Datasets:

---

ftopal

/

huggingface-models-processed

like 0

[ "sentence-transformers", "safetensors", "bert", "feature-extraction", "sentence-similarity", "transformers", "endpoints_compatible", "region:us" ]

[]

[]

[ "# xlreator/biosyn-biobert-snomed\n\nThis is a sentence-transformers model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.", "## Usage (Sentence-Transformers)\n\nUsing this model becomes easy when you have sentence-transformers installed:\n\n\n\nThen you can use the model like this:", "## Usage (HuggingFace Transformers)\nWithout sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.", "## Evaluation Results\n\n\n\nFor an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: URL", "## Training\nThe model was trained with the parameters:\n\nDataLoader:\n\n'URL.dataloader.DataLoader' of length 18434 with parameters:\n\n\nLoss:\n\n'sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss' with parameters:\n \n\nParameters of the fit()-Method:", "## Full Model Architecture", "## Citing & Authors" ]

[ "TAGS\n#sentence-transformers #safetensors #bert #feature-extraction #sentence-similarity #transformers #endpoints_compatible #region-us \n", "# xlreator/biosyn-biobert-snomed\n\nThis is a sentence-transformers model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.", "## Usage (Sentence-Transformers)\n\nUsing this model becomes easy when you have sentence-transformers installed:\n\n\n\nThen you can use the model like this:", "## Usage (HuggingFace Transformers)\nWithout sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.", "## Evaluation Results\n\n\n\nFor an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: URL", "## Training\nThe model was trained with the parameters:\n\nDataLoader:\n\n'URL.dataloader.DataLoader' of length 18434 with parameters:\n\n\nLoss:\n\n'sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss' with parameters:\n \n\nParameters of the fit()-Method:", "## Full Model Architecture", "## Citing & Authors" ]

[ 30, 50, 30, 58, 26, 73, 5, 5 ]

[ "TAGS\n#sentence-transformers #safetensors #bert #feature-extraction #sentence-similarity #transformers #endpoints_compatible #region-us \n# xlreator/biosyn-biobert-snomed\n\nThis is a sentence-transformers model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.## Usage (Sentence-Transformers)\n\nUsing this model becomes easy when you have sentence-transformers installed:\n\n\n\nThen you can use the model like this:## Usage (HuggingFace Transformers)\nWithout sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.## Evaluation Results\n\n\n\nFor an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: URL## Training\nThe model was trained with the parameters:\n\nDataLoader:\n\n'URL.dataloader.DataLoader' of length 18434 with parameters:\n\n\nLoss:\n\n'sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss' with parameters:\n \n\nParameters of the fit()-Method:## Full Model Architecture## Citing & Authors" ]

[ "transformers", "gemma", "text-generation", "pruna-ai", "base_model:google/gemma-2b-it", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.", "## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with hqq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.", "## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo google/gemma-2b-it installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.", "## Configurations\n\nThe configuration info are in 'smash_config.json'.", "## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model google/gemma-2b-it before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.", "## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ "TAGS\n#transformers #gemma #text-generation #pruna-ai #base_model-google/gemma-2b-it #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.", "## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with hqq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.", "## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo google/gemma-2b-it installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.", "## Configurations\n\nThe configuration info are in 'smash_config.json'.", "## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model google/gemma-2b-it before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.", "## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ 47, 83, 451, 67, 19, 62, 36 ]

[ "TAGS\n#transformers #gemma #text-generation #pruna-ai #base_model-google/gemma-2b-it #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with hqq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo google/gemma-2b-it installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.## Configurations\n\nThe configuration info are in 'smash_config.json'.## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model google/gemma-2b-it before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ "diffusers", "text-to-image", "stable-diffusion", "lora", "template:sd-lora", "not-for-all-audiences", "base_model:AstraliteHeart/pony-diffusion-v6", "license:other", "region:us" ]

[]

[]

[ "# Goat Chan - Enanare OC\n\n<Gallery />", "## Model description \nGoat Chan - Enanare's OC!\n\nTrained based on her appareance, it has a trigger word corresponding to the appearance of the character and suggested prompts that summons related clothes and accesories.\n\nWorks well with 0.7-1.0 weight", "## Trigger words\n\nDefault Appareance: 'goatchandef, huge breasts, goat ears, goat horns, tail,' 'Pubic tattoo/crotch tattoo'", "## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab.", "### License\n\nThis LoRA model is provided under the Fair AI Public License 1.0-SD license.", "## Restrictions:\n\n- Usage in Generation Services: You are not allowed to use the model in any generation services without proper permission from the original creator.\n\n- Commercial Usage: The sale of the model or any commercial usage is strictly prohibited without explicit written permission from the original creator." ]

[ "TAGS\n#diffusers #text-to-image #stable-diffusion #lora #template-sd-lora #not-for-all-audiences #base_model-AstraliteHeart/pony-diffusion-v6 #license-other #region-us \n", "# Goat Chan - Enanare OC\n\n<Gallery />", "## Model description \nGoat Chan - Enanare's OC!\n\nTrained based on her appareance, it has a trigger word corresponding to the appearance of the character and suggested prompts that summons related clothes and accesories.\n\nWorks well with 0.7-1.0 weight", "## Trigger words\n\nDefault Appareance: 'goatchandef, huge breasts, goat ears, goat horns, tail,' 'Pubic tattoo/crotch tattoo'", "## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab.", "### License\n\nThis LoRA model is provided under the Fair AI Public License 1.0-SD license.", "## Restrictions:\n\n- Usage in Generation Services: You are not allowed to use the model in any generation services without proper permission from the original creator.\n\n- Commercial Usage: The sale of the model or any commercial usage is strictly prohibited without explicit written permission from the original creator." ]

[ 55, 13, 59, 35, 25, 23, 55 ]

[ "TAGS\n#diffusers #text-to-image #stable-diffusion #lora #template-sd-lora #not-for-all-audiences #base_model-AstraliteHeart/pony-diffusion-v6 #license-other #region-us \n# Goat Chan - Enanare OC\n\n<Gallery />## Model description \nGoat Chan - Enanare's OC!\n\nTrained based on her appareance, it has a trigger word corresponding to the appearance of the character and suggested prompts that summons related clothes and accesories.\n\nWorks well with 0.7-1.0 weight## Trigger words\n\nDefault Appareance: 'goatchandef, huge breasts, goat ears, goat horns, tail,' 'Pubic tattoo/crotch tattoo'## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab.### License\n\nThis LoRA model is provided under the Fair AI Public License 1.0-SD license.## Restrictions:\n\n- Usage in Generation Services: You are not allowed to use the model in any generation services without proper permission from the original creator.\n\n- Commercial Usage: The sale of the model or any commercial usage is strictly prohibited without explicit written permission from the original creator." ]

[ "transformers", "safetensors", "gemma", "text-generation", "text-generation-inference", "unsloth", "trl", "en", "base_model:unsloth/gemma-2b-bnb-4bit", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

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

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

[ 69, 78 ]

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

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

[ "1910.09700" ]

[]

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

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

[ 44, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

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

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

[ "1910.09700" ]

[]

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

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

[ 26, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

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

[ "license:creativeml-openrail-m", "region:us" ]

[]

[]

[]

[ "TAGS\n#license-creativeml-openrail-m #region-us \n" ]

[ 15 ]

[ "TAGS\n#license-creativeml-openrail-m #region-us \n" ]

[ "license:creativeml-openrail-m", "region:us" ]

[]

[]

[]

[ "TAGS\n#license-creativeml-openrail-m #region-us \n" ]

[ 15 ]

[ "TAGS\n#license-creativeml-openrail-m #region-us \n" ]

[ "transformers", "llama", "text-generation", "pruna-ai", "base_model:UnicomLLM/Unichat-llama3-Chinese-8B", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.", "## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with hqq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.", "## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo UnicomLLM/Unichat-llama3-Chinese-8B installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.", "## Configurations\n\nThe configuration info are in 'smash_config.json'.", "## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model UnicomLLM/Unichat-llama3-Chinese-8B before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.", "## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ "TAGS\n#transformers #llama #text-generation #pruna-ai #base_model-UnicomLLM/Unichat-llama3-Chinese-8B #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.", "## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with hqq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.", "## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo UnicomLLM/Unichat-llama3-Chinese-8B installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.", "## Configurations\n\nThe configuration info are in 'smash_config.json'.", "## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model UnicomLLM/Unichat-llama3-Chinese-8B before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.", "## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ 57, 83, 451, 76, 19, 71, 36 ]

[ "TAGS\n#transformers #llama #text-generation #pruna-ai #base_model-UnicomLLM/Unichat-llama3-Chinese-8B #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with hqq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo UnicomLLM/Unichat-llama3-Chinese-8B installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.## Configurations\n\nThe configuration info are in 'smash_config.json'.## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model UnicomLLM/Unichat-llama3-Chinese-8B before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ "license:creativeml-openrail-m", "region:us" ]

[]

[]

[]

[ "TAGS\n#license-creativeml-openrail-m #region-us \n" ]

[ 15 ]

[ "TAGS\n#license-creativeml-openrail-m #region-us \n" ]

[ "transformers", "gemma", "text-generation", "pruna-ai", "base_model:google/codegemma-2b", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.", "## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with hqq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.", "## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo google/codegemma-2b installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.", "## Configurations\n\nThe configuration info are in 'smash_config.json'.", "## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model google/codegemma-2b before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.", "## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ "TAGS\n#transformers #gemma #text-generation #pruna-ai #base_model-google/codegemma-2b #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.", "## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with hqq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.", "## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo google/codegemma-2b installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.", "## Configurations\n\nThe configuration info are in 'smash_config.json'.", "## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model google/codegemma-2b before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.", "## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ 47, 83, 451, 67, 19, 62, 36 ]

[ "TAGS\n#transformers #gemma #text-generation #pruna-ai #base_model-google/codegemma-2b #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with hqq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo google/codegemma-2b installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.## Configurations\n\nThe configuration info are in 'smash_config.json'.## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model google/codegemma-2b before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ "transformers", "safetensors", "mixtral", "text-generation", "generated_from_trainer", "axolotl", "conversational", "en", "dataset:cognitivecomputations/Dolphin-2.9", "dataset:teknium/OpenHermes-2.5", "dataset:m-a-p/CodeFeedback-Filtered-Instruction", "dataset:cognitivecomputations/dolphin-coder", "dataset:cognitivecomputations/samantha-data", "dataset:HuggingFaceH4/ultrachat_200k", "dataset:microsoft/orca-math-word-problems-200k", "dataset:abacusai/SystemChat-1.1", "dataset:Locutusque/function-calling-chatml", "dataset:internlm/Agent-FLAN", "base_model:mistral-community/Mixtral-8x22B-v0.1", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us", "has_space" ]

[]

[ "en" ]

[ "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0.dev0\n* Pytorch 2.2.2+cu121\n* Datasets 2.15.0\n* Tokenizers 0.15.0" ]

[ "TAGS\n#transformers #safetensors #mixtral #text-generation #generated_from_trainer #axolotl #conversational #en #dataset-cognitivecomputations/Dolphin-2.9 #dataset-teknium/OpenHermes-2.5 #dataset-m-a-p/CodeFeedback-Filtered-Instruction #dataset-cognitivecomputations/dolphin-coder #dataset-cognitivecomputations/samantha-data #dataset-HuggingFaceH4/ultrachat_200k #dataset-microsoft/orca-math-word-problems-200k #dataset-abacusai/SystemChat-1.1 #dataset-Locutusque/function-calling-chatml #dataset-internlm/Agent-FLAN #base_model-mistral-community/Mixtral-8x22B-v0.1 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us #has_space \n", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0.dev0\n* Pytorch 2.2.2+cu121\n* Datasets 2.15.0\n* Tokenizers 0.15.0" ]

[ 228, 5, 47 ]

[ "TAGS\n#transformers #safetensors #mixtral #text-generation #generated_from_trainer #axolotl #conversational #en #dataset-cognitivecomputations/Dolphin-2.9 #dataset-teknium/OpenHermes-2.5 #dataset-m-a-p/CodeFeedback-Filtered-Instruction #dataset-cognitivecomputations/dolphin-coder #dataset-cognitivecomputations/samantha-data #dataset-HuggingFaceH4/ultrachat_200k #dataset-microsoft/orca-math-word-problems-200k #dataset-abacusai/SystemChat-1.1 #dataset-Locutusque/function-calling-chatml #dataset-internlm/Agent-FLAN #base_model-mistral-community/Mixtral-8x22B-v0.1 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us #has_space \n### Training results### Framework versions\n\n\n* Transformers 4.40.0.dev0\n* Pytorch 2.2.2+cu121\n* Datasets 2.15.0\n* Tokenizers 0.15.0" ]

[ "transformers", "llama", "text-generation", "pruna-ai", "base_model:UnicomLLM/Unichat-llama3-Chinese-8B", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.", "## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with hqq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.", "## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo UnicomLLM/Unichat-llama3-Chinese-8B installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.", "## Configurations\n\nThe configuration info are in 'smash_config.json'.", "## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model UnicomLLM/Unichat-llama3-Chinese-8B before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.", "## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ "TAGS\n#transformers #llama #text-generation #pruna-ai #base_model-UnicomLLM/Unichat-llama3-Chinese-8B #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.", "## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with hqq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.", "## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo UnicomLLM/Unichat-llama3-Chinese-8B installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.", "## Configurations\n\nThe configuration info are in 'smash_config.json'.", "## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model UnicomLLM/Unichat-llama3-Chinese-8B before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.", "## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ 57, 83, 451, 76, 19, 71, 36 ]

[ "TAGS\n#transformers #llama #text-generation #pruna-ai #base_model-UnicomLLM/Unichat-llama3-Chinese-8B #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with hqq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo UnicomLLM/Unichat-llama3-Chinese-8B installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.## Configurations\n\nThe configuration info are in 'smash_config.json'.## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model UnicomLLM/Unichat-llama3-Chinese-8B before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ "transformers", "gemma", "text-generation", "pruna-ai", "base_model:google/gemma-7b", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.", "## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with hqq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.", "## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo google/gemma-7b installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.", "## Configurations\n\nThe configuration info are in 'smash_config.json'.", "## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model google/gemma-7b before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.", "## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ "TAGS\n#transformers #gemma #text-generation #pruna-ai #base_model-google/gemma-7b #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.", "## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with hqq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.", "## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo google/gemma-7b installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.", "## Configurations\n\nThe configuration info are in 'smash_config.json'.", "## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model google/gemma-7b before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.", "## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ 45, 83, 451, 65, 19, 60, 36 ]

[ "TAGS\n#transformers #gemma #text-generation #pruna-ai #base_model-google/gemma-7b #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with hqq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo google/gemma-7b installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.## Configurations\n\nThe configuration info are in 'smash_config.json'.## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model google/gemma-7b before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ "transformers", "text-generation-inference", "unsloth", "gemma", "trl", "en", "base_model:unsloth/gemma-2b-bnb-4bit", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

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

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

[ 56, 78 ]

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

[ "diffusers", "text-to-image", "stable-diffusion", "lora", "template:sd-lora", "base_model:runwayml/stable-diffusion-v1-5", "license:creativeml-openrail-m", "region:us" ]

[]

[]

[ "# Dottore\n\n<Gallery />", "## Trigger words\n\nYou should use '1boy' to trigger the image generation.", "## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab." ]

[ "TAGS\n#diffusers #text-to-image #stable-diffusion #lora #template-sd-lora #base_model-runwayml/stable-diffusion-v1-5 #license-creativeml-openrail-m #region-us \n", "# Dottore\n\n<Gallery />", "## Trigger words\n\nYou should use '1boy' to trigger the image generation.", "## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab." ]

[ 54, 7, 17, 25 ]

[ "TAGS\n#diffusers #text-to-image #stable-diffusion #lora #template-sd-lora #base_model-runwayml/stable-diffusion-v1-5 #license-creativeml-openrail-m #region-us \n# Dottore\n\n<Gallery />## Trigger words\n\nYou should use '1boy' to trigger the image generation.## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab." ]

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

[ "1910.09700" ]

[]

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

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

[ 47, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

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

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

[ "1910.09700" ]

[]

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

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

[ 22, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

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

[ "gguf", "facebook", "meta", "pytorch", "llama", "llama-3", "text-generation", "en", "license:other", "has_space", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#gguf #facebook #meta #pytorch #llama #llama-3 #text-generation #en #license-other #has_space #region-us \n" ]

[ 40 ]

[ "TAGS\n#gguf #facebook #meta #pytorch #llama #llama-3 #text-generation #en #license-other #has_space #region-us \n" ]

[ "transformers", "gemma", "text-generation", "pruna-ai", "base_model:google/gemma-7b-it", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.", "## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with hqq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.", "## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo google/gemma-7b-it installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.", "## Configurations\n\nThe configuration info are in 'smash_config.json'.", "## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model google/gemma-7b-it before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.", "## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ "TAGS\n#transformers #gemma #text-generation #pruna-ai #base_model-google/gemma-7b-it #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.", "## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with hqq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.", "## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo google/gemma-7b-it installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.", "## Configurations\n\nThe configuration info are in 'smash_config.json'.", "## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model google/gemma-7b-it before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.", "## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ 47, 83, 451, 67, 19, 62, 36 ]

[ "TAGS\n#transformers #gemma #text-generation #pruna-ai #base_model-google/gemma-7b-it #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with hqq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo google/gemma-7b-it installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.## Configurations\n\nThe configuration info are in 'smash_config.json'.## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model google/gemma-7b-it before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ "transformers", "safetensors", "vit_sit", "self-supervised learning", "vision", "SiT", "arxiv:2104.03602", "license:apache-2.0", "region:us" ]

[ "2104.03602" ]

[]

[ "# Model description\n\nSiT is a self-supervised learning model that combines masked image modeling and contrastive learning. The model is trained on ImageNet-1K.", "# Model Sources\n\n- URL\n- URL", "# Model Card Authors \nSara Atito, Muhammad Awais, Josef Kittler", "# How to use", "# BibTeX entry and citation info" ]

[ "TAGS\n#transformers #safetensors #vit_sit #self-supervised learning #vision #SiT #arxiv-2104.03602 #license-apache-2.0 #region-us \n", "# Model description\n\nSiT is a self-supervised learning model that combines masked image modeling and contrastive learning. The model is trained on ImageNet-1K.", "# Model Sources\n\n- URL\n- URL", "# Model Card Authors \nSara Atito, Muhammad Awais, Josef Kittler", "# How to use", "# BibTeX entry and citation info" ]

[ 44, 32, 9, 15, 4, 8 ]

[ "TAGS\n#transformers #safetensors #vit_sit #self-supervised learning #vision #SiT #arxiv-2104.03602 #license-apache-2.0 #region-us \n# Model description\n\nSiT is a self-supervised learning model that combines masked image modeling and contrastive learning. The model is trained on ImageNet-1K.# Model Sources\n\n- URL\n- URL# Model Card Authors \nSara Atito, Muhammad Awais, Josef Kittler# How to use# BibTeX entry and citation info" ]

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

[ "1910.09700" ]

[]

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

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

[ 30, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

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

[ "transformers", "safetensors", "gemma", "text-generation", "pruna-ai", "base_model:google/gemma-2b-it", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]

[]

[]

[ "# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.", "## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with awq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.", "## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo google/gemma-2b-it installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.", "## Configurations\n\nThe configuration info are in 'smash_config.json'.", "## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model google/gemma-2b-it before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.", "## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ "TAGS\n#transformers #safetensors #gemma #text-generation #pruna-ai #base_model-google/gemma-2b-it #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n", "# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.", "## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with awq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.", "## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo google/gemma-2b-it installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.", "## Configurations\n\nThe configuration info are in 'smash_config.json'.", "## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model google/gemma-2b-it before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.", "## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ 55, 83, 451, 67, 19, 62, 36 ]

[ "TAGS\n#transformers #safetensors #gemma #text-generation #pruna-ai #base_model-google/gemma-2b-it #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with awq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo google/gemma-2b-it installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.## Configurations\n\nThe configuration info are in 'smash_config.json'.## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model google/gemma-2b-it before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ "transformers", "gemma", "text-generation", "pruna-ai", "base_model:google/codegemma-7b", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.", "## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with hqq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.", "## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo google/codegemma-7b installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.", "## Configurations\n\nThe configuration info are in 'smash_config.json'.", "## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model google/codegemma-7b before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.", "## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ "TAGS\n#transformers #gemma #text-generation #pruna-ai #base_model-google/codegemma-7b #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.", "## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with hqq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.", "## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo google/codegemma-7b installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.", "## Configurations\n\nThe configuration info are in 'smash_config.json'.", "## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model google/codegemma-7b before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.", "## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ 47, 83, 451, 67, 19, 62, 36 ]

[ "TAGS\n#transformers #gemma #text-generation #pruna-ai #base_model-google/codegemma-7b #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with hqq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo google/codegemma-7b installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.## Configurations\n\nThe configuration info are in 'smash_config.json'.## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model google/codegemma-7b before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ "transformers", "safetensors", "gemma", "text-generation", "pruna-ai", "base_model:google/gemma-2b", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]

[]

[]

[ "# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.", "## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with awq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.", "## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo google/gemma-2b installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.", "## Configurations\n\nThe configuration info are in 'smash_config.json'.", "## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model google/gemma-2b before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.", "## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ "TAGS\n#transformers #safetensors #gemma #text-generation #pruna-ai #base_model-google/gemma-2b #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n", "# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.", "## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with awq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.", "## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo google/gemma-2b installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.", "## Configurations\n\nThe configuration info are in 'smash_config.json'.", "## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model google/gemma-2b before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.", "## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ 53, 83, 451, 65, 19, 60, 36 ]

[ "TAGS\n#transformers #safetensors #gemma #text-generation #pruna-ai #base_model-google/gemma-2b #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with awq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo google/gemma-2b installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.## Configurations\n\nThe configuration info are in 'smash_config.json'.## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model google/gemma-2b before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:roberta-large", "license:mit", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.001\n* train\\_batch\\_size: 96\n* eval\\_batch\\_size: 96\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 2", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.40.1\n* Pytorch 2.3.0+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-roberta-large #license-mit #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.001\n* train\\_batch\\_size: 96\n* eval\\_batch\\_size: 96\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 2", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.40.1\n* Pytorch 2.3.0+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ 30, 100, 5, 52 ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-roberta-large #license-mit #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.001\n* train\\_batch\\_size: 96\n* eval\\_batch\\_size: 96\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 2### Training results### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.40.1\n* Pytorch 2.3.0+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "transformers", "safetensors", "gemma", "text-generation", "pruna-ai", "base_model:google/codegemma-2b", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]

[]

[]

[ "# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.", "## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with awq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.", "## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo google/codegemma-2b installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.", "## Configurations\n\nThe configuration info are in 'smash_config.json'.", "## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model google/codegemma-2b before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.", "## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ "TAGS\n#transformers #safetensors #gemma #text-generation #pruna-ai #base_model-google/codegemma-2b #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n", "# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.", "## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with awq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.", "## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo google/codegemma-2b installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.", "## Configurations\n\nThe configuration info are in 'smash_config.json'.", "## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model google/codegemma-2b before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.", "## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ 55, 83, 451, 67, 19, 62, 36 ]

[ "TAGS\n#transformers #safetensors #gemma #text-generation #pruna-ai #base_model-google/codegemma-2b #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with awq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo google/codegemma-2b installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.## Configurations\n\nThe configuration info are in 'smash_config.json'.## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model google/codegemma-2b before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

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

[ "1910.09700" ]

[]

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

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

[ 30, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

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

[ "fastai", "has_space", "region:us" ]

[]

[]

[ "# Amazing!\n\n Congratulations on hosting your fastai model on the Hugging Face Hub!", "# Some next steps\n1. Fill out this model card with more information (see the template below and the documentation here)!\n\n2. Create a demo in Gradio or Streamlit using Spaces (documentation here).\n\n3. Join the fastai community on the Fastai Discord!\n\nGreetings fellow fastlearner ! Don't forget to delete this content from your model card.\n\n\n---", "# Model card", "## Model description\nMore information needed", "## Intended uses & limitations\nMore information needed", "## Training and evaluation data\nMore information needed" ]

[ "TAGS\n#fastai #has_space #region-us \n", "# Amazing!\n\n Congratulations on hosting your fastai model on the Hugging Face Hub!", "# Some next steps\n1. Fill out this model card with more information (see the template below and the documentation here)!\n\n2. Create a demo in Gradio or Streamlit using Spaces (documentation here).\n\n3. Join the fastai community on the Fastai Discord!\n\nGreetings fellow fastlearner ! Don't forget to delete this content from your model card.\n\n\n---", "# Model card", "## Model description\nMore information needed", "## Intended uses & limitations\nMore information needed", "## Training and evaluation data\nMore information needed" ]

[ 12, 16, 82, 3, 7, 9, 9 ]

[ "TAGS\n#fastai #has_space #region-us \n# Amazing!\n\n Congratulations on hosting your fastai model on the Hugging Face Hub!# Some next steps\n1. Fill out this model card with more information (see the template below and the documentation here)!\n\n2. Create a demo in Gradio or Streamlit using Spaces (documentation here).\n\n3. Join the fastai community on the Fastai Discord!\n\nGreetings fellow fastlearner ! Don't forget to delete this content from your model card.\n\n\n---# Model card## Model description\nMore information needed## Intended uses & limitations\nMore information needed## Training and evaluation data\nMore information needed" ]

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

[ "1910.09700" ]

[]

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

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

[ 55, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

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

[ "transformers", "pytorch", "llama", "text-generation", "llama-3", "instruct", "finetune", "synthetic data", "distillation", "conversational", "en", "base_model:meta-llama/Meta-Llama-3-70B", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[ "en" ]

[ "# Wizard-llama3-70B\n\n\n\n!URL", "## Model description\n\nWizard-llama3-70B is the fine tune of llama3 70b on top of public datasets and some additional code datasets. model uses ChatML prompt template format.\n\nWizard-llama3-70B has a variety of instruction, logic and coding skills. It also has initial agentic abilities and supports function calling.\n\ntried to make the model as uncensored as possible ." ]

[ "TAGS\n#transformers #pytorch #llama #text-generation #llama-3 #instruct #finetune #synthetic data #distillation #conversational #en #base_model-meta-llama/Meta-Llama-3-70B #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Wizard-llama3-70B\n\n\n\n!URL", "## Model description\n\nWizard-llama3-70B is the fine tune of llama3 70b on top of public datasets and some additional code datasets. model uses ChatML prompt template format.\n\nWizard-llama3-70B has a variety of instruction, logic and coding skills. It also has initial agentic abilities and supports function calling.\n\ntried to make the model as uncensored as possible ." ]

[ 82, 12, 88 ]

[ "TAGS\n#transformers #pytorch #llama #text-generation #llama-3 #instruct #finetune #synthetic data #distillation #conversational #en #base_model-meta-llama/Meta-Llama-3-70B #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# Wizard-llama3-70B\n\n\n\n!URL## Model description\n\nWizard-llama3-70B is the fine tune of llama3 70b on top of public datasets and some additional code datasets. model uses ChatML prompt template format.\n\nWizard-llama3-70B has a variety of instruction, logic and coding skills. It also has initial agentic abilities and supports function calling.\n\ntried to make the model as uncensored as possible ." ]

[ "transformers", "safetensors", "llava_mistral", "text-generation", "Mistral", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "synthetic data", "distillation", "function calling", "json mode", "llava", "vision", "multimodal", "conversational", "en", "dataset:teknium/OpenHermes-2.5", "dataset:SkunkworksAI/BakLLaVA-1-FT", "base_model:NousResearch/Hermes-2-Pro-Mistral-7B", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[ "# Hermes 2 Pro BakLLaVA - Mistral 7B\n\nHermes 2 Pro's LLaMA weights + BakLLaVA's mm_projector & vision_tower weights.\n\nGood QA + Function Calling + JSON Mode + Vision Multimodal\n\nGGUFs:\n- Hermes 2 pro: URL\n- BakLLaVA-1: URL\n\n\nTest code:\n\n\nExample:\n!image/png" ]

[ "TAGS\n#transformers #safetensors #llava_mistral #text-generation #Mistral #instruct #finetune #chatml #DPO #RLHF #gpt4 #synthetic data #distillation #function calling #json mode #llava #vision #multimodal #conversational #en #dataset-teknium/OpenHermes-2.5 #dataset-SkunkworksAI/BakLLaVA-1-FT #base_model-NousResearch/Hermes-2-Pro-Mistral-7B #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "# Hermes 2 Pro BakLLaVA - Mistral 7B\n\nHermes 2 Pro's LLaMA weights + BakLLaVA's mm_projector & vision_tower weights.\n\nGood QA + Function Calling + JSON Mode + Vision Multimodal\n\nGGUFs:\n- Hermes 2 pro: URL\n- BakLLaVA-1: URL\n\n\nTest code:\n\n\nExample:\n!image/png" ]

[ 146, 84 ]

[ "TAGS\n#transformers #safetensors #llava_mistral #text-generation #Mistral #instruct #finetune #chatml #DPO #RLHF #gpt4 #synthetic data #distillation #function calling #json mode #llava #vision #multimodal #conversational #en #dataset-teknium/OpenHermes-2.5 #dataset-SkunkworksAI/BakLLaVA-1-FT #base_model-NousResearch/Hermes-2-Pro-Mistral-7B #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n# Hermes 2 Pro BakLLaVA - Mistral 7B\n\nHermes 2 Pro's LLaMA weights + BakLLaVA's mm_projector & vision_tower weights.\n\nGood QA + Function Calling + JSON Mode + Vision Multimodal\n\nGGUFs:\n- Hermes 2 pro: URL\n- BakLLaVA-1: URL\n\n\nTest code:\n\n\nExample:\n!image/png" ]

[ "sentence-transformers", "safetensors", "bert", "sentence-similarity", "feature-extraction", "loss:MSELoss", "en", "arxiv:1908.10084", "arxiv:2004.09813", "base_model:nreimers/TinyBERT_L-4_H-312_v2", "model-index", "co2_eq_emissions", "endpoints_compatible", "region:us" ]

[ "1908.10084", "2004.09813" ]

[ "en" ]

[ "### Model Description\n\n\n* Model Type: Sentence Transformer\n* Base model: nreimers/TinyBERT\\_L-4\\_H-312\\_v2\n* Maximum Sequence Length: 512 tokens\n* Output Dimensionality: 312 tokens\n* Similarity Function: Cosine Similarity\n* Training Dataset:\n\t+ sentence-transformers/wikipedia-en-sentences\n* Language: en", "### Model Sources\n\n\n* Documentation: Sentence Transformers Documentation\n* Repository: Sentence Transformers on GitHub\n* Hugging Face: Sentence Transformers on Hugging Face", "### Full Model Architecture\n\n\nUsage\n-----", "### Direct Usage (Sentence Transformers)\n\n\nFirst install the Sentence Transformers library:\n\n\nThen you can load this model and run inference.\n\n\nEvaluation\n----------", "### Metrics", "#### Semantic Similarity\n\n\n* Dataset: 'sts-dev'\n* Evaluated with `EmbeddingSimilarityEvaluator`", "#### Knowledge Distillation\n\n\n* Evaluated with `MSEEvaluator`", "#### Semantic Similarity\n\n\n* Dataset: 'sts-test'\n* Evaluated with `EmbeddingSimilarityEvaluator`\n\n\n\nTraining Details\n----------------", "### Training Dataset", "#### sentence-transformers/wikipedia-en-sentences\n\n\n* Dataset: sentence-transformers/wikipedia-en-sentences at 4a0972d\n* Size: 200,000 training samples\n* Columns: `sentence` and `label`\n* Approximate statistics based on the first 1000 samples:\n* Samples:\n* Loss: `MSELoss`", "### Evaluation Dataset", "#### sentence-transformers/wikipedia-en-sentences\n\n\n* Dataset: sentence-transformers/wikipedia-en-sentences at 4a0972d\n* Size: 10,000 evaluation samples\n* Columns: `sentence` and `label`\n* Approximate statistics based on the first 1000 samples:\n* Samples:\n* Loss: `MSELoss`", "### Training Hyperparameters", "#### Non-Default Hyperparameters\n\n\n* 'eval\\_strategy': steps\n* 'per\\_device\\_train\\_batch\\_size': 64\n* 'per\\_device\\_eval\\_batch\\_size': 64\n* 'learning\\_rate': 0.0001\n* 'num\\_train\\_epochs': 1\n* 'warmup\\_ratio': 0.1\n* 'fp16': True\n* 'load\\_best\\_model\\_at\\_end': True", "#### All Hyperparameters\n\n\nClick to expand\n* 'overwrite\\_output\\_dir': False\n* 'do\\_predict': False\n* 'eval\\_strategy': steps\n* 'prediction\\_loss\\_only': False\n* 'per\\_device\\_train\\_batch\\_size': 64\n* 'per\\_device\\_eval\\_batch\\_size': 64\n* 'per\\_gpu\\_train\\_batch\\_size': None\n* 'per\\_gpu\\_eval\\_batch\\_size': None\n* 'gradient\\_accumulation\\_steps': 1\n* 'eval\\_accumulation\\_steps': None\n* 'learning\\_rate': 0.0001\n* 'weight\\_decay': 0.0\n* 'adam\\_beta1': 0.9\n* 'adam\\_beta2': 0.999\n* 'adam\\_epsilon': 1e-08\n* 'max\\_grad\\_norm': 1.0\n* 'num\\_train\\_epochs': 1\n* 'max\\_steps': -1\n* 'lr\\_scheduler\\_type': linear\n* 'lr\\_scheduler\\_kwargs': {}\n* 'warmup\\_ratio': 0.1\n* 'warmup\\_steps': 0\n* 'log\\_level': passive\n* 'log\\_level\\_replica': warning\n* 'log\\_on\\_each\\_node': True\n* 'logging\\_nan\\_inf\\_filter': True\n* 'save\\_safetensors': True\n* 'save\\_on\\_each\\_node': False\n* 'save\\_only\\_model': False\n* 'no\\_cuda': False\n* 'use\\_cpu': False\n* 'use\\_mps\\_device': False\n* 'seed': 42\n* 'data\\_seed': None\n* 'jit\\_mode\\_eval': False\n* 'use\\_ipex': False\n* 'bf16': False\n* 'fp16': True\n* 'fp16\\_opt\\_level': O1\n* 'half\\_precision\\_backend': auto\n* 'bf16\\_full\\_eval': False\n* 'fp16\\_full\\_eval': False\n* 'tf32': None\n* 'local\\_rank': 0\n* 'ddp\\_backend': None\n* 'tpu\\_num\\_cores': None\n* 'tpu\\_metrics\\_debug': False\n* 'debug': []\n* 'dataloader\\_drop\\_last': False\n* 'dataloader\\_num\\_workers': 0\n* 'dataloader\\_prefetch\\_factor': None\n* 'past\\_index': -1\n* 'disable\\_tqdm': False\n* 'remove\\_unused\\_columns': True\n* 'label\\_names': None\n* 'load\\_best\\_model\\_at\\_end': True\n* 'ignore\\_data\\_skip': False\n* 'fsdp': []\n* 'fsdp\\_min\\_num\\_params': 0\n* 'fsdp\\_config': {'min\\_num\\_params': 0, 'xla': False, 'xla\\_fsdp\\_v2': False, 'xla\\_fsdp\\_grad\\_ckpt': False}\n* 'fsdp\\_transformer\\_layer\\_cls\\_to\\_wrap': None\n* 'accelerator\\_config': {'split\\_batches': False, 'dispatch\\_batches': None, 'even\\_batches': True, 'use\\_seedable\\_sampler': True, 'non\\_blocking': False, 'gradient\\_accumulation\\_kwargs': None}\n* 'deepspeed': None\n* 'label\\_smoothing\\_factor': 0.0\n* 'optim': adamw\\_torch\n* 'optim\\_args': None\n* 'adafactor': False\n* 'group\\_by\\_length': False\n* 'length\\_column\\_name': length\n* 'ddp\\_find\\_unused\\_parameters': None\n* 'ddp\\_bucket\\_cap\\_mb': None\n* 'ddp\\_broadcast\\_buffers': None\n* 'dataloader\\_pin\\_memory': True\n* 'dataloader\\_persistent\\_workers': False\n* 'skip\\_memory\\_metrics': True\n* 'use\\_legacy\\_prediction\\_loop': False\n* 'push\\_to\\_hub': False\n* 'resume\\_from\\_checkpoint': None\n* 'hub\\_model\\_id': None\n* 'hub\\_strategy': every\\_save\n* 'hub\\_private\\_repo': False\n* 'hub\\_always\\_push': False\n* 'gradient\\_checkpointing': False\n* 'gradient\\_checkpointing\\_kwargs': None\n* 'include\\_inputs\\_for\\_metrics': False\n* 'eval\\_do\\_concat\\_batches': True\n* 'fp16\\_backend': auto\n* 'push\\_to\\_hub\\_model\\_id': None\n* 'push\\_to\\_hub\\_organization': None\n* 'mp\\_parameters':\n* 'auto\\_find\\_batch\\_size': False\n* 'full\\_determinism': False\n* 'torchdynamo': None\n* 'ray\\_scope': last\n* 'ddp\\_timeout': 1800\n* 'torch\\_compile': False\n* 'torch\\_compile\\_backend': None\n* 'torch\\_compile\\_mode': None\n* 'dispatch\\_batches': None\n* 'split\\_batches': None\n* 'include\\_tokens\\_per\\_second': False\n* 'include\\_num\\_input\\_tokens\\_seen': False\n* 'neftune\\_noise\\_alpha': None\n* 'optim\\_target\\_modules': None\n* 'batch\\_sampler': batch\\_sampler\n* 'multi\\_dataset\\_batch\\_sampler': proportional", "### Training Logs\n\n\n\n* The bold row denotes the saved checkpoint.", "### Environmental Impact\n\n\nCarbon emissions were measured using CodeCarbon.\n\n\n* Energy Consumed: 0.009 kWh\n* Carbon Emitted: 0.003 kg of CO2\n* Hours Used: 0.054 hours", "### Training Hardware\n\n\n* On Cloud: No\n* GPU Model: 1 x NVIDIA GeForce RTX 3090\n* CPU Model: 13th Gen Intel(R) Core(TM) i7-13700K\n* RAM Size: 31.78 GB", "### Framework Versions\n\n\n* Python: 3.11.6\n* Sentence Transformers: 3.0.0.dev0\n* Transformers: 4.41.0.dev0\n* PyTorch: 2.3.0+cu121\n* Accelerate: 0.26.1\n* Datasets: 2.18.0\n* Tokenizers: 0.19.1", "### BibTeX", "#### Sentence Transformers", "#### MSELoss" ]

[ "TAGS\n#sentence-transformers #safetensors #bert #sentence-similarity #feature-extraction #loss-MSELoss #en #arxiv-1908.10084 #arxiv-2004.09813 #base_model-nreimers/TinyBERT_L-4_H-312_v2 #model-index #co2_eq_emissions #endpoints_compatible #region-us \n", "### Model Description\n\n\n* Model Type: Sentence Transformer\n* Base model: nreimers/TinyBERT\\_L-4\\_H-312\\_v2\n* Maximum Sequence Length: 512 tokens\n* Output Dimensionality: 312 tokens\n* Similarity Function: Cosine Similarity\n* Training Dataset:\n\t+ sentence-transformers/wikipedia-en-sentences\n* Language: en", "### Model Sources\n\n\n* Documentation: Sentence Transformers Documentation\n* Repository: Sentence Transformers on GitHub\n* Hugging Face: Sentence Transformers on Hugging Face", "### Full Model Architecture\n\n\nUsage\n-----", "### Direct Usage (Sentence Transformers)\n\n\nFirst install the Sentence Transformers library:\n\n\nThen you can load this model and run inference.\n\n\nEvaluation\n----------", "### Metrics", "#### Semantic Similarity\n\n\n* Dataset: 'sts-dev'\n* Evaluated with `EmbeddingSimilarityEvaluator`", "#### Knowledge Distillation\n\n\n* Evaluated with `MSEEvaluator`", "#### Semantic Similarity\n\n\n* Dataset: 'sts-test'\n* Evaluated with `EmbeddingSimilarityEvaluator`\n\n\n\nTraining Details\n----------------", "### Training Dataset", "#### sentence-transformers/wikipedia-en-sentences\n\n\n* Dataset: sentence-transformers/wikipedia-en-sentences at 4a0972d\n* Size: 200,000 training samples\n* Columns: `sentence` and `label`\n* Approximate statistics based on the first 1000 samples:\n* Samples:\n* Loss: `MSELoss`", "### Evaluation Dataset", "#### sentence-transformers/wikipedia-en-sentences\n\n\n* Dataset: sentence-transformers/wikipedia-en-sentences at 4a0972d\n* Size: 10,000 evaluation samples\n* Columns: `sentence` and `label`\n* Approximate statistics based on the first 1000 samples:\n* Samples:\n* Loss: `MSELoss`", "### Training Hyperparameters", "#### Non-Default Hyperparameters\n\n\n* 'eval\\_strategy': steps\n* 'per\\_device\\_train\\_batch\\_size': 64\n* 'per\\_device\\_eval\\_batch\\_size': 64\n* 'learning\\_rate': 0.0001\n* 'num\\_train\\_epochs': 1\n* 'warmup\\_ratio': 0.1\n* 'fp16': True\n* 'load\\_best\\_model\\_at\\_end': True", "#### All Hyperparameters\n\n\nClick to expand\n* 'overwrite\\_output\\_dir': False\n* 'do\\_predict': False\n* 'eval\\_strategy': steps\n* 'prediction\\_loss\\_only': False\n* 'per\\_device\\_train\\_batch\\_size': 64\n* 'per\\_device\\_eval\\_batch\\_size': 64\n* 'per\\_gpu\\_train\\_batch\\_size': None\n* 'per\\_gpu\\_eval\\_batch\\_size': None\n* 'gradient\\_accumulation\\_steps': 1\n* 'eval\\_accumulation\\_steps': None\n* 'learning\\_rate': 0.0001\n* 'weight\\_decay': 0.0\n* 'adam\\_beta1': 0.9\n* 'adam\\_beta2': 0.999\n* 'adam\\_epsilon': 1e-08\n* 'max\\_grad\\_norm': 1.0\n* 'num\\_train\\_epochs': 1\n* 'max\\_steps': -1\n* 'lr\\_scheduler\\_type': linear\n* 'lr\\_scheduler\\_kwargs': {}\n* 'warmup\\_ratio': 0.1\n* 'warmup\\_steps': 0\n* 'log\\_level': passive\n* 'log\\_level\\_replica': warning\n* 'log\\_on\\_each\\_node': True\n* 'logging\\_nan\\_inf\\_filter': True\n* 'save\\_safetensors': True\n* 'save\\_on\\_each\\_node': False\n* 'save\\_only\\_model': False\n* 'no\\_cuda': False\n* 'use\\_cpu': False\n* 'use\\_mps\\_device': False\n* 'seed': 42\n* 'data\\_seed': None\n* 'jit\\_mode\\_eval': False\n* 'use\\_ipex': False\n* 'bf16': False\n* 'fp16': True\n* 'fp16\\_opt\\_level': O1\n* 'half\\_precision\\_backend': auto\n* 'bf16\\_full\\_eval': False\n* 'fp16\\_full\\_eval': False\n* 'tf32': None\n* 'local\\_rank': 0\n* 'ddp\\_backend': None\n* 'tpu\\_num\\_cores': None\n* 'tpu\\_metrics\\_debug': False\n* 'debug': []\n* 'dataloader\\_drop\\_last': False\n* 'dataloader\\_num\\_workers': 0\n* 'dataloader\\_prefetch\\_factor': None\n* 'past\\_index': -1\n* 'disable\\_tqdm': False\n* 'remove\\_unused\\_columns': True\n* 'label\\_names': None\n* 'load\\_best\\_model\\_at\\_end': True\n* 'ignore\\_data\\_skip': False\n* 'fsdp': []\n* 'fsdp\\_min\\_num\\_params': 0\n* 'fsdp\\_config': {'min\\_num\\_params': 0, 'xla': False, 'xla\\_fsdp\\_v2': False, 'xla\\_fsdp\\_grad\\_ckpt': False}\n* 'fsdp\\_transformer\\_layer\\_cls\\_to\\_wrap': None\n* 'accelerator\\_config': {'split\\_batches': False, 'dispatch\\_batches': None, 'even\\_batches': True, 'use\\_seedable\\_sampler': True, 'non\\_blocking': False, 'gradient\\_accumulation\\_kwargs': None}\n* 'deepspeed': None\n* 'label\\_smoothing\\_factor': 0.0\n* 'optim': adamw\\_torch\n* 'optim\\_args': None\n* 'adafactor': False\n* 'group\\_by\\_length': False\n* 'length\\_column\\_name': length\n* 'ddp\\_find\\_unused\\_parameters': None\n* 'ddp\\_bucket\\_cap\\_mb': None\n* 'ddp\\_broadcast\\_buffers': None\n* 'dataloader\\_pin\\_memory': True\n* 'dataloader\\_persistent\\_workers': False\n* 'skip\\_memory\\_metrics': True\n* 'use\\_legacy\\_prediction\\_loop': False\n* 'push\\_to\\_hub': False\n* 'resume\\_from\\_checkpoint': None\n* 'hub\\_model\\_id': None\n* 'hub\\_strategy': every\\_save\n* 'hub\\_private\\_repo': False\n* 'hub\\_always\\_push': False\n* 'gradient\\_checkpointing': False\n* 'gradient\\_checkpointing\\_kwargs': None\n* 'include\\_inputs\\_for\\_metrics': False\n* 'eval\\_do\\_concat\\_batches': True\n* 'fp16\\_backend': auto\n* 'push\\_to\\_hub\\_model\\_id': None\n* 'push\\_to\\_hub\\_organization': None\n* 'mp\\_parameters':\n* 'auto\\_find\\_batch\\_size': False\n* 'full\\_determinism': False\n* 'torchdynamo': None\n* 'ray\\_scope': last\n* 'ddp\\_timeout': 1800\n* 'torch\\_compile': False\n* 'torch\\_compile\\_backend': None\n* 'torch\\_compile\\_mode': None\n* 'dispatch\\_batches': None\n* 'split\\_batches': None\n* 'include\\_tokens\\_per\\_second': False\n* 'include\\_num\\_input\\_tokens\\_seen': False\n* 'neftune\\_noise\\_alpha': None\n* 'optim\\_target\\_modules': None\n* 'batch\\_sampler': batch\\_sampler\n* 'multi\\_dataset\\_batch\\_sampler': proportional", "### Training Logs\n\n\n\n* The bold row denotes the saved checkpoint.", "### Environmental Impact\n\n\nCarbon emissions were measured using CodeCarbon.\n\n\n* Energy Consumed: 0.009 kWh\n* Carbon Emitted: 0.003 kg of CO2\n* Hours Used: 0.054 hours", "### Training Hardware\n\n\n* On Cloud: No\n* GPU Model: 1 x NVIDIA GeForce RTX 3090\n* CPU Model: 13th Gen Intel(R) Core(TM) i7-13700K\n* RAM Size: 31.78 GB", "### Framework Versions\n\n\n* Python: 3.11.6\n* Sentence Transformers: 3.0.0.dev0\n* Transformers: 4.41.0.dev0\n* PyTorch: 2.3.0+cu121\n* Accelerate: 0.26.1\n* Datasets: 2.18.0\n* Tokenizers: 0.19.1", "### BibTeX", "#### Sentence Transformers", "#### MSELoss" ]

[ 90, 79, 29, 12, 37, 5, 30, 18, 48, 6, 72, 6, 72, 8, 122, 1494, 14, 44, 55, 79, 6, 6, 7 ]

[ "TAGS\n#sentence-transformers #safetensors #bert #sentence-similarity #feature-extraction #loss-MSELoss #en #arxiv-1908.10084 #arxiv-2004.09813 #base_model-nreimers/TinyBERT_L-4_H-312_v2 #model-index #co2_eq_emissions #endpoints_compatible #region-us \n### Model Description\n\n\n* Model Type: Sentence Transformer\n* Base model: nreimers/TinyBERT\\_L-4\\_H-312\\_v2\n* Maximum Sequence Length: 512 tokens\n* Output Dimensionality: 312 tokens\n* Similarity Function: Cosine Similarity\n* Training Dataset:\n\t+ sentence-transformers/wikipedia-en-sentences\n* Language: en### Model Sources\n\n\n* Documentation: Sentence Transformers Documentation\n* Repository: Sentence Transformers on GitHub\n* Hugging Face: Sentence Transformers on Hugging Face### Full Model Architecture\n\n\nUsage\n-----### Direct Usage (Sentence Transformers)\n\n\nFirst install the Sentence Transformers library:\n\n\nThen you can load this model and run inference.\n\n\nEvaluation\n----------### Metrics#### Semantic Similarity\n\n\n* Dataset: 'sts-dev'\n* Evaluated with `EmbeddingSimilarityEvaluator`#### Knowledge Distillation\n\n\n* Evaluated with `MSEEvaluator`#### Semantic Similarity\n\n\n* Dataset: 'sts-test'\n* Evaluated with `EmbeddingSimilarityEvaluator`\n\n\n\nTraining Details\n----------------### Training Dataset#### sentence-transformers/wikipedia-en-sentences\n\n\n* Dataset: sentence-transformers/wikipedia-en-sentences at 4a0972d\n* Size: 200,000 training samples\n* Columns: `sentence` and `label`\n* Approximate statistics based on the first 1000 samples:\n* Samples:\n* Loss: `MSELoss`### Evaluation Dataset#### sentence-transformers/wikipedia-en-sentences\n\n\n* Dataset: sentence-transformers/wikipedia-en-sentences at 4a0972d\n* Size: 10,000 evaluation samples\n* Columns: `sentence` and `label`\n* Approximate statistics based on the first 1000 samples:\n* Samples:\n* Loss: `MSELoss`### Training Hyperparameters#### Non-Default Hyperparameters\n\n\n* 'eval\\_strategy': steps\n* 'per\\_device\\_train\\_batch\\_size': 64\n* 'per\\_device\\_eval\\_batch\\_size': 64\n* 'learning\\_rate': 0.0001\n* 'num\\_train\\_epochs': 1\n* 'warmup\\_ratio': 0.1\n* 'fp16': True\n* 'load\\_best\\_model\\_at\\_end': True#### All Hyperparameters\n\n\nClick to expand\n* 'overwrite\\_output\\_dir': False\n* 'do\\_predict': False\n* 'eval\\_strategy': steps\n* 'prediction\\_loss\\_only': False\n* 'per\\_device\\_train\\_batch\\_size': 64\n* 'per\\_device\\_eval\\_batch\\_size': 64\n* 'per\\_gpu\\_train\\_batch\\_size': None\n* 'per\\_gpu\\_eval\\_batch\\_size': None\n* 'gradient\\_accumulation\\_steps': 1\n* 'eval\\_accumulation\\_steps': None\n* 'learning\\_rate': 0.0001\n* 'weight\\_decay': 0.0\n* 'adam\\_beta1': 0.9\n* 'adam\\_beta2': 0.999\n* 'adam\\_epsilon': 1e-08\n* 'max\\_grad\\_norm': 1.0\n* 'num\\_train\\_epochs': 1\n* 'max\\_steps': -1\n* 'lr\\_scheduler\\_type': linear\n* 'lr\\_scheduler\\_kwargs': {}\n* 'warmup\\_ratio': 0.1\n* 'warmup\\_steps': 0\n* 'log\\_level': passive\n* 'log\\_level\\_replica': warning\n* 'log\\_on\\_each\\_node': True\n* 'logging\\_nan\\_inf\\_filter': True\n* 'save\\_safetensors': True\n* 'save\\_on\\_each\\_node': False\n* 'save\\_only\\_model': False\n* 'no\\_cuda': False\n* 'use\\_cpu': False\n* 'use\\_mps\\_device': False\n* 'seed': 42\n* 'data\\_seed': None\n* 'jit\\_mode\\_eval': False\n* 'use\\_ipex': False\n* 'bf16': False\n* 'fp16': True\n* 'fp16\\_opt\\_level': O1\n* 'half\\_precision\\_backend': auto\n* 'bf16\\_full\\_eval': False\n* 'fp16\\_full\\_eval': False\n* 'tf32': None\n* 'local\\_rank': 0\n* 'ddp\\_backend': None\n* 'tpu\\_num\\_cores': None\n* 'tpu\\_metrics\\_debug': False\n* 'debug': []\n* 'dataloader\\_drop\\_last': False\n* 'dataloader\\_num\\_workers': 0\n* 'dataloader\\_prefetch\\_factor': None\n* 'past\\_index': -1\n* 'disable\\_tqdm': False\n* 'remove\\_unused\\_columns': True\n* 'label\\_names': None\n* 'load\\_best\\_model\\_at\\_end': True\n* 'ignore\\_data\\_skip': False\n* 'fsdp': []\n* 'fsdp\\_min\\_num\\_params': 0\n* 'fsdp\\_config': {'min\\_num\\_params': 0, 'xla': False, 'xla\\_fsdp\\_v2': False, 'xla\\_fsdp\\_grad\\_ckpt': False}\n* 'fsdp\\_transformer\\_layer\\_cls\\_to\\_wrap': None\n* 'accelerator\\_config': {'split\\_batches': False, 'dispatch\\_batches': None, 'even\\_batches': True, 'use\\_seedable\\_sampler': True, 'non\\_blocking': False, 'gradient\\_accumulation\\_kwargs': None}\n* 'deepspeed': None\n* 'label\\_smoothing\\_factor': 0.0\n* 'optim': adamw\\_torch\n* 'optim\\_args': None\n* 'adafactor': False\n* 'group\\_by\\_length': False\n* 'length\\_column\\_name': length\n* 'ddp\\_find\\_unused\\_parameters': None\n* 'ddp\\_bucket\\_cap\\_mb': None\n* 'ddp\\_broadcast\\_buffers': None\n* 'dataloader\\_pin\\_memory': True\n* 'dataloader\\_persistent\\_workers': False\n* 'skip\\_memory\\_metrics': True\n* 'use\\_legacy\\_prediction\\_loop': False\n* 'push\\_to\\_hub': False\n* 'resume\\_from\\_checkpoint': None\n* 'hub\\_model\\_id': None\n* 'hub\\_strategy': every\\_save\n* 'hub\\_private\\_repo': False\n* 'hub\\_always\\_push': False\n* 'gradient\\_checkpointing': False\n* 'gradient\\_checkpointing\\_kwargs': None\n* 'include\\_inputs\\_for\\_metrics': False\n* 'eval\\_do\\_concat\\_batches': True\n* 'fp16\\_backend': auto\n* 'push\\_to\\_hub\\_model\\_id': None\n* 'push\\_to\\_hub\\_organization': None\n* 'mp\\_parameters':\n* 'auto\\_find\\_batch\\_size': False\n* 'full\\_determinism': False\n* 'torchdynamo': None\n* 'ray\\_scope': last\n* 'ddp\\_timeout': 1800\n* 'torch\\_compile': False\n* 'torch\\_compile\\_backend': None\n* 'torch\\_compile\\_mode': None\n* 'dispatch\\_batches': None\n* 'split\\_batches': None\n* 'include\\_tokens\\_per\\_second': False\n* 'include\\_num\\_input\\_tokens\\_seen': False\n* 'neftune\\_noise\\_alpha': None\n* 'optim\\_target\\_modules': None\n* 'batch\\_sampler': batch\\_sampler\n* 'multi\\_dataset\\_batch\\_sampler': proportional### Training Logs\n\n\n\n* The bold row denotes the saved checkpoint.### Environmental Impact\n\n\nCarbon emissions were measured using CodeCarbon.\n\n\n* Energy Consumed: 0.009 kWh\n* Carbon Emitted: 0.003 kg of CO2\n* Hours Used: 0.054 hours### Training Hardware\n\n\n* On Cloud: No\n* GPU Model: 1 x NVIDIA GeForce RTX 3090\n* CPU Model: 13th Gen Intel(R) Core(TM) i7-13700K\n* RAM Size: 31.78 GB### Framework Versions\n\n\n* Python: 3.11.6\n* Sentence Transformers: 3.0.0.dev0\n* Transformers: 4.41.0.dev0\n* PyTorch: 2.3.0+cu121\n* Accelerate: 0.26.1\n* Datasets: 2.18.0\n* Tokenizers: 0.19.1### BibTeX#### Sentence Transformers#### MSELoss" ]

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

[]

[]

[ "# Yamshadowexperiment28T3q-7B\n\nYamshadowexperiment28T3q-7B is an automated merge created by Maxime Labonne using the following configuration.", "## Configuration", "## Usage" ]

[ "TAGS\n#merge #mergekit #lazymergekit #automerger #license-apache-2.0 #region-us \n", "# Yamshadowexperiment28T3q-7B\n\nYamshadowexperiment28T3q-7B is an automated merge created by Maxime Labonne using the following configuration.", "## Configuration", "## Usage" ]

[ 27, 46, 3, 3 ]

[ "TAGS\n#merge #mergekit #lazymergekit #automerger #license-apache-2.0 #region-us \n# Yamshadowexperiment28T3q-7B\n\nYamshadowexperiment28T3q-7B is an automated merge created by Maxime Labonne using the following configuration.## Configuration## Usage" ]

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

[ "1910.09700" ]

[]

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

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

[ 30, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

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

[ "gguf", "samantha", "it", "license:mit", "region:us" ]

[]

[ "it" ]

[]

[ "TAGS\n#gguf #samantha #it #license-mit #region-us \n" ]

[ 17 ]

[ "TAGS\n#gguf #samantha #it #license-mit #region-us \n" ]

[ "gguf", "llama-3", "llama", "Mixtral", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "distillation", "GGUF", "en", "arxiv:2305.18290", "arxiv:2303.13375", "arxiv:2212.13138", "arxiv:2305.09617", "arxiv:2402.07023", "base_model:meta-llama/Meta-Llama-3-70B-Instruct", "license:llama3", "region:us" ]

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

[ "en" ]

[ "# Llama3-OpenBioLLM-70B-GGUF\n- Original model: Llama3-OpenBioLLM-70B", "## Description\n\nThis repo contains GGUF format model files for Llama3-OpenBioLLM-70B.", "### About GGUF\nGGUF is a new format introduced by the URL team on August 21st 2023. It is a replacement for GGML, which is no longer supported by URL.\nHere is an incomplete list of clients and libraries that are known to support GGUF:\n* URL. This is the source project for GGUF, providing both a Command Line Interface (CLI) and a server option.\n* text-generation-webui, Known as the most widely used web UI, this project boasts numerous features and powerful extensions, and supports GPU acceleration.\n* Ollama Ollama is a lightweight and extensible framework designed for building and running language models locally. It features a simple API for creating, managing, and executing models, along with a library of pre-built models for use in various applications​\n* KoboldCpp, A comprehensive web UI offering GPU acceleration across all platforms and architectures, particularly renowned for storytelling.\n* GPT4All, This is a free and open source GUI that runs locally, supporting Windows, Linux, and macOS with full GPU acceleration.\n* LM Studio An intuitive and powerful local GUI for Windows and macOS (Silicon), featuring GPU acceleration.\n* LoLLMS Web UI. A notable web UI with a variety of unique features, including a comprehensive model library for easy model selection.\n* URL, An attractive, user-friendly character-based chat GUI for Windows and macOS (both Silicon and Intel), also offering GPU acceleration.\n* llama-cpp-python, A Python library equipped with GPU acceleration, LangChain support, and an OpenAI-compatible API server.\n* candle, A Rust-based ML framework focusing on performance, including GPU support, and designed for ease of use.\n* ctransformers, A Python library featuring GPU acceleration, LangChain support, and an OpenAI-compatible AI server.\n* localGPT An open-source initiative enabling private conversations with documents.", "## Explanation of quantisation methods\n<details>\n <summary>Click to see details</summary>\nThe new methods available are:\n\n* GGML_TYPE_Q2_K - \"type-1\" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)\n* GGML_TYPE_Q3_K - \"type-0\" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.\n* GGML_TYPE_Q4_K - \"type-1\" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.\n* GGML_TYPE_Q5_K - \"type-1\" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw\n* GGML_TYPE_Q6_K - \"type-0\" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw.\n</details>", "## How to download GGUF files\n\nNote for manual downloaders: You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single folder.\n\nThe following clients/libraries will automatically download models for you, providing a list of available models to choose from:\n\n* LM Studio\n* LoLLMS Web UI\n* URL", "### In 'text-generation-webui'\n\nUnder Download Model, you can enter the model repo: LiteLLMs/Llama3-OpenBioLLM-70B-GGUF and below it, a specific filename to download, such as: Q4_0/Q4_0-URL.\n\nThen click Download.", "### On the command line, including multiple files at once\n\nI recommend using the 'huggingface-hub' Python library:\n\n\n\nThen you can download any individual model file to the current directory, at high speed, with a command like this:\n\n\n\n<details>\n <summary>More advanced huggingface-cli download usage (click to read)</summary>\n\nYou can also download multiple files at once with a pattern:\n\n\n\nFor more documentation on downloading with 'huggingface-cli', please see: HF -> Hub Python Library -> Download files -> Download from the CLI.\n\nTo accelerate downloads on fast connections (1Gbit/s or higher), install 'hf_transfer':\n\n\n\nAnd set environment variable 'HF_HUB_ENABLE_HF_TRANSFER' to '1':\n\n\n\nWindows Command Line users: You can set the environment variable by running 'set HF_HUB_ENABLE_HF_TRANSFER=1' before the download command.\n</details>", "## Example 'URL' command\n\nMake sure you are using 'URL' from commit d0cee0d or later.\n\n\n\nChange '-ngl 32' to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.\n\nChange '-c 8192' to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by URL automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.\n\nIf you want to have a chat-style conversation, replace the '-p <PROMPT>' argument with '-i -ins'\n\nFor other parameters and how to use them, please refer to the URL documentation", "## How to run in 'text-generation-webui'\n\nFurther instructions can be found in the text-generation-webui documentation, here: text-generation-webui/docs/04 ‐ Model URL.", "## How to run from Python code\n\nYou can use GGUF models from Python using the llama-cpp-python or ctransformers libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.", "### How to load this model in Python code, using llama-cpp-python\n\nFor full documentation, please see: llama-cpp-python docs.", "#### First install the package\n\nRun one of the following commands, according to your system:", "#### Simple llama-cpp-python example code", "## How to use with LangChain\n\nHere are guides on using llama-cpp-python and ctransformers with LangChain:\n\n* LangChain + llama-cpp-python\n* LangChain + ctransformers", "# Original model card: Llama3-OpenBioLLM-70B\n\n\n\n<div align=\"center\">\n<img width=\"260px\" src=\"URL\n\n!image/png\n\n\n\n\n<div align=\"center\">\n\n <h1>Advancing Open-source Large Language Models in Medical Domain</h1>\n</div>\n\n<p align=\"center\" style=\"margin-top: 0px;\">\n <a href=\"URL\n <img src=\"URL alt=\"OpenChat Logo\" style=\"width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 10px; margin-top: 0px; margin-bottom: 0px;\"/>\n <span class=\"link-text\" style=\" margin-right: 5px;\">Online Demo</span>\n </a> |\n <a href=\"URL\n <img src=\"URL alt=\"GitHub Logo\" style=\"width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;\"/>\n <span class=\"link-text\" style=\" margin-right: 5px;\">GitHub</span>\n </a> |\n <a href=\"#\">\n <img src=\"URL alt=\"ArXiv Logo\" style=\"width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;\"/>\n <span class=\"link-text\" style=\"margin-right: 5px;\">Paper</span>\n </a> |\n <a href=\"URL\n <img src=\"URL alt=\"Discord Logo\" style=\"width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;\"/>\n <span class=\"link-text\">Discord</span>\n </a>\n</p>\n\n!image/jpeg\n\nIntroducing OpenBioLLM-70B: A State-of-the-Art Open Source Biomedical Large Language Model\n\n\nOpenBioLLM-70B is an advanced open source language model designed specifically for the biomedical domain. Developed by Saama AI Labs, this model leverages cutting-edge techniques to achieve state-of-the-art performance on a wide range of biomedical tasks.\n\n Biomedical Specialization: OpenBioLLM-70B is tailored for the unique language and knowledge requirements of the medical and life sciences fields. It was fine-tuned on a vast corpus of high-quality biomedical data, enabling it to understand and generate text with domain-specific accuracy and fluency.\n\n Superior Performance: With 70 billion parameters, OpenBioLLM-70B outperforms other open source biomedical language models of similar scale. It has also demonstrated better results compared to larger proprietary & open-source models like GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 on biomedical benchmarks.\n\n Advanced Training Techniques: OpenBioLLM-70B builds upon the powerful foundations of the Meta-Llama-3-70B-Instruct and Meta-Llama-3-70B-Instruct models. It incorporates the DPO dataset and fine-tuning recipe along with a custom diverse medical instruction dataset. Key components of the training pipeline include:\n\n<div align=\"center\">\n<img width=\"1200px\" src=\"URL\n</div>\n\n\n- Policy Optimization: Direct Preference Optimization: Your Language Model is Secretly a Reward Model (DPO)\n- Fine-tuning dataset: Custom Medical Instruct dataset (We plan to release a sample training dataset in our upcoming paper; please stay updated)\n\nThis combination of cutting-edge techniques enables OpenBioLLM-70B to align with key capabilities and preferences for biomedical applications.\n\n️ Release Details:\n\n- Model Size: 70 billion parameters\n- Quantization: Optimized quantized versions available Here\n- Language(s) (NLP): en\n- Developed By: Ankit Pal (Aaditya Ura) from Saama AI Labs\n- License: Meta-Llama License\n- Fine-tuned from models: Meta-Llama-3-70B-Instruct\n- Resources for more information:\n - Paper: Coming soon\n\nThe model can be fine-tuned for more specialized tasks and datasets as needed.\n\nOpenBioLLM-70B represents an important step forward in democratizing advanced language AI for the biomedical community. By leveraging state-of-the-art architectures and training techniques from leading open source efforts like Llama-3, we have created a powerful tool to accelerate innovation and discovery in healthcare and the life sciences.\n\nWe are excited to share OpenBioLLM-70B with researchers and developers around the world.", "### Use with transformers\n\nImportant: 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.\n\nSee the snippet below for usage with Transformers:", "## Training procedure", "### Training hyperparameters\n\n<details>\n <summary>Click to see details</summary>\n\n- learning_rate: 0.0002\n- lr_scheduler: cosine\n- train_batch_size: 12\n- eval_batch_size: 8\n- GPU: H100 80GB SXM5\n- num_devices: 8\n- optimizer: adamw_bnb_8bit\n- lr_scheduler_warmup_steps: 100\n- num_epochs: 4\n</details>", "### Peft hyperparameters\n\n<details>\n <summary>Click to see details</summary>\n\n- adapter: qlora\n- lora_r: 128\n- lora_alpha: 256\n- lora_dropout: 0.05\n- lora_target_linear: true\n\n-lora_target_modules:\n- q_proj\n- v_proj\n- k_proj\n- o_proj\n- gate_proj\n- down_proj\n- up_proj\n</details>", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.1\n- Axolotl\n- Lm harness for evaluation", "# Benchmark Results\n\n OpenBioLLM-70B demonstrates superior performance compared to larger models, such as GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 across 9 diverse biomedical datasets, achieving state-of-the-art results with an average score of 86.06%, despite having a significantly smaller parameter count. The model's strong performance in domain-specific tasks, such as Clinical KG, Medical Genetics, and PubMedQA, highlights its ability to effectively capture and apply biomedical knowledge.\n\n 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.\n\n| | Clinical KG | Medical Genetics | Anatomy | Pro Medicine | College Biology | College Medicine | MedQA 4 opts | PubMedQA | MedMCQA | Avg |\n| | - | | - | |\n| OpenBioLLM-70B | 92.93 | 93.197 | 83.904 | 93.75 | 93.827 | 85.749 | 78.162 | 78.97 | 74.014 | 86.05588 |\n| Med-PaLM-2 (5-shot) | 88.3 | 90 | 77.8 | 95.2 | 94.4 | 80.9 | 79.7 | 79.2 | 71.3 | 84.08 |\n| GPT-4 | 86.04 | 91 | 80 | 93.01 | 95.14 | 76.88 | 78.87 | 75.2 | 69.52 | 82.85 |\n| 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 |\n| OpenBioLLM-8B | 76.101 | 86.1 | 69.829 | 78.21 | 84.213 | 68.042 | 58.993 | 74.12 | 56.913 | 72.502 |\n| Gemini-1.0 | 76.7 | 75.8 | 66.7 | 77.7 | 88 | 69.2 | 58 | 70.7 | 54.3 | 70.79 |\n| GPT-3.5 Turbo 1106 | 74.71 | 74 | 72.79 | 72.79 | 72.91 | 64.73 | 57.71 | 72.66 | 53.79 | 66 |\n| Meditron-70B | 66.79 | 69 | 53.33 | 71.69 | 76.38 | 63 | 57.1 | 76.6 | 46.85 | 64.52 |\n| gemma-7b | 69.81 | 70 | 59.26 | 66.18 | 79.86 | 60.12 | 47.21 | 76.2 | 48.96 | 64.18 |\n| Mistral-7B-v0.1 | 68.68 | 71 | 55.56 | 68.38 | 68.06 | 59.54 | 50.82 | 75.4 | 48.2 | 62.85 |\n| Apollo-7B | 62.26 | 72 | 61.48 | 69.12 | 70.83 | 55.49 | 55.22 | 39.8 | 53.77 | 60 |\n| MedAlpaca-7b | 57.36 | 69 | 57.04 | 67.28 | 65.28 | 54.34 | 41.71 | 72.8 | 37.51 | 58.03 |\n| BioMistral-7B | 59.9 | 64 | 56.5 | 60.4 | 59 | 54.7 | 50.6 | 77.5 | 48.1 | 57.3 |\n| AlpaCare-llama2-7b | 49.81 | 49 | 45.92 | 33.82 | 50 | 43.35 | 29.77 | 72.2 | 34.42 | 45.36 |\n| ClinicalGPT | 30.56 | 27 | 30.37 | 19.48 | 25 | 24.27 | 26.08 | 63.8 | 28.18 | 30.52 |\n\n<div align=\"center\">\n<img width=\"1600px\" src=\"URL\n</div>", "## Detailed Medical Subjectwise accuracy\n\n\n!image/png", "# Use Cases & Examples\n\n Below results are from the quantized version of OpenBioLLM-70B", "# Summarize Clinical Notes\n\nOpenBioLLM-70B can efficiently analyze and summarize complex clinical notes, EHR data, and discharge summaries, extracting key information and generating concise, structured summaries\n\n\n!image/png", "# Answer Medical Questions\n\nOpenBioLLM-70B can provide answers to a wide range of medical questions.\n\n\n!image/png\n!image/png\n\n<details>\n <summary>Click to see details</summary>\n\n\n!image/png\n!image/png\n!image/png\n\n</details>", "# Clinical Entity Recognition\n\nOpenBioLLM-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.\n\n\n!image/png\n!image/png\n!image/png", "# Biomarkers Extraction\n\n\n!image/png", "# Classification\n\nOpenBioLLM-70B can perform various biomedical classification tasks, such as disease prediction, sentiment analysis, medical document categorization\n\n!image/png", "# De-Identification\n\nOpenBioLLM-70B can detect and remove personally identifiable information (PII) from medical records, ensuring patient privacy and compliance with data protection regulations like HIPAA.\n\n!image/png\n\n\n\nAdvisory Notice!\n\nWhile OpenBioLLM-70B leverages high-quality data sources, its outputs may still contain inaccuracies, biases, or misalignments that could pose risks if relied upon for medical decision-making without further testing and refinement. The model's performance has not yet been rigorously evaluated in randomized controlled trials or real-world healthcare environments.\n\nTherefore, we strongly advise against using OpenBioLLM-70B for any direct patient care, clinical decision support, or other professional medical purposes at this time. Its use should be limited to research, development, and exploratory applications by qualified individuals who understand its limitations.\nOpenBioLLM-70B is intended solely as a research tool to assist healthcare professionals and should never be considered a replacement for the professional judgment and expertise of a qualified medical doctor.\n\nAppropriately adapting and validating OpenBioLLM-70B for specific medical use cases would require significant additional work, potentially including:\n\n- Thorough testing and evaluation in relevant clinical scenarios\n- Alignment with evidence-based guidelines and best practices\n- Mitigation of potential biases and failure modes\n- Integration with human oversight and interpretation\n- Compliance with regulatory and ethical standards\n\nAlways consult a qualified healthcare provider for personal medical needs.\n\n\n\nIf you find OpenBioLLM-70B & 8B useful in your work, please cite the model as follows:\n\n\n\nThe accompanying paper is currently in progress and will be released soon.\n\n<div align=\"center\">\n<h2> Contact </h2>\n</div>\n\nWe look forward to hearing you and collaborating on this exciting project!\n\nContributors:\n- Ankit Pal (Aaditya Ura) [aadityaura at gmail dot com]\n- Saama AI Labs\n- 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\n\nWe thank the Meta Team for their amazing models!\n\n\nResult sources\n\n- [1] GPT-4 [Capabilities of GPT-4 on Medical Challenge Problems] (URL\n- [2] Med-PaLM-1 Large Language Models Encode Clinical Knowledge\n- [3] Med-PaLM-2 Towards Expert-Level Medical Question Answering with Large Language Models\n- [4] Gemini-1.0 Gemini Goes to Med School" ]

[ "TAGS\n#gguf #llama-3 #llama #Mixtral #instruct #finetune #chatml #DPO #RLHF #gpt4 #distillation #GGUF #en #arxiv-2305.18290 #arxiv-2303.13375 #arxiv-2212.13138 #arxiv-2305.09617 #arxiv-2402.07023 #base_model-meta-llama/Meta-Llama-3-70B-Instruct #license-llama3 #region-us \n", "# Llama3-OpenBioLLM-70B-GGUF\n- Original model: Llama3-OpenBioLLM-70B", "## Description\n\nThis repo contains GGUF format model files for Llama3-OpenBioLLM-70B.", "### About GGUF\nGGUF is a new format introduced by the URL team on August 21st 2023. It is a replacement for GGML, which is no longer supported by URL.\nHere is an incomplete list of clients and libraries that are known to support GGUF:\n* URL. This is the source project for GGUF, providing both a Command Line Interface (CLI) and a server option.\n* text-generation-webui, Known as the most widely used web UI, this project boasts numerous features and powerful extensions, and supports GPU acceleration.\n* Ollama Ollama is a lightweight and extensible framework designed for building and running language models locally. It features a simple API for creating, managing, and executing models, along with a library of pre-built models for use in various applications​\n* KoboldCpp, A comprehensive web UI offering GPU acceleration across all platforms and architectures, particularly renowned for storytelling.\n* GPT4All, This is a free and open source GUI that runs locally, supporting Windows, Linux, and macOS with full GPU acceleration.\n* LM Studio An intuitive and powerful local GUI for Windows and macOS (Silicon), featuring GPU acceleration.\n* LoLLMS Web UI. A notable web UI with a variety of unique features, including a comprehensive model library for easy model selection.\n* URL, An attractive, user-friendly character-based chat GUI for Windows and macOS (both Silicon and Intel), also offering GPU acceleration.\n* llama-cpp-python, A Python library equipped with GPU acceleration, LangChain support, and an OpenAI-compatible API server.\n* candle, A Rust-based ML framework focusing on performance, including GPU support, and designed for ease of use.\n* ctransformers, A Python library featuring GPU acceleration, LangChain support, and an OpenAI-compatible AI server.\n* localGPT An open-source initiative enabling private conversations with documents.", "## Explanation of quantisation methods\n<details>\n <summary>Click to see details</summary>\nThe new methods available are:\n\n* GGML_TYPE_Q2_K - \"type-1\" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)\n* GGML_TYPE_Q3_K - \"type-0\" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.\n* GGML_TYPE_Q4_K - \"type-1\" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.\n* GGML_TYPE_Q5_K - \"type-1\" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw\n* GGML_TYPE_Q6_K - \"type-0\" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw.\n</details>", "## How to download GGUF files\n\nNote for manual downloaders: You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single folder.\n\nThe following clients/libraries will automatically download models for you, providing a list of available models to choose from:\n\n* LM Studio\n* LoLLMS Web UI\n* URL", "### In 'text-generation-webui'\n\nUnder Download Model, you can enter the model repo: LiteLLMs/Llama3-OpenBioLLM-70B-GGUF and below it, a specific filename to download, such as: Q4_0/Q4_0-URL.\n\nThen click Download.", "### On the command line, including multiple files at once\n\nI recommend using the 'huggingface-hub' Python library:\n\n\n\nThen you can download any individual model file to the current directory, at high speed, with a command like this:\n\n\n\n<details>\n <summary>More advanced huggingface-cli download usage (click to read)</summary>\n\nYou can also download multiple files at once with a pattern:\n\n\n\nFor more documentation on downloading with 'huggingface-cli', please see: HF -> Hub Python Library -> Download files -> Download from the CLI.\n\nTo accelerate downloads on fast connections (1Gbit/s or higher), install 'hf_transfer':\n\n\n\nAnd set environment variable 'HF_HUB_ENABLE_HF_TRANSFER' to '1':\n\n\n\nWindows Command Line users: You can set the environment variable by running 'set HF_HUB_ENABLE_HF_TRANSFER=1' before the download command.\n</details>", "## Example 'URL' command\n\nMake sure you are using 'URL' from commit d0cee0d or later.\n\n\n\nChange '-ngl 32' to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.\n\nChange '-c 8192' to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by URL automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.\n\nIf you want to have a chat-style conversation, replace the '-p <PROMPT>' argument with '-i -ins'\n\nFor other parameters and how to use them, please refer to the URL documentation", "## How to run in 'text-generation-webui'\n\nFurther instructions can be found in the text-generation-webui documentation, here: text-generation-webui/docs/04 ‐ Model URL.", "## How to run from Python code\n\nYou can use GGUF models from Python using the llama-cpp-python or ctransformers libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.", "### How to load this model in Python code, using llama-cpp-python\n\nFor full documentation, please see: llama-cpp-python docs.", "#### First install the package\n\nRun one of the following commands, according to your system:", "#### Simple llama-cpp-python example code", "## How to use with LangChain\n\nHere are guides on using llama-cpp-python and ctransformers with LangChain:\n\n* LangChain + llama-cpp-python\n* LangChain + ctransformers", "# Original model card: Llama3-OpenBioLLM-70B\n\n\n\n<div align=\"center\">\n<img width=\"260px\" src=\"URL\n\n!image/png\n\n\n\n\n<div align=\"center\">\n\n <h1>Advancing Open-source Large Language Models in Medical Domain</h1>\n</div>\n\n<p align=\"center\" style=\"margin-top: 0px;\">\n <a href=\"URL\n <img src=\"URL alt=\"OpenChat Logo\" style=\"width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 10px; margin-top: 0px; margin-bottom: 0px;\"/>\n <span class=\"link-text\" style=\" margin-right: 5px;\">Online Demo</span>\n </a> |\n <a href=\"URL\n <img src=\"URL alt=\"GitHub Logo\" style=\"width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;\"/>\n <span class=\"link-text\" style=\" margin-right: 5px;\">GitHub</span>\n </a> |\n <a href=\"#\">\n <img src=\"URL alt=\"ArXiv Logo\" style=\"width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;\"/>\n <span class=\"link-text\" style=\"margin-right: 5px;\">Paper</span>\n </a> |\n <a href=\"URL\n <img src=\"URL alt=\"Discord Logo\" style=\"width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;\"/>\n <span class=\"link-text\">Discord</span>\n </a>\n</p>\n\n!image/jpeg\n\nIntroducing OpenBioLLM-70B: A State-of-the-Art Open Source Biomedical Large Language Model\n\n\nOpenBioLLM-70B is an advanced open source language model designed specifically for the biomedical domain. Developed by Saama AI Labs, this model leverages cutting-edge techniques to achieve state-of-the-art performance on a wide range of biomedical tasks.\n\n Biomedical Specialization: OpenBioLLM-70B is tailored for the unique language and knowledge requirements of the medical and life sciences fields. It was fine-tuned on a vast corpus of high-quality biomedical data, enabling it to understand and generate text with domain-specific accuracy and fluency.\n\n Superior Performance: With 70 billion parameters, OpenBioLLM-70B outperforms other open source biomedical language models of similar scale. It has also demonstrated better results compared to larger proprietary & open-source models like GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 on biomedical benchmarks.\n\n Advanced Training Techniques: OpenBioLLM-70B builds upon the powerful foundations of the Meta-Llama-3-70B-Instruct and Meta-Llama-3-70B-Instruct models. It incorporates the DPO dataset and fine-tuning recipe along with a custom diverse medical instruction dataset. Key components of the training pipeline include:\n\n<div align=\"center\">\n<img width=\"1200px\" src=\"URL\n</div>\n\n\n- Policy Optimization: Direct Preference Optimization: Your Language Model is Secretly a Reward Model (DPO)\n- Fine-tuning dataset: Custom Medical Instruct dataset (We plan to release a sample training dataset in our upcoming paper; please stay updated)\n\nThis combination of cutting-edge techniques enables OpenBioLLM-70B to align with key capabilities and preferences for biomedical applications.\n\n️ Release Details:\n\n- Model Size: 70 billion parameters\n- Quantization: Optimized quantized versions available Here\n- Language(s) (NLP): en\n- Developed By: Ankit Pal (Aaditya Ura) from Saama AI Labs\n- License: Meta-Llama License\n- Fine-tuned from models: Meta-Llama-3-70B-Instruct\n- Resources for more information:\n - Paper: Coming soon\n\nThe model can be fine-tuned for more specialized tasks and datasets as needed.\n\nOpenBioLLM-70B represents an important step forward in democratizing advanced language AI for the biomedical community. By leveraging state-of-the-art architectures and training techniques from leading open source efforts like Llama-3, we have created a powerful tool to accelerate innovation and discovery in healthcare and the life sciences.\n\nWe are excited to share OpenBioLLM-70B with researchers and developers around the world.", "### Use with transformers\n\nImportant: 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.\n\nSee the snippet below for usage with Transformers:", "## Training procedure", "### Training hyperparameters\n\n<details>\n <summary>Click to see details</summary>\n\n- learning_rate: 0.0002\n- lr_scheduler: cosine\n- train_batch_size: 12\n- eval_batch_size: 8\n- GPU: H100 80GB SXM5\n- num_devices: 8\n- optimizer: adamw_bnb_8bit\n- lr_scheduler_warmup_steps: 100\n- num_epochs: 4\n</details>", "### Peft hyperparameters\n\n<details>\n <summary>Click to see details</summary>\n\n- adapter: qlora\n- lora_r: 128\n- lora_alpha: 256\n- lora_dropout: 0.05\n- lora_target_linear: true\n\n-lora_target_modules:\n- q_proj\n- v_proj\n- k_proj\n- o_proj\n- gate_proj\n- down_proj\n- up_proj\n</details>", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.1\n- Axolotl\n- Lm harness for evaluation", "# Benchmark Results\n\n OpenBioLLM-70B demonstrates superior performance compared to larger models, such as GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 across 9 diverse biomedical datasets, achieving state-of-the-art results with an average score of 86.06%, despite having a significantly smaller parameter count. The model's strong performance in domain-specific tasks, such as Clinical KG, Medical Genetics, and PubMedQA, highlights its ability to effectively capture and apply biomedical knowledge.\n\n 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.\n\n| | Clinical KG | Medical Genetics | Anatomy | Pro Medicine | College Biology | College Medicine | MedQA 4 opts | PubMedQA | MedMCQA | Avg |\n| | - | | - | |\n| OpenBioLLM-70B | 92.93 | 93.197 | 83.904 | 93.75 | 93.827 | 85.749 | 78.162 | 78.97 | 74.014 | 86.05588 |\n| Med-PaLM-2 (5-shot) | 88.3 | 90 | 77.8 | 95.2 | 94.4 | 80.9 | 79.7 | 79.2 | 71.3 | 84.08 |\n| GPT-4 | 86.04 | 91 | 80 | 93.01 | 95.14 | 76.88 | 78.87 | 75.2 | 69.52 | 82.85 |\n| 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 |\n| OpenBioLLM-8B | 76.101 | 86.1 | 69.829 | 78.21 | 84.213 | 68.042 | 58.993 | 74.12 | 56.913 | 72.502 |\n| Gemini-1.0 | 76.7 | 75.8 | 66.7 | 77.7 | 88 | 69.2 | 58 | 70.7 | 54.3 | 70.79 |\n| GPT-3.5 Turbo 1106 | 74.71 | 74 | 72.79 | 72.79 | 72.91 | 64.73 | 57.71 | 72.66 | 53.79 | 66 |\n| Meditron-70B | 66.79 | 69 | 53.33 | 71.69 | 76.38 | 63 | 57.1 | 76.6 | 46.85 | 64.52 |\n| gemma-7b | 69.81 | 70 | 59.26 | 66.18 | 79.86 | 60.12 | 47.21 | 76.2 | 48.96 | 64.18 |\n| Mistral-7B-v0.1 | 68.68 | 71 | 55.56 | 68.38 | 68.06 | 59.54 | 50.82 | 75.4 | 48.2 | 62.85 |\n| Apollo-7B | 62.26 | 72 | 61.48 | 69.12 | 70.83 | 55.49 | 55.22 | 39.8 | 53.77 | 60 |\n| MedAlpaca-7b | 57.36 | 69 | 57.04 | 67.28 | 65.28 | 54.34 | 41.71 | 72.8 | 37.51 | 58.03 |\n| BioMistral-7B | 59.9 | 64 | 56.5 | 60.4 | 59 | 54.7 | 50.6 | 77.5 | 48.1 | 57.3 |\n| AlpaCare-llama2-7b | 49.81 | 49 | 45.92 | 33.82 | 50 | 43.35 | 29.77 | 72.2 | 34.42 | 45.36 |\n| ClinicalGPT | 30.56 | 27 | 30.37 | 19.48 | 25 | 24.27 | 26.08 | 63.8 | 28.18 | 30.52 |\n\n<div align=\"center\">\n<img width=\"1600px\" src=\"URL\n</div>", "## Detailed Medical Subjectwise accuracy\n\n\n!image/png", "# Use Cases & Examples\n\n Below results are from the quantized version of OpenBioLLM-70B", "# Summarize Clinical Notes\n\nOpenBioLLM-70B can efficiently analyze and summarize complex clinical notes, EHR data, and discharge summaries, extracting key information and generating concise, structured summaries\n\n\n!image/png", "# Answer Medical Questions\n\nOpenBioLLM-70B can provide answers to a wide range of medical questions.\n\n\n!image/png\n!image/png\n\n<details>\n <summary>Click to see details</summary>\n\n\n!image/png\n!image/png\n!image/png\n\n</details>", "# Clinical Entity Recognition\n\nOpenBioLLM-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.\n\n\n!image/png\n!image/png\n!image/png", "# Biomarkers Extraction\n\n\n!image/png", "# Classification\n\nOpenBioLLM-70B can perform various biomedical classification tasks, such as disease prediction, sentiment analysis, medical document categorization\n\n!image/png", "# De-Identification\n\nOpenBioLLM-70B can detect and remove personally identifiable information (PII) from medical records, ensuring patient privacy and compliance with data protection regulations like HIPAA.\n\n!image/png\n\n\n\nAdvisory Notice!\n\nWhile OpenBioLLM-70B leverages high-quality data sources, its outputs may still contain inaccuracies, biases, or misalignments that could pose risks if relied upon for medical decision-making without further testing and refinement. The model's performance has not yet been rigorously evaluated in randomized controlled trials or real-world healthcare environments.\n\nTherefore, we strongly advise against using OpenBioLLM-70B for any direct patient care, clinical decision support, or other professional medical purposes at this time. Its use should be limited to research, development, and exploratory applications by qualified individuals who understand its limitations.\nOpenBioLLM-70B is intended solely as a research tool to assist healthcare professionals and should never be considered a replacement for the professional judgment and expertise of a qualified medical doctor.\n\nAppropriately adapting and validating OpenBioLLM-70B for specific medical use cases would require significant additional work, potentially including:\n\n- Thorough testing and evaluation in relevant clinical scenarios\n- Alignment with evidence-based guidelines and best practices\n- Mitigation of potential biases and failure modes\n- Integration with human oversight and interpretation\n- Compliance with regulatory and ethical standards\n\nAlways consult a qualified healthcare provider for personal medical needs.\n\n\n\nIf you find OpenBioLLM-70B & 8B useful in your work, please cite the model as follows:\n\n\n\nThe accompanying paper is currently in progress and will be released soon.\n\n<div align=\"center\">\n<h2> Contact </h2>\n</div>\n\nWe look forward to hearing you and collaborating on this exciting project!\n\nContributors:\n- Ankit Pal (Aaditya Ura) [aadityaura at gmail dot com]\n- Saama AI Labs\n- 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\n\nWe thank the Meta Team for their amazing models!\n\n\nResult sources\n\n- [1] GPT-4 [Capabilities of GPT-4 on Medical Challenge Problems] (URL\n- [2] Med-PaLM-1 Large Language Models Encode Clinical Knowledge\n- [3] Med-PaLM-2 Towards Expert-Level Medical Question Answering with Large Language Models\n- [4] Gemini-1.0 Gemini Goes to Med School" ]

[ 132, 31, 26, 419, 314, 83, 74, 206, 172, 47, 82, 37, 20, 14, 54, 1140, 68, 4, 115, 110, 5, 54, 978, 12, 21, 52, 65, 139, 10, 34, 442, 87 ]

[ "TAGS\n#gguf #llama-3 #llama #Mixtral #instruct #finetune #chatml #DPO #RLHF #gpt4 #distillation #GGUF #en #arxiv-2305.18290 #arxiv-2303.13375 #arxiv-2212.13138 #arxiv-2305.09617 #arxiv-2402.07023 #base_model-meta-llama/Meta-Llama-3-70B-Instruct #license-llama3 #region-us \n# Llama3-OpenBioLLM-70B-GGUF\n- Original model: Llama3-OpenBioLLM-70B## Description\n\nThis repo contains GGUF format model files for Llama3-OpenBioLLM-70B.### About GGUF\nGGUF is a new format introduced by the URL team on August 21st 2023. It is a replacement for GGML, which is no longer supported by URL.\nHere is an incomplete list of clients and libraries that are known to support GGUF:\n* URL. This is the source project for GGUF, providing both a Command Line Interface (CLI) and a server option.\n* text-generation-webui, Known as the most widely used web UI, this project boasts numerous features and powerful extensions, and supports GPU acceleration.\n* Ollama Ollama is a lightweight and extensible framework designed for building and running language models locally. It features a simple API for creating, managing, and executing models, along with a library of pre-built models for use in various applications​\n* KoboldCpp, A comprehensive web UI offering GPU acceleration across all platforms and architectures, particularly renowned for storytelling.\n* GPT4All, This is a free and open source GUI that runs locally, supporting Windows, Linux, and macOS with full GPU acceleration.\n* LM Studio An intuitive and powerful local GUI for Windows and macOS (Silicon), featuring GPU acceleration.\n* LoLLMS Web UI. A notable web UI with a variety of unique features, including a comprehensive model library for easy model selection.\n* URL, An attractive, user-friendly character-based chat GUI for Windows and macOS (both Silicon and Intel), also offering GPU acceleration.\n* llama-cpp-python, A Python library equipped with GPU acceleration, LangChain support, and an OpenAI-compatible API server.\n* candle, A Rust-based ML framework focusing on performance, including GPU support, and designed for ease of use.\n* ctransformers, A Python library featuring GPU acceleration, LangChain support, and an OpenAI-compatible AI server.\n* localGPT An open-source initiative enabling private conversations with documents.## Explanation of quantisation methods\n<details>\n <summary>Click to see details</summary>\nThe new methods available are:\n\n* GGML_TYPE_Q2_K - \"type-1\" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)\n* GGML_TYPE_Q3_K - \"type-0\" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.\n* GGML_TYPE_Q4_K - \"type-1\" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.\n* GGML_TYPE_Q5_K - \"type-1\" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw\n* GGML_TYPE_Q6_K - \"type-0\" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw.\n</details>## How to download GGUF files\n\nNote for manual downloaders: You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single folder.\n\nThe following clients/libraries will automatically download models for you, providing a list of available models to choose from:\n\n* LM Studio\n* LoLLMS Web UI\n* URL### In 'text-generation-webui'\n\nUnder Download Model, you can enter the model repo: LiteLLMs/Llama3-OpenBioLLM-70B-GGUF and below it, a specific filename to download, such as: Q4_0/Q4_0-URL.\n\nThen click Download.### On the command line, including multiple files at once\n\nI recommend using the 'huggingface-hub' Python library:\n\n\n\nThen you can download any individual model file to the current directory, at high speed, with a command like this:\n\n\n\n<details>\n <summary>More advanced huggingface-cli download usage (click to read)</summary>\n\nYou can also download multiple files at once with a pattern:\n\n\n\nFor more documentation on downloading with 'huggingface-cli', please see: HF -> Hub Python Library -> Download files -> Download from the CLI.\n\nTo accelerate downloads on fast connections (1Gbit/s or higher), install 'hf_transfer':\n\n\n\nAnd set environment variable 'HF_HUB_ENABLE_HF_TRANSFER' to '1':\n\n\n\nWindows Command Line users: You can set the environment variable by running 'set HF_HUB_ENABLE_HF_TRANSFER=1' before the download command.\n</details>## Example 'URL' command\n\nMake sure you are using 'URL' from commit d0cee0d or later.\n\n\n\nChange '-ngl 32' to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.\n\nChange '-c 8192' to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by URL automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.\n\nIf you want to have a chat-style conversation, replace the '-p <PROMPT>' argument with '-i -ins'\n\nFor other parameters and how to use them, please refer to the URL documentation## How to run in 'text-generation-webui'\n\nFurther instructions can be found in the text-generation-webui documentation, here: text-generation-webui/docs/04 ‐ Model URL.## How to run from Python code\n\nYou can use GGUF models from Python using the llama-cpp-python or ctransformers libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.### How to load this model in Python code, using llama-cpp-python\n\nFor full documentation, please see: llama-cpp-python docs.#### First install the package\n\nRun one of the following commands, according to your system:#### Simple llama-cpp-python example code## How to use with LangChain\n\nHere are guides on using llama-cpp-python and ctransformers with LangChain:\n\n* LangChain + llama-cpp-python\n* LangChain + ctransformers# Original model card: Llama3-OpenBioLLM-70B\n\n\n\n<div align=\"center\">\n<img width=\"260px\" src=\"URL\n\n!image/png\n\n\n\n\n<div align=\"center\">\n\n <h1>Advancing Open-source Large Language Models in Medical Domain</h1>\n</div>\n\n<p align=\"center\" style=\"margin-top: 0px;\">\n <a href=\"URL\n <img src=\"URL alt=\"OpenChat Logo\" style=\"width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 10px; margin-top: 0px; margin-bottom: 0px;\"/>\n <span class=\"link-text\" style=\" margin-right: 5px;\">Online Demo</span>\n </a> |\n <a href=\"URL\n <img src=\"URL alt=\"GitHub Logo\" style=\"width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;\"/>\n <span class=\"link-text\" style=\" margin-right: 5px;\">GitHub</span>\n </a> |\n <a href=\"#\">\n <img src=\"URL alt=\"ArXiv Logo\" style=\"width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;\"/>\n <span class=\"link-text\" style=\"margin-right: 5px;\">Paper</span>\n </a> |\n <a href=\"URL\n <img src=\"URL alt=\"Discord Logo\" style=\"width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;\"/>\n <span class=\"link-text\">Discord</span>\n </a>\n</p>\n\n!image/jpeg\n\nIntroducing OpenBioLLM-70B: A State-of-the-Art Open Source Biomedical Large Language Model\n\n\nOpenBioLLM-70B is an advanced open source language model designed specifically for the biomedical domain. Developed by Saama AI Labs, this model leverages cutting-edge techniques to achieve state-of-the-art performance on a wide range of biomedical tasks.\n\n Biomedical Specialization: OpenBioLLM-70B is tailored for the unique language and knowledge requirements of the medical and life sciences fields. It was fine-tuned on a vast corpus of high-quality biomedical data, enabling it to understand and generate text with domain-specific accuracy and fluency.\n\n Superior Performance: With 70 billion parameters, OpenBioLLM-70B outperforms other open source biomedical language models of similar scale. It has also demonstrated better results compared to larger proprietary & open-source models like GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 on biomedical benchmarks.\n\n Advanced Training Techniques: OpenBioLLM-70B builds upon the powerful foundations of the Meta-Llama-3-70B-Instruct and Meta-Llama-3-70B-Instruct models. It incorporates the DPO dataset and fine-tuning recipe along with a custom diverse medical instruction dataset. Key components of the training pipeline include:\n\n<div align=\"center\">\n<img width=\"1200px\" src=\"URL\n</div>\n\n\n- Policy Optimization: Direct Preference Optimization: Your Language Model is Secretly a Reward Model (DPO)\n- Fine-tuning dataset: Custom Medical Instruct dataset (We plan to release a sample training dataset in our upcoming paper; please stay updated)\n\nThis combination of cutting-edge techniques enables OpenBioLLM-70B to align with key capabilities and preferences for biomedical applications.\n\n️ Release Details:\n\n- Model Size: 70 billion parameters\n- Quantization: Optimized quantized versions available Here\n- Language(s) (NLP): en\n- Developed By: Ankit Pal (Aaditya Ura) from Saama AI Labs\n- License: Meta-Llama License\n- Fine-tuned from models: Meta-Llama-3-70B-Instruct\n- Resources for more information:\n - Paper: Coming soon\n\nThe model can be fine-tuned for more specialized tasks and datasets as needed.\n\nOpenBioLLM-70B represents an important step forward in democratizing advanced language AI for the biomedical community. By leveraging state-of-the-art architectures and training techniques from leading open source efforts like Llama-3, we have created a powerful tool to accelerate innovation and discovery in healthcare and the life sciences.\n\nWe are excited to share OpenBioLLM-70B with researchers and developers around the world.### Use with transformers\n\nImportant: 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.\n\nSee the snippet below for usage with Transformers:## Training procedure### Training hyperparameters\n\n<details>\n <summary>Click to see details</summary>\n\n- learning_rate: 0.0002\n- lr_scheduler: cosine\n- train_batch_size: 12\n- eval_batch_size: 8\n- GPU: H100 80GB SXM5\n- num_devices: 8\n- optimizer: adamw_bnb_8bit\n- lr_scheduler_warmup_steps: 100\n- num_epochs: 4\n</details>### Peft hyperparameters\n\n<details>\n <summary>Click to see details</summary>\n\n- adapter: qlora\n- lora_r: 128\n- lora_alpha: 256\n- lora_dropout: 0.05\n- lora_target_linear: true\n\n-lora_target_modules:\n- q_proj\n- v_proj\n- k_proj\n- o_proj\n- gate_proj\n- down_proj\n- up_proj\n</details>### Training results### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.1\n- Axolotl\n- Lm harness for evaluation# Benchmark Results\n\n OpenBioLLM-70B demonstrates superior performance compared to larger models, such as GPT-4, Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 across 9 diverse biomedical datasets, achieving state-of-the-art results with an average score of 86.06%, despite having a significantly smaller parameter count. The model's strong performance in domain-specific tasks, such as Clinical KG, Medical Genetics, and PubMedQA, highlights its ability to effectively capture and apply biomedical knowledge.\n\n 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.\n\n| | Clinical KG | Medical Genetics | Anatomy | Pro Medicine | College Biology | College Medicine | MedQA 4 opts | PubMedQA | MedMCQA | Avg |\n| | - | | - | |\n| OpenBioLLM-70B | 92.93 | 93.197 | 83.904 | 93.75 | 93.827 | 85.749 | 78.162 | 78.97 | 74.014 | 86.05588 |\n| Med-PaLM-2 (5-shot) | 88.3 | 90 | 77.8 | 95.2 | 94.4 | 80.9 | 79.7 | 79.2 | 71.3 | 84.08 |\n| GPT-4 | 86.04 | 91 | 80 | 93.01 | 95.14 | 76.88 | 78.87 | 75.2 | 69.52 | 82.85 |\n| 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 |\n| OpenBioLLM-8B | 76.101 | 86.1 | 69.829 | 78.21 | 84.213 | 68.042 | 58.993 | 74.12 | 56.913 | 72.502 |\n| Gemini-1.0 | 76.7 | 75.8 | 66.7 | 77.7 | 88 | 69.2 | 58 | 70.7 | 54.3 | 70.79 |\n| GPT-3.5 Turbo 1106 | 74.71 | 74 | 72.79 | 72.79 | 72.91 | 64.73 | 57.71 | 72.66 | 53.79 | 66 |\n| Meditron-70B | 66.79 | 69 | 53.33 | 71.69 | 76.38 | 63 | 57.1 | 76.6 | 46.85 | 64.52 |\n| gemma-7b | 69.81 | 70 | 59.26 | 66.18 | 79.86 | 60.12 | 47.21 | 76.2 | 48.96 | 64.18 |\n| Mistral-7B-v0.1 | 68.68 | 71 | 55.56 | 68.38 | 68.06 | 59.54 | 50.82 | 75.4 | 48.2 | 62.85 |\n| Apollo-7B | 62.26 | 72 | 61.48 | 69.12 | 70.83 | 55.49 | 55.22 | 39.8 | 53.77 | 60 |\n| MedAlpaca-7b | 57.36 | 69 | 57.04 | 67.28 | 65.28 | 54.34 | 41.71 | 72.8 | 37.51 | 58.03 |\n| BioMistral-7B | 59.9 | 64 | 56.5 | 60.4 | 59 | 54.7 | 50.6 | 77.5 | 48.1 | 57.3 |\n| AlpaCare-llama2-7b | 49.81 | 49 | 45.92 | 33.82 | 50 | 43.35 | 29.77 | 72.2 | 34.42 | 45.36 |\n| ClinicalGPT | 30.56 | 27 | 30.37 | 19.48 | 25 | 24.27 | 26.08 | 63.8 | 28.18 | 30.52 |\n\n<div align=\"center\">\n<img width=\"1600px\" src=\"URL\n</div>## Detailed Medical Subjectwise accuracy\n\n\n!image/png# Use Cases & Examples\n\n Below results are from the quantized version of OpenBioLLM-70B# Summarize Clinical Notes\n\nOpenBioLLM-70B can efficiently analyze and summarize complex clinical notes, EHR data, and discharge summaries, extracting key information and generating concise, structured summaries\n\n\n!image/png# Answer Medical Questions\n\nOpenBioLLM-70B can provide answers to a wide range of medical questions.\n\n\n!image/png\n!image/png\n\n<details>\n <summary>Click to see details</summary>\n\n\n!image/png\n!image/png\n!image/png\n\n</details># Clinical Entity Recognition\n\nOpenBioLLM-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.\n\n\n!image/png\n!image/png\n!image/png# Biomarkers Extraction\n\n\n!image/png# Classification\n\nOpenBioLLM-70B can perform various biomedical classification tasks, such as disease prediction, sentiment analysis, medical document categorization\n\n!image/png# De-Identification\n\nOpenBioLLM-70B can detect and remove personally identifiable information (PII) from medical records, ensuring patient privacy and compliance with data protection regulations like HIPAA.\n\n!image/png\n\n\n\nAdvisory Notice!\n\nWhile OpenBioLLM-70B leverages high-quality data sources, its outputs may still contain inaccuracies, biases, or misalignments that could pose risks if relied upon for medical decision-making without further testing and refinement. The model's performance has not yet been rigorously evaluated in randomized controlled trials or real-world healthcare environments.\n\nTherefore, we strongly advise against using OpenBioLLM-70B for any direct patient care, clinical decision support, or other professional medical purposes at this time. Its use should be limited to research, development, and exploratory applications by qualified individuals who understand its limitations.\nOpenBioLLM-70B is intended solely as a research tool to assist healthcare professionals and should never be considered a replacement for the professional judgment and expertise of a qualified medical doctor.\n\nAppropriately adapting and validating OpenBioLLM-70B for specific medical use cases would require significant additional work, potentially including:\n\n- Thorough testing and evaluation in relevant clinical scenarios\n- Alignment with evidence-based guidelines and best practices\n- Mitigation of potential biases and failure modes\n- Integration with human oversight and interpretation\n- Compliance with regulatory and ethical standards\n\nAlways consult a qualified healthcare provider for personal medical needs.\n\n\n\nIf you find OpenBioLLM-70B & 8B useful in your work, please cite the model as follows:\n\n\n\nThe accompanying paper is currently in progress and will be released soon.\n\n<div align=\"center\">\n<h2> Contact </h2>\n</div>\n\nWe look forward to hearing you and collaborating on this exciting project!\n\nContributors:\n- Ankit Pal (Aaditya Ura) [aadityaura at gmail dot com]\n- Saama AI Labs\n- 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\n\nWe thank the Meta Team for their amazing models!\n\n\nResult sources\n\n- [1] GPT-4 [Capabilities of GPT-4 on Medical Challenge Problems] (URL\n- [2] Med-PaLM-1 Large Language Models Encode Clinical Knowledge\n- [3] Med-PaLM-2 Towards Expert-Level Medical Question Answering with Large Language Models\n- [4] Gemini-1.0 Gemini Goes to Med School" ]

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

[ "1910.09700" ]

[]

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

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

[ 26, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

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

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

[]

[ "en" ]

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

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

[ 64, 81 ]

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

[ "transformers", "phi3", "text-generation", "pruna-ai", "conversational", "custom_code", "base_model:microsoft/Phi-3-mini-128k-instruct", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.", "## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with hqq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.", "## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo microsoft/Phi-3-mini-128k-instruct installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.", "## Configurations\n\nThe configuration info are in 'smash_config.json'.", "## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model microsoft/Phi-3-mini-128k-instruct before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.", "## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ "TAGS\n#transformers #phi3 #text-generation #pruna-ai #conversational #custom_code #base_model-microsoft/Phi-3-mini-128k-instruct #autotrain_compatible #endpoints_compatible #region-us \n", "# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.", "## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with hqq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.", "## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo microsoft/Phi-3-mini-128k-instruct installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.", "## Configurations\n\nThe configuration info are in 'smash_config.json'.", "## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model microsoft/Phi-3-mini-128k-instruct before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.", "## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ 54, 83, 451, 72, 19, 67, 36 ]

[ "TAGS\n#transformers #phi3 #text-generation #pruna-ai #conversational #custom_code #base_model-microsoft/Phi-3-mini-128k-instruct #autotrain_compatible #endpoints_compatible #region-us \n# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with hqq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo microsoft/Phi-3-mini-128k-instruct installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.## Configurations\n\nThe configuration info are in 'smash_config.json'.## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model microsoft/Phi-3-mini-128k-instruct before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ "transformers", "safetensors", "gemma", "text-generation", "pruna-ai", "base_model:google/codegemma-7b-it", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]

[]

[]

[ "# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.", "## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with awq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.", "## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo google/codegemma-7b-it installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.", "## Configurations\n\nThe configuration info are in 'smash_config.json'.", "## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model google/codegemma-7b-it before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.", "## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ "TAGS\n#transformers #safetensors #gemma #text-generation #pruna-ai #base_model-google/codegemma-7b-it #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n", "# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.", "## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with awq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.", "## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo google/codegemma-7b-it installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.", "## Configurations\n\nThe configuration info are in 'smash_config.json'.", "## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model google/codegemma-7b-it before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.", "## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ 57, 83, 451, 69, 19, 64, 36 ]

[ "TAGS\n#transformers #safetensors #gemma #text-generation #pruna-ai #base_model-google/codegemma-7b-it #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with awq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo google/codegemma-7b-it installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.## Configurations\n\nThe configuration info are in 'smash_config.json'.## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model google/codegemma-7b-it before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ "transformers", "tensorboard", "safetensors", "mbart", "text2text-generation", "translation", "generated_from_trainer", "base_model:vinai/vinai-translate-en2vi-v2", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "# vinai_EnglistToVietnamese\n\nThis model is a fine-tuned version of vinai/vinai-translate-en2vi-v2 on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 2e-05\n- train_batch_size: 64\n- eval_batch_size: 128\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 3\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.36.2\n- Pytorch 2.1.1+cu121\n- Datasets 2.15.0\n- Tokenizers 0.15.0" ]

[ "TAGS\n#transformers #tensorboard #safetensors #mbart #text2text-generation #translation #generated_from_trainer #base_model-vinai/vinai-translate-en2vi-v2 #autotrain_compatible #endpoints_compatible #region-us \n", "# vinai_EnglistToVietnamese\n\nThis model is a fine-tuned version of vinai/vinai-translate-en2vi-v2 on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 2e-05\n- train_batch_size: 64\n- eval_batch_size: 128\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 3\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.36.2\n- Pytorch 2.1.1+cu121\n- Datasets 2.15.0\n- Tokenizers 0.15.0" ]

[ 60, 40, 7, 9, 9, 4, 102, 5, 44 ]

[ "TAGS\n#transformers #tensorboard #safetensors #mbart #text2text-generation #translation #generated_from_trainer #base_model-vinai/vinai-translate-en2vi-v2 #autotrain_compatible #endpoints_compatible #region-us \n# vinai_EnglistToVietnamese\n\nThis model is a fine-tuned version of vinai/vinai-translate-en2vi-v2 on the None dataset.## Model description\n\nMore information needed## Intended uses & limitations\n\nMore information needed## Training and evaluation data\n\nMore information needed## Training procedure### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 2e-05\n- train_batch_size: 64\n- eval_batch_size: 128\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 3\n- mixed_precision_training: Native AMP### Training results### Framework versions\n\n- Transformers 4.36.2\n- Pytorch 2.1.1+cu121\n- Datasets 2.15.0\n- Tokenizers 0.15.0" ]

[ "transformers", "safetensors", "gemma", "text-generation", "pruna-ai", "conversational", "base_model:google/gemma-7b-it", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]

[]

[]

[ "# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.", "## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with awq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.", "## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo google/gemma-7b-it installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.", "## Configurations\n\nThe configuration info are in 'smash_config.json'.", "## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model google/gemma-7b-it before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.", "## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ "TAGS\n#transformers #safetensors #gemma #text-generation #pruna-ai #conversational #base_model-google/gemma-7b-it #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n", "# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.", "## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with awq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.", "## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo google/gemma-7b-it installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.", "## Configurations\n\nThe configuration info are in 'smash_config.json'.", "## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model google/gemma-7b-it before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.", "## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ 58, 83, 451, 67, 19, 62, 36 ]

[ "TAGS\n#transformers #safetensors #gemma #text-generation #pruna-ai #conversational #base_model-google/gemma-7b-it #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with awq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo google/gemma-7b-it installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.## Configurations\n\nThe configuration info are in 'smash_config.json'.## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model google/gemma-7b-it before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ "transformers", "phi3", "text-generation", "pruna-ai", "conversational", "custom_code", "base_model:microsoft/Phi-3-mini-128k-instruct", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.", "## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with hqq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.", "## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo microsoft/Phi-3-mini-128k-instruct installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.", "## Configurations\n\nThe configuration info are in 'smash_config.json'.", "## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model microsoft/Phi-3-mini-128k-instruct before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.", "## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ "TAGS\n#transformers #phi3 #text-generation #pruna-ai #conversational #custom_code #base_model-microsoft/Phi-3-mini-128k-instruct #autotrain_compatible #endpoints_compatible #region-us \n", "# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.", "## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with hqq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.", "## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo microsoft/Phi-3-mini-128k-instruct installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.", "## Configurations\n\nThe configuration info are in 'smash_config.json'.", "## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model microsoft/Phi-3-mini-128k-instruct before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.", "## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ 54, 83, 451, 72, 19, 67, 36 ]

[ "TAGS\n#transformers #phi3 #text-generation #pruna-ai #conversational #custom_code #base_model-microsoft/Phi-3-mini-128k-instruct #autotrain_compatible #endpoints_compatible #region-us \n# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with hqq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo microsoft/Phi-3-mini-128k-instruct installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.## Configurations\n\nThe configuration info are in 'smash_config.json'.## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model microsoft/Phi-3-mini-128k-instruct before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ "sentence-transformers", "safetensors", "bert", "feature-extraction", "sentence-similarity", "transformers", "endpoints_compatible", "region:us" ]

[]

[]

[ "# DivyaMereddy007/FewLayers_Finetuning_V1_TrainSetenceTransforme-Finetuning_COpyfromv5finetuneEPOC5\n\nThis is a sentence-transformers model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.", "## Usage (Sentence-Transformers)\n\nUsing this model becomes easy when you have sentence-transformers installed:\n\n\n\nThen you can use the model like this:", "## Usage (HuggingFace Transformers)\nWithout sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.", "## Evaluation Results\n\n\n\nFor an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: URL", "## Training\nThe model was trained with the parameters:\n\nDataLoader:\n\n'URL.dataloader.DataLoader' of length 55 with parameters:\n\n\nLoss:\n\n'sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss' \n\nParameters of the fit()-Method:", "## Full Model Architecture", "## Citing & Authors" ]

[ "TAGS\n#sentence-transformers #safetensors #bert #feature-extraction #sentence-similarity #transformers #endpoints_compatible #region-us \n", "# DivyaMereddy007/FewLayers_Finetuning_V1_TrainSetenceTransforme-Finetuning_COpyfromv5finetuneEPOC5\n\nThis is a sentence-transformers model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.", "## Usage (Sentence-Transformers)\n\nUsing this model becomes easy when you have sentence-transformers installed:\n\n\n\nThen you can use the model like this:", "## Usage (HuggingFace Transformers)\nWithout sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.", "## Evaluation Results\n\n\n\nFor an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: URL", "## Training\nThe model was trained with the parameters:\n\nDataLoader:\n\n'URL.dataloader.DataLoader' of length 55 with parameters:\n\n\nLoss:\n\n'sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss' \n\nParameters of the fit()-Method:", "## Full Model Architecture", "## Citing & Authors" ]

[ 30, 78, 30, 58, 26, 69, 5, 5 ]

[ "TAGS\n#sentence-transformers #safetensors #bert #feature-extraction #sentence-similarity #transformers #endpoints_compatible #region-us \n# DivyaMereddy007/FewLayers_Finetuning_V1_TrainSetenceTransforme-Finetuning_COpyfromv5finetuneEPOC5\n\nThis is a sentence-transformers model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.## Usage (Sentence-Transformers)\n\nUsing this model becomes easy when you have sentence-transformers installed:\n\n\n\nThen you can use the model like this:## Usage (HuggingFace Transformers)\nWithout sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.## Evaluation Results\n\n\n\nFor an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: URL## Training\nThe model was trained with the parameters:\n\nDataLoader:\n\n'URL.dataloader.DataLoader' of length 55 with parameters:\n\n\nLoss:\n\n'sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss' \n\nParameters of the fit()-Method:## Full Model Architecture## Citing & Authors" ]

[ "transformers", "phi3", "text-generation", "pruna-ai", "conversational", "custom_code", "base_model:microsoft/Phi-3-mini-4k-instruct", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.", "## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with hqq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.", "## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo microsoft/Phi-3-mini-4k-instruct installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.", "## Configurations\n\nThe configuration info are in 'smash_config.json'.", "## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model microsoft/Phi-3-mini-4k-instruct before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.", "## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ "TAGS\n#transformers #phi3 #text-generation #pruna-ai #conversational #custom_code #base_model-microsoft/Phi-3-mini-4k-instruct #autotrain_compatible #endpoints_compatible #region-us \n", "# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.", "## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with hqq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.", "## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo microsoft/Phi-3-mini-4k-instruct installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.", "## Configurations\n\nThe configuration info are in 'smash_config.json'.", "## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model microsoft/Phi-3-mini-4k-instruct before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.", "## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ 54, 83, 451, 72, 19, 67, 36 ]

[ "TAGS\n#transformers #phi3 #text-generation #pruna-ai #conversational #custom_code #base_model-microsoft/Phi-3-mini-4k-instruct #autotrain_compatible #endpoints_compatible #region-us \n# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with hqq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo microsoft/Phi-3-mini-4k-instruct installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.## Configurations\n\nThe configuration info are in 'smash_config.json'.## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model microsoft/Phi-3-mini-4k-instruct before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ "transformers", "safetensors", "gemma", "text-generation", "pruna-ai", "base_model:google/gemma-7b", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]

[]

[]

[ "# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.", "## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with awq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.", "## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo google/gemma-7b installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.", "## Configurations\n\nThe configuration info are in 'smash_config.json'.", "## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model google/gemma-7b before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.", "## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ "TAGS\n#transformers #safetensors #gemma #text-generation #pruna-ai #base_model-google/gemma-7b #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n", "# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.", "## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with awq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.", "## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo google/gemma-7b installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.", "## Configurations\n\nThe configuration info are in 'smash_config.json'.", "## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model google/gemma-7b before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.", "## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ 53, 83, 451, 65, 19, 60, 36 ]

[ "TAGS\n#transformers #safetensors #gemma #text-generation #pruna-ai #base_model-google/gemma-7b #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with awq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo google/gemma-7b installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.## Configurations\n\nThe configuration info are in 'smash_config.json'.## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model google/gemma-7b before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ "transformers", "phi3", "text-generation", "pruna-ai", "conversational", "custom_code", "base_model:microsoft/Phi-3-mini-4k-instruct", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.", "## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with hqq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.", "## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo microsoft/Phi-3-mini-4k-instruct installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.", "## Configurations\n\nThe configuration info are in 'smash_config.json'.", "## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model microsoft/Phi-3-mini-4k-instruct before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.", "## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ "TAGS\n#transformers #phi3 #text-generation #pruna-ai #conversational #custom_code #base_model-microsoft/Phi-3-mini-4k-instruct #autotrain_compatible #endpoints_compatible #region-us \n", "# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.", "## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with hqq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.", "## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo microsoft/Phi-3-mini-4k-instruct installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.", "## Configurations\n\nThe configuration info are in 'smash_config.json'.", "## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model microsoft/Phi-3-mini-4k-instruct before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.", "## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ 54, 83, 451, 72, 19, 67, 36 ]

[ "TAGS\n#transformers #phi3 #text-generation #pruna-ai #conversational #custom_code #base_model-microsoft/Phi-3-mini-4k-instruct #autotrain_compatible #endpoints_compatible #region-us \n# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with hqq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo microsoft/Phi-3-mini-4k-instruct installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.## Configurations\n\nThe configuration info are in 'smash_config.json'.## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model microsoft/Phi-3-mini-4k-instruct before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ "transformers", "safetensors", "cohere", "text-generation", "conversational", "en", "fr", "de", "es", "it", "pt", "ja", "ko", "zh", "ar", "license:cc-by-nc-4.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]

[]

[ "en", "fr", "de", "es", "it", "pt", "ja", "ko", "zh", "ar" ]

[ "# Model Card for C4AI Command-R\n\n This model is non-quantized version of C4AI Command-R. You can find the quantized version of C4AI Command-R using bitsandbytes here.", "## Model Summary\n\nC4AI Command-R is a research release of a 35 billion parameter highly performant generative model. Command-R is a large language model with open weights optimized for a variety of use cases including reasoning, summarization, and question answering. Command-R has the capability for multilingual generation evaluated in 10 languages and highly performant RAG capabilities.\n\nDeveloped by: Cohere and Cohere For AI\n\n- Point of Contact: Cohere For AI: URL\n- License: CC-BY-NC, requires also adhering to C4AI's Acceptable Use Policy\n- Model: c4ai-command-r-v01\n- Model Size: 35 billion parameters\n- Context length: 128K\n\nTry C4AI Command R\n\nIf you want to try Command R before downloading the weights, the model is hosted in a hugging face space here.\n\nUsage\n\nPlease use 'transformers' version 4.39.1 or higher\n\n\nQuantized model through bitsandbytes, 8-bit precision\n\n\n\nQuantized model through bitsandbytes, 4-bit precision\n\nYou can find a quantized version of this model to 4-bit precision here.", "## Model Details\n\nInput: Models input text only.\n\nOutput: Models generate text only.\n\nModel Architecture: This is an auto-regressive language model that uses an optimized transformer architecture. After pretraining, this model uses supervised fine-tuning (SFT) and preference training to align model behavior to human preferences for helpfulness and safety.\n\nLanguages covered: The model is optimized to perform well in the following languages: English, French, Spanish, Italian, German, Brazilian Portuguese, Japanese, Korean, Simplified Chinese, and Arabic. \n\nPre-training data additionally included the following 13 languages: Russian, Polish, Turkish, Vietnamese, Dutch, Czech, Indonesian, Ukrainian, Romanian, Greek, Hindi, Hebrew, Persian.\n\nContext length: Command-R supports a context length of 128K.", "### Tool use capabilities:\n\nCommand-R has been specifically trained with conversational tool use capabilities. These have been trained into the model via a mixture of supervised fine-tuning and preference fine-tuning, using a specific prompt template. Deviating from this prompt template will likely reduce performance, but we encourage experimentation.\n\nCommand-R’s tool use functionality takes a conversation as input (with an optional user-system preamble), along with a list of available tools. The model will then generate a json-formatted list of actions to execute on a subset of those tools. Command-R may use one of its supplied tools more than once. \n\nThe model has been trained to recognise a special 'directly_answer' tool, which it uses to indicate that it doesn’t want to use any of its other tools. The ability to abstain from calling a specific tool can be useful in a range of situations, such as greeting a user, or asking clarifying questions.\nWe recommend including the 'directly_answer' tool, but it can be removed or renamed if required.\n\nComprehensive documentation for working with command-R's tool use prompt template can be found here.\n\nThe code snippet below shows a minimal working example on how to render a prompt.\n\n<details>\n<summary><b>Usage: Rendering Tool Use Prompts [CLICK TO EXPAND]</b> </summary>\n\n\n\n</details>\n\n<details>\n<summary><b>Example Rendered Tool Use Prompt [CLICK TO EXPAND]</b></summary>\n\npython\ndef internet_search(query: str) -> List[Dict]:\n \"\"\"Returns a list of relevant document snippets for a textual query retrieved from the internet\n\n Args:\n query (str): Query to search the internet with\n \"\"\"\n pass\npython\ndef directly_answer() -> List[Dict]:\n \"\"\"Calls a standard (un-augmented) AI chatbot to generate a response given the conversation history\n \"\"\"\n pass\njson\n[\n {\n \"tool_name\": title of the tool in the specification,\n \"parameters\": a dict of parameters to input into the tool as they are defined in the specs, or {} if it takes no parameters\n }\n]'\n\n</details>\n\n<details>\n<summary><b>Example Rendered Tool Use Completion [CLICK TO EXPAND]</b></summary>\n\njson\n[\n {\n \"tool_name\": \"internet_search\",\n \"parameters\": {\n \"query\": \"biggest penguin in the world\"\n }\n }\n]\n'\n</details>", "### Grounded Generation and RAG Capabilities: \n\nCommand-R has been specifically trained with grounded generation capabilities. This means that it can generate responses based on a list of supplied document snippets, and it will include grounding spans (citations) in its response indicating the source of the information.\nThis can be used to enable behaviors such as grounded summarization and the final step of Retrieval Augmented Generation (RAG).This behavior has been trained into the model via a mixture of supervised fine-tuning and preference fine-tuning, using a specific prompt template.\nDeviating from this prompt template may reduce performance, but we encourage experimentation.\n\nCommand-R’s grounded generation behavior takes a conversation as input (with an optional user-supplied system preamble, indicating task, context and desired output style), along with a list of retrieved document snippets.\nThe document snippets should be chunks, rather than long documents, typically around 100-400 words per chunk. Document snippets consist of key-value pairs. The keys should be short descriptive strings, the values can be text or semi-structured.\n\nBy default, Command-R will generate grounded responses by first predicting which documents are relevant, then predicting which ones it will cite, then generating an answer. \nFinally, it will then insert grounding spans into the answer. See below for an example. This is referred to as 'accurate' grounded generation.\n\nThe model is trained with a number of other answering modes, which can be selected by prompt changes . A 'fast' citation mode is supported in the tokenizer, which will directly generate an answer with grounding spans in it, without first writing the answer out in full. This sacrifices some grounding accuracy in favor of generating fewer tokens.\n\nComprehensive documentation for working with command-R's grounded generation prompt template can be found here.\n\nThe code snippet below shows a minimal working example on how to render a prompt.\n\n<details>\n<summary> <b>Usage: Rendering Grounded Generation prompts [CLICK TO EXPAND]</b> </summary>\n\n'\n</details>\n\n<details>\n<summary><b>Example Rendered Grounded Generation Prompt [CLICK TO EXPAND]</b></summary>\n \n'\n\n</details>\n\n<details>\n<summary><b>Example Rendered Grounded Generation Completion [CLICK TO EXPAND]</b></summary>\n\n'\n</details>", "### Code Capabilities:\nCommand-R has been optimized to interact with your code, by requesting code snippets, code explanations, or code rewrites. It might not perform well out-of-the-box for pure code completion. For better performance, we also recommend using a low temperature (and even greedy decoding) for code-generation related instructions.", "### Model Card Contact\nFor errors or additional questions about details in this model card, contact info@URL.", "### Terms of Use: \nWe hope that the release of this model will make community-based research efforts more accessible, by releasing the weights of a highly performant 35 billion parameter model to researchers all over the world. This model is governed by a CC-BY-NC License with an acceptable use addendum, and also requires adhering to C4AI's Acceptable Use Policy.", "### Try Chat:\nYou can try Command-R chat in the playground here." ]

[ "TAGS\n#transformers #safetensors #cohere #text-generation #conversational #en #fr #de #es #it #pt #ja #ko #zh #ar #license-cc-by-nc-4.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n", "# Model Card for C4AI Command-R\n\n This model is non-quantized version of C4AI Command-R. You can find the quantized version of C4AI Command-R using bitsandbytes here.", "## Model Summary\n\nC4AI Command-R is a research release of a 35 billion parameter highly performant generative model. Command-R is a large language model with open weights optimized for a variety of use cases including reasoning, summarization, and question answering. Command-R has the capability for multilingual generation evaluated in 10 languages and highly performant RAG capabilities.\n\nDeveloped by: Cohere and Cohere For AI\n\n- Point of Contact: Cohere For AI: URL\n- License: CC-BY-NC, requires also adhering to C4AI's Acceptable Use Policy\n- Model: c4ai-command-r-v01\n- Model Size: 35 billion parameters\n- Context length: 128K\n\nTry C4AI Command R\n\nIf you want to try Command R before downloading the weights, the model is hosted in a hugging face space here.\n\nUsage\n\nPlease use 'transformers' version 4.39.1 or higher\n\n\nQuantized model through bitsandbytes, 8-bit precision\n\n\n\nQuantized model through bitsandbytes, 4-bit precision\n\nYou can find a quantized version of this model to 4-bit precision here.", "## Model Details\n\nInput: Models input text only.\n\nOutput: Models generate text only.\n\nModel Architecture: This is an auto-regressive language model that uses an optimized transformer architecture. After pretraining, this model uses supervised fine-tuning (SFT) and preference training to align model behavior to human preferences for helpfulness and safety.\n\nLanguages covered: The model is optimized to perform well in the following languages: English, French, Spanish, Italian, German, Brazilian Portuguese, Japanese, Korean, Simplified Chinese, and Arabic. \n\nPre-training data additionally included the following 13 languages: Russian, Polish, Turkish, Vietnamese, Dutch, Czech, Indonesian, Ukrainian, Romanian, Greek, Hindi, Hebrew, Persian.\n\nContext length: Command-R supports a context length of 128K.", "### Tool use capabilities:\n\nCommand-R has been specifically trained with conversational tool use capabilities. These have been trained into the model via a mixture of supervised fine-tuning and preference fine-tuning, using a specific prompt template. Deviating from this prompt template will likely reduce performance, but we encourage experimentation.\n\nCommand-R’s tool use functionality takes a conversation as input (with an optional user-system preamble), along with a list of available tools. The model will then generate a json-formatted list of actions to execute on a subset of those tools. Command-R may use one of its supplied tools more than once. \n\nThe model has been trained to recognise a special 'directly_answer' tool, which it uses to indicate that it doesn’t want to use any of its other tools. The ability to abstain from calling a specific tool can be useful in a range of situations, such as greeting a user, or asking clarifying questions.\nWe recommend including the 'directly_answer' tool, but it can be removed or renamed if required.\n\nComprehensive documentation for working with command-R's tool use prompt template can be found here.\n\nThe code snippet below shows a minimal working example on how to render a prompt.\n\n<details>\n<summary><b>Usage: Rendering Tool Use Prompts [CLICK TO EXPAND]</b> </summary>\n\n\n\n</details>\n\n<details>\n<summary><b>Example Rendered Tool Use Prompt [CLICK TO EXPAND]</b></summary>\n\npython\ndef internet_search(query: str) -> List[Dict]:\n \"\"\"Returns a list of relevant document snippets for a textual query retrieved from the internet\n\n Args:\n query (str): Query to search the internet with\n \"\"\"\n pass\npython\ndef directly_answer() -> List[Dict]:\n \"\"\"Calls a standard (un-augmented) AI chatbot to generate a response given the conversation history\n \"\"\"\n pass\njson\n[\n {\n \"tool_name\": title of the tool in the specification,\n \"parameters\": a dict of parameters to input into the tool as they are defined in the specs, or {} if it takes no parameters\n }\n]'\n\n</details>\n\n<details>\n<summary><b>Example Rendered Tool Use Completion [CLICK TO EXPAND]</b></summary>\n\njson\n[\n {\n \"tool_name\": \"internet_search\",\n \"parameters\": {\n \"query\": \"biggest penguin in the world\"\n }\n }\n]\n'\n</details>", "### Grounded Generation and RAG Capabilities: \n\nCommand-R has been specifically trained with grounded generation capabilities. This means that it can generate responses based on a list of supplied document snippets, and it will include grounding spans (citations) in its response indicating the source of the information.\nThis can be used to enable behaviors such as grounded summarization and the final step of Retrieval Augmented Generation (RAG).This behavior has been trained into the model via a mixture of supervised fine-tuning and preference fine-tuning, using a specific prompt template.\nDeviating from this prompt template may reduce performance, but we encourage experimentation.\n\nCommand-R’s grounded generation behavior takes a conversation as input (with an optional user-supplied system preamble, indicating task, context and desired output style), along with a list of retrieved document snippets.\nThe document snippets should be chunks, rather than long documents, typically around 100-400 words per chunk. Document snippets consist of key-value pairs. The keys should be short descriptive strings, the values can be text or semi-structured.\n\nBy default, Command-R will generate grounded responses by first predicting which documents are relevant, then predicting which ones it will cite, then generating an answer. \nFinally, it will then insert grounding spans into the answer. See below for an example. This is referred to as 'accurate' grounded generation.\n\nThe model is trained with a number of other answering modes, which can be selected by prompt changes . A 'fast' citation mode is supported in the tokenizer, which will directly generate an answer with grounding spans in it, without first writing the answer out in full. This sacrifices some grounding accuracy in favor of generating fewer tokens.\n\nComprehensive documentation for working with command-R's grounded generation prompt template can be found here.\n\nThe code snippet below shows a minimal working example on how to render a prompt.\n\n<details>\n<summary> <b>Usage: Rendering Grounded Generation prompts [CLICK TO EXPAND]</b> </summary>\n\n'\n</details>\n\n<details>\n<summary><b>Example Rendered Grounded Generation Prompt [CLICK TO EXPAND]</b></summary>\n \n'\n\n</details>\n\n<details>\n<summary><b>Example Rendered Grounded Generation Completion [CLICK TO EXPAND]</b></summary>\n\n'\n</details>", "### Code Capabilities:\nCommand-R has been optimized to interact with your code, by requesting code snippets, code explanations, or code rewrites. It might not perform well out-of-the-box for pure code completion. For better performance, we also recommend using a low temperature (and even greedy decoding) for code-generation related instructions.", "### Model Card Contact\nFor errors or additional questions about details in this model card, contact info@URL.", "### Terms of Use: \nWe hope that the release of this model will make community-based research efforts more accessible, by releasing the weights of a highly performant 35 billion parameter model to researchers all over the world. This model is governed by a CC-BY-NC License with an acceptable use addendum, and also requires adhering to C4AI's Acceptable Use Policy.", "### Try Chat:\nYou can try Command-R chat in the playground here." ]

[ 75, 47, 239, 164, 541, 494, 79, 24, 80, 18 ]

[ "TAGS\n#transformers #safetensors #cohere #text-generation #conversational #en #fr #de #es #it #pt #ja #ko #zh #ar #license-cc-by-nc-4.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n# Model Card for C4AI Command-R\n\n This model is non-quantized version of C4AI Command-R. You can find the quantized version of C4AI Command-R using bitsandbytes here.## Model Summary\n\nC4AI Command-R is a research release of a 35 billion parameter highly performant generative model. Command-R is a large language model with open weights optimized for a variety of use cases including reasoning, summarization, and question answering. Command-R has the capability for multilingual generation evaluated in 10 languages and highly performant RAG capabilities.\n\nDeveloped by: Cohere and Cohere For AI\n\n- Point of Contact: Cohere For AI: URL\n- License: CC-BY-NC, requires also adhering to C4AI's Acceptable Use Policy\n- Model: c4ai-command-r-v01\n- Model Size: 35 billion parameters\n- Context length: 128K\n\nTry C4AI Command R\n\nIf you want to try Command R before downloading the weights, the model is hosted in a hugging face space here.\n\nUsage\n\nPlease use 'transformers' version 4.39.1 or higher\n\n\nQuantized model through bitsandbytes, 8-bit precision\n\n\n\nQuantized model through bitsandbytes, 4-bit precision\n\nYou can find a quantized version of this model to 4-bit precision here.## Model Details\n\nInput: Models input text only.\n\nOutput: Models generate text only.\n\nModel Architecture: This is an auto-regressive language model that uses an optimized transformer architecture. After pretraining, this model uses supervised fine-tuning (SFT) and preference training to align model behavior to human preferences for helpfulness and safety.\n\nLanguages covered: The model is optimized to perform well in the following languages: English, French, Spanish, Italian, German, Brazilian Portuguese, Japanese, Korean, Simplified Chinese, and Arabic. \n\nPre-training data additionally included the following 13 languages: Russian, Polish, Turkish, Vietnamese, Dutch, Czech, Indonesian, Ukrainian, Romanian, Greek, Hindi, Hebrew, Persian.\n\nContext length: Command-R supports a context length of 128K.### Tool use capabilities:\n\nCommand-R has been specifically trained with conversational tool use capabilities. These have been trained into the model via a mixture of supervised fine-tuning and preference fine-tuning, using a specific prompt template. Deviating from this prompt template will likely reduce performance, but we encourage experimentation.\n\nCommand-R’s tool use functionality takes a conversation as input (with an optional user-system preamble), along with a list of available tools. The model will then generate a json-formatted list of actions to execute on a subset of those tools. Command-R may use one of its supplied tools more than once. \n\nThe model has been trained to recognise a special 'directly_answer' tool, which it uses to indicate that it doesn’t want to use any of its other tools. The ability to abstain from calling a specific tool can be useful in a range of situations, such as greeting a user, or asking clarifying questions.\nWe recommend including the 'directly_answer' tool, but it can be removed or renamed if required.\n\nComprehensive documentation for working with command-R's tool use prompt template can be found here.\n\nThe code snippet below shows a minimal working example on how to render a prompt.\n\n<details>\n<summary><b>Usage: Rendering Tool Use Prompts [CLICK TO EXPAND]</b> </summary>\n\n\n\n</details>\n\n<details>\n<summary><b>Example Rendered Tool Use Prompt [CLICK TO EXPAND]</b></summary>\n\npython\ndef internet_search(query: str) -> List[Dict]:\n \"\"\"Returns a list of relevant document snippets for a textual query retrieved from the internet\n\n Args:\n query (str): Query to search the internet with\n \"\"\"\n pass\npython\ndef directly_answer() -> List[Dict]:\n \"\"\"Calls a standard (un-augmented) AI chatbot to generate a response given the conversation history\n \"\"\"\n pass\njson\n[\n {\n \"tool_name\": title of the tool in the specification,\n \"parameters\": a dict of parameters to input into the tool as they are defined in the specs, or {} if it takes no parameters\n }\n]'\n\n</details>\n\n<details>\n<summary><b>Example Rendered Tool Use Completion [CLICK TO EXPAND]</b></summary>\n\njson\n[\n {\n \"tool_name\": \"internet_search\",\n \"parameters\": {\n \"query\": \"biggest penguin in the world\"\n }\n }\n]\n'\n</details>### Grounded Generation and RAG Capabilities: \n\nCommand-R has been specifically trained with grounded generation capabilities. This means that it can generate responses based on a list of supplied document snippets, and it will include grounding spans (citations) in its response indicating the source of the information.\nThis can be used to enable behaviors such as grounded summarization and the final step of Retrieval Augmented Generation (RAG).This behavior has been trained into the model via a mixture of supervised fine-tuning and preference fine-tuning, using a specific prompt template.\nDeviating from this prompt template may reduce performance, but we encourage experimentation.\n\nCommand-R’s grounded generation behavior takes a conversation as input (with an optional user-supplied system preamble, indicating task, context and desired output style), along with a list of retrieved document snippets.\nThe document snippets should be chunks, rather than long documents, typically around 100-400 words per chunk. Document snippets consist of key-value pairs. The keys should be short descriptive strings, the values can be text or semi-structured.\n\nBy default, Command-R will generate grounded responses by first predicting which documents are relevant, then predicting which ones it will cite, then generating an answer. \nFinally, it will then insert grounding spans into the answer. See below for an example. This is referred to as 'accurate' grounded generation.\n\nThe model is trained with a number of other answering modes, which can be selected by prompt changes . A 'fast' citation mode is supported in the tokenizer, which will directly generate an answer with grounding spans in it, without first writing the answer out in full. This sacrifices some grounding accuracy in favor of generating fewer tokens.\n\nComprehensive documentation for working with command-R's grounded generation prompt template can be found here.\n\nThe code snippet below shows a minimal working example on how to render a prompt.\n\n<details>\n<summary> <b>Usage: Rendering Grounded Generation prompts [CLICK TO EXPAND]</b> </summary>\n\n'\n</details>\n\n<details>\n<summary><b>Example Rendered Grounded Generation Prompt [CLICK TO EXPAND]</b></summary>\n \n'\n\n</details>\n\n<details>\n<summary><b>Example Rendered Grounded Generation Completion [CLICK TO EXPAND]</b></summary>\n\n'\n</details>### Code Capabilities:\nCommand-R has been optimized to interact with your code, by requesting code snippets, code explanations, or code rewrites. It might not perform well out-of-the-box for pure code completion. For better performance, we also recommend using a low temperature (and even greedy decoding) for code-generation related instructions.### Model Card Contact\nFor errors or additional questions about details in this model card, contact info@URL.### Terms of Use: \nWe hope that the release of this model will make community-based research efforts more accessible, by releasing the weights of a highly performant 35 billion parameter model to researchers all over the world. This model is governed by a CC-BY-NC License with an acceptable use addendum, and also requires adhering to C4AI's Acceptable Use Policy.### Try Chat:\nYou can try Command-R chat in the playground here." ]

[ "peft", "safetensors", "trl", "sft", "generated_from_trainer", "dataset:generator", "base_model:openthaigpt/openthai-llama-pretrained-7B", "region:us" ]

[]

[]

[ "# sea-lion-7b\n\nThis model is a fine-tuned version of openthaigpt/openthai-llama-pretrained-7B on the generator dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0002\n- train_batch_size: 3\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 6\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: constant\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 3", "### Training results", "### Framework versions\n\n- PEFT 0.7.2.dev0\n- Transformers 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.16.1\n- Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #trl #sft #generated_from_trainer #dataset-generator #base_model-openthaigpt/openthai-llama-pretrained-7B #region-us \n", "# sea-lion-7b\n\nThis model is a fine-tuned version of openthaigpt/openthai-llama-pretrained-7B on the generator dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0002\n- train_batch_size: 3\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 6\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: constant\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 3", "### Training results", "### Framework versions\n\n- PEFT 0.7.2.dev0\n- Transformers 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.16.1\n- Tokenizers 0.15.2" ]

[ 52, 40, 7, 9, 9, 4, 126, 5, 55 ]

[ "TAGS\n#peft #safetensors #trl #sft #generated_from_trainer #dataset-generator #base_model-openthaigpt/openthai-llama-pretrained-7B #region-us \n# sea-lion-7b\n\nThis model is a fine-tuned version of openthaigpt/openthai-llama-pretrained-7B on the generator dataset.## Model description\n\nMore information needed## Intended uses & limitations\n\nMore information needed## Training and evaluation data\n\nMore information needed## Training procedure### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0002\n- train_batch_size: 3\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 6\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: constant\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 3### Training results### Framework versions\n\n- PEFT 0.7.2.dev0\n- Transformers 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.16.1\n- Tokenizers 0.15.2" ]

[ "FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]

[]

[]

[ "# Q-Learning Agent playing1 FrozenLake-v1\n This is a trained model of a Q-Learning agent playing FrozenLake-v1 .\n\n ## Usage" ]

[ "TAGS\n#FrozenLake-v1-4x4-no_slippery #q-learning #reinforcement-learning #custom-implementation #model-index #region-us \n", "# Q-Learning Agent playing1 FrozenLake-v1\n This is a trained model of a Q-Learning agent playing FrozenLake-v1 .\n\n ## Usage" ]

[ 35, 33 ]

[ "TAGS\n#FrozenLake-v1-4x4-no_slippery #q-learning #reinforcement-learning #custom-implementation #model-index #region-us \n# Q-Learning Agent playing1 FrozenLake-v1\n This is a trained model of a Q-Learning agent playing FrozenLake-v1 .\n\n ## Usage" ]

[ "transformers", "phi3", "text-generation", "pruna-ai", "conversational", "custom_code", "base_model:microsoft/Phi-3-mini-128k-instruct", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.", "## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with hqq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.", "## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo microsoft/Phi-3-mini-128k-instruct installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.", "## Configurations\n\nThe configuration info are in 'smash_config.json'.", "## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model microsoft/Phi-3-mini-128k-instruct before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.", "## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ "TAGS\n#transformers #phi3 #text-generation #pruna-ai #conversational #custom_code #base_model-microsoft/Phi-3-mini-128k-instruct #autotrain_compatible #endpoints_compatible #region-us \n", "# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.", "## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with hqq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.", "## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo microsoft/Phi-3-mini-128k-instruct installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.", "## Configurations\n\nThe configuration info are in 'smash_config.json'.", "## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model microsoft/Phi-3-mini-128k-instruct before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.", "## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ 54, 83, 451, 72, 19, 67, 36 ]

[ "TAGS\n#transformers #phi3 #text-generation #pruna-ai #conversational #custom_code #base_model-microsoft/Phi-3-mini-128k-instruct #autotrain_compatible #endpoints_compatible #region-us \n# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with hqq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo microsoft/Phi-3-mini-128k-instruct installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.## Configurations\n\nThe configuration info are in 'smash_config.json'.## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model microsoft/Phi-3-mini-128k-instruct before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ "peft", "pytorch", "safetensors", "llama", "axolotl", "generated_from_trainer", "base_model:codellama/CodeLlama-7b-hf", "license:llama2", "8-bit", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 2\n* eval\\_batch\\_size: 2\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 8\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\n* lr\\_scheduler\\_warmup\\_steps: 10\n* num\\_epochs: 4", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.1.dev0\n* Transformers 4.40.0.dev0\n* Pytorch 2.1.2+cu118\n* Datasets 2.15.0\n* Tokenizers 0.15.0" ]

[ "TAGS\n#peft #pytorch #safetensors #llama #axolotl #generated_from_trainer #base_model-codellama/CodeLlama-7b-hf #license-llama2 #8-bit #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 2\n* eval\\_batch\\_size: 2\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 8\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\n* lr\\_scheduler\\_warmup\\_steps: 10\n* num\\_epochs: 4", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.1.dev0\n* Transformers 4.40.0.dev0\n* Pytorch 2.1.2+cu118\n* Datasets 2.15.0\n* Tokenizers 0.15.0" ]

[ 58, 142, 5, 58 ]

[ "TAGS\n#peft #pytorch #safetensors #llama #axolotl #generated_from_trainer #base_model-codellama/CodeLlama-7b-hf #license-llama2 #8-bit #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 2\n* eval\\_batch\\_size: 2\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 8\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\n* lr\\_scheduler\\_warmup\\_steps: 10\n* num\\_epochs: 4### Training results### Framework versions\n\n\n* PEFT 0.10.1.dev0\n* Transformers 4.40.0.dev0\n* Pytorch 2.1.2+cu118\n* Datasets 2.15.0\n* Tokenizers 0.15.0" ]

[ "transformers", "safetensors", "gemma", "text-generation", "pruna-ai", "base_model:google/codegemma-7b", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]

[]

[]

[ "# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.", "## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with awq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.", "## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo google/codegemma-7b installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.", "## Configurations\n\nThe configuration info are in 'smash_config.json'.", "## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model google/codegemma-7b before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.", "## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ "TAGS\n#transformers #safetensors #gemma #text-generation #pruna-ai #base_model-google/codegemma-7b #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n", "# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.", "## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with awq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.", "## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo google/codegemma-7b installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.", "## Configurations\n\nThe configuration info are in 'smash_config.json'.", "## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model google/codegemma-7b before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.", "## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ 55, 83, 451, 67, 19, 62, 36 ]

[ "TAGS\n#transformers #safetensors #gemma #text-generation #pruna-ai #base_model-google/codegemma-7b #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with awq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo google/codegemma-7b installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.## Configurations\n\nThe configuration info are in 'smash_config.json'.## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model google/codegemma-7b before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ "transformers", "phi3", "text-generation", "pruna-ai", "conversational", "custom_code", "base_model:microsoft/Phi-3-mini-4k-instruct", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.", "## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with hqq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.", "## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo microsoft/Phi-3-mini-4k-instruct installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.", "## Configurations\n\nThe configuration info are in 'smash_config.json'.", "## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model microsoft/Phi-3-mini-4k-instruct before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.", "## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ "TAGS\n#transformers #phi3 #text-generation #pruna-ai #conversational #custom_code #base_model-microsoft/Phi-3-mini-4k-instruct #autotrain_compatible #endpoints_compatible #region-us \n", "# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.", "## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with hqq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.", "## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo microsoft/Phi-3-mini-4k-instruct installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.", "## Configurations\n\nThe configuration info are in 'smash_config.json'.", "## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model microsoft/Phi-3-mini-4k-instruct before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.", "## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ 54, 83, 451, 72, 19, 67, 36 ]

[ "TAGS\n#transformers #phi3 #text-generation #pruna-ai #conversational #custom_code #base_model-microsoft/Phi-3-mini-4k-instruct #autotrain_compatible #endpoints_compatible #region-us \n# Simply make AI models cheaper, smaller, faster, and greener!\n\n- Give a thumbs up if you like this model!\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your *own* AI models here.\n- Read the documentations to know more here\n- Join Pruna AI community on Discord here to share feedback/suggestions or get help.## Results\n\n!image info\n\nFrequently Asked Questions\n- *How does the compression work?* The model is compressed with hqq.\n- *How does the model quality change?* The quality of the model output might vary compared to the base model.\n- *How is the model efficiency evaluated?* These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in 'model/smash_config.json' and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.\n- *What is the model format?* We use safetensors.\n- *What calibration data has been used?* If needed by the compression method, we used WikiText as the calibration data.\n- *What is the naming convention for Pruna Huggingface models?* We take the original model name and append \"turbo\", \"tiny\", or \"green\" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.\n- *How to compress my own models?* You can request premium access to more compression methods and tech support for your specific use-cases here.\n- *What are \"first\" metrics?* Results mentioning \"first\" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.\n- *What are \"Sync\" and \"Async\" metrics?* \"Sync\" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. \"Async\" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.## Setup\n\nYou can run the smashed model with these steps:\n\n0. Check requirements from the original repo microsoft/Phi-3-mini-4k-instruct installed. In particular, check python, cuda, and transformers versions.\n1. Make sure that you have installed quantization related packages.\n \n2. Load & run the model.## Configurations\n\nThe configuration info are in 'smash_config.json'.## Credits & License\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model microsoft/Phi-3-mini-4k-instruct before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.## Want to compress other models?\n\n- Contact us and tell us which model to compress next here.\n- Request access to easily compress your own AI models here." ]

[ "diffusers", "stable-diffusion-xl", "stable-diffusion-xl-diffusers", "diffusers-training", "text-to-image", "lora", "template:sd-lora", "base_model:stabilityai/stable-diffusion-xl-base-1.0", "license:openrail++", "region:us" ]

[]

[]

[ "# SDXL LoRA DreamBooth - aarashfeizi/jean-francois-godbout-batch2-repeats3-rank16-snr5.0\n\n<Gallery />", "## Model description", "### These are aarashfeizi/jean-francois-godbout-batch2-repeats3-rank16-snr5.0 LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.", "## Download model", "### Use it with UIs such as AUTOMATIC1111, Comfy UI, SD.Next, Invoke\n\n- LoRA: download '/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch2-repeats3-rank16-snr5.0.safetensors' here .\n - Place it on your 'models/Lora' folder.\n - On AUTOMATIC1111, load the LoRA by adding '<lora:/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch2-repeats3-rank16-snr5.0:1>' to your prompt. On ComfyUI just load it as a regular LoRA.\n- *Embeddings*: download '/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch2-repeats3-rank16-snr5.0_emb.safetensors' here .\n - Place it on it on your 'embeddings' folder\n - Use it by adding '/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch2-repeats3-rank16-snr5.0_emb' to your prompt. For example, 'A photo of /home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch2-repeats3-rank16-snr5.0_emb'\n (you need both the LoRA and the embeddings as they were trained together for this LoRA)", "## Use it with the diffusers library\n\n\n\nFor more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers", "## Trigger words\n\nTo trigger image generation of trained concept(or concepts) replace each concept identifier in you prompt with the new inserted tokens:\n\nto trigger concept 'TOK' → use '<s0><s1>' in your prompt", "## Details\nAll Files & versions.\n\nThe weights were trained using diffusers Advanced Dreambooth Training Script.\n\nLoRA for the text encoder was enabled. False.\n\nPivotal tuning was enabled: True.\n\nSpecial VAE used for training: madebyollin/sdxl-vae-fp16-fix." ]

[ "TAGS\n#diffusers #stable-diffusion-xl #stable-diffusion-xl-diffusers #diffusers-training #text-to-image #lora #template-sd-lora #base_model-stabilityai/stable-diffusion-xl-base-1.0 #license-openrail++ #region-us \n", "# SDXL LoRA DreamBooth - aarashfeizi/jean-francois-godbout-batch2-repeats3-rank16-snr5.0\n\n<Gallery />", "## Model description", "### These are aarashfeizi/jean-francois-godbout-batch2-repeats3-rank16-snr5.0 LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.", "## Download model", "### Use it with UIs such as AUTOMATIC1111, Comfy UI, SD.Next, Invoke\n\n- LoRA: download '/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch2-repeats3-rank16-snr5.0.safetensors' here .\n - Place it on your 'models/Lora' folder.\n - On AUTOMATIC1111, load the LoRA by adding '<lora:/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch2-repeats3-rank16-snr5.0:1>' to your prompt. On ComfyUI just load it as a regular LoRA.\n- *Embeddings*: download '/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch2-repeats3-rank16-snr5.0_emb.safetensors' here .\n - Place it on it on your 'embeddings' folder\n - Use it by adding '/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch2-repeats3-rank16-snr5.0_emb' to your prompt. For example, 'A photo of /home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch2-repeats3-rank16-snr5.0_emb'\n (you need both the LoRA and the embeddings as they were trained together for this LoRA)", "## Use it with the diffusers library\n\n\n\nFor more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers", "## Trigger words\n\nTo trigger image generation of trained concept(or concepts) replace each concept identifier in you prompt with the new inserted tokens:\n\nto trigger concept 'TOK' → use '<s0><s1>' in your prompt", "## Details\nAll Files & versions.\n\nThe weights were trained using diffusers Advanced Dreambooth Training Script.\n\nLoRA for the text encoder was enabled. False.\n\nPivotal tuning was enabled: True.\n\nSpecial VAE used for training: madebyollin/sdxl-vae-fp16-fix." ]

[ 70, 43, 4, 55, 4, 381, 34, 53, 67 ]

[ "TAGS\n#diffusers #stable-diffusion-xl #stable-diffusion-xl-diffusers #diffusers-training #text-to-image #lora #template-sd-lora #base_model-stabilityai/stable-diffusion-xl-base-1.0 #license-openrail++ #region-us \n# SDXL LoRA DreamBooth - aarashfeizi/jean-francois-godbout-batch2-repeats3-rank16-snr5.0\n\n<Gallery />## Model description### These are aarashfeizi/jean-francois-godbout-batch2-repeats3-rank16-snr5.0 LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.## Download model### Use it with UIs such as AUTOMATIC1111, Comfy UI, SD.Next, Invoke\n\n- LoRA: download '/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch2-repeats3-rank16-snr5.0.safetensors' here .\n - Place it on your 'models/Lora' folder.\n - On AUTOMATIC1111, load the LoRA by adding '<lora:/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch2-repeats3-rank16-snr5.0:1>' to your prompt. On ComfyUI just load it as a regular LoRA.\n- *Embeddings*: download '/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch2-repeats3-rank16-snr5.0_emb.safetensors' here .\n - Place it on it on your 'embeddings' folder\n - Use it by adding '/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch2-repeats3-rank16-snr5.0_emb' to your prompt. For example, 'A photo of /home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch2-repeats3-rank16-snr5.0_emb'\n (you need both the LoRA and the embeddings as they were trained together for this LoRA)## Use it with the diffusers library\n\n\n\nFor more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers## Trigger words\n\nTo trigger image generation of trained concept(or concepts) replace each concept identifier in you prompt with the new inserted tokens:\n\nto trigger concept 'TOK' → use '<s0><s1>' in your prompt## Details\nAll Files & versions.\n\nThe weights were trained using diffusers Advanced Dreambooth Training Script.\n\nLoRA for the text encoder was enabled. False.\n\nPivotal tuning was enabled: True.\n\nSpecial VAE used for training: madebyollin/sdxl-vae-fp16-fix." ]

[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]

[]

[]

[ "# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage" ]

[ "TAGS\n#Taxi-v3 #q-learning #reinforcement-learning #custom-implementation #model-index #region-us \n", "# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage" ]

[ 26, 31 ]

[ "TAGS\n#Taxi-v3 #q-learning #reinforcement-learning #custom-implementation #model-index #region-us \n# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage" ]

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

[ "1910.09700" ]

[]

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

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

[ 43, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

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

[ "arxiv:1910.09700", "region:us" ]

[ "1910.09700" ]

[]

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

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

[ 15, 28, 4, 50, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

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

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

[ "1910.09700" ]

[]

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

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

[ 41, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

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

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

[ "1910.09700" ]

[]

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

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

[ 41, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

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

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

[ "1910.09700" ]

[]

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

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

[ 41, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

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

[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]

[]

[]

[ "# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage\n\n model = load_from_hub(repo_id=\"ws11yrin/q-Taxi-v3\", filename=\"URL\")\n\n # Don't forget to check if you need to add additional attributes (is_slippery=False etc)\n env = URL(model[\"env_id\"])" ]

[ "TAGS\n#Taxi-v3 #q-learning #reinforcement-learning #custom-implementation #model-index #region-us \n", "# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage\n\n model = load_from_hub(repo_id=\"ws11yrin/q-Taxi-v3\", filename=\"URL\")\n\n # Don't forget to check if you need to add additional attributes (is_slippery=False etc)\n env = URL(model[\"env_id\"])" ]

[ 26, 105 ]

[ "TAGS\n#Taxi-v3 #q-learning #reinforcement-learning #custom-implementation #model-index #region-us \n# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage\n\n model = load_from_hub(repo_id=\"ws11yrin/q-Taxi-v3\", filename=\"URL\")\n\n # Don't forget to check if you need to add additional attributes (is_slippery=False etc)\n env = URL(model[\"env_id\"])" ]

[ "transformers", "safetensors", "mistral", "text-generation", "text-generation-inference", "unsloth", "trl", "en", "base_model:unsloth/mistral-7b-bnb-4bit", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "4-bit", "region:us" ]

[]

[ "en" ]

[ "# Uploaded model\n\n- Developed by: Madhura\n- License: apache-2.0\n- Finetuned from model : unsloth/mistral-7b-bnb-4bit\n\nThis mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #text-generation-inference #unsloth #trl #en #base_model-unsloth/mistral-7b-bnb-4bit #license-apache-2.0 #autotrain_compatible #endpoints_compatible #4-bit #region-us \n", "# Uploaded model\n\n- Developed by: Madhura\n- License: apache-2.0\n- Finetuned from model : unsloth/mistral-7b-bnb-4bit\n\nThis mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ 75, 78 ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #text-generation-inference #unsloth #trl #en #base_model-unsloth/mistral-7b-bnb-4bit #license-apache-2.0 #autotrain_compatible #endpoints_compatible #4-bit #region-us \n# Uploaded model\n\n- Developed by: Madhura\n- License: apache-2.0\n- Finetuned from model : unsloth/mistral-7b-bnb-4bit\n\nThis mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "diffusers", "stable-diffusion-xl", "stable-diffusion-xl-diffusers", "diffusers-training", "text-to-image", "lora", "template:sd-lora", "base_model:stabilityai/stable-diffusion-xl-base-1.0", "license:openrail++", "region:us" ]

[]

[]

[ "# SDXL LoRA DreamBooth - aarashfeizi/jean-francois-godbout-batch3-repeats3-rank8-snrNone\n\n<Gallery />", "## Model description", "### These are aarashfeizi/jean-francois-godbout-batch3-repeats3-rank8-snrNone LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.", "## Download model", "### Use it with UIs such as AUTOMATIC1111, Comfy UI, SD.Next, Invoke\n\n- LoRA: download '/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch3-repeats3-rank8-snrNone.safetensors' here .\n - Place it on your 'models/Lora' folder.\n - On AUTOMATIC1111, load the LoRA by adding '<lora:/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch3-repeats3-rank8-snrNone:1>' to your prompt. On ComfyUI just load it as a regular LoRA.\n- *Embeddings*: download '/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch3-repeats3-rank8-snrNone_emb.safetensors' here .\n - Place it on it on your 'embeddings' folder\n - Use it by adding '/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch3-repeats3-rank8-snrNone_emb' to your prompt. For example, 'A photo of /home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch3-repeats3-rank8-snrNone_emb'\n (you need both the LoRA and the embeddings as they were trained together for this LoRA)", "## Use it with the diffusers library\n\n\n\nFor more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers", "## Trigger words\n\nTo trigger image generation of trained concept(or concepts) replace each concept identifier in you prompt with the new inserted tokens:\n\nto trigger concept 'TOK' → use '<s0><s1>' in your prompt", "## Details\nAll Files & versions.\n\nThe weights were trained using diffusers Advanced Dreambooth Training Script.\n\nLoRA for the text encoder was enabled. False.\n\nPivotal tuning was enabled: True.\n\nSpecial VAE used for training: madebyollin/sdxl-vae-fp16-fix." ]

[ "TAGS\n#diffusers #stable-diffusion-xl #stable-diffusion-xl-diffusers #diffusers-training #text-to-image #lora #template-sd-lora #base_model-stabilityai/stable-diffusion-xl-base-1.0 #license-openrail++ #region-us \n", "# SDXL LoRA DreamBooth - aarashfeizi/jean-francois-godbout-batch3-repeats3-rank8-snrNone\n\n<Gallery />", "## Model description", "### These are aarashfeizi/jean-francois-godbout-batch3-repeats3-rank8-snrNone LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.", "## Download model", "### Use it with UIs such as AUTOMATIC1111, Comfy UI, SD.Next, Invoke\n\n- LoRA: download '/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch3-repeats3-rank8-snrNone.safetensors' here .\n - Place it on your 'models/Lora' folder.\n - On AUTOMATIC1111, load the LoRA by adding '<lora:/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch3-repeats3-rank8-snrNone:1>' to your prompt. On ComfyUI just load it as a regular LoRA.\n- *Embeddings*: download '/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch3-repeats3-rank8-snrNone_emb.safetensors' here .\n - Place it on it on your 'embeddings' folder\n - Use it by adding '/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch3-repeats3-rank8-snrNone_emb' to your prompt. For example, 'A photo of /home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch3-repeats3-rank8-snrNone_emb'\n (you need both the LoRA and the embeddings as they were trained together for this LoRA)", "## Use it with the diffusers library\n\n\n\nFor more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers", "## Trigger words\n\nTo trigger image generation of trained concept(or concepts) replace each concept identifier in you prompt with the new inserted tokens:\n\nto trigger concept 'TOK' → use '<s0><s1>' in your prompt", "## Details\nAll Files & versions.\n\nThe weights were trained using diffusers Advanced Dreambooth Training Script.\n\nLoRA for the text encoder was enabled. False.\n\nPivotal tuning was enabled: True.\n\nSpecial VAE used for training: madebyollin/sdxl-vae-fp16-fix." ]

[ 70, 42, 4, 54, 4, 376, 34, 53, 67 ]

[ "TAGS\n#diffusers #stable-diffusion-xl #stable-diffusion-xl-diffusers #diffusers-training #text-to-image #lora #template-sd-lora #base_model-stabilityai/stable-diffusion-xl-base-1.0 #license-openrail++ #region-us \n# SDXL LoRA DreamBooth - aarashfeizi/jean-francois-godbout-batch3-repeats3-rank8-snrNone\n\n<Gallery />## Model description### These are aarashfeizi/jean-francois-godbout-batch3-repeats3-rank8-snrNone LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.## Download model### Use it with UIs such as AUTOMATIC1111, Comfy UI, SD.Next, Invoke\n\n- LoRA: download '/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch3-repeats3-rank8-snrNone.safetensors' here .\n - Place it on your 'models/Lora' folder.\n - On AUTOMATIC1111, load the LoRA by adding '<lora:/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch3-repeats3-rank8-snrNone:1>' to your prompt. On ComfyUI just load it as a regular LoRA.\n- *Embeddings*: download '/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch3-repeats3-rank8-snrNone_emb.safetensors' here .\n - Place it on it on your 'embeddings' folder\n - Use it by adding '/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch3-repeats3-rank8-snrNone_emb' to your prompt. For example, 'A photo of /home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch3-repeats3-rank8-snrNone_emb'\n (you need both the LoRA and the embeddings as they were trained together for this LoRA)## Use it with the diffusers library\n\n\n\nFor more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers## Trigger words\n\nTo trigger image generation of trained concept(or concepts) replace each concept identifier in you prompt with the new inserted tokens:\n\nto trigger concept 'TOK' → use '<s0><s1>' in your prompt## Details\nAll Files & versions.\n\nThe weights were trained using diffusers Advanced Dreambooth Training Script.\n\nLoRA for the text encoder was enabled. False.\n\nPivotal tuning was enabled: True.\n\nSpecial VAE used for training: madebyollin/sdxl-vae-fp16-fix." ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:google-t5/t5-small", "license:apache-2.0", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 2\n* eval\\_batch\\_size: 16\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 8\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 1\n* training\\_steps: 250", "### Training results", "### Framework versions\n\n\n* PEFT 0.8.2\n* Transformers 4.38.1\n* Pytorch 1.13.1\n* Datasets 2.17.0\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-google-t5/t5-small #license-apache-2.0 #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 2\n* eval\\_batch\\_size: 16\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 8\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 1\n* training\\_steps: 250", "### Training results", "### Framework versions\n\n\n* PEFT 0.8.2\n* Transformers 4.38.1\n* Pytorch 1.13.1\n* Datasets 2.17.0\n* Tokenizers 0.15.2" ]

[ 40, 138, 5, 48 ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-google-t5/t5-small #license-apache-2.0 #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 2\n* eval\\_batch\\_size: 16\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 8\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 1\n* training\\_steps: 250### Training results### Framework versions\n\n\n* PEFT 0.8.2\n* Transformers 4.38.1\n* Pytorch 1.13.1\n* Datasets 2.17.0\n* Tokenizers 0.15.2" ]

[ "stable-baselines3", "SpaceInvadersNoFrameskip-v4", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]

[]

[]

[ "# DQN Agent playing SpaceInvadersNoFrameskip-v4\nThis is a trained model of a DQN agent playing SpaceInvadersNoFrameskip-v4\nusing the stable-baselines3 library\nand the RL Zoo.\n\nThe RL Zoo is a training framework for Stable Baselines3\nreinforcement learning agents,\nwith hyperparameter optimization and pre-trained agents included.", "## Usage (with SB3 RL Zoo)\n\nRL Zoo: URL\nSB3: URL\nSB3 Contrib: URL\n\nInstall the RL Zoo (with SB3 and SB3-Contrib):\n\n\n\n\nIf you installed the RL Zoo3 via pip ('pip install rl_zoo3'), from anywhere you can do:", "## Training (with the RL Zoo)", "## Hyperparameters", "# Environment Arguments" ]

[ "TAGS\n#stable-baselines3 #SpaceInvadersNoFrameskip-v4 #deep-reinforcement-learning #reinforcement-learning #model-index #region-us \n", "# DQN Agent playing SpaceInvadersNoFrameskip-v4\nThis is a trained model of a DQN agent playing SpaceInvadersNoFrameskip-v4\nusing the stable-baselines3 library\nand the RL Zoo.\n\nThe RL Zoo is a training framework for Stable Baselines3\nreinforcement learning agents,\nwith hyperparameter optimization and pre-trained agents included.", "## Usage (with SB3 RL Zoo)\n\nRL Zoo: URL\nSB3: URL\nSB3 Contrib: URL\n\nInstall the RL Zoo (with SB3 and SB3-Contrib):\n\n\n\n\nIf you installed the RL Zoo3 via pip ('pip install rl_zoo3'), from anywhere you can do:", "## Training (with the RL Zoo)", "## Hyperparameters", "# Environment Arguments" ]

[ 37, 81, 76, 10, 6, 3 ]

[ "TAGS\n#stable-baselines3 #SpaceInvadersNoFrameskip-v4 #deep-reinforcement-learning #reinforcement-learning #model-index #region-us \n# DQN Agent playing SpaceInvadersNoFrameskip-v4\nThis is a trained model of a DQN agent playing SpaceInvadersNoFrameskip-v4\nusing the stable-baselines3 library\nand the RL Zoo.\n\nThe RL Zoo is a training framework for Stable Baselines3\nreinforcement learning agents,\nwith hyperparameter optimization and pre-trained agents included.## Usage (with SB3 RL Zoo)\n\nRL Zoo: URL\nSB3: URL\nSB3 Contrib: URL\n\nInstall the RL Zoo (with SB3 and SB3-Contrib):\n\n\n\n\nIf you installed the RL Zoo3 via pip ('pip install rl_zoo3'), from anywhere you can do:## Training (with the RL Zoo)## Hyperparameters# Environment Arguments" ]

[ "transformers", "safetensors", "mistral", "text-generation", "mergekit", "merge", "arxiv:2306.01708", "base_model:mistralai/Mistral-7B-v0.1", "base_model:PrunaAI/WizardLM-WizardMath-7B-V1.0-bnb-4bit-smashed", "base_model:codellama/CodeLlama-7b-Instruct-hf", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "2306.01708" ]

[]

[ "# output_folder merge\n\nThis is a merge of pre-trained language models created using mergekit.", "## Merge Details", "### Merge Method\n\nThis model was merged using the TIES merge method using mistralai/Mistral-7B-v0.1 as a base.", "### Models Merged\n\nThe following models were included in the merge:\n* PrunaAI/WizardLM-WizardMath-7B-V1.0-bnb-4bit-smashed\n* codellama/CodeLlama-7b-Instruct-hf", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #mergekit #merge #arxiv-2306.01708 #base_model-mistralai/Mistral-7B-v0.1 #base_model-PrunaAI/WizardLM-WizardMath-7B-V1.0-bnb-4bit-smashed #base_model-codellama/CodeLlama-7b-Instruct-hf #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# output_folder merge\n\nThis is a merge of pre-trained language models created using mergekit.", "## Merge Details", "### Merge Method\n\nThis model was merged using the TIES merge method using mistralai/Mistral-7B-v0.1 as a base.", "### Models Merged\n\nThe following models were included in the merge:\n* PrunaAI/WizardLM-WizardMath-7B-V1.0-bnb-4bit-smashed\n* codellama/CodeLlama-7b-Instruct-hf", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ 121, 20, 4, 33, 58, 16 ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #mergekit #merge #arxiv-2306.01708 #base_model-mistralai/Mistral-7B-v0.1 #base_model-PrunaAI/WizardLM-WizardMath-7B-V1.0-bnb-4bit-smashed #base_model-codellama/CodeLlama-7b-Instruct-hf #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# output_folder merge\n\nThis is a merge of pre-trained language models created using mergekit.## Merge Details### Merge Method\n\nThis model was merged using the TIES merge method using mistralai/Mistral-7B-v0.1 as a base.### Models Merged\n\nThe following models were included in the merge:\n* PrunaAI/WizardLM-WizardMath-7B-V1.0-bnb-4bit-smashed\n* codellama/CodeLlama-7b-Instruct-hf### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

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

[ "1910.09700" ]

[]

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

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

[ 44, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

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

[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]

[]

[]

[ "# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage" ]

[ "TAGS\n#Taxi-v3 #q-learning #reinforcement-learning #custom-implementation #model-index #region-us \n", "# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage" ]

[ 26, 31 ]

[ "TAGS\n#Taxi-v3 #q-learning #reinforcement-learning #custom-implementation #model-index #region-us \n# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage" ]

[ "transformers", "tensorboard", "safetensors", "llama", "text-generation", "trl", "sft", "generated_from_trainer", "conversational", "dataset:generator", "base_model:meta-llama/Meta-Llama-3-8B-Instruct", "license:other", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# Meta-Llama-3-8B-Instruct_fictional_arc_Chinese_v2\n\nThis model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the generator dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 1\n- eval_batch_size: 2\n- seed: 42\n- gradient_accumulation_steps: 16\n- total_train_batch_size: 16\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 36", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #tensorboard #safetensors #llama #text-generation #trl #sft #generated_from_trainer #conversational #dataset-generator #base_model-meta-llama/Meta-Llama-3-8B-Instruct #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Meta-Llama-3-8B-Instruct_fictional_arc_Chinese_v2\n\nThis model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the generator dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 1\n- eval_batch_size: 2\n- seed: 42\n- gradient_accumulation_steps: 16\n- total_train_batch_size: 16\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 36", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ 83, 54, 7, 9, 9, 4, 111, 5, 40 ]

[ "TAGS\n#transformers #tensorboard #safetensors #llama #text-generation #trl #sft #generated_from_trainer #conversational #dataset-generator #base_model-meta-llama/Meta-Llama-3-8B-Instruct #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# Meta-Llama-3-8B-Instruct_fictional_arc_Chinese_v2\n\nThis model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the generator dataset.## Model description\n\nMore information needed## Intended uses & limitations\n\nMore information needed## Training and evaluation data\n\nMore information needed## Training procedure### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 1\n- eval_batch_size: 2\n- seed: 42\n- gradient_accumulation_steps: 16\n- total_train_batch_size: 16\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 36### Training results### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "transformers", "tensorboard", "safetensors", "gpt2", "text-generation", "generated_from_trainer", "base_model:MikeMpapa/4_bar_lmd_clean_custom_epochs10", "license:mit", "autotrain_compatible", "endpoints_compatible", "has_space", "text-generation-inference", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.005\n* train\\_batch\\_size: 48\n* eval\\_batch\\_size: 32\n* seed: 1\n* gradient\\_accumulation\\_steps: 2\n* total\\_train\\_batch\\_size: 96\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\n* lr\\_scheduler\\_warmup\\_ratio: 0.01\n* num\\_epochs: 81", "### Training results", "### Framework versions\n\n\n* Transformers 4.36.0\n* Pytorch 2.1.0\n* Datasets 2.15.0\n* Tokenizers 0.15.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #gpt2 #text-generation #generated_from_trainer #base_model-MikeMpapa/4_bar_lmd_clean_custom_epochs10 #license-mit #autotrain_compatible #endpoints_compatible #has_space #text-generation-inference #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.005\n* train\\_batch\\_size: 48\n* eval\\_batch\\_size: 32\n* seed: 1\n* gradient\\_accumulation\\_steps: 2\n* total\\_train\\_batch\\_size: 96\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\n* lr\\_scheduler\\_warmup\\_ratio: 0.01\n* num\\_epochs: 81", "### Training results", "### Framework versions\n\n\n* Transformers 4.36.0\n* Pytorch 2.1.0\n* Datasets 2.15.0\n* Tokenizers 0.15.1" ]

[ 75, 144, 5, 40 ]

[ "TAGS\n#transformers #tensorboard #safetensors #gpt2 #text-generation #generated_from_trainer #base_model-MikeMpapa/4_bar_lmd_clean_custom_epochs10 #license-mit #autotrain_compatible #endpoints_compatible #has_space #text-generation-inference #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.005\n* train\\_batch\\_size: 48\n* eval\\_batch\\_size: 32\n* seed: 1\n* gradient\\_accumulation\\_steps: 2\n* total\\_train\\_batch\\_size: 96\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\n* lr\\_scheduler\\_warmup\\_ratio: 0.01\n* num\\_epochs: 81### Training results### Framework versions\n\n\n* Transformers 4.36.0\n* Pytorch 2.1.0\n* Datasets 2.15.0\n* Tokenizers 0.15.1" ]

[ "transformers", "safetensors", "xlm-roberta", "feature-extraction", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]

[ "1910.09700" ]

[]

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

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

[ 35, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

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

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

[ "1910.09700" ]

[]

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

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

[ 41, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

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

[ "transformers", "safetensors", "mistral", "text-generation", "mergekit", "merge", "arxiv:2306.01708", "base_model:mistralai/Mistral-7B-v0.1", "base_model:PrunaAI/WizardLM-WizardMath-7B-V1.0-bnb-4bit-smashed", "base_model:codellama/CodeLlama-7b-Instruct-hf", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "2306.01708" ]

[]

[ "# output_folder merge\n\nThis is a merge of pre-trained language models created using mergekit.", "## Merge Details", "### Merge Method\n\nThis model was merged using the TIES merge method using mistralai/Mistral-7B-v0.1 as a base.", "### Models Merged\n\nThe following models were included in the merge:\n* PrunaAI/WizardLM-WizardMath-7B-V1.0-bnb-4bit-smashed\n* codellama/CodeLlama-7b-Instruct-hf", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #mergekit #merge #arxiv-2306.01708 #base_model-mistralai/Mistral-7B-v0.1 #base_model-PrunaAI/WizardLM-WizardMath-7B-V1.0-bnb-4bit-smashed #base_model-codellama/CodeLlama-7b-Instruct-hf #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# output_folder merge\n\nThis is a merge of pre-trained language models created using mergekit.", "## Merge Details", "### Merge Method\n\nThis model was merged using the TIES merge method using mistralai/Mistral-7B-v0.1 as a base.", "### Models Merged\n\nThe following models were included in the merge:\n* PrunaAI/WizardLM-WizardMath-7B-V1.0-bnb-4bit-smashed\n* codellama/CodeLlama-7b-Instruct-hf", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ 121, 20, 4, 33, 58, 16 ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #mergekit #merge #arxiv-2306.01708 #base_model-mistralai/Mistral-7B-v0.1 #base_model-PrunaAI/WizardLM-WizardMath-7B-V1.0-bnb-4bit-smashed #base_model-codellama/CodeLlama-7b-Instruct-hf #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# output_folder merge\n\nThis is a merge of pre-trained language models created using mergekit.## Merge Details### Merge Method\n\nThis model was merged using the TIES merge method using mistralai/Mistral-7B-v0.1 as a base.### Models Merged\n\nThe following models were included in the merge:\n* PrunaAI/WizardLM-WizardMath-7B-V1.0-bnb-4bit-smashed\n* codellama/CodeLlama-7b-Instruct-hf### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "gguf", "llama-3", "llama", "Mixtral", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "distillation", "GGUF", "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" ]

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

[ "en" ]

[ "# Llama3-OpenBioLLM-8B-GGUF\n- Original model: Llama3-OpenBioLLM-8B", "## Description\n\nThis repo contains GGUF format model files for Llama3-OpenBioLLM-8B.", "### About GGUF\nGGUF is a new format introduced by the URL team on August 21st 2023. It is a replacement for GGML, which is no longer supported by URL.\nHere is an incomplete list of clients and libraries that are known to support GGUF:\n* URL. This is the source project for GGUF, providing both a Command Line Interface (CLI) and a server option.\n* text-generation-webui, Known as the most widely used web UI, this project boasts numerous features and powerful extensions, and supports GPU acceleration.\n* Ollama Ollama is a lightweight and extensible framework designed for building and running language models locally. It features a simple API for creating, managing, and executing models, along with a library of pre-built models for use in various applications​\n* KoboldCpp, A comprehensive web UI offering GPU acceleration across all platforms and architectures, particularly renowned for storytelling.\n* GPT4All, This is a free and open source GUI that runs locally, supporting Windows, Linux, and macOS with full GPU acceleration.\n* LM Studio An intuitive and powerful local GUI for Windows and macOS (Silicon), featuring GPU acceleration.\n* LoLLMS Web UI. A notable web UI with a variety of unique features, including a comprehensive model library for easy model selection.\n* URL, An attractive, user-friendly character-based chat GUI for Windows and macOS (both Silicon and Intel), also offering GPU acceleration.\n* llama-cpp-python, A Python library equipped with GPU acceleration, LangChain support, and an OpenAI-compatible API server.\n* candle, A Rust-based ML framework focusing on performance, including GPU support, and designed for ease of use.\n* ctransformers, A Python library featuring GPU acceleration, LangChain support, and an OpenAI-compatible AI server.\n* localGPT An open-source initiative enabling private conversations with documents.", "## Explanation of quantisation methods\n<details>\n <summary>Click to see details</summary>\nThe new methods available are:\n\n* GGML_TYPE_Q2_K - \"type-1\" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)\n* GGML_TYPE_Q3_K - \"type-0\" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.\n* GGML_TYPE_Q4_K - \"type-1\" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.\n* GGML_TYPE_Q5_K - \"type-1\" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw\n* GGML_TYPE_Q6_K - \"type-0\" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw.\n</details>", "## How to download GGUF files\n\nNote for manual downloaders: You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single folder.\n\nThe following clients/libraries will automatically download models for you, providing a list of available models to choose from:\n\n* LM Studio\n* LoLLMS Web UI\n* URL", "### In 'text-generation-webui'\n\nUnder Download Model, you can enter the model repo: LiteLLMs/Llama3-OpenBioLLM-8B-GGUF and below it, a specific filename to download, such as: Q4_0/Q4_0-URL.\n\nThen click Download.", "### On the command line, including multiple files at once\n\nI recommend using the 'huggingface-hub' Python library:\n\n\n\nThen you can download any individual model file to the current directory, at high speed, with a command like this:\n\n\n\n<details>\n <summary>More advanced huggingface-cli download usage (click to read)</summary>\n\nYou can also download multiple files at once with a pattern:\n\n\n\nFor more documentation on downloading with 'huggingface-cli', please see: HF -> Hub Python Library -> Download files -> Download from the CLI.\n\nTo accelerate downloads on fast connections (1Gbit/s or higher), install 'hf_transfer':\n\n\n\nAnd set environment variable 'HF_HUB_ENABLE_HF_TRANSFER' to '1':\n\n\n\nWindows Command Line users: You can set the environment variable by running 'set HF_HUB_ENABLE_HF_TRANSFER=1' before the download command.\n</details>", "## Example 'URL' command\n\nMake sure you are using 'URL' from commit d0cee0d or later.\n\n\n\nChange '-ngl 32' to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.\n\nChange '-c 8192' to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by URL automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.\n\nIf you want to have a chat-style conversation, replace the '-p <PROMPT>' argument with '-i -ins'\n\nFor other parameters and how to use them, please refer to the URL documentation", "## How to run in 'text-generation-webui'\n\nFurther instructions can be found in the text-generation-webui documentation, here: text-generation-webui/docs/04 ‐ Model URL.", "## How to run from Python code\n\nYou can use GGUF models from Python using the llama-cpp-python or ctransformers libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.", "### How to load this model in Python code, using llama-cpp-python\n\nFor full documentation, please see: llama-cpp-python docs.", "#### First install the package\n\nRun one of the following commands, according to your system:", "#### Simple llama-cpp-python example code", "## How to use with LangChain\n\nHere are guides on using llama-cpp-python and ctransformers with LangChain:\n\n* LangChain + llama-cpp-python\n* LangChain + ctransformers", "# Original model card: Llama3-OpenBioLLM-8B\n\n\n\n<div align=\"center\">\n<img width=\"260px\" src=\"URL\n\n\n!image/png\n\n\n\n\n<div align=\"center\">\n\n <h1>Advancing Open-source Large Language Models in Medical Domain</h1>\n</div>\n\n<p align=\"center\" style=\"margin-top: 0px;\">\n <a href=\"URL\n <img src=\"URL alt=\"OpenChat Logo\" style=\"width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 10px; margin-top: 0px; margin-bottom: 0px;\"/>\n <span class=\"link-text\" style=\" margin-right: 5px;\">Online Demo</span>\n </a> |\n <a href=\"URL\n <img src=\"URL alt=\"GitHub Logo\" style=\"width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;\"/>\n <span class=\"link-text\" style=\" margin-right: 5px;\">GitHub</span>\n </a> |\n <a href=\"#\">\n <img src=\"URL alt=\"ArXiv Logo\" style=\"width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;\"/>\n <span class=\"link-text\" style=\"margin-right: 5px;\">Paper</span>\n </a> |\n <a href=\"URL\n <img src=\"URL alt=\"Discord Logo\" style=\"width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;\"/>\n <span class=\"link-text\">Discord</span>\n </a>\n</p>\n\n!image/jpeg\n\nIntroducing OpenBioLLM-8B: A State-of-the-Art Open Source Biomedical Large Language Model\n\n\nOpenBioLLM-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.\n\n 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.\n\n 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.\n\n Advanced Training Techniques: OpenBioLLM-8B builds upon the powerful foundations of the Meta-Llama-3-8B and 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:\n\n<div align=\"center\">\n<img width=\"1200px\" src=\"URL\n</div>\n\n- Policy Optimization: Direct Preference Optimization: Your Language Model is Secretly a Reward Model (DPO)\n- Ranking Dataset: berkeley-nest/Nectar\n- Fine-tuning dataset: Custom Medical Instruct dataset (We plan to release a sample training dataset in our upcoming paper; please stay updated)\n\nThis combination of cutting-edge techniques enables OpenBioLLM-8B to align with key capabilities and preferences for biomedical applications.\n\n️ Release Details:\n\n- Model Size: 8 billion parameters\n- Quantization: Optimized quantized versions available Here\n- Language(s) (NLP): en\n- Developed By: Ankit Pal (Aaditya Ura) from Saama AI Labs\n- License: Meta-Llama License\n- Fine-tuned from models: meta-llama/Meta-Llama-3-8B\n- Resources for more information:\n - Paper: Coming soon\n\nThe model can be fine-tuned for more specialized tasks and datasets as needed.\n\nOpenBioLLM-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.\n\nWe are excited to share OpenBioLLM-8B with researchers and developers around the world.", "### Use with transformers\n\nImportant: 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.\n\nSee the snippet below for usage with Transformers:", "## Training procedure", "### Training hyperparameters\n\n<details>\n <summary>Click to see details</summary>\n\n- learning_rate: 0.0002\n- lr_scheduler: cosine\n- train_batch_size: 12\n- eval_batch_size: 8\n- GPU: H100 80GB SXM5\n- num_devices: 1\n- optimizer: adamw_bnb_8bit\n- lr_scheduler_warmup_steps: 100\n- num_epochs: 4\n</details>", "### Peft hyperparameters\n\n<details>\n <summary>Click to see details</summary>\n\n- adapter: qlora\n- lora_r: 128\n- lora_alpha: 256\n- lora_dropout: 0.05\n- lora_target_linear: true\n\n-lora_target_modules:\n- q_proj\n- v_proj\n- k_proj\n- o_proj\n- gate_proj\n- down_proj\n- up_proj\n</details>", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.1\n- Axolotl\n- Lm harness for evaluation", "# Benchmark Results\n\n 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.\n\n 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.\n\n| | Clinical KG | Medical Genetics | Anatomy | Pro Medicine | College Biology | College Medicine | MedQA 4 opts | PubMedQA | MedMCQA | Avg |\n| | - | | - | |\n| OpenBioLLM-70B | 92.93 | 93.197 | 83.904 | 93.75 | 93.827 | 85.749 | 78.162 | 78.97 | 74.014 | 86.05588 |\n| Med-PaLM-2 (5-shot) | 88.3 | 90 | 77.8 | 95.2 | 94.4 | 80.9 | 79.7 | 79.2 | 71.3 | 84.08 |\n| GPT-4 | 86.04 | 91 | 80 | 93.01 | 95.14 | 76.88 | 78.87 | 75.2 | 69.52 | 82.85 |\n| 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 |\n| OpenBioLLM-8B | 76.101 | 86.1 | 69.829 | 78.21 | 84.213 | 68.042 | 58.993 | 74.12 | 56.913 | 72.502 |\n| Gemini-1.0 | 76.7 | 75.8 | 66.7 | 77.7 | 88 | 69.2 | 58 | 70.7 | 54.3 | 70.79 |\n| GPT-3.5 Turbo 1106 | 74.71 | 74 | 72.79 | 72.79 | 72.91 | 64.73 | 57.71 | 72.66 | 53.79 | 66 |\n| Meditron-70B | 66.79 | 69 | 53.33 | 71.69 | 76.38 | 63 | 57.1 | 76.6 | 46.85 | 64.52 |\n| gemma-7b | 69.81 | 70 | 59.26 | 66.18 | 79.86 | 60.12 | 47.21 | 76.2 | 48.96 | 64.18 |\n| Mistral-7B-v0.1 | 68.68 | 71 | 55.56 | 68.38 | 68.06 | 59.54 | 50.82 | 75.4 | 48.2 | 62.85 |\n| Apollo-7B | 62.26 | 72 | 61.48 | 69.12 | 70.83 | 55.49 | 55.22 | 39.8 | 53.77 | 60 |\n| MedAlpaca-7b | 57.36 | 69 | 57.04 | 67.28 | 65.28 | 54.34 | 41.71 | 72.8 | 37.51 | 58.03 |\n| BioMistral-7B | 59.9 | 64 | 56.5 | 60.4 | 59 | 54.7 | 50.6 | 77.5 | 48.1 | 57.3 |\n| AlpaCare-llama2-7b | 49.81 | 49 | 45.92 | 33.82 | 50 | 43.35 | 29.77 | 72.2 | 34.42 | 45.36 |\n| ClinicalGPT | 30.56 | 27 | 30.37 | 19.48 | 25 | 24.27 | 26.08 | 63.8 | 28.18 | 30.52 |\n\n<div align=\"center\">\n<img width=\"1600px\" src=\"URL\n</div>", "## Detailed Medical Subjectwise accuracy\n\n\n!image/png", "# Use Cases & Examples\n\n Below results are from the quantized version of OpenBioLLM-70B", "# Summarize Clinical Notes\n\nOpenBioLLM-70B can efficiently analyze and summarize complex clinical notes, EHR data, and discharge summaries, extracting key information and generating concise, structured summaries\n\n\n!image/png", "# Answer Medical Questions\n\nOpenBioLLM-70B can provide answers to a wide range of medical questions.\n\n\n!image/png\n!image/png\n\n<details>\n <summary>Click to see details</summary>\n\n\n!image/png\n!image/png\n!image/png\n\n</details>", "# Clinical Entity Recognition\n\nOpenBioLLM-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.\n\n\n!image/png\n!image/png\n!image/png", "# Biomarkers Extraction\n\n\n!image/png", "# Classification\n\nOpenBioLLM-70B can perform various biomedical classification tasks, such as disease prediction, sentiment analysis, medical document categorization\n\n!image/png", "# De-Identification\n\nOpenBioLLM-70B can detect and remove personally identifiable information (PII) from medical records, ensuring patient privacy and compliance with data protection regulations like HIPAA.\n\n!image/png\n\n\n\nAdvisory Notice!\n\nWhile 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.\n\nTherefore, 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.\nOpenBioLLM-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.\n\nAppropriately adapting and validating OpenBioLLM-70B & 8B for specific medical use cases would require significant additional work, potentially including:\n\n- Thorough testing and evaluation in relevant clinical scenarios\n- Alignment with evidence-based guidelines and best practices\n- Mitigation of potential biases and failure modes\n- Integration with human oversight and interpretation\n- Compliance with regulatory and ethical standards\n\nAlways consult a qualified healthcare provider for personal medical needs.\n\n\n\nIf you find OpenBioLLM-70B & 8B useful in your work, please cite the model as follows:\n\n\n\nThe accompanying paper is currently in progress and will be released soon.\n\n<div align=\"center\">\n<h2> Contact </h2>\n</div>\n\nWe look forward to hearing you and collaborating on this exciting project!\n\nContributors:\n- Ankit Pal (Aaditya Ura) [aadityaura at gmail dot com]\n- Saama AI Labs\n- 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\n\nWe thank the Meta Team for their amazing models!\n\n\nResult sources\n\n- [1] GPT-4 [Capabilities of GPT-4 on Medical Challenge Problems] (URL\n- [2] Med-PaLM-1 Large Language Models Encode Clinical Knowledge\n- [3] Med-PaLM-2 Towards Expert-Level Medical Question Answering with Large Language Models\n- [4] Gemini-1.0 Gemini Goes to Med School" ]

[ "TAGS\n#gguf #llama-3 #llama #Mixtral #instruct #finetune #chatml #DPO #RLHF #gpt4 #distillation #GGUF #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 \n", "# Llama3-OpenBioLLM-8B-GGUF\n- Original model: Llama3-OpenBioLLM-8B", "## Description\n\nThis repo contains GGUF format model files for Llama3-OpenBioLLM-8B.", "### About GGUF\nGGUF is a new format introduced by the URL team on August 21st 2023. It is a replacement for GGML, which is no longer supported by URL.\nHere is an incomplete list of clients and libraries that are known to support GGUF:\n* URL. This is the source project for GGUF, providing both a Command Line Interface (CLI) and a server option.\n* text-generation-webui, Known as the most widely used web UI, this project boasts numerous features and powerful extensions, and supports GPU acceleration.\n* Ollama Ollama is a lightweight and extensible framework designed for building and running language models locally. It features a simple API for creating, managing, and executing models, along with a library of pre-built models for use in various applications​\n* KoboldCpp, A comprehensive web UI offering GPU acceleration across all platforms and architectures, particularly renowned for storytelling.\n* GPT4All, This is a free and open source GUI that runs locally, supporting Windows, Linux, and macOS with full GPU acceleration.\n* LM Studio An intuitive and powerful local GUI for Windows and macOS (Silicon), featuring GPU acceleration.\n* LoLLMS Web UI. A notable web UI with a variety of unique features, including a comprehensive model library for easy model selection.\n* URL, An attractive, user-friendly character-based chat GUI for Windows and macOS (both Silicon and Intel), also offering GPU acceleration.\n* llama-cpp-python, A Python library equipped with GPU acceleration, LangChain support, and an OpenAI-compatible API server.\n* candle, A Rust-based ML framework focusing on performance, including GPU support, and designed for ease of use.\n* ctransformers, A Python library featuring GPU acceleration, LangChain support, and an OpenAI-compatible AI server.\n* localGPT An open-source initiative enabling private conversations with documents.", "## Explanation of quantisation methods\n<details>\n <summary>Click to see details</summary>\nThe new methods available are:\n\n* GGML_TYPE_Q2_K - \"type-1\" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)\n* GGML_TYPE_Q3_K - \"type-0\" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.\n* GGML_TYPE_Q4_K - \"type-1\" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.\n* GGML_TYPE_Q5_K - \"type-1\" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw\n* GGML_TYPE_Q6_K - \"type-0\" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw.\n</details>", "## How to download GGUF files\n\nNote for manual downloaders: You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single folder.\n\nThe following clients/libraries will automatically download models for you, providing a list of available models to choose from:\n\n* LM Studio\n* LoLLMS Web UI\n* URL", "### In 'text-generation-webui'\n\nUnder Download Model, you can enter the model repo: LiteLLMs/Llama3-OpenBioLLM-8B-GGUF and below it, a specific filename to download, such as: Q4_0/Q4_0-URL.\n\nThen click Download.", "### On the command line, including multiple files at once\n\nI recommend using the 'huggingface-hub' Python library:\n\n\n\nThen you can download any individual model file to the current directory, at high speed, with a command like this:\n\n\n\n<details>\n <summary>More advanced huggingface-cli download usage (click to read)</summary>\n\nYou can also download multiple files at once with a pattern:\n\n\n\nFor more documentation on downloading with 'huggingface-cli', please see: HF -> Hub Python Library -> Download files -> Download from the CLI.\n\nTo accelerate downloads on fast connections (1Gbit/s or higher), install 'hf_transfer':\n\n\n\nAnd set environment variable 'HF_HUB_ENABLE_HF_TRANSFER' to '1':\n\n\n\nWindows Command Line users: You can set the environment variable by running 'set HF_HUB_ENABLE_HF_TRANSFER=1' before the download command.\n</details>", "## Example 'URL' command\n\nMake sure you are using 'URL' from commit d0cee0d or later.\n\n\n\nChange '-ngl 32' to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.\n\nChange '-c 8192' to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by URL automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.\n\nIf you want to have a chat-style conversation, replace the '-p <PROMPT>' argument with '-i -ins'\n\nFor other parameters and how to use them, please refer to the URL documentation", "## How to run in 'text-generation-webui'\n\nFurther instructions can be found in the text-generation-webui documentation, here: text-generation-webui/docs/04 ‐ Model URL.", "## How to run from Python code\n\nYou can use GGUF models from Python using the llama-cpp-python or ctransformers libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.", "### How to load this model in Python code, using llama-cpp-python\n\nFor full documentation, please see: llama-cpp-python docs.", "#### First install the package\n\nRun one of the following commands, according to your system:", "#### Simple llama-cpp-python example code", "## How to use with LangChain\n\nHere are guides on using llama-cpp-python and ctransformers with LangChain:\n\n* LangChain + llama-cpp-python\n* LangChain + ctransformers", "# Original model card: Llama3-OpenBioLLM-8B\n\n\n\n<div align=\"center\">\n<img width=\"260px\" src=\"URL\n\n\n!image/png\n\n\n\n\n<div align=\"center\">\n\n <h1>Advancing Open-source Large Language Models in Medical Domain</h1>\n</div>\n\n<p align=\"center\" style=\"margin-top: 0px;\">\n <a href=\"URL\n <img src=\"URL alt=\"OpenChat Logo\" style=\"width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 10px; margin-top: 0px; margin-bottom: 0px;\"/>\n <span class=\"link-text\" style=\" margin-right: 5px;\">Online Demo</span>\n </a> |\n <a href=\"URL\n <img src=\"URL alt=\"GitHub Logo\" style=\"width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;\"/>\n <span class=\"link-text\" style=\" margin-right: 5px;\">GitHub</span>\n </a> |\n <a href=\"#\">\n <img src=\"URL alt=\"ArXiv Logo\" style=\"width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;\"/>\n <span class=\"link-text\" style=\"margin-right: 5px;\">Paper</span>\n </a> |\n <a href=\"URL\n <img src=\"URL alt=\"Discord Logo\" style=\"width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;\"/>\n <span class=\"link-text\">Discord</span>\n </a>\n</p>\n\n!image/jpeg\n\nIntroducing OpenBioLLM-8B: A State-of-the-Art Open Source Biomedical Large Language Model\n\n\nOpenBioLLM-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.\n\n 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.\n\n 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.\n\n Advanced Training Techniques: OpenBioLLM-8B builds upon the powerful foundations of the Meta-Llama-3-8B and 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:\n\n<div align=\"center\">\n<img width=\"1200px\" src=\"URL\n</div>\n\n- Policy Optimization: Direct Preference Optimization: Your Language Model is Secretly a Reward Model (DPO)\n- Ranking Dataset: berkeley-nest/Nectar\n- Fine-tuning dataset: Custom Medical Instruct dataset (We plan to release a sample training dataset in our upcoming paper; please stay updated)\n\nThis combination of cutting-edge techniques enables OpenBioLLM-8B to align with key capabilities and preferences for biomedical applications.\n\n️ Release Details:\n\n- Model Size: 8 billion parameters\n- Quantization: Optimized quantized versions available Here\n- Language(s) (NLP): en\n- Developed By: Ankit Pal (Aaditya Ura) from Saama AI Labs\n- License: Meta-Llama License\n- Fine-tuned from models: meta-llama/Meta-Llama-3-8B\n- Resources for more information:\n - Paper: Coming soon\n\nThe model can be fine-tuned for more specialized tasks and datasets as needed.\n\nOpenBioLLM-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.\n\nWe are excited to share OpenBioLLM-8B with researchers and developers around the world.", "### Use with transformers\n\nImportant: 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.\n\nSee the snippet below for usage with Transformers:", "## Training procedure", "### Training hyperparameters\n\n<details>\n <summary>Click to see details</summary>\n\n- learning_rate: 0.0002\n- lr_scheduler: cosine\n- train_batch_size: 12\n- eval_batch_size: 8\n- GPU: H100 80GB SXM5\n- num_devices: 1\n- optimizer: adamw_bnb_8bit\n- lr_scheduler_warmup_steps: 100\n- num_epochs: 4\n</details>", "### Peft hyperparameters\n\n<details>\n <summary>Click to see details</summary>\n\n- adapter: qlora\n- lora_r: 128\n- lora_alpha: 256\n- lora_dropout: 0.05\n- lora_target_linear: true\n\n-lora_target_modules:\n- q_proj\n- v_proj\n- k_proj\n- o_proj\n- gate_proj\n- down_proj\n- up_proj\n</details>", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.1\n- Axolotl\n- Lm harness for evaluation", "# Benchmark Results\n\n 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.\n\n 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.\n\n| | Clinical KG | Medical Genetics | Anatomy | Pro Medicine | College Biology | College Medicine | MedQA 4 opts | PubMedQA | MedMCQA | Avg |\n| | - | | - | |\n| OpenBioLLM-70B | 92.93 | 93.197 | 83.904 | 93.75 | 93.827 | 85.749 | 78.162 | 78.97 | 74.014 | 86.05588 |\n| Med-PaLM-2 (5-shot) | 88.3 | 90 | 77.8 | 95.2 | 94.4 | 80.9 | 79.7 | 79.2 | 71.3 | 84.08 |\n| GPT-4 | 86.04 | 91 | 80 | 93.01 | 95.14 | 76.88 | 78.87 | 75.2 | 69.52 | 82.85 |\n| 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 |\n| OpenBioLLM-8B | 76.101 | 86.1 | 69.829 | 78.21 | 84.213 | 68.042 | 58.993 | 74.12 | 56.913 | 72.502 |\n| Gemini-1.0 | 76.7 | 75.8 | 66.7 | 77.7 | 88 | 69.2 | 58 | 70.7 | 54.3 | 70.79 |\n| GPT-3.5 Turbo 1106 | 74.71 | 74 | 72.79 | 72.79 | 72.91 | 64.73 | 57.71 | 72.66 | 53.79 | 66 |\n| Meditron-70B | 66.79 | 69 | 53.33 | 71.69 | 76.38 | 63 | 57.1 | 76.6 | 46.85 | 64.52 |\n| gemma-7b | 69.81 | 70 | 59.26 | 66.18 | 79.86 | 60.12 | 47.21 | 76.2 | 48.96 | 64.18 |\n| Mistral-7B-v0.1 | 68.68 | 71 | 55.56 | 68.38 | 68.06 | 59.54 | 50.82 | 75.4 | 48.2 | 62.85 |\n| Apollo-7B | 62.26 | 72 | 61.48 | 69.12 | 70.83 | 55.49 | 55.22 | 39.8 | 53.77 | 60 |\n| MedAlpaca-7b | 57.36 | 69 | 57.04 | 67.28 | 65.28 | 54.34 | 41.71 | 72.8 | 37.51 | 58.03 |\n| BioMistral-7B | 59.9 | 64 | 56.5 | 60.4 | 59 | 54.7 | 50.6 | 77.5 | 48.1 | 57.3 |\n| AlpaCare-llama2-7b | 49.81 | 49 | 45.92 | 33.82 | 50 | 43.35 | 29.77 | 72.2 | 34.42 | 45.36 |\n| ClinicalGPT | 30.56 | 27 | 30.37 | 19.48 | 25 | 24.27 | 26.08 | 63.8 | 28.18 | 30.52 |\n\n<div align=\"center\">\n<img width=\"1600px\" src=\"URL\n</div>", "## Detailed Medical Subjectwise accuracy\n\n\n!image/png", "# Use Cases & Examples\n\n Below results are from the quantized version of OpenBioLLM-70B", "# Summarize Clinical Notes\n\nOpenBioLLM-70B can efficiently analyze and summarize complex clinical notes, EHR data, and discharge summaries, extracting key information and generating concise, structured summaries\n\n\n!image/png", "# Answer Medical Questions\n\nOpenBioLLM-70B can provide answers to a wide range of medical questions.\n\n\n!image/png\n!image/png\n\n<details>\n <summary>Click to see details</summary>\n\n\n!image/png\n!image/png\n!image/png\n\n</details>", "# Clinical Entity Recognition\n\nOpenBioLLM-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.\n\n\n!image/png\n!image/png\n!image/png", "# Biomarkers Extraction\n\n\n!image/png", "# Classification\n\nOpenBioLLM-70B can perform various biomedical classification tasks, such as disease prediction, sentiment analysis, medical document categorization\n\n!image/png", "# De-Identification\n\nOpenBioLLM-70B can detect and remove personally identifiable information (PII) from medical records, ensuring patient privacy and compliance with data protection regulations like HIPAA.\n\n!image/png\n\n\n\nAdvisory Notice!\n\nWhile 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.\n\nTherefore, 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.\nOpenBioLLM-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.\n\nAppropriately adapting and validating OpenBioLLM-70B & 8B for specific medical use cases would require significant additional work, potentially including:\n\n- Thorough testing and evaluation in relevant clinical scenarios\n- Alignment with evidence-based guidelines and best practices\n- Mitigation of potential biases and failure modes\n- Integration with human oversight and interpretation\n- Compliance with regulatory and ethical standards\n\nAlways consult a qualified healthcare provider for personal medical needs.\n\n\n\nIf you find OpenBioLLM-70B & 8B useful in your work, please cite the model as follows:\n\n\n\nThe accompanying paper is currently in progress and will be released soon.\n\n<div align=\"center\">\n<h2> Contact </h2>\n</div>\n\nWe look forward to hearing you and collaborating on this exciting project!\n\nContributors:\n- Ankit Pal (Aaditya Ura) [aadityaura at gmail dot com]\n- Saama AI Labs\n- 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\n\nWe thank the Meta Team for their amazing models!\n\n\nResult sources\n\n- [1] GPT-4 [Capabilities of GPT-4 on Medical Challenge Problems] (URL\n- [2] Med-PaLM-1 Large Language Models Encode Clinical Knowledge\n- [3] Med-PaLM-2 Towards Expert-Level Medical Question Answering with Large Language Models\n- [4] Gemini-1.0 Gemini Goes to Med School" ]

[ 129, 31, 26, 419, 314, 83, 74, 206, 172, 47, 82, 37, 20, 14, 54, 1134, 68, 4, 115, 110, 5, 54, 966, 12, 21, 52, 65, 139, 10, 34, 454, 87 ]

[ "TAGS\n#gguf #llama-3 #llama #Mixtral #instruct #finetune #chatml #DPO #RLHF #gpt4 #distillation #GGUF #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 \n# Llama3-OpenBioLLM-8B-GGUF\n- Original model: Llama3-OpenBioLLM-8B## Description\n\nThis repo contains GGUF format model files for Llama3-OpenBioLLM-8B.### About GGUF\nGGUF is a new format introduced by the URL team on August 21st 2023. It is a replacement for GGML, which is no longer supported by URL.\nHere is an incomplete list of clients and libraries that are known to support GGUF:\n* URL. This is the source project for GGUF, providing both a Command Line Interface (CLI) and a server option.\n* text-generation-webui, Known as the most widely used web UI, this project boasts numerous features and powerful extensions, and supports GPU acceleration.\n* Ollama Ollama is a lightweight and extensible framework designed for building and running language models locally. It features a simple API for creating, managing, and executing models, along with a library of pre-built models for use in various applications​\n* KoboldCpp, A comprehensive web UI offering GPU acceleration across all platforms and architectures, particularly renowned for storytelling.\n* GPT4All, This is a free and open source GUI that runs locally, supporting Windows, Linux, and macOS with full GPU acceleration.\n* LM Studio An intuitive and powerful local GUI for Windows and macOS (Silicon), featuring GPU acceleration.\n* LoLLMS Web UI. A notable web UI with a variety of unique features, including a comprehensive model library for easy model selection.\n* URL, An attractive, user-friendly character-based chat GUI for Windows and macOS (both Silicon and Intel), also offering GPU acceleration.\n* llama-cpp-python, A Python library equipped with GPU acceleration, LangChain support, and an OpenAI-compatible API server.\n* candle, A Rust-based ML framework focusing on performance, including GPU support, and designed for ease of use.\n* ctransformers, A Python library featuring GPU acceleration, LangChain support, and an OpenAI-compatible AI server.\n* localGPT An open-source initiative enabling private conversations with documents.## Explanation of quantisation methods\n<details>\n <summary>Click to see details</summary>\nThe new methods available are:\n\n* GGML_TYPE_Q2_K - \"type-1\" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)\n* GGML_TYPE_Q3_K - \"type-0\" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.\n* GGML_TYPE_Q4_K - \"type-1\" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.\n* GGML_TYPE_Q5_K - \"type-1\" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw\n* GGML_TYPE_Q6_K - \"type-0\" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw.\n</details>## How to download GGUF files\n\nNote for manual downloaders: You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single folder.\n\nThe following clients/libraries will automatically download models for you, providing a list of available models to choose from:\n\n* LM Studio\n* LoLLMS Web UI\n* URL### In 'text-generation-webui'\n\nUnder Download Model, you can enter the model repo: LiteLLMs/Llama3-OpenBioLLM-8B-GGUF and below it, a specific filename to download, such as: Q4_0/Q4_0-URL.\n\nThen click Download.### On the command line, including multiple files at once\n\nI recommend using the 'huggingface-hub' Python library:\n\n\n\nThen you can download any individual model file to the current directory, at high speed, with a command like this:\n\n\n\n<details>\n <summary>More advanced huggingface-cli download usage (click to read)</summary>\n\nYou can also download multiple files at once with a pattern:\n\n\n\nFor more documentation on downloading with 'huggingface-cli', please see: HF -> Hub Python Library -> Download files -> Download from the CLI.\n\nTo accelerate downloads on fast connections (1Gbit/s or higher), install 'hf_transfer':\n\n\n\nAnd set environment variable 'HF_HUB_ENABLE_HF_TRANSFER' to '1':\n\n\n\nWindows Command Line users: You can set the environment variable by running 'set HF_HUB_ENABLE_HF_TRANSFER=1' before the download command.\n</details>## Example 'URL' command\n\nMake sure you are using 'URL' from commit d0cee0d or later.\n\n\n\nChange '-ngl 32' to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.\n\nChange '-c 8192' to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by URL automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.\n\nIf you want to have a chat-style conversation, replace the '-p <PROMPT>' argument with '-i -ins'\n\nFor other parameters and how to use them, please refer to the URL documentation## How to run in 'text-generation-webui'\n\nFurther instructions can be found in the text-generation-webui documentation, here: text-generation-webui/docs/04 ‐ Model URL.## How to run from Python code\n\nYou can use GGUF models from Python using the llama-cpp-python or ctransformers libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.### How to load this model in Python code, using llama-cpp-python\n\nFor full documentation, please see: llama-cpp-python docs.#### First install the package\n\nRun one of the following commands, according to your system:#### Simple llama-cpp-python example code## How to use with LangChain\n\nHere are guides on using llama-cpp-python and ctransformers with LangChain:\n\n* LangChain + llama-cpp-python\n* LangChain + ctransformers# Original model card: Llama3-OpenBioLLM-8B\n\n\n\n<div align=\"center\">\n<img width=\"260px\" src=\"URL\n\n\n!image/png\n\n\n\n\n<div align=\"center\">\n\n <h1>Advancing Open-source Large Language Models in Medical Domain</h1>\n</div>\n\n<p align=\"center\" style=\"margin-top: 0px;\">\n <a href=\"URL\n <img src=\"URL alt=\"OpenChat Logo\" style=\"width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 10px; margin-top: 0px; margin-bottom: 0px;\"/>\n <span class=\"link-text\" style=\" margin-right: 5px;\">Online Demo</span>\n </a> |\n <a href=\"URL\n <img src=\"URL alt=\"GitHub Logo\" style=\"width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;\"/>\n <span class=\"link-text\" style=\" margin-right: 5px;\">GitHub</span>\n </a> |\n <a href=\"#\">\n <img src=\"URL alt=\"ArXiv Logo\" style=\"width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;\"/>\n <span class=\"link-text\" style=\"margin-right: 5px;\">Paper</span>\n </a> |\n <a href=\"URL\n <img src=\"URL alt=\"Discord Logo\" style=\"width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;\"/>\n <span class=\"link-text\">Discord</span>\n </a>\n</p>\n\n!image/jpeg\n\nIntroducing OpenBioLLM-8B: A State-of-the-Art Open Source Biomedical Large Language Model\n\n\nOpenBioLLM-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.\n\n 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.\n\n 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.\n\n Advanced Training Techniques: OpenBioLLM-8B builds upon the powerful foundations of the Meta-Llama-3-8B and 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:\n\n<div align=\"center\">\n<img width=\"1200px\" src=\"URL\n</div>\n\n- Policy Optimization: Direct Preference Optimization: Your Language Model is Secretly a Reward Model (DPO)\n- Ranking Dataset: berkeley-nest/Nectar\n- Fine-tuning dataset: Custom Medical Instruct dataset (We plan to release a sample training dataset in our upcoming paper; please stay updated)\n\nThis combination of cutting-edge techniques enables OpenBioLLM-8B to align with key capabilities and preferences for biomedical applications.\n\n️ Release Details:\n\n- Model Size: 8 billion parameters\n- Quantization: Optimized quantized versions available Here\n- Language(s) (NLP): en\n- Developed By: Ankit Pal (Aaditya Ura) from Saama AI Labs\n- License: Meta-Llama License\n- Fine-tuned from models: meta-llama/Meta-Llama-3-8B\n- Resources for more information:\n - Paper: Coming soon\n\nThe model can be fine-tuned for more specialized tasks and datasets as needed.\n\nOpenBioLLM-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.\n\nWe are excited to share OpenBioLLM-8B with researchers and developers around the world.### Use with transformers\n\nImportant: 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.\n\nSee the snippet below for usage with Transformers:## Training procedure### Training hyperparameters\n\n<details>\n <summary>Click to see details</summary>\n\n- learning_rate: 0.0002\n- lr_scheduler: cosine\n- train_batch_size: 12\n- eval_batch_size: 8\n- GPU: H100 80GB SXM5\n- num_devices: 1\n- optimizer: adamw_bnb_8bit\n- lr_scheduler_warmup_steps: 100\n- num_epochs: 4\n</details>### Peft hyperparameters\n\n<details>\n <summary>Click to see details</summary>\n\n- adapter: qlora\n- lora_r: 128\n- lora_alpha: 256\n- lora_dropout: 0.05\n- lora_target_linear: true\n\n-lora_target_modules:\n- q_proj\n- v_proj\n- k_proj\n- o_proj\n- gate_proj\n- down_proj\n- up_proj\n</details>### Training results### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.1\n- Axolotl\n- Lm harness for evaluation# Benchmark Results\n\n 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.\n\n 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.\n\n| | Clinical KG | Medical Genetics | Anatomy | Pro Medicine | College Biology | College Medicine | MedQA 4 opts | PubMedQA | MedMCQA | Avg |\n| | - | | - | |\n| OpenBioLLM-70B | 92.93 | 93.197 | 83.904 | 93.75 | 93.827 | 85.749 | 78.162 | 78.97 | 74.014 | 86.05588 |\n| Med-PaLM-2 (5-shot) | 88.3 | 90 | 77.8 | 95.2 | 94.4 | 80.9 | 79.7 | 79.2 | 71.3 | 84.08 |\n| GPT-4 | 86.04 | 91 | 80 | 93.01 | 95.14 | 76.88 | 78.87 | 75.2 | 69.52 | 82.85 |\n| 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 |\n| OpenBioLLM-8B | 76.101 | 86.1 | 69.829 | 78.21 | 84.213 | 68.042 | 58.993 | 74.12 | 56.913 | 72.502 |\n| Gemini-1.0 | 76.7 | 75.8 | 66.7 | 77.7 | 88 | 69.2 | 58 | 70.7 | 54.3 | 70.79 |\n| GPT-3.5 Turbo 1106 | 74.71 | 74 | 72.79 | 72.79 | 72.91 | 64.73 | 57.71 | 72.66 | 53.79 | 66 |\n| Meditron-70B | 66.79 | 69 | 53.33 | 71.69 | 76.38 | 63 | 57.1 | 76.6 | 46.85 | 64.52 |\n| gemma-7b | 69.81 | 70 | 59.26 | 66.18 | 79.86 | 60.12 | 47.21 | 76.2 | 48.96 | 64.18 |\n| Mistral-7B-v0.1 | 68.68 | 71 | 55.56 | 68.38 | 68.06 | 59.54 | 50.82 | 75.4 | 48.2 | 62.85 |\n| Apollo-7B | 62.26 | 72 | 61.48 | 69.12 | 70.83 | 55.49 | 55.22 | 39.8 | 53.77 | 60 |\n| MedAlpaca-7b | 57.36 | 69 | 57.04 | 67.28 | 65.28 | 54.34 | 41.71 | 72.8 | 37.51 | 58.03 |\n| BioMistral-7B | 59.9 | 64 | 56.5 | 60.4 | 59 | 54.7 | 50.6 | 77.5 | 48.1 | 57.3 |\n| AlpaCare-llama2-7b | 49.81 | 49 | 45.92 | 33.82 | 50 | 43.35 | 29.77 | 72.2 | 34.42 | 45.36 |\n| ClinicalGPT | 30.56 | 27 | 30.37 | 19.48 | 25 | 24.27 | 26.08 | 63.8 | 28.18 | 30.52 |\n\n<div align=\"center\">\n<img width=\"1600px\" src=\"URL\n</div>## Detailed Medical Subjectwise accuracy\n\n\n!image/png# Use Cases & Examples\n\n Below results are from the quantized version of OpenBioLLM-70B# Summarize Clinical Notes\n\nOpenBioLLM-70B can efficiently analyze and summarize complex clinical notes, EHR data, and discharge summaries, extracting key information and generating concise, structured summaries\n\n\n!image/png# Answer Medical Questions\n\nOpenBioLLM-70B can provide answers to a wide range of medical questions.\n\n\n!image/png\n!image/png\n\n<details>\n <summary>Click to see details</summary>\n\n\n!image/png\n!image/png\n!image/png\n\n</details># Clinical Entity Recognition\n\nOpenBioLLM-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.\n\n\n!image/png\n!image/png\n!image/png# Biomarkers Extraction\n\n\n!image/png# Classification\n\nOpenBioLLM-70B can perform various biomedical classification tasks, such as disease prediction, sentiment analysis, medical document categorization\n\n!image/png# De-Identification\n\nOpenBioLLM-70B can detect and remove personally identifiable information (PII) from medical records, ensuring patient privacy and compliance with data protection regulations like HIPAA.\n\n!image/png\n\n\n\nAdvisory Notice!\n\nWhile 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.\n\nTherefore, 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.\nOpenBioLLM-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.\n\nAppropriately adapting and validating OpenBioLLM-70B & 8B for specific medical use cases would require significant additional work, potentially including:\n\n- Thorough testing and evaluation in relevant clinical scenarios\n- Alignment with evidence-based guidelines and best practices\n- Mitigation of potential biases and failure modes\n- Integration with human oversight and interpretation\n- Compliance with regulatory and ethical standards\n\nAlways consult a qualified healthcare provider for personal medical needs.\n\n\n\nIf you find OpenBioLLM-70B & 8B useful in your work, please cite the model as follows:\n\n\n\nThe accompanying paper is currently in progress and will be released soon.\n\n<div align=\"center\">\n<h2> Contact </h2>\n</div>\n\nWe look forward to hearing you and collaborating on this exciting project!\n\nContributors:\n- Ankit Pal (Aaditya Ura) [aadityaura at gmail dot com]\n- Saama AI Labs\n- 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\n\nWe thank the Meta Team for their amazing models!\n\n\nResult sources\n\n- [1] GPT-4 [Capabilities of GPT-4 on Medical Challenge Problems] (URL\n- [2] Med-PaLM-1 Large Language Models Encode Clinical Knowledge\n- [3] Med-PaLM-2 Towards Expert-Level Medical Question Answering with Large Language Models\n- [4] Gemini-1.0 Gemini Goes to Med School" ]

[ "gguf", "nlp", "code", "text-generation", "en", "license:mit", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#gguf #nlp #code #text-generation #en #license-mit #region-us \n" ]

[ 24 ]

[ "TAGS\n#gguf #nlp #code #text-generation #en #license-mit #region-us \n" ]

[ "sentence-transformers", "safetensors", "roberta", "sentence-similarity", "feature-extraction", "loss:Matryoshka2dLoss", "loss:MatryoshkaLoss", "loss:MultipleNegativesRankingLoss", "en", "arxiv:1908.10084", "arxiv:2402.14776", "arxiv:2205.13147", "arxiv:1705.00652", "base_model:distilbert/distilroberta-base", "model-index", "co2_eq_emissions", "endpoints_compatible", "region:us" ]

[ "1908.10084", "2402.14776", "2205.13147", "1705.00652" ]

[ "en" ]

[ "### Model Description\n\n\n* Model Type: Sentence Transformer\n* Base model: distilbert/distilroberta-base\n* Maximum Sequence Length: 512 tokens\n* Output Dimensionality: 768 tokens\n* Similarity Function: Cosine Similarity\n* Training Dataset:\n\t+ sentence-transformers/all-nli\n* Language: en", "### Model Sources\n\n\n* Documentation: Sentence Transformers Documentation\n* Repository: Sentence Transformers on GitHub\n* Hugging Face: Sentence Transformers on Hugging Face", "### Full Model Architecture\n\n\nUsage\n-----", "### Direct Usage (Sentence Transformers)\n\n\nFirst install the Sentence Transformers library:\n\n\nThen you can load this model and run inference.\n\n\nEvaluation\n----------", "### Metrics", "#### Semantic Similarity\n\n\n* Dataset: 'sts-dev'\n* Evaluated with `EmbeddingSimilarityEvaluator`", "#### Semantic Similarity\n\n\n* Dataset: 'sts-test'\n* Evaluated with `EmbeddingSimilarityEvaluator`\n\n\n\nTraining Details\n----------------", "### Training Dataset", "#### sentence-transformers/all-nli\n\n\n* Dataset: sentence-transformers/all-nli at 65dd388\n* Size: 557,850 training samples\n* Columns: `anchor`, `positive`, and `negative`\n* Approximate statistics based on the first 1000 samples:\n* Samples:\n* Loss: `Matryoshka2dLoss` with these parameters:", "### Evaluation Dataset", "#### sentence-transformers/stsb\n\n\n* Dataset: sentence-transformers/stsb at ab7a5ac\n* Size: 1,500 evaluation samples\n* Columns: `sentence1`, `sentence2`, and `score`\n* Approximate statistics based on the first 1000 samples:\n* Samples:\n* Loss: `Matryoshka2dLoss` with these parameters:", "### Training Hyperparameters", "#### Non-Default Hyperparameters\n\n\n* 'eval\\_strategy': steps\n* 'per\\_device\\_train\\_batch\\_size': 128\n* 'per\\_device\\_eval\\_batch\\_size': 128\n* 'num\\_train\\_epochs': 1\n* 'warmup\\_ratio': 0.1\n* 'fp16': True\n* 'batch\\_sampler': no\\_duplicates", "#### All Hyperparameters\n\n\nClick to expand\n* 'overwrite\\_output\\_dir': False\n* 'do\\_predict': False\n* 'eval\\_strategy': steps\n* 'prediction\\_loss\\_only': False\n* 'per\\_device\\_train\\_batch\\_size': 128\n* 'per\\_device\\_eval\\_batch\\_size': 128\n* 'per\\_gpu\\_train\\_batch\\_size': None\n* 'per\\_gpu\\_eval\\_batch\\_size': None\n* 'gradient\\_accumulation\\_steps': 1\n* 'eval\\_accumulation\\_steps': None\n* 'learning\\_rate': 5e-05\n* 'weight\\_decay': 0.0\n* 'adam\\_beta1': 0.9\n* 'adam\\_beta2': 0.999\n* 'adam\\_epsilon': 1e-08\n* 'max\\_grad\\_norm': 1.0\n* 'num\\_train\\_epochs': 1\n* 'max\\_steps': -1\n* 'lr\\_scheduler\\_type': linear\n* 'lr\\_scheduler\\_kwargs': {}\n* 'warmup\\_ratio': 0.1\n* 'warmup\\_steps': 0\n* 'log\\_level': passive\n* 'log\\_level\\_replica': warning\n* 'log\\_on\\_each\\_node': True\n* 'logging\\_nan\\_inf\\_filter': True\n* 'save\\_safetensors': True\n* 'save\\_on\\_each\\_node': False\n* 'save\\_only\\_model': False\n* 'no\\_cuda': False\n* 'use\\_cpu': False\n* 'use\\_mps\\_device': False\n* 'seed': 42\n* 'data\\_seed': None\n* 'jit\\_mode\\_eval': False\n* 'use\\_ipex': False\n* 'bf16': False\n* 'fp16': True\n* 'fp16\\_opt\\_level': O1\n* 'half\\_precision\\_backend': auto\n* 'bf16\\_full\\_eval': False\n* 'fp16\\_full\\_eval': False\n* 'tf32': None\n* 'local\\_rank': 0\n* 'ddp\\_backend': None\n* 'tpu\\_num\\_cores': None\n* 'tpu\\_metrics\\_debug': False\n* 'debug': []\n* 'dataloader\\_drop\\_last': False\n* 'dataloader\\_num\\_workers': 0\n* 'dataloader\\_prefetch\\_factor': None\n* 'past\\_index': -1\n* 'disable\\_tqdm': False\n* 'remove\\_unused\\_columns': True\n* 'label\\_names': None\n* 'load\\_best\\_model\\_at\\_end': False\n* 'ignore\\_data\\_skip': False\n* 'fsdp': []\n* 'fsdp\\_min\\_num\\_params': 0\n* 'fsdp\\_config': {'min\\_num\\_params': 0, 'xla': False, 'xla\\_fsdp\\_v2': False, 'xla\\_fsdp\\_grad\\_ckpt': False}\n* 'fsdp\\_transformer\\_layer\\_cls\\_to\\_wrap': None\n* 'accelerator\\_config': {'split\\_batches': False, 'dispatch\\_batches': None, 'even\\_batches': True, 'use\\_seedable\\_sampler': True, 'non\\_blocking': False, 'gradient\\_accumulation\\_kwargs': None}\n* 'deepspeed': None\n* 'label\\_smoothing\\_factor': 0.0\n* 'optim': adamw\\_torch\n* 'optim\\_args': None\n* 'adafactor': False\n* 'group\\_by\\_length': False\n* 'length\\_column\\_name': length\n* 'ddp\\_find\\_unused\\_parameters': None\n* 'ddp\\_bucket\\_cap\\_mb': None\n* 'ddp\\_broadcast\\_buffers': None\n* 'dataloader\\_pin\\_memory': True\n* 'dataloader\\_persistent\\_workers': False\n* 'skip\\_memory\\_metrics': True\n* 'use\\_legacy\\_prediction\\_loop': False\n* 'push\\_to\\_hub': False\n* 'resume\\_from\\_checkpoint': None\n* 'hub\\_model\\_id': None\n* 'hub\\_strategy': every\\_save\n* 'hub\\_private\\_repo': False\n* 'hub\\_always\\_push': False\n* 'gradient\\_checkpointing': False\n* 'gradient\\_checkpointing\\_kwargs': None\n* 'include\\_inputs\\_for\\_metrics': False\n* 'eval\\_do\\_concat\\_batches': True\n* 'fp16\\_backend': auto\n* 'push\\_to\\_hub\\_model\\_id': None\n* 'push\\_to\\_hub\\_organization': None\n* 'mp\\_parameters':\n* 'auto\\_find\\_batch\\_size': False\n* 'full\\_determinism': False\n* 'torchdynamo': None\n* 'ray\\_scope': last\n* 'ddp\\_timeout': 1800\n* 'torch\\_compile': False\n* 'torch\\_compile\\_backend': None\n* 'torch\\_compile\\_mode': None\n* 'dispatch\\_batches': None\n* 'split\\_batches': None\n* 'include\\_tokens\\_per\\_second': False\n* 'include\\_num\\_input\\_tokens\\_seen': False\n* 'neftune\\_noise\\_alpha': None\n* 'optim\\_target\\_modules': None\n* 'batch\\_sampler': no\\_duplicates\n* 'multi\\_dataset\\_batch\\_sampler': proportional", "### Training Logs", "### Environmental Impact\n\n\nCarbon emissions were measured using CodeCarbon.\n\n\n* Energy Consumed: 0.178 kWh\n* Carbon Emitted: 0.069 kg of CO2\n* Hours Used: 0.626 hours", "### Training Hardware\n\n\n* On Cloud: No\n* GPU Model: 1 x NVIDIA GeForce RTX 3090\n* CPU Model: 13th Gen Intel(R) Core(TM) i7-13700K\n* RAM Size: 31.78 GB", "### Framework Versions\n\n\n* Python: 3.11.6\n* Sentence Transformers: 3.0.0.dev0\n* Transformers: 4.41.0.dev0\n* PyTorch: 2.3.0+cu121\n* Accelerate: 0.26.1\n* Datasets: 2.18.0\n* Tokenizers: 0.19.1", "### BibTeX", "#### Sentence Transformers", "#### Matryoshka2dLoss", "#### MatryoshkaLoss", "#### MultipleNegativesRankingLoss" ]

[ "TAGS\n#sentence-transformers #safetensors #roberta #sentence-similarity #feature-extraction #loss-Matryoshka2dLoss #loss-MatryoshkaLoss #loss-MultipleNegativesRankingLoss #en #arxiv-1908.10084 #arxiv-2402.14776 #arxiv-2205.13147 #arxiv-1705.00652 #base_model-distilbert/distilroberta-base #model-index #co2_eq_emissions #endpoints_compatible #region-us \n", "### Model Description\n\n\n* Model Type: Sentence Transformer\n* Base model: distilbert/distilroberta-base\n* Maximum Sequence Length: 512 tokens\n* Output Dimensionality: 768 tokens\n* Similarity Function: Cosine Similarity\n* Training Dataset:\n\t+ sentence-transformers/all-nli\n* Language: en", "### Model Sources\n\n\n* Documentation: Sentence Transformers Documentation\n* Repository: Sentence Transformers on GitHub\n* Hugging Face: Sentence Transformers on Hugging Face", "### Full Model Architecture\n\n\nUsage\n-----", "### Direct Usage (Sentence Transformers)\n\n\nFirst install the Sentence Transformers library:\n\n\nThen you can load this model and run inference.\n\n\nEvaluation\n----------", "### Metrics", "#### Semantic Similarity\n\n\n* Dataset: 'sts-dev'\n* Evaluated with `EmbeddingSimilarityEvaluator`", "#### Semantic Similarity\n\n\n* Dataset: 'sts-test'\n* Evaluated with `EmbeddingSimilarityEvaluator`\n\n\n\nTraining Details\n----------------", "### Training Dataset", "#### sentence-transformers/all-nli\n\n\n* Dataset: sentence-transformers/all-nli at 65dd388\n* Size: 557,850 training samples\n* Columns: `anchor`, `positive`, and `negative`\n* Approximate statistics based on the first 1000 samples:\n* Samples:\n* Loss: `Matryoshka2dLoss` with these parameters:", "### Evaluation Dataset", "#### sentence-transformers/stsb\n\n\n* Dataset: sentence-transformers/stsb at ab7a5ac\n* Size: 1,500 evaluation samples\n* Columns: `sentence1`, `sentence2`, and `score`\n* Approximate statistics based on the first 1000 samples:\n* Samples:\n* Loss: `Matryoshka2dLoss` with these parameters:", "### Training Hyperparameters", "#### Non-Default Hyperparameters\n\n\n* 'eval\\_strategy': steps\n* 'per\\_device\\_train\\_batch\\_size': 128\n* 'per\\_device\\_eval\\_batch\\_size': 128\n* 'num\\_train\\_epochs': 1\n* 'warmup\\_ratio': 0.1\n* 'fp16': True\n* 'batch\\_sampler': no\\_duplicates", "#### All Hyperparameters\n\n\nClick to expand\n* 'overwrite\\_output\\_dir': False\n* 'do\\_predict': False\n* 'eval\\_strategy': steps\n* 'prediction\\_loss\\_only': False\n* 'per\\_device\\_train\\_batch\\_size': 128\n* 'per\\_device\\_eval\\_batch\\_size': 128\n* 'per\\_gpu\\_train\\_batch\\_size': None\n* 'per\\_gpu\\_eval\\_batch\\_size': None\n* 'gradient\\_accumulation\\_steps': 1\n* 'eval\\_accumulation\\_steps': None\n* 'learning\\_rate': 5e-05\n* 'weight\\_decay': 0.0\n* 'adam\\_beta1': 0.9\n* 'adam\\_beta2': 0.999\n* 'adam\\_epsilon': 1e-08\n* 'max\\_grad\\_norm': 1.0\n* 'num\\_train\\_epochs': 1\n* 'max\\_steps': -1\n* 'lr\\_scheduler\\_type': linear\n* 'lr\\_scheduler\\_kwargs': {}\n* 'warmup\\_ratio': 0.1\n* 'warmup\\_steps': 0\n* 'log\\_level': passive\n* 'log\\_level\\_replica': warning\n* 'log\\_on\\_each\\_node': True\n* 'logging\\_nan\\_inf\\_filter': True\n* 'save\\_safetensors': True\n* 'save\\_on\\_each\\_node': False\n* 'save\\_only\\_model': False\n* 'no\\_cuda': False\n* 'use\\_cpu': False\n* 'use\\_mps\\_device': False\n* 'seed': 42\n* 'data\\_seed': None\n* 'jit\\_mode\\_eval': False\n* 'use\\_ipex': False\n* 'bf16': False\n* 'fp16': True\n* 'fp16\\_opt\\_level': O1\n* 'half\\_precision\\_backend': auto\n* 'bf16\\_full\\_eval': False\n* 'fp16\\_full\\_eval': False\n* 'tf32': None\n* 'local\\_rank': 0\n* 'ddp\\_backend': None\n* 'tpu\\_num\\_cores': None\n* 'tpu\\_metrics\\_debug': False\n* 'debug': []\n* 'dataloader\\_drop\\_last': False\n* 'dataloader\\_num\\_workers': 0\n* 'dataloader\\_prefetch\\_factor': None\n* 'past\\_index': -1\n* 'disable\\_tqdm': False\n* 'remove\\_unused\\_columns': True\n* 'label\\_names': None\n* 'load\\_best\\_model\\_at\\_end': False\n* 'ignore\\_data\\_skip': False\n* 'fsdp': []\n* 'fsdp\\_min\\_num\\_params': 0\n* 'fsdp\\_config': {'min\\_num\\_params': 0, 'xla': False, 'xla\\_fsdp\\_v2': False, 'xla\\_fsdp\\_grad\\_ckpt': False}\n* 'fsdp\\_transformer\\_layer\\_cls\\_to\\_wrap': None\n* 'accelerator\\_config': {'split\\_batches': False, 'dispatch\\_batches': None, 'even\\_batches': True, 'use\\_seedable\\_sampler': True, 'non\\_blocking': False, 'gradient\\_accumulation\\_kwargs': None}\n* 'deepspeed': None\n* 'label\\_smoothing\\_factor': 0.0\n* 'optim': adamw\\_torch\n* 'optim\\_args': None\n* 'adafactor': False\n* 'group\\_by\\_length': False\n* 'length\\_column\\_name': length\n* 'ddp\\_find\\_unused\\_parameters': None\n* 'ddp\\_bucket\\_cap\\_mb': None\n* 'ddp\\_broadcast\\_buffers': None\n* 'dataloader\\_pin\\_memory': True\n* 'dataloader\\_persistent\\_workers': False\n* 'skip\\_memory\\_metrics': True\n* 'use\\_legacy\\_prediction\\_loop': False\n* 'push\\_to\\_hub': False\n* 'resume\\_from\\_checkpoint': None\n* 'hub\\_model\\_id': None\n* 'hub\\_strategy': every\\_save\n* 'hub\\_private\\_repo': False\n* 'hub\\_always\\_push': False\n* 'gradient\\_checkpointing': False\n* 'gradient\\_checkpointing\\_kwargs': None\n* 'include\\_inputs\\_for\\_metrics': False\n* 'eval\\_do\\_concat\\_batches': True\n* 'fp16\\_backend': auto\n* 'push\\_to\\_hub\\_model\\_id': None\n* 'push\\_to\\_hub\\_organization': None\n* 'mp\\_parameters':\n* 'auto\\_find\\_batch\\_size': False\n* 'full\\_determinism': False\n* 'torchdynamo': None\n* 'ray\\_scope': last\n* 'ddp\\_timeout': 1800\n* 'torch\\_compile': False\n* 'torch\\_compile\\_backend': None\n* 'torch\\_compile\\_mode': None\n* 'dispatch\\_batches': None\n* 'split\\_batches': None\n* 'include\\_tokens\\_per\\_second': False\n* 'include\\_num\\_input\\_tokens\\_seen': False\n* 'neftune\\_noise\\_alpha': None\n* 'optim\\_target\\_modules': None\n* 'batch\\_sampler': no\\_duplicates\n* 'multi\\_dataset\\_batch\\_sampler': proportional", "### Training Logs", "### Environmental Impact\n\n\nCarbon emissions were measured using CodeCarbon.\n\n\n* Energy Consumed: 0.178 kWh\n* Carbon Emitted: 0.069 kg of CO2\n* Hours Used: 0.626 hours", "### Training Hardware\n\n\n* On Cloud: No\n* GPU Model: 1 x NVIDIA GeForce RTX 3090\n* CPU Model: 13th Gen Intel(R) Core(TM) i7-13700K\n* RAM Size: 31.78 GB", "### Framework Versions\n\n\n* Python: 3.11.6\n* Sentence Transformers: 3.0.0.dev0\n* Transformers: 4.41.0.dev0\n* PyTorch: 2.3.0+cu121\n* Accelerate: 0.26.1\n* Datasets: 2.18.0\n* Tokenizers: 0.19.1", "### BibTeX", "#### Sentence Transformers", "#### Matryoshka2dLoss", "#### MatryoshkaLoss", "#### MultipleNegativesRankingLoss" ]

[ 128, 70, 29, 12, 37, 5, 30, 48, 6, 82, 6, 80, 8, 106, 1494, 5, 43, 55, 79, 6, 6, 11, 9, 12 ]

[ "TAGS\n#sentence-transformers #safetensors #roberta #sentence-similarity #feature-extraction #loss-Matryoshka2dLoss #loss-MatryoshkaLoss #loss-MultipleNegativesRankingLoss #en #arxiv-1908.10084 #arxiv-2402.14776 #arxiv-2205.13147 #arxiv-1705.00652 #base_model-distilbert/distilroberta-base #model-index #co2_eq_emissions #endpoints_compatible #region-us \n### Model Description\n\n\n* Model Type: Sentence Transformer\n* Base model: distilbert/distilroberta-base\n* Maximum Sequence Length: 512 tokens\n* Output Dimensionality: 768 tokens\n* Similarity Function: Cosine Similarity\n* Training Dataset:\n\t+ sentence-transformers/all-nli\n* Language: en### Model Sources\n\n\n* Documentation: Sentence Transformers Documentation\n* Repository: Sentence Transformers on GitHub\n* Hugging Face: Sentence Transformers on Hugging Face### Full Model Architecture\n\n\nUsage\n-----### Direct Usage (Sentence Transformers)\n\n\nFirst install the Sentence Transformers library:\n\n\nThen you can load this model and run inference.\n\n\nEvaluation\n----------### Metrics#### Semantic Similarity\n\n\n* Dataset: 'sts-dev'\n* Evaluated with `EmbeddingSimilarityEvaluator`#### Semantic Similarity\n\n\n* Dataset: 'sts-test'\n* Evaluated with `EmbeddingSimilarityEvaluator`\n\n\n\nTraining Details\n----------------### Training Dataset#### sentence-transformers/all-nli\n\n\n* Dataset: sentence-transformers/all-nli at 65dd388\n* Size: 557,850 training samples\n* Columns: `anchor`, `positive`, and `negative`\n* Approximate statistics based on the first 1000 samples:\n* Samples:\n* Loss: `Matryoshka2dLoss` with these parameters:### Evaluation Dataset#### sentence-transformers/stsb\n\n\n* Dataset: sentence-transformers/stsb at ab7a5ac\n* Size: 1,500 evaluation samples\n* Columns: `sentence1`, `sentence2`, and `score`\n* Approximate statistics based on the first 1000 samples:\n* Samples:\n* Loss: `Matryoshka2dLoss` with these parameters:### Training Hyperparameters#### Non-Default Hyperparameters\n\n\n* 'eval\\_strategy': steps\n* 'per\\_device\\_train\\_batch\\_size': 128\n* 'per\\_device\\_eval\\_batch\\_size': 128\n* 'num\\_train\\_epochs': 1\n* 'warmup\\_ratio': 0.1\n* 'fp16': True\n* 'batch\\_sampler': no\\_duplicates#### All Hyperparameters\n\n\nClick to expand\n* 'overwrite\\_output\\_dir': False\n* 'do\\_predict': False\n* 'eval\\_strategy': steps\n* 'prediction\\_loss\\_only': False\n* 'per\\_device\\_train\\_batch\\_size': 128\n* 'per\\_device\\_eval\\_batch\\_size': 128\n* 'per\\_gpu\\_train\\_batch\\_size': None\n* 'per\\_gpu\\_eval\\_batch\\_size': None\n* 'gradient\\_accumulation\\_steps': 1\n* 'eval\\_accumulation\\_steps': None\n* 'learning\\_rate': 5e-05\n* 'weight\\_decay': 0.0\n* 'adam\\_beta1': 0.9\n* 'adam\\_beta2': 0.999\n* 'adam\\_epsilon': 1e-08\n* 'max\\_grad\\_norm': 1.0\n* 'num\\_train\\_epochs': 1\n* 'max\\_steps': -1\n* 'lr\\_scheduler\\_type': linear\n* 'lr\\_scheduler\\_kwargs': {}\n* 'warmup\\_ratio': 0.1\n* 'warmup\\_steps': 0\n* 'log\\_level': passive\n* 'log\\_level\\_replica': warning\n* 'log\\_on\\_each\\_node': True\n* 'logging\\_nan\\_inf\\_filter': True\n* 'save\\_safetensors': True\n* 'save\\_on\\_each\\_node': False\n* 'save\\_only\\_model': False\n* 'no\\_cuda': False\n* 'use\\_cpu': False\n* 'use\\_mps\\_device': False\n* 'seed': 42\n* 'data\\_seed': None\n* 'jit\\_mode\\_eval': False\n* 'use\\_ipex': False\n* 'bf16': False\n* 'fp16': True\n* 'fp16\\_opt\\_level': O1\n* 'half\\_precision\\_backend': auto\n* 'bf16\\_full\\_eval': False\n* 'fp16\\_full\\_eval': False\n* 'tf32': None\n* 'local\\_rank': 0\n* 'ddp\\_backend': None\n* 'tpu\\_num\\_cores': None\n* 'tpu\\_metrics\\_debug': False\n* 'debug': []\n* 'dataloader\\_drop\\_last': False\n* 'dataloader\\_num\\_workers': 0\n* 'dataloader\\_prefetch\\_factor': None\n* 'past\\_index': -1\n* 'disable\\_tqdm': False\n* 'remove\\_unused\\_columns': True\n* 'label\\_names': None\n* 'load\\_best\\_model\\_at\\_end': False\n* 'ignore\\_data\\_skip': False\n* 'fsdp': []\n* 'fsdp\\_min\\_num\\_params': 0\n* 'fsdp\\_config': {'min\\_num\\_params': 0, 'xla': False, 'xla\\_fsdp\\_v2': False, 'xla\\_fsdp\\_grad\\_ckpt': False}\n* 'fsdp\\_transformer\\_layer\\_cls\\_to\\_wrap': None\n* 'accelerator\\_config': {'split\\_batches': False, 'dispatch\\_batches': None, 'even\\_batches': True, 'use\\_seedable\\_sampler': True, 'non\\_blocking': False, 'gradient\\_accumulation\\_kwargs': None}\n* 'deepspeed': None\n* 'label\\_smoothing\\_factor': 0.0\n* 'optim': adamw\\_torch\n* 'optim\\_args': None\n* 'adafactor': False\n* 'group\\_by\\_length': False\n* 'length\\_column\\_name': length\n* 'ddp\\_find\\_unused\\_parameters': None\n* 'ddp\\_bucket\\_cap\\_mb': None\n* 'ddp\\_broadcast\\_buffers': None\n* 'dataloader\\_pin\\_memory': True\n* 'dataloader\\_persistent\\_workers': False\n* 'skip\\_memory\\_metrics': True\n* 'use\\_legacy\\_prediction\\_loop': False\n* 'push\\_to\\_hub': False\n* 'resume\\_from\\_checkpoint': None\n* 'hub\\_model\\_id': None\n* 'hub\\_strategy': every\\_save\n* 'hub\\_private\\_repo': False\n* 'hub\\_always\\_push': False\n* 'gradient\\_checkpointing': False\n* 'gradient\\_checkpointing\\_kwargs': None\n* 'include\\_inputs\\_for\\_metrics': False\n* 'eval\\_do\\_concat\\_batches': True\n* 'fp16\\_backend': auto\n* 'push\\_to\\_hub\\_model\\_id': None\n* 'push\\_to\\_hub\\_organization': None\n* 'mp\\_parameters':\n* 'auto\\_find\\_batch\\_size': False\n* 'full\\_determinism': False\n* 'torchdynamo': None\n* 'ray\\_scope': last\n* 'ddp\\_timeout': 1800\n* 'torch\\_compile': False\n* 'torch\\_compile\\_backend': None\n* 'torch\\_compile\\_mode': None\n* 'dispatch\\_batches': None\n* 'split\\_batches': None\n* 'include\\_tokens\\_per\\_second': False\n* 'include\\_num\\_input\\_tokens\\_seen': False\n* 'neftune\\_noise\\_alpha': None\n* 'optim\\_target\\_modules': None\n* 'batch\\_sampler': no\\_duplicates\n* 'multi\\_dataset\\_batch\\_sampler': proportional### Training Logs### Environmental Impact\n\n\nCarbon emissions were measured using CodeCarbon.\n\n\n* Energy Consumed: 0.178 kWh\n* Carbon Emitted: 0.069 kg of CO2\n* Hours Used: 0.626 hours### Training Hardware\n\n\n* On Cloud: No\n* GPU Model: 1 x NVIDIA GeForce RTX 3090\n* CPU Model: 13th Gen Intel(R) Core(TM) i7-13700K\n* RAM Size: 31.78 GB### Framework Versions\n\n\n* Python: 3.11.6\n* Sentence Transformers: 3.0.0.dev0\n* Transformers: 4.41.0.dev0\n* PyTorch: 2.3.0+cu121\n* Accelerate: 0.26.1\n* Datasets: 2.18.0\n* Tokenizers: 0.19.1### BibTeX#### Sentence Transformers#### Matryoshka2dLoss#### MatryoshkaLoss#### MultipleNegativesRankingLoss" ]

[ "transformers", "safetensors", "llama", "text-generation", "text-generation-inference", "unsloth", "trl", "orpo", "conversational", "en", "base_model:botbot-ai/CabraLlama3-8b", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[ "# Uploaded model\n\n- Developed by: arthrod\n- License: apache-2.0\n- Finetuned from model : botbot-ai/CabraLlama3-8b\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #text-generation-inference #unsloth #trl #orpo #conversational #en #base_model-botbot-ai/CabraLlama3-8b #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "# Uploaded model\n\n- Developed by: arthrod\n- License: apache-2.0\n- Finetuned from model : botbot-ai/CabraLlama3-8b\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ 75, 76 ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #text-generation-inference #unsloth #trl #orpo #conversational #en #base_model-botbot-ai/CabraLlama3-8b #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n# Uploaded model\n\n- Developed by: arthrod\n- License: apache-2.0\n- Finetuned from model : botbot-ai/CabraLlama3-8b\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "transformers", "safetensors", "t5", "text2text-generation", "arxiv:1910.09700", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "1910.09700" ]

[]

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

[ "TAGS\n#transformers #safetensors #t5 #text2text-generation #arxiv-1910.09700 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 50, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #t5 #text2text-generation #arxiv-1910.09700 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.## How to Get Started with the Model\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "transformers", "safetensors", "pegasus", "text2text-generation", "generated_from_trainer", "base_model:google/pegasus-cnn_dailymail", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 1\n* eval\\_batch\\_size: 1\n* seed: 42\n* gradient\\_accumulation\\_steps: 16\n* total\\_train\\_batch\\_size: 16\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 500\n* num\\_epochs: 1", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #safetensors #pegasus #text2text-generation #generated_from_trainer #base_model-google/pegasus-cnn_dailymail #autotrain_compatible #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 1\n* eval\\_batch\\_size: 1\n* seed: 42\n* gradient\\_accumulation\\_steps: 16\n* total\\_train\\_batch\\_size: 16\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 500\n* num\\_epochs: 1", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ 48, 140, 5, 44 ]

[ "TAGS\n#transformers #safetensors #pegasus #text2text-generation #generated_from_trainer #base_model-google/pegasus-cnn_dailymail #autotrain_compatible #endpoints_compatible #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 1\n* eval\\_batch\\_size: 1\n* seed: 42\n* gradient\\_accumulation\\_steps: 16\n* total\\_train\\_batch\\_size: 16\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 500\n* num\\_epochs: 1### Training results### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "diffusers", "stable-diffusion-xl", "stable-diffusion-xl-diffusers", "diffusers-training", "text-to-image", "lora", "template:sd-lora", "base_model:stabilityai/stable-diffusion-xl-base-1.0", "license:openrail++", "region:us" ]

[]

[]

[ "# SDXL LoRA DreamBooth - aarashfeizi/jean-francois-godbout-batch3-repeats3-rank32-snrNone\n\n<Gallery />", "## Model description", "### These are aarashfeizi/jean-francois-godbout-batch3-repeats3-rank32-snrNone LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.", "## Download model", "### Use it with UIs such as AUTOMATIC1111, Comfy UI, SD.Next, Invoke\n\n- LoRA: download '/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch3-repeats3-rank32-snrNone.safetensors' here .\n - Place it on your 'models/Lora' folder.\n - On AUTOMATIC1111, load the LoRA by adding '<lora:/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch3-repeats3-rank32-snrNone:1>' to your prompt. On ComfyUI just load it as a regular LoRA.\n- *Embeddings*: download '/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch3-repeats3-rank32-snrNone_emb.safetensors' here .\n - Place it on it on your 'embeddings' folder\n - Use it by adding '/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch3-repeats3-rank32-snrNone_emb' to your prompt. For example, 'A photo of /home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch3-repeats3-rank32-snrNone_emb'\n (you need both the LoRA and the embeddings as they were trained together for this LoRA)", "## Use it with the diffusers library\n\n\n\nFor more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers", "## Trigger words\n\nTo trigger image generation of trained concept(or concepts) replace each concept identifier in you prompt with the new inserted tokens:\n\nto trigger concept 'TOK' → use '<s0><s1>' in your prompt", "## Details\nAll Files & versions.\n\nThe weights were trained using diffusers Advanced Dreambooth Training Script.\n\nLoRA for the text encoder was enabled. False.\n\nPivotal tuning was enabled: True.\n\nSpecial VAE used for training: madebyollin/sdxl-vae-fp16-fix." ]

[ "TAGS\n#diffusers #stable-diffusion-xl #stable-diffusion-xl-diffusers #diffusers-training #text-to-image #lora #template-sd-lora #base_model-stabilityai/stable-diffusion-xl-base-1.0 #license-openrail++ #region-us \n", "# SDXL LoRA DreamBooth - aarashfeizi/jean-francois-godbout-batch3-repeats3-rank32-snrNone\n\n<Gallery />", "## Model description", "### These are aarashfeizi/jean-francois-godbout-batch3-repeats3-rank32-snrNone LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.", "## Download model", "### Use it with UIs such as AUTOMATIC1111, Comfy UI, SD.Next, Invoke\n\n- LoRA: download '/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch3-repeats3-rank32-snrNone.safetensors' here .\n - Place it on your 'models/Lora' folder.\n - On AUTOMATIC1111, load the LoRA by adding '<lora:/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch3-repeats3-rank32-snrNone:1>' to your prompt. On ComfyUI just load it as a regular LoRA.\n- *Embeddings*: download '/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch3-repeats3-rank32-snrNone_emb.safetensors' here .\n - Place it on it on your 'embeddings' folder\n - Use it by adding '/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch3-repeats3-rank32-snrNone_emb' to your prompt. For example, 'A photo of /home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch3-repeats3-rank32-snrNone_emb'\n (you need both the LoRA and the embeddings as they were trained together for this LoRA)", "## Use it with the diffusers library\n\n\n\nFor more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers", "## Trigger words\n\nTo trigger image generation of trained concept(or concepts) replace each concept identifier in you prompt with the new inserted tokens:\n\nto trigger concept 'TOK' → use '<s0><s1>' in your prompt", "## Details\nAll Files & versions.\n\nThe weights were trained using diffusers Advanced Dreambooth Training Script.\n\nLoRA for the text encoder was enabled. False.\n\nPivotal tuning was enabled: True.\n\nSpecial VAE used for training: madebyollin/sdxl-vae-fp16-fix." ]

[ 70, 42, 4, 54, 4, 376, 34, 53, 67 ]

[ "TAGS\n#diffusers #stable-diffusion-xl #stable-diffusion-xl-diffusers #diffusers-training #text-to-image #lora #template-sd-lora #base_model-stabilityai/stable-diffusion-xl-base-1.0 #license-openrail++ #region-us \n# SDXL LoRA DreamBooth - aarashfeizi/jean-francois-godbout-batch3-repeats3-rank32-snrNone\n\n<Gallery />## Model description### These are aarashfeizi/jean-francois-godbout-batch3-repeats3-rank32-snrNone LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.## Download model### Use it with UIs such as AUTOMATIC1111, Comfy UI, SD.Next, Invoke\n\n- LoRA: download '/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch3-repeats3-rank32-snrNone.safetensors' here .\n - Place it on your 'models/Lora' folder.\n - On AUTOMATIC1111, load the LoRA by adding '<lora:/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch3-repeats3-rank32-snrNone:1>' to your prompt. On ComfyUI just load it as a regular LoRA.\n- *Embeddings*: download '/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch3-repeats3-rank32-snrNone_emb.safetensors' here .\n - Place it on it on your 'embeddings' folder\n - Use it by adding '/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch3-repeats3-rank32-snrNone_emb' to your prompt. For example, 'A photo of /home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch3-repeats3-rank32-snrNone_emb'\n (you need both the LoRA and the embeddings as they were trained together for this LoRA)## Use it with the diffusers library\n\n\n\nFor more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers## Trigger words\n\nTo trigger image generation of trained concept(or concepts) replace each concept identifier in you prompt with the new inserted tokens:\n\nto trigger concept 'TOK' → use '<s0><s1>' in your prompt## Details\nAll Files & versions.\n\nThe weights were trained using diffusers Advanced Dreambooth Training Script.\n\nLoRA for the text encoder was enabled. False.\n\nPivotal tuning was enabled: True.\n\nSpecial VAE used for training: madebyollin/sdxl-vae-fp16-fix." ]

[ "sentence-transformers", "safetensors", "distilbert", "sentence-similarity", "feature-extraction", "loss:Matryoshka2dLoss", "loss:MatryoshkaLoss", "loss:CoSENTLoss", "en", "arxiv:1908.10084", "arxiv:2402.14776", "arxiv:2205.13147", "base_model:distilbert/distilbert-base-uncased", "model-index", "co2_eq_emissions", "endpoints_compatible", "region:us" ]

[ "1908.10084", "2402.14776", "2205.13147" ]

[ "en" ]

[ "### Model Description\n\n\n* Model Type: Sentence Transformer\n* Base model: distilbert/distilbert-base-uncased\n* Maximum Sequence Length: 512 tokens\n* Output Dimensionality: 768 tokens\n* Similarity Function: Cosine Similarity\n* Training Dataset:\n\t+ sentence-transformers/stsb\n* Language: en", "### Model Sources\n\n\n* Documentation: Sentence Transformers Documentation\n* Repository: Sentence Transformers on GitHub\n* Hugging Face: Sentence Transformers on Hugging Face", "### Full Model Architecture\n\n\nUsage\n-----", "### Direct Usage (Sentence Transformers)\n\n\nFirst install the Sentence Transformers library:\n\n\nThen you can load this model and run inference.\n\n\nEvaluation\n----------", "### Metrics", "#### Semantic Similarity\n\n\n* Dataset: 'sts-dev'\n* Evaluated with `EmbeddingSimilarityEvaluator`", "#### Semantic Similarity\n\n\n* Dataset: 'sts-test'\n* Evaluated with `EmbeddingSimilarityEvaluator`\n\n\n\nTraining Details\n----------------", "### Training Dataset", "#### sentence-transformers/stsb\n\n\n* Dataset: sentence-transformers/stsb at ab7a5ac\n* Size: 5,749 training samples\n* Columns: `sentence1`, `sentence2`, and `score`\n* Approximate statistics based on the first 1000 samples:\n* Samples:\n* Loss: `Matryoshka2dLoss` with these parameters:", "### Evaluation Dataset", "#### sentence-transformers/stsb\n\n\n* Dataset: sentence-transformers/stsb at ab7a5ac\n* Size: 1,500 evaluation samples\n* Columns: `sentence1`, `sentence2`, and `score`\n* Approximate statistics based on the first 1000 samples:\n* Samples:\n* Loss: `Matryoshka2dLoss` with these parameters:", "### Training Hyperparameters", "#### Non-Default Hyperparameters\n\n\n* 'eval\\_strategy': steps\n* 'per\\_device\\_train\\_batch\\_size': 16\n* 'per\\_device\\_eval\\_batch\\_size': 16\n* 'num\\_train\\_epochs': 4\n* 'warmup\\_ratio': 0.1\n* 'fp16': True", "#### All Hyperparameters\n\n\nClick to expand\n* 'overwrite\\_output\\_dir': False\n* 'do\\_predict': False\n* 'eval\\_strategy': steps\n* 'prediction\\_loss\\_only': False\n* 'per\\_device\\_train\\_batch\\_size': 16\n* 'per\\_device\\_eval\\_batch\\_size': 16\n* 'per\\_gpu\\_train\\_batch\\_size': None\n* 'per\\_gpu\\_eval\\_batch\\_size': None\n* 'gradient\\_accumulation\\_steps': 1\n* 'eval\\_accumulation\\_steps': None\n* 'learning\\_rate': 5e-05\n* 'weight\\_decay': 0.0\n* 'adam\\_beta1': 0.9\n* 'adam\\_beta2': 0.999\n* 'adam\\_epsilon': 1e-08\n* 'max\\_grad\\_norm': 1.0\n* 'num\\_train\\_epochs': 4\n* 'max\\_steps': -1\n* 'lr\\_scheduler\\_type': linear\n* 'lr\\_scheduler\\_kwargs': {}\n* 'warmup\\_ratio': 0.1\n* 'warmup\\_steps': 0\n* 'log\\_level': passive\n* 'log\\_level\\_replica': warning\n* 'log\\_on\\_each\\_node': True\n* 'logging\\_nan\\_inf\\_filter': True\n* 'save\\_safetensors': True\n* 'save\\_on\\_each\\_node': False\n* 'save\\_only\\_model': False\n* 'no\\_cuda': False\n* 'use\\_cpu': False\n* 'use\\_mps\\_device': False\n* 'seed': 42\n* 'data\\_seed': None\n* 'jit\\_mode\\_eval': False\n* 'use\\_ipex': False\n* 'bf16': False\n* 'fp16': True\n* 'fp16\\_opt\\_level': O1\n* 'half\\_precision\\_backend': auto\n* 'bf16\\_full\\_eval': False\n* 'fp16\\_full\\_eval': False\n* 'tf32': None\n* 'local\\_rank': 0\n* 'ddp\\_backend': None\n* 'tpu\\_num\\_cores': None\n* 'tpu\\_metrics\\_debug': False\n* 'debug': []\n* 'dataloader\\_drop\\_last': False\n* 'dataloader\\_num\\_workers': 0\n* 'dataloader\\_prefetch\\_factor': None\n* 'past\\_index': -1\n* 'disable\\_tqdm': False\n* 'remove\\_unused\\_columns': True\n* 'label\\_names': None\n* 'load\\_best\\_model\\_at\\_end': False\n* 'ignore\\_data\\_skip': False\n* 'fsdp': []\n* 'fsdp\\_min\\_num\\_params': 0\n* 'fsdp\\_config': {'min\\_num\\_params': 0, 'xla': False, 'xla\\_fsdp\\_v2': False, 'xla\\_fsdp\\_grad\\_ckpt': False}\n* 'fsdp\\_transformer\\_layer\\_cls\\_to\\_wrap': None\n* 'accelerator\\_config': {'split\\_batches': False, 'dispatch\\_batches': None, 'even\\_batches': True, 'use\\_seedable\\_sampler': True, 'non\\_blocking': False, 'gradient\\_accumulation\\_kwargs': None}\n* 'deepspeed': None\n* 'label\\_smoothing\\_factor': 0.0\n* 'optim': adamw\\_torch\n* 'optim\\_args': None\n* 'adafactor': False\n* 'group\\_by\\_length': False\n* 'length\\_column\\_name': length\n* 'ddp\\_find\\_unused\\_parameters': None\n* 'ddp\\_bucket\\_cap\\_mb': None\n* 'ddp\\_broadcast\\_buffers': None\n* 'dataloader\\_pin\\_memory': True\n* 'dataloader\\_persistent\\_workers': False\n* 'skip\\_memory\\_metrics': True\n* 'use\\_legacy\\_prediction\\_loop': False\n* 'push\\_to\\_hub': False\n* 'resume\\_from\\_checkpoint': None\n* 'hub\\_model\\_id': None\n* 'hub\\_strategy': every\\_save\n* 'hub\\_private\\_repo': False\n* 'hub\\_always\\_push': False\n* 'gradient\\_checkpointing': False\n* 'gradient\\_checkpointing\\_kwargs': None\n* 'include\\_inputs\\_for\\_metrics': False\n* 'eval\\_do\\_concat\\_batches': True\n* 'fp16\\_backend': auto\n* 'push\\_to\\_hub\\_model\\_id': None\n* 'push\\_to\\_hub\\_organization': None\n* 'mp\\_parameters':\n* 'auto\\_find\\_batch\\_size': False\n* 'full\\_determinism': False\n* 'torchdynamo': None\n* 'ray\\_scope': last\n* 'ddp\\_timeout': 1800\n* 'torch\\_compile': False\n* 'torch\\_compile\\_backend': None\n* 'torch\\_compile\\_mode': None\n* 'dispatch\\_batches': None\n* 'split\\_batches': None\n* 'include\\_tokens\\_per\\_second': False\n* 'include\\_num\\_input\\_tokens\\_seen': False\n* 'neftune\\_noise\\_alpha': None\n* 'optim\\_target\\_modules': None\n* 'batch\\_sampler': batch\\_sampler\n* 'multi\\_dataset\\_batch\\_sampler': proportional", "### Training Logs", "### Environmental Impact\n\n\nCarbon emissions were measured using CodeCarbon.\n\n\n* Energy Consumed: 0.014 kWh\n* Carbon Emitted: 0.005 kg of CO2\n* Hours Used: 0.072 hours", "### Training Hardware\n\n\n* On Cloud: No\n* GPU Model: 1 x NVIDIA GeForce RTX 3090\n* CPU Model: 13th Gen Intel(R) Core(TM) i7-13700K\n* RAM Size: 31.78 GB", "### Framework Versions\n\n\n* Python: 3.11.6\n* Sentence Transformers: 3.0.0.dev0\n* Transformers: 4.41.0.dev0\n* PyTorch: 2.3.0+cu121\n* Accelerate: 0.26.1\n* Datasets: 2.18.0\n* Tokenizers: 0.19.1", "### BibTeX", "#### Sentence Transformers", "#### Matryoshka2dLoss", "#### MatryoshkaLoss", "#### CoSENTLoss" ]

[ "TAGS\n#sentence-transformers #safetensors #distilbert #sentence-similarity #feature-extraction #loss-Matryoshka2dLoss #loss-MatryoshkaLoss #loss-CoSENTLoss #en #arxiv-1908.10084 #arxiv-2402.14776 #arxiv-2205.13147 #base_model-distilbert/distilbert-base-uncased #model-index #co2_eq_emissions #endpoints_compatible #region-us \n", "### Model Description\n\n\n* Model Type: Sentence Transformer\n* Base model: distilbert/distilbert-base-uncased\n* Maximum Sequence Length: 512 tokens\n* Output Dimensionality: 768 tokens\n* Similarity Function: Cosine Similarity\n* Training Dataset:\n\t+ sentence-transformers/stsb\n* Language: en", "### Model Sources\n\n\n* Documentation: Sentence Transformers Documentation\n* Repository: Sentence Transformers on GitHub\n* Hugging Face: Sentence Transformers on Hugging Face", "### Full Model Architecture\n\n\nUsage\n-----", "### Direct Usage (Sentence Transformers)\n\n\nFirst install the Sentence Transformers library:\n\n\nThen you can load this model and run inference.\n\n\nEvaluation\n----------", "### Metrics", "#### Semantic Similarity\n\n\n* Dataset: 'sts-dev'\n* Evaluated with `EmbeddingSimilarityEvaluator`", "#### Semantic Similarity\n\n\n* Dataset: 'sts-test'\n* Evaluated with `EmbeddingSimilarityEvaluator`\n\n\n\nTraining Details\n----------------", "### Training Dataset", "#### sentence-transformers/stsb\n\n\n* Dataset: sentence-transformers/stsb at ab7a5ac\n* Size: 5,749 training samples\n* Columns: `sentence1`, `sentence2`, and `score`\n* Approximate statistics based on the first 1000 samples:\n* Samples:\n* Loss: `Matryoshka2dLoss` with these parameters:", "### Evaluation Dataset", "#### sentence-transformers/stsb\n\n\n* Dataset: sentence-transformers/stsb at ab7a5ac\n* Size: 1,500 evaluation samples\n* Columns: `sentence1`, `sentence2`, and `score`\n* Approximate statistics based on the first 1000 samples:\n* Samples:\n* Loss: `Matryoshka2dLoss` with these parameters:", "### Training Hyperparameters", "#### Non-Default Hyperparameters\n\n\n* 'eval\\_strategy': steps\n* 'per\\_device\\_train\\_batch\\_size': 16\n* 'per\\_device\\_eval\\_batch\\_size': 16\n* 'num\\_train\\_epochs': 4\n* 'warmup\\_ratio': 0.1\n* 'fp16': True", "#### All Hyperparameters\n\n\nClick to expand\n* 'overwrite\\_output\\_dir': False\n* 'do\\_predict': False\n* 'eval\\_strategy': steps\n* 'prediction\\_loss\\_only': False\n* 'per\\_device\\_train\\_batch\\_size': 16\n* 'per\\_device\\_eval\\_batch\\_size': 16\n* 'per\\_gpu\\_train\\_batch\\_size': None\n* 'per\\_gpu\\_eval\\_batch\\_size': None\n* 'gradient\\_accumulation\\_steps': 1\n* 'eval\\_accumulation\\_steps': None\n* 'learning\\_rate': 5e-05\n* 'weight\\_decay': 0.0\n* 'adam\\_beta1': 0.9\n* 'adam\\_beta2': 0.999\n* 'adam\\_epsilon': 1e-08\n* 'max\\_grad\\_norm': 1.0\n* 'num\\_train\\_epochs': 4\n* 'max\\_steps': -1\n* 'lr\\_scheduler\\_type': linear\n* 'lr\\_scheduler\\_kwargs': {}\n* 'warmup\\_ratio': 0.1\n* 'warmup\\_steps': 0\n* 'log\\_level': passive\n* 'log\\_level\\_replica': warning\n* 'log\\_on\\_each\\_node': True\n* 'logging\\_nan\\_inf\\_filter': True\n* 'save\\_safetensors': True\n* 'save\\_on\\_each\\_node': False\n* 'save\\_only\\_model': False\n* 'no\\_cuda': False\n* 'use\\_cpu': False\n* 'use\\_mps\\_device': False\n* 'seed': 42\n* 'data\\_seed': None\n* 'jit\\_mode\\_eval': False\n* 'use\\_ipex': False\n* 'bf16': False\n* 'fp16': True\n* 'fp16\\_opt\\_level': O1\n* 'half\\_precision\\_backend': auto\n* 'bf16\\_full\\_eval': False\n* 'fp16\\_full\\_eval': False\n* 'tf32': None\n* 'local\\_rank': 0\n* 'ddp\\_backend': None\n* 'tpu\\_num\\_cores': None\n* 'tpu\\_metrics\\_debug': False\n* 'debug': []\n* 'dataloader\\_drop\\_last': False\n* 'dataloader\\_num\\_workers': 0\n* 'dataloader\\_prefetch\\_factor': None\n* 'past\\_index': -1\n* 'disable\\_tqdm': False\n* 'remove\\_unused\\_columns': True\n* 'label\\_names': None\n* 'load\\_best\\_model\\_at\\_end': False\n* 'ignore\\_data\\_skip': False\n* 'fsdp': []\n* 'fsdp\\_min\\_num\\_params': 0\n* 'fsdp\\_config': {'min\\_num\\_params': 0, 'xla': False, 'xla\\_fsdp\\_v2': False, 'xla\\_fsdp\\_grad\\_ckpt': False}\n* 'fsdp\\_transformer\\_layer\\_cls\\_to\\_wrap': None\n* 'accelerator\\_config': {'split\\_batches': False, 'dispatch\\_batches': None, 'even\\_batches': True, 'use\\_seedable\\_sampler': True, 'non\\_blocking': False, 'gradient\\_accumulation\\_kwargs': None}\n* 'deepspeed': None\n* 'label\\_smoothing\\_factor': 0.0\n* 'optim': adamw\\_torch\n* 'optim\\_args': None\n* 'adafactor': False\n* 'group\\_by\\_length': False\n* 'length\\_column\\_name': length\n* 'ddp\\_find\\_unused\\_parameters': None\n* 'ddp\\_bucket\\_cap\\_mb': None\n* 'ddp\\_broadcast\\_buffers': None\n* 'dataloader\\_pin\\_memory': True\n* 'dataloader\\_persistent\\_workers': False\n* 'skip\\_memory\\_metrics': True\n* 'use\\_legacy\\_prediction\\_loop': False\n* 'push\\_to\\_hub': False\n* 'resume\\_from\\_checkpoint': None\n* 'hub\\_model\\_id': None\n* 'hub\\_strategy': every\\_save\n* 'hub\\_private\\_repo': False\n* 'hub\\_always\\_push': False\n* 'gradient\\_checkpointing': False\n* 'gradient\\_checkpointing\\_kwargs': None\n* 'include\\_inputs\\_for\\_metrics': False\n* 'eval\\_do\\_concat\\_batches': True\n* 'fp16\\_backend': auto\n* 'push\\_to\\_hub\\_model\\_id': None\n* 'push\\_to\\_hub\\_organization': None\n* 'mp\\_parameters':\n* 'auto\\_find\\_batch\\_size': False\n* 'full\\_determinism': False\n* 'torchdynamo': None\n* 'ray\\_scope': last\n* 'ddp\\_timeout': 1800\n* 'torch\\_compile': False\n* 'torch\\_compile\\_backend': None\n* 'torch\\_compile\\_mode': None\n* 'dispatch\\_batches': None\n* 'split\\_batches': None\n* 'include\\_tokens\\_per\\_second': False\n* 'include\\_num\\_input\\_tokens\\_seen': False\n* 'neftune\\_noise\\_alpha': None\n* 'optim\\_target\\_modules': None\n* 'batch\\_sampler': batch\\_sampler\n* 'multi\\_dataset\\_batch\\_sampler': proportional", "### Training Logs", "### Environmental Impact\n\n\nCarbon emissions were measured using CodeCarbon.\n\n\n* Energy Consumed: 0.014 kWh\n* Carbon Emitted: 0.005 kg of CO2\n* Hours Used: 0.072 hours", "### Training Hardware\n\n\n* On Cloud: No\n* GPU Model: 1 x NVIDIA GeForce RTX 3090\n* CPU Model: 13th Gen Intel(R) Core(TM) i7-13700K\n* RAM Size: 31.78 GB", "### Framework Versions\n\n\n* Python: 3.11.6\n* Sentence Transformers: 3.0.0.dev0\n* Transformers: 4.41.0.dev0\n* PyTorch: 2.3.0+cu121\n* Accelerate: 0.26.1\n* Datasets: 2.18.0\n* Tokenizers: 0.19.1", "### BibTeX", "#### Sentence Transformers", "#### Matryoshka2dLoss", "#### MatryoshkaLoss", "#### CoSENTLoss" ]

[ 117, 69, 29, 12, 37, 5, 30, 48, 6, 81, 6, 80, 8, 92, 1494, 5, 44, 55, 79, 6, 6, 11, 9, 8 ]

[ "TAGS\n#sentence-transformers #safetensors #distilbert #sentence-similarity #feature-extraction #loss-Matryoshka2dLoss #loss-MatryoshkaLoss #loss-CoSENTLoss #en #arxiv-1908.10084 #arxiv-2402.14776 #arxiv-2205.13147 #base_model-distilbert/distilbert-base-uncased #model-index #co2_eq_emissions #endpoints_compatible #region-us \n### Model Description\n\n\n* Model Type: Sentence Transformer\n* Base model: distilbert/distilbert-base-uncased\n* Maximum Sequence Length: 512 tokens\n* Output Dimensionality: 768 tokens\n* Similarity Function: Cosine Similarity\n* Training Dataset:\n\t+ sentence-transformers/stsb\n* Language: en### Model Sources\n\n\n* Documentation: Sentence Transformers Documentation\n* Repository: Sentence Transformers on GitHub\n* Hugging Face: Sentence Transformers on Hugging Face### Full Model Architecture\n\n\nUsage\n-----### Direct Usage (Sentence Transformers)\n\n\nFirst install the Sentence Transformers library:\n\n\nThen you can load this model and run inference.\n\n\nEvaluation\n----------### Metrics#### Semantic Similarity\n\n\n* Dataset: 'sts-dev'\n* Evaluated with `EmbeddingSimilarityEvaluator`#### Semantic Similarity\n\n\n* Dataset: 'sts-test'\n* Evaluated with `EmbeddingSimilarityEvaluator`\n\n\n\nTraining Details\n----------------### Training Dataset#### sentence-transformers/stsb\n\n\n* Dataset: sentence-transformers/stsb at ab7a5ac\n* Size: 5,749 training samples\n* Columns: `sentence1`, `sentence2`, and `score`\n* Approximate statistics based on the first 1000 samples:\n* Samples:\n* Loss: `Matryoshka2dLoss` with these parameters:### Evaluation Dataset#### sentence-transformers/stsb\n\n\n* Dataset: sentence-transformers/stsb at ab7a5ac\n* Size: 1,500 evaluation samples\n* Columns: `sentence1`, `sentence2`, and `score`\n* Approximate statistics based on the first 1000 samples:\n* Samples:\n* Loss: `Matryoshka2dLoss` with these parameters:### Training Hyperparameters#### Non-Default Hyperparameters\n\n\n* 'eval\\_strategy': steps\n* 'per\\_device\\_train\\_batch\\_size': 16\n* 'per\\_device\\_eval\\_batch\\_size': 16\n* 'num\\_train\\_epochs': 4\n* 'warmup\\_ratio': 0.1\n* 'fp16': True#### All Hyperparameters\n\n\nClick to expand\n* 'overwrite\\_output\\_dir': False\n* 'do\\_predict': False\n* 'eval\\_strategy': steps\n* 'prediction\\_loss\\_only': False\n* 'per\\_device\\_train\\_batch\\_size': 16\n* 'per\\_device\\_eval\\_batch\\_size': 16\n* 'per\\_gpu\\_train\\_batch\\_size': None\n* 'per\\_gpu\\_eval\\_batch\\_size': None\n* 'gradient\\_accumulation\\_steps': 1\n* 'eval\\_accumulation\\_steps': None\n* 'learning\\_rate': 5e-05\n* 'weight\\_decay': 0.0\n* 'adam\\_beta1': 0.9\n* 'adam\\_beta2': 0.999\n* 'adam\\_epsilon': 1e-08\n* 'max\\_grad\\_norm': 1.0\n* 'num\\_train\\_epochs': 4\n* 'max\\_steps': -1\n* 'lr\\_scheduler\\_type': linear\n* 'lr\\_scheduler\\_kwargs': {}\n* 'warmup\\_ratio': 0.1\n* 'warmup\\_steps': 0\n* 'log\\_level': passive\n* 'log\\_level\\_replica': warning\n* 'log\\_on\\_each\\_node': True\n* 'logging\\_nan\\_inf\\_filter': True\n* 'save\\_safetensors': True\n* 'save\\_on\\_each\\_node': False\n* 'save\\_only\\_model': False\n* 'no\\_cuda': False\n* 'use\\_cpu': False\n* 'use\\_mps\\_device': False\n* 'seed': 42\n* 'data\\_seed': None\n* 'jit\\_mode\\_eval': False\n* 'use\\_ipex': False\n* 'bf16': False\n* 'fp16': True\n* 'fp16\\_opt\\_level': O1\n* 'half\\_precision\\_backend': auto\n* 'bf16\\_full\\_eval': False\n* 'fp16\\_full\\_eval': False\n* 'tf32': None\n* 'local\\_rank': 0\n* 'ddp\\_backend': None\n* 'tpu\\_num\\_cores': None\n* 'tpu\\_metrics\\_debug': False\n* 'debug': []\n* 'dataloader\\_drop\\_last': False\n* 'dataloader\\_num\\_workers': 0\n* 'dataloader\\_prefetch\\_factor': None\n* 'past\\_index': -1\n* 'disable\\_tqdm': False\n* 'remove\\_unused\\_columns': True\n* 'label\\_names': None\n* 'load\\_best\\_model\\_at\\_end': False\n* 'ignore\\_data\\_skip': False\n* 'fsdp': []\n* 'fsdp\\_min\\_num\\_params': 0\n* 'fsdp\\_config': {'min\\_num\\_params': 0, 'xla': False, 'xla\\_fsdp\\_v2': False, 'xla\\_fsdp\\_grad\\_ckpt': False}\n* 'fsdp\\_transformer\\_layer\\_cls\\_to\\_wrap': None\n* 'accelerator\\_config': {'split\\_batches': False, 'dispatch\\_batches': None, 'even\\_batches': True, 'use\\_seedable\\_sampler': True, 'non\\_blocking': False, 'gradient\\_accumulation\\_kwargs': None}\n* 'deepspeed': None\n* 'label\\_smoothing\\_factor': 0.0\n* 'optim': adamw\\_torch\n* 'optim\\_args': None\n* 'adafactor': False\n* 'group\\_by\\_length': False\n* 'length\\_column\\_name': length\n* 'ddp\\_find\\_unused\\_parameters': None\n* 'ddp\\_bucket\\_cap\\_mb': None\n* 'ddp\\_broadcast\\_buffers': None\n* 'dataloader\\_pin\\_memory': True\n* 'dataloader\\_persistent\\_workers': False\n* 'skip\\_memory\\_metrics': True\n* 'use\\_legacy\\_prediction\\_loop': False\n* 'push\\_to\\_hub': False\n* 'resume\\_from\\_checkpoint': None\n* 'hub\\_model\\_id': None\n* 'hub\\_strategy': every\\_save\n* 'hub\\_private\\_repo': False\n* 'hub\\_always\\_push': False\n* 'gradient\\_checkpointing': False\n* 'gradient\\_checkpointing\\_kwargs': None\n* 'include\\_inputs\\_for\\_metrics': False\n* 'eval\\_do\\_concat\\_batches': True\n* 'fp16\\_backend': auto\n* 'push\\_to\\_hub\\_model\\_id': None\n* 'push\\_to\\_hub\\_organization': None\n* 'mp\\_parameters':\n* 'auto\\_find\\_batch\\_size': False\n* 'full\\_determinism': False\n* 'torchdynamo': None\n* 'ray\\_scope': last\n* 'ddp\\_timeout': 1800\n* 'torch\\_compile': False\n* 'torch\\_compile\\_backend': None\n* 'torch\\_compile\\_mode': None\n* 'dispatch\\_batches': None\n* 'split\\_batches': None\n* 'include\\_tokens\\_per\\_second': False\n* 'include\\_num\\_input\\_tokens\\_seen': False\n* 'neftune\\_noise\\_alpha': None\n* 'optim\\_target\\_modules': None\n* 'batch\\_sampler': batch\\_sampler\n* 'multi\\_dataset\\_batch\\_sampler': proportional### Training Logs### Environmental Impact\n\n\nCarbon emissions were measured using CodeCarbon.\n\n\n* Energy Consumed: 0.014 kWh\n* Carbon Emitted: 0.005 kg of CO2\n* Hours Used: 0.072 hours### Training Hardware\n\n\n* On Cloud: No\n* GPU Model: 1 x NVIDIA GeForce RTX 3090\n* CPU Model: 13th Gen Intel(R) Core(TM) i7-13700K\n* RAM Size: 31.78 GB### Framework Versions\n\n\n* Python: 3.11.6\n* Sentence Transformers: 3.0.0.dev0\n* Transformers: 4.41.0.dev0\n* PyTorch: 2.3.0+cu121\n* Accelerate: 0.26.1\n* Datasets: 2.18.0\n* Tokenizers: 0.19.1### BibTeX#### Sentence Transformers#### Matryoshka2dLoss#### MatryoshkaLoss#### CoSENTLoss" ]

[ "transformers", "safetensors", "mistral", "text-generation", "unsloth", "phi3", "phi", "conversational", "en", "license:llama2", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #unsloth #phi3 #phi #conversational #en #license-llama2 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n" ]

[ 54 ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #unsloth #phi3 #phi #conversational #en #license-llama2 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n" ]

[ "stable-baselines3", "SpaceInvadersNoFrameskip-v4", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]

[]

[]

[ "# DQN Agent playing SpaceInvadersNoFrameskip-v4\nThis is a trained model of a DQN agent playing SpaceInvadersNoFrameskip-v4\nusing the stable-baselines3 library\nand the RL Zoo.\n\nThe RL Zoo is a training framework for Stable Baselines3\nreinforcement learning agents,\nwith hyperparameter optimization and pre-trained agents included.", "## Usage (with SB3 RL Zoo)\n\nRL Zoo: URL\nSB3: URL\nSB3 Contrib: URL\n\nInstall the RL Zoo (with SB3 and SB3-Contrib):\n\n\n\n\nIf you installed the RL Zoo3 via pip ('pip install rl_zoo3'), from anywhere you can do:", "## Training (with the RL Zoo)", "## Hyperparameters", "# Environment Arguments" ]

[ "TAGS\n#stable-baselines3 #SpaceInvadersNoFrameskip-v4 #deep-reinforcement-learning #reinforcement-learning #model-index #region-us \n", "# DQN Agent playing SpaceInvadersNoFrameskip-v4\nThis is a trained model of a DQN agent playing SpaceInvadersNoFrameskip-v4\nusing the stable-baselines3 library\nand the RL Zoo.\n\nThe RL Zoo is a training framework for Stable Baselines3\nreinforcement learning agents,\nwith hyperparameter optimization and pre-trained agents included.", "## Usage (with SB3 RL Zoo)\n\nRL Zoo: URL\nSB3: URL\nSB3 Contrib: URL\n\nInstall the RL Zoo (with SB3 and SB3-Contrib):\n\n\n\n\nIf you installed the RL Zoo3 via pip ('pip install rl_zoo3'), from anywhere you can do:", "## Training (with the RL Zoo)", "## Hyperparameters", "# Environment Arguments" ]

[ 37, 81, 76, 10, 6, 3 ]

[ "TAGS\n#stable-baselines3 #SpaceInvadersNoFrameskip-v4 #deep-reinforcement-learning #reinforcement-learning #model-index #region-us \n# DQN Agent playing SpaceInvadersNoFrameskip-v4\nThis is a trained model of a DQN agent playing SpaceInvadersNoFrameskip-v4\nusing the stable-baselines3 library\nand the RL Zoo.\n\nThe RL Zoo is a training framework for Stable Baselines3\nreinforcement learning agents,\nwith hyperparameter optimization and pre-trained agents included.## Usage (with SB3 RL Zoo)\n\nRL Zoo: URL\nSB3: URL\nSB3 Contrib: URL\n\nInstall the RL Zoo (with SB3 and SB3-Contrib):\n\n\n\n\nIf you installed the RL Zoo3 via pip ('pip install rl_zoo3'), from anywhere you can do:## Training (with the RL Zoo)## Hyperparameters# Environment Arguments" ]

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

[]

[ "en" ]

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

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

[ 64, 80 ]

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

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

[]

[]

[ "# finetuning-sentiment-model-3000-samples\n\nThis model is a fine-tuned version of distilbert-base-uncased on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- Loss: 0.7678\n- Accuracy: 0.71\n- F1: 0.7100", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 2e-05\n- train_batch_size: 16\n- eval_batch_size: 16\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 2", "### Training results", "### Framework versions\n\n- Transformers 4.40.1\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #distilbert #text-classification #generated_from_trainer #base_model-distilbert-base-uncased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "# finetuning-sentiment-model-3000-samples\n\nThis model is a fine-tuned version of distilbert-base-uncased on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- Loss: 0.7678\n- Accuracy: 0.71\n- F1: 0.7100", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 2e-05\n- train_batch_size: 16\n- eval_batch_size: 16\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 2", "### Training results", "### Framework versions\n\n- Transformers 4.40.1\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ 59, 67, 7, 9, 9, 4, 93, 5, 44 ]

[ "TAGS\n#transformers #tensorboard #safetensors #distilbert #text-classification #generated_from_trainer #base_model-distilbert-base-uncased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n# finetuning-sentiment-model-3000-samples\n\nThis model is a fine-tuned version of distilbert-base-uncased on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- Loss: 0.7678\n- Accuracy: 0.71\n- F1: 0.7100## Model description\n\nMore information needed## Intended uses & limitations\n\nMore information needed## Training and evaluation data\n\nMore information needed## Training procedure### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 2e-05\n- train_batch_size: 16\n- eval_batch_size: 16\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 2### Training results### Framework versions\n\n- Transformers 4.40.1\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "transformers", "tensorboard", "safetensors", "llama", "text-generation", "trl", "sft", "generated_from_trainer", "conversational", "dataset:generator", "base_model:meta-llama/Meta-Llama-3-8B-Instruct", "license:other", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# Meta-Llama-3-8B-Instruct_fictional_arc_Korean_v2\n\nThis model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the generator dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 1\n- eval_batch_size: 2\n- seed: 42\n- gradient_accumulation_steps: 16\n- total_train_batch_size: 16\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 36", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #tensorboard #safetensors #llama #text-generation #trl #sft #generated_from_trainer #conversational #dataset-generator #base_model-meta-llama/Meta-Llama-3-8B-Instruct #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Meta-Llama-3-8B-Instruct_fictional_arc_Korean_v2\n\nThis model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the generator dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 1\n- eval_batch_size: 2\n- seed: 42\n- gradient_accumulation_steps: 16\n- total_train_batch_size: 16\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 36", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ 83, 54, 7, 9, 9, 4, 111, 5, 40 ]

[ "TAGS\n#transformers #tensorboard #safetensors #llama #text-generation #trl #sft #generated_from_trainer #conversational #dataset-generator #base_model-meta-llama/Meta-Llama-3-8B-Instruct #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# Meta-Llama-3-8B-Instruct_fictional_arc_Korean_v2\n\nThis model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the generator dataset.## Model description\n\nMore information needed## Intended uses & limitations\n\nMore information needed## Training and evaluation data\n\nMore information needed## Training procedure### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 1\n- eval_batch_size: 2\n- seed: 42\n- gradient_accumulation_steps: 16\n- total_train_batch_size: 16\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 36### Training results### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "fastai", "region:us", "has_space" ]

[]

[]

[ "# Amazing!\n\n Congratulations on hosting your fastai model on the Hugging Face Hub!", "# Some next steps\n1. Fill out this model card with more information (see the template below and the documentation here)!\n\n2. Create a demo in Gradio or Streamlit using Spaces (documentation here).\n\n3. Join the fastai community on the Fastai Discord!\n\nGreetings fellow fastlearner ! Don't forget to delete this content from your model card.\n\n\n---", "# Model card", "## Model description\nMore information needed", "## Intended uses & limitations\nMore information needed", "## Training and evaluation data\nMore information needed" ]

[ "TAGS\n#fastai #region-us #has_space \n", "# Amazing!\n\n Congratulations on hosting your fastai model on the Hugging Face Hub!", "# Some next steps\n1. Fill out this model card with more information (see the template below and the documentation here)!\n\n2. Create a demo in Gradio or Streamlit using Spaces (documentation here).\n\n3. Join the fastai community on the Fastai Discord!\n\nGreetings fellow fastlearner ! Don't forget to delete this content from your model card.\n\n\n---", "# Model card", "## Model description\nMore information needed", "## Intended uses & limitations\nMore information needed", "## Training and evaluation data\nMore information needed" ]

[ 12, 16, 82, 3, 7, 9, 9 ]

[ "TAGS\n#fastai #region-us #has_space \n# Amazing!\n\n Congratulations on hosting your fastai model on the Hugging Face Hub!# Some next steps\n1. Fill out this model card with more information (see the template below and the documentation here)!\n\n2. Create a demo in Gradio or Streamlit using Spaces (documentation here).\n\n3. Join the fastai community on the Fastai Discord!\n\nGreetings fellow fastlearner ! Don't forget to delete this content from your model card.\n\n\n---# Model card## Model description\nMore information needed## Intended uses & limitations\nMore information needed## Training and evaluation data\nMore information needed" ]

[ "transformers", "safetensors", "bert", "text-classification", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[ "1910.09700" ]

[]

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

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

[ 37, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

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

[ "gguf", "zh", "en", "license:apache-2.0", "region:us" ]

[]

[ "zh", "en" ]

[]

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

[ 22 ]

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

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

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 5", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #distilbert #text-classification #generated_from_trainer #base_model-distilbert-base-uncased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 5", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ 59, 101, 5, 44 ]

[ "TAGS\n#transformers #tensorboard #safetensors #distilbert #text-classification #generated_from_trainer #base_model-distilbert-base-uncased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 5### Training results### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

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

[ "1910.09700" ]

[]

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

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

[ 26, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

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

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

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: [Intellectus AI Labs]\n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: [Text Generation]\n- Language(s) (NLP): [Python]\n- License: \n- Finetuned from model [optional]: [Mixtral 8x7B]", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: [Intellectus AI Labs]\n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: [Text Generation]\n- Language(s) (NLP): [Python]\n- License: \n- Finetuned from model [optional]: [Mixtral 8x7B]", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 26, 6, 4, 96, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: [Intellectus AI Labs]\n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: [Text Generation]\n- Language(s) (NLP): [Python]\n- License: \n- Finetuned from model [optional]: [Mixtral 8x7B]### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.## How to Get Started with the Model\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "doi:10.57967/hf/2134", "region:us" ]

[]

[]

[ "# rakib72642/Unilever_Dump_Pepsodent", "# Higgingface : URL", "# Setup Global API\n\nsudo apt install iproute2 -y && sudo apt install wget -y && sudo apt install nano -y && sudo apt install unzip -y && sudo apt install unzip -y && apt install nvtop -y && sudo apt-get install git-lfs -y && sudo apt-get update && sudo apt-get install libgl1 -y && sudo apt install curl -y && curl -s URL | sudo tee /etc/apt/URL.d/URL >/dev/null && echo \"deb URL buster main\" | sudo tee /etc/apt/URL.d/URL && sudo apt update && sudo apt install ngrok -y && sudo apt update && sudo apt upgrade -y && ngrok config add-authtoken 2Qm8hS1zPhVXiLjEdlI4738tLzF_2QJwGJMK5oTbQD33QSVXS && sudo apt update && sudo apt upgrade -y && ngrok http --domain=URL 4545", "# Setup Local API\n\ngit clone URL && cd Unilever_Dump_Pepsodent && pip install -r URL && sudo apt update && sudo apt upgrade -y && python URL\n\ncd Unilever_Dump_Pepsodent && python URL\n\nhypercorn api:app --bind 127.0.0.1:4545 --workers 4", "# ngrok config add-authtoken 2Qm8hS1zPhVXiLjEdlI4738tLzF_2QJwGJMK5oTbQD33QSVXS && sudo apt update && sudo apt upgrade -y && ngrok http --domain=URL 4545" ]

[ "TAGS\n#doi-10.57967/hf/2134 #region-us \n", "# rakib72642/Unilever_Dump_Pepsodent", "# Higgingface : URL", "# Setup Global API\n\nsudo apt install iproute2 -y && sudo apt install wget -y && sudo apt install nano -y && sudo apt install unzip -y && sudo apt install unzip -y && apt install nvtop -y && sudo apt-get install git-lfs -y && sudo apt-get update && sudo apt-get install libgl1 -y && sudo apt install curl -y && curl -s URL | sudo tee /etc/apt/URL.d/URL >/dev/null && echo \"deb URL buster main\" | sudo tee /etc/apt/URL.d/URL && sudo apt update && sudo apt install ngrok -y && sudo apt update && sudo apt upgrade -y && ngrok config add-authtoken 2Qm8hS1zPhVXiLjEdlI4738tLzF_2QJwGJMK5oTbQD33QSVXS && sudo apt update && sudo apt upgrade -y && ngrok http --domain=URL 4545", "# Setup Local API\n\ngit clone URL && cd Unilever_Dump_Pepsodent && pip install -r URL && sudo apt update && sudo apt upgrade -y && python URL\n\ncd Unilever_Dump_Pepsodent && python URL\n\nhypercorn api:app --bind 127.0.0.1:4545 --workers 4", "# ngrok config add-authtoken 2Qm8hS1zPhVXiLjEdlI4738tLzF_2QJwGJMK5oTbQD33QSVXS && sudo apt update && sudo apt upgrade -y && ngrok http --domain=URL 4545" ]

[ 20, 17, 7, 272, 86, 76 ]

[ "TAGS\n#doi-10.57967/hf/2134 #region-us \n# rakib72642/Unilever_Dump_Pepsodent# Higgingface : URL# Setup Global API\n\nsudo apt install iproute2 -y && sudo apt install wget -y && sudo apt install nano -y && sudo apt install unzip -y && sudo apt install unzip -y && apt install nvtop -y && sudo apt-get install git-lfs -y && sudo apt-get update && sudo apt-get install libgl1 -y && sudo apt install curl -y && curl -s URL | sudo tee /etc/apt/URL.d/URL >/dev/null && echo \"deb URL buster main\" | sudo tee /etc/apt/URL.d/URL && sudo apt update && sudo apt install ngrok -y && sudo apt update && sudo apt upgrade -y && ngrok config add-authtoken 2Qm8hS1zPhVXiLjEdlI4738tLzF_2QJwGJMK5oTbQD33QSVXS && sudo apt update && sudo apt upgrade -y && ngrok http --domain=URL 4545# Setup Local API\n\ngit clone URL && cd Unilever_Dump_Pepsodent && pip install -r URL && sudo apt update && sudo apt upgrade -y && python URL\n\ncd Unilever_Dump_Pepsodent && python URL\n\nhypercorn api:app --bind 127.0.0.1:4545 --workers 4# ngrok config add-authtoken 2Qm8hS1zPhVXiLjEdlI4738tLzF_2QJwGJMK5oTbQD33QSVXS && sudo apt update && sudo apt upgrade -y && ngrok http --domain=URL 4545" ]

[ "region:us" ]

[]

[]

[]

[ "TAGS\n#region-us \n" ]

[ 5 ]

[ "TAGS\n#region-us \n" ]

[ "region:us" ]

[]

[]

[]

[ "TAGS\n#region-us \n" ]

[ 5 ]

[ "TAGS\n#region-us \n" ]

[ "transformers", "safetensors", "mistral", "text-generation", "unsloth", "phi3", "phi", "conversational", "en", "license:llama2", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #unsloth #phi3 #phi #conversational #en #license-llama2 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n" ]

[ 58 ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #unsloth #phi3 #phi #conversational #en #license-llama2 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:facebook/nllb-200-distilled-1.3B", "license:cc-by-nc-4.0", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\n* num\\_epochs: 5", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.39.3\n* Pytorch 2.1.0+cu121\n* Datasets 2.19.0\n* Tokenizers 0.15.0" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-facebook/nllb-200-distilled-1.3B #license-cc-by-nc-4.0 #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\n* num\\_epochs: 5", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.39.3\n* Pytorch 2.1.0+cu121\n* Datasets 2.19.0\n* Tokenizers 0.15.0" ]

[ 50, 103, 5, 52 ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-facebook/nllb-200-distilled-1.3B #license-cc-by-nc-4.0 #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\n* num\\_epochs: 5### Training results### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.39.3\n* Pytorch 2.1.0+cu121\n* Datasets 2.19.0\n* Tokenizers 0.15.0" ]

[ "diffusers", "stable-diffusion-xl", "stable-diffusion-xl-diffusers", "diffusers-training", "text-to-image", "lora", "template:sd-lora", "base_model:stabilityai/stable-diffusion-xl-base-1.0", "license:openrail++", "region:us" ]

[]

[]

[ "# SDXL LoRA DreamBooth - aarashfeizi/jean-francois-godbout-batch2-repeats3-rank16-snrNone\n\n<Gallery />", "## Model description", "### These are aarashfeizi/jean-francois-godbout-batch2-repeats3-rank16-snrNone LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.", "## Download model", "### Use it with UIs such as AUTOMATIC1111, Comfy UI, SD.Next, Invoke\n\n- LoRA: download '/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch2-repeats3-rank16-snrNone.safetensors' here .\n - Place it on your 'models/Lora' folder.\n - On AUTOMATIC1111, load the LoRA by adding '<lora:/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch2-repeats3-rank16-snrNone:1>' to your prompt. On ComfyUI just load it as a regular LoRA.\n- *Embeddings*: download '/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch2-repeats3-rank16-snrNone_emb.safetensors' here .\n - Place it on it on your 'embeddings' folder\n - Use it by adding '/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch2-repeats3-rank16-snrNone_emb' to your prompt. For example, 'A photo of /home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch2-repeats3-rank16-snrNone_emb'\n (you need both the LoRA and the embeddings as they were trained together for this LoRA)", "## Use it with the diffusers library\n\n\n\nFor more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers", "## Trigger words\n\nTo trigger image generation of trained concept(or concepts) replace each concept identifier in you prompt with the new inserted tokens:\n\nto trigger concept 'TOK' → use '<s0><s1>' in your prompt", "## Details\nAll Files & versions.\n\nThe weights were trained using diffusers Advanced Dreambooth Training Script.\n\nLoRA for the text encoder was enabled. False.\n\nPivotal tuning was enabled: True.\n\nSpecial VAE used for training: madebyollin/sdxl-vae-fp16-fix." ]

[ "TAGS\n#diffusers #stable-diffusion-xl #stable-diffusion-xl-diffusers #diffusers-training #text-to-image #lora #template-sd-lora #base_model-stabilityai/stable-diffusion-xl-base-1.0 #license-openrail++ #region-us \n", "# SDXL LoRA DreamBooth - aarashfeizi/jean-francois-godbout-batch2-repeats3-rank16-snrNone\n\n<Gallery />", "## Model description", "### These are aarashfeizi/jean-francois-godbout-batch2-repeats3-rank16-snrNone LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.", "## Download model", "### Use it with UIs such as AUTOMATIC1111, Comfy UI, SD.Next, Invoke\n\n- LoRA: download '/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch2-repeats3-rank16-snrNone.safetensors' here .\n - Place it on your 'models/Lora' folder.\n - On AUTOMATIC1111, load the LoRA by adding '<lora:/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch2-repeats3-rank16-snrNone:1>' to your prompt. On ComfyUI just load it as a regular LoRA.\n- *Embeddings*: download '/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch2-repeats3-rank16-snrNone_emb.safetensors' here .\n - Place it on it on your 'embeddings' folder\n - Use it by adding '/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch2-repeats3-rank16-snrNone_emb' to your prompt. For example, 'A photo of /home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch2-repeats3-rank16-snrNone_emb'\n (you need both the LoRA and the embeddings as they were trained together for this LoRA)", "## Use it with the diffusers library\n\n\n\nFor more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers", "## Trigger words\n\nTo trigger image generation of trained concept(or concepts) replace each concept identifier in you prompt with the new inserted tokens:\n\nto trigger concept 'TOK' → use '<s0><s1>' in your prompt", "## Details\nAll Files & versions.\n\nThe weights were trained using diffusers Advanced Dreambooth Training Script.\n\nLoRA for the text encoder was enabled. False.\n\nPivotal tuning was enabled: True.\n\nSpecial VAE used for training: madebyollin/sdxl-vae-fp16-fix." ]

[ 70, 42, 4, 54, 4, 376, 34, 53, 67 ]

[ "TAGS\n#diffusers #stable-diffusion-xl #stable-diffusion-xl-diffusers #diffusers-training #text-to-image #lora #template-sd-lora #base_model-stabilityai/stable-diffusion-xl-base-1.0 #license-openrail++ #region-us \n# SDXL LoRA DreamBooth - aarashfeizi/jean-francois-godbout-batch2-repeats3-rank16-snrNone\n\n<Gallery />## Model description### These are aarashfeizi/jean-francois-godbout-batch2-repeats3-rank16-snrNone LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.## Download model### Use it with UIs such as AUTOMATIC1111, Comfy UI, SD.Next, Invoke\n\n- LoRA: download '/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch2-repeats3-rank16-snrNone.safetensors' here .\n - Place it on your 'models/Lora' folder.\n - On AUTOMATIC1111, load the LoRA by adding '<lora:/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch2-repeats3-rank16-snrNone:1>' to your prompt. On ComfyUI just load it as a regular LoRA.\n- *Embeddings*: download '/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch2-repeats3-rank16-snrNone_emb.safetensors' here .\n - Place it on it on your 'embeddings' folder\n - Use it by adding '/home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch2-repeats3-rank16-snrNone_emb' to your prompt. For example, 'A photo of /home/mila/f/feiziaar/scratch/dreambooth-outputs/jean-francois-godbout-batch2-repeats3-rank16-snrNone_emb'\n (you need both the LoRA and the embeddings as they were trained together for this LoRA)## Use it with the diffusers library\n\n\n\nFor more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers## Trigger words\n\nTo trigger image generation of trained concept(or concepts) replace each concept identifier in you prompt with the new inserted tokens:\n\nto trigger concept 'TOK' → use '<s0><s1>' in your prompt## Details\nAll Files & versions.\n\nThe weights were trained using diffusers Advanced Dreambooth Training Script.\n\nLoRA for the text encoder was enabled. False.\n\nPivotal tuning was enabled: True.\n\nSpecial VAE used for training: madebyollin/sdxl-vae-fp16-fix." ]