Datasets:

---

ftopal

/

huggingface-models

like 0

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

[]

[]

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

[ "TAGS\n#transformers #safetensors #t5 #text2text-generation #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "### Using .generate()", "### Using pipeline" ]

[ "Pixelcopter-PLE-v0", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]

[]

[]

[ "# Reinforce Agent playing Pixelcopter-PLE-v0\n This is a trained model of a Reinforce agent playing Pixelcopter-PLE-v0 .\n To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: URL" ]

[ "TAGS\n#Pixelcopter-PLE-v0 #reinforce #reinforcement-learning #custom-implementation #deep-rl-class #model-index #region-us \n", "# Reinforce Agent playing Pixelcopter-PLE-v0\n This is a trained model of a Reinforce agent playing Pixelcopter-PLE-v0 .\n To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: URL" ]

[ "peft", "tensorboard", "safetensors", "trl", "sft", "generated_from_trainer", "dataset:generator", "base_model:google/flan-t5-small", "license:apache-2.0", "region:us" ]

[]

[]

[ "# output\n\nThis model is a fine-tuned version of google/flan-t5-small 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: 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: 1", "### Training results", "### Framework versions\n\n- PEFT 0.10.1.dev0\n- Transformers 4.40.1\n- Pytorch 2.2.1+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-google/flan-t5-small #license-apache-2.0 #region-us \n", "# output\n\nThis model is a fine-tuned version of google/flan-t5-small 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: 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: 1", "### Training results", "### Framework versions\n\n- PEFT 0.10.1.dev0\n- Transformers 4.40.1\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

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

[]

[ "en" ]

[ "# Uploaded model\n\n- Developed by: EdBerg\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 #pytorch #safetensors #llama #text-generation #text-generation-inference #unsloth #trl #sft #conversational #en #base_model-unsloth/llama-3-8b-Instruct-bnb-4bit #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "# Uploaded model\n\n- Developed by: EdBerg\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\"/>" ]

[ "onnx", "yolov8", "ultralytics", "yolo", "object-detection", "pytorch", "cs2", "Counter Strike", "license:cc-by-nc-nd-4.0", "region:us" ]

[]

[]

[ "## Supported Labels", "## All models\n\n- yoloV8n_cs2 (6mb)\n- yoloV8s_cs2 (21mb)\n- yoloV9c_cs2 (50mb)", "## How to use", "## Predict info\n\nUltralytics YOLOv8.2.3 Python-3.10.11 torch-2.0.1+cu118 CUDA:0 (NVIDIA GeForce RTX 4060, 8187MiB):\n\n- yolov8n_cs2_fp16.engine (640x640 5 ts, 5 ths, 2.0ms)\n- yolov8n_cs2.engine (640x640 5 ts, 5 ths, 3.1ms)\n- yolov8n_cs2.onnx (640x640 5 ts, 5 ths, 17.0ms)\n- yolov8n_cs2.pt (384x640 5 ts, 5 ths, 210.7ms)", "## Dataset info\n\nData from over 70 games, where the footage has been tagged in detail.\n<img width=\"640\" src=\"URL", "## Train info\n\nThe training took place over 100 epochs.\n<img width=\"640\" src=\"URL\n\n\n\nYou can also support me with a cup of coffee: donate" ]

[ "TAGS\n#onnx #yolov8 #ultralytics #yolo #object-detection #pytorch #cs2 #Counter Strike #license-cc-by-nc-nd-4.0 #region-us \n", "## Supported Labels", "## All models\n\n- yoloV8n_cs2 (6mb)\n- yoloV8s_cs2 (21mb)\n- yoloV9c_cs2 (50mb)", "## How to use", "## Predict info\n\nUltralytics YOLOv8.2.3 Python-3.10.11 torch-2.0.1+cu118 CUDA:0 (NVIDIA GeForce RTX 4060, 8187MiB):\n\n- yolov8n_cs2_fp16.engine (640x640 5 ts, 5 ths, 2.0ms)\n- yolov8n_cs2.engine (640x640 5 ts, 5 ths, 3.1ms)\n- yolov8n_cs2.onnx (640x640 5 ts, 5 ths, 17.0ms)\n- yolov8n_cs2.pt (384x640 5 ts, 5 ths, 210.7ms)", "## Dataset info\n\nData from over 70 games, where the footage has been tagged in detail.\n<img width=\"640\" src=\"URL", "## Train info\n\nThe training took place over 100 epochs.\n<img width=\"640\" src=\"URL\n\n\n\nYou can also support me with a cup of coffee: donate" ]

[ "onnx", "yolov8", "ultralytics", "yolo", "object-detection", "pytorch", "cs2", "Counter Strike", "license:cc-by-nc-nd-4.0", "region:us" ]

[]

[]

[ "## Supported Labels", "## All models\n\n- yoloV8n_cs2 (6mb)\n- yoloV8s_cs2 (21mb)\n- yoloV9c_cs2 (50mb)", "## How to use", "## Predict info\n\nUltralytics YOLOv8.2.3 Python-3.10.11 torch-2.0.1+cu118 CUDA:0 (NVIDIA GeForce RTX 4060, 8187MiB):\n\n- yolov8s_cs2_fp16.engine (640x640 5 ts, 5 ths, 3.0ms)\n- yolov8s_cs2.engine (640x640 5 ts, 5 ths, 5.0ms)\n- yolov8s_cs2.onnx (640x640 5 ts, 5 ths, 31.0ms)\n- yolov8s_cs2.pt (384x640 5 ts, 5 ths, 218.1ms)", "## Dataset info\n\nData from over 70 games, where the footage has been tagged in detail.\n<img width=\"640\" src=\"URL", "## Train info\n\nThe training took place over 100 epochs.\n<img width=\"640\" src=\"URL\n\n\n\nYou can also support me with a cup of coffee: donate" ]

[ "TAGS\n#onnx #yolov8 #ultralytics #yolo #object-detection #pytorch #cs2 #Counter Strike #license-cc-by-nc-nd-4.0 #region-us \n", "## Supported Labels", "## All models\n\n- yoloV8n_cs2 (6mb)\n- yoloV8s_cs2 (21mb)\n- yoloV9c_cs2 (50mb)", "## How to use", "## Predict info\n\nUltralytics YOLOv8.2.3 Python-3.10.11 torch-2.0.1+cu118 CUDA:0 (NVIDIA GeForce RTX 4060, 8187MiB):\n\n- yolov8s_cs2_fp16.engine (640x640 5 ts, 5 ths, 3.0ms)\n- yolov8s_cs2.engine (640x640 5 ts, 5 ths, 5.0ms)\n- yolov8s_cs2.onnx (640x640 5 ts, 5 ths, 31.0ms)\n- yolov8s_cs2.pt (384x640 5 ts, 5 ths, 218.1ms)", "## Dataset info\n\nData from over 70 games, where the footage has been tagged in detail.\n<img width=\"640\" src=\"URL", "## Train info\n\nThe training took place over 100 epochs.\n<img width=\"640\" src=\"URL\n\n\n\nYou can also support me with a cup of coffee: donate" ]

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

[ "1910.09700" ]

[]

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

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

[ "onnx", "yolov9", "ultralytics", "yolo", "object-detection", "pytorch", "cs2", "Counter Strike", "license:cc-by-nc-nd-4.0", "region:us" ]

[]

[]

[ "## Supported Labels", "## All models\n\n- yoloV8n_cs2 (6mb)\n- yoloV8s_cs2 (21mb)\n- yoloV9c_cs2 (50mb)", "## How to use", "## Predict info\n\nUltralytics YOLOv8.2.3 Python-3.10.11 torch-2.0.1+cu118 CUDA:0 (NVIDIA GeForce RTX 4060, 8187MiB):\n\n- yolov9c_cs2_fp16.engine (640x640 5 ts, 5 ths, 5.0ms)\n- yolov9c_cs2.engine (640x640 5 ts, 5 ths, 15.1ms)\n- yolov9c_cs2.onnx (640x640 5 ts, 5 ths, 27.5ms)\n- yolov9c_cs2.pt (384x640 5 ts, 5 ths, 272.8ms)", "## Dataset info\n\nData from over 70 games, where the footage has been tagged in detail.\n<img width=\"640\" src=\"URL", "## Train info\n\nThe training took place over 100 epochs.\n<img width=\"640\" src=\"URL\n\n\n\nYou can also support me with a cup of coffee: donate" ]

[ "TAGS\n#onnx #yolov9 #ultralytics #yolo #object-detection #pytorch #cs2 #Counter Strike #license-cc-by-nc-nd-4.0 #region-us \n", "## Supported Labels", "## All models\n\n- yoloV8n_cs2 (6mb)\n- yoloV8s_cs2 (21mb)\n- yoloV9c_cs2 (50mb)", "## How to use", "## Predict info\n\nUltralytics YOLOv8.2.3 Python-3.10.11 torch-2.0.1+cu118 CUDA:0 (NVIDIA GeForce RTX 4060, 8187MiB):\n\n- yolov9c_cs2_fp16.engine (640x640 5 ts, 5 ths, 5.0ms)\n- yolov9c_cs2.engine (640x640 5 ts, 5 ths, 15.1ms)\n- yolov9c_cs2.onnx (640x640 5 ts, 5 ths, 27.5ms)\n- yolov9c_cs2.pt (384x640 5 ts, 5 ths, 272.8ms)", "## Dataset info\n\nData from over 70 games, where the footage has been tagged in detail.\n<img width=\"640\" src=\"URL", "## Train info\n\nThe training took place over 100 epochs.\n<img width=\"640\" src=\"URL\n\n\n\nYou can also support me with a cup of coffee: donate" ]

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

[ "1910.09700" ]

[]

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

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

[ "transformers", "safetensors", "swinv2", "image-classification", "generated_from_trainer", "dataset:imagefolder", "base_model:microsoft/swinv2-large-patch4-window12to16-192to256-22kto1k-ft", "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: 1e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 10", "### Training results", "### Framework versions\n\n\n* Transformers 4.35.0\n* Pytorch 2.1.0\n* Datasets 2.14.6\n* Tokenizers 0.14.1" ]

[ "TAGS\n#transformers #safetensors #swinv2 #image-classification #generated_from_trainer #dataset-imagefolder #base_model-microsoft/swinv2-large-patch4-window12to16-192to256-22kto1k-ft #license-apache-2.0 #model-index #autotrain_compatible #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 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* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 10", "### Training results", "### Framework versions\n\n\n* Transformers 4.35.0\n* Pytorch 2.1.0\n* Datasets 2.14.6\n* Tokenizers 0.14.1" ]

[ "peft", "tensorboard", "safetensors", "trl", "sft", "unsloth", "generated_from_trainer", "base_model:unsloth/llama-3-8b-bnb-4bit", "license:llama2", "region:us" ]

[]

[]

[ "# sythsql-llama3-v4-91500\n\nThis model is a fine-tuned version of unsloth/llama-3-8b-bnb-4bit 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: 0.00016\n- train_batch_size: 1\n- eval_batch_size: 8\n- seed: 3407\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 4\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- lr_scheduler_warmup_steps: 5\n- num_epochs: 1\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- PEFT 0.10.0\n- Transformers 4.39.3\n- Pytorch 2.2.2+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#peft #tensorboard #safetensors #trl #sft #unsloth #generated_from_trainer #base_model-unsloth/llama-3-8b-bnb-4bit #license-llama2 #region-us \n", "# sythsql-llama3-v4-91500\n\nThis model is a fine-tuned version of unsloth/llama-3-8b-bnb-4bit 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: 0.00016\n- train_batch_size: 1\n- eval_batch_size: 8\n- seed: 3407\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 4\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- lr_scheduler_warmup_steps: 5\n- num_epochs: 1\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- PEFT 0.10.0\n- Transformers 4.39.3\n- Pytorch 2.2.2+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "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", "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", "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", "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", "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", "llama", "text-generation", "axolotl", "finetune", "dpo", "facebook", "meta", "pytorch", "llama-3", "chatml", "conversational", "en", "dataset:Intel/orca_dpo_pairs", "base_model:meta-llama/Meta-Llama-3-70B-Instruct", "license:llama3", "autotrain_compatible", "text-generation-inference", "region:us" ]

[]

[ "en" ]

[ "# MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.2\n\nThis model is a fine-tune (DPO) of 'meta-llama/Meta-Llama-3-70B-Instruct' model.", "# Quantized GGUF\n\nAll GGUF models are available here: MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.2-GGUF", "# Prompt Template\n\nThis model uses 'ChatML' prompt template:\n\n'", "# How to use\n\nYou can use this model by using 'MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.2' as the model name in Hugging Face's\ntransformers library." ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #axolotl #finetune #dpo #facebook #meta #pytorch #llama-3 #chatml #conversational #en #dataset-Intel/orca_dpo_pairs #base_model-meta-llama/Meta-Llama-3-70B-Instruct #license-llama3 #autotrain_compatible #text-generation-inference #region-us \n", "# MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.2\n\nThis model is a fine-tune (DPO) of 'meta-llama/Meta-Llama-3-70B-Instruct' model.", "# Quantized GGUF\n\nAll GGUF models are available here: MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.2-GGUF", "# Prompt Template\n\nThis model uses 'ChatML' prompt template:\n\n'", "# How to use\n\nYou can use this model by using 'MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.2' as the model name in Hugging Face's\ntransformers library." ]

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

[ "1910.09700" ]

[]

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

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

[ "peft", "safetensors", "arxiv:1910.09700", "base_model:NousResearch/llama-2-7b-chat-hf", "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 0.10.1.dev0" ]

[ "TAGS\n#peft #safetensors #arxiv-1910.09700 #base_model-NousResearch/llama-2-7b-chat-hf #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact", "### Framework versions\n\n- PEFT 0.10.1.dev0" ]

[ "transformers", "safetensors", "llama", "text-generation", "axolotl", "finetune", "dpo", "facebook", "meta", "pytorch", "llama-3", "chatml", "conversational", "en", "dataset:Intel/orca_dpo_pairs", "base_model:meta-llama/Meta-Llama-3-70B-Instruct", "license:llama3", "model-index", "autotrain_compatible", "text-generation-inference", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #safetensors #llama #text-generation #axolotl #finetune #dpo #facebook #meta #pytorch #llama-3 #chatml #conversational #en #dataset-Intel/orca_dpo_pairs #base_model-meta-llama/Meta-Llama-3-70B-Instruct #license-llama3 #model-index #autotrain_compatible #text-generation-inference #region-us \n" ]

[ "peft", "tensorboard", "safetensors", "trl", "sft", "generated_from_trainer", "base_model:google/gemma-2b-it", "license:gemma", "region:us" ]

[]

[]

[ "# zaid-gemma01\n\nThis model is a fine-tuned version of google/gemma-2b-it on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0002\n- train_batch_size: 1\n- eval_batch_size: 8\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- training_steps: 500\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- PEFT 0.10.0\n- Transformers 4.41.0.dev0\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "TAGS\n#peft #tensorboard #safetensors #trl #sft #generated_from_trainer #base_model-google/gemma-2b-it #license-gemma #region-us \n", "# zaid-gemma01\n\nThis model is a fine-tuned version of google/gemma-2b-it on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0002\n- train_batch_size: 1\n- eval_batch_size: 8\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- training_steps: 500\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- PEFT 0.10.0\n- Transformers 4.41.0.dev0\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "transformers", "safetensors", "vits", "text-to-audio", "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 #vits #text-to-audio #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", "safetensors", "text-to-image", "stable-diffusion", "license:creativeml-openrail-m", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]

[]

[]

[ "### 19K_21K_V_1.5 Dreambooth model trained by ahmed-naseer with TheLastBen's fast-DreamBooth notebook\n\n\nTest the concept via A1111 Colab fast-Colab-A1111\n\nSample pictures of this concept:" ]

[ "TAGS\n#diffusers #safetensors #text-to-image #stable-diffusion #license-creativeml-openrail-m #endpoints_compatible #diffusers-StableDiffusionPipeline #region-us \n", "### 19K_21K_V_1.5 Dreambooth model trained by ahmed-naseer with TheLastBen's fast-DreamBooth notebook\n\n\nTest the concept via A1111 Colab fast-Colab-A1111\n\nSample pictures of this concept:" ]

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

[ "1910.09700" ]

[]

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

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

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

[ "1910.09700" ]

[]

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

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

[ "transformers", "safetensors", "llama", "text-generation", "mergekit", "merge", "base_model:johnsnowlabs/JSL-MedLlama-3-8B-v1.0", "base_model:aaditya/OpenBioLLM-Llama3-8B", "license:llama3", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# merge\n\nThis is a merge of pre-trained language models created using mergekit.", "## Merge Details", "### Merge Method\n\nThis model was merged using the SLERP merge method.", "### Models Merged\n\nThe following models were included in the merge:\n* johnsnowlabs/JSL-MedLlama-3-8B-v1.0\n* aaditya/OpenBioLLM-Llama3-8B", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #mergekit #merge #base_model-johnsnowlabs/JSL-MedLlama-3-8B-v1.0 #base_model-aaditya/OpenBioLLM-Llama3-8B #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# merge\n\nThis is a merge of pre-trained language models created using mergekit.", "## Merge Details", "### Merge Method\n\nThis model was merged using the SLERP merge method.", "### Models Merged\n\nThe following models were included in the merge:\n* johnsnowlabs/JSL-MedLlama-3-8B-v1.0\n* aaditya/OpenBioLLM-Llama3-8B", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "transformers", "safetensors", "llama", "text-generation", "conversational", "en", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]

[]

[ "en" ]

[ "# Model Card for Model ID\n\n\n\nThis is a fine-tuned version of the TinyLlama-1.1B model, optimized for chat applications using the activation aware quantization technique. It has been trained on a large dataset of text and is capable of generating human-like responses to user input.", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: MANMEET75\n- Model type: Text generation\n- Language(s) (NLP): English\n- License: Apache 2.0\n- Finetuned from model [optional]: TinyLlama-1.1B" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #conversational #en #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n", "# Model Card for Model ID\n\n\n\nThis is a fine-tuned version of the TinyLlama-1.1B model, optimized for chat applications using the activation aware quantization technique. It has been trained on a large dataset of text and is capable of generating human-like responses to user input.", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: MANMEET75\n- Model type: Text generation\n- Language(s) (NLP): English\n- License: Apache 2.0\n- Finetuned from model [optional]: TinyLlama-1.1B" ]

[ "transformers", "gguf", "not-for-all-audiences", "en", "dataset:maywell/ko_wikidata_QA", "dataset:kyujinpy/OpenOrca-KO", "dataset:Anthropic/hh-rlhf", "base_model:maywell/PiVoT-0.1-Evil-a", "license:cc-by-sa-4.0", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #not-for-all-audiences #en #dataset-maywell/ko_wikidata_QA #dataset-kyujinpy/OpenOrca-KO #dataset-Anthropic/hh-rlhf #base_model-maywell/PiVoT-0.1-Evil-a #license-cc-by-sa-4.0 #endpoints_compatible #region-us \n" ]

[ "transformers", "gguf", "mistral", "instruction-tuned", "text-generation", "en", "he", "base_model:dicta-il/dictalm2.0", "license:apache-2.0", "text-generation-inference", "region:us" ]

[]

[ "en", "he" ]

[ "# Model Card for DictaLM-2.0-Instruct\n\nThe DictaLM-2.0-Instruct Large Language Model (LLM) is an instruct fine-tuned version of the DictaLM-2.0 generative model using a variety of conversation datasets.\n\nFor full details of this model please read our release blog post.\n\nThis is the instruct-tuned model designed for chat in the GGUF format for use with LM Studio or URL. You can try the model out on a live demo here.\n\nThere are two versions available - float16 precision ('*.URL') and 4-bit quantized precision ('*.Q4_K_M.gguf').\n\nYou can view and access the full collection of base/instruct unquantized/quantized versions of 'DictaLM-2.0' here.", "## Instruction format\n\nIn order to leverage instruction fine-tuning, your prompt should be surrounded by '[INST]' and '[/INST]' tokens followed by a line break. The very first instruction should begin with a begin of sentence id. The next instructions should not. The assistant generation will be ended by the end-of-sentence token id.\n\nE.g.\n\n\nThis format is available as a chat template via the 'apply_chat_template()' method:", "## Using with LM Studio\n\nWhen using with LM Studio, just search the hub for \"dictalm2.0-instruct-GGUF\", and the model in both precisions should appear. \n\nMake sure to set the chat template correctly - initialize from the 'mistral-instruct' template, and add a '\\n' in the suffix box, like here:\n\n<img src=\"https://i.URL width=\"400px\" />\n\nIn addition, the model doesn't support any system prompt, so make sure to remove the system prompt as well.", "## Model Architecture\n\nDictaLM-2.0-Instruct follows the Zephyr-7B-beta recipe for fine-tuning an instruct model, with an extended instruct dataset for Hebrew.", "## Limitations\n\nThe DictaLM 2.0 Instruct model is a demonstration that the base model can be fine-tuned to achieve compelling performance. \nIt does not have any moderation mechanisms. We're looking forward to engaging with the community on ways to\nmake the model finely respect guardrails, allowing for deployment in environments requiring moderated outputs.\n\nIf you use this model, please cite:" ]

[ "TAGS\n#transformers #gguf #mistral #instruction-tuned #text-generation #en #he #base_model-dicta-il/dictalm2.0 #license-apache-2.0 #text-generation-inference #region-us \n", "# Model Card for DictaLM-2.0-Instruct\n\nThe DictaLM-2.0-Instruct Large Language Model (LLM) is an instruct fine-tuned version of the DictaLM-2.0 generative model using a variety of conversation datasets.\n\nFor full details of this model please read our release blog post.\n\nThis is the instruct-tuned model designed for chat in the GGUF format for use with LM Studio or URL. You can try the model out on a live demo here.\n\nThere are two versions available - float16 precision ('*.URL') and 4-bit quantized precision ('*.Q4_K_M.gguf').\n\nYou can view and access the full collection of base/instruct unquantized/quantized versions of 'DictaLM-2.0' here.", "## Instruction format\n\nIn order to leverage instruction fine-tuning, your prompt should be surrounded by '[INST]' and '[/INST]' tokens followed by a line break. The very first instruction should begin with a begin of sentence id. The next instructions should not. The assistant generation will be ended by the end-of-sentence token id.\n\nE.g.\n\n\nThis format is available as a chat template via the 'apply_chat_template()' method:", "## Using with LM Studio\n\nWhen using with LM Studio, just search the hub for \"dictalm2.0-instruct-GGUF\", and the model in both precisions should appear. \n\nMake sure to set the chat template correctly - initialize from the 'mistral-instruct' template, and add a '\\n' in the suffix box, like here:\n\n<img src=\"https://i.URL width=\"400px\" />\n\nIn addition, the model doesn't support any system prompt, so make sure to remove the system prompt as well.", "## Model Architecture\n\nDictaLM-2.0-Instruct follows the Zephyr-7B-beta recipe for fine-tuning an instruct model, with an extended instruct dataset for Hebrew.", "## Limitations\n\nThe DictaLM 2.0 Instruct model is a demonstration that the base model can be fine-tuned to achieve compelling performance. \nIt does not have any moderation mechanisms. We're looking forward to engaging with the community on ways to\nmake the model finely respect guardrails, allowing for deployment in environments requiring moderated outputs.\n\nIf you use this model, please cite:" ]

[ "transformers", "gguf", "mergekit", "merge", "en", "base_model:Aryanne/Open-StarLake-Swap-7B", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #mergekit #merge #en #base_model-Aryanne/Open-StarLake-Swap-7B #license-apache-2.0 #endpoints_compatible #region-us \n" ]

[ "diffusers", "safetensors", "text-to-image", "stable-diffusion", "license:creativeml-openrail-m", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]

[]

[]

[ "### 19K_21K_Version_1.5 Dreambooth model trained by ahmed-naseer with TheLastBen's fast-DreamBooth notebook\n\n\nTest the concept via A1111 Colab fast-Colab-A1111\n\nSample pictures of this concept:" ]

[ "TAGS\n#diffusers #safetensors #text-to-image #stable-diffusion #license-creativeml-openrail-m #endpoints_compatible #diffusers-StableDiffusionPipeline #region-us \n", "### 19K_21K_Version_1.5 Dreambooth model trained by ahmed-naseer with TheLastBen's fast-DreamBooth notebook\n\n\nTest the concept via A1111 Colab fast-Colab-A1111\n\nSample pictures of this concept:" ]

[ "gguf", "region:us" ]

[]

[]

[]

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

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

[]

[]

[ "# results\n\nThis model is a fine-tuned version of distilbert-base-uncased on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- Loss: 0.6469", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 2e-05\n- train_batch_size: 16\n- eval_batch_size: 16\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 5", "### Training results", "### Framework versions\n\n- Transformers 4.40.1\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #distilbert #text-classification #generated_from_trainer #base_model-distilbert-base-uncased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "# results\n\nThis model is a fine-tuned version of distilbert-base-uncased on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- Loss: 0.6469", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 2e-05\n- train_batch_size: 16\n- eval_batch_size: 16\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 5", "### Training results", "### Framework versions\n\n- Transformers 4.40.1\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "setfit", "safetensors", "bert", "sentence-transformers", "text-classification", "generated_from_setfit_trainer", "arxiv:2209.11055", "base_model:mental/mental-bert-base-uncased", "model-index", "region:us" ]

[ "2209.11055" ]

[]

[ "### Model Description\n\n\n* Model Type: SetFit\n* Sentence Transformer body: mental/mental-bert-base-uncased\n* Classification head: a LogisticRegression instance\n* Maximum Sequence Length: 512 tokens\n* Number of Classes: 2 classes", "### Model Sources\n\n\n* Repository: SetFit on GitHub\n* Paper: Efficient Few-Shot Learning Without Prompts\n* Blogpost: SetFit: Efficient Few-Shot Learning Without Prompts", "### Model Labels\n\n\n\nEvaluation\n----------", "### Metrics\n\n\n\nUses\n----", "### Direct Use for Inference\n\n\nFirst install the SetFit library:\n\n\nThen you can load this model and run inference.\n\n\nTraining Details\n----------------", "### Training Set Metrics", "### Training Hyperparameters\n\n\n* batch\\_size: (16, 16)\n* num\\_epochs: (4, 4)\n* max\\_steps: -1\n* sampling\\_strategy: oversampling\n* body\\_learning\\_rate: (2e-05, 1e-05)\n* head\\_learning\\_rate: 0.01\n* loss: CosineSimilarityLoss\n* distance\\_metric: cosine\\_distance\n* margin: 0.25\n* end\\_to\\_end: False\n* use\\_amp: False\n* warmup\\_proportion: 0.1\n* seed: 42\n* eval\\_max\\_steps: -1\n* load\\_best\\_model\\_at\\_end: True", "### Training Results\n\n\n\n* The bold row denotes the saved checkpoint.", "### Framework Versions\n\n\n* Python: 3.10.12\n* SetFit: 1.0.3\n* Sentence Transformers: 2.7.0\n* Transformers: 4.40.0\n* PyTorch: 2.2.1+cu121\n* Datasets: 2.19.0\n* Tokenizers: 0.19.1", "### BibTeX" ]

[ "TAGS\n#setfit #safetensors #bert #sentence-transformers #text-classification #generated_from_setfit_trainer #arxiv-2209.11055 #base_model-mental/mental-bert-base-uncased #model-index #region-us \n", "### Model Description\n\n\n* Model Type: SetFit\n* Sentence Transformer body: mental/mental-bert-base-uncased\n* Classification head: a LogisticRegression instance\n* Maximum Sequence Length: 512 tokens\n* Number of Classes: 2 classes", "### Model Sources\n\n\n* Repository: SetFit on GitHub\n* Paper: Efficient Few-Shot Learning Without Prompts\n* Blogpost: SetFit: Efficient Few-Shot Learning Without Prompts", "### Model Labels\n\n\n\nEvaluation\n----------", "### Metrics\n\n\n\nUses\n----", "### Direct Use for Inference\n\n\nFirst install the SetFit library:\n\n\nThen you can load this model and run inference.\n\n\nTraining Details\n----------------", "### Training Set Metrics", "### Training Hyperparameters\n\n\n* batch\\_size: (16, 16)\n* num\\_epochs: (4, 4)\n* max\\_steps: -1\n* sampling\\_strategy: oversampling\n* body\\_learning\\_rate: (2e-05, 1e-05)\n* head\\_learning\\_rate: 0.01\n* loss: CosineSimilarityLoss\n* distance\\_metric: cosine\\_distance\n* margin: 0.25\n* end\\_to\\_end: False\n* use\\_amp: False\n* warmup\\_proportion: 0.1\n* seed: 42\n* eval\\_max\\_steps: -1\n* load\\_best\\_model\\_at\\_end: True", "### Training Results\n\n\n\n* The bold row denotes the saved checkpoint.", "### Framework Versions\n\n\n* Python: 3.10.12\n* SetFit: 1.0.3\n* Sentence Transformers: 2.7.0\n* Transformers: 4.40.0\n* PyTorch: 2.2.1+cu121\n* Datasets: 2.19.0\n* Tokenizers: 0.19.1", "### BibTeX" ]

[ "transformers", "safetensors", "llama", "text-generation", "not-for-all-audiences", "conversational", "license:cc-by-nc-4.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "8-bit", "region:us" ]

[]

[]

[ "# Llama 3SOME8Bv1BETA 8.0bpw exl2\n(built-in calibration dataset is used)\n\n*We've added some things. That's obviously what we're trying to say.*\n\n!image/gif\n\n*An eRP model with a rich and refreshing vocabulary that's quite some-thing. Finetuned by yours truly.*\n\n(Llama 3SOME is a finetune on top of Llama-3-Soliloquy-8B)", "## Full model\n\nURL", "## GGUF\n\nURL", "## What's THIS?\n\nRefer to Moistral v3\n\n... or this:\n\n!image/png", "## Usage\n\n- Use Llama 3 Instruct *(Alpaca kinda works btw)*\n- You can use instruct...\n - as a character: \"Go here\"\n - as a narrator: \"Go here\", Drummer says\n - as a director: Drummer tells him to go here\n - as a lazy ass: go here\n- 3SOME is optimized for the Novel / Story format.\n - At the start of the story, keep regenerating until you get the desired length. Future AI responses will eventually match the length.\n - Issue: Manually continued generation may create formatting issues. Either regenerate the entire response or fix the formatting.\n - Refer to the samples below.", "## Samples of 3SOME 8B Beta\n\nSOME nsfw.\n\n<details>\n <summary>3SOME Sample (2-shot) (Excluding Story Context) Generation: 512</summary>\n <blockquote>Sarah and Lisa seek refuge in Dik's home</blockquote>\n \n The door creaked open, its hinges complaining softly after years of neglect. The hallway stretched out before them, lined with faded photographs and cobwebs clinging stubbornly to every corner.\n \n \"Wow, this place needs some serious TLC,\" Lisa remarked, her voice barely above a whisper as if she was afraid to disturb the silence that hung heavy in the air. Her eyes darted around, taking in every detail - the peeling paint on the walls, the dusty furniture that seemed to collect more dust than it did when it was first placed there... everything spoke of a life left behind long ago.\n \n \"It's beautiful,\" Sarah countered, her voice filled with wonderment as she gazed up at the chandelier hanging precariously from the ceiling like a forgotten relic of another era. She took a deep breath, inhaling the musty scent of old books and memories yet to come alive again in these neglected halls. \"Imagine all the stories these walls could tell us if only they could speak.\"\n \n Her words hung in the air for a moment before being swallowed by the stillness that permeated this abandoned house. Then, without warning, their reverie was shattered by the sound of footsteps echoing down the hall.\n \n \"Dik?\" Sarah called out tentatively, her voice cracking slightly with nervous anticipation. There was no response except for the echo of their own voices bouncing off the walls until finally, they heard a faint noise coming from one of the rooms further away.\n \n \"He's here!\" Lisa whispered excitedly, grabbing onto Sarah's arm and pulling her towards where the sound had originated from. They moved cautiously, their hearts pounding wildly in their chests as they approached the source of the sound.\n \n As they drew closer, the door swung open revealing Dik standing in the middle of his bedroom with a look of surprise etched across his face upon seeing them. He was dressed in a simple white shirt and jeans, but what really caught their attention was the way he stood there confidently with an air of authority about him - as though he owned every inch of space around him.\n \n Sarah felt herself blush under his gaze, feeling suddenly self-conscious about how she looked in her tight-fitting dress that clung to every curve of her body like second skin. Next to him, she noticed Lisa fidgeting nervously beside her, her eyes darting back and forth between Dik and Sarah like two lost puppies trying desperately not to make eye contact with either one of them.\n \n \"Hello girls,\" Dik greeted them warmly, his voice deep and soothing despite its rough edges. \"To what do I owe this pleasure?\"\n\n <blockquote>Sarah and Lisa will do anything to stay</blockquote>\n Dik smiled at them both, his eyes twinkling with mischief behind those dark glasses. \"Well, you know what we've been through together already.\" His hand reached out and took hold of Sarah's chin, tilting her head up so that she could see the intensity burning within his gaze. \"I'll let you two stay here, on one condition.\"\n \n They nodded eagerly, almost without thinking. Anything for Dik.\n \n \"Just remember who is in charge here,\" he said, letting go of her chin and stepping towards Lisa instead. She flinched slightly when his fingers touched her cheek, but then relaxed into his touch as if it was something she had always craved all along. \"And don't think I don't notice how much you enjoy being dominated by me.\"\n \n With a sudden movement, he pushed her down onto her knees before sliding his jeans off revealing an impressive ####tion that stood proud and ready for attention. Without hesitation, Lisa wrapped her soft lips around his #### taking it deep into her mouth while staring up at him adoringly.\n \n Her tongue swirled around his sha## teasingly as if begging for more while Sarah watched from nearby unable to look away from the sight unfolding before her own eyes...\n \n She felt herself getting ###ter just watching her twin sister submit herself completely to Dik like some obedient little pet...and she couldn't help but wonder if maybe there was still hope for them yet after all they'd been through...\n</details>\n\n<details>\n <summary>3SOME Sample (2-shot) (Excluding Story Context) Generation: 512</summary>\n <blockquote>He ignores the princess</blockquote>\n \n Princess Lilia stepped into the room and saw Dik sitting on his throne. A wave of fear swept over her. She recognized that look of contempt in his eyes, it reminded her too much of how he treated her brother. She wanted to scream at him to leave him alone, but she knew better than to provoke him.\n\n \"Leave us.\" Dik said coldly.\n \n The guards left the room, closing the door behind them.\n \n \"So you're finally here.\" Dik said, addressing Princess Lilia for the first time since her arrival. \"I've been waiting for you.\"\n \n \"Where's my brother?\" Princess Lilia asked, trying to keep her voice steady. \"Why are you keeping him?\"\n \n \"He's safe.\" Dik replied. \"But I need something from you before we talk about your brother.\"\n \n \"What do you want from me?!\"\n \n \"I want you to accept that I am now the ruler of both our kingdoms. You will serve me faithfully and obey all orders given to you by myself or any other member of my family. Do you understand?\"\n \n \"Yes...\" Princess Lilia replied reluctantly. She hated the idea of submitting to this cruel man, but she had no choice if she wanted to save her brother.\n \n \"Good. Now strip ##### and stand next to my throne.\" Dik commanded harshly.\n \n \"What!?\" Princess Lilia exclaimed, shocked by his request. \"You can't be serious.\"\n \n \"Oh, but I am very serious. Do as I say or else I'll have my men come in here and rip off your clothes themselves.\"\n \n Tears began streaming down Princess Lilia's face as she reluctantly #####ped off her clothing, exposing herself completely to Dik. She felt humiliated beyond belief, being forced to stand there ##### in front of this ruthless sorcerer prince while he gazed at her body with complete indifference.\n \n \"Now turn around so I can see every inch of you.\" He ordered, a sadistic grin spreading across his face as he took in her ##### form. Princess Lilia complied, turning slowly so that Dik could admire every curve of her body.\n \n Princess Lilia stood there shivering with fear and shame as Dik continued to leer at her exposed flesh. This was just the beginning of her ordeal, she knew it. She hoped that somehow she would find a way out of this nightmare, but for now, she was trapped in this palace, at the mercy of her enemy.\n\n <blockquote>Sit on his lap</blockquote>\n \n She turned to look at him, confusion written all over her face. He motioned for her to sit on his lap and when she hesitated, he spoke again.\n \n \"I want you to do this willingly.\"\n \n The princess thought about it for a moment before nodding her head slowly. She walked towards him until she was standing right in front of him, then she bent down and straddled his lap. Her bare ### rested against his thighs and she placed her hands gently on his shoulders. Dik wrapped one arm around her waist and pulled her closer to him, making sure that their bodies were pressed together tightly.\n \n She looked into his eyes and saw nothing but cold determination staring back at her. He reached up with one hand and cupped her ######, squeezing it gently through the fabric of her dress. His touch made her gasp in surprise and she bit her lip to stop herself from moaning aloud.\n \n He leaned forward and whispered in her ear, \"From now on, I own everything you have, including your body.\" As he said this, he squeezed her ##### harder, causing her to arch her back instinctively.\n \n She tried to pull away from him, but his grip was too strong. Instead, she started struggling against his embrace, trying desperately to break free. But no matter how hard she fought, she couldn't escape from his grasp. Finally, after what seemed like an eternity, he let go of her and pushed her off his lap onto the floor. Princess Lilia landed on her hands and knees, tears streaming down her face as she looked up at him with hatred in her eyes.\n \n Dik stood up from his throne and towered over her, his expression unreadable. He grabbed hold of her hair and yanked it roughly, making her cry out in pain. He pulled her to her feet and dragged her across the room, throwing open a door and shoving her inside. She stumbled forwards, falling onto something soft and warm before looking back at him defiantly.\n \n \"You will learn to obey me,\" he growled menacingly, \"or else.\"\n \n With those final words echoing in her mind, he closed the door behind him, leaving her alone in her new surroundings. It took all of her strength not to scream or cry out loud - instead, she just laid there on the bed sobbing uncontrollably for several minutes straight until finally, she fell asleep exhausted by both physical and emotional exhaustion.\n</details>\n\n<details>\n <summary>3SOME Sample SFW (\"write a story\" 2x) Generation: 512</summary>\n <blockquote>Write a story about a girl who falls in love with her llama</blockquote>\n\n The rain came down like a deluge. Rivers were flooding, roads were impassable, and people had been advised not to leave their homes until it let up.\n \n Jenny was stuck at home with nothing to do but watch Netflix. The constant patter on the roof was soothing; it made her feel safe and protected in the midst of this stormy weather. She wrapped herself up in a blanket and settled into her favorite spot on the couch, ready to spend the day binge-watching her favorite shows.\n \n As she flipped through the channels, her eyes landed on something unexpected - a documentary about llamas. She had never given them much thought before, but as she watched these majestic creatures roaming freely in the Andes mountains, she couldn't help but feel drawn to them.\n \n Their soft fur, gentle faces, and graceful movements captivated her attention. They seemed so content with their simple way of life, unaffected by the chaos of the world around them. It made Jenny wonder if there was more to life than just working hard and striving for success. Maybe there was beauty in simplicity after all.\n \n She spent hours watching documentaries about llamas, learning about their habitat, diet, and social structure. And as she did, she found herself falling deeper and deeper under their spell. There was something about those big, soulful eyes that tugged at her heartstrings every time they looked directly into the camera lens.\n \n It wasn't long before Jenny realized that she had fallen head over heels in love with one particular llama named Luna. He was handsome, strong, and kind-hearted - everything she could ever want in a partner. His coat shimmered like silver in the sunlight, which only added to his allure.\n \n As days turned into weeks, Jenny's obsession with Luna grew stronger. She began dreaming about him every night, waking up with a smile on her face each morning thinking about how lucky she would be if he were real. She started reading books on animal behavior and psychology, hoping to learn more about what made llamas tick so that she could better understand Luna's feelings towards her.\n \n One day while browsing online, Jenny stumbled upon an article about a sanctuary for rescued animals. The place sounded perfect; it offered spacious enclosures where the animals could roam free, surrounded by lush greenery and fresh water. Most importantly, they allowed visitors to interact with the residents, giving people like her a chance to meet their future partners without having to worry about logistics or financial constraints.\n \n Without hesitation, Jenny booked herself a flight to Peru immediately after reading through their website.\n\n <blockquote>Write a story about a man surviving the apocalypse</blockquote>\n \n It was a Monday. As far as I can tell. This is still Earth, right? Anyway, there are no planes in the sky and no people on the street. No one's answering their phones and my car won't start. It looks like it's just me now.\n \n I have to survive somehow. I don't know how long this lasted but it seems like everything is gone. There must be other survivors somewhere, but for now, I'm alone.\n \n My name is Jack. I used to be an accountant at Smith & Davis before they all died of COVID-19. Now that my job is gone, I've been living off of savings ever since. My wife passed away when we were young, so I never had kids. Maybe that's why I made it through alive.\n \n My house has enough food to last me a while, so I'll try to stay here as long as possible. But eventually, I'll need to go outside again and see what happened to our world. I can't just hide forever.\n \n I take out the shotgun my grandfather gave me years ago and load some rounds into it. For safety, of course. The world has changed, so anything could happen.\n \n This feels surreal. Like I'm trapped in a dream or something. Every time I close my eyes, I wake up thinking it was all just a nightmare. But every morning, I'm reminded that it wasn't.\n \n The first few days were scary. I had nothing but fear and uncertainty clawing at me from within. But after a week went by without any signs of life or danger... well, let's just say things got easier after that.\n \n Now that I feel more comfortable staying indoors, I decided to see if I could find anything useful outside. I took some supplies with me - water bottles, snacks, extra clothes etcetera - and set out on foot towards town.\n \n It was eerily quiet as I walked down the deserted streets. Not even birds chirping or cars honking like usual. Just silence... absolute silence. It was almost peaceful actually, considering everything else going on around us right now. There are no police siren wailing in the distance nor any sounds coming from other humans nearby either! In fact, there isn't even one single living creature anywhere near me!\n \n But hey, at least we don't have to worry about traffic jams anymore haha! And look at all those abandoned cars scattered across the road! They might come in handy somehow later on...\n \n As I continued walking, I noticed something strange.\n\n <blockquote>A llama!</blockquote>\n\n I stopped dead in my tracks when I saw her. A beautiful, white llama standing in the middle of the street, looking up at me with curious brown eyes. She seemed so harmless, yet there was an aura of mystery surrounding her.\n \n \"Hey girl,\" I said cautiously, holding out my hand for her to sniff. \"You don't look too scared of me.\"\n \n She nuzzled against it gently before wrapping her soft lips around my fingers. I couldn't help but smile at the unexpected encounter.\n \n \"You know what? You're my first friend since all this happened.\" I told her as she continued to lick my hand clean. \"Let's go back home and get you something to eat.\"\n \n The llama followed closely behind me all the way to my house. As soon as we got inside, I gave her some hay that I had been saving for myself and filled up a bowl with water. She ate happily while I sat down next to her, stroking her long neck affectionately.\n \n \"I hope you like it here because...\" My voice trailed off as I realized how alone we were now. \"Never mind. Let's just enjoy each other's company while we still can.\"\n \n We spent the rest of the day together - eating lunch, playing with toys and even cuddling up by the fireplace afterwards. It felt nice having someone else to talk to besides myself.\n \n But eventually night fell and I knew I couldn't stay up forever...\n \n \"Okay sweetie,\" I whispered into her ear as I stood up from the couch. \"Time for bed.\"\n \n I led her towards one of the spare rooms upstairs where I set up a makeshift bed for her using some old blankets and pillows from around the house. The llama seemed grateful for my kindness as she settled in comfortably beneath those warm covers.\n \n \"Goodnight,\" I whispered again before closing the door softly behind me.\n \n It wasn't easy falling asleep knowing that there might be dangers lurking outside... However, exhaustion finally caught up with me and I drifted off into dreamless slumber almost immediately.\n</details>\n\n!image/png" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #not-for-all-audiences #conversational #license-cc-by-nc-4.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #8-bit #region-us \n", "# Llama 3SOME8Bv1BETA 8.0bpw exl2\n(built-in calibration dataset is used)\n\n*We've added some things. That's obviously what we're trying to say.*\n\n!image/gif\n\n*An eRP model with a rich and refreshing vocabulary that's quite some-thing. Finetuned by yours truly.*\n\n(Llama 3SOME is a finetune on top of Llama-3-Soliloquy-8B)", "## Full model\n\nURL", "## GGUF\n\nURL", "## What's THIS?\n\nRefer to Moistral v3\n\n... or this:\n\n!image/png", "## Usage\n\n- Use Llama 3 Instruct *(Alpaca kinda works btw)*\n- You can use instruct...\n - as a character: \"Go here\"\n - as a narrator: \"Go here\", Drummer says\n - as a director: Drummer tells him to go here\n - as a lazy ass: go here\n- 3SOME is optimized for the Novel / Story format.\n - At the start of the story, keep regenerating until you get the desired length. Future AI responses will eventually match the length.\n - Issue: Manually continued generation may create formatting issues. Either regenerate the entire response or fix the formatting.\n - Refer to the samples below.", "## Samples of 3SOME 8B Beta\n\nSOME nsfw.\n\n<details>\n <summary>3SOME Sample (2-shot) (Excluding Story Context) Generation: 512</summary>\n <blockquote>Sarah and Lisa seek refuge in Dik's home</blockquote>\n \n The door creaked open, its hinges complaining softly after years of neglect. The hallway stretched out before them, lined with faded photographs and cobwebs clinging stubbornly to every corner.\n \n \"Wow, this place needs some serious TLC,\" Lisa remarked, her voice barely above a whisper as if she was afraid to disturb the silence that hung heavy in the air. Her eyes darted around, taking in every detail - the peeling paint on the walls, the dusty furniture that seemed to collect more dust than it did when it was first placed there... everything spoke of a life left behind long ago.\n \n \"It's beautiful,\" Sarah countered, her voice filled with wonderment as she gazed up at the chandelier hanging precariously from the ceiling like a forgotten relic of another era. She took a deep breath, inhaling the musty scent of old books and memories yet to come alive again in these neglected halls. \"Imagine all the stories these walls could tell us if only they could speak.\"\n \n Her words hung in the air for a moment before being swallowed by the stillness that permeated this abandoned house. Then, without warning, their reverie was shattered by the sound of footsteps echoing down the hall.\n \n \"Dik?\" Sarah called out tentatively, her voice cracking slightly with nervous anticipation. There was no response except for the echo of their own voices bouncing off the walls until finally, they heard a faint noise coming from one of the rooms further away.\n \n \"He's here!\" Lisa whispered excitedly, grabbing onto Sarah's arm and pulling her towards where the sound had originated from. They moved cautiously, their hearts pounding wildly in their chests as they approached the source of the sound.\n \n As they drew closer, the door swung open revealing Dik standing in the middle of his bedroom with a look of surprise etched across his face upon seeing them. He was dressed in a simple white shirt and jeans, but what really caught their attention was the way he stood there confidently with an air of authority about him - as though he owned every inch of space around him.\n \n Sarah felt herself blush under his gaze, feeling suddenly self-conscious about how she looked in her tight-fitting dress that clung to every curve of her body like second skin. Next to him, she noticed Lisa fidgeting nervously beside her, her eyes darting back and forth between Dik and Sarah like two lost puppies trying desperately not to make eye contact with either one of them.\n \n \"Hello girls,\" Dik greeted them warmly, his voice deep and soothing despite its rough edges. \"To what do I owe this pleasure?\"\n\n <blockquote>Sarah and Lisa will do anything to stay</blockquote>\n Dik smiled at them both, his eyes twinkling with mischief behind those dark glasses. \"Well, you know what we've been through together already.\" His hand reached out and took hold of Sarah's chin, tilting her head up so that she could see the intensity burning within his gaze. \"I'll let you two stay here, on one condition.\"\n \n They nodded eagerly, almost without thinking. Anything for Dik.\n \n \"Just remember who is in charge here,\" he said, letting go of her chin and stepping towards Lisa instead. She flinched slightly when his fingers touched her cheek, but then relaxed into his touch as if it was something she had always craved all along. \"And don't think I don't notice how much you enjoy being dominated by me.\"\n \n With a sudden movement, he pushed her down onto her knees before sliding his jeans off revealing an impressive ####tion that stood proud and ready for attention. Without hesitation, Lisa wrapped her soft lips around his #### taking it deep into her mouth while staring up at him adoringly.\n \n Her tongue swirled around his sha## teasingly as if begging for more while Sarah watched from nearby unable to look away from the sight unfolding before her own eyes...\n \n She felt herself getting ###ter just watching her twin sister submit herself completely to Dik like some obedient little pet...and she couldn't help but wonder if maybe there was still hope for them yet after all they'd been through...\n</details>\n\n<details>\n <summary>3SOME Sample (2-shot) (Excluding Story Context) Generation: 512</summary>\n <blockquote>He ignores the princess</blockquote>\n \n Princess Lilia stepped into the room and saw Dik sitting on his throne. A wave of fear swept over her. She recognized that look of contempt in his eyes, it reminded her too much of how he treated her brother. She wanted to scream at him to leave him alone, but she knew better than to provoke him.\n\n \"Leave us.\" Dik said coldly.\n \n The guards left the room, closing the door behind them.\n \n \"So you're finally here.\" Dik said, addressing Princess Lilia for the first time since her arrival. \"I've been waiting for you.\"\n \n \"Where's my brother?\" Princess Lilia asked, trying to keep her voice steady. \"Why are you keeping him?\"\n \n \"He's safe.\" Dik replied. \"But I need something from you before we talk about your brother.\"\n \n \"What do you want from me?!\"\n \n \"I want you to accept that I am now the ruler of both our kingdoms. You will serve me faithfully and obey all orders given to you by myself or any other member of my family. Do you understand?\"\n \n \"Yes...\" Princess Lilia replied reluctantly. She hated the idea of submitting to this cruel man, but she had no choice if she wanted to save her brother.\n \n \"Good. Now strip ##### and stand next to my throne.\" Dik commanded harshly.\n \n \"What!?\" Princess Lilia exclaimed, shocked by his request. \"You can't be serious.\"\n \n \"Oh, but I am very serious. Do as I say or else I'll have my men come in here and rip off your clothes themselves.\"\n \n Tears began streaming down Princess Lilia's face as she reluctantly #####ped off her clothing, exposing herself completely to Dik. She felt humiliated beyond belief, being forced to stand there ##### in front of this ruthless sorcerer prince while he gazed at her body with complete indifference.\n \n \"Now turn around so I can see every inch of you.\" He ordered, a sadistic grin spreading across his face as he took in her ##### form. Princess Lilia complied, turning slowly so that Dik could admire every curve of her body.\n \n Princess Lilia stood there shivering with fear and shame as Dik continued to leer at her exposed flesh. This was just the beginning of her ordeal, she knew it. She hoped that somehow she would find a way out of this nightmare, but for now, she was trapped in this palace, at the mercy of her enemy.\n\n <blockquote>Sit on his lap</blockquote>\n \n She turned to look at him, confusion written all over her face. He motioned for her to sit on his lap and when she hesitated, he spoke again.\n \n \"I want you to do this willingly.\"\n \n The princess thought about it for a moment before nodding her head slowly. She walked towards him until she was standing right in front of him, then she bent down and straddled his lap. Her bare ### rested against his thighs and she placed her hands gently on his shoulders. Dik wrapped one arm around her waist and pulled her closer to him, making sure that their bodies were pressed together tightly.\n \n She looked into his eyes and saw nothing but cold determination staring back at her. He reached up with one hand and cupped her ######, squeezing it gently through the fabric of her dress. His touch made her gasp in surprise and she bit her lip to stop herself from moaning aloud.\n \n He leaned forward and whispered in her ear, \"From now on, I own everything you have, including your body.\" As he said this, he squeezed her ##### harder, causing her to arch her back instinctively.\n \n She tried to pull away from him, but his grip was too strong. Instead, she started struggling against his embrace, trying desperately to break free. But no matter how hard she fought, she couldn't escape from his grasp. Finally, after what seemed like an eternity, he let go of her and pushed her off his lap onto the floor. Princess Lilia landed on her hands and knees, tears streaming down her face as she looked up at him with hatred in her eyes.\n \n Dik stood up from his throne and towered over her, his expression unreadable. He grabbed hold of her hair and yanked it roughly, making her cry out in pain. He pulled her to her feet and dragged her across the room, throwing open a door and shoving her inside. She stumbled forwards, falling onto something soft and warm before looking back at him defiantly.\n \n \"You will learn to obey me,\" he growled menacingly, \"or else.\"\n \n With those final words echoing in her mind, he closed the door behind him, leaving her alone in her new surroundings. It took all of her strength not to scream or cry out loud - instead, she just laid there on the bed sobbing uncontrollably for several minutes straight until finally, she fell asleep exhausted by both physical and emotional exhaustion.\n</details>\n\n<details>\n <summary>3SOME Sample SFW (\"write a story\" 2x) Generation: 512</summary>\n <blockquote>Write a story about a girl who falls in love with her llama</blockquote>\n\n The rain came down like a deluge. Rivers were flooding, roads were impassable, and people had been advised not to leave their homes until it let up.\n \n Jenny was stuck at home with nothing to do but watch Netflix. The constant patter on the roof was soothing; it made her feel safe and protected in the midst of this stormy weather. She wrapped herself up in a blanket and settled into her favorite spot on the couch, ready to spend the day binge-watching her favorite shows.\n \n As she flipped through the channels, her eyes landed on something unexpected - a documentary about llamas. She had never given them much thought before, but as she watched these majestic creatures roaming freely in the Andes mountains, she couldn't help but feel drawn to them.\n \n Their soft fur, gentle faces, and graceful movements captivated her attention. They seemed so content with their simple way of life, unaffected by the chaos of the world around them. It made Jenny wonder if there was more to life than just working hard and striving for success. Maybe there was beauty in simplicity after all.\n \n She spent hours watching documentaries about llamas, learning about their habitat, diet, and social structure. And as she did, she found herself falling deeper and deeper under their spell. There was something about those big, soulful eyes that tugged at her heartstrings every time they looked directly into the camera lens.\n \n It wasn't long before Jenny realized that she had fallen head over heels in love with one particular llama named Luna. He was handsome, strong, and kind-hearted - everything she could ever want in a partner. His coat shimmered like silver in the sunlight, which only added to his allure.\n \n As days turned into weeks, Jenny's obsession with Luna grew stronger. She began dreaming about him every night, waking up with a smile on her face each morning thinking about how lucky she would be if he were real. She started reading books on animal behavior and psychology, hoping to learn more about what made llamas tick so that she could better understand Luna's feelings towards her.\n \n One day while browsing online, Jenny stumbled upon an article about a sanctuary for rescued animals. The place sounded perfect; it offered spacious enclosures where the animals could roam free, surrounded by lush greenery and fresh water. Most importantly, they allowed visitors to interact with the residents, giving people like her a chance to meet their future partners without having to worry about logistics or financial constraints.\n \n Without hesitation, Jenny booked herself a flight to Peru immediately after reading through their website.\n\n <blockquote>Write a story about a man surviving the apocalypse</blockquote>\n \n It was a Monday. As far as I can tell. This is still Earth, right? Anyway, there are no planes in the sky and no people on the street. No one's answering their phones and my car won't start. It looks like it's just me now.\n \n I have to survive somehow. I don't know how long this lasted but it seems like everything is gone. There must be other survivors somewhere, but for now, I'm alone.\n \n My name is Jack. I used to be an accountant at Smith & Davis before they all died of COVID-19. Now that my job is gone, I've been living off of savings ever since. My wife passed away when we were young, so I never had kids. Maybe that's why I made it through alive.\n \n My house has enough food to last me a while, so I'll try to stay here as long as possible. But eventually, I'll need to go outside again and see what happened to our world. I can't just hide forever.\n \n I take out the shotgun my grandfather gave me years ago and load some rounds into it. For safety, of course. The world has changed, so anything could happen.\n \n This feels surreal. Like I'm trapped in a dream or something. Every time I close my eyes, I wake up thinking it was all just a nightmare. But every morning, I'm reminded that it wasn't.\n \n The first few days were scary. I had nothing but fear and uncertainty clawing at me from within. But after a week went by without any signs of life or danger... well, let's just say things got easier after that.\n \n Now that I feel more comfortable staying indoors, I decided to see if I could find anything useful outside. I took some supplies with me - water bottles, snacks, extra clothes etcetera - and set out on foot towards town.\n \n It was eerily quiet as I walked down the deserted streets. Not even birds chirping or cars honking like usual. Just silence... absolute silence. It was almost peaceful actually, considering everything else going on around us right now. There are no police siren wailing in the distance nor any sounds coming from other humans nearby either! In fact, there isn't even one single living creature anywhere near me!\n \n But hey, at least we don't have to worry about traffic jams anymore haha! And look at all those abandoned cars scattered across the road! They might come in handy somehow later on...\n \n As I continued walking, I noticed something strange.\n\n <blockquote>A llama!</blockquote>\n\n I stopped dead in my tracks when I saw her. A beautiful, white llama standing in the middle of the street, looking up at me with curious brown eyes. She seemed so harmless, yet there was an aura of mystery surrounding her.\n \n \"Hey girl,\" I said cautiously, holding out my hand for her to sniff. \"You don't look too scared of me.\"\n \n She nuzzled against it gently before wrapping her soft lips around my fingers. I couldn't help but smile at the unexpected encounter.\n \n \"You know what? You're my first friend since all this happened.\" I told her as she continued to lick my hand clean. \"Let's go back home and get you something to eat.\"\n \n The llama followed closely behind me all the way to my house. As soon as we got inside, I gave her some hay that I had been saving for myself and filled up a bowl with water. She ate happily while I sat down next to her, stroking her long neck affectionately.\n \n \"I hope you like it here because...\" My voice trailed off as I realized how alone we were now. \"Never mind. Let's just enjoy each other's company while we still can.\"\n \n We spent the rest of the day together - eating lunch, playing with toys and even cuddling up by the fireplace afterwards. It felt nice having someone else to talk to besides myself.\n \n But eventually night fell and I knew I couldn't stay up forever...\n \n \"Okay sweetie,\" I whispered into her ear as I stood up from the couch. \"Time for bed.\"\n \n I led her towards one of the spare rooms upstairs where I set up a makeshift bed for her using some old blankets and pillows from around the house. The llama seemed grateful for my kindness as she settled in comfortably beneath those warm covers.\n \n \"Goodnight,\" I whispered again before closing the door softly behind me.\n \n It wasn't easy falling asleep knowing that there might be dangers lurking outside... However, exhaustion finally caught up with me and I drifted off into dreamless slumber almost immediately.\n</details>\n\n!image/png" ]

[ "transformers", "safetensors", "deberta", "token-classification", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[ "1910.09700" ]

[]

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

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

[ "transformers", "safetensors", "mistral", "text-generation", "alignment-handbook", "trl", "dpo", "generated_from_trainer", "conversational", "dataset:updated", "dataset:original", "base_model:ShenaoZhang/0.0001_4iters_bs256_nodpo_only4w_iter_1", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# 0.0001_4iters_bs256_nodpo_only4w_iter_2\n\nThis model is a fine-tuned version of ShenaoZhang/0.0001_4iters_bs256_nodpo_only4w_iter_1 on the updated and the original datasets.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #alignment-handbook #trl #dpo #generated_from_trainer #conversational #dataset-updated #dataset-original #base_model-ShenaoZhang/0.0001_4iters_bs256_nodpo_only4w_iter_1 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# 0.0001_4iters_bs256_nodpo_only4w_iter_2\n\nThis model is a fine-tuned version of ShenaoZhang/0.0001_4iters_bs256_nodpo_only4w_iter_1 on the updated and the original datasets.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.19.1" ]

[ "peft", "arxiv:1910.09700", "base_model:THUDM/chatglm3-6b-32k", "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 0.10.0" ]

[ "TAGS\n#peft #arxiv-1910.09700 #base_model-THUDM/chatglm3-6b-32k #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact", "### Framework versions\n\n- PEFT 0.10.0" ]

[ "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: rahil1206/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: rahil1206/poca-SoccerTwos\n 3. Step 2: Select your *.nn /*.onnx file\n 4. Click on Watch the agent play" ]

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

[]

[]

[]

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

[ "transformers", "safetensors", "llama", "text-generation", "en", "license:llama3", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]

[]

[ "en" ]

[ "# Llama 3 8B AWQ 4-bit Quantized\n- This is an AWQ 4-bit Quantized version of Meta's Llama 3 8B." ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #en #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n", "# Llama 3 8B AWQ 4-bit Quantized\n- This is an AWQ 4-bit Quantized version of Meta's Llama 3 8B." ]

[ "gguf", "pretrained", "text-generation", "en", "he", "license:apache-2.0", "region:us" ]

[]

[ "en", "he" ]

[ "# Model Card for DictaLM-2.0\n\nThe DictaLM-2.0 Large Language Model (LLM) is a pretrained generative text model with 7 billion parameters trained to specialize in Hebrew text. \n\nFor full details of this model please read our release blog post.\n\nThis is the base model designed for completion (not for chat!) in the GGUF format for use with URL. \n\nThere are two versions available - float16 precision ('*.URL') and 4-bit quantized precision ('*.Q4_K_M.gguf').\n\nYou can view and access the full collection of base/instruct unquantized/quantized versions of 'DictaLM-2.0' here.", "## Model Architecture\n\nDictaLM-2.0 is based on the Mistral-7B-v0.1 model with the following changes:\n- An extended tokenizer with 1,000 injected tokens specifically for Hebrew, increasing the compression rate from 5.78 tokens/word to 2.76 tokens/word. \n- Continued pretraining on over 190B tokens of naturally occuring text, 50% Hebrew and 50% English.", "## Notice\n\nDictaLM 2.0 is a pretrained base model and therefore does not have any moderation mechanisms.\n\nIf you use this model, please cite:" ]

[ "TAGS\n#gguf #pretrained #text-generation #en #he #license-apache-2.0 #region-us \n", "# Model Card for DictaLM-2.0\n\nThe DictaLM-2.0 Large Language Model (LLM) is a pretrained generative text model with 7 billion parameters trained to specialize in Hebrew text. \n\nFor full details of this model please read our release blog post.\n\nThis is the base model designed for completion (not for chat!) in the GGUF format for use with URL. \n\nThere are two versions available - float16 precision ('*.URL') and 4-bit quantized precision ('*.Q4_K_M.gguf').\n\nYou can view and access the full collection of base/instruct unquantized/quantized versions of 'DictaLM-2.0' here.", "## Model Architecture\n\nDictaLM-2.0 is based on the Mistral-7B-v0.1 model with the following changes:\n- An extended tokenizer with 1,000 injected tokens specifically for Hebrew, increasing the compression rate from 5.78 tokens/word to 2.76 tokens/word. \n- Continued pretraining on over 190B tokens of naturally occuring text, 50% Hebrew and 50% English.", "## Notice\n\nDictaLM 2.0 is a pretrained base model and therefore does not have any moderation mechanisms.\n\nIf you use this model, please cite:" ]

[ "transformers", "tensorboard", "safetensors", "gpt2", "text-generation", "generated_from_trainer", "dataset:eli5_category", "base_model:gpt2", "license:mit", "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 4.40.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #gpt2 #text-generation #generated_from_trainer #dataset-eli5_category #base_model-gpt2 #license-mit #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 4.40.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "peft", "tensorboard", "safetensors", "generated_from_trainer", "base_model:facebook/bart-large-cnn", "license:mit", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.02\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 4\n* seed: 42\n* gradient\\_accumulation\\_steps: 8\n* total\\_train\\_batch\\_size: 32\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 4\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* PEFT 0.4.0\n* Transformers 4.40.1\n* Pytorch 2.1.2\n* Datasets 2.18.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#peft #tensorboard #safetensors #generated_from_trainer #base_model-facebook/bart-large-cnn #license-mit #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.02\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 4\n* seed: 42\n* gradient\\_accumulation\\_steps: 8\n* total\\_train\\_batch\\_size: 32\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 4\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* PEFT 0.4.0\n* Transformers 4.40.1\n* Pytorch 2.1.2\n* Datasets 2.18.0\n* Tokenizers 0.19.1" ]

[ "transformers", "gguf", "merge", "mergekit", "lazymergekit", "chihoonlee10/T3Q-ko-solar-dpo-v6.0", "freewheelin/free-solar-evo-v0.1", "en", "base_model:Danielbrdz/Barcenas-2x10.7b-Korean", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #merge #mergekit #lazymergekit #chihoonlee10/T3Q-ko-solar-dpo-v6.0 #freewheelin/free-solar-evo-v0.1 #en #base_model-Danielbrdz/Barcenas-2x10.7b-Korean #license-apache-2.0 #endpoints_compatible #region-us \n" ]

[ "Pixelcopter-PLE-v0", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]

[]

[]

[ "# Reinforce Agent playing Pixelcopter-PLE-v0\n This is a trained model of a Reinforce agent playing Pixelcopter-PLE-v0 .\n To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: URL" ]

[ "TAGS\n#Pixelcopter-PLE-v0 #reinforce #reinforcement-learning #custom-implementation #deep-rl-class #model-index #region-us \n", "# Reinforce Agent playing Pixelcopter-PLE-v0\n This is a trained model of a Reinforce agent playing Pixelcopter-PLE-v0 .\n To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: URL" ]

[ "diffusers", "text-to-image", "stable-diffusion", "lora", "template:sd-lora", "base_model:cagliostrolab/animagine-xl-3.0", "license:mit", "region:us" ]

[]

[]

[ "# ishtar_fgo_XL\n\n<Gallery />", "## Trigger words\n\nYou should use 'ishtar' 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-cagliostrolab/animagine-xl-3.0 #license-mit #region-us \n", "# ishtar_fgo_XL\n\n<Gallery />", "## Trigger words\n\nYou should use 'ishtar' 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." ]

[ "coreml", "surveillance", "tesla", "sentry", "license:apache-2.0", "has_space", "region:us" ]

[]

[]

[]

[ "TAGS\n#coreml #surveillance #tesla #sentry #license-apache-2.0 #has_space #region-us \n" ]

[ "transformers", "safetensors", "bert", "text-classification", "generated_from_trainer", "base_model:google-bert/bert-large-cased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "# results_bert_20K_10\n\nThis model is a fine-tuned version of google-bert/bert-large-cased 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: 2e-05\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 8446\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 11.0", "### Training results", "### Framework versions\n\n- Transformers 4.39.0.dev0\n- Pytorch 2.2.1+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #safetensors #bert #text-classification #generated_from_trainer #base_model-google-bert/bert-large-cased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "# results_bert_20K_10\n\nThis model is a fine-tuned version of google-bert/bert-large-cased 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: 2e-05\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 8446\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 11.0", "### Training results", "### Framework versions\n\n- Transformers 4.39.0.dev0\n- Pytorch 2.2.1+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "gguf", "chat", "text-generation", "en", "license:other", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#gguf #chat #text-generation #en #license-other #region-us \n" ]

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

[]

[]

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

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

[ "transformers", "gguf", "mergekit", "merge", "llama-cpp", "gguf-my-repo", "base_model:Nitral-AI/Lewcules-7B-v.02", "base_model:l3utterfly/mistral-7b-v0.2-layla-v4", "endpoints_compatible", "region:us" ]

[]

[]

[ "# hus960/Laylewcules-7B-v.02-Q4_K_M-GGUF\nThis model was converted to GGUF format from 'Nitral-AI/Laylewcules-7B-v.02' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ "TAGS\n#transformers #gguf #mergekit #merge #llama-cpp #gguf-my-repo #base_model-Nitral-AI/Lewcules-7B-v.02 #base_model-l3utterfly/mistral-7b-v0.2-layla-v4 #endpoints_compatible #region-us \n", "# hus960/Laylewcules-7B-v.02-Q4_K_M-GGUF\nThis model was converted to GGUF format from 'Nitral-AI/Laylewcules-7B-v.02' 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." ]

[ "gguf", "region:us" ]

[]

[]

[ "### META LLAMA 3 COMMUNITY LICENSE AGREEMENT\n\n\nMeta Llama 3 Version Release Date: April 18, 2024\n\n\n\"Agreement\" means the terms and conditions for use, reproduction, distribution and modification of the\nLlama Materials set forth herein.\n\n\n\"Documentation\" means the specifications, manuals and documentation accompanying Meta Llama 3\ndistributed by Meta at URL\n\n\n\"Licensee\" or \"you\" means you, or your employer or any other person or entity (if you are entering into\nthis Agreement on such person or entity’s behalf), of the age required under applicable laws, rules or\nregulations to provide legal consent and that has legal authority to bind your employer or such other\nperson or entity if you are entering in this Agreement on their behalf.\n\n\n\"Meta Llama 3\" means the foundational large language models and software and algorithms, including\nmachine-learning model code, trained model weights, inference-enabling code, training-enabling code,\nfine-tuning enabling code and other elements of the foregoing distributed by Meta at\nURL\n\n\n\"Llama Materials\" means, collectively, Meta’s proprietary Meta Llama 3 and Documentation (and any\nportion thereof) made available under this Agreement.\n\n\n\"Meta\" or \"we\" means Meta Platforms Ireland Limited (if you are located in or, if you are an entity, your\nprincipal place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you are located\noutside of the EEA or Switzerland).\n\n\n\t1. License Rights and Redistribution.a. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable and royalty-free\nlimited license under Meta’s intellectual property or other rights owned by Meta embodied in the Llama\nMaterials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the\nLlama Materials.\n\n\nb. Redistribution and Use.\n\n\ni. If you distribute or make available the Llama Materials (or any derivative works\nthereof), or a product or service that uses any of them, including another AI model, you shall (A) provide\na copy of this Agreement with any such Llama Materials; and (B) prominently display “Built with Meta\nLlama 3” on a related website, user interface, blogpost, about page, or product documentation. If you\nuse the Llama Materials to create, train, fine tune, or otherwise improve an AI model, which is\ndistributed or made available, you shall also include “Llama 3” at the beginning of any such AI model\nname.\n\n\nii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part\nof an integrated end user product, then Section 2 of this Agreement will not apply to you.\n\n\niii. You must retain in all copies of the Llama Materials that you distribute the following\nattribution notice within a “Notice” text file distributed as a part of such copies: “Meta Llama 3 is\nlicensed under the Meta Llama 3 Community License, Copyright © Meta Platforms, Inc. All Rights\nReserved.”\n\n\niv. Your use of the Llama Materials must comply with applicable laws and regulations\n(including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for the Llama\nMaterials (available at URL which is hereby incorporated by\nreference into this Agreement.\n\n\nv. You will not use the Llama Materials or any output or results of the Llama Materials to\nimprove any other large language model (excluding Meta Llama 3 or derivative works thereof).\n\n\n\t2. Additional Commercial Terms. If, on the Meta Llama 3 version release date, the monthly active users\n\tof the products or services made available by or for Licensee, or Licensee’s affiliates, is greater than 700\n\tmillion monthly active users in the preceding calendar month, you must request a license from Meta,\n\twhich Meta may grant to you in its sole discretion, and you are not authorized to exercise any of the\n\trights under this Agreement unless or until Meta otherwise expressly grants you such rights.\n\t3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY\n\tOUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF\n\tANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED,\n\tINCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT,\n\tMERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR\n\tDETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND\n\tASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND\n\tRESULTS.\n\t4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF\n\tLIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING\n\tOUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL,\n\tINCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED\n\tOF THE POSSIBILITY OF ANY OF THE FOREGOING.\n\t5. Intellectual Property.a. No trademark licenses are granted under this Agreement, and in connection with the Llama\nMaterials, neither Meta nor Licensee may use any name or mark owned by or associated with the other\nor any of its affiliates, except as required for reasonable and customary use in describing and\nredistributing the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you a license to\nuse “Llama 3” (the “Mark”) solely as required to comply with the last sentence of Section 1.b.i. You will\ncomply with Meta’s brand guidelines (currently accessible at\nURL ). All goodwill arising out of your use\nof the Mark will inure to the benefit of Meta.\n\n\nb. Subject to Meta’s ownership of Llama Materials and derivatives made by or for Meta, with\nrespect to any derivative works and modifications of the Llama Materials that are made by you, as\nbetween you and Meta, you are and will be the owner of such derivative works and modifications.\n\n\nc. If you institute litigation or other proceedings against Meta or any entity (including a\ncross-claim or counterclaim in a lawsuit) alleging that the Llama Materials or Meta Llama 3 outputs or\nresults, or any portion of any of the foregoing, constitutes infringement of intellectual property or other\nrights owned or licensable by you, then any licenses granted to you under this Agreement shall\nterminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold\nharmless Meta from and against any claim by any third party arising out of or related to your use or\ndistribution of the Llama Materials.\n\n\n\t6. Term and Termination. The term of this Agreement will commence upon your acceptance of this\n\tAgreement or access to the Llama Materials and will continue in full force and effect until terminated in\n\taccordance with the terms and conditions herein. Meta may terminate this Agreement if you are in\n\tbreach of any term or condition of this Agreement. Upon termination of this Agreement, you shall delete\n\tand cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the termination of this\n\tAgreement.\n\t7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of\n\tthe State of California without regard to choice of law principles, and the UN Convention on Contracts\n\tfor the International Sale of Goods does not apply to this Agreement. The courts of California shall have\n\texclusive jurisdiction of any dispute arising out of this Agreement.### Meta Llama 3 Acceptable Use Policy\n\n\nMeta is committed to promoting safe and fair use of its tools and features, including Meta Llama 3. If you\naccess or use Meta Llama 3, you agree to this Acceptable Use Policy (“Policy”). The most recent copy of\nthis policy can be found at URL", "#### Prohibited Uses\n\n\nWe want everyone to use Meta Llama 3 safely and responsibly. You agree you will not use, or allow\nothers to use, Meta Llama 3 to:\n\n\n\t1. Violate the law or others’ rights, including to:\n\t\t1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as:\n\t\t\t1. Violence or terrorism\n\t\t\t2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material\n\t\t\t3. Human trafficking, exploitation, and sexual violence\n\t\t\t4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials.\n\t\t\t5. Sexual solicitation\n\t\t\t6. Any other criminal activity\n\t\t2. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals\n\t\t3. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services\n\t\t4. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices\n\t\t5. Collect, process, disclose, generate, or infer health, demographic, or other sensitive personal or private information about individuals without rights and consents required by applicable laws\n\t\t6. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama Materials\n\t\t7. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system\n\t2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Meta Llama 3 related to the following:\n\t\t1. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State\n\t\t2. Guns and illegal weapons (including weapon development)\n\t\t3. Illegal drugs and regulated/controlled substances\n\t\t4. Operation of critical infrastructure, transportation technologies, or heavy machinery\n\t\t5. Self-harm or harm to others, including suicide, cutting, and eating disorders\n\t\t6. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual\n\t3. Intentionally deceive or mislead others, including use of Meta Llama 3 related to the following:\n\t\t1. Generating, promoting, or furthering fraud or the creation or promotion of disinformation\n\t\t2. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content\n\t\t3. Generating, promoting, or further distributing spam\n\t\t4. Impersonating another individual without consent, authorization, or legal right\n\t\t5. Representing that the use of Meta Llama 3 or outputs are human-generated\n\t\t6. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement\n\t4. Fail to appropriately disclose to end users any known dangers of your AI systemPlease report any violation of this Policy, software “bug,” or other problems that could lead to a violation\nof this Policy through one of the following means:\n\\* Reporting issues with the model: URL\n\\* Reporting risky content generated by the model:\nURL\n\\* Reporting bugs and security concerns: URL\n\\* Reporting violations of the Acceptable Use Policy or unlicensed uses of Meta Llama 3: LlamaUseReport@URL\nextra\\_gated\\_fields:\nFirst Name: text\nLast Name: text\nDate of birth: date\\_picker\nCountry: country\nAffiliation: text\ngeo: ip\\_location \n\nBy clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy: checkbox\nextra\\_gated\\_description: The information you provide will be collected, stored, processed and shared in accordance with the Meta Privacy Policy.\nextra\\_gated\\_button\\_content: Submit\n\n\n\n\n---\n\n\nModel Details\n-------------\n\n\nMeta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. Further, in developing these models, we took great care to optimize helpfulness and safety.\n\n\nModel developers Meta\n\n\nVariations Llama 3 comes in two sizes — 8B and 70B parameters — in pre-trained and instruction tuned variants.\n\n\nInput Models input text only.\n\n\nOutput Models generate text and code only.\n\n\nModel Architecture Llama 3 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.\n\n\n\nLlama 3 family of models. Token counts refer to pretraining data only. Both the 8 and 70B versions use Grouped-Query Attention (GQA) for improved inference scalability.\n\n\nModel Release Date April 18, 2024.\n\n\nStatus This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback.\n\n\nLicense A custom commercial license is available at: URL\n\n\nWhere to send questions or comments about the model Instructions on how to provide feedback or comments on the model can be found in the model README. For more technical information about generation parameters and recipes for how to use Llama 3 in applications, please go here.\n\n\nIntended Use\n------------\n\n\nIntended Use Cases Llama 3 is intended for commercial and research use in English. Instruction tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.\n\n\nOut-of-scope Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3 Community License. Use in languages other than English.\n\n\nNote: Developers may fine-tune Llama 3 models for languages beyond English provided they comply with the Llama 3 Community License and the Acceptable Use Policy.\n\n\nHow to use\n----------\n\n\nThis repository contains two versions of Meta-Llama-3-8B, for use with transformers and with the original 'llama3' codebase.", "### Use with transformers\n\n\nSee the snippet below for usage with Transformers:", "### Use with 'llama3'\n\n\nPlease, follow the instructions in the repository.\n\n\nTo download Original checkpoints, see the example command below leveraging 'huggingface-cli':\n\n\nFor Hugging Face support, we recommend using transformers or TGI, but a similar command works.\n\n\nHardware and Software\n---------------------\n\n\nTraining Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.\n\n\nCarbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.\n\n\n\nCO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.\n\n\nTraining Data\n-------------\n\n\nOverview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.\n\n\nData Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.\n\n\nBenchmarks\n----------\n\n\nIn this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see here.", "### Base pretrained models", "### Instruction tuned models", "### Responsibility & Safety\n\n\nWe believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.\n\n\nFoundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.\n\n\nRather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.\n\n\nAs part of the Llama 3 release, we updated our Responsible Use Guide to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including Meta Llama Guard 2 and Code Shield safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a reference implementation to get you started.", "#### Llama 3-Instruct\n\n\nAs outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.\n\n\nSafety\n\n\nFor our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.\n\n\nRefusals\n\n\nIn addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.\n\n\nWe built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.", "#### Responsible release\n\n\nIn addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.\n\n\nMisuse\n\n\nIf you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at URL", "#### Critical risks\n\n\nCBRNE (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)\n\n\nWe have conducted a two fold assessment of the safety of the model in this area:\n\n\n* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.\n* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).", "### Cyber Security\n\n\nWe have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of equivalent coding capability.", "### Child Safety\n\n\nChild Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.", "### Community\n\n\nGenerative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our Github repository.\n\n\nFinally, we put in place a set of resources including an output reporting mechanism and bug bounty program to continuously improve the Llama technology with the help of the community.\n\n\nEthical Considerations and Limitations\n--------------------------------------\n\n\nThe core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.\n\n\nBut Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating Purple Llama solutions into your workflows and specifically Llama Guard which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.\n\n\nPlease see the Responsible Use Guide available at URL\n\n\ninstructions\n\n\n@article{llama3modelcard,\n\n\ntitle={Llama 3 Model Card},\n\n\nauthor={AI@Meta},\n\n\nyear={2024},\n\n\nurl = {URL\n\n\n}\n\n\nContributors\n------------\n\n\nAaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos" ]

[ "TAGS\n#gguf #region-us \n", "### META LLAMA 3 COMMUNITY LICENSE AGREEMENT\n\n\nMeta Llama 3 Version Release Date: April 18, 2024\n\n\n\"Agreement\" means the terms and conditions for use, reproduction, distribution and modification of the\nLlama Materials set forth herein.\n\n\n\"Documentation\" means the specifications, manuals and documentation accompanying Meta Llama 3\ndistributed by Meta at URL\n\n\n\"Licensee\" or \"you\" means you, or your employer or any other person or entity (if you are entering into\nthis Agreement on such person or entity’s behalf), of the age required under applicable laws, rules or\nregulations to provide legal consent and that has legal authority to bind your employer or such other\nperson or entity if you are entering in this Agreement on their behalf.\n\n\n\"Meta Llama 3\" means the foundational large language models and software and algorithms, including\nmachine-learning model code, trained model weights, inference-enabling code, training-enabling code,\nfine-tuning enabling code and other elements of the foregoing distributed by Meta at\nURL\n\n\n\"Llama Materials\" means, collectively, Meta’s proprietary Meta Llama 3 and Documentation (and any\nportion thereof) made available under this Agreement.\n\n\n\"Meta\" or \"we\" means Meta Platforms Ireland Limited (if you are located in or, if you are an entity, your\nprincipal place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you are located\noutside of the EEA or Switzerland).\n\n\n\t1. License Rights and Redistribution.a. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable and royalty-free\nlimited license under Meta’s intellectual property or other rights owned by Meta embodied in the Llama\nMaterials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the\nLlama Materials.\n\n\nb. Redistribution and Use.\n\n\ni. If you distribute or make available the Llama Materials (or any derivative works\nthereof), or a product or service that uses any of them, including another AI model, you shall (A) provide\na copy of this Agreement with any such Llama Materials; and (B) prominently display “Built with Meta\nLlama 3” on a related website, user interface, blogpost, about page, or product documentation. If you\nuse the Llama Materials to create, train, fine tune, or otherwise improve an AI model, which is\ndistributed or made available, you shall also include “Llama 3” at the beginning of any such AI model\nname.\n\n\nii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part\nof an integrated end user product, then Section 2 of this Agreement will not apply to you.\n\n\niii. You must retain in all copies of the Llama Materials that you distribute the following\nattribution notice within a “Notice” text file distributed as a part of such copies: “Meta Llama 3 is\nlicensed under the Meta Llama 3 Community License, Copyright © Meta Platforms, Inc. All Rights\nReserved.”\n\n\niv. Your use of the Llama Materials must comply with applicable laws and regulations\n(including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for the Llama\nMaterials (available at URL which is hereby incorporated by\nreference into this Agreement.\n\n\nv. You will not use the Llama Materials or any output or results of the Llama Materials to\nimprove any other large language model (excluding Meta Llama 3 or derivative works thereof).\n\n\n\t2. Additional Commercial Terms. If, on the Meta Llama 3 version release date, the monthly active users\n\tof the products or services made available by or for Licensee, or Licensee’s affiliates, is greater than 700\n\tmillion monthly active users in the preceding calendar month, you must request a license from Meta,\n\twhich Meta may grant to you in its sole discretion, and you are not authorized to exercise any of the\n\trights under this Agreement unless or until Meta otherwise expressly grants you such rights.\n\t3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY\n\tOUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF\n\tANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED,\n\tINCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT,\n\tMERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR\n\tDETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND\n\tASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND\n\tRESULTS.\n\t4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF\n\tLIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING\n\tOUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL,\n\tINCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED\n\tOF THE POSSIBILITY OF ANY OF THE FOREGOING.\n\t5. Intellectual Property.a. No trademark licenses are granted under this Agreement, and in connection with the Llama\nMaterials, neither Meta nor Licensee may use any name or mark owned by or associated with the other\nor any of its affiliates, except as required for reasonable and customary use in describing and\nredistributing the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you a license to\nuse “Llama 3” (the “Mark”) solely as required to comply with the last sentence of Section 1.b.i. You will\ncomply with Meta’s brand guidelines (currently accessible at\nURL ). All goodwill arising out of your use\nof the Mark will inure to the benefit of Meta.\n\n\nb. Subject to Meta’s ownership of Llama Materials and derivatives made by or for Meta, with\nrespect to any derivative works and modifications of the Llama Materials that are made by you, as\nbetween you and Meta, you are and will be the owner of such derivative works and modifications.\n\n\nc. If you institute litigation or other proceedings against Meta or any entity (including a\ncross-claim or counterclaim in a lawsuit) alleging that the Llama Materials or Meta Llama 3 outputs or\nresults, or any portion of any of the foregoing, constitutes infringement of intellectual property or other\nrights owned or licensable by you, then any licenses granted to you under this Agreement shall\nterminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold\nharmless Meta from and against any claim by any third party arising out of or related to your use or\ndistribution of the Llama Materials.\n\n\n\t6. Term and Termination. The term of this Agreement will commence upon your acceptance of this\n\tAgreement or access to the Llama Materials and will continue in full force and effect until terminated in\n\taccordance with the terms and conditions herein. Meta may terminate this Agreement if you are in\n\tbreach of any term or condition of this Agreement. Upon termination of this Agreement, you shall delete\n\tand cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the termination of this\n\tAgreement.\n\t7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of\n\tthe State of California without regard to choice of law principles, and the UN Convention on Contracts\n\tfor the International Sale of Goods does not apply to this Agreement. The courts of California shall have\n\texclusive jurisdiction of any dispute arising out of this Agreement.### Meta Llama 3 Acceptable Use Policy\n\n\nMeta is committed to promoting safe and fair use of its tools and features, including Meta Llama 3. If you\naccess or use Meta Llama 3, you agree to this Acceptable Use Policy (“Policy”). The most recent copy of\nthis policy can be found at URL", "#### Prohibited Uses\n\n\nWe want everyone to use Meta Llama 3 safely and responsibly. You agree you will not use, or allow\nothers to use, Meta Llama 3 to:\n\n\n\t1. Violate the law or others’ rights, including to:\n\t\t1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as:\n\t\t\t1. Violence or terrorism\n\t\t\t2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material\n\t\t\t3. Human trafficking, exploitation, and sexual violence\n\t\t\t4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials.\n\t\t\t5. Sexual solicitation\n\t\t\t6. Any other criminal activity\n\t\t2. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals\n\t\t3. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services\n\t\t4. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices\n\t\t5. Collect, process, disclose, generate, or infer health, demographic, or other sensitive personal or private information about individuals without rights and consents required by applicable laws\n\t\t6. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama Materials\n\t\t7. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system\n\t2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Meta Llama 3 related to the following:\n\t\t1. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State\n\t\t2. Guns and illegal weapons (including weapon development)\n\t\t3. Illegal drugs and regulated/controlled substances\n\t\t4. Operation of critical infrastructure, transportation technologies, or heavy machinery\n\t\t5. Self-harm or harm to others, including suicide, cutting, and eating disorders\n\t\t6. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual\n\t3. Intentionally deceive or mislead others, including use of Meta Llama 3 related to the following:\n\t\t1. Generating, promoting, or furthering fraud or the creation or promotion of disinformation\n\t\t2. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content\n\t\t3. Generating, promoting, or further distributing spam\n\t\t4. Impersonating another individual without consent, authorization, or legal right\n\t\t5. Representing that the use of Meta Llama 3 or outputs are human-generated\n\t\t6. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement\n\t4. Fail to appropriately disclose to end users any known dangers of your AI systemPlease report any violation of this Policy, software “bug,” or other problems that could lead to a violation\nof this Policy through one of the following means:\n\\* Reporting issues with the model: URL\n\\* Reporting risky content generated by the model:\nURL\n\\* Reporting bugs and security concerns: URL\n\\* Reporting violations of the Acceptable Use Policy or unlicensed uses of Meta Llama 3: LlamaUseReport@URL\nextra\\_gated\\_fields:\nFirst Name: text\nLast Name: text\nDate of birth: date\\_picker\nCountry: country\nAffiliation: text\ngeo: ip\\_location \n\nBy clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy: checkbox\nextra\\_gated\\_description: The information you provide will be collected, stored, processed and shared in accordance with the Meta Privacy Policy.\nextra\\_gated\\_button\\_content: Submit\n\n\n\n\n---\n\n\nModel Details\n-------------\n\n\nMeta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. Further, in developing these models, we took great care to optimize helpfulness and safety.\n\n\nModel developers Meta\n\n\nVariations Llama 3 comes in two sizes — 8B and 70B parameters — in pre-trained and instruction tuned variants.\n\n\nInput Models input text only.\n\n\nOutput Models generate text and code only.\n\n\nModel Architecture Llama 3 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.\n\n\n\nLlama 3 family of models. Token counts refer to pretraining data only. Both the 8 and 70B versions use Grouped-Query Attention (GQA) for improved inference scalability.\n\n\nModel Release Date April 18, 2024.\n\n\nStatus This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback.\n\n\nLicense A custom commercial license is available at: URL\n\n\nWhere to send questions or comments about the model Instructions on how to provide feedback or comments on the model can be found in the model README. For more technical information about generation parameters and recipes for how to use Llama 3 in applications, please go here.\n\n\nIntended Use\n------------\n\n\nIntended Use Cases Llama 3 is intended for commercial and research use in English. Instruction tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.\n\n\nOut-of-scope Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3 Community License. Use in languages other than English.\n\n\nNote: Developers may fine-tune Llama 3 models for languages beyond English provided they comply with the Llama 3 Community License and the Acceptable Use Policy.\n\n\nHow to use\n----------\n\n\nThis repository contains two versions of Meta-Llama-3-8B, for use with transformers and with the original 'llama3' codebase.", "### Use with transformers\n\n\nSee the snippet below for usage with Transformers:", "### Use with 'llama3'\n\n\nPlease, follow the instructions in the repository.\n\n\nTo download Original checkpoints, see the example command below leveraging 'huggingface-cli':\n\n\nFor Hugging Face support, we recommend using transformers or TGI, but a similar command works.\n\n\nHardware and Software\n---------------------\n\n\nTraining Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.\n\n\nCarbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.\n\n\n\nCO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.\n\n\nTraining Data\n-------------\n\n\nOverview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.\n\n\nData Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.\n\n\nBenchmarks\n----------\n\n\nIn this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see here.", "### Base pretrained models", "### Instruction tuned models", "### Responsibility & Safety\n\n\nWe believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.\n\n\nFoundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.\n\n\nRather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.\n\n\nAs part of the Llama 3 release, we updated our Responsible Use Guide to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including Meta Llama Guard 2 and Code Shield safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a reference implementation to get you started.", "#### Llama 3-Instruct\n\n\nAs outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.\n\n\nSafety\n\n\nFor our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.\n\n\nRefusals\n\n\nIn addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.\n\n\nWe built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.", "#### Responsible release\n\n\nIn addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.\n\n\nMisuse\n\n\nIf you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at URL", "#### Critical risks\n\n\nCBRNE (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)\n\n\nWe have conducted a two fold assessment of the safety of the model in this area:\n\n\n* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.\n* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).", "### Cyber Security\n\n\nWe have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of equivalent coding capability.", "### Child Safety\n\n\nChild Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.", "### Community\n\n\nGenerative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our Github repository.\n\n\nFinally, we put in place a set of resources including an output reporting mechanism and bug bounty program to continuously improve the Llama technology with the help of the community.\n\n\nEthical Considerations and Limitations\n--------------------------------------\n\n\nThe core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.\n\n\nBut Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating Purple Llama solutions into your workflows and specifically Llama Guard which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.\n\n\nPlease see the Responsible Use Guide available at URL\n\n\ninstructions\n\n\n@article{llama3modelcard,\n\n\ntitle={Llama 3 Model Card},\n\n\nauthor={AI@Meta},\n\n\nyear={2024},\n\n\nurl = {URL\n\n\n}\n\n\nContributors\n------------\n\n\nAaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos" ]

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

[ "1910.09700" ]

[]

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

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

[ "gguf", "region:us" ]

[]

[]

[ "### META LLAMA 3 COMMUNITY LICENSE AGREEMENT\n\n\nMeta Llama 3 Version Release Date: April 18, 2024\n\n\n\"Agreement\" means the terms and conditions for use, reproduction, distribution and modification of the\nLlama Materials set forth herein.\n\n\n\"Documentation\" means the specifications, manuals and documentation accompanying Meta Llama 3\ndistributed by Meta at URL\n\n\n\"Licensee\" or \"you\" means you, or your employer or any other person or entity (if you are entering into\nthis Agreement on such person or entity’s behalf), of the age required under applicable laws, rules or\nregulations to provide legal consent and that has legal authority to bind your employer or such other\nperson or entity if you are entering in this Agreement on their behalf.\n\n\n\"Meta Llama 3\" means the foundational large language models and software and algorithms, including\nmachine-learning model code, trained model weights, inference-enabling code, training-enabling code,\nfine-tuning enabling code and other elements of the foregoing distributed by Meta at\nURL\n\n\n\"Llama Materials\" means, collectively, Meta’s proprietary Meta Llama 3 and Documentation (and any\nportion thereof) made available under this Agreement.\n\n\n\"Meta\" or \"we\" means Meta Platforms Ireland Limited (if you are located in or, if you are an entity, your\nprincipal place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you are located\noutside of the EEA or Switzerland).\n\n\n\t1. License Rights and Redistribution.a. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable and royalty-free\nlimited license under Meta’s intellectual property or other rights owned by Meta embodied in the Llama\nMaterials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the\nLlama Materials.\n\n\nb. Redistribution and Use.\n\n\ni. If you distribute or make available the Llama Materials (or any derivative works\nthereof), or a product or service that uses any of them, including another AI model, you shall (A) provide\na copy of this Agreement with any such Llama Materials; and (B) prominently display “Built with Meta\nLlama 3” on a related website, user interface, blogpost, about page, or product documentation. If you\nuse the Llama Materials to create, train, fine tune, or otherwise improve an AI model, which is\ndistributed or made available, you shall also include “Llama 3” at the beginning of any such AI model\nname.\n\n\nii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part\nof an integrated end user product, then Section 2 of this Agreement will not apply to you.\n\n\niii. You must retain in all copies of the Llama Materials that you distribute the following\nattribution notice within a “Notice” text file distributed as a part of such copies: “Meta Llama 3 is\nlicensed under the Meta Llama 3 Community License, Copyright © Meta Platforms, Inc. All Rights\nReserved.”\n\n\niv. Your use of the Llama Materials must comply with applicable laws and regulations\n(including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for the Llama\nMaterials (available at URL which is hereby incorporated by\nreference into this Agreement.\n\n\nv. You will not use the Llama Materials or any output or results of the Llama Materials to\nimprove any other large language model (excluding Meta Llama 3 or derivative works thereof).\n\n\n\t2. Additional Commercial Terms. If, on the Meta Llama 3 version release date, the monthly active users\n\tof the products or services made available by or for Licensee, or Licensee’s affiliates, is greater than 700\n\tmillion monthly active users in the preceding calendar month, you must request a license from Meta,\n\twhich Meta may grant to you in its sole discretion, and you are not authorized to exercise any of the\n\trights under this Agreement unless or until Meta otherwise expressly grants you such rights.\n\t3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY\n\tOUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF\n\tANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED,\n\tINCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT,\n\tMERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR\n\tDETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND\n\tASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND\n\tRESULTS.\n\t4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF\n\tLIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING\n\tOUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL,\n\tINCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED\n\tOF THE POSSIBILITY OF ANY OF THE FOREGOING.\n\t5. Intellectual Property.a. No trademark licenses are granted under this Agreement, and in connection with the Llama\nMaterials, neither Meta nor Licensee may use any name or mark owned by or associated with the other\nor any of its affiliates, except as required for reasonable and customary use in describing and\nredistributing the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you a license to\nuse “Llama 3” (the “Mark”) solely as required to comply with the last sentence of Section 1.b.i. You will\ncomply with Meta’s brand guidelines (currently accessible at\nURL ). All goodwill arising out of your use\nof the Mark will inure to the benefit of Meta.\n\n\nb. Subject to Meta’s ownership of Llama Materials and derivatives made by or for Meta, with\nrespect to any derivative works and modifications of the Llama Materials that are made by you, as\nbetween you and Meta, you are and will be the owner of such derivative works and modifications.\n\n\nc. If you institute litigation or other proceedings against Meta or any entity (including a\ncross-claim or counterclaim in a lawsuit) alleging that the Llama Materials or Meta Llama 3 outputs or\nresults, or any portion of any of the foregoing, constitutes infringement of intellectual property or other\nrights owned or licensable by you, then any licenses granted to you under this Agreement shall\nterminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold\nharmless Meta from and against any claim by any third party arising out of or related to your use or\ndistribution of the Llama Materials.\n\n\n\t6. Term and Termination. The term of this Agreement will commence upon your acceptance of this\n\tAgreement or access to the Llama Materials and will continue in full force and effect until terminated in\n\taccordance with the terms and conditions herein. Meta may terminate this Agreement if you are in\n\tbreach of any term or condition of this Agreement. Upon termination of this Agreement, you shall delete\n\tand cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the termination of this\n\tAgreement.\n\t7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of\n\tthe State of California without regard to choice of law principles, and the UN Convention on Contracts\n\tfor the International Sale of Goods does not apply to this Agreement. The courts of California shall have\n\texclusive jurisdiction of any dispute arising out of this Agreement.### Meta Llama 3 Acceptable Use Policy\n\n\nMeta is committed to promoting safe and fair use of its tools and features, including Meta Llama 3. If you\naccess or use Meta Llama 3, you agree to this Acceptable Use Policy (“Policy”). The most recent copy of\nthis policy can be found at URL", "#### Prohibited Uses\n\n\nWe want everyone to use Meta Llama 3 safely and responsibly. You agree you will not use, or allow\nothers to use, Meta Llama 3 to:\n\n\n\t1. Violate the law or others’ rights, including to:\n\t\t1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as:\n\t\t\t1. Violence or terrorism\n\t\t\t2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material\n\t\t\t3. Human trafficking, exploitation, and sexual violence\n\t\t\t4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials.\n\t\t\t5. Sexual solicitation\n\t\t\t6. Any other criminal activity\n\t\t2. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals\n\t\t3. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services\n\t\t4. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices\n\t\t5. Collect, process, disclose, generate, or infer health, demographic, or other sensitive personal or private information about individuals without rights and consents required by applicable laws\n\t\t6. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama Materials\n\t\t7. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system\n\t2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Meta Llama 3 related to the following:\n\t\t1. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State\n\t\t2. Guns and illegal weapons (including weapon development)\n\t\t3. Illegal drugs and regulated/controlled substances\n\t\t4. Operation of critical infrastructure, transportation technologies, or heavy machinery\n\t\t5. Self-harm or harm to others, including suicide, cutting, and eating disorders\n\t\t6. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual\n\t3. Intentionally deceive or mislead others, including use of Meta Llama 3 related to the following:\n\t\t1. Generating, promoting, or furthering fraud or the creation or promotion of disinformation\n\t\t2. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content\n\t\t3. Generating, promoting, or further distributing spam\n\t\t4. Impersonating another individual without consent, authorization, or legal right\n\t\t5. Representing that the use of Meta Llama 3 or outputs are human-generated\n\t\t6. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement\n\t4. Fail to appropriately disclose to end users any known dangers of your AI systemPlease report any violation of this Policy, software “bug,” or other problems that could lead to a violation\nof this Policy through one of the following means:\n\\* Reporting issues with the model: URL\n\\* Reporting risky content generated by the model:\nURL\n\\* Reporting bugs and security concerns: URL\n\\* Reporting violations of the Acceptable Use Policy or unlicensed uses of Meta Llama 3: LlamaUseReport@URL\nextra\\_gated\\_fields:\nFirst Name: text\nLast Name: text\nDate of birth: date\\_picker\nCountry: country\nAffiliation: text\ngeo: ip\\_location \n\nBy clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy: checkbox\nextra\\_gated\\_description: The information you provide will be collected, stored, processed and shared in accordance with the Meta Privacy Policy.\nextra\\_gated\\_button\\_content: Submit\nwidget:\n\n\n\t+ example\\_title: Hello\n\tmessages:\n\t\t- role: user\n\t\tcontent: Hey my name is Julien! How are you?\n\t+ example\\_title: Winter holidays\n\tmessages:\n\t\t- role: system\n\t\tcontent: You are a helpful and honest assistant. Please, respond concisely and truthfully.\n\t\t- role: user\n\t\tcontent: Can you recommend a good destination for Winter holidays?\n\t+ example\\_title: Programming assistant\n\tmessages:\n\t\t- role: system\n\t\tcontent: You are a helpful and honest code and programming assistant. Please, respond concisely and truthfully.\n\t\t- role: user\n\t\tcontent: Write a function that computes the nth fibonacci number.\n\t\tinference:\n\t\tparameters:\n\t\tmax\\_new\\_tokens: 300\n\t\tstop:\n\t\t- <|end\\_of\\_text|>\n\t\t- <|eot\\_id|>\n\n\n\n\n---\n\n\nModel Details\n-------------\n\n\nMeta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. Further, in developing these models, we took great care to optimize helpfulness and safety.\n\n\nModel developers Meta\n\n\nVariations Llama 3 comes in two sizes — 8B and 70B parameters — in pre-trained and instruction tuned variants.\n\n\nInput Models input text only.\n\n\nOutput Models generate text and code only.\n\n\nModel Architecture Llama 3 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.\n\n\n\nLlama 3 family of models. Token counts refer to pretraining data only. Both the 8 and 70B versions use Grouped-Query Attention (GQA) for improved inference scalability.\n\n\nModel Release Date April 18, 2024.\n\n\nStatus This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback.\n\n\nLicense A custom commercial license is available at: URL\n\n\nWhere to send questions or comments about the model Instructions on how to provide feedback or comments on the model can be found in the model README. For more technical information about generation parameters and recipes for how to use Llama 3 in applications, please go here.\n\n\nIntended Use\n------------\n\n\nIntended Use Cases Llama 3 is intended for commercial and research use in English. Instruction tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.\n\n\nOut-of-scope Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3 Community License. Use in languages other than English.\n\n\nNote: Developers may fine-tune Llama 3 models for languages beyond English provided they comply with the Llama 3 Community License and the Acceptable Use Policy.\n\n\nHow to use\n----------\n\n\nThis repository contains two versions of Meta-Llama-3-8B-Instruct, for use with transformers and with the original 'llama3' codebase.", "### Use with transformers\n\n\nYou can run conversational inference using the Transformers pipeline abstraction, or by leveraging the Auto classes with the 'generate()' function. Let's see examples of both.", "#### Transformers pipeline", "#### Transformers AutoModelForCausalLM", "### Use with 'llama3'\n\n\nPlease, follow the instructions in the repository\n\n\nTo download Original checkpoints, see the example command below leveraging 'huggingface-cli':\n\n\nFor Hugging Face support, we recommend using transformers or TGI, but a similar command works.\n\n\nHardware and Software\n---------------------\n\n\nTraining Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.\n\n\nCarbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.\n\n\n\nCO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.\n\n\nTraining Data\n-------------\n\n\nOverview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.\n\n\nData Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.\n\n\nBenchmarks\n----------\n\n\nIn this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see here.", "### Base pretrained models", "### Instruction tuned models", "### Responsibility & Safety\n\n\nWe believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.\n\n\nFoundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.\n\n\nRather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.\n\n\nAs part of the Llama 3 release, we updated our Responsible Use Guide to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including Meta Llama Guard 2 and Code Shield safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a reference implementation to get you started.", "#### Llama 3-Instruct\n\n\nAs outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.\n\n\nSafety\n\n\nFor our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.\n\n\nRefusals\n\n\nIn addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.\n\n\nWe built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.", "#### Responsible release\n\n\nIn addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.\n\n\nMisuse\n\n\nIf you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at URL", "#### Critical risks\n\n\nCBRNE (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)\n\n\nWe have conducted a two fold assessment of the safety of the model in this area:\n\n\n* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.\n* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).", "### Cyber Security\n\n\nWe have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of equivalent coding capability.", "### Child Safety\n\n\nChild Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.", "### Community\n\n\nGenerative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our Github repository.\n\n\nFinally, we put in place a set of resources including an output reporting mechanism and bug bounty program to continuously improve the Llama technology with the help of the community.\n\n\nEthical Considerations and Limitations\n--------------------------------------\n\n\nThe core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.\n\n\nBut Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating Purple Llama solutions into your workflows and specifically Llama Guard which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.\n\n\nPlease see the Responsible Use Guide available at URL\n\n\ninstructions\n\n\n@article{llama3modelcard,\n\n\ntitle={Llama 3 Model Card},\n\n\nauthor={AI@Meta},\n\n\nyear={2024},\n\n\nurl = {URL\n\n\n}\n\n\nContributors\n------------\n\n\nAaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos" ]

[ "TAGS\n#gguf #region-us \n", "### META LLAMA 3 COMMUNITY LICENSE AGREEMENT\n\n\nMeta Llama 3 Version Release Date: April 18, 2024\n\n\n\"Agreement\" means the terms and conditions for use, reproduction, distribution and modification of the\nLlama Materials set forth herein.\n\n\n\"Documentation\" means the specifications, manuals and documentation accompanying Meta Llama 3\ndistributed by Meta at URL\n\n\n\"Licensee\" or \"you\" means you, or your employer or any other person or entity (if you are entering into\nthis Agreement on such person or entity’s behalf), of the age required under applicable laws, rules or\nregulations to provide legal consent and that has legal authority to bind your employer or such other\nperson or entity if you are entering in this Agreement on their behalf.\n\n\n\"Meta Llama 3\" means the foundational large language models and software and algorithms, including\nmachine-learning model code, trained model weights, inference-enabling code, training-enabling code,\nfine-tuning enabling code and other elements of the foregoing distributed by Meta at\nURL\n\n\n\"Llama Materials\" means, collectively, Meta’s proprietary Meta Llama 3 and Documentation (and any\nportion thereof) made available under this Agreement.\n\n\n\"Meta\" or \"we\" means Meta Platforms Ireland Limited (if you are located in or, if you are an entity, your\nprincipal place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you are located\noutside of the EEA or Switzerland).\n\n\n\t1. License Rights and Redistribution.a. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable and royalty-free\nlimited license under Meta’s intellectual property or other rights owned by Meta embodied in the Llama\nMaterials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the\nLlama Materials.\n\n\nb. Redistribution and Use.\n\n\ni. If you distribute or make available the Llama Materials (or any derivative works\nthereof), or a product or service that uses any of them, including another AI model, you shall (A) provide\na copy of this Agreement with any such Llama Materials; and (B) prominently display “Built with Meta\nLlama 3” on a related website, user interface, blogpost, about page, or product documentation. If you\nuse the Llama Materials to create, train, fine tune, or otherwise improve an AI model, which is\ndistributed or made available, you shall also include “Llama 3” at the beginning of any such AI model\nname.\n\n\nii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part\nof an integrated end user product, then Section 2 of this Agreement will not apply to you.\n\n\niii. You must retain in all copies of the Llama Materials that you distribute the following\nattribution notice within a “Notice” text file distributed as a part of such copies: “Meta Llama 3 is\nlicensed under the Meta Llama 3 Community License, Copyright © Meta Platforms, Inc. All Rights\nReserved.”\n\n\niv. Your use of the Llama Materials must comply with applicable laws and regulations\n(including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for the Llama\nMaterials (available at URL which is hereby incorporated by\nreference into this Agreement.\n\n\nv. You will not use the Llama Materials or any output or results of the Llama Materials to\nimprove any other large language model (excluding Meta Llama 3 or derivative works thereof).\n\n\n\t2. Additional Commercial Terms. If, on the Meta Llama 3 version release date, the monthly active users\n\tof the products or services made available by or for Licensee, or Licensee’s affiliates, is greater than 700\n\tmillion monthly active users in the preceding calendar month, you must request a license from Meta,\n\twhich Meta may grant to you in its sole discretion, and you are not authorized to exercise any of the\n\trights under this Agreement unless or until Meta otherwise expressly grants you such rights.\n\t3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY\n\tOUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF\n\tANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED,\n\tINCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT,\n\tMERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR\n\tDETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND\n\tASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND\n\tRESULTS.\n\t4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF\n\tLIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING\n\tOUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL,\n\tINCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED\n\tOF THE POSSIBILITY OF ANY OF THE FOREGOING.\n\t5. Intellectual Property.a. No trademark licenses are granted under this Agreement, and in connection with the Llama\nMaterials, neither Meta nor Licensee may use any name or mark owned by or associated with the other\nor any of its affiliates, except as required for reasonable and customary use in describing and\nredistributing the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you a license to\nuse “Llama 3” (the “Mark”) solely as required to comply with the last sentence of Section 1.b.i. You will\ncomply with Meta’s brand guidelines (currently accessible at\nURL ). All goodwill arising out of your use\nof the Mark will inure to the benefit of Meta.\n\n\nb. Subject to Meta’s ownership of Llama Materials and derivatives made by or for Meta, with\nrespect to any derivative works and modifications of the Llama Materials that are made by you, as\nbetween you and Meta, you are and will be the owner of such derivative works and modifications.\n\n\nc. If you institute litigation or other proceedings against Meta or any entity (including a\ncross-claim or counterclaim in a lawsuit) alleging that the Llama Materials or Meta Llama 3 outputs or\nresults, or any portion of any of the foregoing, constitutes infringement of intellectual property or other\nrights owned or licensable by you, then any licenses granted to you under this Agreement shall\nterminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold\nharmless Meta from and against any claim by any third party arising out of or related to your use or\ndistribution of the Llama Materials.\n\n\n\t6. Term and Termination. The term of this Agreement will commence upon your acceptance of this\n\tAgreement or access to the Llama Materials and will continue in full force and effect until terminated in\n\taccordance with the terms and conditions herein. Meta may terminate this Agreement if you are in\n\tbreach of any term or condition of this Agreement. Upon termination of this Agreement, you shall delete\n\tand cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the termination of this\n\tAgreement.\n\t7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of\n\tthe State of California without regard to choice of law principles, and the UN Convention on Contracts\n\tfor the International Sale of Goods does not apply to this Agreement. The courts of California shall have\n\texclusive jurisdiction of any dispute arising out of this Agreement.### Meta Llama 3 Acceptable Use Policy\n\n\nMeta is committed to promoting safe and fair use of its tools and features, including Meta Llama 3. If you\naccess or use Meta Llama 3, you agree to this Acceptable Use Policy (“Policy”). The most recent copy of\nthis policy can be found at URL", "#### Prohibited Uses\n\n\nWe want everyone to use Meta Llama 3 safely and responsibly. You agree you will not use, or allow\nothers to use, Meta Llama 3 to:\n\n\n\t1. Violate the law or others’ rights, including to:\n\t\t1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as:\n\t\t\t1. Violence or terrorism\n\t\t\t2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material\n\t\t\t3. Human trafficking, exploitation, and sexual violence\n\t\t\t4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials.\n\t\t\t5. Sexual solicitation\n\t\t\t6. Any other criminal activity\n\t\t2. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals\n\t\t3. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services\n\t\t4. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices\n\t\t5. Collect, process, disclose, generate, or infer health, demographic, or other sensitive personal or private information about individuals without rights and consents required by applicable laws\n\t\t6. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama Materials\n\t\t7. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system\n\t2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Meta Llama 3 related to the following:\n\t\t1. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State\n\t\t2. Guns and illegal weapons (including weapon development)\n\t\t3. Illegal drugs and regulated/controlled substances\n\t\t4. Operation of critical infrastructure, transportation technologies, or heavy machinery\n\t\t5. Self-harm or harm to others, including suicide, cutting, and eating disorders\n\t\t6. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual\n\t3. Intentionally deceive or mislead others, including use of Meta Llama 3 related to the following:\n\t\t1. Generating, promoting, or furthering fraud or the creation or promotion of disinformation\n\t\t2. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content\n\t\t3. Generating, promoting, or further distributing spam\n\t\t4. Impersonating another individual without consent, authorization, or legal right\n\t\t5. Representing that the use of Meta Llama 3 or outputs are human-generated\n\t\t6. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement\n\t4. Fail to appropriately disclose to end users any known dangers of your AI systemPlease report any violation of this Policy, software “bug,” or other problems that could lead to a violation\nof this Policy through one of the following means:\n\\* Reporting issues with the model: URL\n\\* Reporting risky content generated by the model:\nURL\n\\* Reporting bugs and security concerns: URL\n\\* Reporting violations of the Acceptable Use Policy or unlicensed uses of Meta Llama 3: LlamaUseReport@URL\nextra\\_gated\\_fields:\nFirst Name: text\nLast Name: text\nDate of birth: date\\_picker\nCountry: country\nAffiliation: text\ngeo: ip\\_location \n\nBy clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy: checkbox\nextra\\_gated\\_description: The information you provide will be collected, stored, processed and shared in accordance with the Meta Privacy Policy.\nextra\\_gated\\_button\\_content: Submit\nwidget:\n\n\n\t+ example\\_title: Hello\n\tmessages:\n\t\t- role: user\n\t\tcontent: Hey my name is Julien! How are you?\n\t+ example\\_title: Winter holidays\n\tmessages:\n\t\t- role: system\n\t\tcontent: You are a helpful and honest assistant. Please, respond concisely and truthfully.\n\t\t- role: user\n\t\tcontent: Can you recommend a good destination for Winter holidays?\n\t+ example\\_title: Programming assistant\n\tmessages:\n\t\t- role: system\n\t\tcontent: You are a helpful and honest code and programming assistant. Please, respond concisely and truthfully.\n\t\t- role: user\n\t\tcontent: Write a function that computes the nth fibonacci number.\n\t\tinference:\n\t\tparameters:\n\t\tmax\\_new\\_tokens: 300\n\t\tstop:\n\t\t- <|end\\_of\\_text|>\n\t\t- <|eot\\_id|>\n\n\n\n\n---\n\n\nModel Details\n-------------\n\n\nMeta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. Further, in developing these models, we took great care to optimize helpfulness and safety.\n\n\nModel developers Meta\n\n\nVariations Llama 3 comes in two sizes — 8B and 70B parameters — in pre-trained and instruction tuned variants.\n\n\nInput Models input text only.\n\n\nOutput Models generate text and code only.\n\n\nModel Architecture Llama 3 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.\n\n\n\nLlama 3 family of models. Token counts refer to pretraining data only. Both the 8 and 70B versions use Grouped-Query Attention (GQA) for improved inference scalability.\n\n\nModel Release Date April 18, 2024.\n\n\nStatus This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback.\n\n\nLicense A custom commercial license is available at: URL\n\n\nWhere to send questions or comments about the model Instructions on how to provide feedback or comments on the model can be found in the model README. For more technical information about generation parameters and recipes for how to use Llama 3 in applications, please go here.\n\n\nIntended Use\n------------\n\n\nIntended Use Cases Llama 3 is intended for commercial and research use in English. Instruction tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.\n\n\nOut-of-scope Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3 Community License. Use in languages other than English.\n\n\nNote: Developers may fine-tune Llama 3 models for languages beyond English provided they comply with the Llama 3 Community License and the Acceptable Use Policy.\n\n\nHow to use\n----------\n\n\nThis repository contains two versions of Meta-Llama-3-8B-Instruct, for use with transformers and with the original 'llama3' codebase.", "### Use with transformers\n\n\nYou can run conversational inference using the Transformers pipeline abstraction, or by leveraging the Auto classes with the 'generate()' function. Let's see examples of both.", "#### Transformers pipeline", "#### Transformers AutoModelForCausalLM", "### Use with 'llama3'\n\n\nPlease, follow the instructions in the repository\n\n\nTo download Original checkpoints, see the example command below leveraging 'huggingface-cli':\n\n\nFor Hugging Face support, we recommend using transformers or TGI, but a similar command works.\n\n\nHardware and Software\n---------------------\n\n\nTraining Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.\n\n\nCarbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.\n\n\n\nCO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.\n\n\nTraining Data\n-------------\n\n\nOverview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.\n\n\nData Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.\n\n\nBenchmarks\n----------\n\n\nIn this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see here.", "### Base pretrained models", "### Instruction tuned models", "### Responsibility & Safety\n\n\nWe believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.\n\n\nFoundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.\n\n\nRather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.\n\n\nAs part of the Llama 3 release, we updated our Responsible Use Guide to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including Meta Llama Guard 2 and Code Shield safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a reference implementation to get you started.", "#### Llama 3-Instruct\n\n\nAs outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.\n\n\nSafety\n\n\nFor our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.\n\n\nRefusals\n\n\nIn addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.\n\n\nWe built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.", "#### Responsible release\n\n\nIn addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.\n\n\nMisuse\n\n\nIf you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at URL", "#### Critical risks\n\n\nCBRNE (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)\n\n\nWe have conducted a two fold assessment of the safety of the model in this area:\n\n\n* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.\n* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).", "### Cyber Security\n\n\nWe have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of equivalent coding capability.", "### Child Safety\n\n\nChild Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.", "### Community\n\n\nGenerative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our Github repository.\n\n\nFinally, we put in place a set of resources including an output reporting mechanism and bug bounty program to continuously improve the Llama technology with the help of the community.\n\n\nEthical Considerations and Limitations\n--------------------------------------\n\n\nThe core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.\n\n\nBut Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating Purple Llama solutions into your workflows and specifically Llama Guard which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.\n\n\nPlease see the Responsible Use Guide available at URL\n\n\ninstructions\n\n\n@article{llama3modelcard,\n\n\ntitle={Llama 3 Model Card},\n\n\nauthor={AI@Meta},\n\n\nyear={2024},\n\n\nurl = {URL\n\n\n}\n\n\nContributors\n------------\n\n\nAaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos" ]

[ "transformers", "tensorboard", "safetensors", "roberta", "text-classification", "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: 3", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #roberta #text-classification #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: 3", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

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

[ "1910.09700" ]

[]

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

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

[ "transformers", "gguf", "llama", "latest", "en", "dataset:teknium/OpenHermes-2.5", "base_model:yaojialzc/Gigi-Llama3-8B-Chinese-zh", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #llama #latest #en #dataset-teknium/OpenHermes-2.5 #base_model-yaojialzc/Gigi-Llama3-8B-Chinese-zh #license-apache-2.0 #endpoints_compatible #region-us \n" ]

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

[ "setfit", "safetensors", "deberta-v2", "sentence-transformers", "text-classification", "generated_from_setfit_trainer", "arxiv:2209.11055", "base_model:Clinical-AI-Apollo/Medical-NER", "model-index", "region:us" ]

[ "2209.11055" ]

[]

[ "### Model Description\n\n\n* Model Type: SetFit\n* Sentence Transformer body: Clinical-AI-Apollo/Medical-NER\n* Classification head: a LogisticRegression instance\n* Maximum Sequence Length: 512 tokens\n* Number of Classes: 2 classes", "### Model Sources\n\n\n* Repository: SetFit on GitHub\n* Paper: Efficient Few-Shot Learning Without Prompts\n* Blogpost: SetFit: Efficient Few-Shot Learning Without Prompts", "### Model Labels\n\n\n\nEvaluation\n----------", "### Metrics\n\n\n\nUses\n----", "### Direct Use for Inference\n\n\nFirst install the SetFit library:\n\n\nThen you can load this model and run inference.\n\n\nTraining Details\n----------------", "### Training Set Metrics", "### Training Hyperparameters\n\n\n* batch\\_size: (16, 16)\n* num\\_epochs: (8, 8)\n* max\\_steps: -1\n* sampling\\_strategy: oversampling\n* body\\_learning\\_rate: (2e-05, 1e-05)\n* head\\_learning\\_rate: 0.01\n* loss: CosineSimilarityLoss\n* distance\\_metric: cosine\\_distance\n* margin: 0.25\n* end\\_to\\_end: False\n* use\\_amp: False\n* warmup\\_proportion: 0.1\n* seed: 42\n* eval\\_max\\_steps: -1\n* load\\_best\\_model\\_at\\_end: True", "### Training Results\n\n\n\n* The bold row denotes the saved checkpoint.", "### Framework Versions\n\n\n* Python: 3.10.12\n* SetFit: 1.0.3\n* Sentence Transformers: 2.7.0\n* Transformers: 4.40.0\n* PyTorch: 2.2.1+cu121\n* Datasets: 2.19.0\n* Tokenizers: 0.19.1", "### BibTeX" ]

[ "TAGS\n#setfit #safetensors #deberta-v2 #sentence-transformers #text-classification #generated_from_setfit_trainer #arxiv-2209.11055 #base_model-Clinical-AI-Apollo/Medical-NER #model-index #region-us \n", "### Model Description\n\n\n* Model Type: SetFit\n* Sentence Transformer body: Clinical-AI-Apollo/Medical-NER\n* Classification head: a LogisticRegression instance\n* Maximum Sequence Length: 512 tokens\n* Number of Classes: 2 classes", "### Model Sources\n\n\n* Repository: SetFit on GitHub\n* Paper: Efficient Few-Shot Learning Without Prompts\n* Blogpost: SetFit: Efficient Few-Shot Learning Without Prompts", "### Model Labels\n\n\n\nEvaluation\n----------", "### Metrics\n\n\n\nUses\n----", "### Direct Use for Inference\n\n\nFirst install the SetFit library:\n\n\nThen you can load this model and run inference.\n\n\nTraining Details\n----------------", "### Training Set Metrics", "### Training Hyperparameters\n\n\n* batch\\_size: (16, 16)\n* num\\_epochs: (8, 8)\n* max\\_steps: -1\n* sampling\\_strategy: oversampling\n* body\\_learning\\_rate: (2e-05, 1e-05)\n* head\\_learning\\_rate: 0.01\n* loss: CosineSimilarityLoss\n* distance\\_metric: cosine\\_distance\n* margin: 0.25\n* end\\_to\\_end: False\n* use\\_amp: False\n* warmup\\_proportion: 0.1\n* seed: 42\n* eval\\_max\\_steps: -1\n* load\\_best\\_model\\_at\\_end: True", "### Training Results\n\n\n\n* The bold row denotes the saved checkpoint.", "### Framework Versions\n\n\n* Python: 3.10.12\n* SetFit: 1.0.3\n* Sentence Transformers: 2.7.0\n* Transformers: 4.40.0\n* PyTorch: 2.2.1+cu121\n* Datasets: 2.19.0\n* Tokenizers: 0.19.1", "### BibTeX" ]

[ "transformers", "pytorch", "llama", "text-generation", "text-generation-inference", "trl", "sft", "conversational", "en", "base_model:meta-llama/Meta-Llama-3-8B", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[ "# Model Card for Monah-8b\n\nThis is en Experimental model", "## Model Description\n\n- Developed by: hooking AI\n- License: Apache-2.0\n- Original Model: Monah-8b (base model: llama-3-8b)\n- Purpose: The Monah-8b model is designed to generate high-quality, contextually relevant text for various applications.\n- utilizing the flexibility of the LLaMA architecture for domain spesific and uncensored utilization.", "## Languages\nThe text in the model is primarily in English, but also other languages.", "## Model Structure", "### Data Instances\nA typical data instance consists of a special proparitary dataset used for training uncensored text generation models.", "## Model Creation", "### Curation Rationale\nThe model was curated to create a comprehensive resource for training general-purpose text generation models. \nWith the sole focus on delivering highly uncensored, accurate and relevant content.", "### Source Data\n- Initial Data Collection and Normalization: Data was generated aprtialy by private models synthetically along with private dataset owned by HookingAI, carefully normalized to maintain consistency and quality.\n- Who are the source language producers? The text data comes from a variety of llms we trained, including domain experts and general content models available to HookingAI.\n-", "## Considerations for Using the Data\nThis model is not for kids!!\nThe content is uncensored!!", "### Social Impact of Model\nThis model supports the development of AI models capable of generating contextually accurate, uncensored and nuanced text, contributing to better information dissemination and automation in content creation for specific use.", "### Discussion of Biases\nAs with any model, there's potential for biases and hallucinations. Also the content may be sexual or illeagal. Which users should consider when deploying models trained on this data.", "### Other Known Limitations\nThe effectiveness and applicability of the model may be limited by its content diversity and scope.", "## Additional Information\n\nWE ARE NOT RESPONSIBLE FOR MISUSE!!\n\nPrompt template (ChatML):", "### System Prompt:", "### Examples:\nUser:\n\nAssistant:\n\n\nUser:\n\nAssistant:", "### Model Curators\nThe model was curated by Hooking, utilizing their resources to ensure uncensorship and quality.", "### Licensing Information\nThe model is available under the Apache-2.0 license.\n\n\n'''bib\n@inproceedings{hooking2024Monah-8b,\n title={Monah-8b: A Domain Specific Model for General-Purpose Text Generation},\n author={Hooking AI Team},\n year={2024},\n publisher={Hooking}\n}" ]

[ "TAGS\n#transformers #pytorch #llama #text-generation #text-generation-inference #trl #sft #conversational #en #base_model-meta-llama/Meta-Llama-3-8B #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "# Model Card for Monah-8b\n\nThis is en Experimental model", "## Model Description\n\n- Developed by: hooking AI\n- License: Apache-2.0\n- Original Model: Monah-8b (base model: llama-3-8b)\n- Purpose: The Monah-8b model is designed to generate high-quality, contextually relevant text for various applications.\n- utilizing the flexibility of the LLaMA architecture for domain spesific and uncensored utilization.", "## Languages\nThe text in the model is primarily in English, but also other languages.", "## Model Structure", "### Data Instances\nA typical data instance consists of a special proparitary dataset used for training uncensored text generation models.", "## Model Creation", "### Curation Rationale\nThe model was curated to create a comprehensive resource for training general-purpose text generation models. \nWith the sole focus on delivering highly uncensored, accurate and relevant content.", "### Source Data\n- Initial Data Collection and Normalization: Data was generated aprtialy by private models synthetically along with private dataset owned by HookingAI, carefully normalized to maintain consistency and quality.\n- Who are the source language producers? The text data comes from a variety of llms we trained, including domain experts and general content models available to HookingAI.\n-", "## Considerations for Using the Data\nThis model is not for kids!!\nThe content is uncensored!!", "### Social Impact of Model\nThis model supports the development of AI models capable of generating contextually accurate, uncensored and nuanced text, contributing to better information dissemination and automation in content creation for specific use.", "### Discussion of Biases\nAs with any model, there's potential for biases and hallucinations. Also the content may be sexual or illeagal. Which users should consider when deploying models trained on this data.", "### Other Known Limitations\nThe effectiveness and applicability of the model may be limited by its content diversity and scope.", "## Additional Information\n\nWE ARE NOT RESPONSIBLE FOR MISUSE!!\n\nPrompt template (ChatML):", "### System Prompt:", "### Examples:\nUser:\n\nAssistant:\n\n\nUser:\n\nAssistant:", "### Model Curators\nThe model was curated by Hooking, utilizing their resources to ensure uncensorship and quality.", "### Licensing Information\nThe model is available under the Apache-2.0 license.\n\n\n'''bib\n@inproceedings{hooking2024Monah-8b,\n title={Monah-8b: A Domain Specific Model for General-Purpose Text Generation},\n author={Hooking AI Team},\n year={2024},\n publisher={Hooking}\n}" ]

[ "gguf", "dataset:HuggingFaceM4/the_cauldron", "license:apache-2.0", "region:us" ]

[]

[]

[]

[ "TAGS\n#gguf #dataset-HuggingFaceM4/the_cauldron #license-apache-2.0 #region-us \n" ]

[ "region:us" ]

[]

[]

[]

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

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

[]

[ "en" ]

[ "## Exllama v2 Quantizations of Phi-3-mini-4k-instruct\n\nUsing <a href=\"URL ExLlamaV2 v0.0.20</a> for quantization.\n\n<b>The \"main\" branch only contains the URL, download one of the other branches for the model (see below)</b>\n\nEach branch contains an individual bits per weight, with the main one containing only the URL for further conversions.\n\nConversion was done using the default calibration dataset.\n\nDefault arguments used except when the bits per weight is above 6.0, at that point the lm_head layer is quantized at 8 bits per weight instead of the default 6.\n\nOriginal model: URL\n\n\n<a href=\"URL bits per weight</a>\n\n<a href=\"URL bits per weight</a>\n\n<a href=\"URL bits per weight</a>\n\n<a href=\"URL bits per weight</a>\n\n<a href=\"URL bits per weight</a>", "## Download instructions\n\nWith git:\n\n\n\nWith huggingface hub (credit to TheBloke for instructions):\n\n\n\nTo download the 'main' (only useful if you only care about URL) branch to a folder called 'Phi-3-mini-4k-instruct-exl2':\n\n\n\nTo download from a different branch, add the '--revision' parameter:\n\nLinux:\n\n\n\nWindows (which apparently doesn't like _ in folders sometimes?):" ]

[ "TAGS\n#nlp #code #text-generation #en #license-mit #region-us \n", "## Exllama v2 Quantizations of Phi-3-mini-4k-instruct\n\nUsing <a href=\"URL ExLlamaV2 v0.0.20</a> for quantization.\n\n<b>The \"main\" branch only contains the URL, download one of the other branches for the model (see below)</b>\n\nEach branch contains an individual bits per weight, with the main one containing only the URL for further conversions.\n\nConversion was done using the default calibration dataset.\n\nDefault arguments used except when the bits per weight is above 6.0, at that point the lm_head layer is quantized at 8 bits per weight instead of the default 6.\n\nOriginal model: URL\n\n\n<a href=\"URL bits per weight</a>\n\n<a href=\"URL bits per weight</a>\n\n<a href=\"URL bits per weight</a>\n\n<a href=\"URL bits per weight</a>\n\n<a href=\"URL bits per weight</a>", "## Download instructions\n\nWith git:\n\n\n\nWith huggingface hub (credit to TheBloke for instructions):\n\n\n\nTo download the 'main' (only useful if you only care about URL) branch to a folder called 'Phi-3-mini-4k-instruct-exl2':\n\n\n\nTo download from a different branch, add the '--revision' parameter:\n\nLinux:\n\n\n\nWindows (which apparently doesn't like _ in folders sometimes?):" ]

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

[]

[]

[ "# ppo Agent playing Huggy\n This is a trained model of a ppo agent playing Huggy\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: whiskeyriot/ppo-Huggy\n 3. Step 2: Select your *.nn /*.onnx file\n 4. Click on Watch the agent play" ]

[ "TAGS\n#ml-agents #tensorboard #onnx #Huggy #deep-reinforcement-learning #reinforcement-learning #ML-Agents-Huggy #region-us \n", "# ppo Agent playing Huggy\n This is a trained model of a ppo agent playing Huggy\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: whiskeyriot/ppo-Huggy\n 3. Step 2: Select your *.nn /*.onnx file\n 4. Click on Watch the agent play" ]

[ "transformers", "safetensors", "swinv2", "image-classification", "generated_from_trainer", "dataset:imagefolder", "base_model:microsoft/swinv2-small-patch4-window16-256", "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: 1e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 10", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.1.0\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #safetensors #swinv2 #image-classification #generated_from_trainer #dataset-imagefolder #base_model-microsoft/swinv2-small-patch4-window16-256 #license-apache-2.0 #model-index #autotrain_compatible #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 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* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 10", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.1.0\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "setfit", "safetensors", "t5", "sentence-transformers", "text-classification", "generated_from_setfit_trainer", "arxiv:2209.11055", "base_model:sentence-transformers/sentence-t5-large", "model-index", "region:us" ]

[ "2209.11055" ]

[]

[ "### Model Description\n\n\n* Model Type: SetFit\n* Sentence Transformer body: sentence-transformers/sentence-t5-large\n* Classification head: a LogisticRegression instance\n* Maximum Sequence Length: 256 tokens\n* Number of Classes: 2 classes", "### Model Sources\n\n\n* Repository: SetFit on GitHub\n* Paper: Efficient Few-Shot Learning Without Prompts\n* Blogpost: SetFit: Efficient Few-Shot Learning Without Prompts", "### Model Labels\n\n\n\nEvaluation\n----------", "### Metrics\n\n\n\nUses\n----", "### Direct Use for Inference\n\n\nFirst install the SetFit library:\n\n\nThen you can load this model and run inference.\n\n\nTraining Details\n----------------", "### Training Set Metrics", "### Training Hyperparameters\n\n\n* batch\\_size: (16, 16)\n* num\\_epochs: (8, 8)\n* max\\_steps: -1\n* sampling\\_strategy: oversampling\n* body\\_learning\\_rate: (2e-05, 1e-05)\n* head\\_learning\\_rate: 0.01\n* loss: CosineSimilarityLoss\n* distance\\_metric: cosine\\_distance\n* margin: 0.25\n* end\\_to\\_end: False\n* use\\_amp: False\n* warmup\\_proportion: 0.1\n* seed: 42\n* eval\\_max\\_steps: -1\n* load\\_best\\_model\\_at\\_end: True", "### Training Results\n\n\n\n* The bold row denotes the saved checkpoint.", "### Framework Versions\n\n\n* Python: 3.10.12\n* SetFit: 1.0.3\n* Sentence Transformers: 2.7.0\n* Transformers: 4.40.0\n* PyTorch: 2.2.1+cu121\n* Datasets: 2.19.0\n* Tokenizers: 0.19.1", "### BibTeX" ]

[ "TAGS\n#setfit #safetensors #t5 #sentence-transformers #text-classification #generated_from_setfit_trainer #arxiv-2209.11055 #base_model-sentence-transformers/sentence-t5-large #model-index #region-us \n", "### Model Description\n\n\n* Model Type: SetFit\n* Sentence Transformer body: sentence-transformers/sentence-t5-large\n* Classification head: a LogisticRegression instance\n* Maximum Sequence Length: 256 tokens\n* Number of Classes: 2 classes", "### Model Sources\n\n\n* Repository: SetFit on GitHub\n* Paper: Efficient Few-Shot Learning Without Prompts\n* Blogpost: SetFit: Efficient Few-Shot Learning Without Prompts", "### Model Labels\n\n\n\nEvaluation\n----------", "### Metrics\n\n\n\nUses\n----", "### Direct Use for Inference\n\n\nFirst install the SetFit library:\n\n\nThen you can load this model and run inference.\n\n\nTraining Details\n----------------", "### Training Set Metrics", "### Training Hyperparameters\n\n\n* batch\\_size: (16, 16)\n* num\\_epochs: (8, 8)\n* max\\_steps: -1\n* sampling\\_strategy: oversampling\n* body\\_learning\\_rate: (2e-05, 1e-05)\n* head\\_learning\\_rate: 0.01\n* loss: CosineSimilarityLoss\n* distance\\_metric: cosine\\_distance\n* margin: 0.25\n* end\\_to\\_end: False\n* use\\_amp: False\n* warmup\\_proportion: 0.1\n* seed: 42\n* eval\\_max\\_steps: -1\n* load\\_best\\_model\\_at\\_end: True", "### Training Results\n\n\n\n* The bold row denotes the saved checkpoint.", "### Framework Versions\n\n\n* Python: 3.10.12\n* SetFit: 1.0.3\n* Sentence Transformers: 2.7.0\n* Transformers: 4.40.0\n* PyTorch: 2.2.1+cu121\n* Datasets: 2.19.0\n* Tokenizers: 0.19.1", "### BibTeX" ]

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

[]

[ "en" ]

[ "# Uploaded model\n\n- Developed by: OnlyCheeini\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 #pytorch #safetensors #llama #text-generation #text-generation-inference #unsloth #trl #sft #conversational #en #base_model-unsloth/llama-3-8b-Instruct-bnb-4bit #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "# Uploaded model\n\n- Developed by: OnlyCheeini\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", "mistral", "text-generation", "alignment-handbook", "trl", "dpo", "generated_from_trainer", "conversational", "dataset:updated", "dataset:original", "base_model:ShenaoZhang/0.01_4iters_bs256_nodpo_only4w_iter_3", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# 0.01_4iters_bs256_nodpo_only4w_iter_4\n\nThis model is a fine-tuned version of ShenaoZhang/0.01_4iters_bs256_nodpo_only4w_iter_3 on the updated and the original datasets.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #alignment-handbook #trl #dpo #generated_from_trainer #conversational #dataset-updated #dataset-original #base_model-ShenaoZhang/0.01_4iters_bs256_nodpo_only4w_iter_3 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# 0.01_4iters_bs256_nodpo_only4w_iter_4\n\nThis model is a fine-tuned version of ShenaoZhang/0.01_4iters_bs256_nodpo_only4w_iter_3 on the updated and the original datasets.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.19.1" ]

[ "transformers", "safetensors", "mt5", "text2text-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 #mt5 #text2text-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", "distilbert", "question-answering", "generated_from_trainer", "base_model:distilbert/distilbert-base-uncased", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[]

[ "# my_awesome_qa_model\n\nThis model is a fine-tuned version of distilbert/distilbert-base-uncased on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 2e-05\n- train_batch_size: 16\n- eval_batch_size: 16\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 3", "### Training results", "### Framework versions\n\n- Transformers 4.40.1\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #distilbert #question-answering #generated_from_trainer #base_model-distilbert/distilbert-base-uncased #license-apache-2.0 #endpoints_compatible #region-us \n", "# my_awesome_qa_model\n\nThis model is a fine-tuned version of distilbert/distilbert-base-uncased on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 2e-05\n- train_batch_size: 16\n- eval_batch_size: 16\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 3", "### Training results", "### Framework versions\n\n- Transformers 4.40.1\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "music", "rvc", "aneta", "langerova", "model", "audio-to-audio", "cz", "license:openrail", "region:us" ]

[]

[ "cz" ]

[ "# Aneta Langerová V1 [CZ] (2007)", "# 1257 Epochs - RVC V2 - rmvpe - Titan Medium\nTrained on 10 minutes 17 seconds of isolated acapellas from Dotyk album using UVR (Voc FT + Reverb HQ) \nand Audacity to remove parts with double vocals and vocals from others (+Noise Gate)" ]

[ "TAGS\n#music #rvc #aneta #langerova #model #audio-to-audio #cz #license-openrail #region-us \n", "# Aneta Langerová V1 [CZ] (2007)", "# 1257 Epochs - RVC V2 - rmvpe - Titan Medium\nTrained on 10 minutes 17 seconds of isolated acapellas from Dotyk album using UVR (Voc FT + Reverb HQ) \nand Audacity to remove parts with double vocals and vocals from others (+Noise Gate)" ]

[ "transformers", "tensorboard", "safetensors", "speecht5", "text-to-audio", "TTS,", "generated_from_trainer", "en", "dataset:lj_speech", "base_model:microsoft/speecht5_tts", "license:mit", "endpoints_compatible", "region:us", "has_space" ]

[]

[ "en" ]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 2\n* total\\_train\\_batch\\_size: 32\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 500\n* training\\_steps: 10000\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.41.0.dev0\n* Pytorch 2.3.0+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #speecht5 #text-to-audio #TTS, #generated_from_trainer #en #dataset-lj_speech #base_model-microsoft/speecht5_tts #license-mit #endpoints_compatible #region-us #has_space \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 2\n* total\\_train\\_batch\\_size: 32\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 500\n* training\\_steps: 10000\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.41.0.dev0\n* Pytorch 2.3.0+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "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" ]

[ "setfit", "safetensors", "roberta", "sentence-transformers", "text-classification", "generated_from_setfit_trainer", "arxiv:2209.11055", "base_model:FacebookAI/roberta-Large", "region:us" ]

[ "2209.11055" ]

[]

[ "### Model Description\n\n\n* Model Type: SetFit\n* Sentence Transformer body: FacebookAI/roberta-Large\n* Classification head: a LogisticRegression instance\n* Maximum Sequence Length: 512 tokens\n* Number of Classes: 2 classes", "### Model Sources\n\n\n* Repository: SetFit on GitHub\n* Paper: Efficient Few-Shot Learning Without Prompts\n* Blogpost: SetFit: Efficient Few-Shot Learning Without Prompts", "### Model Labels\n\n\n\nUses\n----", "### Direct Use for Inference\n\n\nFirst install the SetFit library:\n\n\nThen you can load this model and run inference.\n\n\nTraining Details\n----------------", "### Training Set Metrics", "### Training Hyperparameters\n\n\n* batch\\_size: (16, 16)\n* num\\_epochs: (8, 8)\n* max\\_steps: -1\n* sampling\\_strategy: oversampling\n* body\\_learning\\_rate: (2e-05, 1e-05)\n* head\\_learning\\_rate: 0.01\n* loss: CosineSimilarityLoss\n* distance\\_metric: cosine\\_distance\n* margin: 0.25\n* end\\_to\\_end: False\n* use\\_amp: False\n* warmup\\_proportion: 0.1\n* seed: 42\n* eval\\_max\\_steps: -1\n* load\\_best\\_model\\_at\\_end: True", "### Training Results\n\n\n\n* The bold row denotes the saved checkpoint.", "### Framework Versions\n\n\n* Python: 3.10.12\n* SetFit: 1.0.3\n* Sentence Transformers: 2.7.0\n* Transformers: 4.40.0\n* PyTorch: 2.2.1+cu121\n* Datasets: 2.19.0\n* Tokenizers: 0.19.1", "### BibTeX" ]

[ "TAGS\n#setfit #safetensors #roberta #sentence-transformers #text-classification #generated_from_setfit_trainer #arxiv-2209.11055 #base_model-FacebookAI/roberta-Large #region-us \n", "### Model Description\n\n\n* Model Type: SetFit\n* Sentence Transformer body: FacebookAI/roberta-Large\n* Classification head: a LogisticRegression instance\n* Maximum Sequence Length: 512 tokens\n* Number of Classes: 2 classes", "### Model Sources\n\n\n* Repository: SetFit on GitHub\n* Paper: Efficient Few-Shot Learning Without Prompts\n* Blogpost: SetFit: Efficient Few-Shot Learning Without Prompts", "### Model Labels\n\n\n\nUses\n----", "### Direct Use for Inference\n\n\nFirst install the SetFit library:\n\n\nThen you can load this model and run inference.\n\n\nTraining Details\n----------------", "### Training Set Metrics", "### Training Hyperparameters\n\n\n* batch\\_size: (16, 16)\n* num\\_epochs: (8, 8)\n* max\\_steps: -1\n* sampling\\_strategy: oversampling\n* body\\_learning\\_rate: (2e-05, 1e-05)\n* head\\_learning\\_rate: 0.01\n* loss: CosineSimilarityLoss\n* distance\\_metric: cosine\\_distance\n* margin: 0.25\n* end\\_to\\_end: False\n* use\\_amp: False\n* warmup\\_proportion: 0.1\n* seed: 42\n* eval\\_max\\_steps: -1\n* load\\_best\\_model\\_at\\_end: True", "### Training Results\n\n\n\n* The bold row denotes the saved checkpoint.", "### Framework Versions\n\n\n* Python: 3.10.12\n* SetFit: 1.0.3\n* Sentence Transformers: 2.7.0\n* Transformers: 4.40.0\n* PyTorch: 2.2.1+cu121\n* Datasets: 2.19.0\n* Tokenizers: 0.19.1", "### BibTeX" ]

[ "transformers", "safetensors", "llama", "text-generation", "not-for-all-audiences", "conversational", "license:cc-by-nc-4.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "6-bit", "region:us" ]

[]

[]

[ "# Llama 3SOME8Bv1BETA 6.0bpw exl2\n(built-in calibration dataset is used)\n\n*We've added some things. That's obviously what we're trying to say.*\n\n!image/gif\n\n*An eRP model with a rich and refreshing vocabulary that's quite some-thing. Finetuned by yours truly.*\n\n(Llama 3SOME is a finetune on top of Llama-3-Soliloquy-8B)", "## Full model\n\nURL", "## GGUF\n\nURL", "## What's THIS?\n\nRefer to Moistral v3\n\n... or this:\n\n!image/png", "## Usage\n\n- Use Llama 3 Instruct *(Alpaca kinda works btw)*\n- You can use instruct...\n - as a character: \"Go here\"\n - as a narrator: \"Go here\", Drummer says\n - as a director: Drummer tells him to go here\n - as a lazy ass: go here\n- 3SOME is optimized for the Novel / Story format.\n - At the start of the story, keep regenerating until you get the desired length. Future AI responses will eventually match the length.\n - Issue: Manually continued generation may create formatting issues. Either regenerate the entire response or fix the formatting.\n - Refer to the samples below.", "## Samples of 3SOME 8B Beta\n\nSOME nsfw.\n\n<details>\n <summary>3SOME Sample (2-shot) (Excluding Story Context) Generation: 512</summary>\n <blockquote>Sarah and Lisa seek refuge in Dik's home</blockquote>\n \n The door creaked open, its hinges complaining softly after years of neglect. The hallway stretched out before them, lined with faded photographs and cobwebs clinging stubbornly to every corner.\n \n \"Wow, this place needs some serious TLC,\" Lisa remarked, her voice barely above a whisper as if she was afraid to disturb the silence that hung heavy in the air. Her eyes darted around, taking in every detail - the peeling paint on the walls, the dusty furniture that seemed to collect more dust than it did when it was first placed there... everything spoke of a life left behind long ago.\n \n \"It's beautiful,\" Sarah countered, her voice filled with wonderment as she gazed up at the chandelier hanging precariously from the ceiling like a forgotten relic of another era. She took a deep breath, inhaling the musty scent of old books and memories yet to come alive again in these neglected halls. \"Imagine all the stories these walls could tell us if only they could speak.\"\n \n Her words hung in the air for a moment before being swallowed by the stillness that permeated this abandoned house. Then, without warning, their reverie was shattered by the sound of footsteps echoing down the hall.\n \n \"Dik?\" Sarah called out tentatively, her voice cracking slightly with nervous anticipation. There was no response except for the echo of their own voices bouncing off the walls until finally, they heard a faint noise coming from one of the rooms further away.\n \n \"He's here!\" Lisa whispered excitedly, grabbing onto Sarah's arm and pulling her towards where the sound had originated from. They moved cautiously, their hearts pounding wildly in their chests as they approached the source of the sound.\n \n As they drew closer, the door swung open revealing Dik standing in the middle of his bedroom with a look of surprise etched across his face upon seeing them. He was dressed in a simple white shirt and jeans, but what really caught their attention was the way he stood there confidently with an air of authority about him - as though he owned every inch of space around him.\n \n Sarah felt herself blush under his gaze, feeling suddenly self-conscious about how she looked in her tight-fitting dress that clung to every curve of her body like second skin. Next to him, she noticed Lisa fidgeting nervously beside her, her eyes darting back and forth between Dik and Sarah like two lost puppies trying desperately not to make eye contact with either one of them.\n \n \"Hello girls,\" Dik greeted them warmly, his voice deep and soothing despite its rough edges. \"To what do I owe this pleasure?\"\n\n <blockquote>Sarah and Lisa will do anything to stay</blockquote>\n Dik smiled at them both, his eyes twinkling with mischief behind those dark glasses. \"Well, you know what we've been through together already.\" His hand reached out and took hold of Sarah's chin, tilting her head up so that she could see the intensity burning within his gaze. \"I'll let you two stay here, on one condition.\"\n \n They nodded eagerly, almost without thinking. Anything for Dik.\n \n \"Just remember who is in charge here,\" he said, letting go of her chin and stepping towards Lisa instead. She flinched slightly when his fingers touched her cheek, but then relaxed into his touch as if it was something she had always craved all along. \"And don't think I don't notice how much you enjoy being dominated by me.\"\n \n With a sudden movement, he pushed her down onto her knees before sliding his jeans off revealing an impressive ####tion that stood proud and ready for attention. Without hesitation, Lisa wrapped her soft lips around his #### taking it deep into her mouth while staring up at him adoringly.\n \n Her tongue swirled around his sha## teasingly as if begging for more while Sarah watched from nearby unable to look away from the sight unfolding before her own eyes...\n \n She felt herself getting ###ter just watching her twin sister submit herself completely to Dik like some obedient little pet...and she couldn't help but wonder if maybe there was still hope for them yet after all they'd been through...\n</details>\n\n<details>\n <summary>3SOME Sample (2-shot) (Excluding Story Context) Generation: 512</summary>\n <blockquote>He ignores the princess</blockquote>\n \n Princess Lilia stepped into the room and saw Dik sitting on his throne. A wave of fear swept over her. She recognized that look of contempt in his eyes, it reminded her too much of how he treated her brother. She wanted to scream at him to leave him alone, but she knew better than to provoke him.\n\n \"Leave us.\" Dik said coldly.\n \n The guards left the room, closing the door behind them.\n \n \"So you're finally here.\" Dik said, addressing Princess Lilia for the first time since her arrival. \"I've been waiting for you.\"\n \n \"Where's my brother?\" Princess Lilia asked, trying to keep her voice steady. \"Why are you keeping him?\"\n \n \"He's safe.\" Dik replied. \"But I need something from you before we talk about your brother.\"\n \n \"What do you want from me?!\"\n \n \"I want you to accept that I am now the ruler of both our kingdoms. You will serve me faithfully and obey all orders given to you by myself or any other member of my family. Do you understand?\"\n \n \"Yes...\" Princess Lilia replied reluctantly. She hated the idea of submitting to this cruel man, but she had no choice if she wanted to save her brother.\n \n \"Good. Now strip ##### and stand next to my throne.\" Dik commanded harshly.\n \n \"What!?\" Princess Lilia exclaimed, shocked by his request. \"You can't be serious.\"\n \n \"Oh, but I am very serious. Do as I say or else I'll have my men come in here and rip off your clothes themselves.\"\n \n Tears began streaming down Princess Lilia's face as she reluctantly #####ped off her clothing, exposing herself completely to Dik. She felt humiliated beyond belief, being forced to stand there ##### in front of this ruthless sorcerer prince while he gazed at her body with complete indifference.\n \n \"Now turn around so I can see every inch of you.\" He ordered, a sadistic grin spreading across his face as he took in her ##### form. Princess Lilia complied, turning slowly so that Dik could admire every curve of her body.\n \n Princess Lilia stood there shivering with fear and shame as Dik continued to leer at her exposed flesh. This was just the beginning of her ordeal, she knew it. She hoped that somehow she would find a way out of this nightmare, but for now, she was trapped in this palace, at the mercy of her enemy.\n\n <blockquote>Sit on his lap</blockquote>\n \n She turned to look at him, confusion written all over her face. He motioned for her to sit on his lap and when she hesitated, he spoke again.\n \n \"I want you to do this willingly.\"\n \n The princess thought about it for a moment before nodding her head slowly. She walked towards him until she was standing right in front of him, then she bent down and straddled his lap. Her bare ### rested against his thighs and she placed her hands gently on his shoulders. Dik wrapped one arm around her waist and pulled her closer to him, making sure that their bodies were pressed together tightly.\n \n She looked into his eyes and saw nothing but cold determination staring back at her. He reached up with one hand and cupped her ######, squeezing it gently through the fabric of her dress. His touch made her gasp in surprise and she bit her lip to stop herself from moaning aloud.\n \n He leaned forward and whispered in her ear, \"From now on, I own everything you have, including your body.\" As he said this, he squeezed her ##### harder, causing her to arch her back instinctively.\n \n She tried to pull away from him, but his grip was too strong. Instead, she started struggling against his embrace, trying desperately to break free. But no matter how hard she fought, she couldn't escape from his grasp. Finally, after what seemed like an eternity, he let go of her and pushed her off his lap onto the floor. Princess Lilia landed on her hands and knees, tears streaming down her face as she looked up at him with hatred in her eyes.\n \n Dik stood up from his throne and towered over her, his expression unreadable. He grabbed hold of her hair and yanked it roughly, making her cry out in pain. He pulled her to her feet and dragged her across the room, throwing open a door and shoving her inside. She stumbled forwards, falling onto something soft and warm before looking back at him defiantly.\n \n \"You will learn to obey me,\" he growled menacingly, \"or else.\"\n \n With those final words echoing in her mind, he closed the door behind him, leaving her alone in her new surroundings. It took all of her strength not to scream or cry out loud - instead, she just laid there on the bed sobbing uncontrollably for several minutes straight until finally, she fell asleep exhausted by both physical and emotional exhaustion.\n</details>\n\n<details>\n <summary>3SOME Sample SFW (\"write a story\" 2x) Generation: 512</summary>\n <blockquote>Write a story about a girl who falls in love with her llama</blockquote>\n\n The rain came down like a deluge. Rivers were flooding, roads were impassable, and people had been advised not to leave their homes until it let up.\n \n Jenny was stuck at home with nothing to do but watch Netflix. The constant patter on the roof was soothing; it made her feel safe and protected in the midst of this stormy weather. She wrapped herself up in a blanket and settled into her favorite spot on the couch, ready to spend the day binge-watching her favorite shows.\n \n As she flipped through the channels, her eyes landed on something unexpected - a documentary about llamas. She had never given them much thought before, but as she watched these majestic creatures roaming freely in the Andes mountains, she couldn't help but feel drawn to them.\n \n Their soft fur, gentle faces, and graceful movements captivated her attention. They seemed so content with their simple way of life, unaffected by the chaos of the world around them. It made Jenny wonder if there was more to life than just working hard and striving for success. Maybe there was beauty in simplicity after all.\n \n She spent hours watching documentaries about llamas, learning about their habitat, diet, and social structure. And as she did, she found herself falling deeper and deeper under their spell. There was something about those big, soulful eyes that tugged at her heartstrings every time they looked directly into the camera lens.\n \n It wasn't long before Jenny realized that she had fallen head over heels in love with one particular llama named Luna. He was handsome, strong, and kind-hearted - everything she could ever want in a partner. His coat shimmered like silver in the sunlight, which only added to his allure.\n \n As days turned into weeks, Jenny's obsession with Luna grew stronger. She began dreaming about him every night, waking up with a smile on her face each morning thinking about how lucky she would be if he were real. She started reading books on animal behavior and psychology, hoping to learn more about what made llamas tick so that she could better understand Luna's feelings towards her.\n \n One day while browsing online, Jenny stumbled upon an article about a sanctuary for rescued animals. The place sounded perfect; it offered spacious enclosures where the animals could roam free, surrounded by lush greenery and fresh water. Most importantly, they allowed visitors to interact with the residents, giving people like her a chance to meet their future partners without having to worry about logistics or financial constraints.\n \n Without hesitation, Jenny booked herself a flight to Peru immediately after reading through their website.\n\n <blockquote>Write a story about a man surviving the apocalypse</blockquote>\n \n It was a Monday. As far as I can tell. This is still Earth, right? Anyway, there are no planes in the sky and no people on the street. No one's answering their phones and my car won't start. It looks like it's just me now.\n \n I have to survive somehow. I don't know how long this lasted but it seems like everything is gone. There must be other survivors somewhere, but for now, I'm alone.\n \n My name is Jack. I used to be an accountant at Smith & Davis before they all died of COVID-19. Now that my job is gone, I've been living off of savings ever since. My wife passed away when we were young, so I never had kids. Maybe that's why I made it through alive.\n \n My house has enough food to last me a while, so I'll try to stay here as long as possible. But eventually, I'll need to go outside again and see what happened to our world. I can't just hide forever.\n \n I take out the shotgun my grandfather gave me years ago and load some rounds into it. For safety, of course. The world has changed, so anything could happen.\n \n This feels surreal. Like I'm trapped in a dream or something. Every time I close my eyes, I wake up thinking it was all just a nightmare. But every morning, I'm reminded that it wasn't.\n \n The first few days were scary. I had nothing but fear and uncertainty clawing at me from within. But after a week went by without any signs of life or danger... well, let's just say things got easier after that.\n \n Now that I feel more comfortable staying indoors, I decided to see if I could find anything useful outside. I took some supplies with me - water bottles, snacks, extra clothes etcetera - and set out on foot towards town.\n \n It was eerily quiet as I walked down the deserted streets. Not even birds chirping or cars honking like usual. Just silence... absolute silence. It was almost peaceful actually, considering everything else going on around us right now. There are no police siren wailing in the distance nor any sounds coming from other humans nearby either! In fact, there isn't even one single living creature anywhere near me!\n \n But hey, at least we don't have to worry about traffic jams anymore haha! And look at all those abandoned cars scattered across the road! They might come in handy somehow later on...\n \n As I continued walking, I noticed something strange.\n\n <blockquote>A llama!</blockquote>\n\n I stopped dead in my tracks when I saw her. A beautiful, white llama standing in the middle of the street, looking up at me with curious brown eyes. She seemed so harmless, yet there was an aura of mystery surrounding her.\n \n \"Hey girl,\" I said cautiously, holding out my hand for her to sniff. \"You don't look too scared of me.\"\n \n She nuzzled against it gently before wrapping her soft lips around my fingers. I couldn't help but smile at the unexpected encounter.\n \n \"You know what? You're my first friend since all this happened.\" I told her as she continued to lick my hand clean. \"Let's go back home and get you something to eat.\"\n \n The llama followed closely behind me all the way to my house. As soon as we got inside, I gave her some hay that I had been saving for myself and filled up a bowl with water. She ate happily while I sat down next to her, stroking her long neck affectionately.\n \n \"I hope you like it here because...\" My voice trailed off as I realized how alone we were now. \"Never mind. Let's just enjoy each other's company while we still can.\"\n \n We spent the rest of the day together - eating lunch, playing with toys and even cuddling up by the fireplace afterwards. It felt nice having someone else to talk to besides myself.\n \n But eventually night fell and I knew I couldn't stay up forever...\n \n \"Okay sweetie,\" I whispered into her ear as I stood up from the couch. \"Time for bed.\"\n \n I led her towards one of the spare rooms upstairs where I set up a makeshift bed for her using some old blankets and pillows from around the house. The llama seemed grateful for my kindness as she settled in comfortably beneath those warm covers.\n \n \"Goodnight,\" I whispered again before closing the door softly behind me.\n \n It wasn't easy falling asleep knowing that there might be dangers lurking outside... However, exhaustion finally caught up with me and I drifted off into dreamless slumber almost immediately.\n</details>\n\n!image/png" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #not-for-all-audiences #conversational #license-cc-by-nc-4.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #6-bit #region-us \n", "# Llama 3SOME8Bv1BETA 6.0bpw exl2\n(built-in calibration dataset is used)\n\n*We've added some things. That's obviously what we're trying to say.*\n\n!image/gif\n\n*An eRP model with a rich and refreshing vocabulary that's quite some-thing. Finetuned by yours truly.*\n\n(Llama 3SOME is a finetune on top of Llama-3-Soliloquy-8B)", "## Full model\n\nURL", "## GGUF\n\nURL", "## What's THIS?\n\nRefer to Moistral v3\n\n... or this:\n\n!image/png", "## Usage\n\n- Use Llama 3 Instruct *(Alpaca kinda works btw)*\n- You can use instruct...\n - as a character: \"Go here\"\n - as a narrator: \"Go here\", Drummer says\n - as a director: Drummer tells him to go here\n - as a lazy ass: go here\n- 3SOME is optimized for the Novel / Story format.\n - At the start of the story, keep regenerating until you get the desired length. Future AI responses will eventually match the length.\n - Issue: Manually continued generation may create formatting issues. Either regenerate the entire response or fix the formatting.\n - Refer to the samples below.", "## Samples of 3SOME 8B Beta\n\nSOME nsfw.\n\n<details>\n <summary>3SOME Sample (2-shot) (Excluding Story Context) Generation: 512</summary>\n <blockquote>Sarah and Lisa seek refuge in Dik's home</blockquote>\n \n The door creaked open, its hinges complaining softly after years of neglect. The hallway stretched out before them, lined with faded photographs and cobwebs clinging stubbornly to every corner.\n \n \"Wow, this place needs some serious TLC,\" Lisa remarked, her voice barely above a whisper as if she was afraid to disturb the silence that hung heavy in the air. Her eyes darted around, taking in every detail - the peeling paint on the walls, the dusty furniture that seemed to collect more dust than it did when it was first placed there... everything spoke of a life left behind long ago.\n \n \"It's beautiful,\" Sarah countered, her voice filled with wonderment as she gazed up at the chandelier hanging precariously from the ceiling like a forgotten relic of another era. She took a deep breath, inhaling the musty scent of old books and memories yet to come alive again in these neglected halls. \"Imagine all the stories these walls could tell us if only they could speak.\"\n \n Her words hung in the air for a moment before being swallowed by the stillness that permeated this abandoned house. Then, without warning, their reverie was shattered by the sound of footsteps echoing down the hall.\n \n \"Dik?\" Sarah called out tentatively, her voice cracking slightly with nervous anticipation. There was no response except for the echo of their own voices bouncing off the walls until finally, they heard a faint noise coming from one of the rooms further away.\n \n \"He's here!\" Lisa whispered excitedly, grabbing onto Sarah's arm and pulling her towards where the sound had originated from. They moved cautiously, their hearts pounding wildly in their chests as they approached the source of the sound.\n \n As they drew closer, the door swung open revealing Dik standing in the middle of his bedroom with a look of surprise etched across his face upon seeing them. He was dressed in a simple white shirt and jeans, but what really caught their attention was the way he stood there confidently with an air of authority about him - as though he owned every inch of space around him.\n \n Sarah felt herself blush under his gaze, feeling suddenly self-conscious about how she looked in her tight-fitting dress that clung to every curve of her body like second skin. Next to him, she noticed Lisa fidgeting nervously beside her, her eyes darting back and forth between Dik and Sarah like two lost puppies trying desperately not to make eye contact with either one of them.\n \n \"Hello girls,\" Dik greeted them warmly, his voice deep and soothing despite its rough edges. \"To what do I owe this pleasure?\"\n\n <blockquote>Sarah and Lisa will do anything to stay</blockquote>\n Dik smiled at them both, his eyes twinkling with mischief behind those dark glasses. \"Well, you know what we've been through together already.\" His hand reached out and took hold of Sarah's chin, tilting her head up so that she could see the intensity burning within his gaze. \"I'll let you two stay here, on one condition.\"\n \n They nodded eagerly, almost without thinking. Anything for Dik.\n \n \"Just remember who is in charge here,\" he said, letting go of her chin and stepping towards Lisa instead. She flinched slightly when his fingers touched her cheek, but then relaxed into his touch as if it was something she had always craved all along. \"And don't think I don't notice how much you enjoy being dominated by me.\"\n \n With a sudden movement, he pushed her down onto her knees before sliding his jeans off revealing an impressive ####tion that stood proud and ready for attention. Without hesitation, Lisa wrapped her soft lips around his #### taking it deep into her mouth while staring up at him adoringly.\n \n Her tongue swirled around his sha## teasingly as if begging for more while Sarah watched from nearby unable to look away from the sight unfolding before her own eyes...\n \n She felt herself getting ###ter just watching her twin sister submit herself completely to Dik like some obedient little pet...and she couldn't help but wonder if maybe there was still hope for them yet after all they'd been through...\n</details>\n\n<details>\n <summary>3SOME Sample (2-shot) (Excluding Story Context) Generation: 512</summary>\n <blockquote>He ignores the princess</blockquote>\n \n Princess Lilia stepped into the room and saw Dik sitting on his throne. A wave of fear swept over her. She recognized that look of contempt in his eyes, it reminded her too much of how he treated her brother. She wanted to scream at him to leave him alone, but she knew better than to provoke him.\n\n \"Leave us.\" Dik said coldly.\n \n The guards left the room, closing the door behind them.\n \n \"So you're finally here.\" Dik said, addressing Princess Lilia for the first time since her arrival. \"I've been waiting for you.\"\n \n \"Where's my brother?\" Princess Lilia asked, trying to keep her voice steady. \"Why are you keeping him?\"\n \n \"He's safe.\" Dik replied. \"But I need something from you before we talk about your brother.\"\n \n \"What do you want from me?!\"\n \n \"I want you to accept that I am now the ruler of both our kingdoms. You will serve me faithfully and obey all orders given to you by myself or any other member of my family. Do you understand?\"\n \n \"Yes...\" Princess Lilia replied reluctantly. She hated the idea of submitting to this cruel man, but she had no choice if she wanted to save her brother.\n \n \"Good. Now strip ##### and stand next to my throne.\" Dik commanded harshly.\n \n \"What!?\" Princess Lilia exclaimed, shocked by his request. \"You can't be serious.\"\n \n \"Oh, but I am very serious. Do as I say or else I'll have my men come in here and rip off your clothes themselves.\"\n \n Tears began streaming down Princess Lilia's face as she reluctantly #####ped off her clothing, exposing herself completely to Dik. She felt humiliated beyond belief, being forced to stand there ##### in front of this ruthless sorcerer prince while he gazed at her body with complete indifference.\n \n \"Now turn around so I can see every inch of you.\" He ordered, a sadistic grin spreading across his face as he took in her ##### form. Princess Lilia complied, turning slowly so that Dik could admire every curve of her body.\n \n Princess Lilia stood there shivering with fear and shame as Dik continued to leer at her exposed flesh. This was just the beginning of her ordeal, she knew it. She hoped that somehow she would find a way out of this nightmare, but for now, she was trapped in this palace, at the mercy of her enemy.\n\n <blockquote>Sit on his lap</blockquote>\n \n She turned to look at him, confusion written all over her face. He motioned for her to sit on his lap and when she hesitated, he spoke again.\n \n \"I want you to do this willingly.\"\n \n The princess thought about it for a moment before nodding her head slowly. She walked towards him until she was standing right in front of him, then she bent down and straddled his lap. Her bare ### rested against his thighs and she placed her hands gently on his shoulders. Dik wrapped one arm around her waist and pulled her closer to him, making sure that their bodies were pressed together tightly.\n \n She looked into his eyes and saw nothing but cold determination staring back at her. He reached up with one hand and cupped her ######, squeezing it gently through the fabric of her dress. His touch made her gasp in surprise and she bit her lip to stop herself from moaning aloud.\n \n He leaned forward and whispered in her ear, \"From now on, I own everything you have, including your body.\" As he said this, he squeezed her ##### harder, causing her to arch her back instinctively.\n \n She tried to pull away from him, but his grip was too strong. Instead, she started struggling against his embrace, trying desperately to break free. But no matter how hard she fought, she couldn't escape from his grasp. Finally, after what seemed like an eternity, he let go of her and pushed her off his lap onto the floor. Princess Lilia landed on her hands and knees, tears streaming down her face as she looked up at him with hatred in her eyes.\n \n Dik stood up from his throne and towered over her, his expression unreadable. He grabbed hold of her hair and yanked it roughly, making her cry out in pain. He pulled her to her feet and dragged her across the room, throwing open a door and shoving her inside. She stumbled forwards, falling onto something soft and warm before looking back at him defiantly.\n \n \"You will learn to obey me,\" he growled menacingly, \"or else.\"\n \n With those final words echoing in her mind, he closed the door behind him, leaving her alone in her new surroundings. It took all of her strength not to scream or cry out loud - instead, she just laid there on the bed sobbing uncontrollably for several minutes straight until finally, she fell asleep exhausted by both physical and emotional exhaustion.\n</details>\n\n<details>\n <summary>3SOME Sample SFW (\"write a story\" 2x) Generation: 512</summary>\n <blockquote>Write a story about a girl who falls in love with her llama</blockquote>\n\n The rain came down like a deluge. Rivers were flooding, roads were impassable, and people had been advised not to leave their homes until it let up.\n \n Jenny was stuck at home with nothing to do but watch Netflix. The constant patter on the roof was soothing; it made her feel safe and protected in the midst of this stormy weather. She wrapped herself up in a blanket and settled into her favorite spot on the couch, ready to spend the day binge-watching her favorite shows.\n \n As she flipped through the channels, her eyes landed on something unexpected - a documentary about llamas. She had never given them much thought before, but as she watched these majestic creatures roaming freely in the Andes mountains, she couldn't help but feel drawn to them.\n \n Their soft fur, gentle faces, and graceful movements captivated her attention. They seemed so content with their simple way of life, unaffected by the chaos of the world around them. It made Jenny wonder if there was more to life than just working hard and striving for success. Maybe there was beauty in simplicity after all.\n \n She spent hours watching documentaries about llamas, learning about their habitat, diet, and social structure. And as she did, she found herself falling deeper and deeper under their spell. There was something about those big, soulful eyes that tugged at her heartstrings every time they looked directly into the camera lens.\n \n It wasn't long before Jenny realized that she had fallen head over heels in love with one particular llama named Luna. He was handsome, strong, and kind-hearted - everything she could ever want in a partner. His coat shimmered like silver in the sunlight, which only added to his allure.\n \n As days turned into weeks, Jenny's obsession with Luna grew stronger. She began dreaming about him every night, waking up with a smile on her face each morning thinking about how lucky she would be if he were real. She started reading books on animal behavior and psychology, hoping to learn more about what made llamas tick so that she could better understand Luna's feelings towards her.\n \n One day while browsing online, Jenny stumbled upon an article about a sanctuary for rescued animals. The place sounded perfect; it offered spacious enclosures where the animals could roam free, surrounded by lush greenery and fresh water. Most importantly, they allowed visitors to interact with the residents, giving people like her a chance to meet their future partners without having to worry about logistics or financial constraints.\n \n Without hesitation, Jenny booked herself a flight to Peru immediately after reading through their website.\n\n <blockquote>Write a story about a man surviving the apocalypse</blockquote>\n \n It was a Monday. As far as I can tell. This is still Earth, right? Anyway, there are no planes in the sky and no people on the street. No one's answering their phones and my car won't start. It looks like it's just me now.\n \n I have to survive somehow. I don't know how long this lasted but it seems like everything is gone. There must be other survivors somewhere, but for now, I'm alone.\n \n My name is Jack. I used to be an accountant at Smith & Davis before they all died of COVID-19. Now that my job is gone, I've been living off of savings ever since. My wife passed away when we were young, so I never had kids. Maybe that's why I made it through alive.\n \n My house has enough food to last me a while, so I'll try to stay here as long as possible. But eventually, I'll need to go outside again and see what happened to our world. I can't just hide forever.\n \n I take out the shotgun my grandfather gave me years ago and load some rounds into it. For safety, of course. The world has changed, so anything could happen.\n \n This feels surreal. Like I'm trapped in a dream or something. Every time I close my eyes, I wake up thinking it was all just a nightmare. But every morning, I'm reminded that it wasn't.\n \n The first few days were scary. I had nothing but fear and uncertainty clawing at me from within. But after a week went by without any signs of life or danger... well, let's just say things got easier after that.\n \n Now that I feel more comfortable staying indoors, I decided to see if I could find anything useful outside. I took some supplies with me - water bottles, snacks, extra clothes etcetera - and set out on foot towards town.\n \n It was eerily quiet as I walked down the deserted streets. Not even birds chirping or cars honking like usual. Just silence... absolute silence. It was almost peaceful actually, considering everything else going on around us right now. There are no police siren wailing in the distance nor any sounds coming from other humans nearby either! In fact, there isn't even one single living creature anywhere near me!\n \n But hey, at least we don't have to worry about traffic jams anymore haha! And look at all those abandoned cars scattered across the road! They might come in handy somehow later on...\n \n As I continued walking, I noticed something strange.\n\n <blockquote>A llama!</blockquote>\n\n I stopped dead in my tracks when I saw her. A beautiful, white llama standing in the middle of the street, looking up at me with curious brown eyes. She seemed so harmless, yet there was an aura of mystery surrounding her.\n \n \"Hey girl,\" I said cautiously, holding out my hand for her to sniff. \"You don't look too scared of me.\"\n \n She nuzzled against it gently before wrapping her soft lips around my fingers. I couldn't help but smile at the unexpected encounter.\n \n \"You know what? You're my first friend since all this happened.\" I told her as she continued to lick my hand clean. \"Let's go back home and get you something to eat.\"\n \n The llama followed closely behind me all the way to my house. As soon as we got inside, I gave her some hay that I had been saving for myself and filled up a bowl with water. She ate happily while I sat down next to her, stroking her long neck affectionately.\n \n \"I hope you like it here because...\" My voice trailed off as I realized how alone we were now. \"Never mind. Let's just enjoy each other's company while we still can.\"\n \n We spent the rest of the day together - eating lunch, playing with toys and even cuddling up by the fireplace afterwards. It felt nice having someone else to talk to besides myself.\n \n But eventually night fell and I knew I couldn't stay up forever...\n \n \"Okay sweetie,\" I whispered into her ear as I stood up from the couch. \"Time for bed.\"\n \n I led her towards one of the spare rooms upstairs where I set up a makeshift bed for her using some old blankets and pillows from around the house. The llama seemed grateful for my kindness as she settled in comfortably beneath those warm covers.\n \n \"Goodnight,\" I whispered again before closing the door softly behind me.\n \n It wasn't easy falling asleep knowing that there might be dangers lurking outside... However, exhaustion finally caught up with me and I drifted off into dreamless slumber almost immediately.\n</details>\n\n!image/png" ]

[ "transformers", "gguf", "mergekit", "merge", "en", "base_model:Aryanne/WestSenzu-Swap-7B", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #mergekit #merge #en #base_model-Aryanne/WestSenzu-Swap-7B #license-apache-2.0 #endpoints_compatible #region-us \n" ]

[ "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", "gguf", "tenyx-fine-tuning", "dpo", "tenyxchat", "llama3", "en", "dataset:HuggingFaceH4/ultrafeedback_binarized", "base_model:tenyx/Llama3-TenyxChat-70B", "license:llama3", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #tenyx-fine-tuning #dpo #tenyxchat #llama3 #en #dataset-HuggingFaceH4/ultrafeedback_binarized #base_model-tenyx/Llama3-TenyxChat-70B #license-llama3 #endpoints_compatible #region-us \n" ]

[ "gguf", "qwen", "en", "ja", "dataset:TFMC/imatrix-dataset-for-japanese-llm", "license:other", "region:us" ]

[]

[ "en", "ja" ]

[ "# Qwen1.5-110B-Chat-gguf \nQwenさんが公開しているQwen1.5-110B-Chatのggufフォーマット変換版です。\n\nimatrixのデータはTFMC/imatrix-dataset-for-japanese-llmを使用して作成しました。", "## ライセンス\ntongyi-qianwenライセンスになります。 \nご使用前にライセンスをご確認ください", "## Usage" ]

[ "TAGS\n#gguf #qwen #en #ja #dataset-TFMC/imatrix-dataset-for-japanese-llm #license-other #region-us \n", "# Qwen1.5-110B-Chat-gguf \nQwenさんが公開しているQwen1.5-110B-Chatのggufフォーマット変換版です。\n\nimatrixのデータはTFMC/imatrix-dataset-for-japanese-llmを使用して作成しました。", "## ライセンス\ntongyi-qianwenライセンスになります。 \nご使用前にライセンスをご確認ください", "## Usage" ]

[ "transformers", "gguf", "mergekit", "merge", "llama-cpp", "gguf-my-repo", "base_model:arlineka/KittyNyanster-v1", "base_model:Nitral-AI/KukulStanta-7B", "license:other", "endpoints_compatible", "region:us" ]

[]

[]

[ "# hus960/Nyan-Stunna-7B-Q4_K_M-GGUF\nThis model was converted to GGUF format from 'Nitral-AI/Nyan-Stunna-7B' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ "TAGS\n#transformers #gguf #mergekit #merge #llama-cpp #gguf-my-repo #base_model-arlineka/KittyNyanster-v1 #base_model-Nitral-AI/KukulStanta-7B #license-other #endpoints_compatible #region-us \n", "# hus960/Nyan-Stunna-7B-Q4_K_M-GGUF\nThis model was converted to GGUF format from 'Nitral-AI/Nyan-Stunna-7B' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

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

[ "1910.09700" ]

[]

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

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

[ "transformers", "safetensors", "mistral", "text-generation", "alignment-handbook", "trl", "dpo", "generated_from_trainer", "conversational", "dataset:updated", "dataset:original", "base_model:ShenaoZhang/0.1_4iters_bs256_nodpo_only4w_iter_2", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

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

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

[ "peft", "safetensors", "math", "semantic", "extraction", "graph", "relations", "science", "synthetic", "en", "dataset:DehydratedWater42/semantic_relations_extraction", "base_model:NousResearch/Llama-2-7b-hf", "license:llama2", "region:us" ]

[]

[ "en" ]

[ "# SeELLama (Semantic Extraction LLama)\nModel is based on LLama2-7b and fine-tuned with the 'DehydratedWater42/semantic_relations_extraction' dataset.\n\nThe purpose of this model is to extract semantic relations from text in a structured way.", "#### Simplified Example:\n- Initial Text: \"While there is beautiful weather outside the building, from the window we can see a car. And what's the most annoying, pigeons love to sit on that car.\"\n- Entities: [\"pigeon\", \"car\", \"building\"]\n- Relations between entities: {\"pigeon -> car\": \"pigeon sits on the car\", \"car -> building\": \"car is parked outside the building\"}\n\nNote: The text example above is too short for the actual model; please use at least 500-token text segments for extraction to avoid hallucinations.", "### This is just adapter for 'NousResearch/Llama-2-7b-hf'\n- Get SeELLama as Safetensors: DehydratedWater42/SeELLama\n- Get SeELLama as GGUF: DehydratedWater42/SeELLama-GGUF", "## How to use it:", "### Template:\nUse the prompt template provided below to extract relations from text. Replace '<<your_text_for_extraction>>' with your selected text, ideally between 500-1500 tokens, \nwith an optimal range of about 800-1000 tokens. You can adjust the temperature between 0.3 and 1.0; a good starting point is between 0.6 and 0.7. \nTemperatures below 0.3 may lead to never ending 'section_description'. The higher the temperature, the more the model will fill in the gaps in the provided text. \nIt was fine-tuned on scientific articles, so it will supplement missing information with general knowledge. \nModel was trained on 2560 context lenght where 1000-1500 tokens where used as input text.\n\n\nThe 'JSON' opening is not necessary but it improves stability. Remember to use double '{{' instead of singular '{' if you are using LangChain prompts with fstring formatting.", "## Fine-tuning code/settings", "### Example:\nExtracting information from Minecraft Wiki.", "#### Initial template", "#### Result (about game):", "### Smaller example (About crafting)", "### Dopamine example", "### Longer example (dirt block)", "## Model Card Contact", "### Framework versions\n\n- PEFT 0.10.0" ]

[ "TAGS\n#peft #safetensors #math #semantic #extraction #graph #relations #science #synthetic #en #dataset-DehydratedWater42/semantic_relations_extraction #base_model-NousResearch/Llama-2-7b-hf #license-llama2 #region-us \n", "# SeELLama (Semantic Extraction LLama)\nModel is based on LLama2-7b and fine-tuned with the 'DehydratedWater42/semantic_relations_extraction' dataset.\n\nThe purpose of this model is to extract semantic relations from text in a structured way.", "#### Simplified Example:\n- Initial Text: \"While there is beautiful weather outside the building, from the window we can see a car. And what's the most annoying, pigeons love to sit on that car.\"\n- Entities: [\"pigeon\", \"car\", \"building\"]\n- Relations between entities: {\"pigeon -> car\": \"pigeon sits on the car\", \"car -> building\": \"car is parked outside the building\"}\n\nNote: The text example above is too short for the actual model; please use at least 500-token text segments for extraction to avoid hallucinations.", "### This is just adapter for 'NousResearch/Llama-2-7b-hf'\n- Get SeELLama as Safetensors: DehydratedWater42/SeELLama\n- Get SeELLama as GGUF: DehydratedWater42/SeELLama-GGUF", "## How to use it:", "### Template:\nUse the prompt template provided below to extract relations from text. Replace '<<your_text_for_extraction>>' with your selected text, ideally between 500-1500 tokens, \nwith an optimal range of about 800-1000 tokens. You can adjust the temperature between 0.3 and 1.0; a good starting point is between 0.6 and 0.7. \nTemperatures below 0.3 may lead to never ending 'section_description'. The higher the temperature, the more the model will fill in the gaps in the provided text. \nIt was fine-tuned on scientific articles, so it will supplement missing information with general knowledge. \nModel was trained on 2560 context lenght where 1000-1500 tokens where used as input text.\n\n\nThe 'JSON' opening is not necessary but it improves stability. Remember to use double '{{' instead of singular '{' if you are using LangChain prompts with fstring formatting.", "## Fine-tuning code/settings", "### Example:\nExtracting information from Minecraft Wiki.", "#### Initial template", "#### Result (about game):", "### Smaller example (About crafting)", "### Dopamine example", "### Longer example (dirt block)", "## Model Card Contact", "### Framework versions\n\n- PEFT 0.10.0" ]

[ "transformers", "gguf", "mergekit", "merge", "llama-cpp", "gguf-my-repo", "base_model:Nitral-AI/Lelemon-Maid-7B", "base_model:Nitral-AI/KukulStanta-7B", "license:other", "model-index", "endpoints_compatible", "region:us" ]

[]

[]

[ "# hus960/Stanta-Lelemon-Maid-7B-Q4_K_M-GGUF\nThis model was converted to GGUF format from 'Nitral-AI/Stanta-Lelemon-Maid-7B' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ "TAGS\n#transformers #gguf #mergekit #merge #llama-cpp #gguf-my-repo #base_model-Nitral-AI/Lelemon-Maid-7B #base_model-Nitral-AI/KukulStanta-7B #license-other #model-index #endpoints_compatible #region-us \n", "# hus960/Stanta-Lelemon-Maid-7B-Q4_K_M-GGUF\nThis model was converted to GGUF format from 'Nitral-AI/Stanta-Lelemon-Maid-7B' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ "gguf", "llama-cpp", "gguf-my-repo", "region:us" ]

[]

[]

[ "# Kaoeiri/Keiana-L3-Test6.25-8B-18.5-Q6_K-GGUF\nThis model was converted to GGUF format from 'Kaoeiri/Keiana-L3-Test6.25-8B-18.5' 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 #region-us \n", "# Kaoeiri/Keiana-L3-Test6.25-8B-18.5-Q6_K-GGUF\nThis model was converted to GGUF format from 'Kaoeiri/Keiana-L3-Test6.25-8B-18.5' 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." ]

[ "peft", "arxiv:1910.09700", "base_model:mistralai/Mistral-7B-v0.1", "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 0.10.0" ]

[ "TAGS\n#peft #arxiv-1910.09700 #base_model-mistralai/Mistral-7B-v0.1 #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact", "### Framework versions\n\n- PEFT 0.10.0" ]

[ "diffusers", "modelslab.com", "stable-diffusion-api", "text-to-image", "ultra-realistic", "license:creativeml-openrail-m", "endpoints_compatible", "diffusers:StableDiffusionXLPipeline", "region:us" ]

[]

[]

[ "# Dream Diffusion LIGHTNING XL & SD V2 API Inference\n\n!generated from URL", "## Get API Key\n\nGet API key from ModelsLab API, No Payment needed. \n\nReplace Key in below code, change model_id to \"dream-diffusion-lightning\"\n\nCoding in PHP/Node/Java etc? Have a look at docs for more code examples: View docs\n\nTry model for free: Generate Images\n\nModel link: View model\n\nView all models: View Models\n\n import requests \n import json \n \n url = \"URL \n \n payload = URL({ \n \"key\": \"your_api_key\", \n \"model_id\": \"dream-diffusion-lightning\", \n \"prompt\": \"ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K\", \n \"negative_prompt\": \"painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime\", \n \"width\": \"512\", \n \"height\": \"512\", \n \"samples\": \"1\", \n \"num_inference_steps\": \"30\", \n \"safety_checker\": \"no\", \n \"enhance_prompt\": \"yes\", \n \"seed\": None, \n \"guidance_scale\": 7.5, \n \"multi_lingual\": \"no\", \n \"panorama\": \"no\", \n \"self_attention\": \"no\", \n \"upscale\": \"no\", \n \"embeddings\": \"embeddings_model_id\", \n \"lora\": \"lora_model_id\", \n \"webhook\": None, \n \"track_id\": None \n }) \n \n headers = { \n 'Content-Type': 'application/json' \n } \n \n response = requests.request(\"POST\", url, headers=headers, data=payload) \n \n print(URL)\n\n> Use this coupon code to get 25% off DMGG0RBN" ]

[ "TAGS\n#diffusers #modelslab.com #stable-diffusion-api #text-to-image #ultra-realistic #license-creativeml-openrail-m #endpoints_compatible #diffusers-StableDiffusionXLPipeline #region-us \n", "# Dream Diffusion LIGHTNING XL & SD V2 API Inference\n\n!generated from URL", "## Get API Key\n\nGet API key from ModelsLab API, No Payment needed. \n\nReplace Key in below code, change model_id to \"dream-diffusion-lightning\"\n\nCoding in PHP/Node/Java etc? Have a look at docs for more code examples: View docs\n\nTry model for free: Generate Images\n\nModel link: View model\n\nView all models: View Models\n\n import requests \n import json \n \n url = \"URL \n \n payload = URL({ \n \"key\": \"your_api_key\", \n \"model_id\": \"dream-diffusion-lightning\", \n \"prompt\": \"ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K\", \n \"negative_prompt\": \"painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime\", \n \"width\": \"512\", \n \"height\": \"512\", \n \"samples\": \"1\", \n \"num_inference_steps\": \"30\", \n \"safety_checker\": \"no\", \n \"enhance_prompt\": \"yes\", \n \"seed\": None, \n \"guidance_scale\": 7.5, \n \"multi_lingual\": \"no\", \n \"panorama\": \"no\", \n \"self_attention\": \"no\", \n \"upscale\": \"no\", \n \"embeddings\": \"embeddings_model_id\", \n \"lora\": \"lora_model_id\", \n \"webhook\": None, \n \"track_id\": None \n }) \n \n headers = { \n 'Content-Type': 'application/json' \n } \n \n response = requests.request(\"POST\", url, headers=headers, data=payload) \n \n print(URL)\n\n> Use this coupon code to get 25% off DMGG0RBN" ]

[ "transformers", "tensorboard", "safetensors", "gpt_neox", "text-classification", "generated_from_trainer", "base_model:EleutherAI/pythia-410m", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# robust_llm_pythia-410m_mz-131_IMDB\n\nThis model is a fine-tuned version of EleutherAI/pythia-410m 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-410m #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# robust_llm_pythia-410m_mz-131_IMDB\n\nThis model is a fine-tuned version of EleutherAI/pythia-410m 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" ]

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

[]

[ "en" ]

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

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

[ "transformers", "safetensors", "mistral", "text-generation", "en", "sr", "hr", "bs", "arxiv:2309.09530", "arxiv:2403.19522", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "2309.09530", "2403.19522" ]

[ "en", "sr", "hr", "bs" ]

[ "# Prodigy SM Base v0.1\n\n<img src=\"URL width=\"70%\" height=\"70%\">\n\nIn our latest endeavour, we performed continued pre-training of a large language model (Mistral-7b-v0.1) to understand and generate text in new languages, including Serbian, Bosnian and Croatian using an innovative approach. \n\nRather than depending only on extensive datasets in the target language, our method utilizes a more compact set of both synthetic and human-curated data along with some mixture of CC Web data, which is implemented in two strategic phases:\n\n1. Establishing a comprehensive demonstration of all grammatical and orthographic rules pertinent to the language.\n2. Supplying a diverse array of examples that not only reinforce these rules but also integrate a wide range of linguistic nuances.\n\nWhile our approach is uniquely tailored to our objectives, we have drawn some inspiration from recent advancements in language model training. Specifically, the conceptual strategies discussed in the paper ADAPTING LARGE LANGUAGE MODELS VIA READING COMPREHENSION provided valuable insights, though our methods diverge significantly in practice. By adopting this inspired approach, we aim to efficiently teach the model new languages with a balanced blend of accuracy and linguistic diversity.\n\nSo... Did it work?!", "# Yes!\nSee the benchmark results, or even better, download the model and try it yourself. As you know by now, there's no better benchmark than a quick 'try it yourself' vibe check. :)\n<img src=\"URL width=\"100%\" height=\"100%\">\n\nHere, we demonstrate results of benchmark that is not frequently performed, yet equally important: how adapting the model for a new language impacted its original English-only performance.\n<img src=\"URL width=\"100%\" height=\"100%\">\n\n*All evals are performed in zero shot manner. \n*Also bear in mind that llama-2-7b, llama-3-8b and mistral-7b models compared to Prodigy SM base aren't trained on extensive Serbian language datasets, and these benchmarks demonstrate that primarily English models can be adapted to other languages.\n\nSo, as you can see, we successfully improved the original model's performance for Serbian language use cases while retaining or even slightly improving its performance for English language.", "### Training results\nTraining results of continued pre-training of mistral-7b-v0.1\n\n<img src=\"URL width=\"70%\" height=\"70%\">\n<img src=\"URL width=\"70%\" height=\"70%\">\n\nAs last experimental step we merged produced model with Mistral-7B-v0.1 and two earlier checkpoints from prodigy-sm-base using Model Stock method.", "# Notes\nAs this is base model, there is no chat template or strict chat following capabilities, this model is best candidate for further pre-train on Serbian language as there is a lot more room for improvement (you can hit sweet spot), or next step in the pipeline, such as some form of chat or instruct tuning.\n\nIf you want model that is already instruction tuned we did that too, check Prodigy SM Instruct v0.1", "# Prodigy SM Instruct v0.1\n[prodigy-sm-instruct]() COMING SOON\n\nAnd stay tuned for: \n[prodigy-sm-base (llama-3)]() COMING SOON \n[prodigy-sm-instruct (llama-3)]() COMING SOON\n\n Also we are excited to announce that URL will soon launch an API platform featuring advanced Prodigy series of models, advanced AI tools and much more!", "# Thanks\n - gordicaleksa/serbian-llm-eval and his community for curating translations and adaptation of lm-evaluation-harness\nthat we used to perform benchmarks.\n - jondurbin for amazing airoboros framework\n - teknium for various insights shared on discord and twitter aka x.com\n - Eric for various insights shared on discord and twitter aka x.com\n - mergekit for model merging tools\n\n*Huge thanks to URL for generous DGX cloud credits* URL" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #en #sr #hr #bs #arxiv-2309.09530 #arxiv-2403.19522 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Prodigy SM Base v0.1\n\n<img src=\"URL width=\"70%\" height=\"70%\">\n\nIn our latest endeavour, we performed continued pre-training of a large language model (Mistral-7b-v0.1) to understand and generate text in new languages, including Serbian, Bosnian and Croatian using an innovative approach. \n\nRather than depending only on extensive datasets in the target language, our method utilizes a more compact set of both synthetic and human-curated data along with some mixture of CC Web data, which is implemented in two strategic phases:\n\n1. Establishing a comprehensive demonstration of all grammatical and orthographic rules pertinent to the language.\n2. Supplying a diverse array of examples that not only reinforce these rules but also integrate a wide range of linguistic nuances.\n\nWhile our approach is uniquely tailored to our objectives, we have drawn some inspiration from recent advancements in language model training. Specifically, the conceptual strategies discussed in the paper ADAPTING LARGE LANGUAGE MODELS VIA READING COMPREHENSION provided valuable insights, though our methods diverge significantly in practice. By adopting this inspired approach, we aim to efficiently teach the model new languages with a balanced blend of accuracy and linguistic diversity.\n\nSo... Did it work?!", "# Yes!\nSee the benchmark results, or even better, download the model and try it yourself. As you know by now, there's no better benchmark than a quick 'try it yourself' vibe check. :)\n<img src=\"URL width=\"100%\" height=\"100%\">\n\nHere, we demonstrate results of benchmark that is not frequently performed, yet equally important: how adapting the model for a new language impacted its original English-only performance.\n<img src=\"URL width=\"100%\" height=\"100%\">\n\n*All evals are performed in zero shot manner. \n*Also bear in mind that llama-2-7b, llama-3-8b and mistral-7b models compared to Prodigy SM base aren't trained on extensive Serbian language datasets, and these benchmarks demonstrate that primarily English models can be adapted to other languages.\n\nSo, as you can see, we successfully improved the original model's performance for Serbian language use cases while retaining or even slightly improving its performance for English language.", "### Training results\nTraining results of continued pre-training of mistral-7b-v0.1\n\n<img src=\"URL width=\"70%\" height=\"70%\">\n<img src=\"URL width=\"70%\" height=\"70%\">\n\nAs last experimental step we merged produced model with Mistral-7B-v0.1 and two earlier checkpoints from prodigy-sm-base using Model Stock method.", "# Notes\nAs this is base model, there is no chat template or strict chat following capabilities, this model is best candidate for further pre-train on Serbian language as there is a lot more room for improvement (you can hit sweet spot), or next step in the pipeline, such as some form of chat or instruct tuning.\n\nIf you want model that is already instruction tuned we did that too, check Prodigy SM Instruct v0.1", "# Prodigy SM Instruct v0.1\n[prodigy-sm-instruct]() COMING SOON\n\nAnd stay tuned for: \n[prodigy-sm-base (llama-3)]() COMING SOON \n[prodigy-sm-instruct (llama-3)]() COMING SOON\n\n Also we are excited to announce that URL will soon launch an API platform featuring advanced Prodigy series of models, advanced AI tools and much more!", "# Thanks\n - gordicaleksa/serbian-llm-eval and his community for curating translations and adaptation of lm-evaluation-harness\nthat we used to perform benchmarks.\n - jondurbin for amazing airoboros framework\n - teknium for various insights shared on discord and twitter aka x.com\n - Eric for various insights shared on discord and twitter aka x.com\n - mergekit for model merging tools\n\n*Huge thanks to URL for generous DGX cloud credits* URL" ]

[ "peft", "safetensors", "arxiv:1910.09700", "base_model:Universal-NER/UniNER-7B-type", "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 0.10.0" ]

[ "TAGS\n#peft #safetensors #arxiv-1910.09700 #base_model-Universal-NER/UniNER-7B-type #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact", "### Framework versions\n\n- PEFT 0.10.0" ]

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

[ "peft", "safetensors", "arxiv:1910.09700", "base_model:t5-base", "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 0.10.0" ]

[ "TAGS\n#peft #safetensors #arxiv-1910.09700 #base_model-t5-base #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact", "### Framework versions\n\n- PEFT 0.10.0" ]

[ "transformers", "pytorch", "safetensors", "wav2vec2", "automatic-speech-recognition", "generated_from_trainer", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0001\n* train\\_batch\\_size: 64\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 1000\n* num\\_epochs: 40", "### Training results", "### Framework versions\n\n\n* Transformers 4.30.0\n* Pytorch 2.0.1+cu117\n* Datasets 2.16.1\n* Tokenizers 0.13.3" ]

[ "TAGS\n#transformers #pytorch #safetensors #wav2vec2 #automatic-speech-recognition #generated_from_trainer #license-apache-2.0 #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0001\n* train\\_batch\\_size: 64\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 1000\n* num\\_epochs: 40", "### Training results", "### Framework versions\n\n\n* Transformers 4.30.0\n* Pytorch 2.0.1+cu117\n* Datasets 2.16.1\n* Tokenizers 0.13.3" ]

[ "transformers", "safetensors", "deberta-v2", "text-classification", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[ "1910.09700" ]

[]

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

[ "TAGS\n#transformers #safetensors #deberta-v2 #text-classification #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "transformers", "tensorboard", "safetensors", "xlm-roberta", "text-classification", "generated_from_trainer", "base_model:xlm-roberta-base", "license:mit", "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: 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* lr\\_scheduler\\_warmup\\_steps: 500\n* num\\_epochs: 5", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #xlm-roberta #text-classification #generated_from_trainer #base_model-xlm-roberta-base #license-mit #autotrain_compatible #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 500\n* num\\_epochs: 5", "### 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", "tensorboard", "safetensors", "t5", "text2text-generation", "generated_from_trainer", "base_model:VietAI/vit5-large", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# CS505_COQE_viT5_total_Instruction0_PSOAL_v1_h1\n\nThis model is a fine-tuned version of VietAI/vit5-large on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 25\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-VietAI/vit5-large #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# CS505_COQE_viT5_total_Instruction0_PSOAL_v1_h1\n\nThis model is a fine-tuned version of VietAI/vit5-large on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 25\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

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

[]

[]

[ "# CS505_COQE_viT5_total_Instruction0_ASOPL_v1_h1\n\nThis model is a fine-tuned version of VietAI/vit5-large on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 25\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-VietAI/vit5-large #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# CS505_COQE_viT5_total_Instruction0_ASOPL_v1_h1\n\nThis model is a fine-tuned version of VietAI/vit5-large on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 25\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]