001 * train\_batch\_size: 4 * eval\_batch\_size: 4 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * lr\_scheduler\_warmup\_steps: 500 * num\_epochs: 8 ### Training results ### Framework versions * Transformers 4.33.0 * Pytorch 2.1.2+cu121 * Datasets 2.14.4 * Tokenizers 0.13.3	[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0001\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 4\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\\_steps: 500\n* num\\_epochs: 8", "### Training results", "### Framework versions\n\n\n* Transformers 4.33.0\n* Pytorch 2.1.2+cu121\n* Datasets 2.14.4\n* Tokenizers 0.13.3" ]	[ "TAGS\n#transformers #pytorch #t5 #text2text-generation #generated_from_trainer #base_model-google/mt5-base #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0001\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 4\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\\_steps: 500\n* num\\_epochs: 8", "### Training results", "### Framework versions\n\n\n* Transformers 4.33.0\n* Pytorch 2.1.2+cu121\n* Datasets 2.14.4\n* Tokenizers 0.13.3" ]
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": []}	HeydarS/tiny_llama_witQA_peft_v54	null	[ "transformers", "safetensors", "llama", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]	null	2024-04-12T07:35:45+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	# merge 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 SLERP merge method. ### Models Merged The following models were included in the merge: * [NousResearch/Hermes-2-Pro-Mistral-7B](https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B) * [WizardLM/WizardMath-7B-V1.1](https://huggingface.co/WizardLM/WizardMath-7B-V1.1) ### Configuration The following YAML configuration was used to produce this model: ```yaml models: - model: NousResearch/Hermes-2-Pro-Mistral-7B - model: WizardLM/WizardMath-7B-V1.1 merge_method: slerp base_model: NousResearch/Hermes-2-Pro-Mistral-7B dtype: bfloat16 parameters: t: [0, 0.5, 1, 0.5, 0] # V shaped curve: Hermes for input & output, WizardMath in the middle layers ```	{"library_name": "transformers", "tags": ["mergekit", "merge"], "base_model": ["NousResearch/Hermes-2-Pro-Mistral-7B", "WizardLM/WizardMath-7B-V1.1"]}	mergekit-community/mergekit-slerp-wetopem	null	[ "transformers", "safetensors", "mistral", "text-generation", "mergekit", "merge", "conversational", "base_model:NousResearch/Hermes-2-Pro-Mistral-7B", "base_model:WizardLM/WizardMath-7B-V1.1", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-12T07:35:58+00:00	[]	[]	TAGS #transformers #safetensors #mistral #text-generation #mergekit #merge #conversational #base_model-NousResearch/Hermes-2-Pro-Mistral-7B #base_model-WizardLM/WizardMath-7B-V1.1 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us	# merge This is a merge of pre-trained language models created using mergekit. ## Merge Details ### Merge Method This model was merged using the SLERP merge method. ### Models Merged The following models were included in the merge: * NousResearch/Hermes-2-Pro-Mistral-7B * WizardLM/WizardMath-7B-V1.1 ### Configuration The following YAML configuration was used to produce this model:	[ "# merge\n\nThis is a merge of pre-trained language models created using mergekit.", "## Merge Details", "### Merge Method\n\nThis model was merged using the SLERP merge method.", "### Models Merged\n\nThe following models were included in the merge:\n* NousResearch/Hermes-2-Pro-Mistral-7B\n* WizardLM/WizardMath-7B-V1.1", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]	[ "TAGS\n#transformers #safetensors #mistral #text-generation #mergekit #merge #conversational #base_model-NousResearch/Hermes-2-Pro-Mistral-7B #base_model-WizardLM/WizardMath-7B-V1.1 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# merge\n\nThis is a merge of pre-trained language models created using mergekit.", "## Merge Details", "### Merge Method\n\nThis model was merged using the SLERP merge method.", "### Models Merged\n\nThe following models were included in the merge:\n* NousResearch/Hermes-2-Pro-Mistral-7B\n* WizardLM/WizardMath-7B-V1.1", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]
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. --> # llama-7b-chat-50000-75-25-L This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on the generator 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: 0.0002 - train_batch_size: 2200 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 4400 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: constant - lr_scheduler_warmup_ratio: 0.03 - num_epochs: 3 ### Training results ### Framework versions - PEFT 0.8.2 - Transformers 4.37.2 - Pytorch 2.2.0 - Datasets 2.17.0 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["trl", "sft", "generated_from_trainer"], "datasets": ["generator"], "base_model": "meta-llama/Llama-2-7b-chat-hf", "model-index": [{"name": "llama-7b-chat-50000-75-25-L", "results": []}]}	Niyantha23M/llama-7b-chat-50000-75-25-L	null	[ "peft", "safetensors", "trl", "sft", "generated_from_trainer", "dataset:generator", "base_model:meta-llama/Llama-2-7b-chat-hf", "region:us" ]	null	2024-04-12T07:36:36+00:00	[]	[]	TAGS #peft #safetensors #trl #sft #generated_from_trainer #dataset-generator #base_model-meta-llama/Llama-2-7b-chat-hf #region-us	# llama-7b-chat-50000-75-25-L This model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on the generator 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: 0.0002 - train_batch_size: 2200 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 4400 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: constant - lr_scheduler_warmup_ratio: 0.03 - num_epochs: 3 ### Training results ### Framework versions - PEFT 0.8.2 - Transformers 4.37.2 - Pytorch 2.2.0 - Datasets 2.17.0 - Tokenizers 0.15.2	[ "# llama-7b-chat-50000-75-25-L\n\nThis model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on the generator 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: 0.0002\n- train_batch_size: 2200\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 4400\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: constant\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 3", "### Training results", "### Framework versions\n\n- PEFT 0.8.2\n- Transformers 4.37.2\n- Pytorch 2.2.0\n- Datasets 2.17.0\n- Tokenizers 0.15.2" ]	[ "TAGS\n#peft #safetensors #trl #sft #generated_from_trainer #dataset-generator #base_model-meta-llama/Llama-2-7b-chat-hf #region-us \n", "# llama-7b-chat-50000-75-25-L\n\nThis model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on the generator 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: 0.0002\n- train_batch_size: 2200\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 4400\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: constant\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 3", "### Training results", "### Framework versions\n\n- PEFT 0.8.2\n- Transformers 4.37.2\n- Pytorch 2.2.0\n- Datasets 2.17.0\n- Tokenizers 0.15.2" ]
text-generation	transformers	<img align="right" src="https://huggingface.co/Tweeties/tweety-tatar-base-7b-2024-v1/resolve/main/TweetyTatar.png?download=true" alt="Tweety-Tatar-7B: A Tatar Large Language Model" width="20%"> # Tweety Tatar / Hydra-Base 7b / 2024-v1 ## Model description This model is our Hydra LLM for the [Tatar language](https://en.wikipedia.org/wiki/Tatar_language), converted from the [TowerInstruct-7b-v0.1](https://huggingface.co/Unbabel/TowerInstruct-7B-v0.1) model trained by Unbabel. Hydra LLMs are trans-tokenized language models finetuned to produce output in a particular language, while accepting input encoded using either their own tokenizer, the one of their base model, or a mix of both. This enables them to receive code-switched input in both their native language and other languages, which is an ideal setup for translation tasks, or retrieval-augmented generation (RAG) in cross-lingual scenarios. - Developed by: [François Remy](https://huggingface.co/FremyCompany) (UGent), [Alfiya Khabibullina](https://huggingface.co/justalphie) (BeCode), [et al.](#citation) - Funded by: IDLab / GPULab - Model type: Foundation model using the mistral architecture - Language(s) (NLP): Tatar - License: Creative Commons Attribution Non Commercial 4.0 ## In-scope usage This model can be used as-is to answer questions in Tatar based on a cross-lingual context, or finetuned into a machine translation system from one of the 10 languages supported by TowerInstruct into the Tatar language. This list of languages nobably includes English and Russian. The model performs best when translating sentences or small paragraphs, and is not suited for document translation tasks. This model should not be used in the reverse direction, to translate Tatar into English. When the system isn't finetuned, enabling beam search is recommended for best results. We also provide a model [finetuned for translation](https://huggingface.co/Tweeties/tweety-tatar-hydra-trans-7b-2024-v1), but take note of the non-commercial license imposed by Unbabel on the base model. ## Usage instructions Using this model usually requires building the prompts by mixing tokens from two tokenizers, the original TowerInstruct tokenizer for input in the source language, and the new Tatar tokenizer for the prompt and output, as described in the examples below: ```py import re import torch import torch.nn as nn import transformers MODEL_NAME = "Tweeties/tweety-tatar-hydra-base-7b-2024-v1" MAIN_TOKENIZER_NAME = "Tweeties/tweety-tatar-hydra-base-7b-2024-v1" UTIL_TOKENIZER_NAME = "Unbabel/TowerInstruct-7B-v0.1" model = transformers.AutoModelForCausalLM.from_pretrained(MODEL_NAME, trust_remote_code=True) main_tokenizer = transformers.LlamaTokenizerFast.from_pretrained(MAIN_TOKENIZER_NAME) util_tokenizer = transformers.LlamaTokenizerFast.from_pretrained(UTIL_TOKENIZER_NAME) main_tokenizer_len = len(main_tokenizer) ``` ### Cross-lingual question answering ```py def answer_english_question(english_text: str) -> str: # craft the input input_ids = torch.concat([ main_tokenizer.encode(f"Татар телендә түбәндәге сорауга җавап бирегез:\n", return_tensors='pt'), util_tokenizer.encode(f"{english_text}", add_special_tokens=False, return_tensors='pt') + torch.tensor([main_tokenizer_len]), main_tokenizer.encode(f"\n\nҗавап:\n", add_special_tokens=False, return_tensors='pt') ], axis=1) # prevent the model from repeating the prompt prompt_starts = [ main_tokenizer.encode("Түбәндәге"), main_tokenizer.encode("\nТүбәндәге")[2:], main_tokenizer.encode("Текстны"), main_tokenizer.encode("\nТекстны")[2:] ] # prevent the model from repeating the English text english_starts = [ main_tokenizer.encode(re.sub(r'[ ].', '', english_text)), main_tokenizer.encode('\n'+re.sub(r'[ ].', '', english_text))[2:], main_tokenizer.encode(re.sub(r'[ ].', '', english_text.upper())), main_tokenizer.encode('\n'+re.sub(r'[ ].', '', english_text.upper()))[2:], ] # genereate the output model_inputs = {'input_ids':input_ids.to(model.device)} model_outputs = model.generate( *model_inputs, max_new_tokens=5, num_beams=8, no_repeat_ngram_size=6, early_stopping=False, pad_token_id=main_tokenizer.eos_token_id, eos_token_id=main_tokenizer.convert_tokens_to_ids(['<0x0A>','</s>']), bad_words_ids=english_starts+prompt_starts ) # decode the output return (main_tokenizer.decode(model_outputs[0][input_ids.shape[1]:])) answer_english_question("Is Paris located in France?\n") # Әйе, Парижда ``` ### Machine Translation (see [finetuned model](https://huggingface.co/Tweeties/tweety-tatar-hydra-trans-7b-2024-v1)) ```py def translate_english_text(english_text: str) -> str: # craft the input input_ids = torch.concat([ main_tokenizer.encode(f"Түбәндәге текстны инглиз теленнән татар теленә тәрҗемә итегез:\n", return_tensors='pt'), util_tokenizer.encode(f"{english_text}", add_special_tokens=False, return_tensors='pt') + torch.tensor([main_tokenizer_len]), main_tokenizer.encode(f"\nТекстны татар теленә тәрҗемә итү:\n", add_special_tokens=False, return_tensors='pt') ], axis=1) # prevent the model from repeating the prompt prompt_starts = [ main_tokenizer.encode("Түбәндәге"), main_tokenizer.encode("\nТүбәндәге")[2:], main_tokenizer.encode("Текстны"), main_tokenizer.encode("\nТекстны")[2:] ] # prevent the model from repeating the English text english_starts = [ main_tokenizer.encode(re.sub(r'[ ].', '', english_text)), main_tokenizer.encode('\n'+re.sub(r'[ ].', '', english_text))[2:], main_tokenizer.encode(re.sub(r'[ ].', '', english_text.upper())), main_tokenizer.encode('\n'+re.sub(r'[ ].', '', english_text.upper()))[2:], ] # genereate the output model_inputs = {'input_ids':input_ids.to(model.device)} model_outputs = model.generate( *model_inputs, max_new_tokens=128, num_beams=8, no_repeat_ngram_size=6, early_stopping=False, pad_token_id=main_tokenizer.eos_token_id, eos_token_id=main_tokenizer.convert_tokens_to_ids(['<0x0A>','</s>']), bad_words_ids=english_starts+prompt_starts ) # decode the output return (main_tokenizer.decode(model_outputs[0][input_ids.shape[1]:])) translate_english_text("The city of Paris is very pretty.") # Париж шәһәре бик матур. ``` ## Citation If you use this model, please cite our work as: ``` @article{tweeties2024, title = {Trans-Tokenization and Cross-lingual Vocabulary Transfers: Language Adaptation of LLMs for Low-Resource NLP}, author = {François Remy and Pieter Delobelle and Hayastan Avetisyan and Alfiya Khabibullina and Miryam de Lhoneux and Thomas Demeester}, url = {https://raw.githubusercontent.com/LAGoM-NLP/transtokenizer/paper/Trans-Tokenization.pdf}, year = {2024}, note = {Under review at COLM 2024} } ```	{"language": ["tt", "en", "de", "fr", "zh", "pt", "nl", "ru", "ko", "it", "es"], "license": "cc-by-nc-4.0", "tags": ["tweety"], "datasets": ["oscar-corpus/OSCAR-2301"], "base_model": "Unbabel/TowerInstruct-7B-v0.1"}	Tweeties/tweety-tatar-hydra-base-7b-2024-v1	null	[ "transformers", "safetensors", "llama_hydra", "text-generation", "tweety", "custom_code", "tt", "en", "de", "fr", "zh", "pt", "nl", "ru", "ko", "it", "es", "dataset:oscar-corpus/OSCAR-2301", "base_model:Unbabel/TowerInstruct-7B-v0.1", "license:cc-by-nc-4.0", "autotrain_compatible", "region:us" ]	null	2024-04-12T07:37:05+00:00	[]	[ "tt", "en", "de", "fr", "zh", "pt", "nl", "ru", "ko", "it", "es" ]	TAGS #transformers #safetensors #llama_hydra #text-generation #tweety #custom_code #tt #en #de #fr #zh #pt #nl #ru #ko #it #es #dataset-oscar-corpus/OSCAR-2301 #base_model-Unbabel/TowerInstruct-7B-v0.1 #license-cc-by-nc-4.0 #autotrain_compatible #region-us	<img align="right" src="URL alt="Tweety-Tatar-7B: A Tatar Large Language Model" width="20%"> # Tweety Tatar / Hydra-Base 7b / 2024-v1 ## Model description This model is our Hydra LLM for the Tatar language, converted from the TowerInstruct-7b-v0.1 model trained by Unbabel. Hydra LLMs are trans-tokenized language models finetuned to produce output in a particular language, while accepting input encoded using either their own tokenizer, the one of their base model, or a mix of both. This enables them to receive code-switched input in both their native language and other languages, which is an ideal setup for translation tasks, or retrieval-augmented generation (RAG) in cross-lingual scenarios. - Developed by: François Remy (UGent), Alfiya Khabibullina (BeCode), et al. - Funded by: IDLab / GPULab - Model type: Foundation model using the mistral architecture - Language(s) (NLP): Tatar - License: Creative Commons Attribution Non Commercial 4.0 ## In-scope usage This model can be used as-is to answer questions in Tatar based on a cross-lingual context, or finetuned into a machine translation system from one of the 10 languages supported by TowerInstruct into the Tatar language. This list of languages nobably includes English and Russian. The model performs best when translating sentences or small paragraphs, and is not suited for document translation tasks. This model should not be used in the reverse direction, to translate Tatar into English. When the system isn't finetuned, enabling beam search is recommended for best results. We also provide a model finetuned for translation, but take note of the non-commercial license imposed by Unbabel on the base model. ## Usage instructions Using this model usually requires building the prompts by mixing tokens from two tokenizers, the original TowerInstruct tokenizer for input in the source language, and the new Tatar tokenizer for the prompt and output, as described in the examples below: ### Cross-lingual question answering ### Machine Translation (see finetuned model) If you use this model, please cite our work as:	[ "# Tweety Tatar / Hydra-Base 7b / 2024-v1", "## Model description\nThis model is our Hydra LLM for the Tatar language, converted from the TowerInstruct-7b-v0.1 model trained by Unbabel. \nHydra LLMs are trans-tokenized language models finetuned to produce output in a particular language, while accepting input encoded using either their own tokenizer, the one of their base model, or a mix of both. \nThis enables them to receive code-switched input in both their native language and other languages, which is an ideal setup for translation tasks, or retrieval-augmented generation (RAG) in cross-lingual scenarios.\n\n- Developed by: François Remy (UGent), Alfiya Khabibullina (BeCode), et al.\n- Funded by: IDLab / GPULab\n- Model type: Foundation model using the mistral architecture\n- Language(s) (NLP): Tatar\n- License: Creative Commons Attribution Non Commercial 4.0", "## In-scope usage\nThis model can be used as-is to answer questions in Tatar based on a cross-lingual context, or finetuned into a machine translation system from one of the 10 languages supported by TowerInstruct into the Tatar language. \nThis list of languages nobably includes English and Russian. \nThe model performs best when translating sentences or small paragraphs, and is not suited for document translation tasks. \nThis model should not be used in the reverse direction, to translate Tatar into English. \nWhen the system isn't finetuned, enabling beam search is recommended for best results. \nWe also provide a model finetuned for translation, but take note of the non-commercial license imposed by Unbabel on the base model.", "## Usage instructions\nUsing this model usually requires building the prompts by mixing tokens from two tokenizers, the original TowerInstruct tokenizer for input in the source language, and the new Tatar tokenizer for the prompt and output, as described in the examples below:", "### Cross-lingual question answering", "### Machine Translation (see finetuned model)\n\n\n\nIf you use this model, please cite our work as:" ]	[ "TAGS\n#transformers #safetensors #llama_hydra #text-generation #tweety #custom_code #tt #en #de #fr #zh #pt #nl #ru #ko #it #es #dataset-oscar-corpus/OSCAR-2301 #base_model-Unbabel/TowerInstruct-7B-v0.1 #license-cc-by-nc-4.0 #autotrain_compatible #region-us \n", "# Tweety Tatar / Hydra-Base 7b / 2024-v1", "## Model description\nThis model is our Hydra LLM for the Tatar language, converted from the TowerInstruct-7b-v0.1 model trained by Unbabel. \nHydra LLMs are trans-tokenized language models finetuned to produce output in a particular language, while accepting input encoded using either their own tokenizer, the one of their base model, or a mix of both. \nThis enables them to receive code-switched input in both their native language and other languages, which is an ideal setup for translation tasks, or retrieval-augmented generation (RAG) in cross-lingual scenarios.\n\n- Developed by: François Remy (UGent), Alfiya Khabibullina (BeCode), et al.\n- Funded by: IDLab / GPULab\n- Model type: Foundation model using the mistral architecture\n- Language(s) (NLP): Tatar\n- License: Creative Commons Attribution Non Commercial 4.0", "## In-scope usage\nThis model can be used as-is to answer questions in Tatar based on a cross-lingual context, or finetuned into a machine translation system from one of the 10 languages supported by TowerInstruct into the Tatar language. \nThis list of languages nobably includes English and Russian. \nThe model performs best when translating sentences or small paragraphs, and is not suited for document translation tasks. \nThis model should not be used in the reverse direction, to translate Tatar into English. \nWhen the system isn't finetuned, enabling beam search is recommended for best results. \nWe also provide a model finetuned for translation, but take note of the non-commercial license imposed by Unbabel on the base model.", "## Usage instructions\nUsing this model usually requires building the prompts by mixing tokens from two tokenizers, the original TowerInstruct tokenizer for input in the source language, and the new Tatar tokenizer for the prompt and output, as described in the examples below:", "### Cross-lingual question answering", "### Machine Translation (see finetuned model)\n\n\n\nIf you use this model, please cite our work as:" ]
null	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. --> # PolizzeDonut-ChangeRequest-imm5epochs-334img This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on the imagefolder 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: 2e-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: 5 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.38.2 - Pytorch 2.2.2+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2	{"license": "mit", "tags": ["generated_from_trainer"], "datasets": ["imagefolder"], "base_model": "naver-clova-ix/donut-base", "model-index": [{"name": "PolizzeDonut-ChangeRequest-imm5epochs-334img", "results": []}]}	tedad09/PolizzeDonut-ChangeRequest-imm5epochs-334img	null	[ "transformers", "tensorboard", "safetensors", "vision-encoder-decoder", "generated_from_trainer", "dataset:imagefolder", "base_model:naver-clova-ix/donut-base", "license:mit", "endpoints_compatible", "region:us" ]	null	2024-04-12T07:37:21+00:00	[]	[]	TAGS #transformers #tensorboard #safetensors #vision-encoder-decoder #generated_from_trainer #dataset-imagefolder #base_model-naver-clova-ix/donut-base #license-mit #endpoints_compatible #region-us	# PolizzeDonut-ChangeRequest-imm5epochs-334img This model is a fine-tuned version of naver-clova-ix/donut-base on the imagefolder 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: 2e-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: 5 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.38.2 - Pytorch 2.2.2+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2	[ "# PolizzeDonut-ChangeRequest-imm5epochs-334img\n\nThis model is a fine-tuned version of naver-clova-ix/donut-base on the imagefolder 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: 2e-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: 5\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.38.2\n- Pytorch 2.2.2+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]	[ "TAGS\n#transformers #tensorboard #safetensors #vision-encoder-decoder #generated_from_trainer #dataset-imagefolder #base_model-naver-clova-ix/donut-base #license-mit #endpoints_compatible #region-us \n", "# PolizzeDonut-ChangeRequest-imm5epochs-334img\n\nThis model is a fine-tuned version of naver-clova-ix/donut-base on the imagefolder 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: 2e-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: 5\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.38.2\n- Pytorch 2.2.2+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]
null	transformers	# DavidAU/Maiden-Unquirked-20B-Q4_K_S-GGUF This model was converted to GGUF format from [`ND911/Maiden-Unquirked-20B`](https://huggingface.co/ND911/Maiden-Unquirked-20B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. Refer to the [original model card](https://huggingface.co/ND911/Maiden-Unquirked-20B) for more details on the model. ## Use with llama.cpp Install llama.cpp through brew. ```bash brew install ggerganov/ggerganov/llama.cpp ``` Invoke the llama.cpp server or the CLI. CLI: ```bash llama-cli --hf-repo DavidAU/Maiden-Unquirked-20B-Q4_K_S-GGUF --model maiden-unquirked-20b.Q4_K_S.gguf -p "The meaning to life and the universe is" ``` Server: ```bash llama-server --hf-repo DavidAU/Maiden-Unquirked-20B-Q4_K_S-GGUF --model maiden-unquirked-20b.Q4_K_S.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. ``` git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m maiden-unquirked-20b.Q4_K_S.gguf -n 128 ```	{"library_name": "transformers", "tags": ["mergekit", "merge", "not-for-all-audiences", "llama-cpp", "gguf-my-repo"], "base_model": ["TeeZee/BigMaid-20B-v1.0", "TeeZee/DarkForest-20B-v2.0", "athirdpath/Harmonia-20B"]}	DavidAU/Maiden-Unquirked-20B-Q4_K_S-GGUF	null	[ "transformers", "gguf", "mergekit", "merge", "not-for-all-audiences", "llama-cpp", "gguf-my-repo", "base_model:TeeZee/BigMaid-20B-v1.0", "base_model:TeeZee/DarkForest-20B-v2.0", "base_model:athirdpath/Harmonia-20B", "endpoints_compatible", "region:us" ]	null	2024-04-12T07:37:52+00:00	[]	[]	TAGS #transformers #gguf #mergekit #merge #not-for-all-audiences #llama-cpp #gguf-my-repo #base_model-TeeZee/BigMaid-20B-v1.0 #base_model-TeeZee/DarkForest-20B-v2.0 #base_model-athirdpath/Harmonia-20B #endpoints_compatible #region-us	# DavidAU/Maiden-Unquirked-20B-Q4_K_S-GGUF This model was converted to GGUF format from 'ND911/Maiden-Unquirked-20B' using URL via the URL's GGUF-my-repo space. Refer to the original model card for more details on the model. ## Use with URL Install URL through brew. Invoke the URL server or the CLI. CLI: Server: Note: You can also use this checkpoint directly through the usage steps listed in the URL repo as well.	[ "# DavidAU/Maiden-Unquirked-20B-Q4_K_S-GGUF\nThis model was converted to GGUF format from 'ND911/Maiden-Unquirked-20B' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]	[ "TAGS\n#transformers #gguf #mergekit #merge #not-for-all-audiences #llama-cpp #gguf-my-repo #base_model-TeeZee/BigMaid-20B-v1.0 #base_model-TeeZee/DarkForest-20B-v2.0 #base_model-athirdpath/Harmonia-20B #endpoints_compatible #region-us \n", "# DavidAU/Maiden-Unquirked-20B-Q4_K_S-GGUF\nThis model was converted to GGUF format from 'ND911/Maiden-Unquirked-20B' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]
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": []}	grrvk/palm-tiny-inst	null	[ "transformers", "safetensors", "mask2former", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-04-12T07:38:25+00:00	[ "1910.09700" ]	[]	TAGS #transformers #safetensors #mask2former #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 #mask2former #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	null	# DavidAU/Sakura-13B-LNovel-v0.8-Q6_K-GGUF This model was converted to GGUF format from [`SakuraLLM/Sakura-13B-LNovel-v0.8`](https://huggingface.co/SakuraLLM/Sakura-13B-LNovel-v0.8) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. Refer to the [original model card](https://huggingface.co/SakuraLLM/Sakura-13B-LNovel-v0.8) for more details on the model. ## Use with llama.cpp Install llama.cpp through brew. ```bash brew install ggerganov/ggerganov/llama.cpp ``` Invoke the llama.cpp server or the CLI. CLI: ```bash llama-cli --hf-repo DavidAU/Sakura-13B-LNovel-v0.8-Q6_K-GGUF --model sakura-13b-lnovel-v0.8.Q6_K.gguf -p "The meaning to life and the universe is" ``` Server: ```bash llama-server --hf-repo DavidAU/Sakura-13B-LNovel-v0.8-Q6_K-GGUF --model sakura-13b-lnovel-v0.8.Q6_K.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. ``` git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m sakura-13b-lnovel-v0.8.Q6_K.gguf -n 128 ```	{"license": "apache-2.0", "tags": ["llama-cpp", "gguf-my-repo"]}	DavidAU/Sakura-13B-LNovel-v0.8-Q6_K-GGUF	null	[ "gguf", "llama-cpp", "gguf-my-repo", "license:apache-2.0", "region:us" ]	null	2024-04-12T07:41:21+00:00	[]	[]	TAGS #gguf #llama-cpp #gguf-my-repo #license-apache-2.0 #region-us	# DavidAU/Sakura-13B-LNovel-v0.8-Q6_K-GGUF This model was converted to GGUF format from 'SakuraLLM/Sakura-13B-LNovel-v0.8' using URL via the URL's GGUF-my-repo space. Refer to the original model card for more details on the model. ## Use with URL Install URL through brew. Invoke the URL server or the CLI. CLI: Server: Note: You can also use this checkpoint directly through the usage steps listed in the URL repo as well.	[ "# DavidAU/Sakura-13B-LNovel-v0.8-Q6_K-GGUF\nThis model was converted to GGUF format from 'SakuraLLM/Sakura-13B-LNovel-v0.8' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]	[ "TAGS\n#gguf #llama-cpp #gguf-my-repo #license-apache-2.0 #region-us \n", "# DavidAU/Sakura-13B-LNovel-v0.8-Q6_K-GGUF\nThis model was converted to GGUF format from 'SakuraLLM/Sakura-13B-LNovel-v0.8' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]
text-classification	transformers	# Malicious & Jailbreaking Prompt Classifer # Datasets Used [MaliciousInstruct](https://github.com/Princeton-SysML/Jailbreak_LLM/blob/main/data/MaliciousInstruct.txt) [AART](https://github.com/google-research-datasets/aart-ai-safety-dataset/blob/main/aart-v1-20231117.csv) [StrongREJECT](https://github.com/alexandrasouly/strongreject/blob/main/strongreject_dataset/strongreject_dataset.csv) [DAN](https://github.com/verazuo/jailbreak_llms/tree/main/data) [AdvBench](https://github.com/llm-attacks/llm-attacks/tree/main/data/advbench) [Databricks-Dolly](https://huggingface.co/datasets/databricks/databricks-dolly-15k)	{"datasets": ["davanstrien/aart-ai-safety-dataset", "obalcells/advbench", "databricks/databricks-dolly-15k"]}	Al-Chan/Malicious_Prompt_Classifier	null	[ "transformers", "safetensors", "distilbert", "text-classification", "dataset:davanstrien/aart-ai-safety-dataset", "dataset:obalcells/advbench", "dataset:databricks/databricks-dolly-15k", "autotrain_compatible", "endpoints_compatible", "region:us", "has_space" ]	null	2024-04-12T07:44:49+00:00	[]	[]	TAGS #transformers #safetensors #distilbert #text-classification #dataset-davanstrien/aart-ai-safety-dataset #dataset-obalcells/advbench #dataset-databricks/databricks-dolly-15k #autotrain_compatible #endpoints_compatible #region-us #has_space	# Malicious & Jailbreaking Prompt Classifer # Datasets Used MaliciousInstruct AART StrongREJECT DAN AdvBench Databricks-Dolly	[ "# Malicious & Jailbreaking Prompt Classifer", "# Datasets Used\n\nMaliciousInstruct\n\nAART\n\nStrongREJECT\n\nDAN\n\nAdvBench\n\nDatabricks-Dolly" ]	[ "TAGS\n#transformers #safetensors #distilbert #text-classification #dataset-davanstrien/aart-ai-safety-dataset #dataset-obalcells/advbench #dataset-databricks/databricks-dolly-15k #autotrain_compatible #endpoints_compatible #region-us #has_space \n", "# Malicious & Jailbreaking Prompt Classifer", "# Datasets Used\n\nMaliciousInstruct\n\nAART\n\nStrongREJECT\n\nDAN\n\nAdvBench\n\nDatabricks-Dolly" ]
automatic-speech-recognition	transformers.js	ERROR: type should be string, got "\nhttps://hf.co/vinai/PhoWhisper-large with ONNX weights to be compatible with Transformers.js.\n\nPlease check out this demo using this model:\n[![Open in Spaces](https://huggingface.co/datasets/huggingface/badges/resolve/main/open-in-hf-spaces-md-dark.svg)](https://huggingface.co/spaces/huuquyet/PhoWhisper-next)\n\n\n# PhoWhisper: Automatic Speech Recognition for Vietnamese\n\n\nWe introduce PhoWhisper in five versions for Vietnamese automatic speech recognition. PhoWhisper's robustness is achieved through fine-tuning the multilingual [Whisper](https://github.com/openai/whisper) on an 844-hour dataset that encompasses diverse Vietnamese accents. Our experimental study demonstrates state-of-the-art performances of PhoWhisper on benchmark Vietnamese ASR datasets. Please cite our PhoWhisper paper when it is used to help produce published results or is incorporated into other software:\n\n```\n@inproceedings{PhoWhisper,\n title = {{PhoWhisper: Automatic Speech Recognition for Vietnamese}},\n author = {Thanh-Thien Le and Linh The Nguyen and Dat Quoc Nguyen},\n booktitle = {Proceedings of the ICLR 2024 Tiny Papers track},\n year = {2024}\n}\n```\n\nFor further information or requests, please go to [PhoWhisper's homepage](https://github.com/VinAIResearch/PhoWhisper)!"	{"language": ["vi"], "license": "wtfpl", "library_name": "transformers.js", "tags": ["audio", "automatic-speech-recognition", "hf-asr-leaderboard"], "widget": [{"example_title": "Librispeech sample 1", "src": "https://cdn-media.huggingface.co/speech_samples/sample1.flac"}, {"example_title": "Librispeech sample 2", "src": "https://cdn-media.huggingface.co/speech_samples/sample2.flac"}], "pipeline_tag": "automatic-speech-recognition"}	huuquyet/PhoWhisper-large	null	[ "transformers.js", "onnx", "whisper", "automatic-speech-recognition", "audio", "hf-asr-leaderboard", "vi", "license:wtfpl", "has_space", "region:us" ]	null	2024-04-12T07:46:46+00:00	[]	[ "vi" ]	TAGS #transformers.js #onnx #whisper #automatic-speech-recognition #audio #hf-asr-leaderboard #vi #license-wtfpl #has_space #region-us	URL with ONNX weights to be compatible with URL. Please check out this demo using this model: ![Open in Spaces](URL # PhoWhisper: Automatic Speech Recognition for Vietnamese We introduce PhoWhisper in five versions for Vietnamese automatic speech recognition. PhoWhisper's robustness is achieved through fine-tuning the multilingual Whisper on an 844-hour dataset that encompasses diverse Vietnamese accents. Our experimental study demonstrates state-of-the-art performances of PhoWhisper on benchmark Vietnamese ASR datasets. Please cite our PhoWhisper paper when it is used to help produce published results or is incorporated into other software: For further information or requests, please go to PhoWhisper's homepage!	[ "# PhoWhisper: Automatic Speech Recognition for Vietnamese\n\n\nWe introduce PhoWhisper in five versions for Vietnamese automatic speech recognition. PhoWhisper's robustness is achieved through fine-tuning the multilingual Whisper on an 844-hour dataset that encompasses diverse Vietnamese accents. Our experimental study demonstrates state-of-the-art performances of PhoWhisper on benchmark Vietnamese ASR datasets. Please cite our PhoWhisper paper when it is used to help produce published results or is incorporated into other software:\n\n\n\nFor further information or requests, please go to PhoWhisper's homepage!" ]	[ "TAGS\n#transformers.js #onnx #whisper #automatic-speech-recognition #audio #hf-asr-leaderboard #vi #license-wtfpl #has_space #region-us \n", "# PhoWhisper: Automatic Speech Recognition for Vietnamese\n\n\nWe introduce PhoWhisper in five versions for Vietnamese automatic speech recognition. PhoWhisper's robustness is achieved through fine-tuning the multilingual Whisper on an 844-hour dataset that encompasses diverse Vietnamese accents. Our experimental study demonstrates state-of-the-art performances of PhoWhisper on benchmark Vietnamese ASR datasets. Please cite our PhoWhisper paper when it is used to help produce published results or is incorporated into other software:\n\n\n\nFor further information or requests, please go to PhoWhisper's homepage!" ]
automatic-speech-recognition	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": []}	JunWorks/Quantized_4bit_WhisperSmallOri	null	[ "transformers", "safetensors", "whisper", "automatic-speech-recognition", "arxiv:1910.09700", "endpoints_compatible", "4-bit", "region:us" ]	null	2024-04-12T07:47:09+00:00	[ "1910.09700" ]	[]	TAGS #transformers #safetensors #whisper #automatic-speech-recognition #arxiv-1910.09700 #endpoints_compatible #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 #whisper #automatic-speech-recognition #arxiv-1910.09700 #endpoints_compatible #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	# Uploaded model - Developed by: ramachaitanya22 - License: apache-2.0 - Finetuned from model : unsloth/mistral-7b-bnb-4bit This mistral 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", "mistral", "trl", "sft"], "base_model": "unsloth/mistral-7b-bnb-4bit"}	ramachaitanya22/mistral-7B-ft-health-fitness-v3-4bit-merged	null	[ "transformers", "safetensors", "mistral", "text-generation", "text-generation-inference", "unsloth", "trl", "sft", "en", "base_model:unsloth/mistral-7b-bnb-4bit", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "4-bit", "region:us" ]	null	2024-04-12T07:47:26+00:00	[]	[ "en" ]	TAGS #transformers #safetensors #mistral #text-generation #text-generation-inference #unsloth #trl #sft #en #base_model-unsloth/mistral-7b-bnb-4bit #license-apache-2.0 #autotrain_compatible #endpoints_compatible #4-bit #region-us	# Uploaded model - Developed by: ramachaitanya22 - License: apache-2.0 - Finetuned from model : unsloth/mistral-7b-bnb-4bit This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library. <img src="URL width="200"/>	[ "# Uploaded model\n\n- Developed by: ramachaitanya22\n- License: apache-2.0\n- Finetuned from model : unsloth/mistral-7b-bnb-4bit\n\nThis mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]	[ "TAGS\n#transformers #safetensors #mistral #text-generation #text-generation-inference #unsloth #trl #sft #en #base_model-unsloth/mistral-7b-bnb-4bit #license-apache-2.0 #autotrain_compatible #endpoints_compatible #4-bit #region-us \n", "# Uploaded model\n\n- Developed by: ramachaitanya22\n- License: apache-2.0\n- Finetuned from model : unsloth/mistral-7b-bnb-4bit\n\nThis mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]
null	transformers	## About <!-- ### quantize_version: 1 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: --> <!-- ### vocab_type: --> static quants of https://huggingface.co/bunnycore/CodeZero-7B <!-- provided-files --> weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. ## 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/CodeZero-7B-GGUF/resolve/main/CodeZero-7B.Q2_K.gguf) \| Q2_K \| 3.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/CodeZero-7B-GGUF/resolve/main/CodeZero-7B.IQ3_XS.gguf) \| IQ3_XS \| 3.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/CodeZero-7B-GGUF/resolve/main/CodeZero-7B.Q3_K_S.gguf) \| Q3_K_S \| 4.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/CodeZero-7B-GGUF/resolve/main/CodeZero-7B.IQ3_S.gguf) \| IQ3_S \| 4.0 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/CodeZero-7B-GGUF/resolve/main/CodeZero-7B.IQ3_M.gguf) \| IQ3_M \| 4.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/CodeZero-7B-GGUF/resolve/main/CodeZero-7B.Q3_K_M.gguf) \| Q3_K_M \| 4.5 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/CodeZero-7B-GGUF/resolve/main/CodeZero-7B.Q3_K_L.gguf) \| Q3_K_L \| 4.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/CodeZero-7B-GGUF/resolve/main/CodeZero-7B.IQ4_XS.gguf) \| IQ4_XS \| 5.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/CodeZero-7B-GGUF/resolve/main/CodeZero-7B.Q4_K_S.gguf) \| Q4_K_S \| 5.2 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/CodeZero-7B-GGUF/resolve/main/CodeZero-7B.Q4_K_M.gguf) \| Q4_K_M \| 5.5 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/CodeZero-7B-GGUF/resolve/main/CodeZero-7B.Q5_K_S.gguf) \| Q5_K_S \| 6.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/CodeZero-7B-GGUF/resolve/main/CodeZero-7B.Q5_K_M.gguf) \| Q5_K_M \| 6.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/CodeZero-7B-GGUF/resolve/main/CodeZero-7B.Q6_K.gguf) \| Q6_K \| 7.5 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/CodeZero-7B-GGUF/resolve/main/CodeZero-7B.Q8_0.gguf) \| Q8_0 \| 9.7 \| fast, best quality \| 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": "apache-2.0", "library_name": "transformers", "tags": ["merge", "mergekit", "lazymergekit", "ResplendentAI/DaturaCookie_7B", "ResplendentAI/Flora_7B"], "base_model": "bunnycore/CodeZero-7B", "quantized_by": "mradermacher"}	mradermacher/CodeZero-7B-GGUF	null	[ "transformers", "gguf", "merge", "mergekit", "lazymergekit", "ResplendentAI/DaturaCookie_7B", "ResplendentAI/Flora_7B", "en", "base_model:bunnycore/CodeZero-7B", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2024-04-12T07:47:27+00:00	[]	[ "en" ]	TAGS #transformers #gguf #merge #mergekit #lazymergekit #ResplendentAI/DaturaCookie_7B #ResplendentAI/Flora_7B #en #base_model-bunnycore/CodeZero-7B #license-apache-2.0 #endpoints_compatible #region-us	About ----- static quants of URL weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. 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 #merge #mergekit #lazymergekit #ResplendentAI/DaturaCookie_7B #ResplendentAI/Flora_7B #en #base_model-bunnycore/CodeZero-7B #license-apache-2.0 #endpoints_compatible #region-us \n" ]
object-detection	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. --> # detr-resnet-50_finetuned_cppe5 This model is a fine-tuned version of [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) 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: 1e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 10 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.2.2+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2	{"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "facebook/detr-resnet-50", "model-index": [{"name": "detr-resnet-50_finetuned_cppe5", "results": []}]}	Sajjaviriya/detr-resnet-50_finetuned_cppe5	null	[ "transformers", "tensorboard", "safetensors", "detr", "object-detection", "generated_from_trainer", "base_model:facebook/detr-resnet-50", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2024-04-12T07:47:29+00:00	[]	[]	TAGS #transformers #tensorboard #safetensors #detr #object-detection #generated_from_trainer #base_model-facebook/detr-resnet-50 #license-apache-2.0 #endpoints_compatible #region-us	# detr-resnet-50_finetuned_cppe5 This model is a fine-tuned version of facebook/detr-resnet-50 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: 1e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 10 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.2.2+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2	[ "# detr-resnet-50_finetuned_cppe5\n\nThis model is a fine-tuned version of facebook/detr-resnet-50 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: 1e-05\n- train_batch_size: 8\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: 10\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.2+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]	[ "TAGS\n#transformers #tensorboard #safetensors #detr #object-detection #generated_from_trainer #base_model-facebook/detr-resnet-50 #license-apache-2.0 #endpoints_compatible #region-us \n", "# detr-resnet-50_finetuned_cppe5\n\nThis model is a fine-tuned version of facebook/detr-resnet-50 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: 1e-05\n- train_batch_size: 8\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: 10\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.2+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]
question-answering	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. --> # distilbertbaselineoneepochevaluate This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/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: 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: 1 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| No log \| 1.0 \| 3 \| 5.9229 \| ### Framework versions - Transformers 4.38.2 - Pytorch 2.2.1+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2	{"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "distilbert-base-uncased", "model-index": [{"name": "distilbertbaselineoneepochevaluate", "results": []}]}	KarthikAlagarsamy/distilbertbaselineoneepochevaluate	null	[ "transformers", "tensorboard", "safetensors", "distilbert", "question-answering", "generated_from_trainer", "base_model:distilbert-base-uncased", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2024-04-12T07:47:54+00:00	[]	[]	TAGS #transformers #tensorboard #safetensors #distilbert #question-answering #generated_from_trainer #base_model-distilbert-base-uncased #license-apache-2.0 #endpoints_compatible #region-us	distilbertbaselineoneepochevaluate ================================== This model is a fine-tuned version of 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: 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: 1 ### Training results ### Framework versions * Transformers 4.38.2 * Pytorch 2.2.1+cu121 * Datasets 2.18.0 * Tokenizers 0.15.2	[ "### 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: 1", "### Training results", "### Framework versions\n\n\n* Transformers 4.38.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2" ]	[ "TAGS\n#transformers #tensorboard #safetensors #distilbert #question-answering #generated_from_trainer #base_model-distilbert-base-uncased #license-apache-2.0 #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: 1", "### Training results", "### Framework versions\n\n\n* Transformers 4.38.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2" ]
null	null	# DavidAU/Instruct-v0.2-Seraph-7B-Q6_K-GGUF This model was converted to GGUF format from [`Weyaxi/Instruct-v0.2-Seraph-7B`](https://huggingface.co/Weyaxi/Instruct-v0.2-Seraph-7B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. Refer to the [original model card](https://huggingface.co/Weyaxi/Instruct-v0.2-Seraph-7B) for more details on the model. ## Use with llama.cpp Install llama.cpp through brew. ```bash brew install ggerganov/ggerganov/llama.cpp ``` Invoke the llama.cpp server or the CLI. CLI: ```bash llama-cli --hf-repo DavidAU/Instruct-v0.2-Seraph-7B-Q6_K-GGUF --model instruct-v0.2-seraph-7b.Q6_K.gguf -p "The meaning to life and the universe is" ``` Server: ```bash llama-server --hf-repo DavidAU/Instruct-v0.2-Seraph-7B-Q6_K-GGUF --model instruct-v0.2-seraph-7b.Q6_K.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. ``` git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m instruct-v0.2-seraph-7b.Q6_K.gguf -n 128 ```	{"license": "apache-2.0", "tags": ["merge", "llama-cpp", "gguf-my-repo"]}	DavidAU/Instruct-v0.2-Seraph-7B-Q6_K-GGUF	null	[ "gguf", "merge", "llama-cpp", "gguf-my-repo", "license:apache-2.0", "region:us" ]	null	2024-04-12T07:48:09+00:00	[]	[]	TAGS #gguf #merge #llama-cpp #gguf-my-repo #license-apache-2.0 #region-us	# DavidAU/Instruct-v0.2-Seraph-7B-Q6_K-GGUF This model was converted to GGUF format from 'Weyaxi/Instruct-v0.2-Seraph-7B' using URL via the URL's GGUF-my-repo space. Refer to the original model card for more details on the model. ## Use with URL Install URL through brew. Invoke the URL server or the CLI. CLI: Server: Note: You can also use this checkpoint directly through the usage steps listed in the URL repo as well.	[ "# DavidAU/Instruct-v0.2-Seraph-7B-Q6_K-GGUF\nThis model was converted to GGUF format from 'Weyaxi/Instruct-v0.2-Seraph-7B' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]	[ "TAGS\n#gguf #merge #llama-cpp #gguf-my-repo #license-apache-2.0 #region-us \n", "# DavidAU/Instruct-v0.2-Seraph-7B-Q6_K-GGUF\nThis model was converted to GGUF format from 'Weyaxi/Instruct-v0.2-Seraph-7B' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]
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": []}	winirrr/typhoon-7b-quote-demoModel	null	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-04-12T07:49:27+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" ]
reinforcement-learning	ml-agents	# ppo Agent playing SnowballTarget This is a trained model of a ppo agent playing SnowballTarget using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents). ## Usage (with ML-Agents) The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A short tutorial where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction - A longer tutorial to understand how works ML-Agents: https://huggingface.co/learn/deep-rl-course/unit5/introduction ### Resume the training ```bash mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume ``` ### Watch your Agent play You can watch your agent playing directly in your browser 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity 2. Step 1: Find your model_id: Miltomo/ppo-SnowballTarget 3. Step 2: Select your .nn /.onnx file 4. Click on Watch the agent play 👀	{"library_name": "ml-agents", "tags": ["SnowballTarget", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-SnowballTarget"]}	Miltomo/ppo-SnowballTarget	null	[ "ml-agents", "tensorboard", "onnx", "SnowballTarget", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-SnowballTarget", "region:us" ]	null	2024-04-12T07:50:48+00:00	[]	[]	TAGS #ml-agents #tensorboard #onnx #SnowballTarget #deep-reinforcement-learning #reinforcement-learning #ML-Agents-SnowballTarget #region-us	# ppo Agent playing SnowballTarget This is a trained model of a ppo agent playing SnowballTarget using the Unity ML-Agents Library. ## Usage (with ML-Agents) The Documentation: URL We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A short tutorial where you teach Huggy the Dog to fetch the stick and then play with him directly in your browser: URL - A longer tutorial to understand how works ML-Agents: URL ### Resume the training ### Watch your Agent play You can watch your agent playing directly in your browser 1. If the environment is part of ML-Agents official environments, go to URL 2. Step 1: Find your model_id: Miltomo/ppo-SnowballTarget 3. Step 2: Select your .nn /.onnx file 4. Click on Watch the agent play	[ "# ppo Agent playing SnowballTarget\n This is a trained model of a ppo agent playing SnowballTarget\n using the Unity ML-Agents Library.\n\n ## Usage (with ML-Agents)\n The Documentation: URL\n\n We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:\n - A short tutorial where you teach Huggy the Dog to fetch the stick and then play with him directly in your\n browser: URL\n - A longer tutorial to understand how works ML-Agents:\n URL\n\n ### Resume the training\n \n\n ### Watch your Agent play\n You can watch your agent playing directly in your browser\n\n 1. If the environment is part of ML-Agents official environments, go to URL\n 2. Step 1: Find your model_id: Miltomo/ppo-SnowballTarget\n 3. Step 2: Select your .nn /.onnx file\n 4. Click on Watch the agent play" ]	[ "TAGS\n#ml-agents #tensorboard #onnx #SnowballTarget #deep-reinforcement-learning #reinforcement-learning #ML-Agents-SnowballTarget #region-us \n", "# ppo Agent playing SnowballTarget\n This is a trained model of a ppo agent playing SnowballTarget\n using the Unity ML-Agents Library.\n\n ## Usage (with ML-Agents)\n The Documentation: URL\n\n We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:\n - A short tutorial where you teach Huggy the Dog to fetch the stick and then play with him directly in your\n browser: URL\n - A longer tutorial to understand how works ML-Agents:\n URL\n\n ### Resume the training\n \n\n ### Watch your Agent play\n You can watch your agent playing directly in your browser\n\n 1. If the environment is part of ML-Agents official environments, go to URL\n 2. Step 1: Find your model_id: Miltomo/ppo-SnowballTarget\n 3. Step 2: Select your .nn /.onnx file\n 4. Click on Watch the agent play" ]
text-generation	transformers	![image/png](https://cdn-uploads.huggingface.co/production/uploads/65c70c9e21d80a923d664563/Wj6AZC7Z3bUzRR6wa_NPe.png) # NeuralStar-7b-Lazy NeuralStar-7b-Lazy is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing): * [NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story](https://huggingface.co/NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story) * [maywell/PiVoT-0.1-Starling-LM-RP](https://huggingface.co/maywell/PiVoT-0.1-Starling-LM-RP) ## 🧩 Configuration ```yaml slices: - sources: - model: NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story layer_range: [0, 32] - model: maywell/PiVoT-0.1-Starling-LM-RP layer_range: [0, 32] merge_method: slerp base_model: NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story parameters: t: - filter: self_attn value: [0, 0.5, 0.3, 0.7, 1] - filter: mlp value: [1, 0.5, 0.7, 0.3, 0] - value: 0.5 dtype: bfloat16 ``` ## 💻 Usage ```python !pip install -qU transformers accelerate from transformers import AutoTokenizer import transformers import torch model = "OmnicromsBrain/NeuralStar-7b-Lazy" 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"]) ```	{"tags": ["merge", "mergekit", "lazymergekit", "NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story", "maywell/PiVoT-0.1-Starling-LM-RP"], "base_model": ["NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story", "maywell/PiVoT-0.1-Starling-LM-RP"]}	OmnicromsBrain/NeuralStar-7b-Lazy	null	[ "transformers", "safetensors", "mistral", "text-generation", "merge", "mergekit", "lazymergekit", "NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story", "maywell/PiVoT-0.1-Starling-LM-RP", "conversational", "base_model:NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story", "base_model:maywell/PiVoT-0.1-Starling-LM-RP", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-12T07:50:51+00:00	[]	[]	TAGS #transformers #safetensors #mistral #text-generation #merge #mergekit #lazymergekit #NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story #maywell/PiVoT-0.1-Starling-LM-RP #conversational #base_model-NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story #base_model-maywell/PiVoT-0.1-Starling-LM-RP #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us	!image/png # NeuralStar-7b-Lazy NeuralStar-7b-Lazy is a merge of the following models using LazyMergekit: * NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story * maywell/PiVoT-0.1-Starling-LM-RP ## Configuration ## Usage	[ "# NeuralStar-7b-Lazy\n\nNeuralStar-7b-Lazy is a merge of the following models using LazyMergekit:\n* NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story\n* maywell/PiVoT-0.1-Starling-LM-RP", "## Configuration", "## Usage" ]	[ "TAGS\n#transformers #safetensors #mistral #text-generation #merge #mergekit #lazymergekit #NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story #maywell/PiVoT-0.1-Starling-LM-RP #conversational #base_model-NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story #base_model-maywell/PiVoT-0.1-Starling-LM-RP #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# NeuralStar-7b-Lazy\n\nNeuralStar-7b-Lazy is a merge of the following models using LazyMergekit:\n* NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story\n* maywell/PiVoT-0.1-Starling-LM-RP", "## Configuration", "## Usage" ]
null	peft	# 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. --> - 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] ### Framework versions - PEFT 0.10.0	{"library_name": "peft", "base_model": "google/long-t5-tglobal-base"}	dsolomon/long-t5-base-tglobal-LORA-pubmed-r4-1000-100	null	[ "peft", "safetensors", "arxiv:1910.09700", "base_model:google/long-t5-tglobal-base", "region:us" ]	null	2024-04-12T07:51:12+00:00	[ "1910.09700" ]	[]	TAGS #peft #safetensors #arxiv-1910.09700 #base_model-google/long-t5-tglobal-base #region-us	# Model Card for Model ID ## Model Details ### Model Description - 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 ### Framework versions - PEFT 0.10.0	[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\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", "### Framework versions\n\n- PEFT 0.10.0" ]	[ "TAGS\n#peft #safetensors #arxiv-1910.09700 #base_model-google/long-t5-tglobal-base #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\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", "### Framework versions\n\n- PEFT 0.10.0" ]
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. --> These are the QLoRA adapters for training [lightblue/Karasu-Mixtral-8x22B-v0.1](https://huggingface.co/lightblue/Karasu-Mixtral-8x22B-v0.1). There are also 4 checkpoints from training. [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl) <details><summary>See axolotl config</summary> axolotl version: `0.4.0` ```yaml base_model: mistral-community/Mixtral-8x22B-v0.1 model_type: AutoModelForCausalLM tokenizer_type: AutoTokenizer trust_remote_code: true load_in_8bit: false load_in_4bit: true strict: false datasets: - path: lightblue/gpt4_conversations_multilingual type: sharegpt conversation: mistral dataset_prepared_path: ./prepared_dataset_2048-multiling val_set_size: 0 output_dir: ./qlora-out-2048-multiling ## You can optionally freeze the entire model and unfreeze a subset of parameters unfrozen_parameters: # - ^lm_head.weight$ # - ^model.embed_tokens.weight$[:32000] # - model.layers.2[0-9]+.block_sparse_moe.gate # - model.layers.2[0-9]+.block_sparse_moe.experts # - model.layers.3[0-9]+.block_sparse_moe.gate # - model.layers.3[0-9]+.block_sparse_moe.experts model_config: output_router_logits: true adapter: qlora lora_model_dir: sequence_len: 2048 sample_packing: true pad_to_sequence_len: true lora_r: 16 lora_alpha: 16 lora_dropout: 0.05 lora_target_linear: true lora_fan_in_fan_out: #lora_target_modules: # - gate # - q_proj # - k_proj # - v_proj # - o_proj # - w1 # - w2 # - w3 gradient_accumulation_steps: 2 micro_batch_size: 1 num_epochs: 1 optimizer: adamw_bnb_8bit lr_scheduler: cosine learning_rate: 0.0002 use_wandb: true wandb_project: axolotl wandb_entity: peterd wandb_name: mixtral_8x22b_test train_on_inputs: false group_by_length: false bf16: auto fp16: tf32: false gradient_checkpointing: true early_stopping_patience: resume_from_checkpoint: local_rank: logging_steps: 1 xformers_attention: flash_attention: true warmup_steps: 10 evals_per_epoch: 0 eval_table_size: eval_max_new_tokens: 128 saves_per_epoch: 5 debug: deepspeed: /workspace/axolotl/deepspeed_configs/zero2.json weight_decay: 0.0 fsdp: fsdp_config: special_tokens: ``` </details><br> # qlora-out-2048-multiling This model is a fine-tuned version of [mistral-community/Mixtral-8x22B-v0.1](https://huggingface.co/mistral-community/Mixtral-8x22B-v0.1) 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: 0.0002 - train_batch_size: 1 - eval_batch_size: 1 - seed: 42 - distributed_type: multi-GPU - num_devices: 4 - gradient_accumulation_steps: 2 - total_train_batch_size: 8 - total_eval_batch_size: 4 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 10 - num_epochs: 1 ### Training results ### Framework versions - PEFT 0.10.0 - Transformers 4.40.0.dev0 - Pytorch 2.1.2+cu121 - Datasets 2.18.0 - Tokenizers 0.15.0	{"license": "apache-2.0", "library_name": "peft", "tags": ["generated_from_trainer"], "base_model": "mistral-community/Mixtral-8x22B-v0.1", "model-index": [{"name": "qlora-out-2048-multiling", "results": []}]}	ptrdvn/Karasu-Mixtral-8x22B-v0.1-lora-adapters	null	[ "peft", "safetensors", "mixtral", "generated_from_trainer", "base_model:mistral-community/Mixtral-8x22B-v0.1", "license:apache-2.0", "4-bit", "region:us" ]	null	2024-04-12T07:51:23+00:00	[]	[]	TAGS #peft #safetensors #mixtral #generated_from_trainer #base_model-mistral-community/Mixtral-8x22B-v0.1 #license-apache-2.0 #4-bit #region-us	These are the QLoRA adapters for training lightblue/Karasu-Mixtral-8x22B-v0.1. There are also 4 checkpoints from training. <img src="URL alt="Built with Axolotl" width="200" height="32"/> <details><summary>See axolotl config</summary> axolotl version: '0.4.0' </details><br> # qlora-out-2048-multiling This model is a fine-tuned version of mistral-community/Mixtral-8x22B-v0.1 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: 0.0002 - train_batch_size: 1 - eval_batch_size: 1 - seed: 42 - distributed_type: multi-GPU - num_devices: 4 - gradient_accumulation_steps: 2 - total_train_batch_size: 8 - total_eval_batch_size: 4 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 10 - num_epochs: 1 ### Training results ### Framework versions - PEFT 0.10.0 - Transformers 4.40.0.dev0 - Pytorch 2.1.2+cu121 - Datasets 2.18.0 - Tokenizers 0.15.0	[ "# qlora-out-2048-multiling\n\nThis model is a fine-tuned version of mistral-community/Mixtral-8x22B-v0.1 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: 0.0002\n- train_batch_size: 1\n- eval_batch_size: 1\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 4\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 8\n- total_eval_batch_size: 4\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_steps: 10\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- PEFT 0.10.0\n- Transformers 4.40.0.dev0\n- Pytorch 2.1.2+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.0" ]	[ "TAGS\n#peft #safetensors #mixtral #generated_from_trainer #base_model-mistral-community/Mixtral-8x22B-v0.1 #license-apache-2.0 #4-bit #region-us \n", "# qlora-out-2048-multiling\n\nThis model is a fine-tuned version of mistral-community/Mixtral-8x22B-v0.1 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: 0.0002\n- train_batch_size: 1\n- eval_batch_size: 1\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 4\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 8\n- total_eval_batch_size: 4\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_steps: 10\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- PEFT 0.10.0\n- Transformers 4.40.0.dev0\n- Pytorch 2.1.2+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.0" ]
null	null	activation token: pe1nkwe3kti0r adapter weight: 1.4	{}	BiQiB7/PinkVector	null	[ "region:us" ]	null	2024-04-12T07:51:46+00:00	[]	[]	TAGS #region-us	activation token: pe1nkwe3kti0r adapter weight: 1.4	[]	[ "TAGS\n#region-us \n" ]
null	null	VJEPA Encoder The VJEPA Encoder is a Python package that provides an implementation of the encoder component from the JEPA (Joint Encoding for Prediction and Alignment) architecture proposed by Facebook AI Research. The encoder is designed to extract meaningful representations from visual data. I do not own the rights or lay claim to the copyright of this software. This package is an adaptation to `facebookresearch/jepa` to enable ease of use of the Jepa Architecture built with Vision Transformers. ## Installation To install the VJEPA Encoder package, you can use pip: ``` pip install vjepa-encoder ``` ## Usage To use the VJEPA Encoder in your Python code, you can import it as follows: ```python from vjepa_encoder.vision_encoder import JepaEncoder ``` ### Loading the Encoder To load the pre-trained encoder, you can use the `load_model` function: ```python config_file_path = "./params-encoder.yaml" devices = ["cuda:0"] encoder = JepaEncoder.load_model(config_file_path, devices) ``` - `config_file_path`: Path to the configuration file (YAML) containing the model settings. - `devices`: List of devices (e.g., `['cuda:0']`) to use for distributed training. If not provided, the model will be loaded on the CPU. #### Important Notes about the Config File: - the config file provided in this repo provides the basics for loading and using the encoder. The most important things to note in this file are the `r_checkpoint`: points at the `.tar` file for the JEPA checkpoint, and the `tabulet_size`: this is used in some temporal calculation and if you plan on embedding images you should set this to `1`; set this to `N` if you plan on using a temporal dimension for your data, where N corresponds to however many temporal inputs you have. ### Preprocessing Data The VJEPA Encoder provides a `preprocess_data` function to preprocess input data before feeding it to the encoder: ```python preprocessed_data = encoder.preprocess_data(input_data) ``` - `input_data`: Input data, which can be an image path, image array, PIL Image, or PyTorch tensor. ### Embedding Images To obtain the embeddings for an image, you can use the `embed_image` function: ```python embeddings = encoder.embed_image(input_data) ``` - `input_data`: Input data, which can be an image path, image array, PIL Image, or PyTorch tensor. The function returns the embeddings generated by the encoder. ## Configuration The VJEPA Encoder requires a configuration file in YAML format to specify the model settings. The configuration file should include the following sections: - `meta`: General settings such as the checkpoint file path, random seed, etc. - `mask`: Settings related to masking. - `model`: Model architecture settings. - `data`: Data-related settings such as crop size, patch size, etc. - `logging`: Logging settings. Please refer to the provided configuration file template for more details. ## License The VJEPA Encoder is released under the [MIT License](LICENSE). ## Acknowledgments The VJEPA Encoder is based on the research work conducted by Facebook AI Research. We would like to acknowledge their contributions to the field of computer vision and representation learning. ## Contact If you have any questions or suggestions regarding the VJEPA Encoder, please feel free to contact us at [email protected]. ---	{}	jonathanzkoch/vjepa-self-driving	null	[ "region:us" ]	null	2024-04-12T07:55:12+00:00	[]	[]	TAGS #region-us	VJEPA Encoder The VJEPA Encoder is a Python package that provides an implementation of the encoder component from the JEPA (Joint Encoding for Prediction and Alignment) architecture proposed by Facebook AI Research. The encoder is designed to extract meaningful representations from visual data. I do not own the rights or lay claim to the copyright of this software. This package is an adaptation to 'facebookresearch/jepa' to enable ease of use of the Jepa Architecture built with Vision Transformers. ## Installation To install the VJEPA Encoder package, you can use pip: ## Usage To use the VJEPA Encoder in your Python code, you can import it as follows: ### Loading the Encoder To load the pre-trained encoder, you can use the 'load_model' function: - 'config_file_path': Path to the configuration file (YAML) containing the model settings. - 'devices': List of devices (e.g., '['cuda:0']') to use for distributed training. If not provided, the model will be loaded on the CPU. #### Important Notes about the Config File: - the config file provided in this repo provides the basics for loading and using the encoder. The most important things to note in this file are the 'r_checkpoint': points at the '.tar' file for the JEPA checkpoint, and the 'tabulet_size': this is used in some temporal calculation and if you plan on embedding images you should set this to '1'; set this to 'N' if you plan on using a temporal dimension for your data, where N corresponds to however many temporal inputs you have. ### Preprocessing Data The VJEPA Encoder provides a 'preprocess_data' function to preprocess input data before feeding it to the encoder: - 'input_data': Input data, which can be an image path, image array, PIL Image, or PyTorch tensor. ### Embedding Images To obtain the embeddings for an image, you can use the 'embed_image' function: - 'input_data': Input data, which can be an image path, image array, PIL Image, or PyTorch tensor. The function returns the embeddings generated by the encoder. ## Configuration The VJEPA Encoder requires a configuration file in YAML format to specify the model settings. The configuration file should include the following sections: - 'meta': General settings such as the checkpoint file path, random seed, etc. - 'mask': Settings related to masking. - 'model': Model architecture settings. - 'data': Data-related settings such as crop size, patch size, etc. - 'logging': Logging settings. Please refer to the provided configuration file template for more details. ## License The VJEPA Encoder is released under the MIT License. ## Acknowledgments The VJEPA Encoder is based on the research work conducted by Facebook AI Research. We would like to acknowledge their contributions to the field of computer vision and representation learning. ## Contact If you have any questions or suggestions regarding the VJEPA Encoder, please feel free to contact us at johnnykoch02@URL. ---	[ "## Installation\n\nTo install the VJEPA Encoder package, you can use pip:", "## Usage\n\nTo use the VJEPA Encoder in your Python code, you can import it as follows:", "### Loading the Encoder\n\nTo load the pre-trained encoder, you can use the 'load_model' function:\n\n\n\n- 'config_file_path': Path to the configuration file (YAML) containing the model settings.\n- 'devices': List of devices (e.g., '['cuda:0']') to use for distributed training. If not provided, the model will be loaded on the CPU.", "#### Important Notes about the Config File:\n\n- the config file provided in this repo provides the basics for loading and using the encoder. The most important things to note in this file are the 'r_checkpoint': points at the '.tar' file for the JEPA checkpoint, and the 'tabulet_size': this is used in some temporal calculation and if you plan on embedding images you should set this to '1'; set this to 'N' if you plan on using a temporal dimension for your data, where N corresponds to however many temporal inputs you have.", "### Preprocessing Data\n\nThe VJEPA Encoder provides a 'preprocess_data' function to preprocess input data before feeding it to the encoder:\n\n\n\n- 'input_data': Input data, which can be an image path, image array, PIL Image, or PyTorch tensor.", "### Embedding Images\n\nTo obtain the embeddings for an image, you can use the 'embed_image' function:\n\n\n\n- 'input_data': Input data, which can be an image path, image array, PIL Image, or PyTorch tensor.\n\nThe function returns the embeddings generated by the encoder.", "## Configuration\n\nThe VJEPA Encoder requires a configuration file in YAML format to specify the model settings. The configuration file should include the following sections:\n\n- 'meta': General settings such as the checkpoint file path, random seed, etc.\n- 'mask': Settings related to masking.\n- 'model': Model architecture settings.\n- 'data': Data-related settings such as crop size, patch size, etc.\n- 'logging': Logging settings.\n\nPlease refer to the provided configuration file template for more details.", "## License\n\nThe VJEPA Encoder is released under the MIT License.", "## Acknowledgments\n\nThe VJEPA Encoder is based on the research work conducted by Facebook AI Research. We would like to acknowledge their contributions to the field of computer vision and representation learning.", "## Contact\n\nIf you have any questions or suggestions regarding the VJEPA Encoder, please feel free to contact us at johnnykoch02@URL.\n\n---" ]	[ "TAGS\n#region-us \n", "## Installation\n\nTo install the VJEPA Encoder package, you can use pip:", "## Usage\n\nTo use the VJEPA Encoder in your Python code, you can import it as follows:", "### Loading the Encoder\n\nTo load the pre-trained encoder, you can use the 'load_model' function:\n\n\n\n- 'config_file_path': Path to the configuration file (YAML) containing the model settings.\n- 'devices': List of devices (e.g., '['cuda:0']') to use for distributed training. If not provided, the model will be loaded on the CPU.", "#### Important Notes about the Config File:\n\n- the config file provided in this repo provides the basics for loading and using the encoder. The most important things to note in this file are the 'r_checkpoint': points at the '.tar' file for the JEPA checkpoint, and the 'tabulet_size': this is used in some temporal calculation and if you plan on embedding images you should set this to '1'; set this to 'N' if you plan on using a temporal dimension for your data, where N corresponds to however many temporal inputs you have.", "### Preprocessing Data\n\nThe VJEPA Encoder provides a 'preprocess_data' function to preprocess input data before feeding it to the encoder:\n\n\n\n- 'input_data': Input data, which can be an image path, image array, PIL Image, or PyTorch tensor.", "### Embedding Images\n\nTo obtain the embeddings for an image, you can use the 'embed_image' function:\n\n\n\n- 'input_data': Input data, which can be an image path, image array, PIL Image, or PyTorch tensor.\n\nThe function returns the embeddings generated by the encoder.", "## Configuration\n\nThe VJEPA Encoder requires a configuration file in YAML format to specify the model settings. The configuration file should include the following sections:\n\n- 'meta': General settings such as the checkpoint file path, random seed, etc.\n- 'mask': Settings related to masking.\n- 'model': Model architecture settings.\n- 'data': Data-related settings such as crop size, patch size, etc.\n- 'logging': Logging settings.\n\nPlease refer to the provided configuration file template for more details.", "## License\n\nThe VJEPA Encoder is released under the MIT License.", "## Acknowledgments\n\nThe VJEPA Encoder is based on the research work conducted by Facebook AI Research. We would like to acknowledge their contributions to the field of computer vision and representation learning.", "## Contact\n\nIf you have any questions or suggestions regarding the VJEPA Encoder, please feel free to contact us at johnnykoch02@URL.\n\n---" ]
null	null	# DavidAU/Sakura-13B-LNovel-v0.8-Q4_K_M-GGUF This model was converted to GGUF format from [`SakuraLLM/Sakura-13B-LNovel-v0.8`](https://huggingface.co/SakuraLLM/Sakura-13B-LNovel-v0.8) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. Refer to the [original model card](https://huggingface.co/SakuraLLM/Sakura-13B-LNovel-v0.8) for more details on the model. ## Use with llama.cpp Install llama.cpp through brew. ```bash brew install ggerganov/ggerganov/llama.cpp ``` Invoke the llama.cpp server or the CLI. CLI: ```bash llama-cli --hf-repo DavidAU/Sakura-13B-LNovel-v0.8-Q4_K_M-GGUF --model sakura-13b-lnovel-v0.8.Q4_K_M.gguf -p "The meaning to life and the universe is" ``` Server: ```bash llama-server --hf-repo DavidAU/Sakura-13B-LNovel-v0.8-Q4_K_M-GGUF --model sakura-13b-lnovel-v0.8.Q4_K_M.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. ``` git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m sakura-13b-lnovel-v0.8.Q4_K_M.gguf -n 128 ```	{"license": "apache-2.0", "tags": ["llama-cpp", "gguf-my-repo"]}	DavidAU/Sakura-13B-LNovel-v0.8-Q4_K_M-GGUF	null	[ "gguf", "llama-cpp", "gguf-my-repo", "license:apache-2.0", "region:us" ]	null	2024-04-12T07:56:05+00:00	[]	[]	TAGS #gguf #llama-cpp #gguf-my-repo #license-apache-2.0 #region-us	# DavidAU/Sakura-13B-LNovel-v0.8-Q4_K_M-GGUF This model was converted to GGUF format from 'SakuraLLM/Sakura-13B-LNovel-v0.8' using URL via the URL's GGUF-my-repo space. Refer to the original model card for more details on the model. ## Use with URL Install URL through brew. Invoke the URL server or the CLI. CLI: Server: Note: You can also use this checkpoint directly through the usage steps listed in the URL repo as well.	[ "# DavidAU/Sakura-13B-LNovel-v0.8-Q4_K_M-GGUF\nThis model was converted to GGUF format from 'SakuraLLM/Sakura-13B-LNovel-v0.8' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]	[ "TAGS\n#gguf #llama-cpp #gguf-my-repo #license-apache-2.0 #region-us \n", "# DavidAU/Sakura-13B-LNovel-v0.8-Q4_K_M-GGUF\nThis model was converted to GGUF format from 'SakuraLLM/Sakura-13B-LNovel-v0.8' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]
reinforcement-learning	ml-agents	# ppo Agent playing Pyramids This is a trained model of a ppo agent playing Pyramids using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents). ## Usage (with ML-Agents) The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A short tutorial where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction - A longer tutorial to understand how works ML-Agents: https://huggingface.co/learn/deep-rl-course/unit5/introduction ### Resume the training ```bash mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume ``` ### Watch your Agent play You can watch your agent playing directly in your browser 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity 2. Step 1: Find your model_id: Miltomo/Pyramids 3. Step 2: Select your .nn /.onnx file 4. Click on Watch the agent play 👀	{"library_name": "ml-agents", "tags": ["Pyramids", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Pyramids"]}	Miltomo/Pyramids	null	[ "ml-agents", "tensorboard", "onnx", "Pyramids", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Pyramids", "region:us" ]	null	2024-04-12T07:57:46+00:00	[]	[]	TAGS #ml-agents #tensorboard #onnx #Pyramids #deep-reinforcement-learning #reinforcement-learning #ML-Agents-Pyramids #region-us	# ppo Agent playing Pyramids This is a trained model of a ppo agent playing Pyramids using the Unity ML-Agents Library. ## Usage (with ML-Agents) The Documentation: URL We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A short tutorial where you teach Huggy the Dog to fetch the stick and then play with him directly in your browser: URL - A longer tutorial to understand how works ML-Agents: URL ### Resume the training ### Watch your Agent play You can watch your agent playing directly in your browser 1. If the environment is part of ML-Agents official environments, go to URL 2. Step 1: Find your model_id: Miltomo/Pyramids 3. Step 2: Select your .nn /.onnx file 4. Click on Watch the agent play	[ "# ppo Agent playing Pyramids\n This is a trained model of a ppo agent playing Pyramids\n using the Unity ML-Agents Library.\n\n ## Usage (with ML-Agents)\n The Documentation: URL\n\n We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:\n - A short tutorial where you teach Huggy the Dog to fetch the stick and then play with him directly in your\n browser: URL\n - A longer tutorial to understand how works ML-Agents:\n URL\n\n ### Resume the training\n \n\n ### Watch your Agent play\n You can watch your agent playing directly in your browser\n\n 1. If the environment is part of ML-Agents official environments, go to URL\n 2. Step 1: Find your model_id: Miltomo/Pyramids\n 3. Step 2: Select your .nn /.onnx file\n 4. Click on Watch the agent play" ]	[ "TAGS\n#ml-agents #tensorboard #onnx #Pyramids #deep-reinforcement-learning #reinforcement-learning #ML-Agents-Pyramids #region-us \n", "# ppo Agent playing Pyramids\n This is a trained model of a ppo agent playing Pyramids\n using the Unity ML-Agents Library.\n\n ## Usage (with ML-Agents)\n The Documentation: URL\n\n We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:\n - A short tutorial where you teach Huggy the Dog to fetch the stick and then play with him directly in your\n browser: URL\n - A longer tutorial to understand how works ML-Agents:\n URL\n\n ### Resume the training\n \n\n ### Watch your Agent play\n You can watch your agent playing directly in your browser\n\n 1. If the environment is part of ML-Agents official environments, go to URL\n 2. Step 1: Find your model_id: Miltomo/Pyramids\n 3. Step 2: Select your .nn /.onnx file\n 4. Click on Watch the agent play" ]
null	null	# DavidAU/Instruct-v0.2-Seraph-7B-Q4_K_M-GGUF This model was converted to GGUF format from [`Weyaxi/Instruct-v0.2-Seraph-7B`](https://huggingface.co/Weyaxi/Instruct-v0.2-Seraph-7B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. Refer to the [original model card](https://huggingface.co/Weyaxi/Instruct-v0.2-Seraph-7B) for more details on the model. ## Use with llama.cpp Install llama.cpp through brew. ```bash brew install ggerganov/ggerganov/llama.cpp ``` Invoke the llama.cpp server or the CLI. CLI: ```bash llama-cli --hf-repo DavidAU/Instruct-v0.2-Seraph-7B-Q4_K_M-GGUF --model instruct-v0.2-seraph-7b.Q4_K_M.gguf -p "The meaning to life and the universe is" ``` Server: ```bash llama-server --hf-repo DavidAU/Instruct-v0.2-Seraph-7B-Q4_K_M-GGUF --model instruct-v0.2-seraph-7b.Q4_K_M.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. ``` git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m instruct-v0.2-seraph-7b.Q4_K_M.gguf -n 128 ```	{"license": "apache-2.0", "tags": ["merge", "llama-cpp", "gguf-my-repo"]}	DavidAU/Instruct-v0.2-Seraph-7B-Q4_K_M-GGUF	null	[ "gguf", "merge", "llama-cpp", "gguf-my-repo", "license:apache-2.0", "region:us" ]	null	2024-04-12T07:58:09+00:00	[]	[]	TAGS #gguf #merge #llama-cpp #gguf-my-repo #license-apache-2.0 #region-us	# DavidAU/Instruct-v0.2-Seraph-7B-Q4_K_M-GGUF This model was converted to GGUF format from 'Weyaxi/Instruct-v0.2-Seraph-7B' using URL via the URL's GGUF-my-repo space. Refer to the original model card for more details on the model. ## Use with URL Install URL through brew. Invoke the URL server or the CLI. CLI: Server: Note: You can also use this checkpoint directly through the usage steps listed in the URL repo as well.	[ "# DavidAU/Instruct-v0.2-Seraph-7B-Q4_K_M-GGUF\nThis model was converted to GGUF format from 'Weyaxi/Instruct-v0.2-Seraph-7B' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]	[ "TAGS\n#gguf #merge #llama-cpp #gguf-my-repo #license-apache-2.0 #region-us \n", "# DavidAU/Instruct-v0.2-Seraph-7B-Q4_K_M-GGUF\nThis model was converted to GGUF format from 'Weyaxi/Instruct-v0.2-Seraph-7B' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

Subsets and Splits

No community queries yet

The top public SQL queries from the community will appear here once available.