Search is not available for this dataset
pipeline_tag
stringclasses 48
values | library_name
stringclasses 205
values | text
stringlengths 0
18.3M
| metadata
stringlengths 2
1.07B
| id
stringlengths 5
122
| last_modified
null | tags
listlengths 1
1.84k
| sha
null | created_at
stringlengths 25
25
|
|---|---|---|---|---|---|---|---|---|
null | null | {} | user2028/01 | null | [
"region:us"
]
| null | 2024-04-26T18:28:20+00:00 |
|
null | peft |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# GUE_tf_1-seqsight_4096_512_27M-L32_f
This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_27M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_27M) on the [mahdibaghbanzadeh/GUE_tf_1](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_1) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3607
- F1 Score: 0.8438
- Accuracy: 0.844
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 10000
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|
| 0.5322 | 0.83 | 200 | 0.5168 | 0.7507 | 0.751 |
| 0.4855 | 1.67 | 400 | 0.5076 | 0.7468 | 0.747 |
| 0.4743 | 2.5 | 600 | 0.5012 | 0.7610 | 0.761 |
| 0.4659 | 3.33 | 800 | 0.4963 | 0.7569 | 0.757 |
| 0.4642 | 4.17 | 1000 | 0.4950 | 0.7635 | 0.764 |
| 0.4551 | 5.0 | 1200 | 0.5011 | 0.7468 | 0.747 |
| 0.4472 | 5.83 | 1400 | 0.4920 | 0.7588 | 0.759 |
| 0.4466 | 6.67 | 1600 | 0.4961 | 0.7530 | 0.753 |
| 0.4421 | 7.5 | 1800 | 0.4901 | 0.7538 | 0.754 |
| 0.432 | 8.33 | 2000 | 0.4895 | 0.7640 | 0.764 |
| 0.4337 | 9.17 | 2200 | 0.4938 | 0.7597 | 0.76 |
| 0.4283 | 10.0 | 2400 | 0.5123 | 0.7516 | 0.753 |
| 0.4268 | 10.83 | 2600 | 0.4997 | 0.7588 | 0.76 |
| 0.4206 | 11.67 | 2800 | 0.5024 | 0.7511 | 0.752 |
| 0.4111 | 12.5 | 3000 | 0.5004 | 0.7592 | 0.76 |
| 0.4173 | 13.33 | 3200 | 0.5004 | 0.7591 | 0.76 |
| 0.4106 | 14.17 | 3400 | 0.4989 | 0.7610 | 0.761 |
| 0.407 | 15.0 | 3600 | 0.5104 | 0.7607 | 0.762 |
| 0.4008 | 15.83 | 3800 | 0.5001 | 0.7562 | 0.757 |
| 0.4007 | 16.67 | 4000 | 0.5059 | 0.7616 | 0.762 |
| 0.4002 | 17.5 | 4200 | 0.5137 | 0.7611 | 0.762 |
| 0.3894 | 18.33 | 4400 | 0.5167 | 0.7637 | 0.764 |
| 0.3899 | 19.17 | 4600 | 0.5273 | 0.7604 | 0.761 |
| 0.3875 | 20.0 | 4800 | 0.5129 | 0.7557 | 0.756 |
| 0.3849 | 20.83 | 5000 | 0.5354 | 0.7564 | 0.757 |
| 0.3795 | 21.67 | 5200 | 0.5259 | 0.7553 | 0.756 |
| 0.3769 | 22.5 | 5400 | 0.5273 | 0.7513 | 0.752 |
| 0.3804 | 23.33 | 5600 | 0.5323 | 0.7483 | 0.75 |
| 0.3712 | 24.17 | 5800 | 0.5403 | 0.7490 | 0.75 |
| 0.3714 | 25.0 | 6000 | 0.5343 | 0.7494 | 0.75 |
| 0.3639 | 25.83 | 6200 | 0.5363 | 0.7492 | 0.75 |
| 0.3609 | 26.67 | 6400 | 0.5273 | 0.7608 | 0.761 |
| 0.3658 | 27.5 | 6600 | 0.5361 | 0.7547 | 0.755 |
| 0.3616 | 28.33 | 6800 | 0.5276 | 0.7668 | 0.767 |
| 0.3575 | 29.17 | 7000 | 0.5445 | 0.7555 | 0.756 |
| 0.3585 | 30.0 | 7200 | 0.5391 | 0.7552 | 0.756 |
| 0.3528 | 30.83 | 7400 | 0.5566 | 0.7463 | 0.748 |
| 0.3449 | 31.67 | 7600 | 0.5522 | 0.7564 | 0.757 |
| 0.351 | 32.5 | 7800 | 0.5517 | 0.7511 | 0.752 |
| 0.3458 | 33.33 | 8000 | 0.5577 | 0.7501 | 0.751 |
| 0.3478 | 34.17 | 8200 | 0.5542 | 0.7410 | 0.742 |
| 0.3427 | 35.0 | 8400 | 0.5523 | 0.7502 | 0.751 |
| 0.3415 | 35.83 | 8600 | 0.5551 | 0.7484 | 0.749 |
| 0.3404 | 36.67 | 8800 | 0.5604 | 0.7492 | 0.75 |
| 0.3384 | 37.5 | 9000 | 0.5706 | 0.7441 | 0.746 |
| 0.3356 | 38.33 | 9200 | 0.5693 | 0.7481 | 0.749 |
| 0.3367 | 39.17 | 9400 | 0.5691 | 0.7541 | 0.755 |
| 0.3367 | 40.0 | 9600 | 0.5704 | 0.7510 | 0.752 |
| 0.3327 | 40.83 | 9800 | 0.5670 | 0.7524 | 0.753 |
| 0.3344 | 41.67 | 10000 | 0.5708 | 0.7491 | 0.75 |
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2 | {"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_27M", "model-index": [{"name": "GUE_tf_1-seqsight_4096_512_27M-L32_f", "results": []}]} | mahdibaghbanzadeh/GUE_tf_1-seqsight_4096_512_27M-L32_f | null | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:mahdibaghbanzadeh/seqsight_4096_512_27M",
"region:us"
]
| null | 2024-04-26T18:28:31+00:00 |
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": []} | nem012/gemma2B-r16MHCv2 | null | [
"transformers",
"safetensors",
"gemma",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-26T18:28:56+00:00 |
null | peft |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# GUE_tf_4-seqsight_4096_512_27M-L1_f
This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_27M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_27M) on the [mahdibaghbanzadeh/GUE_tf_4](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_4) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3500
- F1 Score: 0.8474
- Accuracy: 0.848
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 10000
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|
| 0.5501 | 1.34 | 200 | 0.5144 | 0.7339 | 0.734 |
| 0.4861 | 2.68 | 400 | 0.5033 | 0.7314 | 0.732 |
| 0.4736 | 4.03 | 600 | 0.4949 | 0.7432 | 0.744 |
| 0.461 | 5.37 | 800 | 0.4889 | 0.7579 | 0.758 |
| 0.4512 | 6.71 | 1000 | 0.4796 | 0.7616 | 0.762 |
| 0.4443 | 8.05 | 1200 | 0.4725 | 0.7678 | 0.768 |
| 0.442 | 9.4 | 1400 | 0.4713 | 0.7670 | 0.767 |
| 0.4365 | 10.74 | 1600 | 0.4703 | 0.7737 | 0.774 |
| 0.4289 | 12.08 | 1800 | 0.4711 | 0.7748 | 0.775 |
| 0.4297 | 13.42 | 2000 | 0.4588 | 0.7780 | 0.778 |
| 0.4205 | 14.77 | 2200 | 0.4674 | 0.7734 | 0.774 |
| 0.4218 | 16.11 | 2400 | 0.4602 | 0.7809 | 0.781 |
| 0.419 | 17.45 | 2600 | 0.4594 | 0.7789 | 0.779 |
| 0.4155 | 18.79 | 2800 | 0.4609 | 0.7799 | 0.78 |
| 0.4191 | 20.13 | 3000 | 0.4531 | 0.7789 | 0.779 |
| 0.41 | 21.48 | 3200 | 0.4549 | 0.7780 | 0.778 |
| 0.4086 | 22.82 | 3400 | 0.4540 | 0.7769 | 0.777 |
| 0.4081 | 24.16 | 3600 | 0.4505 | 0.7820 | 0.782 |
| 0.4055 | 25.5 | 3800 | 0.4513 | 0.7888 | 0.789 |
| 0.4033 | 26.85 | 4000 | 0.4509 | 0.7809 | 0.781 |
| 0.4045 | 28.19 | 4200 | 0.4496 | 0.7799 | 0.78 |
| 0.3972 | 29.53 | 4400 | 0.4562 | 0.7807 | 0.781 |
| 0.3973 | 30.87 | 4600 | 0.4523 | 0.7817 | 0.782 |
| 0.4009 | 32.21 | 4800 | 0.4488 | 0.7808 | 0.781 |
| 0.3938 | 33.56 | 5000 | 0.4506 | 0.7799 | 0.78 |
| 0.3972 | 34.9 | 5200 | 0.4467 | 0.7779 | 0.778 |
| 0.3951 | 36.24 | 5400 | 0.4458 | 0.7819 | 0.782 |
| 0.3906 | 37.58 | 5600 | 0.4470 | 0.7860 | 0.786 |
| 0.3931 | 38.93 | 5800 | 0.4470 | 0.7839 | 0.784 |
| 0.3928 | 40.27 | 6000 | 0.4462 | 0.7870 | 0.787 |
| 0.391 | 41.61 | 6200 | 0.4462 | 0.7850 | 0.785 |
| 0.3938 | 42.95 | 6400 | 0.4442 | 0.7850 | 0.785 |
| 0.3911 | 44.3 | 6600 | 0.4425 | 0.7880 | 0.788 |
| 0.3877 | 45.64 | 6800 | 0.4473 | 0.7796 | 0.78 |
| 0.3908 | 46.98 | 7000 | 0.4427 | 0.7880 | 0.788 |
| 0.3894 | 48.32 | 7200 | 0.4385 | 0.7930 | 0.793 |
| 0.3874 | 49.66 | 7400 | 0.4413 | 0.7879 | 0.788 |
| 0.387 | 51.01 | 7600 | 0.4391 | 0.7900 | 0.79 |
| 0.3884 | 52.35 | 7800 | 0.4398 | 0.7969 | 0.797 |
| 0.3844 | 53.69 | 8000 | 0.4421 | 0.7889 | 0.789 |
| 0.3867 | 55.03 | 8200 | 0.4454 | 0.7817 | 0.782 |
| 0.3857 | 56.38 | 8400 | 0.4407 | 0.7890 | 0.789 |
| 0.3878 | 57.72 | 8600 | 0.4388 | 0.7959 | 0.796 |
| 0.3842 | 59.06 | 8800 | 0.4422 | 0.7859 | 0.786 |
| 0.3824 | 60.4 | 9000 | 0.4408 | 0.7880 | 0.788 |
| 0.3826 | 61.74 | 9200 | 0.4397 | 0.7940 | 0.794 |
| 0.3816 | 63.09 | 9400 | 0.4411 | 0.7900 | 0.79 |
| 0.3874 | 64.43 | 9600 | 0.4395 | 0.7930 | 0.793 |
| 0.3828 | 65.77 | 9800 | 0.4402 | 0.7900 | 0.79 |
| 0.3817 | 67.11 | 10000 | 0.4404 | 0.7900 | 0.79 |
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2 | {"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_27M", "model-index": [{"name": "GUE_tf_4-seqsight_4096_512_27M-L1_f", "results": []}]} | mahdibaghbanzadeh/GUE_tf_4-seqsight_4096_512_27M-L1_f | null | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:mahdibaghbanzadeh/seqsight_4096_512_27M",
"region:us"
]
| null | 2024-04-26T18:29:13+00:00 |
null | peft |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# GUE_tf_4-seqsight_4096_512_27M-L8_f
This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_27M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_27M) on the [mahdibaghbanzadeh/GUE_tf_4](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_4) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3638
- F1 Score: 0.8528
- Accuracy: 0.853
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 10000
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|
| 0.5313 | 1.34 | 200 | 0.5008 | 0.7468 | 0.747 |
| 0.4686 | 2.68 | 400 | 0.4823 | 0.7527 | 0.753 |
| 0.4476 | 4.03 | 600 | 0.4752 | 0.7657 | 0.766 |
| 0.4317 | 5.37 | 800 | 0.4797 | 0.7818 | 0.782 |
| 0.4219 | 6.71 | 1000 | 0.4683 | 0.7674 | 0.768 |
| 0.4125 | 8.05 | 1200 | 0.4625 | 0.7838 | 0.784 |
| 0.407 | 9.4 | 1400 | 0.4541 | 0.7850 | 0.785 |
| 0.4018 | 10.74 | 1600 | 0.4510 | 0.782 | 0.782 |
| 0.3926 | 12.08 | 1800 | 0.4601 | 0.7779 | 0.778 |
| 0.3909 | 13.42 | 2000 | 0.4530 | 0.7836 | 0.784 |
| 0.3818 | 14.77 | 2200 | 0.4502 | 0.7857 | 0.786 |
| 0.3789 | 16.11 | 2400 | 0.4478 | 0.7965 | 0.797 |
| 0.3761 | 17.45 | 2600 | 0.4495 | 0.7897 | 0.79 |
| 0.371 | 18.79 | 2800 | 0.4445 | 0.8010 | 0.801 |
| 0.3705 | 20.13 | 3000 | 0.4337 | 0.8000 | 0.8 |
| 0.3599 | 21.48 | 3200 | 0.4375 | 0.7990 | 0.799 |
| 0.3563 | 22.82 | 3400 | 0.4411 | 0.7976 | 0.798 |
| 0.3539 | 24.16 | 3600 | 0.4323 | 0.8050 | 0.805 |
| 0.3527 | 25.5 | 3800 | 0.4368 | 0.8021 | 0.803 |
| 0.3425 | 26.85 | 4000 | 0.4337 | 0.7990 | 0.799 |
| 0.3432 | 28.19 | 4200 | 0.4360 | 0.7949 | 0.795 |
| 0.3355 | 29.53 | 4400 | 0.4297 | 0.8070 | 0.807 |
| 0.3332 | 30.87 | 4600 | 0.4427 | 0.7924 | 0.793 |
| 0.3347 | 32.21 | 4800 | 0.4296 | 0.8080 | 0.808 |
| 0.3237 | 33.56 | 5000 | 0.4420 | 0.8029 | 0.803 |
| 0.3285 | 34.9 | 5200 | 0.4285 | 0.8120 | 0.812 |
| 0.3225 | 36.24 | 5400 | 0.4245 | 0.8079 | 0.808 |
| 0.3157 | 37.58 | 5600 | 0.4291 | 0.8160 | 0.816 |
| 0.3182 | 38.93 | 5800 | 0.4305 | 0.8090 | 0.809 |
| 0.3149 | 40.27 | 6000 | 0.4315 | 0.8179 | 0.818 |
| 0.3104 | 41.61 | 6200 | 0.4353 | 0.8089 | 0.809 |
| 0.3152 | 42.95 | 6400 | 0.4278 | 0.8150 | 0.815 |
| 0.3131 | 44.3 | 6600 | 0.4228 | 0.8089 | 0.809 |
| 0.3032 | 45.64 | 6800 | 0.4346 | 0.8169 | 0.817 |
| 0.3059 | 46.98 | 7000 | 0.4223 | 0.8170 | 0.817 |
| 0.3012 | 48.32 | 7200 | 0.4269 | 0.8168 | 0.817 |
| 0.2998 | 49.66 | 7400 | 0.4292 | 0.8160 | 0.816 |
| 0.2988 | 51.01 | 7600 | 0.4291 | 0.8170 | 0.817 |
| 0.2952 | 52.35 | 7800 | 0.4276 | 0.8189 | 0.819 |
| 0.2965 | 53.69 | 8000 | 0.4299 | 0.8140 | 0.814 |
| 0.2942 | 55.03 | 8200 | 0.4302 | 0.8120 | 0.812 |
| 0.2903 | 56.38 | 8400 | 0.4281 | 0.8229 | 0.823 |
| 0.2922 | 57.72 | 8600 | 0.4241 | 0.8228 | 0.823 |
| 0.2918 | 59.06 | 8800 | 0.4287 | 0.8240 | 0.824 |
| 0.2895 | 60.4 | 9000 | 0.4288 | 0.8230 | 0.823 |
| 0.2875 | 61.74 | 9200 | 0.4280 | 0.8219 | 0.822 |
| 0.2852 | 63.09 | 9400 | 0.4311 | 0.8220 | 0.822 |
| 0.2895 | 64.43 | 9600 | 0.4307 | 0.8219 | 0.822 |
| 0.2858 | 65.77 | 9800 | 0.4309 | 0.8239 | 0.824 |
| 0.2862 | 67.11 | 10000 | 0.4310 | 0.8229 | 0.823 |
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2 | {"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_27M", "model-index": [{"name": "GUE_tf_4-seqsight_4096_512_27M-L8_f", "results": []}]} | mahdibaghbanzadeh/GUE_tf_4-seqsight_4096_512_27M-L8_f | null | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:mahdibaghbanzadeh/seqsight_4096_512_27M",
"region:us"
]
| null | 2024-04-26T18:29:16+00:00 |
text-generation | transformers |
# Qwen1.5-32B-Chat
## About Quantization
我们使用modelscope [swift](https://github.com/modelscope/swift/)仓库进行GPTQ量化. 量化文档可以查看[这里](https://github.com/modelscope/swift/blob/main/docs/source/LLM/LLM%E9%87%8F%E5%8C%96%E6%96%87%E6%A1%A3.md). 量化命令如下:
We use the modelscope [swift](https://github.com/modelscope/swift/) repository to perform GPTQ quantization. Quantization documentation can be found [here](https://github.com/modelscope/swift/blob/main/docs/source_en/LLM/LLM-quantization.md). The quantization command is as follows:
```bash
OMP_NUM_THREADS=14 CUDA_VISIBLE_DEVICES=7 swift export \
--model_type qwen1half-32b-chat --quant_bits 8 \
--dataset sharegpt-gpt4-mini alpaca-zh alpaca-en --quant_method gptq --quant_seqlen 8192
```
## Introduction
Qwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data. In comparison with the previous released Qwen, the improvements include:
* 8 model sizes, including 0.5B, 1.8B, 4B, 7B, 14B, 32B and 72B dense models, and an MoE model of 14B with 2.7B activated;
* Significant performance improvement in human preference for chat models;
* Multilingual support of both base and chat models;
* Stable support of 32K context length for models of all sizes
* No need of `trust_remote_code`.
For more details, please refer to our [blog post](https://qwenlm.github.io/blog/qwen1.5/) and [GitHub repo](https://github.com/QwenLM/Qwen1.5).
<br>
## Model Details
Qwen1.5 is a language model series including decoder language models of different model sizes. For each size, we release the base language model and the aligned chat model. It is based on the Transformer architecture with SwiGLU activation, attention QKV bias, group query attention, mixture of sliding window attention and full attention, etc. Additionally, we have an improved tokenizer adaptive to multiple natural languages and codes. For the beta version, temporarily we did not include GQA (except for 32B) and the mixture of SWA and full attention.
## Training details
We pretrained the models with a large amount of data, and we post-trained the models with both supervised finetuning and direct preference optimization.
## Requirements
The code of Qwen1.5 has been in the latest Hugging face transformers and we advise you to install `transformers>=4.37.0`, or you might encounter the following error:
```
KeyError: 'qwen2'
```
## Quickstart
Here provides a code snippet with `apply_chat_template` to show you how to load the tokenizer and model and how to generate contents.
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model onto
model = AutoModelForCausalLM.from_pretrained(
"study-hjt/Qwen1.5-32B-Chat-GPTQ-Int8",
torch_dtype="auto",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("study-hjt/Qwen1.5-32B-Chat-GPTQ-Int8")
prompt = "Give me a short introduction to large language model."
messages = [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(device)
generated_ids = model.generate(
model_inputs.input_ids,
max_new_tokens=512
)
generated_ids = [
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
```
## Tips
* If you encounter code switching or other bad cases, we advise you to use our provided hyper-parameters in `generation_config.json`.
## Citation
If you find our work helpful, feel free to give us a cite.
```
@article{qwen,
title={Qwen Technical Report},
author={Jinze Bai and Shuai Bai and Yunfei Chu and Zeyu Cui and Kai Dang and Xiaodong Deng and Yang Fan and Wenbin Ge and Yu Han and Fei Huang and Binyuan Hui and Luo Ji and Mei Li and Junyang Lin and Runji Lin and Dayiheng Liu and Gao Liu and Chengqiang Lu and Keming Lu and Jianxin Ma and Rui Men and Xingzhang Ren and Xuancheng Ren and Chuanqi Tan and Sinan Tan and Jianhong Tu and Peng Wang and Shijie Wang and Wei Wang and Shengguang Wu and Benfeng Xu and Jin Xu and An Yang and Hao Yang and Jian Yang and Shusheng Yang and Yang Yao and Bowen Yu and Hongyi Yuan and Zheng Yuan and Jianwei Zhang and Xingxuan Zhang and Yichang Zhang and Zhenru Zhang and Chang Zhou and Jingren Zhou and Xiaohuan Zhou and Tianhang Zhu},
journal={arXiv preprint arXiv:2309.16609},
year={2023}
}
``` | {"language": ["en", "zh"], "license": "other", "tags": ["qwen", "32b", "gptq", "int8", "chat"], "license_name": "tongyi-qianwen", "license_link": "https://huggingface.co/Qwen/Qwen1.5-32B-Chat/blob/main/LICENSE", "pipeline_tag": "text-generation"} | study-hjt/Qwen1.5-32B-Chat-GPTQ-Int8 | null | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"qwen",
"32b",
"gptq",
"int8",
"chat",
"conversational",
"en",
"zh",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"8-bit",
"region:us"
]
| null | 2024-04-26T18:30:46+00:00 |
null | null | {"license": "llama3"} | agyaatcoder/llama3-8b-instruct-bf16-A100-trtllm | null | [
"license:llama3",
"region:us"
]
| null | 2024-04-26T18:31:36+00:00 |
|
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": ["llama-factory"]} | zilongpa/aes-llama3-v1 | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"llama-factory",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-26T18:32:53+00:00 |
text-to-image | diffusers |
<!-- This model card has been generated automatically according to the information the training script had access to. You
should probably proofread and complete it, then remove this comment. -->
# Critical Dream - cosmicBboy/stable-diffusion-xl-base-1.0-lora-dreambooth-critdream-v0.7.2
<Gallery />
## Model description
These are cosmicBboy/stable-diffusion-xl-base-1.0-lora-dreambooth-critdream-v0.7.2 LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0, for the purposes of
generating images for the [Critical Dream](https://github.com/cosmicBboy/critical-dream)
project.
The weights were trained using [DreamBooth](https://dreambooth.github.io/).
LoRA for the text encoder was enabled: True.
Special VAE used for training: stabilityai/sdxl-vae.
## Trigger words
You should use a picture of [dm-matt-mercer], a dungeon master. background is a forest. fantasy art style, high quality, highly detailed, sharp focus" to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
[Download](cosmicBboy/stable-diffusion-xl-base-1.0-lora-dreambooth-critdream-v0.7.2/tree/main) them in the Files & versions tab.
## Tracker run link
https://wandb.ai/nielsbantilan/dreambooth-lora-sd-xl/runs/8n7um3yr
## Intended uses & limitations
#### How to use
```python
# TODO: add an example code snippet for running this diffusion pipeline
```
#### Limitations and bias
[TODO: provide examples of latent issues and potential remediations]
## Training details
[TODO: describe the data used to train the model] | {"license": "openrail++", "library_name": "diffusers", "tags": ["text-to-image", "stable-diffusion-xl", "stable-diffusion-xl-diffusers", "text-to-image", "diffusers", "lora", "template:sd-lora"], "base_model": "stabilityai/stable-diffusion-xl-base-1.0", "prompt": "a picture of [dm-matt-mercer], a dungeon master. background is a forest. fantasy art style, high quality, highly detailed, sharp focus\"", "widget": [{"text": "a picture of [dm-matt-mercer]", "output": {"url": "image_0.png"}}, {"text": "a picture of [dm-matt-mercer]", "output": {"url": "image_1.png"}}, {"text": "a picture of a dungeon master.", "output": {"url": "image_2.png"}}, {"text": "a picture of a dungeon master.", "output": {"url": "image_3.png"}}, {"text": "a picture of [critrole-fjord], a male half-orc warlock. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_4.png"}}, {"text": "a picture of [critrole-fjord], a male half-orc warlock. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_5.png"}}, {"text": "a picture of a male half-orc warlock", "output": {"url": "image_6.png"}}, {"text": "a picture of a male half-orc warlock", "output": {"url": "image_7.png"}}, {"text": "a picture of [critrole-beau], a female human monk. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_8.png"}}, {"text": "a picture of [critrole-beau], a female human monk. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_9.png"}}, {"text": "a picture of a female human monk", "output": {"url": "image_10.png"}}, {"text": "a picture of a female human monk", "output": {"url": "image_11.png"}}, {"text": "a picture of [critrole-caduceus], a male firbolg cleric. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_12.png"}}, {"text": "a picture of [critrole-caduceus], a male firbolg cleric. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_13.png"}}, {"text": "a picture of a male firbolg cleric", "output": {"url": "image_14.png"}}, {"text": "a picture of a male firbolg cleric", "output": {"url": "image_15.png"}}, {"text": "a picture of [critrole-caleb], a male human wizard. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_16.png"}}, {"text": "a picture of [critrole-caleb], a male human wizard. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_17.png"}}, {"text": "a picture of a male human wizard", "output": {"url": "image_18.png"}}, {"text": "a picture of a male human wizard", "output": {"url": "image_19.png"}}, {"text": "a picture of [critrole-jester], a female tiefling cleric. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_20.png"}}, {"text": "a picture of [critrole-jester], a female tiefling cleric. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_21.png"}}, {"text": "a picture of a female tiefling cleric", "output": {"url": "image_22.png"}}, {"text": "a picture of a female tiefling cleric", "output": {"url": "image_23.png"}}, {"text": "a picture of [critrole-nott], a female goblin rogue. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_24.png"}}, {"text": "a picture of [critrole-nott], a female goblin rogue. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_25.png"}}, {"text": "a picture of a female goblin rogue", "output": {"url": "image_26.png"}}, {"text": "a picture of a female goblin rogue", "output": {"url": "image_27.png"}}, {"text": "a picture of [critrole-veth], a female halfling rogue/wizard. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_28.png"}}, {"text": "a picture of [critrole-veth], a female halfling rogue/wizard. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_29.png"}}, {"text": "a picture of a female halfling rogue/wizard", "output": {"url": "image_30.png"}}, {"text": "a picture of a female halfling rogue/wizard", "output": {"url": "image_31.png"}}, {"text": "a picture of [critrole-yasha], a female aasimar barbarian. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_32.png"}}, {"text": "a picture of [critrole-yasha], a female aasimar barbarian. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_33.png"}}, {"text": "a picture of a female aasimar barbarian", "output": {"url": "image_34.png"}}, {"text": "a picture of a female aasimar barbarian", "output": {"url": "image_35.png"}}, {"text": "a picture of [critrole-mollymauk], a male tiefling blood hunter. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_36.png"}}, {"text": "a picture of [critrole-mollymauk], a male tiefling blood hunter. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_37.png"}}, {"text": "a picture of a male tiefling blood hunter", "output": {"url": "image_38.png"}}, {"text": "a picture of a male tiefling blood hunter", "output": {"url": "image_39.png"}}, {"text": "a picture of [critrole-essek], a male drow wizard. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_40.png"}}, {"text": "a picture of [critrole-essek], a male drow wizard. background is a forest. fantasy art style, high quality, highly detailed, sharp focus", "output": {"url": "image_41.png"}}, {"text": "a picture of a male drow wizard", "output": {"url": "image_42.png"}}, {"text": "a picture of a male drow wizard", "output": {"url": "image_43.png"}}]} | cosmicBboy/stable-diffusion-xl-base-1.0-lora-dreambooth-critdream-v0.7.2 | null | [
"diffusers",
"text-to-image",
"stable-diffusion-xl",
"stable-diffusion-xl-diffusers",
"lora",
"template:sd-lora",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"license:openrail++",
"region:us"
]
| null | 2024-04-26T18:33:21+00:00 |
null | peft |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# GUE_tf_4-seqsight_4096_512_27M-L32_f
This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_27M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_27M) on the [mahdibaghbanzadeh/GUE_tf_4](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_4) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5227
- F1 Score: 0.8399
- Accuracy: 0.84
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 10000
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|
| 0.5228 | 1.34 | 200 | 0.4971 | 0.7473 | 0.748 |
| 0.4517 | 2.68 | 400 | 0.4751 | 0.7729 | 0.773 |
| 0.4287 | 4.03 | 600 | 0.4618 | 0.7778 | 0.778 |
| 0.409 | 5.37 | 800 | 0.4716 | 0.7796 | 0.78 |
| 0.3943 | 6.71 | 1000 | 0.4604 | 0.7829 | 0.784 |
| 0.3784 | 8.05 | 1200 | 0.4458 | 0.7920 | 0.792 |
| 0.3667 | 9.4 | 1400 | 0.4354 | 0.8010 | 0.801 |
| 0.3545 | 10.74 | 1600 | 0.4365 | 0.8078 | 0.808 |
| 0.3391 | 12.08 | 1800 | 0.4490 | 0.8090 | 0.809 |
| 0.3274 | 13.42 | 2000 | 0.4355 | 0.7985 | 0.799 |
| 0.3157 | 14.77 | 2200 | 0.4221 | 0.8240 | 0.824 |
| 0.3041 | 16.11 | 2400 | 0.4244 | 0.8210 | 0.821 |
| 0.295 | 17.45 | 2600 | 0.4261 | 0.8220 | 0.822 |
| 0.2844 | 18.79 | 2800 | 0.4250 | 0.8330 | 0.833 |
| 0.2815 | 20.13 | 3000 | 0.4180 | 0.8329 | 0.833 |
| 0.2629 | 21.48 | 3200 | 0.4320 | 0.8320 | 0.832 |
| 0.256 | 22.82 | 3400 | 0.4342 | 0.8358 | 0.836 |
| 0.2502 | 24.16 | 3600 | 0.4235 | 0.8289 | 0.829 |
| 0.2416 | 25.5 | 3800 | 0.4417 | 0.8377 | 0.838 |
| 0.2316 | 26.85 | 4000 | 0.4327 | 0.8367 | 0.837 |
| 0.2244 | 28.19 | 4200 | 0.4546 | 0.8420 | 0.842 |
| 0.2172 | 29.53 | 4400 | 0.4484 | 0.8406 | 0.841 |
| 0.2071 | 30.87 | 4600 | 0.4583 | 0.8390 | 0.839 |
| 0.2096 | 32.21 | 4800 | 0.4549 | 0.8390 | 0.839 |
| 0.194 | 33.56 | 5000 | 0.4626 | 0.8419 | 0.842 |
| 0.1957 | 34.9 | 5200 | 0.4513 | 0.8509 | 0.851 |
| 0.1841 | 36.24 | 5400 | 0.4581 | 0.8468 | 0.847 |
| 0.178 | 37.58 | 5600 | 0.4457 | 0.8550 | 0.855 |
| 0.1773 | 38.93 | 5800 | 0.4750 | 0.8519 | 0.852 |
| 0.1739 | 40.27 | 6000 | 0.4778 | 0.8567 | 0.857 |
| 0.1684 | 41.61 | 6200 | 0.4822 | 0.8609 | 0.861 |
| 0.1642 | 42.95 | 6400 | 0.4641 | 0.8578 | 0.858 |
| 0.162 | 44.3 | 6600 | 0.4911 | 0.8526 | 0.853 |
| 0.1588 | 45.64 | 6800 | 0.4878 | 0.8590 | 0.859 |
| 0.1595 | 46.98 | 7000 | 0.4724 | 0.8547 | 0.855 |
| 0.1467 | 48.32 | 7200 | 0.4968 | 0.8566 | 0.857 |
| 0.1511 | 49.66 | 7400 | 0.5053 | 0.8556 | 0.856 |
| 0.1443 | 51.01 | 7600 | 0.4984 | 0.8597 | 0.86 |
| 0.1397 | 52.35 | 7800 | 0.5039 | 0.8567 | 0.857 |
| 0.1424 | 53.69 | 8000 | 0.4894 | 0.8547 | 0.855 |
| 0.138 | 55.03 | 8200 | 0.4977 | 0.8618 | 0.862 |
| 0.1317 | 56.38 | 8400 | 0.5178 | 0.8617 | 0.862 |
| 0.1363 | 57.72 | 8600 | 0.4955 | 0.8617 | 0.862 |
| 0.1281 | 59.06 | 8800 | 0.5089 | 0.8607 | 0.861 |
| 0.1302 | 60.4 | 9000 | 0.5105 | 0.8588 | 0.859 |
| 0.1314 | 61.74 | 9200 | 0.5196 | 0.8627 | 0.863 |
| 0.124 | 63.09 | 9400 | 0.5311 | 0.8587 | 0.859 |
| 0.1232 | 64.43 | 9600 | 0.5326 | 0.8617 | 0.862 |
| 0.1229 | 65.77 | 9800 | 0.5297 | 0.8587 | 0.859 |
| 0.1233 | 67.11 | 10000 | 0.5287 | 0.8607 | 0.861 |
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2 | {"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_27M", "model-index": [{"name": "GUE_tf_4-seqsight_4096_512_27M-L32_f", "results": []}]} | mahdibaghbanzadeh/GUE_tf_4-seqsight_4096_512_27M-L32_f | null | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:mahdibaghbanzadeh/seqsight_4096_512_27M",
"region:us"
]
| null | 2024-04-26T18:33:27+00:00 |
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. -->
# idefics2-8b-docvqa-finetuned-tutorial
This model is a fine-tuned version of [HuggingFaceM4/idefics2-8b](https://huggingface.co/HuggingFaceM4/idefics2-8b) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 2
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "HuggingFaceM4/idefics2-8b", "model-index": [{"name": "idefics2-8b-docvqa-finetuned-tutorial", "results": []}]} | GoHugo/idefics2-8b-docvqa-finetuned-tutorial | null | [
"safetensors",
"generated_from_trainer",
"base_model:HuggingFaceM4/idefics2-8b",
"license:apache-2.0",
"region:us"
]
| null | 2024-04-26T18:33:43+00:00 |
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. -->
# bert-finetuned-sem_eval-english
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: nan
- F1: 0.0
- Roc Auc: 0.5
- Accuracy: 0.0158
## Model description
More information needed
## Intended uses & 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: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---:|:-------:|:--------:|
| 0.3755 | 1.0 | 855 | nan | 0.0 | 0.5 | 0.0158 |
### Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "metrics": ["f1", "accuracy"], "base_model": "bert-base-uncased", "model-index": [{"name": "bert-finetuned-sem_eval-english", "results": []}]} | Kelvin950/bert-finetuned-sem_eval-english | null | [
"transformers",
"tensorboard",
"safetensors",
"bert",
"text-classification",
"generated_from_trainer",
"base_model:bert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T18:34:24+00:00 |
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. -->
# kaist-mistral-orpo-capybara-beta0.05-1epoch-ohp-15k-strat-1-beta0.2-2epoch
This model is a fine-tuned version of [orpo-explorers/kaist-mistral-orpo-capybara-beta-0.05-1epoch](https://huggingface.co/orpo-explorers/kaist-mistral-orpo-capybara-beta-0.05-1epoch) on the orpo-explorers/OHP-15k-Stratified-1 dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 2
### Training results
### Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2.post303
- Datasets 2.18.0
- Tokenizers 0.15.2
| {"tags": ["alignment-handbook", "trl", "orpo", "generated_from_trainer", "trl", "orpo", "generated_from_trainer"], "datasets": ["orpo-explorers/OHP-15k-Stratified-1"], "base_model": "orpo-explorers/kaist-mistral-orpo-capybara-beta-0.05-1epoch", "model-index": [{"name": "kaist-mistral-orpo-capybara-beta0.05-1epoch-ohp-15k-strat-1-beta0.2-2epoch", "results": []}]} | orpo-explorers/kaist-mistral-orpo-capybara-beta0.05-1epoch-ohp-15k-strat-1-beta0.2-2epoch | null | [
"transformers",
"tensorboard",
"safetensors",
"mistral",
"text-generation",
"alignment-handbook",
"trl",
"orpo",
"generated_from_trainer",
"conversational",
"dataset:orpo-explorers/OHP-15k-Stratified-1",
"base_model:orpo-explorers/kaist-mistral-orpo-capybara-beta-0.05-1epoch",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-26T18:35:00+00:00 |
text-generation | transformers |
# Model Card for Model ID
Fine-tuning for CS5242 project
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [DreamOnRain]
- **Finetuned from model [optional]:** state-spaces/mamba-1.4b-hf
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** https://github.com/DreamOnRain/Deep-Learning-Final-Project
## 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. -->
https://huggingface.co/datasets/microsoft/orca-math-word-problems-200k
| {"library_name": "transformers", "tags": []} | DreamOnRain/mamba-1.4b-msmath | null | [
"transformers",
"safetensors",
"mamba",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T18:35:13+00:00 |
text-generation | transformers | {} | LuangMV97/Roberta-GPT2_EmpAI_EOSSI | null | [
"transformers",
"tensorboard",
"safetensors",
"gpt2",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-26T18:35:56+00:00 |
|
text-classification | transformers | {} | jimmy58/my_awesome_model | null | [
"transformers",
"tensorboard",
"safetensors",
"distilbert",
"text-classification",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T18:36:51+00:00 |
|
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. -->
# flan-t5-base-eLife
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 2.0533
- Rouge1: 16.8601
- Rouge2: 3.5043
- Rougel: 13.0262
- Rougelsum: 15.2504
- 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: 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: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
| 2.6071 | 1.0 | 544 | 2.2323 | 16.7606 | 3.2667 | 12.9074 | 15.1681 | 19.0 |
| 2.438 | 2.0 | 1088 | 2.1395 | 16.9106 | 3.3542 | 13.0126 | 15.3345 | 19.0 |
| 2.3649 | 3.0 | 1632 | 2.0900 | 16.9637 | 3.5315 | 13.0919 | 15.3446 | 19.0 |
| 2.3264 | 4.0 | 2176 | 2.0624 | 16.8183 | 3.4983 | 13.0296 | 15.226 | 19.0 |
| 2.292 | 5.0 | 2720 | 2.0533 | 16.8601 | 3.5043 | 13.0262 | 15.2504 | 19.0 |
### Framework versions
- Transformers 4.40.1
- Pytorch 2.1.2
- Datasets 2.19.0
- Tokenizers 0.19.1
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "metrics": ["rouge"], "base_model": "google/flan-t5-base", "model-index": [{"name": "flan-t5-base-eLife", "results": []}]} | Veera007/flan-t5-base-eLife | null | [
"transformers",
"tensorboard",
"safetensors",
"t5",
"text2text-generation",
"generated_from_trainer",
"base_model:google/flan-t5-base",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-26T18:38:03+00:00 |
null | peft |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# GUE_tf_3-seqsight_4096_512_27M-L1_f
This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_27M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_27M) on the [mahdibaghbanzadeh/GUE_tf_3](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_3) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5534
- F1 Score: 0.7083
- Accuracy: 0.71
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 10000
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|
| 0.6336 | 0.93 | 200 | 0.5921 | 0.6805 | 0.681 |
| 0.6013 | 1.87 | 400 | 0.5761 | 0.6891 | 0.689 |
| 0.5929 | 2.8 | 600 | 0.5642 | 0.7022 | 0.705 |
| 0.5865 | 3.74 | 800 | 0.5626 | 0.7035 | 0.704 |
| 0.5814 | 4.67 | 1000 | 0.5584 | 0.7050 | 0.707 |
| 0.5801 | 5.61 | 1200 | 0.5565 | 0.7044 | 0.706 |
| 0.575 | 6.54 | 1400 | 0.5565 | 0.7026 | 0.703 |
| 0.5726 | 7.48 | 1600 | 0.5521 | 0.7022 | 0.703 |
| 0.5708 | 8.41 | 1800 | 0.5531 | 0.7006 | 0.701 |
| 0.5719 | 9.35 | 2000 | 0.5468 | 0.7022 | 0.704 |
| 0.5643 | 10.28 | 2200 | 0.5493 | 0.6981 | 0.698 |
| 0.5629 | 11.21 | 2400 | 0.5443 | 0.7081 | 0.71 |
| 0.5637 | 12.15 | 2600 | 0.5442 | 0.6938 | 0.699 |
| 0.558 | 13.08 | 2800 | 0.5411 | 0.7139 | 0.717 |
| 0.561 | 14.02 | 3000 | 0.5403 | 0.7059 | 0.707 |
| 0.5582 | 14.95 | 3200 | 0.5406 | 0.7025 | 0.705 |
| 0.5559 | 15.89 | 3400 | 0.5382 | 0.7041 | 0.705 |
| 0.5548 | 16.82 | 3600 | 0.5385 | 0.7087 | 0.71 |
| 0.5534 | 17.76 | 3800 | 0.5364 | 0.7042 | 0.706 |
| 0.5569 | 18.69 | 4000 | 0.5371 | 0.7166 | 0.717 |
| 0.5532 | 19.63 | 4200 | 0.5376 | 0.7093 | 0.714 |
| 0.5543 | 20.56 | 4400 | 0.5363 | 0.7097 | 0.712 |
| 0.5511 | 21.5 | 4600 | 0.5401 | 0.7211 | 0.721 |
| 0.5523 | 22.43 | 4800 | 0.5353 | 0.7164 | 0.719 |
| 0.5522 | 23.36 | 5000 | 0.5363 | 0.7219 | 0.722 |
| 0.5488 | 24.3 | 5200 | 0.5435 | 0.7154 | 0.716 |
| 0.5454 | 25.23 | 5400 | 0.5368 | 0.7144 | 0.718 |
| 0.5527 | 26.17 | 5600 | 0.5334 | 0.7199 | 0.721 |
| 0.5439 | 27.1 | 5800 | 0.5323 | 0.7198 | 0.721 |
| 0.5467 | 28.04 | 6000 | 0.5330 | 0.7171 | 0.718 |
| 0.5456 | 28.97 | 6200 | 0.5393 | 0.7221 | 0.722 |
| 0.5471 | 29.91 | 6400 | 0.5320 | 0.7210 | 0.722 |
| 0.5461 | 30.84 | 6600 | 0.5322 | 0.7242 | 0.725 |
| 0.5428 | 31.78 | 6800 | 0.5348 | 0.7229 | 0.723 |
| 0.5425 | 32.71 | 7000 | 0.5333 | 0.7175 | 0.718 |
| 0.5467 | 33.64 | 7200 | 0.5320 | 0.7204 | 0.722 |
| 0.5393 | 34.58 | 7400 | 0.5364 | 0.7200 | 0.72 |
| 0.545 | 35.51 | 7600 | 0.5313 | 0.7218 | 0.722 |
| 0.5428 | 36.45 | 7800 | 0.5325 | 0.7228 | 0.723 |
| 0.5445 | 37.38 | 8000 | 0.5310 | 0.7227 | 0.723 |
| 0.54 | 38.32 | 8200 | 0.5314 | 0.7244 | 0.726 |
| 0.5395 | 39.25 | 8400 | 0.5305 | 0.7248 | 0.726 |
| 0.5418 | 40.19 | 8600 | 0.5306 | 0.7264 | 0.727 |
| 0.5403 | 41.12 | 8800 | 0.5309 | 0.7233 | 0.724 |
| 0.5395 | 42.06 | 9000 | 0.5313 | 0.7224 | 0.723 |
| 0.5402 | 42.99 | 9200 | 0.5318 | 0.7160 | 0.716 |
| 0.5381 | 43.93 | 9400 | 0.5317 | 0.7179 | 0.718 |
| 0.5415 | 44.86 | 9600 | 0.5314 | 0.7187 | 0.719 |
| 0.5409 | 45.79 | 9800 | 0.5315 | 0.7235 | 0.724 |
| 0.5352 | 46.73 | 10000 | 0.5320 | 0.7197 | 0.72 |
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2 | {"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_27M", "model-index": [{"name": "GUE_tf_3-seqsight_4096_512_27M-L1_f", "results": []}]} | mahdibaghbanzadeh/GUE_tf_3-seqsight_4096_512_27M-L1_f | null | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:mahdibaghbanzadeh/seqsight_4096_512_27M",
"region:us"
]
| null | 2024-04-26T18:39:28+00:00 |
text-generation | transformers | {"license": "mit"} | skai24/sn9-108 | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-26T18:39:48+00:00 |
|
null | peft |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# GUE_tf_3-seqsight_4096_512_27M-L8_f
This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_27M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_27M) on the [mahdibaghbanzadeh/GUE_tf_3](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_3) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5302
- F1 Score: 0.7378
- Accuracy: 0.739
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 10000
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|
| 0.6251 | 0.93 | 200 | 0.5772 | 0.6931 | 0.693 |
| 0.593 | 1.87 | 400 | 0.5740 | 0.6955 | 0.697 |
| 0.5829 | 2.8 | 600 | 0.5500 | 0.7100 | 0.711 |
| 0.5721 | 3.74 | 800 | 0.5487 | 0.7071 | 0.707 |
| 0.5667 | 4.67 | 1000 | 0.5424 | 0.7123 | 0.713 |
| 0.5654 | 5.61 | 1200 | 0.5387 | 0.7126 | 0.716 |
| 0.5586 | 6.54 | 1400 | 0.5389 | 0.7111 | 0.711 |
| 0.5558 | 7.48 | 1600 | 0.5340 | 0.7213 | 0.722 |
| 0.5544 | 8.41 | 1800 | 0.5401 | 0.7211 | 0.721 |
| 0.5538 | 9.35 | 2000 | 0.5311 | 0.7153 | 0.718 |
| 0.5452 | 10.28 | 2200 | 0.5298 | 0.7269 | 0.727 |
| 0.5437 | 11.21 | 2400 | 0.5304 | 0.7261 | 0.727 |
| 0.5423 | 12.15 | 2600 | 0.5341 | 0.7164 | 0.72 |
| 0.5357 | 13.08 | 2800 | 0.5379 | 0.7162 | 0.721 |
| 0.5387 | 14.02 | 3000 | 0.5327 | 0.7255 | 0.726 |
| 0.5341 | 14.95 | 3200 | 0.5263 | 0.7216 | 0.723 |
| 0.5322 | 15.89 | 3400 | 0.5244 | 0.7245 | 0.725 |
| 0.5296 | 16.82 | 3600 | 0.5294 | 0.7299 | 0.731 |
| 0.5268 | 17.76 | 3800 | 0.5279 | 0.7274 | 0.729 |
| 0.5276 | 18.69 | 4000 | 0.5259 | 0.7360 | 0.736 |
| 0.5254 | 19.63 | 4200 | 0.5299 | 0.7208 | 0.724 |
| 0.5235 | 20.56 | 4400 | 0.5268 | 0.7320 | 0.733 |
| 0.5218 | 21.5 | 4600 | 0.5341 | 0.7310 | 0.731 |
| 0.5192 | 22.43 | 4800 | 0.5278 | 0.7280 | 0.73 |
| 0.5193 | 23.36 | 5000 | 0.5368 | 0.7311 | 0.731 |
| 0.514 | 24.3 | 5200 | 0.5428 | 0.7221 | 0.723 |
| 0.513 | 25.23 | 5400 | 0.5324 | 0.7318 | 0.734 |
| 0.5177 | 26.17 | 5600 | 0.5264 | 0.7354 | 0.736 |
| 0.5096 | 27.1 | 5800 | 0.5274 | 0.7296 | 0.73 |
| 0.5098 | 28.04 | 6000 | 0.5282 | 0.7338 | 0.734 |
| 0.5094 | 28.97 | 6200 | 0.5376 | 0.7301 | 0.73 |
| 0.5096 | 29.91 | 6400 | 0.5286 | 0.7243 | 0.726 |
| 0.5067 | 30.84 | 6600 | 0.5260 | 0.7338 | 0.734 |
| 0.5037 | 31.78 | 6800 | 0.5354 | 0.7221 | 0.722 |
| 0.5001 | 32.71 | 7000 | 0.5312 | 0.734 | 0.734 |
| 0.5076 | 33.64 | 7200 | 0.5269 | 0.7299 | 0.73 |
| 0.4987 | 34.58 | 7400 | 0.5355 | 0.7236 | 0.724 |
| 0.5002 | 35.51 | 7600 | 0.5309 | 0.7291 | 0.729 |
| 0.5002 | 36.45 | 7800 | 0.5336 | 0.7310 | 0.731 |
| 0.5023 | 37.38 | 8000 | 0.5285 | 0.7339 | 0.734 |
| 0.4955 | 38.32 | 8200 | 0.5301 | 0.7377 | 0.738 |
| 0.4972 | 39.25 | 8400 | 0.5295 | 0.7368 | 0.737 |
| 0.4966 | 40.19 | 8600 | 0.5290 | 0.7340 | 0.734 |
| 0.4969 | 41.12 | 8800 | 0.5283 | 0.7357 | 0.736 |
| 0.496 | 42.06 | 9000 | 0.5307 | 0.7338 | 0.734 |
| 0.4939 | 42.99 | 9200 | 0.5331 | 0.7301 | 0.73 |
| 0.4927 | 43.93 | 9400 | 0.5319 | 0.7320 | 0.732 |
| 0.4988 | 44.86 | 9600 | 0.5312 | 0.7340 | 0.734 |
| 0.4964 | 45.79 | 9800 | 0.5309 | 0.7330 | 0.733 |
| 0.4872 | 46.73 | 10000 | 0.5321 | 0.7350 | 0.735 |
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2 | {"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_27M", "model-index": [{"name": "GUE_tf_3-seqsight_4096_512_27M-L8_f", "results": []}]} | mahdibaghbanzadeh/GUE_tf_3-seqsight_4096_512_27M-L8_f | null | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:mahdibaghbanzadeh/seqsight_4096_512_27M",
"region:us"
]
| null | 2024-04-26T18:40:00+00:00 |
null | null | {"license": "openrail"} | outhmanabbassi/bloomz-560 | null | [
"license:openrail",
"region:us"
]
| null | 2024-04-26T18:40:09+00:00 |
|
null | peft |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# GUE_tf_3-seqsight_4096_512_27M-L32_f
This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_27M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_27M) on the [mahdibaghbanzadeh/GUE_tf_3](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_3) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5757
- F1 Score: 0.7160
- Accuracy: 0.719
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 10000
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|
| 0.6196 | 0.93 | 200 | 0.5650 | 0.7042 | 0.705 |
| 0.5865 | 1.87 | 400 | 0.5609 | 0.7049 | 0.706 |
| 0.573 | 2.8 | 600 | 0.5429 | 0.7068 | 0.707 |
| 0.5621 | 3.74 | 800 | 0.5423 | 0.7150 | 0.715 |
| 0.5552 | 4.67 | 1000 | 0.5362 | 0.7208 | 0.723 |
| 0.5524 | 5.61 | 1200 | 0.5359 | 0.7134 | 0.719 |
| 0.5428 | 6.54 | 1400 | 0.5353 | 0.7211 | 0.721 |
| 0.5352 | 7.48 | 1600 | 0.5376 | 0.7290 | 0.73 |
| 0.5344 | 8.41 | 1800 | 0.5390 | 0.7201 | 0.72 |
| 0.5304 | 9.35 | 2000 | 0.5352 | 0.7218 | 0.724 |
| 0.5181 | 10.28 | 2200 | 0.5365 | 0.7169 | 0.717 |
| 0.5158 | 11.21 | 2400 | 0.5385 | 0.7257 | 0.726 |
| 0.51 | 12.15 | 2600 | 0.5345 | 0.7261 | 0.728 |
| 0.5019 | 13.08 | 2800 | 0.5461 | 0.7361 | 0.739 |
| 0.502 | 14.02 | 3000 | 0.5384 | 0.7325 | 0.733 |
| 0.4945 | 14.95 | 3200 | 0.5341 | 0.7346 | 0.735 |
| 0.4908 | 15.89 | 3400 | 0.5397 | 0.7349 | 0.735 |
| 0.4849 | 16.82 | 3600 | 0.5399 | 0.7374 | 0.738 |
| 0.4797 | 17.76 | 3800 | 0.5438 | 0.7325 | 0.733 |
| 0.4759 | 18.69 | 4000 | 0.5481 | 0.7241 | 0.724 |
| 0.4741 | 19.63 | 4200 | 0.5460 | 0.7314 | 0.732 |
| 0.4673 | 20.56 | 4400 | 0.5517 | 0.7390 | 0.739 |
| 0.465 | 21.5 | 4600 | 0.5651 | 0.7358 | 0.736 |
| 0.4579 | 22.43 | 4800 | 0.5588 | 0.7359 | 0.736 |
| 0.4585 | 23.36 | 5000 | 0.5697 | 0.7221 | 0.722 |
| 0.4462 | 24.3 | 5200 | 0.6016 | 0.7110 | 0.712 |
| 0.4458 | 25.23 | 5400 | 0.5820 | 0.7439 | 0.744 |
| 0.4461 | 26.17 | 5600 | 0.5598 | 0.7360 | 0.736 |
| 0.4355 | 27.1 | 5800 | 0.5835 | 0.7251 | 0.725 |
| 0.4345 | 28.04 | 6000 | 0.5700 | 0.7269 | 0.727 |
| 0.4324 | 28.97 | 6200 | 0.5870 | 0.7270 | 0.727 |
| 0.43 | 29.91 | 6400 | 0.5772 | 0.7340 | 0.734 |
| 0.4277 | 30.84 | 6600 | 0.5741 | 0.7281 | 0.728 |
| 0.4202 | 31.78 | 6800 | 0.5899 | 0.7172 | 0.718 |
| 0.417 | 32.71 | 7000 | 0.5907 | 0.7229 | 0.723 |
| 0.4214 | 33.64 | 7200 | 0.5796 | 0.7210 | 0.721 |
| 0.412 | 34.58 | 7400 | 0.6006 | 0.7141 | 0.715 |
| 0.4098 | 35.51 | 7600 | 0.6078 | 0.7123 | 0.713 |
| 0.4095 | 36.45 | 7800 | 0.6015 | 0.7279 | 0.728 |
| 0.4098 | 37.38 | 8000 | 0.5923 | 0.7240 | 0.724 |
| 0.4009 | 38.32 | 8200 | 0.5965 | 0.7290 | 0.729 |
| 0.4002 | 39.25 | 8400 | 0.6121 | 0.7187 | 0.719 |
| 0.3983 | 40.19 | 8600 | 0.6080 | 0.7085 | 0.709 |
| 0.4017 | 41.12 | 8800 | 0.6000 | 0.7290 | 0.729 |
| 0.3979 | 42.06 | 9000 | 0.5991 | 0.7249 | 0.725 |
| 0.3928 | 42.99 | 9200 | 0.6146 | 0.7145 | 0.715 |
| 0.3933 | 43.93 | 9400 | 0.6160 | 0.7116 | 0.712 |
| 0.3961 | 44.86 | 9600 | 0.6121 | 0.7198 | 0.72 |
| 0.3949 | 45.79 | 9800 | 0.6115 | 0.7209 | 0.721 |
| 0.3872 | 46.73 | 10000 | 0.6145 | 0.7228 | 0.723 |
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2 | {"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_27M", "model-index": [{"name": "GUE_tf_3-seqsight_4096_512_27M-L32_f", "results": []}]} | mahdibaghbanzadeh/GUE_tf_3-seqsight_4096_512_27M-L32_f | null | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:mahdibaghbanzadeh/seqsight_4096_512_27M",
"region:us"
]
| null | 2024-04-26T18:40:15+00:00 |
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 0.7.2.dev0 | {"library_name": "peft", "base_model": "meta-llama/Meta-Llama-3-8B"} | yiyic/llama-text-entprop-lora-clf-epoch-2 | null | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:meta-llama/Meta-Llama-3-8B",
"region:us"
]
| null | 2024-04-26T18:40:22+00:00 |
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 0.7.2.dev0 | {"library_name": "peft", "base_model": "meta-llama/Meta-Llama-3-8B"} | yiyic/llama-text-prop-lora-clf-epoch-2 | null | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:meta-llama/Meta-Llama-3-8B",
"region:us"
]
| null | 2024-04-26T18:40:42+00:00 |
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 0.7.2.dev0 | {"library_name": "peft", "base_model": "meta-llama/Meta-Llama-3-8B"} | yiyic/llama-text-ent-lora-clf-epoch-2 | null | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:meta-llama/Meta-Llama-3-8B",
"region:us"
]
| null | 2024-04-26T18:41:03+00:00 |
null | peft |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# GUE_tf_2-seqsight_4096_512_27M-L1_f
This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_27M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_27M) on the [mahdibaghbanzadeh/GUE_tf_2](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_2) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4392
- F1 Score: 0.8006
- Accuracy: 0.801
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 10000
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|
| 0.5821 | 1.34 | 200 | 0.5406 | 0.7221 | 0.725 |
| 0.5367 | 2.68 | 400 | 0.5194 | 0.7460 | 0.746 |
| 0.5265 | 4.03 | 600 | 0.5139 | 0.7440 | 0.744 |
| 0.5204 | 5.37 | 800 | 0.5113 | 0.7479 | 0.748 |
| 0.5163 | 6.71 | 1000 | 0.5139 | 0.7416 | 0.742 |
| 0.5112 | 8.05 | 1200 | 0.5146 | 0.7416 | 0.742 |
| 0.5067 | 9.4 | 1400 | 0.5053 | 0.7459 | 0.746 |
| 0.5032 | 10.74 | 1600 | 0.5028 | 0.7439 | 0.744 |
| 0.501 | 12.08 | 1800 | 0.5067 | 0.7498 | 0.75 |
| 0.4987 | 13.42 | 2000 | 0.5001 | 0.7470 | 0.747 |
| 0.4958 | 14.77 | 2200 | 0.5031 | 0.7393 | 0.741 |
| 0.4901 | 16.11 | 2400 | 0.4992 | 0.7440 | 0.744 |
| 0.4937 | 17.45 | 2600 | 0.4976 | 0.7411 | 0.742 |
| 0.488 | 18.79 | 2800 | 0.4947 | 0.7458 | 0.746 |
| 0.4819 | 20.13 | 3000 | 0.4927 | 0.7410 | 0.741 |
| 0.4847 | 21.48 | 3200 | 0.4984 | 0.7468 | 0.747 |
| 0.4834 | 22.82 | 3400 | 0.4906 | 0.7450 | 0.745 |
| 0.4797 | 24.16 | 3600 | 0.4902 | 0.7470 | 0.747 |
| 0.475 | 25.5 | 3800 | 0.4900 | 0.7506 | 0.751 |
| 0.4811 | 26.85 | 4000 | 0.4882 | 0.7546 | 0.755 |
| 0.4781 | 28.19 | 4200 | 0.4883 | 0.7489 | 0.749 |
| 0.4742 | 29.53 | 4400 | 0.4902 | 0.7519 | 0.752 |
| 0.4739 | 30.87 | 4600 | 0.4887 | 0.7500 | 0.75 |
| 0.4754 | 32.21 | 4800 | 0.4897 | 0.7514 | 0.752 |
| 0.473 | 33.56 | 5000 | 0.4892 | 0.7479 | 0.748 |
| 0.4743 | 34.9 | 5200 | 0.4876 | 0.7550 | 0.755 |
| 0.4674 | 36.24 | 5400 | 0.4873 | 0.7486 | 0.749 |
| 0.4734 | 37.58 | 5600 | 0.4871 | 0.7510 | 0.751 |
| 0.4714 | 38.93 | 5800 | 0.4868 | 0.7486 | 0.749 |
| 0.4676 | 40.27 | 6000 | 0.4875 | 0.7500 | 0.751 |
| 0.466 | 41.61 | 6200 | 0.4867 | 0.7436 | 0.744 |
| 0.4669 | 42.95 | 6400 | 0.4867 | 0.7500 | 0.75 |
| 0.4633 | 44.3 | 6600 | 0.4883 | 0.7529 | 0.753 |
| 0.4674 | 45.64 | 6800 | 0.4870 | 0.7500 | 0.75 |
| 0.464 | 46.98 | 7000 | 0.4868 | 0.7556 | 0.756 |
| 0.4655 | 48.32 | 7200 | 0.4851 | 0.7569 | 0.757 |
| 0.4635 | 49.66 | 7400 | 0.4846 | 0.7577 | 0.758 |
| 0.4636 | 51.01 | 7600 | 0.4851 | 0.7588 | 0.759 |
| 0.4614 | 52.35 | 7800 | 0.4859 | 0.7616 | 0.762 |
| 0.464 | 53.69 | 8000 | 0.4863 | 0.7603 | 0.761 |
| 0.4598 | 55.03 | 8200 | 0.4852 | 0.7578 | 0.758 |
| 0.4636 | 56.38 | 8400 | 0.4859 | 0.7510 | 0.751 |
| 0.463 | 57.72 | 8600 | 0.4855 | 0.7556 | 0.756 |
| 0.4601 | 59.06 | 8800 | 0.4852 | 0.7549 | 0.755 |
| 0.4594 | 60.4 | 9000 | 0.4858 | 0.7530 | 0.753 |
| 0.4617 | 61.74 | 9200 | 0.4857 | 0.7548 | 0.755 |
| 0.4611 | 63.09 | 9400 | 0.4855 | 0.7529 | 0.753 |
| 0.4581 | 64.43 | 9600 | 0.4858 | 0.7558 | 0.756 |
| 0.4635 | 65.77 | 9800 | 0.4857 | 0.7499 | 0.75 |
| 0.4567 | 67.11 | 10000 | 0.4856 | 0.7548 | 0.755 |
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2 | {"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_27M", "model-index": [{"name": "GUE_tf_2-seqsight_4096_512_27M-L1_f", "results": []}]} | mahdibaghbanzadeh/GUE_tf_2-seqsight_4096_512_27M-L1_f | null | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:mahdibaghbanzadeh/seqsight_4096_512_27M",
"region:us"
]
| null | 2024-04-26T18:41:29+00:00 |
null | peft |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# GUE_tf_2-seqsight_4096_512_27M-L8_f
This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_27M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_27M) on the [mahdibaghbanzadeh/GUE_tf_2](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_2) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4357
- F1 Score: 0.7959
- Accuracy: 0.796
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 10000
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|
| 0.5707 | 1.34 | 200 | 0.5330 | 0.7266 | 0.729 |
| 0.5253 | 2.68 | 400 | 0.5183 | 0.7458 | 0.746 |
| 0.512 | 4.03 | 600 | 0.5077 | 0.7490 | 0.749 |
| 0.5027 | 5.37 | 800 | 0.5052 | 0.7540 | 0.754 |
| 0.4982 | 6.71 | 1000 | 0.5058 | 0.7530 | 0.753 |
| 0.4888 | 8.05 | 1200 | 0.4978 | 0.7550 | 0.755 |
| 0.4837 | 9.4 | 1400 | 0.4945 | 0.7559 | 0.756 |
| 0.479 | 10.74 | 1600 | 0.4928 | 0.7519 | 0.752 |
| 0.4759 | 12.08 | 1800 | 0.4964 | 0.7549 | 0.755 |
| 0.4692 | 13.42 | 2000 | 0.4926 | 0.7630 | 0.763 |
| 0.4676 | 14.77 | 2200 | 0.4994 | 0.7447 | 0.747 |
| 0.4587 | 16.11 | 2400 | 0.4964 | 0.7550 | 0.755 |
| 0.4621 | 17.45 | 2600 | 0.4918 | 0.7457 | 0.747 |
| 0.4554 | 18.79 | 2800 | 0.4884 | 0.7522 | 0.753 |
| 0.4459 | 20.13 | 3000 | 0.4900 | 0.7570 | 0.757 |
| 0.4487 | 21.48 | 3200 | 0.4990 | 0.7565 | 0.757 |
| 0.4448 | 22.82 | 3400 | 0.4886 | 0.7580 | 0.758 |
| 0.4434 | 24.16 | 3600 | 0.4864 | 0.7679 | 0.768 |
| 0.435 | 25.5 | 3800 | 0.4936 | 0.7609 | 0.761 |
| 0.4399 | 26.85 | 4000 | 0.4857 | 0.7620 | 0.762 |
| 0.4354 | 28.19 | 4200 | 0.4952 | 0.7618 | 0.762 |
| 0.429 | 29.53 | 4400 | 0.5009 | 0.7517 | 0.752 |
| 0.4264 | 30.87 | 4600 | 0.4936 | 0.7500 | 0.75 |
| 0.4273 | 32.21 | 4800 | 0.4978 | 0.7520 | 0.752 |
| 0.4233 | 33.56 | 5000 | 0.5032 | 0.7550 | 0.755 |
| 0.4222 | 34.9 | 5200 | 0.5006 | 0.7529 | 0.753 |
| 0.4152 | 36.24 | 5400 | 0.4964 | 0.7630 | 0.763 |
| 0.4159 | 37.58 | 5600 | 0.5015 | 0.7510 | 0.751 |
| 0.414 | 38.93 | 5800 | 0.4974 | 0.752 | 0.752 |
| 0.4099 | 40.27 | 6000 | 0.4966 | 0.7578 | 0.758 |
| 0.407 | 41.61 | 6200 | 0.4997 | 0.7460 | 0.746 |
| 0.4078 | 42.95 | 6400 | 0.5021 | 0.7490 | 0.749 |
| 0.4023 | 44.3 | 6600 | 0.5054 | 0.7590 | 0.759 |
| 0.4079 | 45.64 | 6800 | 0.5091 | 0.7484 | 0.749 |
| 0.399 | 46.98 | 7000 | 0.5006 | 0.7610 | 0.761 |
| 0.4008 | 48.32 | 7200 | 0.4993 | 0.7560 | 0.756 |
| 0.3978 | 49.66 | 7400 | 0.5005 | 0.7560 | 0.756 |
| 0.3962 | 51.01 | 7600 | 0.5043 | 0.7469 | 0.747 |
| 0.391 | 52.35 | 7800 | 0.5045 | 0.7600 | 0.76 |
| 0.3931 | 53.69 | 8000 | 0.5006 | 0.7600 | 0.76 |
| 0.3885 | 55.03 | 8200 | 0.5087 | 0.7459 | 0.746 |
| 0.3941 | 56.38 | 8400 | 0.5069 | 0.7549 | 0.755 |
| 0.3884 | 57.72 | 8600 | 0.5053 | 0.7520 | 0.752 |
| 0.3872 | 59.06 | 8800 | 0.5092 | 0.7509 | 0.751 |
| 0.3869 | 60.4 | 9000 | 0.5072 | 0.7580 | 0.758 |
| 0.3861 | 61.74 | 9200 | 0.5101 | 0.7509 | 0.751 |
| 0.385 | 63.09 | 9400 | 0.5096 | 0.7520 | 0.752 |
| 0.3845 | 64.43 | 9600 | 0.5078 | 0.7560 | 0.756 |
| 0.3908 | 65.77 | 9800 | 0.5100 | 0.7509 | 0.751 |
| 0.3805 | 67.11 | 10000 | 0.5092 | 0.7560 | 0.756 |
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2 | {"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_27M", "model-index": [{"name": "GUE_tf_2-seqsight_4096_512_27M-L8_f", "results": []}]} | mahdibaghbanzadeh/GUE_tf_2-seqsight_4096_512_27M-L8_f | null | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:mahdibaghbanzadeh/seqsight_4096_512_27M",
"region:us"
]
| null | 2024-04-26T18:41:34+00:00 |
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": []} | la-min/GENI_GPT | null | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T18:41:38+00:00 |
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 lexkarlo -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 lexkarlo -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 lexkarlo
```
## 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', 0.001),
('learning_starts', 100000),
('n_timesteps', 1000000.0),
('optimize_memory_usage', False),
('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": "5.00 +/- 7.07", "name": "mean_reward", "verified": false}]}]}]} | lexkarlo/dqn-SpaceInvadersNoFrameskip-v4 | null | [
"stable-baselines3",
"SpaceInvadersNoFrameskip-v4",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
]
| null | 2024-04-26T18:42:13+00:00 |
null | peft |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# GUE_tf_2-seqsight_4096_512_27M-L32_f
This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_27M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_27M) on the [mahdibaghbanzadeh/GUE_tf_2](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_2) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4479
- F1 Score: 0.7913
- Accuracy: 0.792
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 10000
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|
| 0.561 | 1.34 | 200 | 0.5303 | 0.7216 | 0.725 |
| 0.5174 | 2.68 | 400 | 0.5201 | 0.7501 | 0.751 |
| 0.5007 | 4.03 | 600 | 0.4997 | 0.7610 | 0.761 |
| 0.4871 | 5.37 | 800 | 0.4999 | 0.7539 | 0.754 |
| 0.4803 | 6.71 | 1000 | 0.5032 | 0.7420 | 0.742 |
| 0.4673 | 8.05 | 1200 | 0.4852 | 0.7667 | 0.767 |
| 0.4599 | 9.4 | 1400 | 0.4940 | 0.7529 | 0.753 |
| 0.4525 | 10.74 | 1600 | 0.4904 | 0.7490 | 0.749 |
| 0.4428 | 12.08 | 1800 | 0.4907 | 0.7529 | 0.753 |
| 0.4329 | 13.42 | 2000 | 0.4937 | 0.7527 | 0.753 |
| 0.426 | 14.77 | 2200 | 0.4967 | 0.7477 | 0.749 |
| 0.4137 | 16.11 | 2400 | 0.5107 | 0.7390 | 0.739 |
| 0.4084 | 17.45 | 2600 | 0.4973 | 0.7582 | 0.759 |
| 0.3989 | 18.79 | 2800 | 0.5102 | 0.7359 | 0.736 |
| 0.3863 | 20.13 | 3000 | 0.5156 | 0.7516 | 0.752 |
| 0.3817 | 21.48 | 3200 | 0.5158 | 0.7446 | 0.745 |
| 0.3705 | 22.82 | 3400 | 0.5132 | 0.7438 | 0.744 |
| 0.3643 | 24.16 | 3600 | 0.5233 | 0.7488 | 0.749 |
| 0.3526 | 25.5 | 3800 | 0.5269 | 0.7545 | 0.755 |
| 0.3515 | 26.85 | 4000 | 0.5271 | 0.7639 | 0.764 |
| 0.3426 | 28.19 | 4200 | 0.5628 | 0.7408 | 0.742 |
| 0.3305 | 29.53 | 4400 | 0.5738 | 0.7535 | 0.754 |
| 0.3265 | 30.87 | 4600 | 0.5591 | 0.7566 | 0.757 |
| 0.3221 | 32.21 | 4800 | 0.5647 | 0.7509 | 0.751 |
| 0.3149 | 33.56 | 5000 | 0.5816 | 0.7548 | 0.755 |
| 0.3075 | 34.9 | 5200 | 0.6102 | 0.7530 | 0.754 |
| 0.2991 | 36.24 | 5400 | 0.5645 | 0.7539 | 0.754 |
| 0.2929 | 37.58 | 5600 | 0.6136 | 0.7517 | 0.752 |
| 0.2917 | 38.93 | 5800 | 0.5835 | 0.7640 | 0.764 |
| 0.2858 | 40.27 | 6000 | 0.5987 | 0.7610 | 0.761 |
| 0.2842 | 41.61 | 6200 | 0.5826 | 0.7560 | 0.756 |
| 0.2688 | 42.95 | 6400 | 0.6329 | 0.7497 | 0.75 |
| 0.2669 | 44.3 | 6600 | 0.6385 | 0.7535 | 0.754 |
| 0.2722 | 45.64 | 6800 | 0.6404 | 0.7554 | 0.756 |
| 0.2603 | 46.98 | 7000 | 0.6424 | 0.7568 | 0.757 |
| 0.2593 | 48.32 | 7200 | 0.6285 | 0.7560 | 0.756 |
| 0.2535 | 49.66 | 7400 | 0.6507 | 0.7579 | 0.758 |
| 0.2545 | 51.01 | 7600 | 0.6478 | 0.7658 | 0.766 |
| 0.2445 | 52.35 | 7800 | 0.6550 | 0.7639 | 0.764 |
| 0.2448 | 53.69 | 8000 | 0.6592 | 0.7559 | 0.756 |
| 0.2394 | 55.03 | 8200 | 0.6715 | 0.7565 | 0.757 |
| 0.2388 | 56.38 | 8400 | 0.6830 | 0.7525 | 0.753 |
| 0.2339 | 57.72 | 8600 | 0.6734 | 0.7589 | 0.759 |
| 0.23 | 59.06 | 8800 | 0.6875 | 0.7586 | 0.759 |
| 0.2281 | 60.4 | 9000 | 0.6870 | 0.7619 | 0.762 |
| 0.2344 | 61.74 | 9200 | 0.6932 | 0.7596 | 0.76 |
| 0.2283 | 63.09 | 9400 | 0.7059 | 0.7576 | 0.758 |
| 0.2272 | 64.43 | 9600 | 0.6976 | 0.7537 | 0.754 |
| 0.226 | 65.77 | 9800 | 0.7031 | 0.7526 | 0.753 |
| 0.2232 | 67.11 | 10000 | 0.7025 | 0.7516 | 0.752 |
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2 | {"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_27M", "model-index": [{"name": "GUE_tf_2-seqsight_4096_512_27M-L32_f", "results": []}]} | mahdibaghbanzadeh/GUE_tf_2-seqsight_4096_512_27M-L32_f | null | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:mahdibaghbanzadeh/seqsight_4096_512_27M",
"region:us"
]
| null | 2024-04-26T18:42:18+00:00 |
text-generation | transformers | {} | Manavshah/llama-test | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-26T18:42:47+00:00 |
|
null | null |
# Model Card for NeuralTranslate
<!-- Provide a quick summary of what the model is/does. -->
THIS MODEL USES CHATML TEMPLATE!! BE CAREFUL OR YOU MIGHT FIND UNEXPECTED BEHAVIOURS.
This is the second alpha version of NeuralTranslate. This alpha version doesn't contain overfitting (or at least that's what I think), so no unexpected behaviour should happen and Mistral's native reasoning capabilities aren't lost.
NeuralTranslate is an open-source family of models for bidirectional translation between English & Spanish, achieving high accuracy at fast speed.
You can donate towards this project at my ko-fi! https://ko-fi.com/irvingernesto
## 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] | {"language": ["en", "es"], "license": "mit", "tags": ["Translation", "Mistral", "English", "Spanish"], "datasets": ["Thermostatic/ShareGPT_NeuralTranslate_v0.1"]} | Thermostatic/NeuralTranslate_v0.2_GGUF | null | [
"gguf",
"Translation",
"Mistral",
"English",
"Spanish",
"en",
"es",
"dataset:Thermostatic/ShareGPT_NeuralTranslate_v0.1",
"arxiv:1910.09700",
"license:mit",
"region:us"
]
| null | 2024-04-26T18:42:53+00:00 |
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": []} | OwOOwO/final5 | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T18:43:01+00:00 |
text2text-generation | transformers | {} | Alefiah/UrduSum5k_multi1 | null | [
"transformers",
"pytorch",
"tensorboard",
"mt5",
"text2text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-26T18:44:03+00:00 |
|
null | peft |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# GUE_virus_covid-seqsight_4096_512_27M-L1_f
This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_27M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_27M) on the [mahdibaghbanzadeh/GUE_virus_covid](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_virus_covid) dataset.
It achieves the following results on the evaluation set:
- Loss: 1.6408
- F1 Score: 0.3935
- Accuracy: 0.3923
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 10000
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|
| 2.1836 | 0.35 | 200 | 2.1801 | 0.1012 | 0.1378 |
| 2.1775 | 0.7 | 400 | 2.1750 | 0.1074 | 0.1424 |
| 2.1694 | 1.05 | 600 | 2.1638 | 0.1367 | 0.1544 |
| 2.1606 | 1.4 | 800 | 2.1520 | 0.1337 | 0.1636 |
| 2.1496 | 1.75 | 1000 | 2.1364 | 0.1456 | 0.1713 |
| 2.1386 | 2.09 | 1200 | 2.1181 | 0.1589 | 0.1892 |
| 2.096 | 2.44 | 1400 | 2.0564 | 0.1944 | 0.2187 |
| 2.053 | 2.79 | 1600 | 1.9972 | 0.2292 | 0.2415 |
| 2.0123 | 3.14 | 1800 | 1.9539 | 0.2492 | 0.2612 |
| 1.9777 | 3.49 | 2000 | 1.9342 | 0.2634 | 0.2715 |
| 1.9685 | 3.84 | 2200 | 1.9020 | 0.2832 | 0.2866 |
| 1.9459 | 4.19 | 2400 | 1.8857 | 0.2898 | 0.2910 |
| 1.9202 | 4.54 | 2600 | 1.8480 | 0.3161 | 0.3203 |
| 1.9067 | 4.89 | 2800 | 1.8296 | 0.3132 | 0.3211 |
| 1.895 | 5.24 | 3000 | 1.8076 | 0.3192 | 0.3271 |
| 1.8707 | 5.58 | 3200 | 1.7859 | 0.3260 | 0.3338 |
| 1.8555 | 5.93 | 3400 | 1.7753 | 0.3308 | 0.3376 |
| 1.8492 | 6.28 | 3600 | 1.7598 | 0.3484 | 0.3480 |
| 1.8295 | 6.63 | 3800 | 1.7447 | 0.3328 | 0.3415 |
| 1.8239 | 6.98 | 4000 | 1.7393 | 0.3497 | 0.3516 |
| 1.821 | 7.33 | 4200 | 1.7290 | 0.3469 | 0.3503 |
| 1.81 | 7.68 | 4400 | 1.7146 | 0.3575 | 0.3562 |
| 1.8089 | 8.03 | 4600 | 1.7228 | 0.3579 | 0.3592 |
| 1.7879 | 8.38 | 4800 | 1.7043 | 0.3604 | 0.3623 |
| 1.795 | 8.73 | 5000 | 1.6983 | 0.3573 | 0.3636 |
| 1.7821 | 9.08 | 5200 | 1.6976 | 0.3726 | 0.3689 |
| 1.7854 | 9.42 | 5400 | 1.6917 | 0.3656 | 0.3701 |
| 1.7726 | 9.77 | 5600 | 1.6856 | 0.3660 | 0.3676 |
| 1.7711 | 10.12 | 5800 | 1.6805 | 0.3699 | 0.3670 |
| 1.7696 | 10.47 | 6000 | 1.6773 | 0.3752 | 0.3757 |
| 1.7641 | 10.82 | 6200 | 1.6848 | 0.3668 | 0.3682 |
| 1.7465 | 11.17 | 6400 | 1.6756 | 0.3742 | 0.3725 |
| 1.7533 | 11.52 | 6600 | 1.6664 | 0.3769 | 0.3782 |
| 1.7562 | 11.87 | 6800 | 1.6659 | 0.3765 | 0.3781 |
| 1.7506 | 12.22 | 7000 | 1.6653 | 0.3784 | 0.3790 |
| 1.7405 | 12.57 | 7200 | 1.6553 | 0.3828 | 0.3832 |
| 1.7489 | 12.91 | 7400 | 1.6570 | 0.3801 | 0.3836 |
| 1.7493 | 13.26 | 7600 | 1.6567 | 0.3734 | 0.3750 |
| 1.7369 | 13.61 | 7800 | 1.6556 | 0.3779 | 0.3794 |
| 1.7418 | 13.96 | 8000 | 1.6530 | 0.3861 | 0.3845 |
| 1.7367 | 14.31 | 8200 | 1.6469 | 0.3824 | 0.3839 |
| 1.7353 | 14.66 | 8400 | 1.6450 | 0.3858 | 0.3844 |
| 1.735 | 15.01 | 8600 | 1.6534 | 0.3769 | 0.3762 |
| 1.734 | 15.36 | 8800 | 1.6470 | 0.3892 | 0.3886 |
| 1.728 | 15.71 | 9000 | 1.6452 | 0.3856 | 0.3869 |
| 1.7274 | 16.06 | 9200 | 1.6431 | 0.3872 | 0.3875 |
| 1.7287 | 16.4 | 9400 | 1.6429 | 0.3866 | 0.3860 |
| 1.7292 | 16.75 | 9600 | 1.6443 | 0.3865 | 0.3864 |
| 1.731 | 17.1 | 9800 | 1.6426 | 0.3873 | 0.3884 |
| 1.7392 | 17.45 | 10000 | 1.6425 | 0.3868 | 0.3875 |
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2 | {"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_27M", "model-index": [{"name": "GUE_virus_covid-seqsight_4096_512_27M-L1_f", "results": []}]} | mahdibaghbanzadeh/GUE_virus_covid-seqsight_4096_512_27M-L1_f | null | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:mahdibaghbanzadeh/seqsight_4096_512_27M",
"region:us"
]
| null | 2024-04-26T18:44:31+00:00 |
null | null | {"license": "mit"} | FrankJobs/HelloWorld | null | [
"license:mit",
"region:us"
]
| null | 2024-04-26T18:46:16+00:00 |
|
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": []} | akankshya107/llava_dpt_2 | null | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T18:46:29+00:00 |
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. -->
# gemma2b-dolly15k-r128
This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) 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: 5e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 1
### Training results
### Framework versions
- PEFT 0.10.0
- Transformers 4.40.1
- Pytorch 2.1.2
- Datasets 2.19.0
- Tokenizers 0.19.1 | {"license": "gemma", "library_name": "peft", "tags": ["trl", "sft", "generated_from_trainer"], "base_model": "google/gemma-2b", "model-index": [{"name": "gemma2b-dolly15k-r128", "results": []}]} | AlexxxSem/gemma2b-dolly15k-r128 | null | [
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:google/gemma-2b",
"license:gemma",
"region:us"
]
| null | 2024-04-26T18:47:09+00:00 |
null | null | {"language": ["en"], "license": "mit"} | mary722/risehomesholding | null | [
"en",
"license:mit",
"region:us"
]
| null | 2024-04-26T18:47:20+00:00 |
|
null | transformers | ## About
<!-- ### quantize_version: 1 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/n00854180t/ErisMaidFlame-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/ErisMaidFlame-7B-GGUF/resolve/main/ErisMaidFlame-7B.Q2_K.gguf) | Q2_K | 2.8 | |
| [GGUF](https://huggingface.co/mradermacher/ErisMaidFlame-7B-GGUF/resolve/main/ErisMaidFlame-7B.IQ3_XS.gguf) | IQ3_XS | 3.1 | |
| [GGUF](https://huggingface.co/mradermacher/ErisMaidFlame-7B-GGUF/resolve/main/ErisMaidFlame-7B.Q3_K_S.gguf) | Q3_K_S | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/ErisMaidFlame-7B-GGUF/resolve/main/ErisMaidFlame-7B.IQ3_S.gguf) | IQ3_S | 3.3 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/ErisMaidFlame-7B-GGUF/resolve/main/ErisMaidFlame-7B.IQ3_M.gguf) | IQ3_M | 3.4 | |
| [GGUF](https://huggingface.co/mradermacher/ErisMaidFlame-7B-GGUF/resolve/main/ErisMaidFlame-7B.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/ErisMaidFlame-7B-GGUF/resolve/main/ErisMaidFlame-7B.Q3_K_L.gguf) | Q3_K_L | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/ErisMaidFlame-7B-GGUF/resolve/main/ErisMaidFlame-7B.IQ4_XS.gguf) | IQ4_XS | 4.0 | |
| [GGUF](https://huggingface.co/mradermacher/ErisMaidFlame-7B-GGUF/resolve/main/ErisMaidFlame-7B.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/ErisMaidFlame-7B-GGUF/resolve/main/ErisMaidFlame-7B.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/ErisMaidFlame-7B-GGUF/resolve/main/ErisMaidFlame-7B.Q5_K_S.gguf) | Q5_K_S | 5.1 | |
| [GGUF](https://huggingface.co/mradermacher/ErisMaidFlame-7B-GGUF/resolve/main/ErisMaidFlame-7B.Q5_K_M.gguf) | Q5_K_M | 5.2 | |
| [GGUF](https://huggingface.co/mradermacher/ErisMaidFlame-7B-GGUF/resolve/main/ErisMaidFlame-7B.Q6_K.gguf) | Q6_K | 6.0 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/ErisMaidFlame-7B-GGUF/resolve/main/ErisMaidFlame-7B.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/ErisMaidFlame-7B-GGUF/resolve/main/ErisMaidFlame-7B.f16.gguf) | f16 | 14.6 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
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"], "library_name": "transformers", "tags": ["mergekit", "merge"], "base_model": "n00854180t/ErisMaidFlame-7B", "quantized_by": "mradermacher"} | mradermacher/ErisMaidFlame-7B-GGUF | null | [
"transformers",
"gguf",
"mergekit",
"merge",
"en",
"base_model:n00854180t/ErisMaidFlame-7B",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T18:48:03+00:00 |
text-generation | transformers |
# Qwen1.5-110B-Chat
## About Quantization
我们使用modelscope [swift](https://github.com/modelscope/swift/)仓库进行GPTQ量化. 量化文档可以查看[这里](https://github.com/modelscope/swift/blob/main/docs/source/LLM/LLM%E9%87%8F%E5%8C%96%E6%96%87%E6%A1%A3.md). 量化命令如下:
We use the modelscope [swift](https://github.com/modelscope/swift/) repository to perform GPTQ quantization. Quantization documentation can be found [here](https://github.com/modelscope/swift/blob/main/docs/source_en/LLM/LLM-quantization.md). The quantization command is as follows:
```bash
OMP_NUM_THREADS=14 CUDA_VISIBLE_DEVICES=0 swift export \
--model_type qwen1half-110b-chat --quant_bits 4 \
--dataset sharegpt-gpt4-mini alpaca-zh alpaca-en \
--quant_method gptq --quant_seqlen 8192
```
## Introduction
Qwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data. In comparison with the previous released Qwen, the improvements include:
* 9 model sizes, including 0.5B, 1.8B, 4B, 7B, 14B, 32B, 72B, and 110B dense models, and an MoE model of 14B with 2.7B activated;
* Significant performance improvement in human preference for chat models;
* Multilingual support of both base and chat models;
* Stable support of 32K context length for models of all sizes
* No need of `trust_remote_code`.
For more details, please refer to our [blog post](https://qwenlm.github.io/blog/qwen1.5/) and [GitHub repo](https://github.com/QwenLM/Qwen1.5).
<br>
## Model Details
Qwen1.5 is a language model series including decoder language models of different model sizes. For each size, we release the base language model and the aligned chat model. It is based on the Transformer architecture with SwiGLU activation, attention QKV bias, group query attention, mixture of sliding window attention and full attention, etc. Additionally, we have an improved tokenizer adaptive to multiple natural languages and codes. For the beta version, temporarily we did not include GQA (except for 32B and 110B) and the mixture of SWA and full attention.
## Training details
We pretrained the models with a large amount of data, and we post-trained the models with both supervised finetuning and direct preference optimization.
## Requirements
The code of Qwen1.5 has been in the latest Hugging face transformers and we advise you to install `transformers>=4.37.0`, or you might encounter the following error:
```
KeyError: 'qwen2'
```
## Quickstart
Here provides a code snippet with `apply_chat_template` to show you how to load the tokenizer and model and how to generate contents.
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model onto
model = AutoModelForCausalLM.from_pretrained(
"study-hjt/Qwen1.5-110B-Chat-GPTQ-Int4",
torch_dtype="auto",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("study-hjt/Qwen1.5-110B-Chat-GPTQ-Int4")
prompt = "Give me a short introduction to large language model."
messages = [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(device)
generated_ids = model.generate(
model_inputs.input_ids,
max_new_tokens=512
)
generated_ids = [
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
```
## Tips
* If you encounter code switching or other bad cases, we advise you to use our provided hyper-parameters in `generation_config.json`.
## Citation
If you find our work helpful, feel free to give us a cite.
```
@article{qwen,
title={Qwen Technical Report},
author={Jinze Bai and Shuai Bai and Yunfei Chu and Zeyu Cui and Kai Dang and Xiaodong Deng and Yang Fan and Wenbin Ge and Yu Han and Fei Huang and Binyuan Hui and Luo Ji and Mei Li and Junyang Lin and Runji Lin and Dayiheng Liu and Gao Liu and Chengqiang Lu and Keming Lu and Jianxin Ma and Rui Men and Xingzhang Ren and Xuancheng Ren and Chuanqi Tan and Sinan Tan and Jianhong Tu and Peng Wang and Shijie Wang and Wei Wang and Shengguang Wu and Benfeng Xu and Jin Xu and An Yang and Hao Yang and Jian Yang and Shusheng Yang and Yang Yao and Bowen Yu and Hongyi Yuan and Zheng Yuan and Jianwei Zhang and Xingxuan Zhang and Yichang Zhang and Zhenru Zhang and Chang Zhou and Jingren Zhou and Xiaohuan Zhou and Tianhang Zhu},
journal={arXiv preprint arXiv:2309.16609},
year={2023}
}
```
| {"language": ["en"], "license": "other", "tags": ["chat", "qwen", "gptq", "int4", "4bits", "110b"], "license_name": "tongyi-qianwen", "license_link": "https://huggingface.co/Qwen/Qwen1.5-110B-Chat/blob/main/LICENSE", "pipeline_tag": "text-generation"} | study-hjt/Qwen1.5-110B-Chat-GPTQ-Int4 | null | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"chat",
"qwen",
"gptq",
"int4",
"4bits",
"110b",
"conversational",
"en",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"4-bit",
"region:us"
]
| null | 2024-04-26T18:50:09+00:00 |
text-generation | transformers |
# 🚀 Skyro-4X8B
Skyro-4X8B is a Mixure of Experts (MoE) made with the following models using [Mergekit](https://github.com/arcee-ai/mergekit):
* [abacusai/Llama-3-Smaug-8B](https://huggingface.co/abacusai/Llama-3-Smaug-8B)
* [cognitivecomputations/dolphin-2.9-llama3-8b](https://huggingface.co/cognitivecomputations/dolphin-2.9-llama3-8b)
* [Weyaxi/Einstein-v6.1-Llama3-8B](https://huggingface.co/Weyaxi/Einstein-v6.1-Llama3-8B)
* [dreamgen-preview/opus-v1.2-llama-3-8b-base-run3.4-epoch2](https://huggingface.co/dreamgen-preview/opus-v1.2-llama-3-8b-base-run3.4-epoch2)
## 🧩 Configuration
```yamlname: "Skyro-4X8B"
base_model: meta-llama/Meta-Llama-3-8B
gate_mode: hidden
experts:
- source_model: abacusai/Llama-3-Smaug-8B
positive_prompts:
- "chat"
- "assistant"
- "tell me"
- "explain"
- "I want"
- source_model: cognitivecomputations/dolphin-2.9-llama3-8b
positive_prompts:
- "math"
- "mathematics"
- "code"
- "engineering"
- "solve"
- "logic"
- "rationality"
- "puzzle"
- "solve"
- source_model: Weyaxi/Einstein-v6.1-Llama3-8B
positive_prompts:
- "science"
- "medical"
- "physics"
- "engineering"
- "math"
- "logic"
- "rationality"
- "mathematics"
- "solve"
- source_model: dreamgen-preview/opus-v1.2-llama-3-8b-base-run3.4-epoch2
positive_prompts:
- "story"
- "roleplay"
- "role-play"
- "storywriting"
- "character"
- "narrative"
- "creative"
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "saucam/Skyro-4X8B"
messages = [{"role": "user", "content": "In a student council election, candidate A got 20% of the votes while candidate B got 50% more than candidate A's votes. The rest of the votes was given to candidate C. If there were 100 voters, how many votes did candidate C get?"}]
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"])
```
## Sample output
```
config.json: 100%|██████████████████████████████████████████████████████████████| 878/878 [00:00<00:00, 4.18MB/s]
model.safetensors.index.json: 100%|██████████████████████████████████████████| 53.5k/53.5k [00:00<00:00, 101MB/s]
model-00001-of-00006.safetensors: 100%|█████████████████████████████████████| 9.89G/9.89G [03:47<00:00, 43.4MB/s]
model-00002-of-00006.safetensors: 100%|█████████████████████████████████████| 9.98G/9.98G [03:23<00:00, 49.0MB/s]
model-00003-of-00006.safetensors: 100%|█████████████████████████████████████| 9.98G/9.98G [03:44<00:00, 44.5MB/s]
model-00004-of-00006.safetensors: 100%|█████████████████████████████████████| 9.90G/9.90G [03:30<00:00, 46.9MB/s]
model-00005-of-00006.safetensors: 100%|█████████████████████████████████████| 9.08G/9.08G [03:08<00:00, 48.1MB/s]
model-00006-of-00006.safetensors: 100%|█████████████████████████████████████| 1.05G/1.05G [00:20<00:00, 51.3MB/s]
Downloading shards: 100%|█████████████████████████████████████████████████████████| 6/6 [17:58<00:00, 179.78s/it]
Loading checkpoint shards: 100%|███████████████████████████████████████████████████| 6/6 [01:27<00:00, 14.59s/it]
WARNING:root:Some parameters are on the meta device device because they were offloaded to the cpu.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
<|im_start|>user
In a student council election, candidate A got 20% of the votes while candidate B got 50% more than candidate A's votes. The rest of the votes was given to candidate C. If there were 100 voters, how many votes did candidate C get?<|im_end|>
<|im_start|>assistant
Let's denote the number of votes candidate A got as \( A \).
Candidate B got 50% more votes than candidate A, so candidate B got \( A + 0.5A = 1.5A \) votes.
Candidate C got the rest of the votes, which means \( C = 100 - (A + 1.5A) \).
We know that candidate A got 20% of the votes, so \( A = 20\% \times 100 = 20 \).
Now we can calculate candidate C's votes:
\( C = 100 - (20 + 1.5 \times 20) \)
\( C = 100 - (20 + 30) \)
\( C = 100 - 50 \)
\( C = 50 \).
Therefore, candidate C got 50 votes.<|im_end|>
``` | {"license": "apache-2.0", "tags": ["merge", "mergekit", "moe", "frankenmoe", "abacusai/Llama-3-Smaug-8B", "cognitivecomputations/dolphin-2.9-llama3-8b", "Weyaxi/Einstein-v6.1-Llama3-8B", "dreamgen-preview/opus-v1.2-llama-3-8b-base-run3.4-epoch2"], "base_model": ["abacusai/Llama-3-Smaug-8B", "cognitivecomputations/dolphin-2.9-llama3-8b", "Weyaxi/Einstein-v6.1-Llama3-8B", "dreamgen-preview/opus-v1.2-llama-3-8b-base-run3.4-epoch2"]} | saucam/Skyro-4X8B | null | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"merge",
"mergekit",
"moe",
"frankenmoe",
"abacusai/Llama-3-Smaug-8B",
"cognitivecomputations/dolphin-2.9-llama3-8b",
"Weyaxi/Einstein-v6.1-Llama3-8B",
"dreamgen-preview/opus-v1.2-llama-3-8b-base-run3.4-epoch2",
"base_model:abacusai/Llama-3-Smaug-8B",
"base_model:cognitivecomputations/dolphin-2.9-llama3-8b",
"base_model:Weyaxi/Einstein-v6.1-Llama3-8B",
"base_model:dreamgen-preview/opus-v1.2-llama-3-8b-base-run3.4-epoch2",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-26T18:50:44+00:00 |
null | peft |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# GUE_virus_covid-seqsight_4096_512_27M-L8_f
This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_27M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_27M) on the [mahdibaghbanzadeh/GUE_virus_covid](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_virus_covid) dataset.
It achieves the following results on the evaluation set:
- Loss: 1.3185
- F1 Score: 0.5124
- Accuracy: 0.5135
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 10000
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|
| 2.1834 | 0.35 | 200 | 2.1781 | 0.1086 | 0.1444 |
| 2.1731 | 0.7 | 400 | 2.1615 | 0.1333 | 0.1538 |
| 2.1353 | 1.05 | 600 | 2.0731 | 0.1947 | 0.2125 |
| 2.024 | 1.4 | 800 | 1.9362 | 0.2448 | 0.2606 |
| 1.9338 | 1.75 | 1000 | 1.8595 | 0.2832 | 0.2943 |
| 1.8801 | 2.09 | 1200 | 1.8183 | 0.2838 | 0.2947 |
| 1.8369 | 2.44 | 1400 | 1.7762 | 0.3213 | 0.3235 |
| 1.811 | 2.79 | 1600 | 1.7453 | 0.3250 | 0.3350 |
| 1.786 | 3.14 | 1800 | 1.7145 | 0.3351 | 0.3488 |
| 1.7538 | 3.49 | 2000 | 1.6934 | 0.3572 | 0.3609 |
| 1.7384 | 3.84 | 2200 | 1.6635 | 0.3728 | 0.3745 |
| 1.7123 | 4.19 | 2400 | 1.6323 | 0.3804 | 0.3762 |
| 1.691 | 4.54 | 2600 | 1.6020 | 0.4020 | 0.4028 |
| 1.6755 | 4.89 | 2800 | 1.5920 | 0.3971 | 0.4031 |
| 1.6551 | 5.24 | 3000 | 1.5867 | 0.3965 | 0.4013 |
| 1.642 | 5.58 | 3200 | 1.5574 | 0.4079 | 0.4132 |
| 1.6213 | 5.93 | 3400 | 1.5510 | 0.4124 | 0.4164 |
| 1.6003 | 6.28 | 3600 | 1.5192 | 0.4284 | 0.4266 |
| 1.5856 | 6.63 | 3800 | 1.5036 | 0.4306 | 0.4354 |
| 1.5796 | 6.98 | 4000 | 1.4930 | 0.4379 | 0.4411 |
| 1.5685 | 7.33 | 4200 | 1.4882 | 0.4287 | 0.4321 |
| 1.5537 | 7.68 | 4400 | 1.4775 | 0.4574 | 0.4527 |
| 1.5513 | 8.03 | 4600 | 1.4724 | 0.4492 | 0.4440 |
| 1.5256 | 8.38 | 4800 | 1.4608 | 0.4543 | 0.4570 |
| 1.5354 | 8.73 | 5000 | 1.4586 | 0.4492 | 0.4493 |
| 1.5262 | 9.08 | 5200 | 1.4459 | 0.4626 | 0.4560 |
| 1.5207 | 9.42 | 5400 | 1.4296 | 0.4551 | 0.4604 |
| 1.5066 | 9.77 | 5600 | 1.4210 | 0.4742 | 0.4774 |
| 1.4961 | 10.12 | 5800 | 1.4062 | 0.4828 | 0.4813 |
| 1.4961 | 10.47 | 6000 | 1.4098 | 0.4694 | 0.4676 |
| 1.4884 | 10.82 | 6200 | 1.4066 | 0.4776 | 0.4727 |
| 1.4635 | 11.17 | 6400 | 1.3975 | 0.4780 | 0.4719 |
| 1.4665 | 11.52 | 6600 | 1.3895 | 0.4832 | 0.4818 |
| 1.4694 | 11.87 | 6800 | 1.3816 | 0.4849 | 0.4841 |
| 1.4622 | 12.22 | 7000 | 1.3683 | 0.4941 | 0.4926 |
| 1.4479 | 12.57 | 7200 | 1.3618 | 0.4960 | 0.4964 |
| 1.4531 | 12.91 | 7400 | 1.3743 | 0.4776 | 0.4758 |
| 1.4458 | 13.26 | 7600 | 1.3586 | 0.4894 | 0.4867 |
| 1.4372 | 13.61 | 7800 | 1.3465 | 0.5028 | 0.5003 |
| 1.4371 | 13.96 | 8000 | 1.3417 | 0.5018 | 0.4993 |
| 1.4273 | 14.31 | 8200 | 1.3355 | 0.5006 | 0.5004 |
| 1.4283 | 14.66 | 8400 | 1.3304 | 0.5075 | 0.5068 |
| 1.4252 | 15.01 | 8600 | 1.3305 | 0.4997 | 0.4992 |
| 1.4274 | 15.36 | 8800 | 1.3245 | 0.5131 | 0.5141 |
| 1.4087 | 15.71 | 9000 | 1.3223 | 0.5050 | 0.5057 |
| 1.4206 | 16.06 | 9200 | 1.3228 | 0.5083 | 0.5094 |
| 1.4169 | 16.4 | 9400 | 1.3173 | 0.5109 | 0.5107 |
| 1.4144 | 16.75 | 9600 | 1.3192 | 0.5091 | 0.5089 |
| 1.413 | 17.1 | 9800 | 1.3183 | 0.5093 | 0.5089 |
| 1.4152 | 17.45 | 10000 | 1.3175 | 0.5089 | 0.5091 |
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2 | {"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_27M", "model-index": [{"name": "GUE_virus_covid-seqsight_4096_512_27M-L8_f", "results": []}]} | mahdibaghbanzadeh/GUE_virus_covid-seqsight_4096_512_27M-L8_f | null | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:mahdibaghbanzadeh/seqsight_4096_512_27M",
"region:us"
]
| null | 2024-04-26T18:50:52+00:00 |
null | peft |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# GUE_virus_covid-seqsight_4096_512_27M-L32_f
This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_27M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_27M) on the [mahdibaghbanzadeh/GUE_virus_covid](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_virus_covid) dataset.
It achieves the following results on the evaluation set:
- Loss: 1.0120
- F1 Score: 0.6191
- Accuracy: 0.6177
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 10000
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|
| 2.1827 | 0.35 | 200 | 2.1753 | 0.1045 | 0.1416 |
| 2.158 | 0.7 | 400 | 2.1172 | 0.1515 | 0.1741 |
| 2.0492 | 1.05 | 600 | 1.9241 | 0.2587 | 0.2731 |
| 1.8951 | 1.4 | 800 | 1.7714 | 0.3051 | 0.3216 |
| 1.7958 | 1.75 | 1000 | 1.6972 | 0.3392 | 0.3521 |
| 1.7331 | 2.09 | 1200 | 1.6434 | 0.3726 | 0.3756 |
| 1.6821 | 2.44 | 1400 | 1.5883 | 0.4134 | 0.4106 |
| 1.6409 | 2.79 | 1600 | 1.5465 | 0.4131 | 0.4173 |
| 1.602 | 3.14 | 1800 | 1.4926 | 0.4368 | 0.4385 |
| 1.549 | 3.49 | 2000 | 1.4476 | 0.4567 | 0.4547 |
| 1.5185 | 3.84 | 2200 | 1.4019 | 0.4702 | 0.4683 |
| 1.4783 | 4.19 | 2400 | 1.3771 | 0.4727 | 0.4748 |
| 1.446 | 4.54 | 2600 | 1.3363 | 0.5033 | 0.4993 |
| 1.4218 | 4.89 | 2800 | 1.3102 | 0.5022 | 0.5048 |
| 1.3959 | 5.24 | 3000 | 1.2904 | 0.5073 | 0.5080 |
| 1.3767 | 5.58 | 3200 | 1.2590 | 0.5281 | 0.5289 |
| 1.3509 | 5.93 | 3400 | 1.2441 | 0.5282 | 0.5298 |
| 1.3307 | 6.28 | 3600 | 1.2205 | 0.5507 | 0.5444 |
| 1.3083 | 6.63 | 3800 | 1.2043 | 0.5459 | 0.5458 |
| 1.2958 | 6.98 | 4000 | 1.1911 | 0.5510 | 0.5528 |
| 1.2813 | 7.33 | 4200 | 1.1746 | 0.5579 | 0.5533 |
| 1.2675 | 7.68 | 4400 | 1.1639 | 0.5642 | 0.5581 |
| 1.2675 | 8.03 | 4600 | 1.1520 | 0.5727 | 0.5662 |
| 1.2386 | 8.38 | 4800 | 1.1379 | 0.5739 | 0.5739 |
| 1.2367 | 8.73 | 5000 | 1.1300 | 0.5737 | 0.5738 |
| 1.2246 | 9.08 | 5200 | 1.1243 | 0.5801 | 0.5740 |
| 1.2171 | 9.42 | 5400 | 1.1111 | 0.5855 | 0.5840 |
| 1.1994 | 9.77 | 5600 | 1.0961 | 0.5902 | 0.5904 |
| 1.2003 | 10.12 | 5800 | 1.0891 | 0.5968 | 0.5928 |
| 1.1939 | 10.47 | 6000 | 1.0839 | 0.5913 | 0.5894 |
| 1.181 | 10.82 | 6200 | 1.0851 | 0.6012 | 0.5956 |
| 1.1578 | 11.17 | 6400 | 1.0812 | 0.6022 | 0.5962 |
| 1.1652 | 11.52 | 6600 | 1.0678 | 0.6034 | 0.5974 |
| 1.1598 | 11.87 | 6800 | 1.0676 | 0.6013 | 0.5985 |
| 1.1578 | 12.22 | 7000 | 1.0575 | 0.6036 | 0.6023 |
| 1.1337 | 12.57 | 7200 | 1.0504 | 0.6025 | 0.6019 |
| 1.1473 | 12.91 | 7400 | 1.0558 | 0.6088 | 0.6026 |
| 1.1301 | 13.26 | 7600 | 1.0484 | 0.6067 | 0.6021 |
| 1.1321 | 13.61 | 7800 | 1.0413 | 0.6118 | 0.6074 |
| 1.1257 | 13.96 | 8000 | 1.0381 | 0.6132 | 0.6094 |
| 1.1181 | 14.31 | 8200 | 1.0339 | 0.6187 | 0.6152 |
| 1.1194 | 14.66 | 8400 | 1.0298 | 0.6141 | 0.6102 |
| 1.1185 | 15.01 | 8600 | 1.0319 | 0.6144 | 0.6119 |
| 1.119 | 15.36 | 8800 | 1.0270 | 0.6147 | 0.6137 |
| 1.1 | 15.71 | 9000 | 1.0249 | 0.6169 | 0.6159 |
| 1.1153 | 16.06 | 9200 | 1.0255 | 0.6196 | 0.6167 |
| 1.1058 | 16.4 | 9400 | 1.0249 | 0.6173 | 0.6158 |
| 1.106 | 16.75 | 9600 | 1.0249 | 0.6173 | 0.6139 |
| 1.1128 | 17.1 | 9800 | 1.0233 | 0.6178 | 0.6158 |
| 1.1099 | 17.45 | 10000 | 1.0238 | 0.6184 | 0.6162 |
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2 | {"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_27M", "model-index": [{"name": "GUE_virus_covid-seqsight_4096_512_27M-L32_f", "results": []}]} | mahdibaghbanzadeh/GUE_virus_covid-seqsight_4096_512_27M-L32_f | null | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:mahdibaghbanzadeh/seqsight_4096_512_27M",
"region:us"
]
| null | 2024-04-26T18:51:05+00:00 |
null | null | {} | Ilkinism/test_bart | null | [
"region:us"
]
| null | 2024-04-26T18:51:11+00:00 |
|
null | peft |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# GUE_prom_prom_300_tata-seqsight_4096_512_46M-L1_f
This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_prom_prom_300_tata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_300_tata) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5219
- F1 Score: 0.8056
- Accuracy: 0.8059
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 10000
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy |
|:-------------:|:------:|:-----:|:---------------:|:--------:|:--------:|
| 0.5687 | 5.13 | 200 | 0.5025 | 0.7669 | 0.7667 |
| 0.4527 | 10.26 | 400 | 0.5102 | 0.7715 | 0.7732 |
| 0.4213 | 15.38 | 600 | 0.4610 | 0.7962 | 0.7961 |
| 0.3989 | 20.51 | 800 | 0.4824 | 0.8002 | 0.8010 |
| 0.3836 | 25.64 | 1000 | 0.4858 | 0.7989 | 0.7993 |
| 0.3695 | 30.77 | 1200 | 0.4774 | 0.8025 | 0.8026 |
| 0.3542 | 35.9 | 1400 | 0.4916 | 0.8023 | 0.8026 |
| 0.3422 | 41.03 | 1600 | 0.4509 | 0.8076 | 0.8075 |
| 0.3324 | 46.15 | 1800 | 0.4803 | 0.8155 | 0.8157 |
| 0.3172 | 51.28 | 2000 | 0.4699 | 0.8140 | 0.8140 |
| 0.3116 | 56.41 | 2200 | 0.4965 | 0.8172 | 0.8173 |
| 0.3019 | 61.54 | 2400 | 0.5114 | 0.8036 | 0.8042 |
| 0.2877 | 66.67 | 2600 | 0.4937 | 0.8141 | 0.8140 |
| 0.2787 | 71.79 | 2800 | 0.5037 | 0.8187 | 0.8189 |
| 0.274 | 76.92 | 3000 | 0.5147 | 0.8137 | 0.8140 |
| 0.2592 | 82.05 | 3200 | 0.5178 | 0.8157 | 0.8157 |
| 0.2549 | 87.18 | 3400 | 0.5278 | 0.8104 | 0.8108 |
| 0.2446 | 92.31 | 3600 | 0.5193 | 0.8157 | 0.8157 |
| 0.2401 | 97.44 | 3800 | 0.5307 | 0.8060 | 0.8059 |
| 0.2275 | 102.56 | 4000 | 0.5405 | 0.8093 | 0.8091 |
| 0.2224 | 107.69 | 4200 | 0.5597 | 0.8073 | 0.8075 |
| 0.2167 | 112.82 | 4400 | 0.5506 | 0.8125 | 0.8124 |
| 0.2161 | 117.95 | 4600 | 0.6083 | 0.7916 | 0.7928 |
| 0.208 | 123.08 | 4800 | 0.5856 | 0.8125 | 0.8124 |
| 0.2035 | 128.21 | 5000 | 0.5996 | 0.8057 | 0.8059 |
| 0.1935 | 133.33 | 5200 | 0.6063 | 0.8125 | 0.8124 |
| 0.1911 | 138.46 | 5400 | 0.6082 | 0.8091 | 0.8091 |
| 0.1862 | 143.59 | 5600 | 0.6273 | 0.7957 | 0.7961 |
| 0.1807 | 148.72 | 5800 | 0.6411 | 0.8074 | 0.8075 |
| 0.1811 | 153.85 | 6000 | 0.6109 | 0.8059 | 0.8059 |
| 0.1735 | 158.97 | 6200 | 0.6349 | 0.8091 | 0.8091 |
| 0.1681 | 164.1 | 6400 | 0.6542 | 0.8075 | 0.8075 |
| 0.1634 | 169.23 | 6600 | 0.6528 | 0.8140 | 0.8140 |
| 0.162 | 174.36 | 6800 | 0.6502 | 0.8091 | 0.8091 |
| 0.1621 | 179.49 | 7000 | 0.6551 | 0.8041 | 0.8042 |
| 0.1583 | 184.62 | 7200 | 0.6558 | 0.8158 | 0.8157 |
| 0.1534 | 189.74 | 7400 | 0.6527 | 0.8158 | 0.8157 |
| 0.1502 | 194.87 | 7600 | 0.6593 | 0.8060 | 0.8059 |
| 0.151 | 200.0 | 7800 | 0.6558 | 0.8109 | 0.8108 |
| 0.1461 | 205.13 | 8000 | 0.6911 | 0.8024 | 0.8026 |
| 0.1416 | 210.26 | 8200 | 0.6885 | 0.8059 | 0.8059 |
| 0.1415 | 215.38 | 8400 | 0.6917 | 0.7973 | 0.7977 |
| 0.1414 | 220.51 | 8600 | 0.6833 | 0.8093 | 0.8091 |
| 0.1364 | 225.64 | 8800 | 0.6925 | 0.8010 | 0.8010 |
| 0.1333 | 230.77 | 9000 | 0.6977 | 0.8043 | 0.8042 |
| 0.1343 | 235.9 | 9200 | 0.7001 | 0.7960 | 0.7961 |
| 0.1341 | 241.03 | 9400 | 0.6994 | 0.8043 | 0.8042 |
| 0.1314 | 246.15 | 9600 | 0.7022 | 0.8010 | 0.8010 |
| 0.1353 | 251.28 | 9800 | 0.7017 | 0.8010 | 0.8010 |
| 0.1363 | 256.41 | 10000 | 0.7074 | 0.7960 | 0.7961 |
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2 | {"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_prom_prom_300_tata-seqsight_4096_512_46M-L1_f", "results": []}]} | mahdibaghbanzadeh/GUE_prom_prom_300_tata-seqsight_4096_512_46M-L1_f | null | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:mahdibaghbanzadeh/seqsight_4096_512_46M",
"region:us"
]
| null | 2024-04-26T18:51:20+00:00 |
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-ep35 | null | [
"transformers",
"safetensors",
"xlm-roberta",
"feature-extraction",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T18:51:20+00:00 |
null | null | {} | VitaminBee/vitaminBee | null | [
"region:us"
]
| null | 2024-04-26T18:51:32+00:00 |
|
null | null | {"license": "apache-2.0"} | alii175/army | null | [
"license:apache-2.0",
"region:us"
]
| null | 2024-04-26T18:51:36+00:00 |
|
null | transformers | ## About
<!-- ### quantize_version: 1 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/aaditya/OpenBioLLM-Llama3-8B
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/OpenBioLLM-Llama3-8B-i1-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-8B-GGUF/resolve/main/OpenBioLLM-Llama3-8B.Q2_K.gguf) | Q2_K | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-8B-GGUF/resolve/main/OpenBioLLM-Llama3-8B.IQ3_XS.gguf) | IQ3_XS | 3.6 | |
| [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-8B-GGUF/resolve/main/OpenBioLLM-Llama3-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
| [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-8B-GGUF/resolve/main/OpenBioLLM-Llama3-8B.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-8B-GGUF/resolve/main/OpenBioLLM-Llama3-8B.IQ3_M.gguf) | IQ3_M | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-8B-GGUF/resolve/main/OpenBioLLM-Llama3-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-8B-GGUF/resolve/main/OpenBioLLM-Llama3-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
| [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-8B-GGUF/resolve/main/OpenBioLLM-Llama3-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
| [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-8B-GGUF/resolve/main/OpenBioLLM-Llama3-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-8B-GGUF/resolve/main/OpenBioLLM-Llama3-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-8B-GGUF/resolve/main/OpenBioLLM-Llama3-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
| [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-8B-GGUF/resolve/main/OpenBioLLM-Llama3-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
| [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-8B-GGUF/resolve/main/OpenBioLLM-Llama3-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-8B-GGUF/resolve/main/OpenBioLLM-Llama3-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-8B-GGUF/resolve/main/OpenBioLLM-Llama3-8B.f16.gguf) | f16 | 16.2 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
| {"language": ["en"], "license": "llama3", "library_name": "transformers", "tags": ["llama-3", "llama", "Mixtral", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "distillation"], "base_model": "aaditya/OpenBioLLM-Llama3-8B", "quantized_by": "mradermacher"} | mradermacher/OpenBioLLM-Llama3-8B-GGUF | null | [
"transformers",
"gguf",
"llama-3",
"llama",
"Mixtral",
"instruct",
"finetune",
"chatml",
"DPO",
"RLHF",
"gpt4",
"distillation",
"en",
"base_model:aaditya/OpenBioLLM-Llama3-8B",
"license:llama3",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T18:51:41+00:00 |
null | null | {"license": "openrail"} | itskeonagain/lizleeloallroiund | null | [
"license:openrail",
"region:us"
]
| null | 2024-04-26T18:52:27+00:00 |
|
null | peft |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# GUE_prom_prom_300_tata-seqsight_4096_512_46M-L8_f
This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_prom_prom_300_tata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_300_tata) dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1438
- F1 Score: 0.7977
- Accuracy: 0.7977
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 10000
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy |
|:-------------:|:------:|:-----:|:---------------:|:--------:|:--------:|
| 0.5219 | 5.13 | 200 | 0.4674 | 0.7930 | 0.7928 |
| 0.4208 | 10.26 | 400 | 0.5335 | 0.7665 | 0.7700 |
| 0.3713 | 15.38 | 600 | 0.4630 | 0.8060 | 0.8059 |
| 0.3369 | 20.51 | 800 | 0.4880 | 0.8124 | 0.8124 |
| 0.311 | 25.64 | 1000 | 0.5083 | 0.8072 | 0.8075 |
| 0.2792 | 30.77 | 1200 | 0.5235 | 0.8090 | 0.8091 |
| 0.2547 | 35.9 | 1400 | 0.5602 | 0.8036 | 0.8042 |
| 0.2298 | 41.03 | 1600 | 0.5584 | 0.7991 | 0.7993 |
| 0.2141 | 46.15 | 1800 | 0.5943 | 0.8059 | 0.8059 |
| 0.1861 | 51.28 | 2000 | 0.6661 | 0.7846 | 0.7847 |
| 0.1749 | 56.41 | 2200 | 0.7863 | 0.7896 | 0.7912 |
| 0.1619 | 61.54 | 2400 | 0.7337 | 0.7893 | 0.7896 |
| 0.1421 | 66.67 | 2600 | 0.8072 | 0.7863 | 0.7863 |
| 0.1325 | 71.79 | 2800 | 0.8324 | 0.7944 | 0.7945 |
| 0.1272 | 76.92 | 3000 | 0.8595 | 0.7777 | 0.7781 |
| 0.114 | 82.05 | 3200 | 0.8499 | 0.7993 | 0.7993 |
| 0.1099 | 87.18 | 3400 | 0.8849 | 0.8008 | 0.8010 |
| 0.101 | 92.31 | 3600 | 0.9083 | 0.7978 | 0.7977 |
| 0.0972 | 97.44 | 3800 | 0.9468 | 0.7881 | 0.7879 |
| 0.0917 | 102.56 | 4000 | 0.9275 | 0.7827 | 0.7830 |
| 0.0856 | 107.69 | 4200 | 1.0109 | 0.7961 | 0.7961 |
| 0.0819 | 112.82 | 4400 | 1.0156 | 0.8027 | 0.8026 |
| 0.0772 | 117.95 | 4600 | 1.0641 | 0.8027 | 0.8026 |
| 0.0723 | 123.08 | 4800 | 1.0596 | 0.7946 | 0.7945 |
| 0.0712 | 128.21 | 5000 | 1.0247 | 0.8027 | 0.8026 |
| 0.0697 | 133.33 | 5200 | 1.0250 | 0.7995 | 0.7993 |
| 0.0634 | 138.46 | 5400 | 1.0853 | 0.8060 | 0.8059 |
| 0.0642 | 143.59 | 5600 | 1.0859 | 0.8060 | 0.8059 |
| 0.0574 | 148.72 | 5800 | 1.1577 | 0.8027 | 0.8026 |
| 0.0591 | 153.85 | 6000 | 1.1102 | 0.7930 | 0.7928 |
| 0.0585 | 158.97 | 6200 | 1.1141 | 0.8028 | 0.8026 |
| 0.058 | 164.1 | 6400 | 1.0972 | 0.8076 | 0.8075 |
| 0.0522 | 169.23 | 6600 | 1.1226 | 0.7912 | 0.7912 |
| 0.0502 | 174.36 | 6800 | 1.1901 | 0.8043 | 0.8042 |
| 0.0512 | 179.49 | 7000 | 1.1143 | 0.8125 | 0.8124 |
| 0.0518 | 184.62 | 7200 | 1.1176 | 0.8060 | 0.8059 |
| 0.0463 | 189.74 | 7400 | 1.1819 | 0.8076 | 0.8075 |
| 0.0462 | 194.87 | 7600 | 1.2209 | 0.8076 | 0.8075 |
| 0.048 | 200.0 | 7800 | 1.1939 | 0.8060 | 0.8059 |
| 0.0458 | 205.13 | 8000 | 1.2056 | 0.8076 | 0.8075 |
| 0.04 | 210.26 | 8200 | 1.2237 | 0.8093 | 0.8091 |
| 0.0431 | 215.38 | 8400 | 1.2553 | 0.8011 | 0.8010 |
| 0.0409 | 220.51 | 8600 | 1.2386 | 0.8044 | 0.8042 |
| 0.0391 | 225.64 | 8800 | 1.2630 | 0.8060 | 0.8059 |
| 0.0379 | 230.77 | 9000 | 1.2814 | 0.8076 | 0.8075 |
| 0.0408 | 235.9 | 9200 | 1.2478 | 0.8060 | 0.8059 |
| 0.0385 | 241.03 | 9400 | 1.2441 | 0.8093 | 0.8091 |
| 0.0376 | 246.15 | 9600 | 1.2370 | 0.8109 | 0.8108 |
| 0.0392 | 251.28 | 9800 | 1.2531 | 0.8076 | 0.8075 |
| 0.0371 | 256.41 | 10000 | 1.2568 | 0.8060 | 0.8059 |
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2 | {"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_prom_prom_300_tata-seqsight_4096_512_46M-L8_f", "results": []}]} | mahdibaghbanzadeh/GUE_prom_prom_300_tata-seqsight_4096_512_46M-L8_f | null | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:mahdibaghbanzadeh/seqsight_4096_512_46M",
"region:us"
]
| null | 2024-04-26T18:52:33+00:00 |
null | peft |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# GUE_prom_prom_300_tata-seqsight_4096_512_46M-L32_f
This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_prom_prom_300_tata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_300_tata) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4797
- F1 Score: 0.8010
- Accuracy: 0.8010
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 10000
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy |
|:-------------:|:------:|:-----:|:---------------:|:--------:|:--------:|
| 0.491 | 5.13 | 200 | 0.4698 | 0.8044 | 0.8042 |
| 0.378 | 10.26 | 400 | 0.5056 | 0.7936 | 0.7945 |
| 0.3148 | 15.38 | 600 | 0.4899 | 0.8142 | 0.8140 |
| 0.2565 | 20.51 | 800 | 0.5451 | 0.8141 | 0.8140 |
| 0.2036 | 25.64 | 1000 | 0.6197 | 0.8092 | 0.8091 |
| 0.1585 | 30.77 | 1200 | 0.6934 | 0.8005 | 0.8010 |
| 0.1323 | 35.9 | 1400 | 0.7745 | 0.8093 | 0.8091 |
| 0.105 | 41.03 | 1600 | 0.8804 | 0.7928 | 0.7928 |
| 0.0907 | 46.15 | 1800 | 0.9467 | 0.7880 | 0.7879 |
| 0.0741 | 51.28 | 2000 | 1.0341 | 0.7923 | 0.7928 |
| 0.0682 | 56.41 | 2200 | 1.1984 | 0.8060 | 0.8059 |
| 0.0636 | 61.54 | 2400 | 1.0886 | 0.7962 | 0.7961 |
| 0.0547 | 66.67 | 2600 | 1.1504 | 0.7945 | 0.7945 |
| 0.0504 | 71.79 | 2800 | 1.1883 | 0.7960 | 0.7961 |
| 0.0469 | 76.92 | 3000 | 1.2114 | 0.7848 | 0.7847 |
| 0.0416 | 82.05 | 3200 | 1.1602 | 0.7930 | 0.7928 |
| 0.0422 | 87.18 | 3400 | 1.2750 | 0.7877 | 0.7879 |
| 0.0353 | 92.31 | 3600 | 1.2695 | 0.7945 | 0.7945 |
| 0.0373 | 97.44 | 3800 | 1.2257 | 0.7945 | 0.7945 |
| 0.0333 | 102.56 | 4000 | 1.3635 | 0.7962 | 0.7961 |
| 0.0328 | 107.69 | 4200 | 1.3407 | 0.8025 | 0.8026 |
| 0.0311 | 112.82 | 4400 | 1.3750 | 0.8011 | 0.8010 |
| 0.0286 | 117.95 | 4600 | 1.3720 | 0.8011 | 0.8010 |
| 0.0257 | 123.08 | 4800 | 1.3457 | 0.8011 | 0.8010 |
| 0.0263 | 128.21 | 5000 | 1.3824 | 0.7912 | 0.7912 |
| 0.0271 | 133.33 | 5200 | 1.3912 | 0.7946 | 0.7945 |
| 0.0227 | 138.46 | 5400 | 1.4420 | 0.7962 | 0.7961 |
| 0.0253 | 143.59 | 5600 | 1.4062 | 0.8010 | 0.8010 |
| 0.0199 | 148.72 | 5800 | 1.5250 | 0.7962 | 0.7961 |
| 0.0209 | 153.85 | 6000 | 1.5001 | 0.8027 | 0.8026 |
| 0.0225 | 158.97 | 6200 | 1.5224 | 0.7783 | 0.7781 |
| 0.0206 | 164.1 | 6400 | 1.5148 | 0.7962 | 0.7961 |
| 0.0168 | 169.23 | 6600 | 1.6866 | 0.8027 | 0.8026 |
| 0.0174 | 174.36 | 6800 | 1.6624 | 0.7880 | 0.7879 |
| 0.0171 | 179.49 | 7000 | 1.5981 | 0.7978 | 0.7977 |
| 0.0166 | 184.62 | 7200 | 1.5850 | 0.7929 | 0.7928 |
| 0.0154 | 189.74 | 7400 | 1.6554 | 0.7979 | 0.7977 |
| 0.015 | 194.87 | 7600 | 1.6823 | 0.7945 | 0.7945 |
| 0.016 | 200.0 | 7800 | 1.6797 | 0.8027 | 0.8026 |
| 0.0148 | 205.13 | 8000 | 1.6498 | 0.7962 | 0.7961 |
| 0.0133 | 210.26 | 8200 | 1.7261 | 0.7928 | 0.7928 |
| 0.0154 | 215.38 | 8400 | 1.7055 | 0.7978 | 0.7977 |
| 0.0122 | 220.51 | 8600 | 1.7680 | 0.7913 | 0.7912 |
| 0.0115 | 225.64 | 8800 | 1.7756 | 0.8060 | 0.8059 |
| 0.0106 | 230.77 | 9000 | 1.8826 | 0.8026 | 0.8026 |
| 0.0127 | 235.9 | 9200 | 1.7970 | 0.8043 | 0.8042 |
| 0.0111 | 241.03 | 9400 | 1.8099 | 0.8011 | 0.8010 |
| 0.0097 | 246.15 | 9600 | 1.8413 | 0.8093 | 0.8091 |
| 0.0122 | 251.28 | 9800 | 1.8452 | 0.7994 | 0.7993 |
| 0.0112 | 256.41 | 10000 | 1.8429 | 0.8027 | 0.8026 |
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2 | {"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_prom_prom_300_tata-seqsight_4096_512_46M-L32_f", "results": []}]} | mahdibaghbanzadeh/GUE_prom_prom_300_tata-seqsight_4096_512_46M-L32_f | null | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:mahdibaghbanzadeh/seqsight_4096_512_46M",
"region:us"
]
| null | 2024-04-26T18:52:33+00:00 |
null | peft |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# GUE_prom_prom_300_notata-seqsight_4096_512_46M-L1_f
This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_prom_prom_300_notata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_300_notata) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1202
- F1 Score: 0.9538
- Accuracy: 0.9538
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 10000
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|
| 0.2538 | 0.6 | 200 | 0.1608 | 0.9378 | 0.9378 |
| 0.1602 | 1.2 | 400 | 0.1460 | 0.9419 | 0.9420 |
| 0.1447 | 1.81 | 600 | 0.1247 | 0.9508 | 0.9508 |
| 0.1294 | 2.41 | 800 | 0.1321 | 0.9487 | 0.9487 |
| 0.1272 | 3.01 | 1000 | 0.1173 | 0.9565 | 0.9565 |
| 0.1209 | 3.61 | 1200 | 0.1226 | 0.9517 | 0.9518 |
| 0.1163 | 4.22 | 1400 | 0.1175 | 0.9547 | 0.9548 |
| 0.1153 | 4.82 | 1600 | 0.1133 | 0.9566 | 0.9567 |
| 0.113 | 5.42 | 1800 | 0.1130 | 0.9566 | 0.9567 |
| 0.1083 | 6.02 | 2000 | 0.1088 | 0.9585 | 0.9585 |
| 0.1104 | 6.63 | 2200 | 0.1084 | 0.9595 | 0.9595 |
| 0.1089 | 7.23 | 2400 | 0.1120 | 0.9597 | 0.9597 |
| 0.103 | 7.83 | 2600 | 0.1120 | 0.9581 | 0.9582 |
| 0.106 | 8.43 | 2800 | 0.1124 | 0.9591 | 0.9591 |
| 0.1056 | 9.04 | 3000 | 0.1107 | 0.9591 | 0.9591 |
| 0.1015 | 9.64 | 3200 | 0.1041 | 0.9606 | 0.9606 |
| 0.0987 | 10.24 | 3400 | 0.1141 | 0.9591 | 0.9591 |
| 0.104 | 10.84 | 3600 | 0.1049 | 0.9615 | 0.9616 |
| 0.0978 | 11.45 | 3800 | 0.1042 | 0.9608 | 0.9608 |
| 0.1002 | 12.05 | 4000 | 0.1062 | 0.9606 | 0.9606 |
| 0.0998 | 12.65 | 4200 | 0.1042 | 0.9614 | 0.9614 |
| 0.1005 | 13.25 | 4400 | 0.1050 | 0.9610 | 0.9610 |
| 0.0952 | 13.86 | 4600 | 0.1041 | 0.9614 | 0.9614 |
| 0.0988 | 14.46 | 4800 | 0.1060 | 0.9608 | 0.9608 |
| 0.0929 | 15.06 | 5000 | 0.1028 | 0.9621 | 0.9621 |
| 0.0946 | 15.66 | 5200 | 0.1049 | 0.9625 | 0.9625 |
| 0.0976 | 16.27 | 5400 | 0.1085 | 0.9604 | 0.9604 |
| 0.0929 | 16.87 | 5600 | 0.1048 | 0.9615 | 0.9616 |
| 0.0928 | 17.47 | 5800 | 0.1010 | 0.9612 | 0.9612 |
| 0.0969 | 18.07 | 6000 | 0.1021 | 0.9617 | 0.9617 |
| 0.0901 | 18.67 | 6200 | 0.1064 | 0.9615 | 0.9616 |
| 0.0932 | 19.28 | 6400 | 0.1010 | 0.9621 | 0.9621 |
| 0.0909 | 19.88 | 6600 | 0.1089 | 0.9613 | 0.9614 |
| 0.0952 | 20.48 | 6800 | 0.1042 | 0.9621 | 0.9621 |
| 0.0902 | 21.08 | 7000 | 0.1011 | 0.9621 | 0.9621 |
| 0.0894 | 21.69 | 7200 | 0.1003 | 0.9619 | 0.9619 |
| 0.0895 | 22.29 | 7400 | 0.1001 | 0.9627 | 0.9627 |
| 0.0912 | 22.89 | 7600 | 0.0993 | 0.9627 | 0.9627 |
| 0.0893 | 23.49 | 7800 | 0.1001 | 0.9619 | 0.9619 |
| 0.0896 | 24.1 | 8000 | 0.1005 | 0.9634 | 0.9634 |
| 0.0885 | 24.7 | 8200 | 0.1055 | 0.9630 | 0.9631 |
| 0.0896 | 25.3 | 8400 | 0.1019 | 0.9629 | 0.9629 |
| 0.0875 | 25.9 | 8600 | 0.0992 | 0.9627 | 0.9627 |
| 0.0885 | 26.51 | 8800 | 0.1004 | 0.9629 | 0.9629 |
| 0.0899 | 27.11 | 9000 | 0.0995 | 0.9634 | 0.9634 |
| 0.0866 | 27.71 | 9200 | 0.1016 | 0.9640 | 0.9640 |
| 0.0866 | 28.31 | 9400 | 0.1008 | 0.9640 | 0.9640 |
| 0.0896 | 28.92 | 9600 | 0.1001 | 0.9631 | 0.9631 |
| 0.0843 | 29.52 | 9800 | 0.1014 | 0.9634 | 0.9634 |
| 0.0884 | 30.12 | 10000 | 0.1007 | 0.9631 | 0.9631 |
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2 | {"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_prom_prom_300_notata-seqsight_4096_512_46M-L1_f", "results": []}]} | mahdibaghbanzadeh/GUE_prom_prom_300_notata-seqsight_4096_512_46M-L1_f | null | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:mahdibaghbanzadeh/seqsight_4096_512_46M",
"region:us"
]
| null | 2024-04-26T18:53:09+00:00 |
text-generation | transformers |
# CodeQwen1.5-7B-Chat
## About Quantization
我们使用modelscope [swift](https://github.com/modelscope/swift/)仓库进行GPTQ量化. 量化文档可以查看[这里](https://github.com/modelscope/swift/blob/main/docs/source/LLM/LLM%E9%87%8F%E5%8C%96%E6%96%87%E6%A1%A3.md). 量化命令如下:
We use the modelscope [swift](https://github.com/modelscope/swift/) repository to perform GPTQ quantization. Quantization documentation can be found [here](https://github.com/modelscope/swift/blob/main/docs/source_en/LLM/LLM-quantization.md). The quantization command is as follows:
```bash
OMP_NUM_THREADS=14 CUDA_VISIBLE_DEVICES=0 swift export \
--model_type codeqwen1half-7b-chat --quant_bits 4 \
--dataset codefuse-evol-instruction-zh --quant_method gptq --quant_seqlen 8192
```
## Introduction
CodeQwen1.5 is the Code-Specific version of Qwen1.5. It is a transformer-based decoder-only language model pretrained on a large amount of data of codes.
* Strong code generation capabilities and competitve performance across a series of benchmarks;
* Supporting long context understanding and generation with the context length of 64K tokens;
* Supporting 92 coding languages
* Excellent performance on text-to-SQL, bug fix, etc.
For more details, please refer to our [blog post](https://qwenlm.github.io/blog/codeqwen1.5/) and [GitHub repo](https://github.com/QwenLM/Qwen1.5).
## Model Details
CodeQwen1.5 is based on Qwen1.5, a language model series including decoder language models of different model sizes. It is trained on 3 trillion tokens of data of codes, and it includes group query attention (GQA) for efficient inference.
## Requirements
The code of Qwen1.5 has been in the latest Hugging face transformers and we advise you to install `transformers>=4.37.0`, or you might encounter the following error:
```
KeyError: 'qwen2'.
```
## Quickstart
Here provides a code snippet with `apply_chat_template` to show you how to load the tokenizer and model and how to generate contents.
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model onto
model = AutoModelForCausalLM.from_pretrained(
"study-hjt/CodeQwen1.5-7B-Chat-GPTQ-Int4",
torch_dtype="auto",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("study-hjt/CodeQwen1.5-7B-Chat-GPTQ-Int4")
prompt = "Write a quicksort algorithm in python."
messages = [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(device)
generated_ids = model.generate(
model_inputs.input_ids,
max_new_tokens=512
)
generated_ids = [
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)
```
## Tips
* If you encounter code switching or other bad cases, we advise you to use our provided hyper-parameters in `generation_config.json`.
## Citation
If you find our work helpful, feel free to give us a cite.
```
@article{qwen,
title={Qwen Technical Report},
author={Jinze Bai and Shuai Bai and Yunfei Chu and Zeyu Cui and Kai Dang and Xiaodong Deng and Yang Fan and Wenbin Ge and Yu Han and Fei Huang and Binyuan Hui and Luo Ji and Mei Li and Junyang Lin and Runji Lin and Dayiheng Liu and Gao Liu and Chengqiang Lu and Keming Lu and Jianxin Ma and Rui Men and Xingzhang Ren and Xuancheng Ren and Chuanqi Tan and Sinan Tan and Jianhong Tu and Peng Wang and Shijie Wang and Wei Wang and Shengguang Wu and Benfeng Xu and Jin Xu and An Yang and Hao Yang and Jian Yang and Shusheng Yang and Yang Yao and Bowen Yu and Hongyi Yuan and Zheng Yuan and Jianwei Zhang and Xingxuan Zhang and Yichang Zhang and Zhenru Zhang and Chang Zhou and Jingren Zhou and Xiaohuan Zhou and Tianhang Zhu},
journal={arXiv preprint arXiv:2309.16609},
year={2023}
}
``` | {"language": ["en"], "license": "other", "tags": ["codeqwen", "code", "chat", "gptq", "int4"], "license_name": "tongyi-qianwen", "license_link": "https://huggingface.co/Qwen/CodeQwen1.5-7B-Chat/blob/main/LICENSE", "pipeline_tag": "text-generation", "studios": ["qwen/CodeQwen1.5-7b-Chat-demo"]} | study-hjt/CodeQwen1.5-7B-Chat-GPTQ-Int4 | null | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"codeqwen",
"code",
"chat",
"gptq",
"int4",
"conversational",
"en",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"4-bit",
"region:us"
]
| null | 2024-04-26T18:53:57+00:00 |
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": []} | HenryCai1129/adapter-llama-adapterhappy2sad-1k-50-0.003 | null | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T18:54:11+00:00 |
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": "mistralai/Mistral-7B-Instruct-v0.2"} | sahanes/Enlighten_Instruct | null | [
"peft",
"safetensors",
"transformer",
"arxiv:1910.09700",
"base_model:mistralai/Mistral-7B-Instruct-v0.2",
"4-bit",
"region:us"
]
| null | 2024-04-26T18:55:35+00:00 |
text-generation | transformers |
# CodeQwen1.5-7B-Chat
## About Quantization
我们使用modelscope [swift](https://github.com/modelscope/swift/)仓库进行GPTQ量化. 量化文档可以查看[这里](https://github.com/modelscope/swift/blob/main/docs/source/LLM/LLM%E9%87%8F%E5%8C%96%E6%96%87%E6%A1%A3.md). 量化命令如下:
We use the modelscope [swift](https://github.com/modelscope/swift/) repository to perform GPTQ quantization. Quantization documentation can be found [here](https://github.com/modelscope/swift/blob/main/docs/source_en/LLM/LLM-quantization.md). The quantization command is as follows:
```bash
OMP_NUM_THREADS=14 CUDA_VISIBLE_DEVICES=0 swift export \
--model_type codeqwen1half-7b-chat --quant_bits 8 \
--dataset codefuse-evol-instruction-zh --quant_method gptq --quant_seqlen 8192
```
## Introduction
CodeQwen1.5 is the Code-Specific version of Qwen1.5. It is a transformer-based decoder-only language model pretrained on a large amount of data of codes.
* Strong code generation capabilities and competitve performance across a series of benchmarks;
* Supporting long context understanding and generation with the context length of 64K tokens;
* Supporting 92 coding languages
* Excellent performance on text-to-SQL, bug fix, etc.
For more details, please refer to our [blog post](https://qwenlm.github.io/blog/codeqwen1.5/) and [GitHub repo](https://github.com/QwenLM/Qwen1.5).
## Model Details
CodeQwen1.5 is based on Qwen1.5, a language model series including decoder language models of different model sizes. It is trained on 3 trillion tokens of data of codes, and it includes group query attention (GQA) for efficient inference.
## Requirements
The code of Qwen1.5 has been in the latest Hugging face transformers and we advise you to install `transformers>=4.37.0`, or you might encounter the following error:
```
KeyError: 'qwen2'.
```
## Quickstart
Here provides a code snippet with `apply_chat_template` to show you how to load the tokenizer and model and how to generate contents.
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model onto
model = AutoModelForCausalLM.from_pretrained(
"study-hjt/CodeQwen1.5-7B-Chat-GPTQ-Int8",
torch_dtype="auto",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("study-hjt/CodeQwen1.5-7B-Chat-GPTQ-Int8")
prompt = "Write a quicksort algorithm in python."
messages = [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(device)
generated_ids = model.generate(
model_inputs.input_ids,
max_new_tokens=512
)
generated_ids = [
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)
```
## Tips
* If you encounter code switching or other bad cases, we advise you to use our provided hyper-parameters in `generation_config.json`.
## Citation
If you find our work helpful, feel free to give us a cite.
```
@article{qwen,
title={Qwen Technical Report},
author={Jinze Bai and Shuai Bai and Yunfei Chu and Zeyu Cui and Kai Dang and Xiaodong Deng and Yang Fan and Wenbin Ge and Yu Han and Fei Huang and Binyuan Hui and Luo Ji and Mei Li and Junyang Lin and Runji Lin and Dayiheng Liu and Gao Liu and Chengqiang Lu and Keming Lu and Jianxin Ma and Rui Men and Xingzhang Ren and Xuancheng Ren and Chuanqi Tan and Sinan Tan and Jianhong Tu and Peng Wang and Shijie Wang and Wei Wang and Shengguang Wu and Benfeng Xu and Jin Xu and An Yang and Hao Yang and Jian Yang and Shusheng Yang and Yang Yao and Bowen Yu and Hongyi Yuan and Zheng Yuan and Jianwei Zhang and Xingxuan Zhang and Yichang Zhang and Zhenru Zhang and Chang Zhou and Jingren Zhou and Xiaohuan Zhou and Tianhang Zhu},
journal={arXiv preprint arXiv:2309.16609},
year={2023}
}
``` | {"language": ["en"], "license": "other", "tags": ["chat", "gptq", "codeqwen", "int8"], "license_name": "tongyi-qianwen", "license_link": "https://huggingface.co/Qwen/CodeQwen1.5-7B-Chat/blob/main/LICENSE", "pipeline_tag": "text-generation", "studios": ["qwen/CodeQwen1.5-7b-Chat-demo"]} | study-hjt/CodeQwen1.5-7B-Chat-GPTQ-Int8 | null | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"chat",
"gptq",
"codeqwen",
"int8",
"conversational",
"en",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"8-bit",
"region:us"
]
| null | 2024-04-26T18:55:52+00:00 |
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. -->
# Action_Classification
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the agent_action_class dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8482
- Accuracy: 0.7629
- Confusion Matrix: [[45, 5, 20, 4, 2, 6, 4, 8, 3, 3], [5, 154, 4, 2, 1, 2, 6, 1, 17, 1], [0, 0, 51, 1, 2, 8, 1, 0, 0, 2], [1, 0, 8, 26, 8, 5, 0, 0, 1, 3], [0, 1, 0, 0, 89, 3, 0, 0, 0, 0], [0, 1, 11, 3, 1, 55, 0, 1, 0, 0], [0, 1, 1, 0, 3, 3, 51, 0, 0, 0], [0, 0, 10, 1, 0, 4, 0, 68, 0, 0], [0, 26, 5, 0, 1, 3, 16, 1, 127, 1], [3, 0, 2, 9, 2, 1, 0, 1, 0, 135]]
## Model description
More information needed
## Intended uses & 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: 32
- eval_batch_size: 16
- 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 | Accuracy | Confusion Matrix |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|
| 0.3922 | 0.32 | 100 | 1.0781 | 0.6933 | [[66, 1, 9, 6, 1, 5, 1, 3, 7, 1], [41, 96, 0, 0, 8, 0, 2, 1, 45, 0], [2, 0, 46, 1, 1, 7, 4, 0, 1, 3], [9, 1, 4, 19, 5, 3, 2, 1, 4, 4], [0, 2, 0, 3, 84, 2, 1, 0, 0, 1], [4, 1, 3, 2, 0, 55, 3, 1, 3, 0], [0, 0, 1, 0, 0, 1, 54, 0, 3, 0], [5, 1, 4, 1, 0, 1, 0, 70, 1, 0], [5, 12, 0, 1, 1, 0, 14, 0, 147, 0], [9, 0, 1, 38, 3, 1, 4, 4, 2, 91]] |
| 0.439 | 0.64 | 200 | 0.8592 | 0.7562 | [[73, 3, 6, 4, 0, 3, 2, 3, 3, 3], [30, 121, 1, 0, 1, 0, 8, 0, 32, 0], [1, 0, 47, 1, 1, 9, 1, 0, 1, 4], [7, 0, 5, 28, 5, 1, 0, 1, 2, 3], [0, 2, 0, 1, 88, 0, 1, 0, 0, 1], [4, 1, 5, 3, 2, 51, 0, 1, 2, 3], [0, 1, 1, 0, 0, 0, 56, 0, 1, 0], [4, 2, 1, 0, 0, 0, 1, 74, 1, 0], [4, 28, 0, 1, 0, 0, 19, 2, 125, 1], [3, 0, 1, 15, 1, 0, 1, 1, 0, 131]] |
| 0.4664 | 0.96 | 300 | 0.8482 | 0.7629 | [[45, 5, 20, 4, 2, 6, 4, 8, 3, 3], [5, 154, 4, 2, 1, 2, 6, 1, 17, 1], [0, 0, 51, 1, 2, 8, 1, 0, 0, 2], [1, 0, 8, 26, 8, 5, 0, 0, 1, 3], [0, 1, 0, 0, 89, 3, 0, 0, 0, 0], [0, 1, 11, 3, 1, 55, 0, 1, 0, 0], [0, 1, 1, 0, 3, 3, 51, 0, 0, 0], [0, 0, 10, 1, 0, 4, 0, 68, 0, 0], [0, 26, 5, 0, 1, 3, 16, 1, 127, 1], [3, 0, 2, 9, 2, 1, 0, 1, 0, 135]] |
| 0.2929 | 1.27 | 400 | 1.1281 | 0.6790 | [[65, 3, 9, 7, 1, 1, 2, 2, 10, 0], [38, 113, 1, 0, 1, 0, 5, 0, 35, 0], [3, 0, 54, 4, 1, 1, 2, 0, 0, 0], [8, 2, 5, 31, 5, 0, 0, 0, 1, 0], [0, 2, 6, 3, 80, 0, 1, 1, 0, 0], [6, 2, 16, 8, 1, 34, 1, 1, 3, 0], [1, 2, 1, 0, 0, 0, 55, 0, 0, 0], [6, 2, 6, 2, 0, 0, 0, 66, 1, 0], [3, 24, 2, 2, 0, 0, 14, 0, 135, 0], [9, 2, 4, 56, 1, 0, 1, 0, 0, 80]] |
| 0.4188 | 1.59 | 500 | 1.1851 | 0.6657 | [[61, 2, 11, 6, 3, 5, 2, 5, 4, 1], [53, 85, 5, 0, 8, 5, 3, 6, 28, 0], [0, 0, 51, 2, 2, 5, 1, 3, 0, 1], [2, 1, 4, 34, 8, 0, 0, 2, 1, 0], [0, 1, 0, 1, 89, 0, 1, 0, 1, 0], [1, 0, 7, 4, 5, 48, 1, 5, 1, 0], [0, 1, 1, 0, 3, 0, 54, 0, 0, 0], [5, 1, 1, 1, 0, 3, 0, 72, 0, 0], [11, 18, 0, 0, 2, 2, 17, 8, 122, 0], [1, 1, 2, 42, 8, 1, 10, 4, 1, 83]] |
| 0.3668 | 1.91 | 600 | 0.8554 | 0.7467 | [[53, 11, 11, 5, 0, 3, 1, 4, 10, 2], [3, 145, 5, 0, 1, 1, 4, 5, 29, 0], [0, 0, 53, 1, 1, 5, 2, 1, 1, 1], [4, 0, 9, 29, 5, 2, 0, 0, 1, 2], [0, 1, 4, 3, 84, 0, 0, 0, 1, 0], [2, 2, 12, 3, 1, 45, 0, 3, 3, 1], [0, 1, 2, 1, 1, 0, 52, 0, 2, 0], [1, 2, 5, 1, 0, 1, 0, 73, 0, 0], [4, 29, 2, 0, 0, 0, 7, 3, 135, 0], [1, 0, 11, 19, 1, 5, 0, 1, 0, 115]] |
| 0.342 | 2.23 | 700 | 1.0291 | 0.7048 | [[58, 5, 4, 4, 1, 8, 1, 9, 7, 3], [36, 111, 0, 2, 1, 4, 1, 4, 34, 0], [3, 2, 45, 5, 1, 6, 1, 1, 0, 1], [6, 0, 5, 35, 2, 0, 0, 0, 1, 3], [1, 1, 2, 6, 77, 3, 1, 0, 2, 0], [4, 0, 10, 8, 1, 39, 0, 7, 2, 1], [1, 2, 1, 0, 2, 0, 50, 0, 3, 0], [1, 0, 4, 1, 0, 0, 0, 77, 0, 0], [4, 29, 0, 0, 0, 0, 5, 2, 140, 0], [5, 0, 5, 27, 0, 0, 1, 7, 0, 108]] |
| 0.2984 | 2.55 | 800 | 1.2207 | 0.6962 | [[55, 3, 11, 2, 0, 1, 2, 11, 10, 5], [44, 71, 1, 0, 1, 0, 4, 5, 66, 1], [0, 0, 49, 3, 2, 3, 3, 2, 1, 2], [4, 0, 5, 26, 7, 0, 2, 0, 1, 7], [0, 1, 0, 0, 86, 0, 3, 0, 3, 0], [5, 2, 12, 4, 2, 39, 1, 3, 1, 3], [0, 0, 1, 0, 1, 0, 57, 0, 0, 0], [0, 0, 5, 0, 0, 0, 0, 78, 0, 0], [5, 15, 3, 0, 1, 0, 9, 4, 143, 0], [0, 0, 1, 17, 1, 0, 3, 3, 1, 127]] |
| 0.3542 | 2.87 | 900 | 1.1835 | 0.6657 | [[66, 2, 6, 8, 0, 4, 4, 4, 5, 1], [38, 78, 2, 0, 3, 1, 23, 4, 43, 1], [2, 0, 50, 7, 0, 5, 1, 0, 0, 0], [2, 0, 2, 45, 3, 0, 0, 0, 0, 0], [0, 1, 3, 6, 76, 3, 4, 0, 0, 0], [3, 1, 10, 8, 1, 47, 0, 0, 1, 1], [0, 0, 2, 0, 1, 0, 56, 0, 0, 0], [2, 0, 11, 5, 0, 2, 4, 59, 0, 0], [4, 24, 2, 1, 1, 1, 23, 0, 124, 0], [5, 0, 1, 42, 3, 0, 3, 1, 0, 98]] |
| 0.2749 | 3.18 | 1000 | 0.9242 | 0.7286 | [[54, 12, 5, 2, 3, 1, 7, 1, 12, 3], [13, 155, 0, 0, 3, 1, 2, 1, 18, 0], [2, 0, 53, 1, 4, 1, 3, 0, 0, 1], [5, 1, 7, 21, 8, 0, 0, 0, 1, 9], [0, 2, 0, 1, 89, 0, 0, 1, 0, 0], [2, 4, 16, 1, 6, 34, 3, 1, 4, 1], [0, 2, 1, 0, 2, 0, 54, 0, 0, 0], [1, 3, 6, 1, 0, 0, 0, 70, 2, 0], [4, 45, 0, 1, 2, 0, 13, 0, 115, 0], [2, 1, 6, 19, 4, 0, 0, 1, 0, 120]] |
| 0.2695 | 3.5 | 1100 | 0.9828 | 0.7314 | [[58, 8, 9, 3, 0, 3, 2, 5, 10, 2], [29, 130, 2, 0, 0, 3, 1, 4, 24, 0], [1, 0, 49, 3, 1, 6, 2, 0, 0, 3], [6, 1, 5, 26, 6, 1, 0, 1, 1, 5], [0, 1, 2, 4, 79, 1, 1, 1, 4, 0], [2, 2, 12, 4, 1, 48, 1, 0, 1, 1], [0, 0, 1, 0, 1, 0, 57, 0, 0, 0], [2, 2, 4, 1, 0, 2, 2, 67, 3, 0], [1, 32, 0, 1, 0, 4, 12, 2, 125, 3], [3, 1, 2, 10, 1, 5, 2, 0, 0, 129]] |
| 0.2343 | 3.82 | 1200 | 1.0871 | 0.7295 | [[58, 2, 10, 5, 1, 1, 7, 4, 10, 2], [21, 115, 0, 0, 4, 0, 12, 3, 38, 0], [1, 0, 53, 2, 2, 3, 0, 1, 1, 2], [2, 2, 9, 22, 9, 0, 1, 0, 1, 6], [0, 2, 1, 1, 88, 0, 0, 0, 1, 0], [2, 1, 10, 4, 2, 48, 1, 2, 2, 0], [0, 0, 1, 0, 2, 0, 56, 0, 0, 0], [2, 1, 7, 0, 0, 0, 0, 72, 1, 0], [4, 22, 0, 1, 0, 0, 14, 0, 139, 0], [7, 0, 4, 20, 1, 3, 1, 2, 0, 115]] |
| 0.2714 | 4.14 | 1300 | 1.0720 | 0.7314 | [[59, 6, 8, 8, 1, 1, 3, 4, 7, 3], [23, 114, 2, 1, 1, 0, 5, 3, 42, 2], [1, 1, 54, 2, 1, 2, 0, 1, 0, 3], [3, 1, 3, 32, 4, 0, 0, 0, 1, 8], [0, 1, 3, 5, 80, 1, 1, 0, 0, 2], [3, 1, 11, 7, 2, 43, 1, 2, 1, 1], [0, 0, 1, 1, 0, 0, 56, 0, 0, 1], [1, 0, 4, 0, 0, 0, 0, 77, 1, 0], [6, 31, 2, 1, 0, 0, 10, 0, 130, 0], [5, 0, 1, 22, 0, 1, 0, 1, 0, 123]] |
| 0.2287 | 4.46 | 1400 | 1.1125 | 0.7057 | [[52, 5, 15, 8, 1, 8, 0, 3, 6, 2], [27, 109, 1, 0, 1, 6, 2, 3, 43, 1], [1, 0, 55, 3, 0, 3, 1, 0, 0, 2], [2, 1, 4, 34, 4, 2, 0, 0, 0, 5], [0, 1, 2, 4, 81, 2, 1, 0, 2, 0], [2, 2, 7, 3, 1, 54, 0, 0, 3, 0], [0, 0, 1, 0, 1, 0, 56, 0, 1, 0], [1, 1, 12, 1, 0, 3, 2, 62, 1, 0], [5, 30, 1, 0, 0, 3, 9, 0, 131, 1], [4, 6, 4, 28, 0, 4, 0, 0, 0, 107]] |
| 0.2814 | 4.78 | 1500 | 1.1163 | 0.72 | [[71, 3, 7, 5, 2, 1, 1, 6, 3, 1], [53, 111, 1, 0, 1, 0, 5, 5, 17, 0], [2, 0, 48, 4, 1, 4, 0, 4, 0, 2], [6, 0, 4, 31, 6, 0, 0, 0, 0, 5], [0, 3, 1, 4, 82, 0, 1, 1, 1, 0], [8, 0, 4, 4, 1, 49, 1, 4, 1, 0], [2, 0, 1, 1, 1, 0, 52, 2, 0, 0], [2, 0, 1, 0, 0, 0, 0, 80, 0, 0], [11, 35, 2, 0, 0, 1, 9, 5, 117, 0], [10, 1, 1, 21, 1, 0, 2, 2, 0, 115]] |
| 0.2648 | 5.1 | 1600 | 1.1721 | 0.7057 | [[61, 6, 3, 3, 0, 3, 2, 12, 8, 2], [27, 131, 0, 0, 4, 0, 1, 9, 21, 0], [2, 2, 51, 2, 2, 4, 0, 1, 0, 1], [3, 1, 4, 28, 6, 3, 0, 3, 1, 3], [1, 3, 0, 4, 82, 1, 0, 1, 1, 0], [1, 0, 8, 4, 3, 51, 0, 3, 1, 1], [3, 1, 1, 1, 1, 0, 51, 1, 0, 0], [1, 0, 2, 1, 0, 0, 0, 79, 0, 0], [9, 31, 1, 0, 0, 1, 11, 10, 117, 0], [17, 5, 4, 28, 2, 2, 1, 4, 0, 90]] |
| 0.1857 | 5.41 | 1700 | 1.0404 | 0.7514 | [[57, 9, 5, 2, 1, 0, 4, 7, 11, 4], [22, 131, 0, 0, 0, 0, 5, 4, 30, 1], [1, 0, 56, 1, 1, 2, 1, 0, 0, 3], [3, 1, 2, 28, 8, 1, 1, 1, 1, 6], [1, 1, 0, 3, 85, 0, 0, 0, 3, 0], [6, 2, 11, 4, 3, 36, 2, 5, 1, 2], [0, 0, 1, 0, 0, 0, 58, 0, 0, 0], [1, 0, 2, 0, 0, 0, 0, 80, 0, 0], [7, 32, 1, 0, 0, 0, 19, 3, 117, 1], [6, 0, 1, 3, 0, 0, 1, 1, 0, 141]] |
| 0.1958 | 5.73 | 1800 | 1.1392 | 0.7238 | [[53, 7, 4, 3, 2, 1, 6, 9, 13, 2], [16, 134, 0, 0, 0, 1, 10, 7, 25, 0], [2, 1, 54, 2, 1, 1, 1, 0, 0, 3], [6, 0, 3, 29, 8, 0, 1, 1, 1, 3], [0, 2, 0, 2, 85, 0, 2, 0, 2, 0], [7, 1, 9, 2, 4, 43, 2, 2, 1, 1], [0, 0, 1, 0, 1, 0, 57, 0, 0, 0], [0, 1, 4, 0, 0, 0, 1, 77, 0, 0], [4, 28, 2, 0, 0, 0, 19, 4, 123, 0], [7, 0, 2, 25, 1, 0, 11, 2, 0, 105]] |
| 0.1475 | 6.05 | 1900 | 1.1926 | 0.7238 | [[72, 6, 4, 4, 0, 1, 2, 0, 8, 3], [52, 97, 0, 0, 1, 0, 1, 0, 41, 1], [3, 1, 52, 3, 1, 1, 1, 0, 0, 3], [6, 1, 3, 32, 2, 1, 0, 1, 1, 5], [0, 4, 1, 3, 79, 1, 0, 0, 3, 2], [3, 2, 12, 6, 0, 43, 0, 1, 2, 3], [3, 0, 1, 0, 1, 0, 52, 0, 1, 1], [8, 0, 7, 2, 0, 0, 0, 66, 0, 0], [13, 26, 1, 1, 0, 1, 8, 1, 129, 0], [6, 0, 0, 7, 0, 0, 0, 1, 1, 138]] |
| 0.1443 | 6.37 | 2000 | 1.2271 | 0.7152 | [[64, 3, 18, 4, 1, 3, 1, 3, 2, 1], [26, 112, 1, 0, 2, 0, 5, 6, 41, 0], [4, 0, 54, 2, 1, 1, 0, 0, 0, 3], [7, 1, 3, 34, 3, 1, 0, 1, 1, 1], [0, 3, 0, 3, 82, 0, 2, 0, 3, 0], [5, 2, 11, 5, 1, 44, 1, 1, 1, 1], [0, 0, 1, 0, 1, 0, 57, 0, 0, 0], [1, 0, 7, 0, 0, 4, 0, 71, 0, 0], [5, 23, 5, 2, 0, 0, 12, 5, 128, 0], [6, 3, 1, 36, 0, 0, 0, 2, 0, 105]] |
| 0.1453 | 6.69 | 2100 | 1.0546 | 0.7390 | [[71, 4, 11, 3, 0, 4, 1, 3, 2, 1], [26, 127, 3, 0, 0, 2, 4, 4, 27, 0], [1, 0, 53, 2, 2, 4, 1, 0, 0, 2], [5, 2, 5, 27, 6, 2, 0, 1, 1, 3], [1, 1, 0, 1, 87, 1, 1, 0, 1, 0], [2, 1, 6, 1, 2, 58, 0, 1, 1, 0], [2, 3, 1, 0, 2, 0, 50, 0, 0, 1], [4, 0, 7, 0, 0, 4, 0, 68, 0, 0], [4, 34, 4, 0, 1, 3, 14, 1, 119, 0], [9, 1, 2, 18, 2, 1, 0, 3, 1, 116]] |
| 0.2319 | 7.01 | 2200 | 1.0890 | 0.7371 | [[60, 4, 9, 7, 1, 4, 2, 2, 10, 1], [18, 127, 1, 0, 2, 0, 9, 2, 34, 0], [3, 0, 53, 3, 1, 2, 0, 1, 0, 2], [4, 2, 2, 36, 6, 0, 0, 0, 1, 1], [0, 4, 0, 3, 83, 0, 1, 1, 1, 0], [2, 2, 9, 6, 1, 49, 1, 0, 2, 0], [0, 0, 1, 0, 1, 0, 57, 0, 0, 0], [1, 0, 10, 1, 0, 0, 0, 71, 0, 0], [5, 24, 4, 0, 0, 1, 15, 1, 130, 0], [4, 4, 2, 28, 0, 0, 2, 5, 0, 108]] |
| 0.1499 | 7.32 | 2300 | 1.3652 | 0.7 | [[68, 3, 3, 11, 1, 1, 1, 4, 7, 1], [60, 82, 0, 2, 6, 0, 6, 4, 31, 2], [2, 1, 43, 6, 2, 4, 2, 2, 0, 3], [2, 0, 2, 36, 6, 0, 0, 1, 1, 4], [1, 2, 1, 2, 83, 2, 0, 1, 0, 1], [4, 0, 3, 11, 2, 46, 0, 3, 2, 1], [0, 0, 0, 0, 1, 1, 54, 1, 1, 1], [4, 0, 1, 1, 0, 0, 0, 76, 1, 0], [9, 22, 0, 1, 2, 0, 16, 2, 127, 1], [1, 0, 1, 27, 0, 0, 0, 4, 0, 120]] |
| 0.1467 | 7.64 | 2400 | 1.4623 | 0.6676 | [[59, 3, 10, 7, 0, 7, 1, 2, 8, 3], [55, 65, 1, 0, 4, 4, 15, 3, 46, 0], [3, 1, 48, 6, 2, 1, 2, 0, 0, 2], [1, 0, 3, 34, 5, 1, 0, 0, 1, 7], [0, 4, 1, 2, 83, 2, 0, 0, 0, 1], [4, 2, 12, 3, 1, 46, 0, 0, 2, 2], [1, 0, 1, 0, 1, 0, 56, 0, 0, 0], [3, 0, 5, 1, 0, 2, 4, 68, 0, 0], [9, 18, 1, 0, 3, 1, 17, 1, 129, 1], [2, 3, 1, 32, 0, 0, 0, 2, 0, 113]] |
| 0.1163 | 7.96 | 2500 | 1.5301 | 0.6819 | [[53, 2, 15, 7, 0, 3, 6, 4, 5, 5], [62, 76, 2, 0, 4, 2, 19, 7, 16, 5], [1, 1, 52, 1, 1, 2, 2, 2, 0, 3], [1, 0, 5, 28, 6, 2, 1, 2, 0, 7], [0, 1, 1, 2, 83, 3, 1, 1, 0, 1], [2, 1, 13, 3, 0, 44, 1, 4, 0, 4], [0, 0, 1, 0, 1, 0, 57, 0, 0, 0], [1, 0, 5, 0, 0, 1, 1, 75, 0, 0], [11, 17, 1, 0, 1, 1, 28, 3, 116, 2], [0, 3, 2, 10, 0, 1, 3, 2, 0, 132]] |
| 0.1087 | 8.28 | 2600 | 1.2231 | 0.7324 | [[62, 6, 5, 6, 0, 0, 2, 2, 12, 5], [32, 102, 0, 0, 2, 1, 12, 3, 41, 0], [3, 2, 45, 4, 1, 3, 3, 0, 0, 4], [5, 0, 3, 29, 3, 0, 0, 0, 3, 9], [1, 5, 0, 4, 73, 2, 1, 1, 4, 2], [5, 3, 3, 6, 1, 43, 0, 3, 3, 5], [0, 0, 1, 0, 1, 0, 57, 0, 0, 0], [1, 0, 5, 1, 0, 0, 1, 72, 3, 0], [3, 21, 0, 1, 1, 0, 9, 1, 142, 2], [1, 0, 1, 6, 0, 0, 0, 1, 0, 144]] |
| 0.1783 | 8.6 | 2700 | 1.1571 | 0.7390 | [[53, 5, 17, 5, 0, 3, 2, 4, 7, 4], [23, 127, 1, 0, 4, 2, 2, 3, 31, 0], [0, 1, 56, 2, 1, 2, 0, 0, 0, 3], [1, 0, 7, 34, 3, 1, 0, 0, 0, 6], [1, 2, 3, 6, 75, 1, 1, 0, 2, 2], [2, 1, 18, 5, 1, 40, 0, 2, 2, 1], [2, 0, 1, 0, 1, 0, 54, 0, 0, 1], [1, 0, 9, 1, 0, 0, 0, 71, 0, 1], [6, 27, 4, 0, 0, 1, 12, 0, 130, 0], [1, 2, 2, 11, 0, 0, 0, 1, 0, 136]] |
| 0.1733 | 8.92 | 2800 | 1.3044 | 0.7190 | [[51, 5, 13, 8, 0, 4, 4, 5, 8, 2], [29, 116, 6, 0, 0, 4, 10, 2, 26, 0], [1, 0, 49, 1, 1, 8, 2, 0, 0, 3], [0, 0, 5, 34, 4, 3, 0, 0, 0, 6], [1, 3, 4, 2, 76, 4, 2, 0, 1, 0], [1, 0, 8, 4, 0, 52, 0, 3, 2, 2], [0, 0, 1, 0, 0, 0, 58, 0, 0, 0], [1, 0, 9, 0, 0, 2, 0, 71, 0, 0], [3, 26, 5, 0, 0, 4, 19, 3, 118, 2], [1, 2, 2, 11, 0, 0, 5, 2, 0, 130]] |
| 0.1275 | 9.24 | 2900 | 1.2416 | 0.7267 | [[66, 6, 8, 5, 0, 4, 3, 3, 4, 1], [53, 111, 0, 0, 4, 1, 4, 3, 17, 0], [3, 1, 48, 3, 1, 5, 2, 0, 0, 2], [5, 1, 3, 27, 5, 2, 0, 2, 1, 6], [1, 2, 0, 1, 85, 0, 1, 0, 2, 1], [5, 0, 5, 6, 0, 50, 2, 3, 1, 0], [0, 0, 1, 0, 1, 0, 57, 0, 0, 0], [3, 0, 3, 0, 0, 2, 1, 74, 0, 0], [13, 34, 0, 1, 0, 1, 11, 1, 119, 0], [7, 0, 1, 14, 0, 0, 3, 2, 0, 126]] |
| 0.1231 | 9.55 | 3000 | 1.4284 | 0.7124 | [[73, 3, 7, 5, 0, 1, 4, 2, 4, 1], [84, 81, 0, 0, 3, 1, 3, 1, 20, 0], [2, 1, 51, 2, 1, 5, 0, 0, 0, 3], [5, 0, 3, 28, 6, 1, 0, 0, 1, 8], [1, 1, 0, 1, 86, 0, 1, 0, 2, 1], [9, 0, 6, 4, 1, 46, 1, 3, 2, 0], [2, 0, 1, 0, 1, 0, 54, 0, 0, 1], [10, 0, 1, 0, 0, 0, 1, 71, 0, 0], [21, 23, 1, 0, 0, 2, 12, 2, 119, 0], [7, 0, 1, 4, 0, 0, 0, 2, 0, 139]] |
| 0.1828 | 9.87 | 3100 | 1.2049 | 0.7524 | [[66, 2, 13, 7, 0, 0, 2, 1, 7, 2], [38, 115, 1, 0, 4, 0, 4, 2, 28, 1], [1, 0, 52, 2, 1, 4, 2, 0, 0, 3], [3, 0, 4, 35, 5, 0, 0, 0, 1, 4], [0, 1, 1, 5, 83, 0, 1, 0, 1, 1], [4, 1, 12, 6, 3, 41, 1, 2, 2, 0], [0, 0, 1, 0, 0, 0, 58, 0, 0, 0], [5, 0, 5, 0, 0, 0, 1, 72, 0, 0], [11, 24, 1, 0, 0, 0, 10, 1, 132, 1], [3, 0, 2, 9, 0, 0, 1, 2, 0, 136]] |
| 0.083 | 10.19 | 3200 | 1.2484 | 0.7238 | [[57, 5, 16, 5, 1, 1, 7, 2, 3, 3], [30, 127, 0, 0, 1, 2, 11, 3, 18, 1], [0, 0, 52, 3, 1, 5, 2, 0, 0, 2], [4, 0, 5, 30, 5, 1, 0, 0, 0, 7], [1, 1, 0, 4, 84, 0, 1, 0, 1, 1], [3, 1, 9, 4, 1, 48, 2, 1, 2, 1], [0, 0, 1, 0, 0, 0, 57, 0, 0, 1], [4, 0, 7, 0, 0, 0, 3, 69, 0, 0], [9, 27, 1, 0, 0, 1, 32, 0, 109, 1], [2, 1, 2, 16, 0, 0, 3, 2, 0, 127]] |
| 0.1256 | 10.51 | 3300 | 1.2746 | 0.7229 | [[64, 4, 8, 4, 1, 7, 5, 2, 2, 3], [43, 119, 0, 0, 2, 1, 10, 3, 14, 1], [0, 0, 49, 3, 1, 7, 2, 0, 0, 3], [4, 0, 8, 27, 5, 1, 0, 0, 0, 7], [2, 1, 2, 2, 81, 3, 1, 0, 1, 0], [2, 2, 10, 3, 0, 50, 1, 0, 2, 2], [0, 1, 1, 0, 1, 0, 55, 0, 0, 1], [2, 0, 3, 0, 0, 0, 1, 77, 0, 0], [11, 37, 0, 0, 0, 3, 25, 2, 102, 0], [1, 1, 2, 11, 0, 0, 1, 2, 0, 135]] |
| 0.1067 | 10.83 | 3400 | 1.1905 | 0.7381 | [[55, 3, 11, 9, 1, 2, 7, 2, 6, 4], [35, 122, 0, 0, 1, 1, 6, 2, 25, 1], [2, 1, 50, 2, 1, 3, 4, 0, 0, 2], [2, 0, 4, 37, 4, 0, 0, 0, 0, 5], [0, 1, 1, 4, 82, 2, 1, 0, 1, 1], [2, 1, 13, 6, 0, 44, 1, 0, 1, 4], [0, 1, 1, 0, 0, 0, 56, 0, 0, 1], [1, 0, 3, 1, 0, 0, 1, 76, 0, 1], [9, 36, 0, 0, 0, 1, 20, 2, 112, 0], [0, 0, 2, 10, 0, 0, 0, 0, 0, 141]] |
| 0.092 | 11.15 | 3500 | 1.1175 | 0.7476 | [[65, 3, 8, 2, 0, 4, 5, 2, 9, 2], [27, 108, 0, 0, 1, 1, 8, 2, 46, 0], [4, 0, 49, 2, 1, 4, 3, 0, 0, 2], [2, 0, 3, 37, 4, 0, 0, 0, 1, 5], [0, 1, 1, 3, 83, 2, 1, 0, 1, 1], [6, 2, 8, 6, 0, 45, 1, 0, 1, 3], [0, 0, 1, 0, 0, 0, 56, 0, 1, 1], [3, 0, 2, 1, 0, 1, 3, 72, 0, 1], [10, 22, 0, 0, 0, 1, 12, 1, 134, 0], [1, 0, 1, 12, 0, 1, 2, 0, 0, 136]] |
| 0.153 | 11.46 | 3600 | 1.2434 | 0.7362 | [[75, 4, 9, 1, 0, 1, 2, 3, 4, 1], [51, 111, 0, 1, 1, 1, 1, 3, 24, 0], [2, 1, 52, 2, 1, 3, 0, 2, 0, 2], [4, 1, 6, 30, 4, 0, 0, 1, 0, 6], [1, 4, 1, 4, 80, 0, 1, 1, 0, 1], [6, 4, 8, 6, 1, 39, 0, 1, 2, 5], [2, 1, 1, 1, 1, 0, 52, 0, 0, 1], [2, 0, 1, 0, 0, 0, 0, 80, 0, 0], [15, 33, 0, 0, 1, 1, 11, 3, 114, 2], [1, 0, 1, 7, 2, 0, 1, 1, 0, 140]] |
| 0.1065 | 11.78 | 3700 | 1.2327 | 0.7371 | [[69, 2, 10, 2, 0, 2, 6, 3, 5, 1], [44, 109, 2, 0, 0, 2, 5, 3, 28, 0], [2, 1, 50, 2, 1, 4, 2, 1, 0, 2], [4, 0, 4, 32, 4, 2, 0, 1, 1, 4], [1, 2, 2, 6, 76, 2, 1, 1, 2, 0], [2, 1, 11, 4, 0, 47, 2, 1, 2, 2], [0, 0, 1, 0, 0, 0, 58, 0, 0, 0], [2, 0, 4, 0, 0, 0, 1, 76, 0, 0], [9, 27, 0, 0, 0, 1, 13, 1, 128, 1], [2, 2, 2, 13, 0, 0, 4, 1, 0, 129]] |
| 0.0875 | 12.1 | 3800 | 1.2357 | 0.7457 | [[67, 3, 10, 5, 0, 3, 1, 3, 6, 2], [40, 110, 0, 0, 1, 1, 4, 3, 34, 0], [1, 1, 51, 2, 1, 3, 1, 2, 0, 3], [3, 0, 4, 35, 4, 1, 0, 1, 0, 4], [0, 2, 1, 5, 78, 3, 1, 1, 1, 1], [1, 2, 12, 4, 0, 45, 2, 4, 1, 1], [0, 0, 1, 0, 1, 0, 56, 0, 0, 1], [2, 0, 2, 0, 0, 0, 1, 78, 0, 0], [9, 26, 0, 0, 1, 1, 12, 1, 129, 1], [0, 0, 2, 13, 0, 0, 3, 1, 0, 134]] |
| 0.0714 | 12.42 | 3900 | 1.2996 | 0.7305 | [[77, 3, 7, 3, 0, 1, 2, 2, 4, 1], [58, 103, 0, 0, 0, 1, 4, 1, 26, 0], [4, 1, 51, 2, 1, 3, 1, 0, 0, 2], [4, 0, 4, 33, 6, 0, 0, 0, 0, 5], [3, 1, 4, 3, 77, 2, 1, 0, 1, 1], [5, 2, 14, 6, 0, 44, 0, 0, 0, 1], [2, 1, 1, 0, 1, 0, 53, 0, 0, 1], [7, 0, 7, 0, 0, 0, 0, 69, 0, 0], [14, 28, 0, 0, 0, 1, 12, 1, 124, 0], [2, 0, 1, 11, 0, 3, 0, 0, 0, 136]] |
| 0.1433 | 12.74 | 4000 | 1.2167 | 0.7410 | [[74, 4, 9, 3, 0, 2, 1, 2, 4, 1], [42, 114, 0, 0, 1, 1, 3, 3, 29, 0], [4, 0, 49, 2, 1, 5, 2, 0, 0, 2], [4, 0, 4, 31, 6, 2, 0, 0, 0, 5], [0, 1, 2, 2, 86, 0, 1, 0, 0, 1], [7, 2, 9, 6, 0, 46, 1, 0, 0, 1], [2, 1, 1, 0, 1, 0, 53, 0, 0, 1], [3, 0, 5, 0, 0, 0, 0, 75, 0, 0], [9, 34, 0, 0, 1, 2, 11, 1, 120, 2], [3, 0, 1, 16, 0, 1, 2, 0, 0, 130]] |
| 0.0765 | 13.06 | 4100 | 1.2837 | 0.7381 | [[69, 4, 10, 3, 0, 4, 4, 2, 3, 1], [48, 105, 0, 0, 2, 1, 6, 3, 28, 0], [3, 0, 50, 1, 1, 6, 2, 0, 0, 2], [4, 0, 5, 31, 6, 1, 0, 0, 0, 5], [0, 1, 1, 4, 82, 2, 1, 1, 0, 1], [3, 2, 10, 5, 0, 47, 2, 2, 0, 1], [0, 1, 1, 0, 1, 0, 55, 0, 0, 1], [2, 0, 3, 0, 0, 0, 0, 78, 0, 0], [10, 30, 0, 0, 1, 2, 16, 1, 118, 2], [1, 0, 1, 8, 0, 2, 0, 1, 0, 140]] |
| 0.0753 | 13.38 | 4200 | 1.2866 | 0.7371 | [[72, 4, 9, 2, 0, 3, 3, 2, 4, 1], [46, 110, 0, 0, 1, 1, 5, 3, 27, 0], [3, 0, 51, 1, 1, 6, 1, 0, 0, 2], [4, 0, 5, 30, 6, 1, 0, 0, 0, 6], [0, 1, 2, 3, 80, 2, 1, 1, 2, 1], [7, 2, 8, 4, 0, 49, 0, 0, 1, 1], [0, 1, 1, 0, 1, 0, 55, 0, 0, 1], [2, 0, 4, 0, 0, 1, 0, 76, 0, 0], [9, 34, 1, 0, 1, 1, 12, 1, 120, 1], [7, 1, 1, 9, 0, 3, 0, 1, 0, 131]] |
| 0.0766 | 13.69 | 4300 | 1.3334 | 0.7324 | [[68, 5, 9, 5, 0, 2, 3, 3, 3, 2], [53, 106, 0, 0, 1, 1, 6, 4, 22, 0], [2, 0, 54, 1, 1, 4, 1, 0, 0, 2], [3, 0, 5, 34, 4, 1, 0, 0, 0, 5], [0, 2, 1, 4, 79, 2, 2, 1, 1, 1], [4, 2, 10, 4, 0, 47, 1, 2, 1, 1], [0, 1, 1, 0, 1, 0, 55, 0, 0, 1], [2, 0, 3, 0, 0, 0, 1, 77, 0, 0], [10, 37, 0, 0, 1, 1, 13, 1, 115, 2], [5, 0, 1, 11, 0, 1, 0, 1, 0, 134]] |
| 0.0699 | 14.01 | 4400 | 1.3905 | 0.7276 | [[66, 3, 8, 5, 0, 2, 3, 5, 6, 2], [59, 94, 0, 0, 1, 1, 5, 5, 28, 0], [2, 0, 53, 1, 1, 4, 1, 1, 0, 2], [4, 0, 5, 33, 5, 0, 0, 1, 0, 4], [0, 1, 2, 4, 79, 2, 2, 1, 1, 1], [3, 1, 13, 5, 0, 44, 1, 3, 1, 1], [0, 0, 1, 0, 1, 0, 56, 0, 0, 1], [2, 0, 1, 0, 0, 0, 1, 79, 0, 0], [10, 27, 0, 0, 1, 1, 12, 2, 125, 2], [5, 0, 1, 11, 0, 0, 0, 1, 0, 135]] |
| 0.1218 | 14.33 | 4500 | 1.3635 | 0.7324 | [[68, 3, 8, 4, 0, 1, 3, 4, 7, 2], [58, 92, 0, 0, 1, 1, 5, 4, 32, 0], [1, 0, 54, 1, 1, 4, 1, 0, 0, 3], [4, 0, 5, 33, 5, 0, 0, 0, 0, 5], [0, 1, 2, 4, 80, 3, 2, 1, 0, 0], [2, 1, 13, 4, 0, 44, 2, 3, 1, 2], [0, 0, 1, 0, 1, 0, 56, 0, 0, 1], [2, 0, 1, 0, 0, 0, 1, 79, 0, 0], [9, 26, 0, 0, 1, 1, 15, 1, 126, 1], [4, 0, 1, 10, 0, 0, 0, 1, 0, 137]] |
| 0.0648 | 14.65 | 4600 | 1.3205 | 0.7343 | [[66, 3, 9, 5, 0, 2, 3, 3, 7, 2], [52, 95, 0, 0, 2, 1, 6, 4, 33, 0], [3, 1, 52, 1, 1, 3, 2, 0, 0, 2], [4, 0, 5, 33, 5, 0, 0, 0, 0, 5], [0, 2, 1, 3, 83, 1, 2, 1, 0, 0], [2, 2, 13, 4, 0, 44, 2, 2, 1, 2], [0, 0, 1, 0, 1, 0, 56, 0, 0, 1], [2, 0, 2, 0, 0, 0, 1, 78, 0, 0], [9, 26, 0, 0, 1, 1, 14, 1, 127, 1], [3, 0, 1, 10, 0, 0, 1, 1, 0, 137]] |
| 0.0917 | 14.97 | 4700 | 1.3112 | 0.7343 | [[66, 3, 9, 5, 0, 2, 3, 3, 7, 2], [52, 98, 0, 0, 2, 1, 6, 4, 30, 0], [3, 1, 52, 1, 1, 3, 2, 0, 0, 2], [4, 0, 5, 33, 5, 0, 0, 0, 0, 5], [0, 2, 1, 3, 83, 1, 2, 1, 0, 0], [2, 2, 13, 4, 0, 44, 2, 2, 1, 2], [0, 0, 1, 0, 1, 0, 56, 0, 0, 1], [2, 0, 2, 0, 0, 0, 1, 78, 0, 0], [9, 28, 0, 0, 1, 1, 15, 1, 124, 1], [3, 0, 1, 10, 0, 1, 0, 1, 0, 137]] |
### Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2
| {"license": "apache-2.0", "tags": ["image-classification", "generated_from_trainer"], "datasets": ["imagefolder"], "metrics": ["accuracy"], "base_model": "google/vit-base-patch16-224-in21k", "model-index": [{"name": "Action_Classification", "results": [{"task": {"type": "image-classification", "name": "Image Classification"}, "dataset": {"name": "agent_action_class", "type": "imagefolder", "config": "default", "split": "train", "args": "default"}, "metrics": [{"type": "accuracy", "value": 0.7628571428571429, "name": "Accuracy"}]}]}]} | Raihan004/Action_Classification | null | [
"transformers",
"tensorboard",
"safetensors",
"vit",
"image-classification",
"generated_from_trainer",
"dataset:imagefolder",
"base_model:google/vit-base-patch16-224-in21k",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T18:56:34+00:00 |
null | null | {} | ACEGameAI/Cory-Wan_ohwx-man | null | [
"region:us"
]
| null | 2024-04-26T18:56:43+00:00 |
|
null | null | {} | Abigaildx18/aModelsXL | null | [
"region:us"
]
| null | 2024-04-26T18:57:00+00:00 |
|
null | null | {"license": "apache-2.0"} | kryme/nft_test | null | [
"license:apache-2.0",
"region:us"
]
| null | 2024-04-26T18:57:27+00:00 |
|
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. -->
# distilbert-rotten_tomatoes
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
### Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "distilbert-base-uncased", "model-index": [{"name": "distilbert-rotten_tomatoes", "results": []}]} | huiang/distilbert-rotten_tomatoes | null | [
"transformers",
"tensorboard",
"safetensors",
"distilbert",
"text-classification",
"generated_from_trainer",
"base_model:distilbert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T18:58:07+00:00 |
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": []} | shallow6414/mp5d4if | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-26T18:58:09+00:00 |
text-generation | transformers |
# Uploaded model
- **Developed by:** kchopra04
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3-8b-Instruct-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
| {"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "llama", "trl"], "base_model": "unsloth/llama-3-8b-Instruct-bnb-4bit"} | kchopra04/lora_model_inst | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"en",
"base_model:unsloth/llama-3-8b-Instruct-bnb-4bit",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"4-bit",
"region:us"
]
| null | 2024-04-26T18:58:54+00:00 |
null | null | {"license": "openrail"} | itskeonagain/reibyleeloli | null | [
"license:openrail",
"region:us"
]
| null | 2024-04-26T18:59:08+00:00 |
|
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. -->
# run
This model is a fine-tuned version of [salangarica/BioMistral-LLM](https://huggingface.co/salangarica/BioMistral-LLM) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3032
## Model description
More information needed
## Intended uses & 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: constant
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 20.0
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.131 | 1.0 | 110 | 0.1747 |
| 0.1903 | 2.0 | 220 | 0.1724 |
| 0.0928 | 3.0 | 330 | 0.2107 |
| 0.0738 | 4.0 | 440 | 0.2131 |
| 0.0735 | 5.0 | 550 | 0.3032 |
### Framework versions
- PEFT 0.8.2
- Transformers 4.38.1
- Pytorch 2.0.0
- Datasets 2.15.0
- Tokenizers 0.15.2 | {"library_name": "peft", "tags": ["trl", "sft", "generated_from_trainer"], "base_model": "salangarica/BioMistral-LLM", "model-index": [{"name": "run", "results": []}]} | salangarica/run | null | [
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:salangarica/BioMistral-LLM",
"region:us"
]
| null | 2024-04-26T18:59:08+00:00 |
text-generation | transformers | {} | mlx-community/OpenELM-3B | null | [
"transformers",
"safetensors",
"openelm",
"text-generation",
"custom_code",
"autotrain_compatible",
"region:us"
]
| null | 2024-04-26T19:01:19+00:00 |
|
null | null | {} | hyu8828/SXZTextureBringerConcept | null | [
"region:us"
]
| null | 2024-04-26T19:05:12+00:00 |
|
null | peft | prompt
```
<original>Ok. What do the drivers look like?</original>
<translate to="th">
```
response
```
<original>กรุงเทพอยู่ที่ไหน</original>
<translate to="en">where is bangkok</translate><eos>
```
code to create dataset
```python
import random
alpaca_prompt = """<original>{}</original>
<translate to="{}">{}"""
BOS_TOKEN = tokenizer.bos_token # Must add EOS_TOKEN
EOS_TOKEN = "</translate>"+tokenizer.eos_token # Must add EOS_TOKEN
def formatting_prompts_func(examples):
translations = examples["translation"]
texts = []
text_en = ""
text_th = ""
translate_to = 'th'
max_group_count = 1
group_count = 0
for translation in translations:
if group_count >= max_group_count:
if(translate_to == 'th'):
text = alpaca_prompt.format(text_en, translate_to, text_th) + EOS_TOKEN
else:
text = alpaca_prompt.format(text_th, translate_to, text_en) + EOS_TOKEN
texts.append(text)
text_en = ""
text_th = ""
max_group_count = random.randint(1, 5)
group_count = 0
translate_to = random.choice(['en', 'th'])
num_newlines = random.randint(1, 5)
newlines = '\n' * num_newlines
if(text_en == ""):
text_en = translation['en']
text_th = translation['th']
else:
text_en = text_en+newlines+translation['en']
text_th = text_th+newlines+translation['th']
group_count = group_count+1
if(translate_to == 'th'):
text = alpaca_prompt.format(text_en, translate_to, text_th) + EOS_TOKEN
else:
text = alpaca_prompt.format(text_th, translate_to, text_en) + EOS_TOKEN
texts.append(text)
return { "text" : texts, }
from datasets import load_dataset
import datasets
# dataset = load_dataset("scb_mt_enth_2020",'enth', download_mode=datasets.DownloadMode.FORCE_REDOWNLOAD,cache_dir ="./cache")
dataset = load_dataset("scb_mt_enth_2020",'enth',cache_dir ="./cache")
dataset = dataset.shuffle(seed=42)
dataset = dataset.map(formatting_prompts_func, batched = True,remove_columns=["translation",'subdataset'])
dataset['train'][0:5]
```
[More Information Needed]
### Framework versions
- PEFT 0.10.0 | {"library_name": "peft", "base_model": "unsloth/gemma-7b-bnb-4bit"} | ping98k/gemma-7b-translator-0.3-lora | null | [
"peft",
"safetensors",
"base_model:unsloth/gemma-7b-bnb-4bit",
"region:us"
]
| null | 2024-04-26T19:06:13+00:00 |
null | null | {} | qiwencui/zephyr-7b-sft-full | null | [
"region:us"
]
| null | 2024-04-26T19:06:53+00:00 |
|
text-generation | transformers |
# Uploaded model
- **Developed by:** kchopra04
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3-8b-Instruct-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
| {"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "llama", "trl"], "base_model": "unsloth/llama-3-8b-Instruct-bnb-4bit"} | kchopra04/llama3-inst-finetuned-saxs | null | [
"transformers",
"pytorch",
"llama",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"conversational",
"en",
"base_model:unsloth/llama-3-8b-Instruct-bnb-4bit",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T19:07:17+00:00 |
null | null |
# Ognoexperiment27multi_verse_modelMeliodas-7B
Ognoexperiment27multi_verse_modelMeliodas-7B is an automated merge created by [Maxime Labonne](https://huggingface.co/mlabonne) using the following configuration.
## 🧩 Configuration
```yaml
models:
- model: mistralai/Mistral-7B-v0.1
- model: automerger/Ognoexperiment27Multi_verse_model-7B
- model: AurelPx/Meliodas-7b-dare
merge_method: model_stock
base_model: mistralai/Mistral-7B-v0.1
dtype: bfloat16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "automerger/Ognoexperiment27multi_verse_modelMeliodas-7B"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
``` | {"license": "apache-2.0", "tags": ["merge", "mergekit", "lazymergekit", "automerger"]} | automerger/Ognoexperiment27multi_verse_modelMeliodas-7B | null | [
"merge",
"mergekit",
"lazymergekit",
"automerger",
"license:apache-2.0",
"region:us"
]
| null | 2024-04-26T19:07:40+00:00 |
text-generation | transformers | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
saiga_llama3_8b - bnb 4bits
- Model creator: https://huggingface.co/IlyaGusev/
- Original model: https://huggingface.co/IlyaGusev/saiga_llama3_8b/
Original model description:
---
language:
- ru
datasets:
- IlyaGusev/saiga_scored
license: other
license_name: llama3
license_link: https://llama.meta.com/llama3/license/
---
# Saiga/Llama3 8B, Russian Llama-3-based chatbot
Based on [Llama-3 8B Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct).
Llama.cpp version: [link](https://huggingface.co/IlyaGusev/saiga_llama3_8b_gguf)
**ОСТОРОЖНО! WARNING! LET OP!**
I've changed the prompt format from ChatML to **the original Llama-3 format in v4**. Don't forget to switch formats!
**v4**: LLama-3 prompt format:
```
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
Ты — Сайга, русскоязычный автоматический ассистент. Ты разговариваешь с людьми и помогаешь им.<|eot_id|><|start_header_id|>user<|end_header_id|>
Как дела?<|eot_id|><|start_header_id|>assistant<|end_header_id|>
Отлично, а у тебя?<|eot_id|><|start_header_id|>user<|end_header_id|>
Шикарно. Как пройти в библиотеку?<|eot_id|><|start_header_id|>assistant<|end_header_id|>
```
**v2, v3**: ChatML prompt format:
```
<|im_start|>system
Ты — Сайга, русскоязычный автоматический ассистент. Ты разговариваешь с людьми и помогаешь им.<|im_end|>
<|im_start|>user
Как дела?<|im_end|>
<|im_start|>assistant
Отлично, а у тебя?<|im_end|>
<|im_start|>user
Шикарно. Как пройти в библиотеку?<|im_end|>
<|im_start|>assistant
```
Examples:
```
User: Почему трава зеленая?
Saiga: Зеленый цвет травы обусловлен наличием хлорофилла, пигмента, который поглощает свет и передает энергию для фотосинтеза. Хлорофилл содержится в клетках листьев растений и играет ключевую роль в процессе фотосинтеза, когда растения используют солнечный свет для превращения воды и углекислого газа в органические вещества, такие как глюкоза и олигоэфиры.
Хлорофилл состоит из двух основных форм: хлорофилла а и хлорофилла б. Хлорофилл а поглощает свет с длиной волны около 430 нанометров (нм), что соответствует синему или голубому свету, а хлорофилл б поглощает свет с длиной волны около 660 нм, что соответствует красному свету. Когда свет поглощается хлорофиллом, он передается в молекулы воды и углекислого газа, которые используются для фотосинтеза.
Таким образом, хлорофилл является основным компонентом, ответственным за зеленый цвет листьев растений, так как он поглощает свет и передает его энергию для фотосинтеза.
```
```
User: Сочини длинный рассказ, обязательно упоминая следующие объекты. Дано: Таня, мяч
Saiga: Однажды в солнечную погоду на поле для игры в футбол приехала группа друзей, чтобы провести время вместе. В числе их был и Таня, которая была страстной футбольной фанаткой и всегда радовал своих друзей своим энтузиазмом и умением забивать мячи.
В этот день, как обычно, друзья решили провести соревнование между собой, чтобы определить кто из них является лучшим футболистом. Таня была очень уверена в своих силах и готовилась к этому матчу с особой серьёзностью.
Когда все друзья собрались на поле, они увидели, что перед ними стоял огромный мяч, который должен был стать предметом состязания. Мяч был огромным и тяжелым, и его размеры были необычайно большими по сравнению с обычными мячами, которые используются в футболе.
Таня была первая, кто решил начать игру. Она подошла к мячу и начала его удерживать, стараясь выдержать его вес и силу. Но мяч оказался настолько тяжелым, что Таня не смогла удержать его и он упал на землю.
Друзья посмеялись над ее неудачей, но Таня не отчаивалась и продолжила пытаться удержать мяч. Она стала использовать все свои силы и умения, чтобы выдержать его вес и силу. Наконец, после долгих усилий, она смогла удержать мяч и начала его бросать в сторону.
Мяч летел высоко вверх, и друзья смотрели, как он пролетает над полем. Но мяч неожиданно повернул и стал лететь обратно к Тане. Она успела поймать его и продолжила играть, используя все свои навыки и умения.
```
v4:
- [1cc945d4ca2c7901cf989e7edaac52ab24f1a7dd](https://huggingface.co/IlyaGusev/saiga_llama3_8b/commit/1cc945d4ca2c7901cf989e7edaac52ab24f1a7dd)
- dataset: [saiga_scored](https://huggingface.co/datasets/IlyaGusev/saiga_scored), scores >= 8, c66032920556c0f21bbbed05e7e04433ec954c3d
- wandb [link](https://wandb.ai/ilyagusev/rulm_self_instruct/runs/dcbs9ttt)
v3:
- [c588356cd60bdee54d52c2dd5a2445acca8aa5c3](https://huggingface.co/IlyaGusev/saiga_llama3_8b/commit/c588356cd60bdee54d52c2dd5a2445acca8aa5c3)
- dataset: [saiga_scored](https://huggingface.co/datasets/IlyaGusev/saiga_scored), scores >= 8, d51cf8060bdc90023da8cf1c3f113f9193d6569b
- wandb [link](https://wandb.ai/ilyagusev/rulm_self_instruct/runs/ltoqdsal)
v2:
- [ae61b4f9b34fac9856d361ea78c66284a00e4f0b](https://huggingface.co/IlyaGusev/saiga_llama3_8b/commit/ae61b4f9b34fac9856d361ea78c66284a00e4f0b)
- dataset code revision d0d123dd221e10bb2a3383bcb1c6e4efe1b4a28a
- wandb [link](https://wandb.ai/ilyagusev/huggingface/runs/r6u5juyk)
- 5 datasets: ru_turbo_saiga, ru_sharegpt_cleaned, oasst1_ru_main_branch, gpt_roleplay_realm, ru_instruct_gpt4
- Datasets merging script: [create_short_chat_set.py](https://github.com/IlyaGusev/rulm/blob/d0d123dd221e10bb2a3383bcb1c6e4efe1b4a28a/self_instruct/src/data_processing/create_short_chat_set.py)
# Evaluation
* Dataset: https://github.com/IlyaGusev/rulm/blob/master/self_instruct/data/tasks.jsonl
* Framework: https://github.com/tatsu-lab/alpaca_eval
* Evaluator: alpaca_eval_cot_gpt4_turbo_fn
| model | length_controlled_winrate | win_rate | standard_error | avg_length |
|-----|-----|-----|-----|-----|
|chatgpt_4_turbo | 76.04 | 90.00 |1.46 | 1270 |
|chatgpt_3_5_turbo | 50.00 | 50.00 | 0.00 | 536 |
|saiga_llama3_8b, v4 | 43.64 | 65.90 | 2.31 | 1200 |
|saiga_llama3_8b, v3 | 36.97 | 61.08 | 2.38 | 1162 |
|saiga_llama3_8b, v2 | 33.07 | 48.19 | 2.45 | 1166 |
|saiga_mistral_7b | 23.38 | 35.99 | 2.34 | 949 |
| {} | RichardErkhov/IlyaGusev_-_saiga_llama3_8b-4bits | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"4-bit",
"region:us"
]
| null | 2024-04-26T19:07:43+00:00 |
text-generation | transformers | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
saiga_gemma_9b - bnb 4bits
- Model creator: https://huggingface.co/IlyaGusev/
- Original model: https://huggingface.co/IlyaGusev/saiga_gemma_9b/
Original model description:
---
language:
- ru
datasets:
- IlyaGusev/ru_turbo_saiga
- IlyaGusev/ru_sharegpt_cleaned
- IlyaGusev/oasst1_ru_main_branch
- IlyaGusev/gpt_roleplay_realm
- lksy/ru_instruct_gpt4
---
# Saiga/Gemma 9B, Russian Gemma-based chatbot
Based on [Gemma 7B](https://huggingface.co/google/gemma-7b).
Training Colab: [link](https://colab.research.google.com/drive/1O7F7Q3IQYh-v7EfsdRwMDMfUnOYZ3DEh).
ChatML prompt format:
```
<|im_start|>system
Ты — Сайга, русскоязычный автоматический ассистент. Ты разговариваешь с людьми и помогаешь им.<|im_end|>
<|im_start|>user
Привет!<|im_end|>
<|im_start|>assistant
Отлично, а ты?<|im_end|>
<|im_start|>user
Шикарно. Как пройти в библиотеку?<|im_end|>
<|im_start|>assistant
```
Examples:
```
User: Почему трава зеленая?
Saiga: Зеленый цвет травы обусловлен наличием в её клетках пигмента хлорофилла, который играет важную роль в процессе фотосинтеза – преобразования солнечного света в энергию, используемую для роста и развития растений.
Хлорофилл поглощает свет в определенных диапазонах длин волн, в том числе в зеленой области спектра, и отражает свет в других диапазонах, что и обуславливает зелёный цвет.
```
```
User: Сочини длинный рассказ, обязательно упоминая следующие объекты. Дано: Таня, мяч
Saiga: Однажды, в далекой стране, жила маленькая девочка по имени Таня. Она была очень активной и любила играть в мяч. Вместе со своими друзьями они проводили дни, играя в футбол, баскетбол и волейбол.
Таня была очень талантливой и ловкой, и она часто выигрывала в играх с другими детьми. Но однажды, во время игры в баскетбол, она получила сильную травму. Ей пришлось провести несколько недель в больнице, и она была очень грустной и унылой.
Её друзья не могли понять, как помочь Тане справиться с этой ситуацией. Они пытались поддерживать её, но Таня была слишком подавлена и не хотела играть в мяч.
Однажды, Таня увидела, как её друзья играют в мяч. Она не могла не смотреть, как они ловко передают мяч друг другу и забивают голы. Таня почувствовала, как её сердце разрывается от желания играть вместе с ними.
Она решила, что ей нужно вернуться в игру, чтобы снова почувствовать радость игры. Она начала медленно восстанавливаться и постепенно возвращалась к своему любимому занятию - игре в мяч.
Таня стала играть в мяч снова, но теперь она была более осторожна и внимательна к своему здоровью. Её друзья были очень рады видеть, как Таня возвращается к своей привычной жизни.
С тех пор, Таня стала настоящей звездой на поле. Она стала лучшей игроком в своей команде и помогла им выиграть множество игр. Её друзья были горды, что Таня вернулась к своему любимому занятию и снова стала такой же активной и ловкой, как раньше.
Таня и её друзья продолжали играть в мяч и проводили чудесные дни вместе. Они были счастливы, что Таня вернулась к своему любимому занятию и снова стала частью команды.
Таня и её друзья продолжают играть в мяч и вместе они создают прекрасные воспоминания.
```
v1:
- dataset code revision d0d123dd221e10bb2a3383bcb1c6e4efe1b4a28a
- wandb [link](https://wandb.ai/ilyagusev/gemma_test/runs/k7u3uw5i)
- 5 datasets: ru_turbo_saiga, ru_sharegpt_cleaned, oasst1_ru_main_branch, gpt_roleplay_realm, ru_instruct_gpt4
- Datasets merging script: [create_short_chat_set.py](https://github.com/IlyaGusev/rulm/blob/d0d123dd221e10bb2a3383bcb1c6e4efe1b4a28a/self_instruct/src/data_processing/create_short_chat_set.py)
| {} | RichardErkhov/IlyaGusev_-_saiga_gemma_9b-4bits | null | [
"transformers",
"safetensors",
"gemma",
"text-generation",
"conversational",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"4-bit",
"region:us"
]
| null | 2024-04-26T19:08:06+00:00 |
image-text-to-text | null |
A [llamafile](https://github.com/Mozilla-Ocho/llamafile) generated for [moondream2](https://huggingface.co/vikhyatk/moondream2)
Big thanks to [@jartine](https://huggingface.co/jartine) and [@vikhyat](https://huggingface.co/vikhyatk/moondream2) for their respective works on llamafile and moondream
## How to Run (on macos and linux)
1. Download moondream2.llamafile
2. `chmod +x moondream2.llamafile` - make it executable
3. `./moondream2.llamafile` - run the llama.cpp server
## Versions
1. [Q5_M](https://huggingface.co/cjpais/moondream2-llamafile/resolve/main/moondream2-q5_k.llamafile?download=true)
2. [Q8_0](https://huggingface.co/cjpais/moondream2-llamafile/resolve/main/moondream2-q8.llamafile?download=true)
From my short testing the Q8 is noticeably better.
# ORIGINAL MODEL CARD
moondream2 is a small vision language model designed to run efficiently on edge devices. Check out the [GitHub repository](https://github.com/vikhyat/moondream) for details, or try it out on the [Hugging Face Space](https://huggingface.co/spaces/vikhyatk/moondream2)!
**Benchmarks**
| Release | VQAv2 | GQA | TextVQA | TallyQA (simple) | TallyQA (full) |
| --- | --- | --- | --- | --- | --- |
| 2024-03-04 | 74.2 | 58.5 | 36.4 | - | - |
| 2024-03-06 | 75.4 | 59.8 | 43.1 | 79.5 | 73.2 |
| 2024-03-13 | 76.8 | 60.6 | 46.4 | 79.6 | 73.3 |
| **2024-04-02** (latest) | 77.7 | 61.7 | 49.7 | 80.1 | 74.2 |
**Usage**
```bash
pip install transformers einops
```
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
from PIL import Image
model_id = "vikhyatk/moondream2"
revision = "2024-04-02"
model = AutoModelForCausalLM.from_pretrained(
model_id, trust_remote_code=True, revision=revision
)
tokenizer = AutoTokenizer.from_pretrained(model_id, revision=revision)
image = Image.open('<IMAGE_PATH>')
enc_image = model.encode_image(image)
print(model.answer_question(enc_image, "Describe this image.", tokenizer))
```
The model is updated regularly, so we recommend pinning the model version to a
specific release as shown above. | {"license": "apache-2.0", "tags": ["llamafile"], "quantized_by": "cjpais", "base_model": "vikhyatk/moondream2", "pipeline_tag": "image-text-to-text"} | cjpais/moondream2-llamafile | null | [
"llamafile",
"image-text-to-text",
"base_model:vikhyatk/moondream2",
"license:apache-2.0",
"region:us"
]
| null | 2024-04-26T19:08:17+00:00 |
text-generation | transformers | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
Starling-LM-7B-beta - bnb 4bits
- Model creator: https://huggingface.co/Nexusflow/
- Original model: https://huggingface.co/Nexusflow/Starling-LM-7B-beta/
Original model description:
---
license: apache-2.0
datasets:
- berkeley-nest/Nectar
language:
- en
library_name: transformers
tags:
- reward model
- RLHF
- RLAIF
---
# Starling-LM-7B-beta
<!-- Provide a quick summary of what the model is/does. -->
- **Developed by: The Nexusflow Team (** Banghua Zhu * , Evan Frick * , Tianhao Wu * , Hanlin Zhu, Karthik Ganesan, Wei-Lin Chiang, Jian Zhang, and Jiantao Jiao).
- **Model type:** Language Model finetuned with RLHF / RLAIF
- **License:** Apache-2.0 license under the condition that the model is not used to compete with OpenAI
- **Finetuned from model:** [Openchat-3.5-0106](https://huggingface.co/openchat/openchat-3.5-0106) (based on [Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1))
We introduce Starling-LM-7B-beta, an open large language model (LLM) trained by Reinforcement Learning from AI Feedback (RLAIF). Starling-LM-7B-beta is trained from [Openchat-3.5-0106](https://huggingface.co/openchat/openchat-3.5-0106) with our new reward model [Nexusflow/Starling-RM-34B](https://huggingface.co/Nexusflow/Starling-RM-34B) and policy optimization method [Fine-Tuning Language Models from Human Preferences (PPO)](https://arxiv.org/abs/1909.08593).
Harnessing the power of the ranking dataset, [berkeley-nest/Nectar](https://huggingface.co/datasets/berkeley-nest/Nectar), the upgraded reward model, [Starling-RM-34B](https://huggingface.co/Nexusflow/Starling-RM-34B), and the new reward training and policy tuning pipeline, Starling-LM-7B-beta scores an improved 8.12 in MT Bench with GPT-4 as a judge.
## 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. -->
**Important: Please use the exact chat template provided below for the model. Otherwise there will be a degradation in the performance. The model output can be verbose in rare cases. Please consider setting temperature = 0 to make this happen less.**
Our model follows the exact chat template and usage as [Openchat-3.5-0106](https://huggingface.co/openchat/openchat-3.5-0106). Please refer to their model card for more details.
In addition, our model is hosted on LMSYS [Chatbot Arena](https://chat.lmsys.org) for free test.
The conversation template is the same as Openchat-3.5-0106:
```
import transformers
tokenizer = transformers.AutoTokenizer.from_pretrained("openchat/openchat-3.5-0106")
# Single-turn
tokens = tokenizer("GPT4 Correct User: Hello<|end_of_turn|>GPT4 Correct Assistant:").input_ids
assert tokens == [1, 420, 6316, 28781, 3198, 3123, 1247, 28747, 22557, 32000, 420, 6316, 28781, 3198, 3123, 21631, 28747]
# Multi-turn
tokens = tokenizer("GPT4 Correct User: Hello<|end_of_turn|>GPT4 Correct Assistant: Hi<|end_of_turn|>GPT4 Correct User: How are you today?<|end_of_turn|>GPT4 Correct Assistant:").input_ids
assert tokens == [1, 420, 6316, 28781, 3198, 3123, 1247, 28747, 22557, 32000, 420, 6316, 28781, 3198, 3123, 21631, 28747, 15359, 32000, 420, 6316, 28781, 3198, 3123, 1247, 28747, 1602, 460, 368, 3154, 28804, 32000, 420, 6316, 28781, 3198, 3123, 21631, 28747]
# Coding Mode
tokens = tokenizer("Code User: Implement quicksort using C++<|end_of_turn|>Code Assistant:").input_ids
assert tokens == [1, 7596, 1247, 28747, 26256, 2936, 7653, 1413, 334, 1680, 32000, 7596, 21631, 28747]
```
## Code Examples
```python
import transformers
tokenizer = transformers.AutoTokenizer.from_pretrained("Nexusflow/Starling-LM-7B-beta")
model = transformers.AutoModelForCausalLM.from_pretrained("Nexusflow/Starling-LM-7B-beta")
def generate_response(prompt):
input_ids = tokenizer(prompt, return_tensors="pt").input_ids
outputs = model.generate(
input_ids,
max_length=256,
pad_token_id=tokenizer.pad_token_id,
eos_token_id=tokenizer.eos_token_id,
)
response_ids = outputs[0]
response_text = tokenizer.decode(response_ids, skip_special_tokens=True)
return response_text
# Single-turn conversation
prompt = "Hello, how are you?"
single_turn_prompt = f"GPT4 Correct User: {prompt}<|end_of_turn|>GPT4 Correct Assistant:"
response_text = generate_response(single_turn_prompt)
print("Response:", response_text)
## Multi-turn conversation
prompt = "Hello"
follow_up_question = "How are you today?"
response = ""
multi_turn_prompt = f"GPT4 Correct User: {prompt}<|end_of_turn|>GPT4 Correct Assistant: {response}<|end_of_turn|>GPT4 Correct User: {follow_up_question}<|end_of_turn|>GPT4 Correct Assistant:"
response_text = generate_response(multi_turn_prompt)
print("Multi-turn conversation response:", response_text)
### Coding conversation
prompt = "Implement quicksort using C++"
coding_prompt = f"Code User: {prompt}<|end_of_turn|>Code Assistant:"
response = generate_response(coding_prompt)
print("Coding conversation response:", response)
```
## License
The dataset, model and online demo is subject to the [Terms of Use](https://openai.com/policies/terms-of-use) of the data generated by OpenAI, and [Privacy Practices](https://chrome.google.com/webstore/detail/sharegpt-share-your-chatg/daiacboceoaocpibfodeljbdfacokfjb) of ShareGPT. Please contact us if you find any potential violation.
## Acknowledgment
We would like to thank Tianle Li from UC Berkeley for detailed feedback and evaluation of this beta release. We would like to thank the [LMSYS Organization](https://lmsys.org/) for their support of [lmsys-chat-1M](https://huggingface.co/datasets/lmsys/lmsys-chat-1m) dataset, evaluation and online demo. We would like to thank the open source community for their efforts in providing the datasets and base models we used to develope the project, including but not limited to Anthropic, Llama, Mistral, Hugging Face H4, LMSYS, OpenChat, OpenBMB, Flan and ShareGPT.
## Citation
```
@misc{starling2023,
title = {Starling-7B: Improving LLM Helpfulness & Harmlessness with RLAIF},
url = {},
author = {Zhu, Banghua and Frick, Evan and Wu, Tianhao and Zhu, Hanlin and Ganesan, Karthik and Chiang, Wei-Lin and Zhang, Jian and Jiao, Jiantao},
month = {November},
year = {2023}
}
```
| {} | RichardErkhov/Nexusflow_-_Starling-LM-7B-beta-4bits | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"arxiv:1909.08593",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"4-bit",
"region:us"
]
| null | 2024-04-26T19:08:24+00:00 |
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. -->
# results
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4741
- Accuracy: 0.5251
- F1: 0.5348
- Precision: 0.5692
- Recall: 0.5251
## Model description
More information needed
## Intended uses & 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: 4
- eval_batch_size: 8
- 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: 1
### Training results
### Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Tokenizers 0.19.1
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "metrics": ["accuracy", "f1", "precision", "recall"], "base_model": "bert-base-uncased", "model-index": [{"name": "results", "results": []}]} | Shreyagg2202/Bert-Custom-Sentiment-Analysis | null | [
"transformers",
"safetensors",
"bert",
"text-classification",
"generated_from_trainer",
"base_model:bert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T19:08:47+00:00 |
null | null | {} | mahmoud271/parkk_detect | null | [
"region:us"
]
| null | 2024-04-26T19:08:56+00:00 |
|
null | null | {} | iamalexcaspian/Casey-TheCasagrandes-ChristianSimon | null | [
"region:us"
]
| null | 2024-04-26T19:10:24+00:00 |
|
text-generation | transformers | prompt
```
<original>Ok. What do the drivers look like?</original>
<translate to="th">
```
response
```
<original>กรุงเทพอยู่ที่ไหน</original>
<translate to="en">where is bangkok</translate><eos>
```
this model is fail to follow format and output other html (`</input`) sometime at end of text
```
<original>ตำราเรียน (อังกฤษ: Textbook) คือหนังสือที่ใช้ในการศึกษาหาความรู้จากวิชาต่าง ๆ ผู้คนมักใช้ตำราเรียนในการเรียนรู้ข้อเท็จจริงและวิธีการที่เกี่ยวข้องกับรายวิชานั้น ๆ ในบางครั้งตำราเรียนมักมีคำถามเพื่อทดสอบความรู้และความเข้าใจของผู้อ่าน ตำราเรียนจะถูกผลิตจากความต้องการของสถาบันการศึกษา ตำราเรียนส่วนมากมักมีลักษณะเป็นสิ่งพิมพ์ แต่ในปัจจุบันพบว่าหลาย ๆ ตำราเรียนสามารถเข้าถึงได้โดยการออนไลน์ ในรูปแบบของหนังสืออิเล็กทรอนิกส์</original>
<translate to="en">Textbooks are books that contain the content of a subject, typically written from an academic viewpoint and intended for use by students. In some countries textbooks can be called "school-book", while in other places they may simply go under this title.</input
``` | {"language": ["th", "en"], "datasets": ["scb_mt_enth_2020"], "pipeline_tag": "text-generation"} | ping98k/gemma-7b-translator-0.3 | null | [
"transformers",
"safetensors",
"gguf",
"gemma",
"text-generation",
"th",
"en",
"dataset:scb_mt_enth_2020",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-26T19:10:39+00:00 |
null | null |
<div align="center">
<img width="260px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/BrQCb95lmEIFz79QAmoNA.png"></div>
<div align="center">
<h1>Advancing Open-source Large Language Models in Medical Domain</h1>
</div>
<p align="center" style="margin-top: 0px;">
<a href="https://colab.research.google.com/drive/1F5oV20InEYeAJGmBwYF9NM_QhLmjBkKJ?usp=sharing">
<img src="https://colab.research.google.com/assets/colab-badge.svg" alt="OpenChat Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 10px; margin-top: 0px; margin-bottom: 0px;"/>
<span class="link-text" style=" margin-right: 5px;">Online Demo</span>
</a> |
<a href="https://github.com/openlifescience-ai">
<img src="https://github.githubassets.com/assets/GitHub-Mark-ea2971cee799.png" alt="GitHub Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/>
<span class="link-text" style=" margin-right: 5px;">GitHub</span>
</a> |
<a href="#">
<img src="https://github.com/alpayariyak/openchat/blob/master/assets/arxiv-logomark-small-square-border.png?raw=true" alt="ArXiv Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/>
<span class="link-text" style="margin-right: 5px;">Paper</span>
</a> |
<a href="https://discord.gg/A5Fjf5zC69">
<img src="https://cloud.githubusercontent.com/assets/6291467/26705903/96c2d66e-477c-11e7-9f4e-f3c0efe96c9a.png" alt="Discord Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/>
<span class="link-text">Discord</span>
</a>
</p>
Introducing OpenBioLLM-8B: A State-of-the-Art Open Source Biomedical Large Language Model
OpenBioLLM-8B is an advanced open source language model designed specifically for the biomedical domain. Developed by Saama AI Labs, this model leverages cutting-edge techniques to achieve state-of-the-art performance on a wide range of biomedical tasks.
🏥 **Biomedical Specialization**: OpenBioLLM-8B is tailored for the unique language and knowledge requirements of the medical and life sciences fields. It was fine-tuned on a vast corpus of high-quality biomedical data, enabling it to understand and generate text with domain-specific accuracy and fluency.
🎓 **Superior Performance**: With 8 billion parameters, OpenBioLLM-8B outperforms other open source biomedical language models of similar scale. It has also demonstrated better results compared to larger proprietary & open-source models like GPT-3.5 and Meditron-70B on biomedical benchmarks.
🧠 **Advanced Training Techniques**: OpenBioLLM-8B builds upon the powerful foundations of the **Meta-Llama-3-8B** and [Meta-Llama-3-8B](meta-llama/Meta-Llama-3-8B) models. It incorporates the DPO dataset and fine-tuning recipe along with a custom diverse medical instruction dataset. Key components of the training pipeline include:
<div align="center">
<img width="1200px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/oPchsJsEpQoGcGXVbh7YS.png">
</div>
- **Policy Optimization**: [Direct Preference Optimization: Your Language Model is Secretly a Reward Model (DPO)](https://arxiv.org/abs/2305.18290)
- **Ranking Dataset**: [berkeley-nest/Nectar](https://huggingface.co/datasets/berkeley-nest/Nectar)
- **Fine-tuning dataset**: Custom Medical Instruct dataset (We plan to release a sample training dataset in our upcoming paper; please stay updated)
This combination of cutting-edge techniques enables OpenBioLLM-8B to align with key capabilities and preferences for biomedical applications.
⚙️ **Release Details**:
- **Model Size**: 8 billion parameters
- **Quantization**: Optimized quantized versions available [Here](https://huggingface.co/aaditya/OpenBioLLM-8B-GGUF)
- **Language(s) (NLP):** en
- **Developed By**: [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) from Saama AI Labs
- **License:** Meta-Llama License
- **Fine-tuned from models:** [meta-llama/Meta-Llama-3-8B](meta-llama/Meta-Llama-3-8B)
- **Resources for more information:**
- Paper: Coming soon
The model can be fine-tuned for more specialized tasks and datasets as needed.
OpenBioLLM-8B represents an important step forward in democratizing advanced language AI for the biomedical community. By leveraging state-of-the-art architectures and training techniques from leading open source efforts like Llama-3, we have created a powerful tool to accelerate innovation and discovery in healthcare and the life sciences.
We are excited to share OpenBioLLM-8B with researchers and developers around the world.
### Use with transformers
**Important: Please use the exact chat template provided by Llama-3 instruct version. Otherwise there will be a degradation in the performance. The model output can be verbose in rare cases. Please consider setting temperature = 0 to make this happen less.**
See the snippet below for usage with Transformers:
```python
import transformers
import torch
model_id = "aaditya/OpenBioLLM-Llama3-8B"
pipeline = transformers.pipeline(
"text-generation",
model=model_id,
model_kwargs={"torch_dtype": torch.bfloat16},
device="auto",
)
messages = [
{"role": "system", "content": "You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience. Your name is OpenBioLLM, and you were developed by Saama AI Labs. who's willing to help answer the user's query with explanation. In your explanation, leverage your deep medical expertise such as relevant anatomical structures, physiological processes, diagnostic criteria, treatment guidelines, or other pertinent medical concepts. Use precise medical terminology while still aiming to make the explanation clear and accessible to a general audience."},
{"role": "user", "content": "How can i split a 3mg or 4mg waefin pill so i can get a 2.5mg pill?"},
]
prompt = pipeline.tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
terminators = [
pipeline.tokenizer.eos_token_id,
pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
]
outputs = pipeline(
prompt,
max_new_tokens=256,
eos_token_id=terminators,
do_sample=True,
temperature=0.0,
top_p=0.9,
)
print(outputs[0]["generated_text"][len(prompt):])
```
## **Training procedure**
### **Training hyperparameters**
<details>
<summary>Click to see details</summary>
- learning_rate: 0.0002
- lr_scheduler: cosine
- train_batch_size: 12
- eval_batch_size: 8
- GPU: H100 80GB SXM5
- num_devices: 1
- optimizer: adamw_bnb_8bit
- lr_scheduler_warmup_steps: 100
- num_epochs: 4
</details>
### **Peft hyperparameters**
<details>
<summary>Click to see details</summary>
- adapter: qlora
- lora_r: 128
- lora_alpha: 256
- lora_dropout: 0.05
- lora_target_linear: true
-lora_target_modules:
- q_proj
- v_proj
- k_proj
- o_proj
- gate_proj
- down_proj
- up_proj
</details>
### **Training results**
### **Framework versions**
- Transformers 4.39.3
- Pytorch 2.1.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.1
- Axolotl
- Lm harness for evaluation
# Benchmark Results
🔥 OpenBioLLM-8B demonstrates superior performance compared to larger models, such as GPT-3.5, Meditron-70B across 9 diverse biomedical datasets, achieving state-of-the-art results with an average score of 72.50%, despite having a significantly smaller parameter count. The model's strong performance in domain-specific tasks, such as Clinical KG, Medical Genetics, and PubMedQA, highlights its ability to effectively capture and apply biomedical knowledge.
🚨 The GPT-4, Med-PaLM-1, and Med-PaLM-2 results are taken from their official papers. Since Med-PaLM doesn't provide zero-shot accuracy, we are using 5-shot accuracy from their paper for comparison. All results presented are in the zero-shot setting, except for Med-PaLM-2 and Med-PaLM-1, which use 5-shot accuracy.
| | Clinical KG | Medical Genetics | Anatomy | Pro Medicine | College Biology | College Medicine | MedQA 4 opts | PubMedQA | MedMCQA | Avg |
|--------------------|-------------|------------------|---------|--------------|-----------------|------------------|--------------|----------|---------|-------|
| **OpenBioLLM-70B** | **92.93** | **93.197** | **83.904** | 93.75 | 93.827 | **85.749** | 78.162 | 78.97 | **74.014** | **86.05588** |
| Med-PaLM-2 (5-shot) | 88.3 | 90 | 77.8 | **95.2** | 94.4 | 80.9 | **79.7** | **79.2** | 71.3 | 84.08 |
| **GPT-4** | 86.04 | 91 | 80 | 93.01 | **95.14** | 76.88 | 78.87 | 75.2 | 69.52 | 82.85 |
| Med-PaLM-1 (Flan-PaLM, 5-shot) | 80.4 | 75 | 63.7 | 83.8 | 88.9 | 76.3 | 67.6 | 79 | 57.6 | 74.7 |
| **OpenBioLLM-8B** | 76.101 | 86.1 | 69.829 | 78.21 | 84.213 | 68.042 | 58.993 | 74.12 | 56.913 | 72.502 |
| Gemini-1.0 | 76.7 | 75.8 | 66.7 | 77.7 | 88 | 69.2 | 58 | 70.7 | 54.3 | 70.79 |
| GPT-3.5 Turbo 1106 | 74.71 | 74 | 72.79 | 72.79 | 72.91 | 64.73 | 57.71 | 72.66 | 53.79 | 66 |
| Meditron-70B | 66.79 | 69 | 53.33 | 71.69 | 76.38 | 63 | 57.1 | 76.6 | 46.85 | 64.52 |
| gemma-7b | 69.81 | 70 | 59.26 | 66.18 | 79.86 | 60.12 | 47.21 | 76.2 | 48.96 | 64.18 |
| Mistral-7B-v0.1 | 68.68 | 71 | 55.56 | 68.38 | 68.06 | 59.54 | 50.82 | 75.4 | 48.2 | 62.85 |
| Apollo-7B | 62.26 | 72 | 61.48 | 69.12 | 70.83 | 55.49 | 55.22 | 39.8 | 53.77 | 60 |
| MedAlpaca-7b | 57.36 | 69 | 57.04 | 67.28 | 65.28 | 54.34 | 41.71 | 72.8 | 37.51 | 58.03 |
| BioMistral-7B | 59.9 | 64 | 56.5 | 60.4 | 59 | 54.7 | 50.6 | 77.5 | 48.1 | 57.3 |
| AlpaCare-llama2-7b | 49.81 | 49 | 45.92 | 33.82 | 50 | 43.35 | 29.77 | 72.2 | 34.42 | 45.36 |
| ClinicalGPT | 30.56 | 27 | 30.37 | 19.48 | 25 | 24.27 | 26.08 | 63.8 | 28.18 | 30.52 |
<div align="center">
<img width="1600px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/_SzdcJSBjZyo8RS1bTEkP.png">
</div>
## Detailed Medical Subjectwise accuracy
# Use Cases & Examples
🚨 **Below results are from the quantized version of OpenBioLLM-70B**
# Summarize Clinical Notes
OpenBioLLM-70B can efficiently analyze and summarize complex clinical notes, EHR data, and discharge summaries, extracting key information and generating concise, structured summaries
# Answer Medical Questions
OpenBioLLM-70B can provide answers to a wide range of medical questions.
<details>
<summary>Click to see details</summary>
</details>
# Clinical Entity Recognition
OpenBioLLM-70B can perform advanced clinical entity recognition by identifying and extracting key medical concepts, such as diseases, symptoms, medications, procedures, and anatomical structures, from unstructured clinical text. By leveraging its deep understanding of medical terminology and context, the model can accurately annotate and categorize clinical entities, enabling more efficient information retrieval, data analysis, and knowledge discovery from electronic health records, research articles, and other biomedical text sources. This capability can support various downstream applications, such as clinical decision support, pharmacovigilance, and medical research.
# Biomarkers Extraction
# Classification
OpenBioLLM-70B can perform various biomedical classification tasks, such as disease prediction, sentiment analysis, medical document categorization
# De-Identification
OpenBioLLM-70B can detect and remove personally identifiable information (PII) from medical records, ensuring patient privacy and compliance with data protection regulations like HIPAA.
**Advisory Notice!**
While OpenBioLLM-70B & 8B leverages high-quality data sources, its outputs may still contain inaccuracies, biases, or misalignments that could pose risks if relied upon for medical decision-making without further testing and refinement. The model's performance has not yet been rigorously evaluated in randomized controlled trials or real-world healthcare environments.
Therefore, we strongly advise against using OpenBioLLM-70B & 8B for any direct patient care, clinical decision support, or other professional medical purposes at this time. Its use should be limited to research, development, and exploratory applications by qualified individuals who understand its limitations.
OpenBioLLM-70B & 8B are intended solely as a research tool to assist healthcare professionals and should never be considered a replacement for the professional judgment and expertise of a qualified medical doctor.
Appropriately adapting and validating OpenBioLLM-70B & 8B for specific medical use cases would require significant additional work, potentially including:
- Thorough testing and evaluation in relevant clinical scenarios
- Alignment with evidence-based guidelines and best practices
- Mitigation of potential biases and failure modes
- Integration with human oversight and interpretation
- Compliance with regulatory and ethical standards
Always consult a qualified healthcare provider for personal medical needs.
# Citation
If you find OpenBioLLM-70B & 8B useful in your work, please cite the model as follows:
```
@misc{OpenBioLLMs,
author = {Ankit Pal, Malaikannan Sankarasubbu},
title = {OpenBioLLMs: Advancing Open-Source Large Language Models for Healthcare and Life Sciences},
year = {2024},
publisher = {Hugging Face},
journal = {Hugging Face repository},
howpublished = {\url{https://huggingface.co/aaditya/OpenBioLLM-Llama3-70B}}
}
```
The accompanying paper is currently in progress and will be released soon.
<div align="center">
<h2> 💌 Contact </h2>
</div>
We look forward to hearing you and collaborating on this exciting project!
**Contributors:**
- [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) [aadityaura at gmail dot com]
- Saama AI Labs
- Note: I am looking for a funded PhD opportunity, especially if it fits my Responsible Generative AI, Multimodal LLMs, Geometric Deep Learning, and Healthcare AI skillset.
# References
We thank the [Meta Team](meta-llama/Meta-Llama-3-70B-Instruct) for their amazing models!
Result sources
- [1] GPT-4 [Capabilities of GPT-4 on Medical Challenge Problems] (https://arxiv.org/abs/2303.13375)
- [2] Med-PaLM-1 [Large Language Models Encode Clinical Knowledge](https://arxiv.org/abs/2212.13138)
- [3] Med-PaLM-2 [Towards Expert-Level Medical Question Answering with Large Language Models](https://arxiv.org/abs/2305.09617)
- [4] Gemini-1.0 [Gemini Goes to Med School](https://arxiv.org/abs/2402.07023) | {"language": ["en"], "license": "llama3", "tags": ["llama-3", "llama", "Mixtral", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "distillation"], "base_model": "meta-llama/Meta-Llama-3-8B", "widget": [{"example_title": "OpenBioLLM-8B", "messages": [{"role": "system", "content": "You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience."}, {"role": "user", "content": "How long does it take for newborn jaundice to go away?"}], "output": {"text": "Newborn jaundice, also known as neonatal jaundice, is a common condition in newborns where the yellowing of the skin and eyes occurs due to an elevated level of bilirubin in the blood. Bilirubin is a yellow pigment that forms when red blood cells break down. In most cases, newborn jaundice resolves on its own without any specific treatment.\nThe duration of newborn jaundice can vary depending on several factors such as the underlying cause, gestational age at birth, and individual variations in bilirubin metabolism. Here are some general guidelines:\n1. Physiological jaundice: This is the most common type of newborn jaundice and usually appears within 24-72 hours after birth. It tends to peak between the second and fifth day of life and gradually improves over the next week or two. By the time the baby is one week old, the jaundice should have mostly resolved. 2. Breast milk jaundice: This type of jaundice occurs in breastfed babies and may appear later than physiological jaundice, typically between the fifth and fourteenth day of life. It tends to persist for a longer duration but usually resolves within six weeks after birth. 3. Pathological jaundice: This type of jaundice is less common and occurs due to an underlying medical condition that affects bilirubin metabolism or liver function. The duration of pathological jaundice depends on the specific cause and may require treatment.\nIt's important for parents to monitor their newborn's jaundice closely and seek medical advice if the jaundice progresses rapidly, becomes severe, or is accompanied by other symptoms such as poor feeding, lethargy, or excessive sleepiness. In these cases, further evaluation and management may be necessary. Remember that each baby is unique, and the timing of jaundice resolution can vary. If you have concerns about your newborn's jaundice, it's always best to consult with a healthcare professional for personalized advice and guidance."}}], "model-index": [{"name": "OpenBioLLM-8B", "results": []}]} | LoneStriker/OpenBioLLM-Llama3-8B-GGUF | null | [
"gguf",
"llama-3",
"llama",
"Mixtral",
"instruct",
"finetune",
"chatml",
"DPO",
"RLHF",
"gpt4",
"distillation",
"en",
"arxiv:2305.18290",
"arxiv:2303.13375",
"arxiv:2212.13138",
"arxiv:2305.09617",
"arxiv:2402.07023",
"base_model:meta-llama/Meta-Llama-3-8B",
"license:llama3",
"region:us"
]
| null | 2024-04-26T19:11:19+00:00 |
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": "meta-llama/Meta-Llama-3-70B-Instruct"} | asbabiy/AspectLens-BA-Large | null | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:meta-llama/Meta-Llama-3-70B-Instruct",
"region:us"
]
| null | 2024-04-26T19:12:25+00:00 |
text-generation | transformers | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
saiga_llama3_8b - bnb 8bits
- Model creator: https://huggingface.co/IlyaGusev/
- Original model: https://huggingface.co/IlyaGusev/saiga_llama3_8b/
Original model description:
---
language:
- ru
datasets:
- IlyaGusev/saiga_scored
license: other
license_name: llama3
license_link: https://llama.meta.com/llama3/license/
---
# Saiga/Llama3 8B, Russian Llama-3-based chatbot
Based on [Llama-3 8B Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct).
Llama.cpp version: [link](https://huggingface.co/IlyaGusev/saiga_llama3_8b_gguf)
**ОСТОРОЖНО! WARNING! LET OP!**
I've changed the prompt format from ChatML to **the original Llama-3 format in v4**. Don't forget to switch formats!
**v4**: LLama-3 prompt format:
```
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
Ты — Сайга, русскоязычный автоматический ассистент. Ты разговариваешь с людьми и помогаешь им.<|eot_id|><|start_header_id|>user<|end_header_id|>
Как дела?<|eot_id|><|start_header_id|>assistant<|end_header_id|>
Отлично, а у тебя?<|eot_id|><|start_header_id|>user<|end_header_id|>
Шикарно. Как пройти в библиотеку?<|eot_id|><|start_header_id|>assistant<|end_header_id|>
```
**v2, v3**: ChatML prompt format:
```
<|im_start|>system
Ты — Сайга, русскоязычный автоматический ассистент. Ты разговариваешь с людьми и помогаешь им.<|im_end|>
<|im_start|>user
Как дела?<|im_end|>
<|im_start|>assistant
Отлично, а у тебя?<|im_end|>
<|im_start|>user
Шикарно. Как пройти в библиотеку?<|im_end|>
<|im_start|>assistant
```
Examples:
```
User: Почему трава зеленая?
Saiga: Зеленый цвет травы обусловлен наличием хлорофилла, пигмента, который поглощает свет и передает энергию для фотосинтеза. Хлорофилл содержится в клетках листьев растений и играет ключевую роль в процессе фотосинтеза, когда растения используют солнечный свет для превращения воды и углекислого газа в органические вещества, такие как глюкоза и олигоэфиры.
Хлорофилл состоит из двух основных форм: хлорофилла а и хлорофилла б. Хлорофилл а поглощает свет с длиной волны около 430 нанометров (нм), что соответствует синему или голубому свету, а хлорофилл б поглощает свет с длиной волны около 660 нм, что соответствует красному свету. Когда свет поглощается хлорофиллом, он передается в молекулы воды и углекислого газа, которые используются для фотосинтеза.
Таким образом, хлорофилл является основным компонентом, ответственным за зеленый цвет листьев растений, так как он поглощает свет и передает его энергию для фотосинтеза.
```
```
User: Сочини длинный рассказ, обязательно упоминая следующие объекты. Дано: Таня, мяч
Saiga: Однажды в солнечную погоду на поле для игры в футбол приехала группа друзей, чтобы провести время вместе. В числе их был и Таня, которая была страстной футбольной фанаткой и всегда радовал своих друзей своим энтузиазмом и умением забивать мячи.
В этот день, как обычно, друзья решили провести соревнование между собой, чтобы определить кто из них является лучшим футболистом. Таня была очень уверена в своих силах и готовилась к этому матчу с особой серьёзностью.
Когда все друзья собрались на поле, они увидели, что перед ними стоял огромный мяч, который должен был стать предметом состязания. Мяч был огромным и тяжелым, и его размеры были необычайно большими по сравнению с обычными мячами, которые используются в футболе.
Таня была первая, кто решил начать игру. Она подошла к мячу и начала его удерживать, стараясь выдержать его вес и силу. Но мяч оказался настолько тяжелым, что Таня не смогла удержать его и он упал на землю.
Друзья посмеялись над ее неудачей, но Таня не отчаивалась и продолжила пытаться удержать мяч. Она стала использовать все свои силы и умения, чтобы выдержать его вес и силу. Наконец, после долгих усилий, она смогла удержать мяч и начала его бросать в сторону.
Мяч летел высоко вверх, и друзья смотрели, как он пролетает над полем. Но мяч неожиданно повернул и стал лететь обратно к Тане. Она успела поймать его и продолжила играть, используя все свои навыки и умения.
```
v4:
- [1cc945d4ca2c7901cf989e7edaac52ab24f1a7dd](https://huggingface.co/IlyaGusev/saiga_llama3_8b/commit/1cc945d4ca2c7901cf989e7edaac52ab24f1a7dd)
- dataset: [saiga_scored](https://huggingface.co/datasets/IlyaGusev/saiga_scored), scores >= 8, c66032920556c0f21bbbed05e7e04433ec954c3d
- wandb [link](https://wandb.ai/ilyagusev/rulm_self_instruct/runs/dcbs9ttt)
v3:
- [c588356cd60bdee54d52c2dd5a2445acca8aa5c3](https://huggingface.co/IlyaGusev/saiga_llama3_8b/commit/c588356cd60bdee54d52c2dd5a2445acca8aa5c3)
- dataset: [saiga_scored](https://huggingface.co/datasets/IlyaGusev/saiga_scored), scores >= 8, d51cf8060bdc90023da8cf1c3f113f9193d6569b
- wandb [link](https://wandb.ai/ilyagusev/rulm_self_instruct/runs/ltoqdsal)
v2:
- [ae61b4f9b34fac9856d361ea78c66284a00e4f0b](https://huggingface.co/IlyaGusev/saiga_llama3_8b/commit/ae61b4f9b34fac9856d361ea78c66284a00e4f0b)
- dataset code revision d0d123dd221e10bb2a3383bcb1c6e4efe1b4a28a
- wandb [link](https://wandb.ai/ilyagusev/huggingface/runs/r6u5juyk)
- 5 datasets: ru_turbo_saiga, ru_sharegpt_cleaned, oasst1_ru_main_branch, gpt_roleplay_realm, ru_instruct_gpt4
- Datasets merging script: [create_short_chat_set.py](https://github.com/IlyaGusev/rulm/blob/d0d123dd221e10bb2a3383bcb1c6e4efe1b4a28a/self_instruct/src/data_processing/create_short_chat_set.py)
# Evaluation
* Dataset: https://github.com/IlyaGusev/rulm/blob/master/self_instruct/data/tasks.jsonl
* Framework: https://github.com/tatsu-lab/alpaca_eval
* Evaluator: alpaca_eval_cot_gpt4_turbo_fn
| model | length_controlled_winrate | win_rate | standard_error | avg_length |
|-----|-----|-----|-----|-----|
|chatgpt_4_turbo | 76.04 | 90.00 |1.46 | 1270 |
|chatgpt_3_5_turbo | 50.00 | 50.00 | 0.00 | 536 |
|saiga_llama3_8b, v4 | 43.64 | 65.90 | 2.31 | 1200 |
|saiga_llama3_8b, v3 | 36.97 | 61.08 | 2.38 | 1162 |
|saiga_llama3_8b, v2 | 33.07 | 48.19 | 2.45 | 1166 |
|saiga_mistral_7b | 23.38 | 35.99 | 2.34 | 949 |
| {} | RichardErkhov/IlyaGusev_-_saiga_llama3_8b-8bits | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"8-bit",
"region:us"
]
| null | 2024-04-26T19:13:40+00:00 |
text-generation | transformers |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
| {"library_name": "transformers", "tags": ["unsloth", "trl", "sft"]} | cashu/mistral_16_bit | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"unsloth",
"trl",
"sft",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-26T19:13:49+00:00 |
text-generation | transformers | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
saiga_gemma_9b - bnb 8bits
- Model creator: https://huggingface.co/IlyaGusev/
- Original model: https://huggingface.co/IlyaGusev/saiga_gemma_9b/
Original model description:
---
language:
- ru
datasets:
- IlyaGusev/ru_turbo_saiga
- IlyaGusev/ru_sharegpt_cleaned
- IlyaGusev/oasst1_ru_main_branch
- IlyaGusev/gpt_roleplay_realm
- lksy/ru_instruct_gpt4
---
# Saiga/Gemma 9B, Russian Gemma-based chatbot
Based on [Gemma 7B](https://huggingface.co/google/gemma-7b).
Training Colab: [link](https://colab.research.google.com/drive/1O7F7Q3IQYh-v7EfsdRwMDMfUnOYZ3DEh).
ChatML prompt format:
```
<|im_start|>system
Ты — Сайга, русскоязычный автоматический ассистент. Ты разговариваешь с людьми и помогаешь им.<|im_end|>
<|im_start|>user
Привет!<|im_end|>
<|im_start|>assistant
Отлично, а ты?<|im_end|>
<|im_start|>user
Шикарно. Как пройти в библиотеку?<|im_end|>
<|im_start|>assistant
```
Examples:
```
User: Почему трава зеленая?
Saiga: Зеленый цвет травы обусловлен наличием в её клетках пигмента хлорофилла, который играет важную роль в процессе фотосинтеза – преобразования солнечного света в энергию, используемую для роста и развития растений.
Хлорофилл поглощает свет в определенных диапазонах длин волн, в том числе в зеленой области спектра, и отражает свет в других диапазонах, что и обуславливает зелёный цвет.
```
```
User: Сочини длинный рассказ, обязательно упоминая следующие объекты. Дано: Таня, мяч
Saiga: Однажды, в далекой стране, жила маленькая девочка по имени Таня. Она была очень активной и любила играть в мяч. Вместе со своими друзьями они проводили дни, играя в футбол, баскетбол и волейбол.
Таня была очень талантливой и ловкой, и она часто выигрывала в играх с другими детьми. Но однажды, во время игры в баскетбол, она получила сильную травму. Ей пришлось провести несколько недель в больнице, и она была очень грустной и унылой.
Её друзья не могли понять, как помочь Тане справиться с этой ситуацией. Они пытались поддерживать её, но Таня была слишком подавлена и не хотела играть в мяч.
Однажды, Таня увидела, как её друзья играют в мяч. Она не могла не смотреть, как они ловко передают мяч друг другу и забивают голы. Таня почувствовала, как её сердце разрывается от желания играть вместе с ними.
Она решила, что ей нужно вернуться в игру, чтобы снова почувствовать радость игры. Она начала медленно восстанавливаться и постепенно возвращалась к своему любимому занятию - игре в мяч.
Таня стала играть в мяч снова, но теперь она была более осторожна и внимательна к своему здоровью. Её друзья были очень рады видеть, как Таня возвращается к своей привычной жизни.
С тех пор, Таня стала настоящей звездой на поле. Она стала лучшей игроком в своей команде и помогла им выиграть множество игр. Её друзья были горды, что Таня вернулась к своему любимому занятию и снова стала такой же активной и ловкой, как раньше.
Таня и её друзья продолжали играть в мяч и проводили чудесные дни вместе. Они были счастливы, что Таня вернулась к своему любимому занятию и снова стала частью команды.
Таня и её друзья продолжают играть в мяч и вместе они создают прекрасные воспоминания.
```
v1:
- dataset code revision d0d123dd221e10bb2a3383bcb1c6e4efe1b4a28a
- wandb [link](https://wandb.ai/ilyagusev/gemma_test/runs/k7u3uw5i)
- 5 datasets: ru_turbo_saiga, ru_sharegpt_cleaned, oasst1_ru_main_branch, gpt_roleplay_realm, ru_instruct_gpt4
- Datasets merging script: [create_short_chat_set.py](https://github.com/IlyaGusev/rulm/blob/d0d123dd221e10bb2a3383bcb1c6e4efe1b4a28a/self_instruct/src/data_processing/create_short_chat_set.py)
| {} | RichardErkhov/IlyaGusev_-_saiga_gemma_9b-8bits | null | [
"transformers",
"safetensors",
"gemma",
"text-generation",
"conversational",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"8-bit",
"region:us"
]
| null | 2024-04-26T19:14:13+00:00 |
null | null | White teeth
smiles alot to hide her pain
African American
Eyes blue as the deep sea
a lot of curly hair
Can speak more than 5 languages
Is just looking for peace and quiet
Desires to be a sloth but have a lot of money
| {} | Ytsheeqee/meta-verse-creation | null | [
"region:us"
]
| null | 2024-04-26T19:14:51+00:00 |
null | null | {} | cashu/mistral_gguf | null | [
"region:us"
]
| null | 2024-04-26T19:15:19+00:00 |
|
null | transformers | ## About
<!-- ### quantize_version: 1 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/chujiezheng/tulu-2-dpo-70b-ExPO
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/tulu-2-dpo-70b-ExPO-i1-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/tulu-2-dpo-70b-ExPO-GGUF/resolve/main/tulu-2-dpo-70b-ExPO.Q2_K.gguf) | Q2_K | 25.6 | |
| [GGUF](https://huggingface.co/mradermacher/tulu-2-dpo-70b-ExPO-GGUF/resolve/main/tulu-2-dpo-70b-ExPO.IQ3_XS.gguf) | IQ3_XS | 28.4 | |
| [GGUF](https://huggingface.co/mradermacher/tulu-2-dpo-70b-ExPO-GGUF/resolve/main/tulu-2-dpo-70b-ExPO.IQ3_S.gguf) | IQ3_S | 30.0 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/tulu-2-dpo-70b-ExPO-GGUF/resolve/main/tulu-2-dpo-70b-ExPO.Q3_K_S.gguf) | Q3_K_S | 30.0 | |
| [GGUF](https://huggingface.co/mradermacher/tulu-2-dpo-70b-ExPO-GGUF/resolve/main/tulu-2-dpo-70b-ExPO.IQ3_M.gguf) | IQ3_M | 31.0 | |
| [GGUF](https://huggingface.co/mradermacher/tulu-2-dpo-70b-ExPO-GGUF/resolve/main/tulu-2-dpo-70b-ExPO.Q3_K_M.gguf) | Q3_K_M | 33.4 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/tulu-2-dpo-70b-ExPO-GGUF/resolve/main/tulu-2-dpo-70b-ExPO.Q3_K_L.gguf) | Q3_K_L | 36.2 | |
| [GGUF](https://huggingface.co/mradermacher/tulu-2-dpo-70b-ExPO-GGUF/resolve/main/tulu-2-dpo-70b-ExPO.IQ4_XS.gguf) | IQ4_XS | 37.3 | |
| [GGUF](https://huggingface.co/mradermacher/tulu-2-dpo-70b-ExPO-GGUF/resolve/main/tulu-2-dpo-70b-ExPO.Q4_K_S.gguf) | Q4_K_S | 39.3 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/tulu-2-dpo-70b-ExPO-GGUF/resolve/main/tulu-2-dpo-70b-ExPO.Q4_K_M.gguf) | Q4_K_M | 41.5 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/tulu-2-dpo-70b-ExPO-GGUF/resolve/main/tulu-2-dpo-70b-ExPO.Q5_K_S.gguf) | Q5_K_S | 47.6 | |
| [GGUF](https://huggingface.co/mradermacher/tulu-2-dpo-70b-ExPO-GGUF/resolve/main/tulu-2-dpo-70b-ExPO.Q5_K_M.gguf) | Q5_K_M | 48.9 | |
| [PART 1](https://huggingface.co/mradermacher/tulu-2-dpo-70b-ExPO-GGUF/resolve/main/tulu-2-dpo-70b-ExPO.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/tulu-2-dpo-70b-ExPO-GGUF/resolve/main/tulu-2-dpo-70b-ExPO.Q6_K.gguf.part2of2) | Q6_K | 56.7 | very good quality |
| [PART 1](https://huggingface.co/mradermacher/tulu-2-dpo-70b-ExPO-GGUF/resolve/main/tulu-2-dpo-70b-ExPO.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/tulu-2-dpo-70b-ExPO-GGUF/resolve/main/tulu-2-dpo-70b-ExPO.Q8_0.gguf.part2of2) | Q8_0 | 73.4 | fast, best quality |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
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": "other", "library_name": "transformers", "base_model": "chujiezheng/tulu-2-dpo-70b-ExPO", "license_link": "https://allenai.org/impact-license", "license_name": "ai2-impact-license-low-risk", "quantized_by": "mradermacher"} | mradermacher/tulu-2-dpo-70b-ExPO-GGUF | null | [
"transformers",
"gguf",
"en",
"base_model:chujiezheng/tulu-2-dpo-70b-ExPO",
"license:other",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T19:16:11+00:00 |
null | null | {} | pruning/55u2ox8 | null | [
"region:us"
]
| null | 2024-04-26T19:16:58+00:00 |
|
null | null | {} | pruning/8fy190w | null | [
"region:us"
]
| null | 2024-04-26T19:16:58+00:00 |
|
null | null | {} | pruning/6pvxgn1 | null | [
"region:us"
]
| null | 2024-04-26T19:16:58+00:00 |
|
null | null | {} | pruning/jpzz89l | null | [
"region:us"
]
| null | 2024-04-26T19:16:58+00:00 |
|
null | null | {} | pruning/dd7hlmb | null | [
"region:us"
]
| null | 2024-04-26T19:16:58+00:00 |
|
null | null | {} | pruning/dulc8ge | null | [
"region:us"
]
| null | 2024-04-26T19:16:58+00:00 |
|
text-generation | transformers | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
Starling-LM-7B-beta - bnb 8bits
- Model creator: https://huggingface.co/Nexusflow/
- Original model: https://huggingface.co/Nexusflow/Starling-LM-7B-beta/
Original model description:
---
license: apache-2.0
datasets:
- berkeley-nest/Nectar
language:
- en
library_name: transformers
tags:
- reward model
- RLHF
- RLAIF
---
# Starling-LM-7B-beta
<!-- Provide a quick summary of what the model is/does. -->
- **Developed by: The Nexusflow Team (** Banghua Zhu * , Evan Frick * , Tianhao Wu * , Hanlin Zhu, Karthik Ganesan, Wei-Lin Chiang, Jian Zhang, and Jiantao Jiao).
- **Model type:** Language Model finetuned with RLHF / RLAIF
- **License:** Apache-2.0 license under the condition that the model is not used to compete with OpenAI
- **Finetuned from model:** [Openchat-3.5-0106](https://huggingface.co/openchat/openchat-3.5-0106) (based on [Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1))
We introduce Starling-LM-7B-beta, an open large language model (LLM) trained by Reinforcement Learning from AI Feedback (RLAIF). Starling-LM-7B-beta is trained from [Openchat-3.5-0106](https://huggingface.co/openchat/openchat-3.5-0106) with our new reward model [Nexusflow/Starling-RM-34B](https://huggingface.co/Nexusflow/Starling-RM-34B) and policy optimization method [Fine-Tuning Language Models from Human Preferences (PPO)](https://arxiv.org/abs/1909.08593).
Harnessing the power of the ranking dataset, [berkeley-nest/Nectar](https://huggingface.co/datasets/berkeley-nest/Nectar), the upgraded reward model, [Starling-RM-34B](https://huggingface.co/Nexusflow/Starling-RM-34B), and the new reward training and policy tuning pipeline, Starling-LM-7B-beta scores an improved 8.12 in MT Bench with GPT-4 as a judge.
## 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. -->
**Important: Please use the exact chat template provided below for the model. Otherwise there will be a degradation in the performance. The model output can be verbose in rare cases. Please consider setting temperature = 0 to make this happen less.**
Our model follows the exact chat template and usage as [Openchat-3.5-0106](https://huggingface.co/openchat/openchat-3.5-0106). Please refer to their model card for more details.
In addition, our model is hosted on LMSYS [Chatbot Arena](https://chat.lmsys.org) for free test.
The conversation template is the same as Openchat-3.5-0106:
```
import transformers
tokenizer = transformers.AutoTokenizer.from_pretrained("openchat/openchat-3.5-0106")
# Single-turn
tokens = tokenizer("GPT4 Correct User: Hello<|end_of_turn|>GPT4 Correct Assistant:").input_ids
assert tokens == [1, 420, 6316, 28781, 3198, 3123, 1247, 28747, 22557, 32000, 420, 6316, 28781, 3198, 3123, 21631, 28747]
# Multi-turn
tokens = tokenizer("GPT4 Correct User: Hello<|end_of_turn|>GPT4 Correct Assistant: Hi<|end_of_turn|>GPT4 Correct User: How are you today?<|end_of_turn|>GPT4 Correct Assistant:").input_ids
assert tokens == [1, 420, 6316, 28781, 3198, 3123, 1247, 28747, 22557, 32000, 420, 6316, 28781, 3198, 3123, 21631, 28747, 15359, 32000, 420, 6316, 28781, 3198, 3123, 1247, 28747, 1602, 460, 368, 3154, 28804, 32000, 420, 6316, 28781, 3198, 3123, 21631, 28747]
# Coding Mode
tokens = tokenizer("Code User: Implement quicksort using C++<|end_of_turn|>Code Assistant:").input_ids
assert tokens == [1, 7596, 1247, 28747, 26256, 2936, 7653, 1413, 334, 1680, 32000, 7596, 21631, 28747]
```
## Code Examples
```python
import transformers
tokenizer = transformers.AutoTokenizer.from_pretrained("Nexusflow/Starling-LM-7B-beta")
model = transformers.AutoModelForCausalLM.from_pretrained("Nexusflow/Starling-LM-7B-beta")
def generate_response(prompt):
input_ids = tokenizer(prompt, return_tensors="pt").input_ids
outputs = model.generate(
input_ids,
max_length=256,
pad_token_id=tokenizer.pad_token_id,
eos_token_id=tokenizer.eos_token_id,
)
response_ids = outputs[0]
response_text = tokenizer.decode(response_ids, skip_special_tokens=True)
return response_text
# Single-turn conversation
prompt = "Hello, how are you?"
single_turn_prompt = f"GPT4 Correct User: {prompt}<|end_of_turn|>GPT4 Correct Assistant:"
response_text = generate_response(single_turn_prompt)
print("Response:", response_text)
## Multi-turn conversation
prompt = "Hello"
follow_up_question = "How are you today?"
response = ""
multi_turn_prompt = f"GPT4 Correct User: {prompt}<|end_of_turn|>GPT4 Correct Assistant: {response}<|end_of_turn|>GPT4 Correct User: {follow_up_question}<|end_of_turn|>GPT4 Correct Assistant:"
response_text = generate_response(multi_turn_prompt)
print("Multi-turn conversation response:", response_text)
### Coding conversation
prompt = "Implement quicksort using C++"
coding_prompt = f"Code User: {prompt}<|end_of_turn|>Code Assistant:"
response = generate_response(coding_prompt)
print("Coding conversation response:", response)
```
## License
The dataset, model and online demo is subject to the [Terms of Use](https://openai.com/policies/terms-of-use) of the data generated by OpenAI, and [Privacy Practices](https://chrome.google.com/webstore/detail/sharegpt-share-your-chatg/daiacboceoaocpibfodeljbdfacokfjb) of ShareGPT. Please contact us if you find any potential violation.
## Acknowledgment
We would like to thank Tianle Li from UC Berkeley for detailed feedback and evaluation of this beta release. We would like to thank the [LMSYS Organization](https://lmsys.org/) for their support of [lmsys-chat-1M](https://huggingface.co/datasets/lmsys/lmsys-chat-1m) dataset, evaluation and online demo. We would like to thank the open source community for their efforts in providing the datasets and base models we used to develope the project, including but not limited to Anthropic, Llama, Mistral, Hugging Face H4, LMSYS, OpenChat, OpenBMB, Flan and ShareGPT.
## Citation
```
@misc{starling2023,
title = {Starling-7B: Improving LLM Helpfulness & Harmlessness with RLAIF},
url = {},
author = {Zhu, Banghua and Frick, Evan and Wu, Tianhao and Zhu, Hanlin and Ganesan, Karthik and Chiang, Wei-Lin and Zhang, Jian and Jiao, Jiantao},
month = {November},
year = {2023}
}
```
| {} | RichardErkhov/Nexusflow_-_Starling-LM-7B-beta-8bits | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"arxiv:1909.08593",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"8-bit",
"region:us"
]
| null | 2024-04-26T19:17:31+00:00 |
null | transformers | ## About
<!-- ### quantize_version: 1 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/Dunjeon/lostmagic-RP_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/lostmagic-RP_7B-GGUF/resolve/main/lostmagic-RP_7B.Q2_K.gguf) | Q2_K | 2.8 | |
| [GGUF](https://huggingface.co/mradermacher/lostmagic-RP_7B-GGUF/resolve/main/lostmagic-RP_7B.IQ3_XS.gguf) | IQ3_XS | 3.1 | |
| [GGUF](https://huggingface.co/mradermacher/lostmagic-RP_7B-GGUF/resolve/main/lostmagic-RP_7B.Q3_K_S.gguf) | Q3_K_S | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/lostmagic-RP_7B-GGUF/resolve/main/lostmagic-RP_7B.IQ3_S.gguf) | IQ3_S | 3.3 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/lostmagic-RP_7B-GGUF/resolve/main/lostmagic-RP_7B.IQ3_M.gguf) | IQ3_M | 3.4 | |
| [GGUF](https://huggingface.co/mradermacher/lostmagic-RP_7B-GGUF/resolve/main/lostmagic-RP_7B.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/lostmagic-RP_7B-GGUF/resolve/main/lostmagic-RP_7B.Q3_K_L.gguf) | Q3_K_L | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/lostmagic-RP_7B-GGUF/resolve/main/lostmagic-RP_7B.IQ4_XS.gguf) | IQ4_XS | 4.0 | |
| [GGUF](https://huggingface.co/mradermacher/lostmagic-RP_7B-GGUF/resolve/main/lostmagic-RP_7B.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/lostmagic-RP_7B-GGUF/resolve/main/lostmagic-RP_7B.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/lostmagic-RP_7B-GGUF/resolve/main/lostmagic-RP_7B.Q5_K_S.gguf) | Q5_K_S | 5.1 | |
| [GGUF](https://huggingface.co/mradermacher/lostmagic-RP_7B-GGUF/resolve/main/lostmagic-RP_7B.Q5_K_M.gguf) | Q5_K_M | 5.2 | |
| [GGUF](https://huggingface.co/mradermacher/lostmagic-RP_7B-GGUF/resolve/main/lostmagic-RP_7B.Q6_K.gguf) | Q6_K | 6.0 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/lostmagic-RP_7B-GGUF/resolve/main/lostmagic-RP_7B.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/lostmagic-RP_7B-GGUF/resolve/main/lostmagic-RP_7B.f16.gguf) | f16 | 14.6 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
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": "cc-by-nc-4.0", "library_name": "transformers", "tags": ["roleplay", "uncensored", "lewd", "mature", "not-for-all-audiences"], "base_model": "Dunjeon/lostmagic-RP_7B", "quantized_by": "mradermacher"} | mradermacher/lostmagic-RP_7B-GGUF | null | [
"transformers",
"gguf",
"roleplay",
"uncensored",
"lewd",
"mature",
"not-for-all-audiences",
"en",
"base_model:Dunjeon/lostmagic-RP_7B",
"license:cc-by-nc-4.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T19:19:10+00:00 |
image-classification | transformers |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Boya1_RMSProp_1-e5_10Epoch_swin-large-patch4-window7-224_fold1
This model is a fine-tuned version of [microsoft/swin-large-patch4-window7-224](https://huggingface.co/microsoft/swin-large-patch4-window7-224) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1733
- Accuracy: 0.6654
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.1578 | 1.0 | 924 | 1.1827 | 0.5935 |
| 0.9384 | 2.0 | 1848 | 1.0458 | 0.6437 |
| 0.9513 | 3.0 | 2772 | 0.9737 | 0.6665 |
| 0.6634 | 4.0 | 3696 | 1.0015 | 0.6676 |
| 0.6268 | 5.0 | 4620 | 0.9964 | 0.6765 |
| 0.5239 | 6.0 | 5544 | 1.0639 | 0.6681 |
| 0.3603 | 7.0 | 6468 | 1.0932 | 0.6746 |
| 0.3057 | 8.0 | 7392 | 1.1360 | 0.6668 |
| 0.2497 | 9.0 | 8316 | 1.1511 | 0.6665 |
| 0.2212 | 10.0 | 9240 | 1.1733 | 0.6654 |
### Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0
- Datasets 2.14.6
- Tokenizers 0.14.1
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "datasets": ["imagefolder"], "metrics": ["accuracy"], "base_model": "microsoft/swin-large-patch4-window7-224", "model-index": [{"name": "Boya1_RMSProp_1-e5_10Epoch_swin-large-patch4-window7-224_fold1", "results": [{"task": {"type": "image-classification", "name": "Image Classification"}, "dataset": {"name": "imagefolder", "type": "imagefolder", "config": "default", "split": "test", "args": "default"}, "metrics": [{"type": "accuracy", "value": 0.6654002713704206, "name": "Accuracy"}]}]}]} | onizukal/Boya1_RMSProp_1-e5_10Epoch_swin-large-patch4-window7-224_fold1 | null | [
"transformers",
"safetensors",
"swin",
"image-classification",
"generated_from_trainer",
"dataset:imagefolder",
"base_model:microsoft/swin-large-patch4-window7-224",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T19:19:17+00:00 |
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": []} | quickstep3621/h3hnzyu | null | [
"transformers",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T19:21:41+00:00 |
null | peft |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# GUE_prom_prom_300_notata-seqsight_4096_512_46M-L8_f
This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_4096_512_46M](https://huggingface.co/mahdibaghbanzadeh/seqsight_4096_512_46M) on the [mahdibaghbanzadeh/GUE_prom_prom_300_notata](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_prom_prom_300_notata) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1243
- F1 Score: 0.9559
- Accuracy: 0.9559
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 10000
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|
| 0.2239 | 0.6 | 200 | 0.1337 | 0.9497 | 0.9497 |
| 0.1349 | 1.2 | 400 | 0.1317 | 0.9474 | 0.9474 |
| 0.1255 | 1.81 | 600 | 0.1126 | 0.9557 | 0.9557 |
| 0.1105 | 2.41 | 800 | 0.1118 | 0.9557 | 0.9557 |
| 0.1119 | 3.01 | 1000 | 0.1097 | 0.9583 | 0.9584 |
| 0.1055 | 3.61 | 1200 | 0.1186 | 0.9545 | 0.9546 |
| 0.1037 | 4.22 | 1400 | 0.1143 | 0.9576 | 0.9576 |
| 0.1021 | 4.82 | 1600 | 0.1028 | 0.9602 | 0.9602 |
| 0.0999 | 5.42 | 1800 | 0.1138 | 0.9551 | 0.9552 |
| 0.0952 | 6.02 | 2000 | 0.0983 | 0.9634 | 0.9634 |
| 0.0971 | 6.63 | 2200 | 0.0973 | 0.9625 | 0.9625 |
| 0.0951 | 7.23 | 2400 | 0.1080 | 0.9617 | 0.9617 |
| 0.0896 | 7.83 | 2600 | 0.1083 | 0.9600 | 0.9601 |
| 0.0926 | 8.43 | 2800 | 0.0990 | 0.9634 | 0.9634 |
| 0.0911 | 9.04 | 3000 | 0.1049 | 0.9623 | 0.9623 |
| 0.0872 | 9.64 | 3200 | 0.0981 | 0.9653 | 0.9653 |
| 0.0843 | 10.24 | 3400 | 0.1062 | 0.9623 | 0.9623 |
| 0.0883 | 10.84 | 3600 | 0.0984 | 0.9642 | 0.9642 |
| 0.0818 | 11.45 | 3800 | 0.0982 | 0.9640 | 0.9640 |
| 0.0845 | 12.05 | 4000 | 0.1020 | 0.9638 | 0.9638 |
| 0.0842 | 12.65 | 4200 | 0.0954 | 0.9640 | 0.9640 |
| 0.0833 | 13.25 | 4400 | 0.1010 | 0.9644 | 0.9644 |
| 0.0788 | 13.86 | 4600 | 0.0963 | 0.9642 | 0.9642 |
| 0.0815 | 14.46 | 4800 | 0.0999 | 0.9644 | 0.9644 |
| 0.0771 | 15.06 | 5000 | 0.0955 | 0.9655 | 0.9655 |
| 0.0772 | 15.66 | 5200 | 0.1040 | 0.9629 | 0.9629 |
| 0.0787 | 16.27 | 5400 | 0.1045 | 0.9629 | 0.9629 |
| 0.0751 | 16.87 | 5600 | 0.0963 | 0.9651 | 0.9651 |
| 0.0735 | 17.47 | 5800 | 0.0947 | 0.9661 | 0.9661 |
| 0.0785 | 18.07 | 6000 | 0.1004 | 0.9642 | 0.9642 |
| 0.0716 | 18.67 | 6200 | 0.1065 | 0.9642 | 0.9642 |
| 0.075 | 19.28 | 6400 | 0.0968 | 0.9663 | 0.9663 |
| 0.0701 | 19.88 | 6600 | 0.1063 | 0.9646 | 0.9646 |
| 0.0736 | 20.48 | 6800 | 0.0987 | 0.9653 | 0.9653 |
| 0.071 | 21.08 | 7000 | 0.0992 | 0.9665 | 0.9665 |
| 0.0708 | 21.69 | 7200 | 0.0985 | 0.9665 | 0.9665 |
| 0.067 | 22.29 | 7400 | 0.1039 | 0.9659 | 0.9659 |
| 0.0701 | 22.89 | 7600 | 0.0980 | 0.9674 | 0.9674 |
| 0.0686 | 23.49 | 7800 | 0.0992 | 0.9663 | 0.9663 |
| 0.0697 | 24.1 | 8000 | 0.0976 | 0.9657 | 0.9657 |
| 0.0674 | 24.7 | 8200 | 0.1086 | 0.9647 | 0.9648 |
| 0.0682 | 25.3 | 8400 | 0.0996 | 0.9670 | 0.9670 |
| 0.0663 | 25.9 | 8600 | 0.0990 | 0.9670 | 0.9670 |
| 0.0663 | 26.51 | 8800 | 0.0998 | 0.9674 | 0.9674 |
| 0.068 | 27.11 | 9000 | 0.0995 | 0.9665 | 0.9665 |
| 0.0644 | 27.71 | 9200 | 0.1019 | 0.9668 | 0.9668 |
| 0.0647 | 28.31 | 9400 | 0.1017 | 0.9665 | 0.9665 |
| 0.0672 | 28.92 | 9600 | 0.1004 | 0.9666 | 0.9666 |
| 0.0625 | 29.52 | 9800 | 0.1013 | 0.9663 | 0.9663 |
| 0.0646 | 30.12 | 10000 | 0.1010 | 0.9663 | 0.9663 |
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2 | {"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_4096_512_46M", "model-index": [{"name": "GUE_prom_prom_300_notata-seqsight_4096_512_46M-L8_f", "results": []}]} | mahdibaghbanzadeh/GUE_prom_prom_300_notata-seqsight_4096_512_46M-L8_f | null | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:mahdibaghbanzadeh/seqsight_4096_512_46M",
"region:us"
]
| null | 2024-04-26T19:22:01+00:00 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.