Datasets:

---

ftopal

/

huggingface-models

like 0

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

[]

[]

[]

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

[ "transformers", "safetensors", "distilbert", "token-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: 8\n* eval\\_batch\\_size: 4\n* seed: 42\n* gradient\\_accumulation\\_steps: 16\n* total\\_train\\_batch\\_size: 128\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 17", "### Training results", "### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.1.2\n* Datasets 2.18.0\n* Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #safetensors #distilbert #token-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: 8\n* eval\\_batch\\_size: 4\n* seed: 42\n* gradient\\_accumulation\\_steps: 16\n* total\\_train\\_batch\\_size: 128\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 17", "### Training results", "### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.1.2\n* Datasets 2.18.0\n* Tokenizers 0.15.2" ]

[ "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" ]

[ "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" ]

[ "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" ]

[ "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" ]

[ "transformers", "pytorch", "llama", "text-generation", "en", "de", "dataset:oscar-corpus/OSCAR-2301", "dataset:wikipedia", "dataset:bjoernp/tagesschau-2018-2023", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[ "en", "de" ]

[ "# LAION LeoLM: Linguistically Enhanced Open Language Model\nMeet LeoLM, the first open and commercially available German Foundation Language Model built on Llama-2. \nOur models extend Llama-2's capabilities into German through continued pretraining on a large corpus of German-language and mostly locality specific text.\nThanks to a compute grant at HessianAI's new supercomputer 42, we release two foundation models trained with 8k context length,\n'LeoLM/leo-hessianai-7b' and 'LeoLM/leo-hessianai-13b' under the Llama-2 community license (70b also coming soon! ).\nWith this release, we hope to bring a new wave of opportunities to German open-source and commercial LLM research and accelerate adoption.\nRead our [blog post]() or our paper (preprint coming soon) for more details!\n\n*A project by Björn Plüster and Christoph Schuhmann in collaboration with LAION and HessianAI.*", "## Model Details\n- Finetuned from: meta-llama/Llama-2-7b-hf\n- Model type: Causal decoder-only transformer language model\n- Language: English and German\n- License: LLAMA 2 COMMUNITY LICENSE AGREEMENT\n- Contact: LAION Discord or Björn Plüster", "## Use in Transformers\nFirst install direct dependencies:\n\nIf you want faster inference using flash-attention2, you need to install these dependencies:\n\nThen load the model in transformers:", "## Training parameters\n!training_parameters", "## Benchmarks\n!benchmarks" ]

[ "TAGS\n#transformers #pytorch #llama #text-generation #en #de #dataset-oscar-corpus/OSCAR-2301 #dataset-wikipedia #dataset-bjoernp/tagesschau-2018-2023 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# LAION LeoLM: Linguistically Enhanced Open Language Model\nMeet LeoLM, the first open and commercially available German Foundation Language Model built on Llama-2. \nOur models extend Llama-2's capabilities into German through continued pretraining on a large corpus of German-language and mostly locality specific text.\nThanks to a compute grant at HessianAI's new supercomputer 42, we release two foundation models trained with 8k context length,\n'LeoLM/leo-hessianai-7b' and 'LeoLM/leo-hessianai-13b' under the Llama-2 community license (70b also coming soon! ).\nWith this release, we hope to bring a new wave of opportunities to German open-source and commercial LLM research and accelerate adoption.\nRead our [blog post]() or our paper (preprint coming soon) for more details!\n\n*A project by Björn Plüster and Christoph Schuhmann in collaboration with LAION and HessianAI.*", "## Model Details\n- Finetuned from: meta-llama/Llama-2-7b-hf\n- Model type: Causal decoder-only transformer language model\n- Language: English and German\n- License: LLAMA 2 COMMUNITY LICENSE AGREEMENT\n- Contact: LAION Discord or Björn Plüster", "## Use in Transformers\nFirst install direct dependencies:\n\nIf you want faster inference using flash-attention2, you need to install these dependencies:\n\nThen load the model in transformers:", "## Training parameters\n!training_parameters", "## Benchmarks\n!benchmarks" ]

[ "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" ]

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

[]

[]

[ "# AutoTrain SDXL LoRA DreamBooth - satyam23/lora_model\n\n<Gallery />", "## Model description\n\nThese are satyam23/lora_model LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.\n\nThe weights were trained using DreamBooth.\n\nLoRA for the text encoder was enabled: False.\n\nSpecial VAE used for training: None.", "## Trigger words\n\nYou should use photo of a sks person 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 #autotrain #stable-diffusion-xl #stable-diffusion-xl-diffusers #text-to-image #lora #template-sd-lora #base_model-stabilityai/stable-diffusion-xl-base-1.0 #license-openrail++ #region-us \n", "# AutoTrain SDXL LoRA DreamBooth - satyam23/lora_model\n\n<Gallery />", "## Model description\n\nThese are satyam23/lora_model LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.\n\nThe weights were trained using DreamBooth.\n\nLoRA for the text encoder was enabled: False.\n\nSpecial VAE used for training: None.", "## Trigger words\n\nYou should use photo of a sks person 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." ]

[ "peft", "safetensors", "llama", "axolotl", "generated_from_trainer", "base_model:nlpai-lab/KULLM3", "license:apache-2.0", "4-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* distributed\\_type: multi-GPU\n* num\\_devices: 4\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 32\n* total\\_eval\\_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: 100\n* num\\_epochs: 10", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.40.0.dev0\n* Pytorch 2.1.2+cu121\n* Datasets 2.15.0\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #llama #axolotl #generated_from_trainer #base_model-nlpai-lab/KULLM3 #license-apache-2.0 #4-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* distributed\\_type: multi-GPU\n* num\\_devices: 4\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 32\n* total\\_eval\\_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: 100\n* num\\_epochs: 10", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.40.0.dev0\n* Pytorch 2.1.2+cu121\n* Datasets 2.15.0\n* Tokenizers 0.15.2" ]

[ "transformers", "safetensors", "text-generation-inference", "unsloth", "llama", "trl", "en", "base_model:unsloth/llama-2-7b-bnb-4bit", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[ "# Uploaded model\n\n- Developed by: Mandalor09\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-2-7b-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-2-7b-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us \n", "# Uploaded model\n\n- Developed by: Mandalor09\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-2-7b-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", "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" ]

[ "transformers", "safetensors", "llama", "text-generation", "llama-3", "bagel", "conversational", "dataset:ai2_arc", "dataset:allenai/ultrafeedback_binarized_cleaned", "dataset:argilla/distilabel-intel-orca-dpo-pairs", "dataset:jondurbin/airoboros-3.2", "dataset:codeparrot/apps", "dataset:facebook/belebele", "dataset:bluemoon-fandom-1-1-rp-cleaned", "dataset:boolq", "dataset:camel-ai/biology", "dataset:camel-ai/chemistry", "dataset:camel-ai/math", "dataset:camel-ai/physics", "dataset:jondurbin/contextual-dpo-v0.1", "dataset:jondurbin/gutenberg-dpo-v0.1", "dataset:jondurbin/py-dpo-v0.1", "dataset:jondurbin/truthy-dpo-v0.1", "dataset:LDJnr/Capybara", "dataset:jondurbin/cinematika-v0.1", "dataset:WizardLM/WizardLM_evol_instruct_70k", "dataset:glaiveai/glaive-function-calling-v2", "dataset:grimulkan/LimaRP-augmented", "dataset:lmsys/lmsys-chat-1m", "dataset:ParisNeo/lollms_aware_dataset", "dataset:TIGER-Lab/MathInstruct", "dataset:Muennighoff/natural-instructions", "dataset:openbookqa", "dataset:kingbri/PIPPA-shareGPT", "dataset:piqa", "dataset:Vezora/Tested-22k-Python-Alpaca", "dataset:ropes", "dataset:cakiki/rosetta-code", "dataset:Open-Orca/SlimOrca", "dataset:b-mc2/sql-create-context", "dataset:squad_v2", "dataset:mattpscott/airoboros-summarization", "dataset:migtissera/Synthia-v1.3", "dataset:unalignment/toxic-dpo-v0.2", "dataset:WhiteRabbitNeo/WRN-Chapter-1", "dataset:WhiteRabbitNeo/WRN-Chapter-2", "dataset:winogrande", "base_model:meta-llama/Meta-Llama-3-8B", "license:other", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "### Data sources\n\n\nThere are many data sources used in the bagel models. See URL for more information.\n\n\n***Only train splits are used, and a decontamination by cosine similarity is performed at the end as a sanity check against common benchmarks. If you don't know the difference between train and test, please learn.***\n\n\n\nSFT data sources\n* ai2\\_arc\n\t+ Abstraction and reasoning dataset, useful in measuring \"intelligence\" to a certain extent.\n* airoboros\n\t+ Variety of categories of synthetic instructions generated by gpt-4.\n* apps\n\t+ Python coding dataset with 10k problems.\n* belebele\n\t+ Multi-lingual reading comprehension dataset.\n* bluemoon\n\t+ Roleplay data scraped from Bluemoon, then cleaned and formatted as ShareGPT.\n* boolq\n\t+ Corpus of yes/no questions (which can be surprisingly difficult for AI to answer apparently?)\n* camel-ai biology\n\t+ GPT-4 generated biology instructions.\n* camel-ai chemistry\n\t+ GPT-4 generated chemistryinstructions.\n* camel-ai math\n\t+ GPT-4 generated math instructions.\n* camel-ai physics\n\t+ GPT-4 generated physics instructions.\n* capybara\n\t+ Multi-turn dataset used to create the capybara models.\n* cinematika (instruction and plain text)\n\t+ RP-style data synthesized from movie scripts so the model isn't quite as boring as it otherwise would be.\n* emobank\n\t+ Emotion annotations using the Valence-Arousal-Domninance scheme.\n* evol-instruct\n\t+ WizardLM's evol instruct 70k dataset.\n* glaive-function-calling-v2\n\t+ GlaiveAI function calling dataset.\n* gutenberg (plain text)\n\t+ Books/plain text, again to make the model less boring, only a handful of examples supported by chapterize\n* limarp-augmented\n\t+ Augmented and further modified version of LimaRP\n* lmsys\\_chat\\_1m (only gpt-4 items, also used for DPO)\n\t+ Chats collected by the lmsys chat arena, containing a wide variety of chats with various models.\n* lollms\n\t+ LoLLMs question answering dataset by ParisNeo, with helpful question answer pairs for using LoLLMs.\n* mathinstruct\n\t+ Composite dataset with a variety of math-related tasks and problem/question formats.\n* natural\\_instructions\n\t+ Millions of instructions from 1600+ task categories (sampled down substantially, stratified by task type)\n* openbookqa\n\t+ Question answering dataset.\n* pippa\n\t+ Deduped version of PIPPA in ShareGPT format.\n* piqa\n\t+ Phyiscal interaction question answering.\n* python\\_alpaca\n\t+ Python instruction response pairs, validated as functional.\n* ropes\n\t+ Reasoning Over PAragraph Effects in Situations - enhances ability to apply knowledge from a passage of text to a new situation.\n* rosetta\\_code\n\t+ Code problems and solutions in a variety of programming languages taken from URL.\n* slimorca\n\t+ Collection of ~500k gpt-4 verified chats from OpenOrca.\n* sql-create-context\n\t+ SQL-targeted dataset, combining WikiSQL and Spider.\n* squad\\_v2\n\t+ Contextual question answering (RAG).\n* airoboros-summarization\n\t+ Combination of various summarization datasets, formatted into the airoboros context-obedient format.\n* synthia\n\t+ GPT-4 generated data using advanced prompting from Migel Tissera.\n* whiterabbitneo chapter 1 and chapter 2\n\t+ Offensive cybersecurity dataset by WhiteRabbitNeo/Migel Tissera\n* winogrande\n\t+ Fill in the blank style prompts.\n\n\n\n\nDPO data sources\n* airoboros 3.2 vs airoboros m2.0\n\t+ The creative/writing tasks from airoboros-2.2.1 were re-generated using gpt4-0314 and a custom prompt to get longer, more creative, less clichè responses for airoboros 3.1, so we can use the shorter/boring version as the \"rejected\" value and the rerolled response as \"chosen\"\n* contextual-dpo\n\t+ Contextual prompt/response dataset using the airoboros context-obedient question answering format.\n* helpsteer\n\t+ Really neat dataset provided by the folks at NVidia with human annotation across a variety of metrics. Only items with the highest \"correctness\" value were used for DPO here, with the highest scoring output as \"chosen\" and random lower scoring value as \"rejected\"\n* distilabel\\_orca\\_dpo\\_pairs\n\t+ Another interesting dataset, originally by Intel, enhanced by argilla with distilabel which provides various DPO pairs generated from prompts included in the SlimOrca dataset.\n* gutenberg-dpo\n\t+ DPO pairs meant to increase the models novel writing abilities, using public domain books from URL\n* py-dpo\n\t+ Python DPO dataset (based on the SFT python\\_alpaca dataset above)\n* toxic-dpo\n\t+ ***highly toxic and potentially illegal content!*** De-censorship, for academic and lawful purposes only, of course. Generated by llama-2-70b via prompt engineering.\n* truthy\n\t+ DPO pairs meant to increase truthfulness of the model, e.g. common misconceptions, differentiate between AI assistants and roleplayed human in terms of corporeal awareness/locality/etc.\n* ultrafeedback\n\t+ One of the bits of magic behind the Zephyr model. Only the items with a chosen score of 8 or higher were included.\n\n\n\nPrompt formatting\n-----------------\n\n\nThis model uses the llama-3-instruct prompt template, and is provided in the tokenizer config. You can use the 'apply\\_chat\\_template' method to accurate format prompts, e.g.:\n\n\nPrompting strategies\n--------------------\n\n\n\n\n**Context obedient question answering**\n \n\n This is a special prompt format made specifically for answering questions from provided context, e.g. RAG.\n \nBy obedient, I mean the model was trained to ignore what it thinks it knows, and uses the context to answer the question. The model was also tuned to limit the values to the provided context as much as possible to reduce hallucinations.\n\n\nThe format for a closed-context prompt is as follows:\n\n\nIt's also helpful to add \"Don't make up answers if you don't know.\" to your instruction block to make sure if the context is completely unrelated it doesn't make something up.\n\n\n*The **only** prompts that need this closed context formating are closed-context instructions. Normal questions/instructions do not!*\n\n\nI know it's a bit verbose and annoying, but after much trial and error, using these explicit delimiters helps the model understand where to find the responses and how to associate specific sources with it.\n\n\n* 'BEGININPUT' - denotes a new input block\n* 'BEGINCONTEXT' - denotes the block of context (metadata key/value pairs) to associate with the current input block\n* 'ENDCONTEXT' - denotes the end of the metadata block for the current input\n* [text] - Insert whatever text you want for the input block, as many paragraphs as can fit in the context.\n* 'ENDINPUT' - denotes the end of the current input block\n* [repeat as many input blocks in this format as you want]\n* 'BEGININSTRUCTION' - denotes the start of the list (or one) instruction(s) to respond to for all of the input blocks above.\n* [instruction(s)]\n* 'ENDINSTRUCTION' - denotes the end of instruction set\n\n\nIt sometimes works without 'ENDINSTRUCTION', but by explicitly including that in the prompt, the model better understands that all of the instructions in the block should be responded to.\n\n\n**Use a very low temperature!**\n\n\nHere's a trivial, but important example to prove the point:\n\n\nAnd the response:\n\n\nYou can also add an instruction similar to the following, to have a more deterministic response when the context doesn't provide an answer to the question:\n\n\n\n\n\n**Summarization**\n \n\n Same prompt format as context obedient question answering, but meant for summarization tasks.\n \nSummarization is primarily fine-tuned with this dataset, which uses the same format as above, e.g.:\n\n\n\n\n\n**Function calling**\n \n\n Two primary formats for prompting for function calling use-cases.\n \n There are two function-calling related formats used in fine-tuning this model.\n1. Providing an input and list of possible functions within the instruction (from airoboros dataset), e.g.:\n\n\nPrompt:\n\n\nResponse:\n\n\n2. GlaiveAI function calling, which uses special tags and adds function specs in the system prompt:\n\n\nPrompt:\n\n\nResponse:\n\n\nThen, you re-prompt the model with the function response.\n\n\nWhich has a response of:\n\n\n\n\n\n**Chain of thought**\n \n\n Useful for having the model propose multiple possible responses, reasoning through each, and selecting a final, most probable answer.\n \nYou can ask for several possible responses to a given problem, with a ranking and final answer selection.\n\n\nExample prompt:\n\n\nExample response:\n\n\n\n\n\n**reWOO style function planning/execution**\n \n\n Useful for a longer, complex chain of function calls without having to continue re-prompting manually.\n \nThe model now supports execution planning for complex instructions that would require making use of several tools. The output is just the plan, you must implement a mechanism to parse the output and actually call the functions!\n\n\nExample prompt:\n\n\nResponse:\n\n\nFor this to be useful, you'd have to parse the output plan text, and implement/call each of the functions. This is just pseudo-code, completely untested off the top of my head, and obviously would requiring full implementation + hardening:\n\n\n\n\n\n**Creating roleplay character cards**\n \n\n Useful in creating YAML formatted character cards for roleplay/creative writing tasks.\n \nIncluded in the cinematika dataset, you can create YAML formatted character cards easily, e.g.:\n\n\n\n\n\n**Conversational memory creation**\n \n\n Summarization style prompt to create memories from previous chat turns, useful when context becomes long.\n \nAlso part of cinematika dataset, you can use a summarization style prompt to create memories from previous chat turns, which can then be used in a RAG system to populate your prompts when context becomes too long.\n\n\n\n\n\n**Novel writing, chapter by chapter**\n \n\n Based on the public domain books in project Gutenberg, this style of prompting creates very long, novel style writing.\n \nWriting the first chapter:\n\n\nWriting subsequent chapters:\n\n\nIn other words, write the first chapter, then use a summarization prompt for it, then include the summary in the next chapter's prompt.\n\n\n\n\n\n**Boolean questions**\n \n\n For content filtering and other use-cases which only require a true/false response.\n \nThe prompts in the fine-tuning dataset are formatted as follows:\n\n\nThe model will then, theoretically, respond with only a single word.\n\n\n\n\n\n**SQL queries**\n \n\n Generating SQL queries given a table definition.\n \nFor example:\n\n\nResponse:\n\n\n\n\n\n**Emotion detection**\n \n\n You can produce Valence-Arousal-Dominance scores for a given input text, which can in turn be mapped to human emotions (e.g. with k-means clustering on V and A)\n \nExample prompt:\n\n\nResponse:\n\n\n\n\n\n**Multi-character chat director**\n \n\n Select which NPC should speak next.\n \nThe scope of the entire multi-NPC chat mechanism is a bit too large to include here, but essentially you want separate prompts for each character, as well as a \"director\" prompt which selects which NPC should speak next.\n\n\nSystem prompt:\n\n\nFirst round instruction, i.e. selecting who should speak first:\n\n\nResponse for the first round:\n\n\nNow, you'd prompt the model for a response from Aria.\n\n\nAfterwards, you'd add Aria's response to the \"director\" prompt to see who speaks next, e.g.:\n\n\n\nRenting instances to run the model\n----------------------------------", "### Massed Compute Virtual Machine\n\n\nMassed Compute has created a Virtual Machine (VM) pre-loaded with TGI and Text Generation WebUI.\n\n\n1. For this model, create an account in Massed Compute. When renting a Virtual Machine use the code 'JonDurbin' for 50% your rental.\n2. After you created your account update your billing and navigate to the deploy page.\n3. Select the following\n\t* GPU Type: A6000\n\t* GPU Quantity: 1\n\t* Category: Creator\n\t* Image: Jon Durbin\n\t* Coupon Code: JonDurbin\n4. Deploy the VM!\n5. Navigate to 'Running Instances' to retrieve instructions to login to the VM\n6. Once inside the VM, open the terminal and run 'volume=$PWD/data'\n7. Run 'model=jondurbin/bagel-8b-v1.0'\n8. 'sudo docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data URL --model-id $model'\n9. The model will take some time to load...\n10. Once loaded the model will be available on port 8080\n\n\nSample command within the VM\n\n\nYou can also access the model from outside the VM\n\n\nFor assistance with the VM join the Massed Compute Discord Server", "### URL\n\n\nLatitude has h100 instances available (as of today, 2024-02-08) for $3/hr! A single h100 works great for this model, though you probably want to decrease the context length from 200k to 8k or 16k.\n\n\nSupport me\n----------\n\n\n* URL\n* ETH 0xce914eAFC2fe52FdceE59565Dd92c06f776fcb11\n* BTC bc1qdwuth4vlg8x37ggntlxu5cjfwgmdy5zaa7pswf" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #llama-3 #bagel #conversational #dataset-ai2_arc #dataset-allenai/ultrafeedback_binarized_cleaned #dataset-argilla/distilabel-intel-orca-dpo-pairs #dataset-jondurbin/airoboros-3.2 #dataset-codeparrot/apps #dataset-facebook/belebele #dataset-bluemoon-fandom-1-1-rp-cleaned #dataset-boolq #dataset-camel-ai/biology #dataset-camel-ai/chemistry #dataset-camel-ai/math #dataset-camel-ai/physics #dataset-jondurbin/contextual-dpo-v0.1 #dataset-jondurbin/gutenberg-dpo-v0.1 #dataset-jondurbin/py-dpo-v0.1 #dataset-jondurbin/truthy-dpo-v0.1 #dataset-LDJnr/Capybara #dataset-jondurbin/cinematika-v0.1 #dataset-WizardLM/WizardLM_evol_instruct_70k #dataset-glaiveai/glaive-function-calling-v2 #dataset-grimulkan/LimaRP-augmented #dataset-lmsys/lmsys-chat-1m #dataset-ParisNeo/lollms_aware_dataset #dataset-TIGER-Lab/MathInstruct #dataset-Muennighoff/natural-instructions #dataset-openbookqa #dataset-kingbri/PIPPA-shareGPT #dataset-piqa #dataset-Vezora/Tested-22k-Python-Alpaca #dataset-ropes #dataset-cakiki/rosetta-code #dataset-Open-Orca/SlimOrca #dataset-b-mc2/sql-create-context #dataset-squad_v2 #dataset-mattpscott/airoboros-summarization #dataset-migtissera/Synthia-v1.3 #dataset-unalignment/toxic-dpo-v0.2 #dataset-WhiteRabbitNeo/WRN-Chapter-1 #dataset-WhiteRabbitNeo/WRN-Chapter-2 #dataset-winogrande #base_model-meta-llama/Meta-Llama-3-8B #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "### Data sources\n\n\nThere are many data sources used in the bagel models. See URL for more information.\n\n\n***Only train splits are used, and a decontamination by cosine similarity is performed at the end as a sanity check against common benchmarks. If you don't know the difference between train and test, please learn.***\n\n\n\nSFT data sources\n* ai2\\_arc\n\t+ Abstraction and reasoning dataset, useful in measuring \"intelligence\" to a certain extent.\n* airoboros\n\t+ Variety of categories of synthetic instructions generated by gpt-4.\n* apps\n\t+ Python coding dataset with 10k problems.\n* belebele\n\t+ Multi-lingual reading comprehension dataset.\n* bluemoon\n\t+ Roleplay data scraped from Bluemoon, then cleaned and formatted as ShareGPT.\n* boolq\n\t+ Corpus of yes/no questions (which can be surprisingly difficult for AI to answer apparently?)\n* camel-ai biology\n\t+ GPT-4 generated biology instructions.\n* camel-ai chemistry\n\t+ GPT-4 generated chemistryinstructions.\n* camel-ai math\n\t+ GPT-4 generated math instructions.\n* camel-ai physics\n\t+ GPT-4 generated physics instructions.\n* capybara\n\t+ Multi-turn dataset used to create the capybara models.\n* cinematika (instruction and plain text)\n\t+ RP-style data synthesized from movie scripts so the model isn't quite as boring as it otherwise would be.\n* emobank\n\t+ Emotion annotations using the Valence-Arousal-Domninance scheme.\n* evol-instruct\n\t+ WizardLM's evol instruct 70k dataset.\n* glaive-function-calling-v2\n\t+ GlaiveAI function calling dataset.\n* gutenberg (plain text)\n\t+ Books/plain text, again to make the model less boring, only a handful of examples supported by chapterize\n* limarp-augmented\n\t+ Augmented and further modified version of LimaRP\n* lmsys\\_chat\\_1m (only gpt-4 items, also used for DPO)\n\t+ Chats collected by the lmsys chat arena, containing a wide variety of chats with various models.\n* lollms\n\t+ LoLLMs question answering dataset by ParisNeo, with helpful question answer pairs for using LoLLMs.\n* mathinstruct\n\t+ Composite dataset with a variety of math-related tasks and problem/question formats.\n* natural\\_instructions\n\t+ Millions of instructions from 1600+ task categories (sampled down substantially, stratified by task type)\n* openbookqa\n\t+ Question answering dataset.\n* pippa\n\t+ Deduped version of PIPPA in ShareGPT format.\n* piqa\n\t+ Phyiscal interaction question answering.\n* python\\_alpaca\n\t+ Python instruction response pairs, validated as functional.\n* ropes\n\t+ Reasoning Over PAragraph Effects in Situations - enhances ability to apply knowledge from a passage of text to a new situation.\n* rosetta\\_code\n\t+ Code problems and solutions in a variety of programming languages taken from URL.\n* slimorca\n\t+ Collection of ~500k gpt-4 verified chats from OpenOrca.\n* sql-create-context\n\t+ SQL-targeted dataset, combining WikiSQL and Spider.\n* squad\\_v2\n\t+ Contextual question answering (RAG).\n* airoboros-summarization\n\t+ Combination of various summarization datasets, formatted into the airoboros context-obedient format.\n* synthia\n\t+ GPT-4 generated data using advanced prompting from Migel Tissera.\n* whiterabbitneo chapter 1 and chapter 2\n\t+ Offensive cybersecurity dataset by WhiteRabbitNeo/Migel Tissera\n* winogrande\n\t+ Fill in the blank style prompts.\n\n\n\n\nDPO data sources\n* airoboros 3.2 vs airoboros m2.0\n\t+ The creative/writing tasks from airoboros-2.2.1 were re-generated using gpt4-0314 and a custom prompt to get longer, more creative, less clichè responses for airoboros 3.1, so we can use the shorter/boring version as the \"rejected\" value and the rerolled response as \"chosen\"\n* contextual-dpo\n\t+ Contextual prompt/response dataset using the airoboros context-obedient question answering format.\n* helpsteer\n\t+ Really neat dataset provided by the folks at NVidia with human annotation across a variety of metrics. Only items with the highest \"correctness\" value were used for DPO here, with the highest scoring output as \"chosen\" and random lower scoring value as \"rejected\"\n* distilabel\\_orca\\_dpo\\_pairs\n\t+ Another interesting dataset, originally by Intel, enhanced by argilla with distilabel which provides various DPO pairs generated from prompts included in the SlimOrca dataset.\n* gutenberg-dpo\n\t+ DPO pairs meant to increase the models novel writing abilities, using public domain books from URL\n* py-dpo\n\t+ Python DPO dataset (based on the SFT python\\_alpaca dataset above)\n* toxic-dpo\n\t+ ***highly toxic and potentially illegal content!*** De-censorship, for academic and lawful purposes only, of course. Generated by llama-2-70b via prompt engineering.\n* truthy\n\t+ DPO pairs meant to increase truthfulness of the model, e.g. common misconceptions, differentiate between AI assistants and roleplayed human in terms of corporeal awareness/locality/etc.\n* ultrafeedback\n\t+ One of the bits of magic behind the Zephyr model. Only the items with a chosen score of 8 or higher were included.\n\n\n\nPrompt formatting\n-----------------\n\n\nThis model uses the llama-3-instruct prompt template, and is provided in the tokenizer config. You can use the 'apply\\_chat\\_template' method to accurate format prompts, e.g.:\n\n\nPrompting strategies\n--------------------\n\n\n\n\n**Context obedient question answering**\n \n\n This is a special prompt format made specifically for answering questions from provided context, e.g. RAG.\n \nBy obedient, I mean the model was trained to ignore what it thinks it knows, and uses the context to answer the question. The model was also tuned to limit the values to the provided context as much as possible to reduce hallucinations.\n\n\nThe format for a closed-context prompt is as follows:\n\n\nIt's also helpful to add \"Don't make up answers if you don't know.\" to your instruction block to make sure if the context is completely unrelated it doesn't make something up.\n\n\n*The **only** prompts that need this closed context formating are closed-context instructions. Normal questions/instructions do not!*\n\n\nI know it's a bit verbose and annoying, but after much trial and error, using these explicit delimiters helps the model understand where to find the responses and how to associate specific sources with it.\n\n\n* 'BEGININPUT' - denotes a new input block\n* 'BEGINCONTEXT' - denotes the block of context (metadata key/value pairs) to associate with the current input block\n* 'ENDCONTEXT' - denotes the end of the metadata block for the current input\n* [text] - Insert whatever text you want for the input block, as many paragraphs as can fit in the context.\n* 'ENDINPUT' - denotes the end of the current input block\n* [repeat as many input blocks in this format as you want]\n* 'BEGININSTRUCTION' - denotes the start of the list (or one) instruction(s) to respond to for all of the input blocks above.\n* [instruction(s)]\n* 'ENDINSTRUCTION' - denotes the end of instruction set\n\n\nIt sometimes works without 'ENDINSTRUCTION', but by explicitly including that in the prompt, the model better understands that all of the instructions in the block should be responded to.\n\n\n**Use a very low temperature!**\n\n\nHere's a trivial, but important example to prove the point:\n\n\nAnd the response:\n\n\nYou can also add an instruction similar to the following, to have a more deterministic response when the context doesn't provide an answer to the question:\n\n\n\n\n\n**Summarization**\n \n\n Same prompt format as context obedient question answering, but meant for summarization tasks.\n \nSummarization is primarily fine-tuned with this dataset, which uses the same format as above, e.g.:\n\n\n\n\n\n**Function calling**\n \n\n Two primary formats for prompting for function calling use-cases.\n \n There are two function-calling related formats used in fine-tuning this model.\n1. Providing an input and list of possible functions within the instruction (from airoboros dataset), e.g.:\n\n\nPrompt:\n\n\nResponse:\n\n\n2. GlaiveAI function calling, which uses special tags and adds function specs in the system prompt:\n\n\nPrompt:\n\n\nResponse:\n\n\nThen, you re-prompt the model with the function response.\n\n\nWhich has a response of:\n\n\n\n\n\n**Chain of thought**\n \n\n Useful for having the model propose multiple possible responses, reasoning through each, and selecting a final, most probable answer.\n \nYou can ask for several possible responses to a given problem, with a ranking and final answer selection.\n\n\nExample prompt:\n\n\nExample response:\n\n\n\n\n\n**reWOO style function planning/execution**\n \n\n Useful for a longer, complex chain of function calls without having to continue re-prompting manually.\n \nThe model now supports execution planning for complex instructions that would require making use of several tools. The output is just the plan, you must implement a mechanism to parse the output and actually call the functions!\n\n\nExample prompt:\n\n\nResponse:\n\n\nFor this to be useful, you'd have to parse the output plan text, and implement/call each of the functions. This is just pseudo-code, completely untested off the top of my head, and obviously would requiring full implementation + hardening:\n\n\n\n\n\n**Creating roleplay character cards**\n \n\n Useful in creating YAML formatted character cards for roleplay/creative writing tasks.\n \nIncluded in the cinematika dataset, you can create YAML formatted character cards easily, e.g.:\n\n\n\n\n\n**Conversational memory creation**\n \n\n Summarization style prompt to create memories from previous chat turns, useful when context becomes long.\n \nAlso part of cinematika dataset, you can use a summarization style prompt to create memories from previous chat turns, which can then be used in a RAG system to populate your prompts when context becomes too long.\n\n\n\n\n\n**Novel writing, chapter by chapter**\n \n\n Based on the public domain books in project Gutenberg, this style of prompting creates very long, novel style writing.\n \nWriting the first chapter:\n\n\nWriting subsequent chapters:\n\n\nIn other words, write the first chapter, then use a summarization prompt for it, then include the summary in the next chapter's prompt.\n\n\n\n\n\n**Boolean questions**\n \n\n For content filtering and other use-cases which only require a true/false response.\n \nThe prompts in the fine-tuning dataset are formatted as follows:\n\n\nThe model will then, theoretically, respond with only a single word.\n\n\n\n\n\n**SQL queries**\n \n\n Generating SQL queries given a table definition.\n \nFor example:\n\n\nResponse:\n\n\n\n\n\n**Emotion detection**\n \n\n You can produce Valence-Arousal-Dominance scores for a given input text, which can in turn be mapped to human emotions (e.g. with k-means clustering on V and A)\n \nExample prompt:\n\n\nResponse:\n\n\n\n\n\n**Multi-character chat director**\n \n\n Select which NPC should speak next.\n \nThe scope of the entire multi-NPC chat mechanism is a bit too large to include here, but essentially you want separate prompts for each character, as well as a \"director\" prompt which selects which NPC should speak next.\n\n\nSystem prompt:\n\n\nFirst round instruction, i.e. selecting who should speak first:\n\n\nResponse for the first round:\n\n\nNow, you'd prompt the model for a response from Aria.\n\n\nAfterwards, you'd add Aria's response to the \"director\" prompt to see who speaks next, e.g.:\n\n\n\nRenting instances to run the model\n----------------------------------", "### Massed Compute Virtual Machine\n\n\nMassed Compute has created a Virtual Machine (VM) pre-loaded with TGI and Text Generation WebUI.\n\n\n1. For this model, create an account in Massed Compute. When renting a Virtual Machine use the code 'JonDurbin' for 50% your rental.\n2. After you created your account update your billing and navigate to the deploy page.\n3. Select the following\n\t* GPU Type: A6000\n\t* GPU Quantity: 1\n\t* Category: Creator\n\t* Image: Jon Durbin\n\t* Coupon Code: JonDurbin\n4. Deploy the VM!\n5. Navigate to 'Running Instances' to retrieve instructions to login to the VM\n6. Once inside the VM, open the terminal and run 'volume=$PWD/data'\n7. Run 'model=jondurbin/bagel-8b-v1.0'\n8. 'sudo docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data URL --model-id $model'\n9. The model will take some time to load...\n10. Once loaded the model will be available on port 8080\n\n\nSample command within the VM\n\n\nYou can also access the model from outside the VM\n\n\nFor assistance with the VM join the Massed Compute Discord Server", "### URL\n\n\nLatitude has h100 instances available (as of today, 2024-02-08) for $3/hr! A single h100 works great for this model, though you probably want to decrease the context length from 200k to 8k or 16k.\n\n\nSupport me\n----------\n\n\n* URL\n* ETH 0xce914eAFC2fe52FdceE59565Dd92c06f776fcb11\n* BTC bc1qdwuth4vlg8x37ggntlxu5cjfwgmdy5zaa7pswf" ]

[ "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: rahulrajpv\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: rahulrajpv\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", "safetensors", "mixtral", "text-generation", "merge", "mergekit", "lazymergekit", "conversational", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# Turkish-moe\n\nTurkish-moe is a merge of the following models using mergekit:", "## Configuration" ]

[ "TAGS\n#transformers #safetensors #mixtral #text-generation #merge #mergekit #lazymergekit #conversational #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Turkish-moe\n\nTurkish-moe is a merge of the following models using mergekit:", "## Configuration" ]

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

[]

[ "en" ]

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

[ "TAGS\n#transformers #gguf #llama #text-generation-inference #unsloth #en #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us \n", "# Uploaded model\n\n- Developed by: richie-ghost\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\"/>" ]

[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]

[]

[]

[ "# PPO Agent playing LunarLander-v2\nThis is a trained model of a PPO agent playing LunarLander-v2\nusing the stable-baselines3 library.", "## Usage (with Stable-baselines3)\nTODO: Add your code" ]

[ "TAGS\n#stable-baselines3 #LunarLander-v2 #deep-reinforcement-learning #reinforcement-learning #model-index #region-us \n", "# PPO Agent playing LunarLander-v2\nThis is a trained model of a PPO agent playing LunarLander-v2\nusing the stable-baselines3 library.", "## Usage (with Stable-baselines3)\nTODO: Add your code" ]

[ "gguf", "llama-cpp", "gguf-my-repo", "en", "dataset:cerebras/SlimPajama-627B", "dataset:bigcode/starcoderdata", "license:apache-2.0", "region:us" ]

[]

[ "en" ]

[ "# Bakanayatsu/TinyLlama-1.1B-intermediate-step-1431k-3T-Q8_0-GGUF\nThis model was converted to GGUF format from 'TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ "TAGS\n#gguf #llama-cpp #gguf-my-repo #en #dataset-cerebras/SlimPajama-627B #dataset-bigcode/starcoderdata #license-apache-2.0 #region-us \n", "# Bakanayatsu/TinyLlama-1.1B-intermediate-step-1431k-3T-Q8_0-GGUF\nThis model was converted to GGUF format from 'TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ "region:us" ]

[]

[]

[]

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

[ "transformers", "safetensors", "bert", "token-classification", "generated_from_trainer", "base_model:google-bert/bert-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: 10", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #safetensors #bert #token-classification #generated_from_trainer #base_model-google-bert/bert-base-uncased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 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: 10", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "transformers", "gguf", "mergekit", "merge", "en", "base_model:Azazelle/L3-RP_io", "license:llama3", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #mergekit #merge #en #base_model-Azazelle/L3-RP_io #license-llama3 #endpoints_compatible #region-us \n" ]

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

[]

[]

[ "# Huh Yun-jin XL\n\n<Gallery />", "## Model description \n\nDon&#39;t use for NSFW purposes,\nDon&#39;t Post on any social media platforms.", "## Trigger words\n\nYou should use 'Yunjin' 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-stabilityai/stable-diffusion-xl-base-1.0 #region-us \n", "# Huh Yun-jin XL\n\n<Gallery />", "## Model description \n\nDon&#39;t use for NSFW purposes,\nDon&#39;t Post on any social media platforms.", "## Trigger words\n\nYou should use 'Yunjin' 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", "tf", "bert", "text-classification", "generated_from_keras_callback", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "# hate_speech\n\nThis model was trained from scratch on an unknown dataset.\nIt achieves the following results on the evaluation set:", "## 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- optimizer: None\n- training_precision: float32", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- TensorFlow 2.16.1\n- Datasets 2.18.0\n- Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tf #bert #text-classification #generated_from_keras_callback #autotrain_compatible #endpoints_compatible #region-us \n", "# hate_speech\n\nThis model was trained from scratch on an unknown dataset.\nIt achieves the following results on the evaluation set:", "## 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- optimizer: None\n- training_precision: float32", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- TensorFlow 2.16.1\n- Datasets 2.18.0\n- Tokenizers 0.19.1" ]

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

[ "transformers", "tensorboard", "safetensors", "gpt_neox", "text-classification", "generated_from_trainer", "base_model:EleutherAI/pythia-31m", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# robust_llm_pythia-31m_mz-130_IMDB_n-its-10-seed-2\n\nThis model is a fine-tuned version of EleutherAI/pythia-31m on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 2\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.1\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #tensorboard #safetensors #gpt_neox #text-classification #generated_from_trainer #base_model-EleutherAI/pythia-31m #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# robust_llm_pythia-31m_mz-130_IMDB_n-its-10-seed-2\n\nThis model is a fine-tuned version of EleutherAI/pythia-31m on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 2\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.1\n- Datasets 2.18.0\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" ]

[ "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" ]

[ "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" ]

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

[ "transformers", "pytorch", "llama", "text-generation", "en", "de", "dataset:oscar-corpus/OSCAR-2301", "dataset:wikipedia", "dataset:bjoernp/tagesschau-2018-2023", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[ "en", "de" ]

[ "# LAION LeoLM: Linguistically Enhanced Open Language Model\nMeet LeoLM, the first open and commercially available German Foundation Language Model built on Llama-2. \nOur models extend Llama-2's capabilities into German through continued pretraining on a large corpus of German-language and mostly locality specific text.\nThanks to a compute grant at HessianAI's new supercomputer 42, we release two foundation models trained with 8k context length,\n'LeoLM/leo-hessianai-7b' and 'LeoLM/leo-hessianai-13b' under the Llama-2 community license (70b also coming soon! ).\nWith this release, we hope to bring a new wave of opportunities to German open-source and commercial LLM research and accelerate adoption.\nRead our [blog post]() or our paper (preprint coming soon) for more details!\n\n*A project by Björn Plüster and Christoph Schuhmann in collaboration with LAION and HessianAI.*", "## Model Details\n- Finetuned from: meta-llama/Llama-2-13b-hf\n- Model type: Causal decoder-only transformer language model\n- Language: English and German\n- License: LLAMA 2 COMMUNITY LICENSE AGREEMENT\n- Contact: LAION Discord or Björn Plüster", "## Use in Transformers\nFirst install direct dependencies:\n\nIf you want faster inference using flash-attention2, you need to install these dependencies:\n\nThen load the model in transformers:", "## Training parameters\n!training_parameters", "## Benchmarks\n!benchmarks" ]

[ "TAGS\n#transformers #pytorch #llama #text-generation #en #de #dataset-oscar-corpus/OSCAR-2301 #dataset-wikipedia #dataset-bjoernp/tagesschau-2018-2023 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# LAION LeoLM: Linguistically Enhanced Open Language Model\nMeet LeoLM, the first open and commercially available German Foundation Language Model built on Llama-2. \nOur models extend Llama-2's capabilities into German through continued pretraining on a large corpus of German-language and mostly locality specific text.\nThanks to a compute grant at HessianAI's new supercomputer 42, we release two foundation models trained with 8k context length,\n'LeoLM/leo-hessianai-7b' and 'LeoLM/leo-hessianai-13b' under the Llama-2 community license (70b also coming soon! ).\nWith this release, we hope to bring a new wave of opportunities to German open-source and commercial LLM research and accelerate adoption.\nRead our [blog post]() or our paper (preprint coming soon) for more details!\n\n*A project by Björn Plüster and Christoph Schuhmann in collaboration with LAION and HessianAI.*", "## Model Details\n- Finetuned from: meta-llama/Llama-2-13b-hf\n- Model type: Causal decoder-only transformer language model\n- Language: English and German\n- License: LLAMA 2 COMMUNITY LICENSE AGREEMENT\n- Contact: LAION Discord or Björn Plüster", "## Use in Transformers\nFirst install direct dependencies:\n\nIf you want faster inference using flash-attention2, you need to install these dependencies:\n\nThen load the model in transformers:", "## Training parameters\n!training_parameters", "## Benchmarks\n!benchmarks" ]

[ "transformers", "safetensors", "gpt2", "text-generation", "generated_from_trainer", "base_model:distilgpt2", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3.0", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.2+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #safetensors #gpt2 #text-generation #generated_from_trainer #base_model-distilgpt2 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3.0", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.2+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "espnet", "Derm La Fleur Anti Aging Serum", "en", "license:bigscience-openrail-m", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#espnet #Derm La Fleur Anti Aging Serum #en #license-bigscience-openrail-m #region-us \n" ]

[ "diffusers", "safetensors", "arxiv:1910.09700", "diffusers:PixArtAlphaPipeline", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a diffusers 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#diffusers #safetensors #arxiv-1910.09700 #diffusers-PixArtAlphaPipeline #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a diffusers 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", "distilbert", "text-classification", "generated_from_trainer", "base_model:distilbert/distilbert-base-uncased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "# test_distilbert_standardized_job_title_role_categorizer\n\nThis model is a fine-tuned version of distilbert/distilbert-base-uncased on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 128\n- eval_batch_size: 128\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 0.01", "### Training results", "### Framework versions\n\n- Transformers 4.38.2\n- Pytorch 2.2.2+cu118\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #safetensors #distilbert #text-classification #generated_from_trainer #base_model-distilbert/distilbert-base-uncased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "# test_distilbert_standardized_job_title_role_categorizer\n\nThis model is a fine-tuned version of distilbert/distilbert-base-uncased on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 128\n- eval_batch_size: 128\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 0.01", "### Training results", "### Framework versions\n\n- Transformers 4.38.2\n- Pytorch 2.2.2+cu118\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "transformers", "tensorboard", "safetensors", "gpt_neox", "text-classification", "generated_from_trainer", "base_model:EleutherAI/pythia-14m", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# robust_llm_pythia-14m_mz-130_IMDB_n-its-10-seed-0\n\nThis model is a fine-tuned version of EleutherAI/pythia-14m on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 0\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.1\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #tensorboard #safetensors #gpt_neox #text-classification #generated_from_trainer #base_model-EleutherAI/pythia-14m #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# robust_llm_pythia-14m_mz-130_IMDB_n-its-10-seed-0\n\nThis model is a fine-tuned version of EleutherAI/pythia-14m on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 0\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.1\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "peft", "safetensors", "arxiv:1910.09700", "base_model:deepseek-ai/deepseek-coder-6.7b-instruct", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact", "### Framework versions\n\n- PEFT 0.7.1" ]

[ "TAGS\n#peft #safetensors #arxiv-1910.09700 #base_model-deepseek-ai/deepseek-coder-6.7b-instruct #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact", "### Framework versions\n\n- PEFT 0.7.1" ]

[ "transformers", "gguf", "mistral", "quantized", "2-bit", "3-bit", "4-bit", "5-bit", "6-bit", "8-bit", "GGUF", "text-generation", "llama", "llama-3", "base_model:MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.1", "text-generation-inference", "region:us" ]

[]

[]

[ "# MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.1-GGUF\n- Model creator: MaziyarPanahi\n- Original model: MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.1", "## Description\nMaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.1-GGUF contains GGUF format model files for MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.1.", "## Prompt Template\n\nThis model uses 'ChatML' prompt template:\n\n'", "### About GGUF\n\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.\n\nHere is an incomplete list of clients and libraries that are known to support GGUF:\n\n* URL. The source project for GGUF. Offers a CLI and a server option.\n* llama-cpp-python, a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.\n* LM Studio, an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.\n* text-generation-webui, the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.\n* KoboldCpp, a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.\n* GPT4All, a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.\n* LoLLMS Web UI, a great web UI with many interesting and unique features, including a full model library for easy model selection.\n* URL, an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.\n* candle, a Rust ML framework with a focus on performance, including GPU support, and ease of use.\n* ctransformers, a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.", "## Special thanks\n\n Special thanks to Georgi Gerganov and the whole team working on URL for making all of this possible." ]

[ "TAGS\n#transformers #gguf #mistral #quantized #2-bit #3-bit #4-bit #5-bit #6-bit #8-bit #GGUF #text-generation #llama #llama-3 #base_model-MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.1 #text-generation-inference #region-us \n", "# MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.1-GGUF\n- Model creator: MaziyarPanahi\n- Original model: MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.1", "## Description\nMaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.1-GGUF contains GGUF format model files for MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.1.", "## Prompt Template\n\nThis model uses 'ChatML' prompt template:\n\n'", "### About GGUF\n\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.\n\nHere is an incomplete list of clients and libraries that are known to support GGUF:\n\n* URL. The source project for GGUF. Offers a CLI and a server option.\n* llama-cpp-python, a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.\n* LM Studio, an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.\n* text-generation-webui, the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.\n* KoboldCpp, a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.\n* GPT4All, a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.\n* LoLLMS Web UI, a great web UI with many interesting and unique features, including a full model library for easy model selection.\n* URL, an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.\n* candle, a Rust ML framework with a focus on performance, including GPU support, and ease of use.\n* ctransformers, a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.", "## Special thanks\n\n Special thanks to Georgi Gerganov and the whole team working on URL for making all of this possible." ]

[ "transformers", "tensorboard", "safetensors", "m2m_100", "text2text-generation", "generated_from_trainer", "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\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.3.0+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #m2m_100 #text2text-generation #generated_from_trainer #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\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.3.0+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "doi:10.57967/hf/2110", "region:us" ]

[]

[]

[ "### Himel_Face_Detection", "# install \r\npip install fastapi pydantic uvicorn pytz", "# Himel app \r\n------------\r\nngrok config add-authtoken 2Qm8hS1zPhVXiLjEdlI4738tLzF_2QJwGJMK5oTbQD33QSVXS && sudo apt update && sudo apt upgrade && ngrok http --domain=URL 8000" ]

[ "TAGS\n#doi-10.57967/hf/2110 #region-us \n", "### Himel_Face_Detection", "# install \r\npip install fastapi pydantic uvicorn pytz", "# Himel app \r\n------------\r\nngrok config add-authtoken 2Qm8hS1zPhVXiLjEdlI4738tLzF_2QJwGJMK5oTbQD33QSVXS && sudo apt update && sudo apt upgrade && ngrok http --domain=URL 8000" ]

[ "transformers", "tensorboard", "safetensors", "gpt_neox", "text-classification", "generated_from_trainer", "base_model:EleutherAI/pythia-14m", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# robust_llm_pythia-14m_mz-130_IMDB_n-its-10-seed-1\n\nThis model is a fine-tuned version of EleutherAI/pythia-14m on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 1\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.1\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #tensorboard #safetensors #gpt_neox #text-classification #generated_from_trainer #base_model-EleutherAI/pythia-14m #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# robust_llm_pythia-14m_mz-130_IMDB_n-its-10-seed-1\n\nThis model is a fine-tuned version of EleutherAI/pythia-14m on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 1\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.1\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "transformers", "tensorboard", "safetensors", "gpt_neox", "text-classification", "generated_from_trainer", "base_model:EleutherAI/pythia-70m", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# robust_llm_pythia-70m_mz-130_IMDB_n-its-10-seed-2\n\nThis model is a fine-tuned version of EleutherAI/pythia-70m on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 2\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.1\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #tensorboard #safetensors #gpt_neox #text-classification #generated_from_trainer #base_model-EleutherAI/pythia-70m #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# robust_llm_pythia-70m_mz-130_IMDB_n-its-10-seed-2\n\nThis model is a fine-tuned version of EleutherAI/pythia-70m on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 2\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.1\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "transformers", "tensorboard", "safetensors", "gpt_neox", "text-classification", "generated_from_trainer", "base_model:EleutherAI/pythia-70m", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# robust_llm_pythia-70m_mz-130_IMDB_n-its-10-seed-3\n\nThis model is a fine-tuned version of EleutherAI/pythia-70m on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 3\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.1\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #tensorboard #safetensors #gpt_neox #text-classification #generated_from_trainer #base_model-EleutherAI/pythia-70m #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# robust_llm_pythia-70m_mz-130_IMDB_n-its-10-seed-3\n\nThis model is a fine-tuned version of EleutherAI/pythia-70m on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 3\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.1\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "transformers", "safetensors", "llama", "text-generation", "mergekit", "merge", "conversational", "arxiv:2306.01708", "base_model:Sao10K/L3-Solana-8B-v1", "base_model:Masterjp123/Llama-3-SnowyRP-8B-V1", "base_model:kuotient/Meta-Llama-3-8B-Instruct", "base_model:cgato/L3-TheSpice-8b-v0.1.3", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "2306.01708" ]

[]

[ "# merged\nThis is the unquantized Seccond version of SnowyRP using LLama3, added some models will add a EXL2 Quant.\n\nEXL2", "## Merge Details\nFor this model I used the most uncensored and smartest finetunes of LLama 3, since LLama 3 has the largest ammount of training tokens I know of, so I expect it to have more than enough of a knowledge base.\n\nThis model is under both the LLama 3 licince and a few other ones that only affect conmerical uses, But I am not a lawer so use in commerical settings at your own risk.", "## Model Use:\n\nHere is an modified Alpaca prompt I use with this model:", "### Merge Method\n\nThis model was merged using the TIES merge method using kuotient/Meta-Llama-3-8B-Instruct as a base.", "### Models Merged\n\nThe following models were included in the merge:\n* Sao10K/L3-Solana-8B-v1\n* Masterjp123/Llama-3-SnowyRP-8B-V1\n* cgato/L3-TheSpice-8b-v0.1.3", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #mergekit #merge #conversational #arxiv-2306.01708 #base_model-Sao10K/L3-Solana-8B-v1 #base_model-Masterjp123/Llama-3-SnowyRP-8B-V1 #base_model-kuotient/Meta-Llama-3-8B-Instruct #base_model-cgato/L3-TheSpice-8b-v0.1.3 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# merged\nThis is the unquantized Seccond version of SnowyRP using LLama3, added some models will add a EXL2 Quant.\n\nEXL2", "## Merge Details\nFor this model I used the most uncensored and smartest finetunes of LLama 3, since LLama 3 has the largest ammount of training tokens I know of, so I expect it to have more than enough of a knowledge base.\n\nThis model is under both the LLama 3 licince and a few other ones that only affect conmerical uses, But I am not a lawer so use in commerical settings at your own risk.", "## Model Use:\n\nHere is an modified Alpaca prompt I use with this model:", "### Merge Method\n\nThis model was merged using the TIES merge method using kuotient/Meta-Llama-3-8B-Instruct as a base.", "### Models Merged\n\nThe following models were included in the merge:\n* Sao10K/L3-Solana-8B-v1\n* Masterjp123/Llama-3-SnowyRP-8B-V1\n* cgato/L3-TheSpice-8b-v0.1.3", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

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

[]

[]

[ "# Fonglets Sabudenego Pony XL\n\n<Gallery />", "## 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 #not-for-all-audiences #base_model-stablediffusionapi/pony-diffusion-v6-xl #region-us \n", "# Fonglets Sabudenego Pony XL\n\n<Gallery />", "## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab." ]

[ "transformers", "gguf", "en", "base_model:megumi21/Megumi-Chat-llama3-8b-v0.1", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #en #base_model-megumi21/Megumi-Chat-llama3-8b-v0.1 #endpoints_compatible #region-us \n" ]

[ "gguf", "nlp", "code", "text-generation", "en", "base_model:microsoft/Phi-3-mini-128k-instruct", "license:mit", "region:us" ]

[]

[ "en" ]

[ "### About GGUF\n\n\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.\n\n\nHere is an incomplete list of clients and libraries that are known to support GGUF:\n\n\n* URL. The source project for GGUF. Offers a CLI and a server option.\n* text-generation-webui, the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.\n* KoboldCpp, a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.\n* GPT4All, a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.\n* LM Studio, an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.\n* LoLLMS Web UI, a great web UI with many interesting and unique features, including a full model library for easy model selection.\n* URL, an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.\n* llama-cpp-python, a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.\n* candle, a Rust ML framework with a focus on performance, including GPU support, and ease of use.\n* ctransformers, a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.\n\n\nRepositories available\n----------------------\n\n\n* 16-bit GGUF models for CPU+GPU inference\n* Microsoft's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions\n\n\nPrompt template: Phi\n--------------------\n\n\nCompatibility\n-------------\n\n\nThese quantised GGUFv2 files are compatible with URL from August 27th onwards, as of commit d0cee0d\n\n\nThey are also compatible with many third party UIs and libraries - please see the list at the top of this README.\n\n\nExplanation of quantisation methods\n-----------------------------------\n\n\n\nClick to see details\nThe new methods available are:\n\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\n\nRefer to the Provided Files table below to see what files use which methods, and how.\n\n\n\nProvided files\n--------------\n\n\nTBD\n\n\nNote: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.\n\n\nHow to download GGUF files\n--------------------------\n\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 file.\n\n\nThe following clients/libraries will automatically download models for you, providing a list of available models to choose from:\n\n\n* LM Studio\n* LoLLMS Web UI\n* URL", "### In 'text-generation-webui'\n\n\nUnder Download Model, you can enter the model repo: professorf/phi-3-mini-128k-f16-gguf and below it, a specific filename to download, such as: URL\n\n\nThen click Download.", "### On the command line, including multiple files at once\n\n\nI recommend using the 'huggingface-hub' Python library:\n\n\nThen you can download any individual model file to the current directory, at high speed, with a command like this:\n\n\nFor more documentation on downloading with 'huggingface-cli', please see: HF -> Hub Python Library -> Download files -> Download from the CLI.\n\n\nTo accelerate downloads on fast connections (1Gbit/s or higher), install 'hf\\_transfer':\n\n\nAnd set environment variable 'HF\\_HUB\\_ENABLE\\_HF\\_TRANSFER' to '1':\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\n\n\nExample 'URL' command\n---------------------\n\n\nMake sure you are using 'URL' from commit d0cee0d or later.\n\n\nChange '-ngl 32' to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.\n\n\nChange '-c 2048' 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\n\nIf you want to have a chat-style conversation, replace the '-p ' argument with '-i -ins'\n\n\nFor other parameters and how to use them, please refer to the URL documentation\n\n\nHow to run in 'text-generation-webui'\n-------------------------------------\n\n\nFurther instructions can be found in the text-generation-webui documentation, here: text-generation-webui/docs/04 ‐ Model URL.\n\n\nHow to run from Python code\n---------------------------\n\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\n\nFor full documentation, please see: llama-cpp-python docs.", "#### First install the package\n\n\nRun one of the following commands, according to your system:", "#### Simple llama-cpp-python example code\n\n\nHow to use with LangChain\n-------------------------\n\n\nHere are guides on using llama-cpp-python and ctransformers with LangChain:\n\n\n* LangChain + llama-cpp-python\n* LangChain + ctransformers\n\n\n\n\n---" ]

[ "TAGS\n#gguf #nlp #code #text-generation #en #base_model-microsoft/Phi-3-mini-128k-instruct #license-mit #region-us \n", "### About GGUF\n\n\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.\n\n\nHere is an incomplete list of clients and libraries that are known to support GGUF:\n\n\n* URL. The source project for GGUF. Offers a CLI and a server option.\n* text-generation-webui, the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.\n* KoboldCpp, a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.\n* GPT4All, a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.\n* LM Studio, an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.\n* LoLLMS Web UI, a great web UI with many interesting and unique features, including a full model library for easy model selection.\n* URL, an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.\n* llama-cpp-python, a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.\n* candle, a Rust ML framework with a focus on performance, including GPU support, and ease of use.\n* ctransformers, a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.\n\n\nRepositories available\n----------------------\n\n\n* 16-bit GGUF models for CPU+GPU inference\n* Microsoft's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions\n\n\nPrompt template: Phi\n--------------------\n\n\nCompatibility\n-------------\n\n\nThese quantised GGUFv2 files are compatible with URL from August 27th onwards, as of commit d0cee0d\n\n\nThey are also compatible with many third party UIs and libraries - please see the list at the top of this README.\n\n\nExplanation of quantisation methods\n-----------------------------------\n\n\n\nClick to see details\nThe new methods available are:\n\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\n\nRefer to the Provided Files table below to see what files use which methods, and how.\n\n\n\nProvided files\n--------------\n\n\nTBD\n\n\nNote: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.\n\n\nHow to download GGUF files\n--------------------------\n\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 file.\n\n\nThe following clients/libraries will automatically download models for you, providing a list of available models to choose from:\n\n\n* LM Studio\n* LoLLMS Web UI\n* URL", "### In 'text-generation-webui'\n\n\nUnder Download Model, you can enter the model repo: professorf/phi-3-mini-128k-f16-gguf and below it, a specific filename to download, such as: URL\n\n\nThen click Download.", "### On the command line, including multiple files at once\n\n\nI recommend using the 'huggingface-hub' Python library:\n\n\nThen you can download any individual model file to the current directory, at high speed, with a command like this:\n\n\nFor more documentation on downloading with 'huggingface-cli', please see: HF -> Hub Python Library -> Download files -> Download from the CLI.\n\n\nTo accelerate downloads on fast connections (1Gbit/s or higher), install 'hf\\_transfer':\n\n\nAnd set environment variable 'HF\\_HUB\\_ENABLE\\_HF\\_TRANSFER' to '1':\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\n\n\nExample 'URL' command\n---------------------\n\n\nMake sure you are using 'URL' from commit d0cee0d or later.\n\n\nChange '-ngl 32' to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.\n\n\nChange '-c 2048' 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\n\nIf you want to have a chat-style conversation, replace the '-p ' argument with '-i -ins'\n\n\nFor other parameters and how to use them, please refer to the URL documentation\n\n\nHow to run in 'text-generation-webui'\n-------------------------------------\n\n\nFurther instructions can be found in the text-generation-webui documentation, here: text-generation-webui/docs/04 ‐ Model URL.\n\n\nHow to run from Python code\n---------------------------\n\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\n\nFor full documentation, please see: llama-cpp-python docs.", "#### First install the package\n\n\nRun one of the following commands, according to your system:", "#### Simple llama-cpp-python example code\n\n\nHow to use with LangChain\n-------------------------\n\n\nHere are guides on using llama-cpp-python and ctransformers with LangChain:\n\n\n* LangChain + llama-cpp-python\n* LangChain + ctransformers\n\n\n\n\n---" ]

[ "transformers", "safetensors", "distilbert", "fill-mask", "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: 64\n* eval\\_batch\\_size: 64\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3.0", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.2.2\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #safetensors #distilbert #fill-mask #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: 64\n* eval\\_batch\\_size: 64\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3.0", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.2.2\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "transformers", "safetensors", "llama", "text-generation", "deutsch", "german", "seedbox", "llama3", "english", "conversational", "de", "en", "dataset:seedboxai/multitask_german_examples_32k", "license:llama3", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us", "has_space" ]

[]

[ "de", "en" ]

[ "# Llama-3-KafkaLM-8B-v0.1\n\nKafkaLM 8b is a Llama3 8b model which was finetuned on an ensemble of popular high-quality open-source instruction sets (translated from English to German). \n\nLlama 3 KafkaLM 8b is a Seedbox project trained by Dennis Dickmann.\n\nWhy Kafka? \nThe models are proficient, yet creative, and have some tendencies to linguistically push boundaries", "## Model Details\n\nThe purpose of releasing the KafkaLM series is to contribute to the German AI community with a set of fine-tuned LLMs that are easy to use in everyday applications across a variety of tasks.\n\nThe main goal is to provide LLMs proficient in German, especially to be used in German-speaking business contexts where English alone is not sufficient.", "### Dataset\n\nI used a 8k filtered version of the following seedboxai/multitask_german_examples_32k", "### Inference\n\nGetting started with the model is straightforward", "## Disclaimer\n\nThe license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model.\nThis model should only be used for research purposes. The original Llama3 license and all restrictions of datasets used to train this model apply." ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #deutsch #german #seedbox #llama3 #english #conversational #de #en #dataset-seedboxai/multitask_german_examples_32k #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us #has_space \n", "# Llama-3-KafkaLM-8B-v0.1\n\nKafkaLM 8b is a Llama3 8b model which was finetuned on an ensemble of popular high-quality open-source instruction sets (translated from English to German). \n\nLlama 3 KafkaLM 8b is a Seedbox project trained by Dennis Dickmann.\n\nWhy Kafka? \nThe models are proficient, yet creative, and have some tendencies to linguistically push boundaries", "## Model Details\n\nThe purpose of releasing the KafkaLM series is to contribute to the German AI community with a set of fine-tuned LLMs that are easy to use in everyday applications across a variety of tasks.\n\nThe main goal is to provide LLMs proficient in German, especially to be used in German-speaking business contexts where English alone is not sufficient.", "### Dataset\n\nI used a 8k filtered version of the following seedboxai/multitask_german_examples_32k", "### Inference\n\nGetting started with the model is straightforward", "## Disclaimer\n\nThe license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model.\nThis model should only be used for research purposes. The original Llama3 license and all restrictions of datasets used to train this model apply." ]

[ "transformers", "safetensors", "vision-encoder-decoder", "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 #vision-encoder-decoder #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" ]

[ "peft", "safetensors", "llama", "base_model:unsloth/llama-3-8b-bnb-4bit", "license:llama3", "region:us" ]

[]

[]

[ "# Llama3_8B_Odia_Unsloth\n\nLlama3_8B_Odia_Unsloth is a fine-tuned Odia large language model with 8 billion parameters, and it is based on Llama3. The model is fine-tuned on a comprehensive 171k Odia instruction set, encompassing domain-specific and cultural nuances.\n\nThe fine-tuning process leverages Unsloth, expediting the training process for optimal efficiency.\n\nFor more details about the model, data, training procedure, and evaluations, go through the blog post.", "## Model Description\n* Model type: A 8B fine-tuned model\n* Primary Language(s): Odia and English \n* License: Llama3", "## Inference\n\nSample inference script.", "### Installation", "### Model loading", "### Inference\n\n\n\n\nIf you find this model useful, please consider giving and citing:", "### Contributions\n\n- Dr.Shantipriya Parida\n- Sambit Sekhar\n- Debasish Dhal\n- Shakshi Panwar" ]

[ "TAGS\n#peft #safetensors #llama #base_model-unsloth/llama-3-8b-bnb-4bit #license-llama3 #region-us \n", "# Llama3_8B_Odia_Unsloth\n\nLlama3_8B_Odia_Unsloth is a fine-tuned Odia large language model with 8 billion parameters, and it is based on Llama3. The model is fine-tuned on a comprehensive 171k Odia instruction set, encompassing domain-specific and cultural nuances.\n\nThe fine-tuning process leverages Unsloth, expediting the training process for optimal efficiency.\n\nFor more details about the model, data, training procedure, and evaluations, go through the blog post.", "## Model Description\n* Model type: A 8B fine-tuned model\n* Primary Language(s): Odia and English \n* License: Llama3", "## Inference\n\nSample inference script.", "### Installation", "### Model loading", "### Inference\n\n\n\n\nIf you find this model useful, please consider giving and citing:", "### Contributions\n\n- Dr.Shantipriya Parida\n- Sambit Sekhar\n- Debasish Dhal\n- Shakshi Panwar" ]

[ "transformers", "gguf", "shining-valiant", "shining-valiant-2", "valiant", "valiant-labs", "llama", "llama-3", "llama-3-instruct", "llama-3-instruct-70b", "70b", "conversational", "chat", "instruct", "en", "base_model:ValiantLabs/Llama3-70B-ShiningValiant2", "license:other", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #shining-valiant #shining-valiant-2 #valiant #valiant-labs #llama #llama-3 #llama-3-instruct #llama-3-instruct-70b #70b #conversational #chat #instruct #en #base_model-ValiantLabs/Llama3-70B-ShiningValiant2 #license-other #endpoints_compatible #region-us \n" ]

[ "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" ]

[ "transformers", "safetensors", "llama", "text-generation", "axolotl", "generated_from_trainer", "base_model:winglian/llama-3-32k-merged", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 2\n* eval\\_batch\\_size: 2\n* seed: 42\n* distributed\\_type: multi-GPU\n* num\\_devices: 5\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 40\n* total\\_eval\\_batch\\_size: 10\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\n* lr\\_scheduler\\_warmup\\_steps: 100\n* num\\_epochs: 3", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0.dev0\n* Pytorch 2.2.0+cu121\n* Datasets 2.15.0\n* Tokenizers 0.15.0" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #axolotl #generated_from_trainer #base_model-winglian/llama-3-32k-merged #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 2\n* eval\\_batch\\_size: 2\n* seed: 42\n* distributed\\_type: multi-GPU\n* num\\_devices: 5\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 40\n* total\\_eval\\_batch\\_size: 10\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\n* lr\\_scheduler\\_warmup\\_steps: 100\n* num\\_epochs: 3", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0.dev0\n* Pytorch 2.2.0+cu121\n* Datasets 2.15.0\n* Tokenizers 0.15.0" ]

[ "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" ]

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

[]

[ "en" ]

[ "# Skyrim Fine-Tune for Meta Llama 3 8B Instruct\n<img src=\"URL width=\"1000\"/>\n\nGGUF models: URL", "## Introduction\nThis fine-tune of Meta's Llama 3 8B Instruct model is intended to be used as a custom-tailored model for the Mantella Skyrim mod.", "## Dataset\nAn Alpaca-style dataset of 8,800+ player <-> NPC interactions has been used in this fine-tune. Details on this dataset can be found in the Mantella LLM Fine-Tuning repo.\n\nExample:", "## Specifications\n- Developed by: art-from-the-machine\n- License: apache-2.0\n- Fine-tuned from model: unsloth/llama-3-8b-Instruct-bnb-4bit\n- Context length: 8,192", "## Example Output\nThe fine-tuned Mantella-Skyrim-Llama-3-8B-Q4_K_M.gguf model has been tested in Mantella v0.11.2's debug mode, with the model running locally in koboldcpp. The character tested is Hulda. A list of questions are tested against both the fine-tuned model as well as an equivalent Q4_K_M Llama 3 Instruct base model for comparison. For both models, Mantella's 'max_response_sentences' setting has been set to 4. \n<details>\n<summary><b>Mantella-Skyrim-Llama-3-8B-Q4_K_M.gguf</b></summary>\n \n\n</details>\n<br>\n\n<details>\n<summary><b>Meta-Llama-3-8B-Instruct-Q4_K_M.gguf</b></summary>\n \n\n</details>", "## How to use with Mantella\nSee here for full instructions on how to run Mantella with a local LLM.", "## Notes\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 #gguf #conversational #en #base_model-unsloth/llama-3-8b-Instruct-bnb-4bit #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "# Skyrim Fine-Tune for Meta Llama 3 8B Instruct\n<img src=\"URL width=\"1000\"/>\n\nGGUF models: URL", "## Introduction\nThis fine-tune of Meta's Llama 3 8B Instruct model is intended to be used as a custom-tailored model for the Mantella Skyrim mod.", "## Dataset\nAn Alpaca-style dataset of 8,800+ player <-> NPC interactions has been used in this fine-tune. Details on this dataset can be found in the Mantella LLM Fine-Tuning repo.\n\nExample:", "## Specifications\n- Developed by: art-from-the-machine\n- License: apache-2.0\n- Fine-tuned from model: unsloth/llama-3-8b-Instruct-bnb-4bit\n- Context length: 8,192", "## Example Output\nThe fine-tuned Mantella-Skyrim-Llama-3-8B-Q4_K_M.gguf model has been tested in Mantella v0.11.2's debug mode, with the model running locally in koboldcpp. The character tested is Hulda. A list of questions are tested against both the fine-tuned model as well as an equivalent Q4_K_M Llama 3 Instruct base model for comparison. For both models, Mantella's 'max_response_sentences' setting has been set to 4. \n<details>\n<summary><b>Mantella-Skyrim-Llama-3-8B-Q4_K_M.gguf</b></summary>\n \n\n</details>\n<br>\n\n<details>\n<summary><b>Meta-Llama-3-8B-Instruct-Q4_K_M.gguf</b></summary>\n \n\n</details>", "## How to use with Mantella\nSee here for full instructions on how to run Mantella with a local LLM.", "## Notes\nThis llama 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" ]

[ "transformers", "safetensors", "unsloth", "en", "dataset:unalignment/toxic-dpo-v0.2", "dataset:NobodyExistsOnTheInternet/ToxicQAFinal", "dataset:Open-Orca/SlimOrca", "dataset:PygmalionAI/PIPPA", "dataset:MinervaAI/Aesir-Preview", "license:llama3", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[ "# Disclaimer\n\nThis model is an experimental fine tune of LLama-3", "## Datasets used:\n\n- unalignment/toxic-dpo-v0.2\n- NobodyExistsOnTheInternet/ToxicQAFinal\n- Open-Orca/SlimOrca (subset of data)\n- PygmalionAI/PIPPA\n- MinervaAI/Aesir-Preview", "### Model Description\n\n\nThe model is highly uncensored + suitable for roleplay", "## About Us\nBuilding - AI Waifu Supremacy\n\nX\n\nDiscord", "## Credits:\n(For open sourcing tools + methodology to assist with fine tuning)\n- Unisloth\n- NurtureAI\n(For open sourcing data to be used for fine tuning)\n- NobodyExistsOnTheInternet\n- unalignment\n- Open-Orca\n- PygmalionAI\n- MinervaAI" ]

[ "TAGS\n#transformers #safetensors #unsloth #en #dataset-unalignment/toxic-dpo-v0.2 #dataset-NobodyExistsOnTheInternet/ToxicQAFinal #dataset-Open-Orca/SlimOrca #dataset-PygmalionAI/PIPPA #dataset-MinervaAI/Aesir-Preview #license-llama3 #endpoints_compatible #region-us \n", "# Disclaimer\n\nThis model is an experimental fine tune of LLama-3", "## Datasets used:\n\n- unalignment/toxic-dpo-v0.2\n- NobodyExistsOnTheInternet/ToxicQAFinal\n- Open-Orca/SlimOrca (subset of data)\n- PygmalionAI/PIPPA\n- MinervaAI/Aesir-Preview", "### Model Description\n\n\nThe model is highly uncensored + suitable for roleplay", "## About Us\nBuilding - AI Waifu Supremacy\n\nX\n\nDiscord", "## Credits:\n(For open sourcing tools + methodology to assist with fine tuning)\n- Unisloth\n- NurtureAI\n(For open sourcing data to be used for fine tuning)\n- NobodyExistsOnTheInternet\n- unalignment\n- Open-Orca\n- PygmalionAI\n- MinervaAI" ]

[ "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" ]

[ "region:us" ]

[]

[]

[]

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

[ "transformers", "safetensors", "llama", "text-generation", "axolotl", "generated_from_trainer", "instruct", "finetune", "chatml", "gpt4", "synthetic data", "science", "physics", "chemistry", "biology", "math", "llama3", "conversational", "en", "dataset:allenai/ai2_arc", "dataset:camel-ai/physics", "dataset:camel-ai/chemistry", "dataset:camel-ai/biology", "dataset:camel-ai/math", "dataset:metaeval/reclor", "dataset:openbookqa", "dataset:mandyyyyii/scibench", "dataset:derek-thomas/ScienceQA", "dataset:TIGER-Lab/ScienceEval", "dataset:jondurbin/airoboros-3.2", "dataset:LDJnr/Capybara", "dataset:Cot-Alpaca-GPT4-From-OpenHermes-2.5", "dataset:STEM-AI-mtl/Electrical-engineering", "dataset:knowrohit07/saraswati-stem", "dataset:sablo/oasst2_curated", "dataset:lmsys/lmsys-chat-1m", "dataset:TIGER-Lab/MathInstruct", "dataset:bigbio/med_qa", "dataset:meta-math/MetaMathQA-40K", "dataset:piqa", "dataset:scibench", "dataset:sciq", "dataset:Open-Orca/SlimOrca", "dataset:migtissera/Synthia-v1.3", "dataset:allenai/WildChat", "dataset:microsoft/orca-math-word-problems-200k", "dataset:openchat/openchat_sharegpt4_dataset", "dataset:teknium/GPTeacher-General-Instruct", "dataset:m-a-p/CodeFeedback-Filtered-Instruction", "dataset:totally-not-an-llm/EverythingLM-data-V3", "dataset:HuggingFaceH4/no_robots", "dataset:OpenAssistant/oasst_top1_2023-08-25", "dataset:WizardLM/WizardLM_evol_instruct_70k", "base_model:meta-llama/Meta-Llama-3-8B", "license:other", "model-index", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #safetensors #llama #text-generation #axolotl #generated_from_trainer #instruct #finetune #chatml #gpt4 #synthetic data #science #physics #chemistry #biology #math #llama3 #conversational #en #dataset-allenai/ai2_arc #dataset-camel-ai/physics #dataset-camel-ai/chemistry #dataset-camel-ai/biology #dataset-camel-ai/math #dataset-metaeval/reclor #dataset-openbookqa #dataset-mandyyyyii/scibench #dataset-derek-thomas/ScienceQA #dataset-TIGER-Lab/ScienceEval #dataset-jondurbin/airoboros-3.2 #dataset-LDJnr/Capybara #dataset-Cot-Alpaca-GPT4-From-OpenHermes-2.5 #dataset-STEM-AI-mtl/Electrical-engineering #dataset-knowrohit07/saraswati-stem #dataset-sablo/oasst2_curated #dataset-lmsys/lmsys-chat-1m #dataset-TIGER-Lab/MathInstruct #dataset-bigbio/med_qa #dataset-meta-math/MetaMathQA-40K #dataset-piqa #dataset-scibench #dataset-sciq #dataset-Open-Orca/SlimOrca #dataset-migtissera/Synthia-v1.3 #dataset-allenai/WildChat #dataset-microsoft/orca-math-word-problems-200k #dataset-openchat/openchat_sharegpt4_dataset #dataset-teknium/GPTeacher-General-Instruct #dataset-m-a-p/CodeFeedback-Filtered-Instruction #dataset-totally-not-an-llm/EverythingLM-data-V3 #dataset-HuggingFaceH4/no_robots #dataset-OpenAssistant/oasst_top1_2023-08-25 #dataset-WizardLM/WizardLM_evol_instruct_70k #base_model-meta-llama/Meta-Llama-3-8B #license-other #model-index #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n" ]

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

[]

[ "en" ]

[ "# Uploaded model\n\n- Developed by: art-from-the-machine\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-Instruct-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-Instruct-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us \n", "# Uploaded model\n\n- Developed by: art-from-the-machine\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-Instruct-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", "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" ]

[ "transformers", "gguf", "en", "dataset:adalbertojunior/openHermes_portuguese", "base_model:adalbertojunior/Llama-3-8B-Instruct-Portuguese-v0.4", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #en #dataset-adalbertojunior/openHermes_portuguese #base_model-adalbertojunior/Llama-3-8B-Instruct-Portuguese-v0.4 #endpoints_compatible #region-us \n" ]

[ "transformers", "tensorboard", "safetensors", "mbart", "text2text-generation", "generated_from_trainer", "custom_code", "ru", "base_model:Auruncus/lsg-lsh-mbart-cc25-16384-128-4-2ep", "autotrain_compatible", "region:us" ]

[]

[ "ru" ]

[ "# lsg-lsh-mbart-cc25-16384-128-4-4ep\n\nThis model is a fine-tuned version of Auruncus/lsg-lsh-mbart-cc25-16384-128-4-2ep on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- Loss: 2.5736\n- Rouge1: 2.6972\n- Rouge2: 1.6893\n- Rougel: 2.6528\n- Rougelsum: 2.6347\n- Gen Len: 135.5", "## 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: 2\n- eval_batch_size: 1\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- num_epochs: 2.0\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.41.0.dev0\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #mbart #text2text-generation #generated_from_trainer #custom_code #ru #base_model-Auruncus/lsg-lsh-mbart-cc25-16384-128-4-2ep #autotrain_compatible #region-us \n", "# lsg-lsh-mbart-cc25-16384-128-4-4ep\n\nThis model is a fine-tuned version of Auruncus/lsg-lsh-mbart-cc25-16384-128-4-2ep on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- Loss: 2.5736\n- Rouge1: 2.6972\n- Rouge2: 1.6893\n- Rougel: 2.6528\n- Rougelsum: 2.6347\n- Gen Len: 135.5", "## 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: 2\n- eval_batch_size: 1\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- num_epochs: 2.0\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.41.0.dev0\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

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

[ "1910.09700" ]

[ "zh" ]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\nThis model is an artificial intelligence generated text detection model trained using real human text and AI generated text (mainly including Erine-Bot 4.0, Qwen-Turbo 4.0 and ChatGPT 3.0 )Can effectively identify whether text is generated by artificial intelligence.\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\nYou could implement the model with the sample if you want to classify between AI-generated text and real-text.", "## 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 #zh #arxiv-1910.09700 #license-mit #autotrain_compatible #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\nThis model is an artificial intelligence generated text detection model trained using real human text and AI generated text (mainly including Erine-Bot 4.0, Qwen-Turbo 4.0 and ChatGPT 3.0 )Can effectively identify whether text is generated by artificial intelligence.\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\nYou could implement the model with the sample if you want to classify between AI-generated text and real-text.", "## 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" ]

[ "region:us" ]

[]

[]

[ "# EffectXmed Creme Deutschland Erfahrungen Inhaltsstoffe, Vorteile Offizielle Preis, Kaufen\n\nEffectXMed ist eine Marke, die über eine gewisse Erfahrung mit Hautpflegeprodukten verfügt und anspruchsvolle Seren und Cremes anbietet. Die Produkte sind ausschließlich darauf ausgerichtet, den Reifungsprozess der Haut anzukurbeln, die Erhaltungsfunktionen zu unterstützen und die Hautalterung weiter voranzutreiben. Besonders wirksame Wirkstoffe zur Krebsprävention, Nährstoffe und feine Pflanzenöle sowie Aminosäuren stehen im Mittelpunkt der Details.", "## Klicken Sie hier, um jetzt auf der offiziellen Website von EffectXmed Creme zu kaufen", "## EffectXmed-Befestigungen\nDer Gegenreifungsgenuss wird durch die Art und Weise gefördert, in der sich die wichtigsten natürlichen dynamischen Fixierungen befinden. Daher sollte das Produkt auch von allen Kunden rundum akzeptiert werden. Die zugehörigen EffectXmed-Befestigungen sind angegeben:\n\n\nKigelia Africana extrahieren\n\nPlatinpeptide\n\nTraubenkernöl\n\nKaviar und Muscheln entfernen\n\nShea-Margarine, Aprikosenkernöl, Sonnenblumenöl und Olivenöl", "## Gold- und Juwelenpulver\n \n\nKigelia Africana-Konzentrat: Dies ist ein wesentlicher Bestandteil zahlreicher Anti-Aging-Cremes, einschließlich EffectXmed. Es sättigt die Haut. Dadurch wird die Entstehung von Falten gemildert und die Haut kann wiederbelebt werden.\n\nTraubenkernöl: Dieses einzigartige Öl fördert die Wundheilung und sorgt anschließend für ein glattes und verfeinertes Hautbild.\n\nPlatinpeptide: Peptide garantieren eine hervorragende Bildung von Kollagen Typ 1 und 3. Dies führt zu einer strafferen und geglätteten Haut.\n\nShea-Aufstrich, Aprikosenkernöl und Sonnenblumenöl: Die in der EffectXmed-Creme enthaltenen dynamischen Wirkstoffe sind ein erfolgreicher Ratgeber bei trockener Haut, die gleichzeitig eine Hautreifung zeigt.\n\nGold- und Juwelenpuder: Dieses Puder wirkt nachts gegen Falten und hinterlässt einen echten Glanzeffekt.", "## Klicken Sie hier, um jetzt auf der offiziellen Website von EffectXmed Creme zu kaufen" ]

[ "TAGS\n#region-us \n", "# EffectXmed Creme Deutschland Erfahrungen Inhaltsstoffe, Vorteile Offizielle Preis, Kaufen\n\nEffectXMed ist eine Marke, die über eine gewisse Erfahrung mit Hautpflegeprodukten verfügt und anspruchsvolle Seren und Cremes anbietet. Die Produkte sind ausschließlich darauf ausgerichtet, den Reifungsprozess der Haut anzukurbeln, die Erhaltungsfunktionen zu unterstützen und die Hautalterung weiter voranzutreiben. Besonders wirksame Wirkstoffe zur Krebsprävention, Nährstoffe und feine Pflanzenöle sowie Aminosäuren stehen im Mittelpunkt der Details.", "## Klicken Sie hier, um jetzt auf der offiziellen Website von EffectXmed Creme zu kaufen", "## EffectXmed-Befestigungen\nDer Gegenreifungsgenuss wird durch die Art und Weise gefördert, in der sich die wichtigsten natürlichen dynamischen Fixierungen befinden. Daher sollte das Produkt auch von allen Kunden rundum akzeptiert werden. Die zugehörigen EffectXmed-Befestigungen sind angegeben:\n\n\nKigelia Africana extrahieren\n\nPlatinpeptide\n\nTraubenkernöl\n\nKaviar und Muscheln entfernen\n\nShea-Margarine, Aprikosenkernöl, Sonnenblumenöl und Olivenöl", "## Gold- und Juwelenpulver\n \n\nKigelia Africana-Konzentrat: Dies ist ein wesentlicher Bestandteil zahlreicher Anti-Aging-Cremes, einschließlich EffectXmed. Es sättigt die Haut. Dadurch wird die Entstehung von Falten gemildert und die Haut kann wiederbelebt werden.\n\nTraubenkernöl: Dieses einzigartige Öl fördert die Wundheilung und sorgt anschließend für ein glattes und verfeinertes Hautbild.\n\nPlatinpeptide: Peptide garantieren eine hervorragende Bildung von Kollagen Typ 1 und 3. Dies führt zu einer strafferen und geglätteten Haut.\n\nShea-Aufstrich, Aprikosenkernöl und Sonnenblumenöl: Die in der EffectXmed-Creme enthaltenen dynamischen Wirkstoffe sind ein erfolgreicher Ratgeber bei trockener Haut, die gleichzeitig eine Hautreifung zeigt.\n\nGold- und Juwelenpuder: Dieses Puder wirkt nachts gegen Falten und hinterlässt einen echten Glanzeffekt.", "## Klicken Sie hier, um jetzt auf der offiziellen Website von EffectXmed Creme zu kaufen" ]

[ "peft", "tensorboard", "safetensors", "trl", "sft", "generated_from_trainer", "dataset:generator", "base_model:mistralai/Mistral-7B-v0.1", "license:apache-2.0", "region:us" ]

[]

[]

[ "# Mistral-7B-v0.1-VIGGO-qlora\n\nThis model is a fine-tuned version of mistralai/Mistral-7B-v0.1 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 0.10.0\n- Transformers 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.16.1\n- Tokenizers 0.15.2" ]

[ "TAGS\n#peft #tensorboard #safetensors #trl #sft #generated_from_trainer #dataset-generator #base_model-mistralai/Mistral-7B-v0.1 #license-apache-2.0 #region-us \n", "# Mistral-7B-v0.1-VIGGO-qlora\n\nThis model is a fine-tuned version of mistralai/Mistral-7B-v0.1 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 0.10.0\n- Transformers 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.16.1\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" ]

[ "ml-agents", "tensorboard", "onnx", "SoccerTwos", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-SoccerTwos", "region:us" ]

[]

[]

[ "# poca Agent playing SoccerTwos\n This is a trained model of a poca agent playing SoccerTwos\n using the Unity ML-Agents Library.\n\n ## Usage (with ML-Agents)\n The Documentation: URL\n\n We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:\n - A *short tutorial* where you teach Huggy the Dog to fetch the stick and then play with him directly in your\n browser: URL\n - A *longer tutorial* to understand how works ML-Agents:\n URL\n\n ### Resume the training\n \n\n ### Watch your Agent play\n You can watch your agent playing directly in your browser\n\n 1. If the environment is part of ML-Agents official environments, go to URL\n 2. Step 1: Find your model_id: mrbesher/poca-SoccerTwos\n 3. Step 2: Select your *.nn /*.onnx file\n 4. Click on Watch the agent play" ]

[ "TAGS\n#ml-agents #tensorboard #onnx #SoccerTwos #deep-reinforcement-learning #reinforcement-learning #ML-Agents-SoccerTwos #region-us \n", "# poca Agent playing SoccerTwos\n This is a trained model of a poca agent playing SoccerTwos\n using the Unity ML-Agents Library.\n\n ## Usage (with ML-Agents)\n The Documentation: URL\n\n We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:\n - A *short tutorial* where you teach Huggy the Dog to fetch the stick and then play with him directly in your\n browser: URL\n - A *longer tutorial* to understand how works ML-Agents:\n URL\n\n ### Resume the training\n \n\n ### Watch your Agent play\n You can watch your agent playing directly in your browser\n\n 1. If the environment is part of ML-Agents official environments, go to URL\n 2. Step 1: Find your model_id: mrbesher/poca-SoccerTwos\n 3. Step 2: Select your *.nn /*.onnx file\n 4. Click on Watch the agent play" ]

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

[]

[]

[ "# Llama 3 DiscoLM German 8b v0.1 Experimental\n\n<p align=\"center\"><img src=\"/DiscoResearch/Llama3_DiscoLM_German_8b_v0.1_experimental/resolve/main/disco_llama.webp\" width=\"400\"></p>", "# Introduction\n\nLlama 3 DiscoLM German 8b v0.1 Experimental is an experimental Llama 3 based version of DiscoLM German.\n\nThis is an experimental release and not intended for production use. The model is still in development and will be updated with new features and improvements in the future.\n\nPlease find a online Demo here (we may take this offline for updates).", "# Prompt Format\n\nDiscoLM German uses ChatML as the prompt format which enables OpenAI endpoint compatability and is supported by most inference libraries and frontends.\n\nSystem prompts allow steerability and interesting new ways to interact with an LLM, guiding rules, roles, and stylistic choices of the model.\n\n\n\nThis prompt is available as a chat template, which means you can format messages using the\n'tokenizer.apply_chat_template()' method:\n\n\n\nWhen tokenizing messages for generation, set 'add_generation_prompt=True' when calling 'apply_chat_template()'. This will append '<|im_start|>assistant\\n' to your prompt, to ensure\nthat the model continues with an assistant response.", "# Example Code for Inference", "# Limitations & Biases\n\nThis model can produce factually incorrect and offensive output, and should not be relied on to produce factually accurate information.\nThis model was trained on various public datasets. While great efforts have been taken to clean the pretraining data, it is possible that this model could generate biased or otherwise offensive outputs and it is the responsibility of the user to implement a safety/moderation layer. Please use with caution.", "# License\n\nThis model is distributed under the META LLAMA 3 COMMUNITY LICENSE, see LICENSE for more information.", "# Acknowledgements\n\nBuilt with Meta Llama 3.\n\nDiscoLM German is a DiscoResearch project, a collective effort by JP Harries, Björn Plüster and Daniel Auras.\n\nDevelopment of Llama 3 DiscoLM German 8b was sponsored by ellamind.\nCompute was sponsored generously by sysGen GmbH.\n\n<img src=\"URL alt=\"Built with Axolotl\" width=\"200\" height=\"32\"/>", "# About DiscoResearch\n\nDiscoResearch is an aspiring open research community for AI enthusiasts and LLM hackers. Come join our Discord, share your opinions and ideas, and advance open LLM research with us!", "# Disclaimer\n\nThe license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. This model should only be deployed with additional safety measures in place." ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #conversational #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n", "# Llama 3 DiscoLM German 8b v0.1 Experimental\n\n<p align=\"center\"><img src=\"/DiscoResearch/Llama3_DiscoLM_German_8b_v0.1_experimental/resolve/main/disco_llama.webp\" width=\"400\"></p>", "# Introduction\n\nLlama 3 DiscoLM German 8b v0.1 Experimental is an experimental Llama 3 based version of DiscoLM German.\n\nThis is an experimental release and not intended for production use. The model is still in development and will be updated with new features and improvements in the future.\n\nPlease find a online Demo here (we may take this offline for updates).", "# Prompt Format\n\nDiscoLM German uses ChatML as the prompt format which enables OpenAI endpoint compatability and is supported by most inference libraries and frontends.\n\nSystem prompts allow steerability and interesting new ways to interact with an LLM, guiding rules, roles, and stylistic choices of the model.\n\n\n\nThis prompt is available as a chat template, which means you can format messages using the\n'tokenizer.apply_chat_template()' method:\n\n\n\nWhen tokenizing messages for generation, set 'add_generation_prompt=True' when calling 'apply_chat_template()'. This will append '<|im_start|>assistant\\n' to your prompt, to ensure\nthat the model continues with an assistant response.", "# Example Code for Inference", "# Limitations & Biases\n\nThis model can produce factually incorrect and offensive output, and should not be relied on to produce factually accurate information.\nThis model was trained on various public datasets. While great efforts have been taken to clean the pretraining data, it is possible that this model could generate biased or otherwise offensive outputs and it is the responsibility of the user to implement a safety/moderation layer. Please use with caution.", "# License\n\nThis model is distributed under the META LLAMA 3 COMMUNITY LICENSE, see LICENSE for more information.", "# Acknowledgements\n\nBuilt with Meta Llama 3.\n\nDiscoLM German is a DiscoResearch project, a collective effort by JP Harries, Björn Plüster and Daniel Auras.\n\nDevelopment of Llama 3 DiscoLM German 8b was sponsored by ellamind.\nCompute was sponsored generously by sysGen GmbH.\n\n<img src=\"URL alt=\"Built with Axolotl\" width=\"200\" height=\"32\"/>", "# About DiscoResearch\n\nDiscoResearch is an aspiring open research community for AI enthusiasts and LLM hackers. Come join our Discord, share your opinions and ideas, and advance open LLM research with us!", "# Disclaimer\n\nThe license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. This model should only be deployed with additional safety measures in place." ]

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

[]

[ "en" ]

[ "# Skyrim Fine-Tune for Meta Llama 3 8B Instruct\n<img src=\"URL width=\"1000\"/>", "## Introduction\nThis fine-tune of Meta's Llama 3 8B Instruct model is intended to be used as a custom-tailored model for the Mantella Skyrim mod.", "## Dataset\nAn Alpaca-style dataset of 8,800+ player <-> NPC interactions has been used in this fine-tune. Details on this dataset can be found in the Mantella LLM Fine-Tuning repo.\n\nExample:", "## Specifications\n- Developed by: art-from-the-machine\n- License: apache-2.0\n- Fine-tuned from model: unsloth/llama-3-8b-Instruct-bnb-4bit\n- Context length: 8,192", "## Example Output\nThe fine-tuned Mantella-Skyrim-Llama-3-8B-Q4_K_M.gguf model has been tested in Mantella v0.11.2's debug mode, with the model running locally in koboldcpp. The character tested is Hulda. A list of questions are tested against both the fine-tuned model as well as an equivalent Q4_K_M Llama 3 Instruct base model for comparison. For both models, Mantella's 'max_response_sentences' setting has been set to 4. \n<details>\n<summary><b>Mantella-Skyrim-Llama-3-8B-Q4_K_M.gguf</b></summary>\n \n\n</details>\n<br>\n\n<details>\n<summary><b>Meta-Llama-3-8B-Instruct-Q4_K_M.gguf</b></summary>\n \n\n</details>", "## How to use with Mantella\nSee here for full instructions on how to run Mantella with a local LLM.", "## Notes\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "TAGS\n#transformers #gguf #llama #text-generation-inference #unsloth #en #base_model-unsloth/llama-3-8b-Instruct-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us \n", "# Skyrim Fine-Tune for Meta Llama 3 8B Instruct\n<img src=\"URL width=\"1000\"/>", "## Introduction\nThis fine-tune of Meta's Llama 3 8B Instruct model is intended to be used as a custom-tailored model for the Mantella Skyrim mod.", "## Dataset\nAn Alpaca-style dataset of 8,800+ player <-> NPC interactions has been used in this fine-tune. Details on this dataset can be found in the Mantella LLM Fine-Tuning repo.\n\nExample:", "## Specifications\n- Developed by: art-from-the-machine\n- License: apache-2.0\n- Fine-tuned from model: unsloth/llama-3-8b-Instruct-bnb-4bit\n- Context length: 8,192", "## Example Output\nThe fine-tuned Mantella-Skyrim-Llama-3-8B-Q4_K_M.gguf model has been tested in Mantella v0.11.2's debug mode, with the model running locally in koboldcpp. The character tested is Hulda. A list of questions are tested against both the fine-tuned model as well as an equivalent Q4_K_M Llama 3 Instruct base model for comparison. For both models, Mantella's 'max_response_sentences' setting has been set to 4. \n<details>\n<summary><b>Mantella-Skyrim-Llama-3-8B-Q4_K_M.gguf</b></summary>\n \n\n</details>\n<br>\n\n<details>\n<summary><b>Meta-Llama-3-8B-Instruct-Q4_K_M.gguf</b></summary>\n \n\n</details>", "## How to use with Mantella\nSee here for full instructions on how to run Mantella with a local LLM.", "## Notes\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "transformers", "gguf", "mistral", "quantized", "2-bit", "3-bit", "4-bit", "5-bit", "6-bit", "8-bit", "GGUF", "text-generation", "llama", "llama-3", "base_model:MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.2", "text-generation-inference", "region:us" ]

[]

[]

[ "# MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.2-GGUF\n- Model creator: MaziyarPanahi\n- Original model: MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.2", "## Description\nMaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.2-GGUF contains GGUF format model files for MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.2.", "## Prompt Template\n\nThis model uses 'ChatML' prompt template:\n\n'", "### About GGUF\n\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.\n\nHere is an incomplete list of clients and libraries that are known to support GGUF:\n\n* URL. The source project for GGUF. Offers a CLI and a server option.\n* llama-cpp-python, a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.\n* LM Studio, an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.\n* text-generation-webui, the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.\n* KoboldCpp, a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.\n* GPT4All, a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.\n* LoLLMS Web UI, a great web UI with many interesting and unique features, including a full model library for easy model selection.\n* URL, an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.\n* candle, a Rust ML framework with a focus on performance, including GPU support, and ease of use.\n* ctransformers, a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.", "## Special thanks\n\n Special thanks to Georgi Gerganov and the whole team working on URL for making all of this possible." ]

[ "TAGS\n#transformers #gguf #mistral #quantized #2-bit #3-bit #4-bit #5-bit #6-bit #8-bit #GGUF #text-generation #llama #llama-3 #base_model-MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.2 #text-generation-inference #region-us \n", "# MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.2-GGUF\n- Model creator: MaziyarPanahi\n- Original model: MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.2", "## Description\nMaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.2-GGUF contains GGUF format model files for MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.2.", "## Prompt Template\n\nThis model uses 'ChatML' prompt template:\n\n'", "### About GGUF\n\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.\n\nHere is an incomplete list of clients and libraries that are known to support GGUF:\n\n* URL. The source project for GGUF. Offers a CLI and a server option.\n* llama-cpp-python, a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.\n* LM Studio, an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.\n* text-generation-webui, the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.\n* KoboldCpp, a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.\n* GPT4All, a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.\n* LoLLMS Web UI, a great web UI with many interesting and unique features, including a full model library for easy model selection.\n* URL, an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.\n* candle, a Rust ML framework with a focus on performance, including GPU support, and ease of use.\n* ctransformers, a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.", "## Special thanks\n\n Special thanks to Georgi Gerganov and the whole team working on URL for making all of this possible." ]

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

[]

[ "en" ]

[]

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

[ "peft", "safetensors", "llama-factory", "lora", "generated_from_trainer", "base_model:meta-llama/Meta-Llama-3-8B", "license:other", "region:us" ]

[]

[]

[ "# train_2024-04-24-11-25-37\n\nThis model is a fine-tuned version of meta-llama/Meta-Llama-3-8B on the alpaca_zh and the alpaca_gpt4_zh datasets.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0002\n- train_batch_size: 2\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 8\n- total_train_batch_size: 16\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- num_epochs: 2.0\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- PEFT 0.10.0\n- Transformers 4.37.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.19.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #llama-factory #lora #generated_from_trainer #base_model-meta-llama/Meta-Llama-3-8B #license-other #region-us \n", "# train_2024-04-24-11-25-37\n\nThis model is a fine-tuned version of meta-llama/Meta-Llama-3-8B on the alpaca_zh and the alpaca_gpt4_zh datasets.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0002\n- train_batch_size: 2\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 8\n- total_train_batch_size: 16\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- num_epochs: 2.0\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- PEFT 0.10.0\n- Transformers 4.37.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.19.0\n- Tokenizers 0.15.2" ]

[ "transformers", "safetensors", "roberta", "text-classification", "arxiv:1907.11692", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[ "1907.11692" ]

[]

[ "# Model Card for j34330vk-q26752aa-NLI\n\n\n\nThis is a Natural Language Inference (NLI) classification model that was trained to\n detect if a hypothesis is true based on a premise.", "## Model Details", "### Model Description\n\n\n\nThis model is based upon a RoBERTa model that was fine-tuned\n on 26.9K pairs of premise-hypothesis texts.\n\n- Developed by: Awab Alshami and Vansh Kharbanda\n- Language(s): English\n- Model type: Supervised\n- Model architecture: Transformers\n- Finetuned from model [optional]: roberta-base", "### Model Resources\n\n\n\n- Repository: URL\n- Paper or documentation: URL", "## Training Details", "### Training Data\n\n\n\n26.9k pairs of premise-hypothesis texts.", "### Training Procedure", "#### Training Hyperparameters\n\n\n\n\n - learning_rate: 2e-05\n - train_batch_size: 32\n - eval_batch_size: 32\n - num_epochs: 8", "#### Speeds, Sizes, Times\n\n\n\n\n - overall training time: 1.2 hours\n - duration per training epoch: 9 minutes\n - model size: 600 MB", "## Evaluation", "### Testing Data & Metrics", "#### Testing Data\n\n\n\nA subset of the development set provided, amounting to 6.7K pairs.", "#### Metrics\n\n\n\n\n - Precision: 0.882\n - Recall: 0.879\n - F1-score: 0.880\n - Accuracy: 0.880", "### Results\n\nThe model obtained a precision score of 88.2%, a recall score of 87.9%, an F1-score of 88% and an accuracy of 88%.", "## Technical Specifications", "### Hardware\n\n\n - RAM: at least 22.5 GB\n - Storage: at least 2GB,\n - GPU: A100", "### Software\n\n\n - Transformers 4.18.0\n - Pytorch 1.11.0+cu113", "## Bias, Risks, and Limitations\n\n\n\nAny inputs (concatenation of two sequences) longer than\n 512 subwords will be truncated by the model." ]

[ "TAGS\n#transformers #safetensors #roberta #text-classification #arxiv-1907.11692 #autotrain_compatible #endpoints_compatible #region-us \n", "# Model Card for j34330vk-q26752aa-NLI\n\n\n\nThis is a Natural Language Inference (NLI) classification model that was trained to\n detect if a hypothesis is true based on a premise.", "## Model Details", "### Model Description\n\n\n\nThis model is based upon a RoBERTa model that was fine-tuned\n on 26.9K pairs of premise-hypothesis texts.\n\n- Developed by: Awab Alshami and Vansh Kharbanda\n- Language(s): English\n- Model type: Supervised\n- Model architecture: Transformers\n- Finetuned from model [optional]: roberta-base", "### Model Resources\n\n\n\n- Repository: URL\n- Paper or documentation: URL", "## Training Details", "### Training Data\n\n\n\n26.9k pairs of premise-hypothesis texts.", "### Training Procedure", "#### Training Hyperparameters\n\n\n\n\n - learning_rate: 2e-05\n - train_batch_size: 32\n - eval_batch_size: 32\n - num_epochs: 8", "#### Speeds, Sizes, Times\n\n\n\n\n - overall training time: 1.2 hours\n - duration per training epoch: 9 minutes\n - model size: 600 MB", "## Evaluation", "### Testing Data & Metrics", "#### Testing Data\n\n\n\nA subset of the development set provided, amounting to 6.7K pairs.", "#### Metrics\n\n\n\n\n - Precision: 0.882\n - Recall: 0.879\n - F1-score: 0.880\n - Accuracy: 0.880", "### Results\n\nThe model obtained a precision score of 88.2%, a recall score of 87.9%, an F1-score of 88% and an accuracy of 88%.", "## Technical Specifications", "### Hardware\n\n\n - RAM: at least 22.5 GB\n - Storage: at least 2GB,\n - GPU: A100", "### Software\n\n\n - Transformers 4.18.0\n - Pytorch 1.11.0+cu113", "## Bias, Risks, and Limitations\n\n\n\nAny inputs (concatenation of two sequences) longer than\n 512 subwords will be truncated by the 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" ]

[ "transformers", "gguf", "imatrix", "MiniCPM-3B-OpenHermes-2.5-v2", "text-generation", "en", "license:other", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #imatrix #MiniCPM-3B-OpenHermes-2.5-v2 #text-generation #en #license-other #region-us \n" ]

[ "transformers", "pytorch", "chatglm", "feature-extraction", "custom_code", "license:apache-2.0", "region:us" ]

[]

[]

[ "# CNTDAI-6B", "## Model Description\nCNTDAI-6B 是 Community AI Model Group 为了进行POC来微调出来的符合公司需求的一个实验行模型，基于GLM Transformer模型进行微调的中英文LLM.采用了更多样的训练数据、更充分的训练步数和更合理的训练策略。在语义、数学、推理、代码、知识等不同角度的数据集上进行优化.\n\nCNTDAI-6B is an experimental model fine-tuned by the Community AI Model Group for POC to meet the company's internal needs. It is a Chinese and English LLM fine-tuned based on the GLM Transformer model. It uses more diverse training data and more sufficient training steps. numbers and more reasonable training strategies. Optimize on data sets from different perspectives such as semantics, mathematics, reasoning, code, knowledge, etc.", "## Usage" ]

[ "TAGS\n#transformers #pytorch #chatglm #feature-extraction #custom_code #license-apache-2.0 #region-us \n", "# CNTDAI-6B", "## Model Description\nCNTDAI-6B 是 Community AI Model Group 为了进行POC来微调出来的符合公司需求的一个实验行模型，基于GLM Transformer模型进行微调的中英文LLM.采用了更多样的训练数据、更充分的训练步数和更合理的训练策略。在语义、数学、推理、代码、知识等不同角度的数据集上进行优化.\n\nCNTDAI-6B is an experimental model fine-tuned by the Community AI Model Group for POC to meet the company's internal needs. It is a Chinese and English LLM fine-tuned based on the GLM Transformer model. It uses more diverse training data and more sufficient training steps. numbers and more reasonable training strategies. Optimize on data sets from different perspectives such as semantics, mathematics, reasoning, code, knowledge, etc.", "## Usage" ]

[ "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" ]

[ "transformers", "tensorboard", "safetensors", "mistral", "text-generation", "autotrain", "text-generation-inference", "peft", "conversational", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "# Model Trained Using AutoTrain\n\nThis model was trained using AutoTrain. For more information, please visit AutoTrain.", "# Usage" ]

[ "TAGS\n#transformers #tensorboard #safetensors #mistral #text-generation #autotrain #text-generation-inference #peft #conversational #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "# Model Trained Using AutoTrain\n\nThis model was trained using AutoTrain. For more information, please visit AutoTrain.", "# Usage" ]

[ "transformers", "safetensors", "llama", "text-generation", "not-for-all-audiences", "conversational", "en", "dataset:Intel/orca_dpo_pairs", "dataset:athirdpath/DPO_Pairs-Roleplay-Alpaca-NSFW", "dataset:Open-Orca/SlimOrca", "dataset:MinervaAI/Aesir-Preview", "dataset:allenai/ultrafeedback_binarized_cleaned", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[ "en" ]

[ "# GALAXY-16B-v1.0\n\n!image/png", "## Technical notes\n- 72 layers,DUS procedure, mistral(32)->SOLAR(48)->GALAXY(72)\n- 16B parameters\n- model created as a extension of depth upscaling procedure used for SOLAR by upstage", "## Results\n- model can and will produce NSFW content\n- waiting for eval results" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #not-for-all-audiences #conversational #en #dataset-Intel/orca_dpo_pairs #dataset-athirdpath/DPO_Pairs-Roleplay-Alpaca-NSFW #dataset-Open-Orca/SlimOrca #dataset-MinervaAI/Aesir-Preview #dataset-allenai/ultrafeedback_binarized_cleaned #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# GALAXY-16B-v1.0\n\n!image/png", "## Technical notes\n- 72 layers,DUS procedure, mistral(32)->SOLAR(48)->GALAXY(72)\n- 16B parameters\n- model created as a extension of depth upscaling procedure used for SOLAR by upstage", "## Results\n- model can and will produce NSFW content\n- waiting for eval results" ]

[ "transformers", "pytorch", "LEGO", "text-generation", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[]

[ "TAGS\n#transformers #pytorch #LEGO #text-generation #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n" ]

[ "transformers", "gguf", "Mistral", "en", "base_model:AIdenU/Mistral-7B-v0.2-ko-Y24_v2.0", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #Mistral #en #base_model-AIdenU/Mistral-7B-v0.2-ko-Y24_v2.0 #license-apache-2.0 #endpoints_compatible #region-us \n" ]

[ "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" ]

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

[]

[]

[ "# Fonglets Diathorn Pony XL\n\n<Gallery />", "## 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 #not-for-all-audiences #base_model-stablediffusionapi/pony-diffusion-v6-xl #region-us \n", "# Fonglets Diathorn Pony XL\n\n<Gallery />", "## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab." ]

[ "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" ]

[ "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" ]

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

[]

[]

[ "# HSE_PRAVO_complexity_classifier_roberta\n\nThis model is a fine-tuned version of FacebookAI/xlm-roberta-large on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0003\n- train_batch_size: 3\n- eval_batch_size: 3\n- seed: 42\n- gradient_accumulation_steps: 10\n- total_train_batch_size: 30\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- training_steps: 200", "### Training results", "### Framework versions\n\n- PEFT 0.10.1.dev0\n- Transformers 4.36.2\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-FacebookAI/xlm-roberta-large #license-mit #region-us \n", "# HSE_PRAVO_complexity_classifier_roberta\n\nThis model is a fine-tuned version of FacebookAI/xlm-roberta-large on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0003\n- train_batch_size: 3\n- eval_batch_size: 3\n- seed: 42\n- gradient_accumulation_steps: 10\n- total_train_batch_size: 30\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- training_steps: 200", "### Training results", "### Framework versions\n\n- PEFT 0.10.1.dev0\n- Transformers 4.36.2\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.15.2" ]

[ "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" ]

[ "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" ]

[ "transformers", "safetensors", "distilbert", "text-classification", "generated_from_trainer", "dataset:emotion", "base_model:distilbert-base-uncased", "license:apache-2.0", "model-index", "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: 64\n* eval\\_batch\\_size: 64\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 2", "### Training results", "### Framework versions\n\n\n* Transformers 4.36.0\n* Pytorch 2.2.1+cpu\n* Datasets 2.19.0\n* Tokenizers 0.15.0" ]

[ "TAGS\n#transformers #safetensors #distilbert #text-classification #generated_from_trainer #dataset-emotion #base_model-distilbert-base-uncased #license-apache-2.0 #model-index #autotrain_compatible #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 64\n* eval\\_batch\\_size: 64\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 2", "### Training results", "### Framework versions\n\n\n* Transformers 4.36.0\n* Pytorch 2.2.1+cpu\n* Datasets 2.19.0\n* Tokenizers 0.15.0" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mistralai/Mistral-7B-v0.1", "region:us" ]

[]

[]

[ "# mistralv1_spectral_r4_7e-5_e5_bf16\n\nThis model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 7e-05\n- train_batch_size: 4\n- eval_batch_size: 8\n- seed: 0\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- PEFT 0.9.0\n- Transformers 4.39.3\n- Pytorch 2.2.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mistralai/Mistral-7B-v0.1 #region-us \n", "# mistralv1_spectral_r4_7e-5_e5_bf16\n\nThis model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 7e-05\n- train_batch_size: 4\n- eval_batch_size: 8\n- seed: 0\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- PEFT 0.9.0\n- Transformers 4.39.3\n- Pytorch 2.2.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "peft", "tensorboard", "safetensors", "trl", "sft", "generated_from_trainer", "dataset:generator", "base_model:filipealmeida/Mistral-7B-Instruct-v0.1-sharded", "license:apache-2.0", "region:us" ]

[]

[]

[ "# mistral_7b_finetune_test2_sharded\n\nThis model is a fine-tuned version of filipealmeida/Mistral-7B-Instruct-v0.1-sharded 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: 4\n- eval_batch_size: 8\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 3", "### Training results", "### Framework versions\n\n- PEFT 0.10.0\n- Transformers 4.40.1\n- Pytorch 2.2.2+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "TAGS\n#peft #tensorboard #safetensors #trl #sft #generated_from_trainer #dataset-generator #base_model-filipealmeida/Mistral-7B-Instruct-v0.1-sharded #license-apache-2.0 #region-us \n", "# mistral_7b_finetune_test2_sharded\n\nThis model is a fine-tuned version of filipealmeida/Mistral-7B-Instruct-v0.1-sharded 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: 4\n- eval_batch_size: 8\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 3", "### Training results", "### Framework versions\n\n- PEFT 0.10.0\n- Transformers 4.40.1\n- Pytorch 2.2.2+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "transformers", "safetensors", "mistral", "text-generation", "text-generation-inference", "unsloth", "trl", "sft", "4bit", "2epochs", "BNP_25", "en", "base_model:unsloth/mistral-7b-bnb-4bit", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "8-bit", "region:us" ]

[]

[ "en" ]

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

[ "TAGS\n#transformers #safetensors #mistral #text-generation #text-generation-inference #unsloth #trl #sft #4bit #2epochs #BNP_25 #en #base_model-unsloth/mistral-7b-bnb-4bit #license-apache-2.0 #autotrain_compatible #endpoints_compatible #8-bit #region-us \n", "# Uploaded model\n\n- Developed by: tgey\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\"/>" ]

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

[ "transformers", "pytorch", "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 #pytorch #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" ]

[ "mlx", "safetensors", "openelm", "custom_code", "license:other", "region:us" ]

[]

[]

[ "# mlx-community/OpenELM-270M-instruct\nThis model was converted to MLX format from ['apple/OpenELM-270M-instruct']() using mlx-lm version 0.10.0.\nRefer to the original model card for more details on the model.", "## Use with mlx" ]

[ "TAGS\n#mlx #safetensors #openelm #custom_code #license-other #region-us \n", "# mlx-community/OpenELM-270M-instruct\nThis model was converted to MLX format from ['apple/OpenELM-270M-instruct']() using mlx-lm version 0.10.0.\nRefer to the original model card for more details on the model.", "## Use with mlx" ]

[ "transformers", "pytorch", "tensorboard", "roberta", "text-classification", "generated_from_trainer", "dataset:glue", "license:mit", "model-index", "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 4.16.2\n* Pytorch 2.2.1+cu121\n* Datasets 1.16.1\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #pytorch #tensorboard #roberta #text-classification #generated_from_trainer #dataset-glue #license-mit #model-index #autotrain_compatible #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 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 4.16.2\n* Pytorch 2.2.1+cu121\n* Datasets 1.16.1\n* Tokenizers 0.19.1" ]

[ "mlx", "safetensors", "openelm", "custom_code", "license:other", "region:us" ]

[]

[]

[ "# mlx-community/OpenELM-270M\nThis model was converted to MLX format from ['apple/OpenELM-270M']() using mlx-lm version 0.10.0.\nRefer to the original model card for more details on the model.", "## Use with mlx" ]

[ "TAGS\n#mlx #safetensors #openelm #custom_code #license-other #region-us \n", "# mlx-community/OpenELM-270M\nThis model was converted to MLX format from ['apple/OpenELM-270M']() using mlx-lm version 0.10.0.\nRefer to the original model card for more details on the model.", "## Use with mlx" ]

[ "safetensors", "generated_from_trainer", "base_model:microsoft/phi-2", "license:mit", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0003\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 16\n* total\\_train\\_batch\\_size: 128\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\\_with\\_restarts\n* lr\\_scheduler\\_warmup\\_steps: 100\n* num\\_epochs: 3\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.36.0.dev0\n* Pytorch 2.1.2+cu121\n* Datasets 2.18.0\n* Tokenizers 0.14.1" ]

[ "TAGS\n#safetensors #generated_from_trainer #base_model-microsoft/phi-2 #license-mit #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0003\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 16\n* total\\_train\\_batch\\_size: 128\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\\_with\\_restarts\n* lr\\_scheduler\\_warmup\\_steps: 100\n* num\\_epochs: 3\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.36.0.dev0\n* Pytorch 2.1.2+cu121\n* Datasets 2.18.0\n* Tokenizers 0.14.1" ]