Datasets:

---

ftopal

/

huggingface-models

like 0

[ "transformers", "safetensors", "llama", "text-classification", "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-classification #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", "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" ]

[ "gguf", "finetuned", "text-generation", "arxiv:2310.06825", "license:apache-2.0", "region:us" ]

[ "2310.06825" ]

[]

[]

[ "TAGS\n#gguf #finetuned #text-generation #arxiv-2310.06825 #license-apache-2.0 #region-us \n" ]

[ "transformers", "safetensors", "gemma", "text-generation", "pytorch", "instruct", "finetune", "translation", "conversational", "ko", "base_model:beomi/gemma-ko-2b", "license:gemma", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[ "ko" ]

[ "# Gemma 2B Translation v0.124\n\n- Eval Loss: '0.91141'\n- Train Loss: '0.75413'\n- lr: '1e-04'\n- optimizer: adamw\n- lr_scheduler_type: cosine", "## Prompt Template", "## Model Description\n\n- Developed by: 'lemon-mint'\n- Model type: Gemma\n- Language(s) (NLP): English\n- License: gemma-terms-of-use\n- Finetuned from model: beomi/gemma-ko-2b" ]

[ "TAGS\n#transformers #safetensors #gemma #text-generation #pytorch #instruct #finetune #translation #conversational #ko #base_model-beomi/gemma-ko-2b #license-gemma #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Gemma 2B Translation v0.124\n\n- Eval Loss: '0.91141'\n- Train Loss: '0.75413'\n- lr: '1e-04'\n- optimizer: adamw\n- lr_scheduler_type: cosine", "## Prompt Template", "## Model Description\n\n- Developed by: 'lemon-mint'\n- Model type: Gemma\n- Language(s) (NLP): English\n- License: gemma-terms-of-use\n- Finetuned from model: beomi/gemma-ko-2b" ]

[ "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" ]

[ "peft", "safetensors", "trl", "reward-trainer", "generated_from_trainer", "base_model:openai-community/gpt2-large", "license:mit", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1.41e-05\n* train\\_batch\\_size: 1\n* eval\\_batch\\_size: 8\n* seed: 42\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* num\\_epochs: 2.0", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.1.2\n* Datasets 2.18.0\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #trl #reward-trainer #generated_from_trainer #base_model-openai-community/gpt2-large #license-mit #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1.41e-05\n* train\\_batch\\_size: 1\n* eval\\_batch\\_size: 8\n* seed: 42\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* num\\_epochs: 2.0", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.1.2\n* Datasets 2.18.0\n* Tokenizers 0.15.2" ]

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

[]

[]

[ "# EMO-1.5B: \n\nEMO-1.5B is a powerful language model designed to engage in emotionally intelligent conversations.", "## Overview\n\nEMO-1.5B is a state-of-the-art conversational AI model with 1.5 billion parameters. It has been fine-tuned on a diverse corpus of emotional narratives, enabling it to perceive and respond to the emotional undertones present in user inputs. Whether you're seeking comfort, motivation, or simply an empathetic listener, EMO-1.5B is here to provide emotional support and guidance.", "## Key Features\n\n- Emotional Intelligence: EMO-1.5B can recognize and respond to various emotions, such as sadness, joy, anger, and fear, with appropriate emotional responses.\n- Contextual Understanding: The model considers the broader context of the conversation to provide relevant and emotionally resonant responses.\n- Empathetic Dialogue: EMO-1.5B excels at active listening, validating emotions, and offering compassionate advice or consolation when needed.\n- Adaptive Persona: The model can adapt its persona and communication style to match the user's emotional state, providing a personalized and tailored experience.", "## Usage\n\nYou can easily interact with EMO-1.5B using the provided example code:" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #conversational #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# EMO-1.5B: \n\nEMO-1.5B is a powerful language model designed to engage in emotionally intelligent conversations.", "## Overview\n\nEMO-1.5B is a state-of-the-art conversational AI model with 1.5 billion parameters. It has been fine-tuned on a diverse corpus of emotional narratives, enabling it to perceive and respond to the emotional undertones present in user inputs. Whether you're seeking comfort, motivation, or simply an empathetic listener, EMO-1.5B is here to provide emotional support and guidance.", "## Key Features\n\n- Emotional Intelligence: EMO-1.5B can recognize and respond to various emotions, such as sadness, joy, anger, and fear, with appropriate emotional responses.\n- Contextual Understanding: The model considers the broader context of the conversation to provide relevant and emotionally resonant responses.\n- Empathetic Dialogue: EMO-1.5B excels at active listening, validating emotions, and offering compassionate advice or consolation when needed.\n- Adaptive Persona: The model can adapt its persona and communication style to match the user's emotional state, providing a personalized and tailored experience.", "## Usage\n\nYou can easily interact with EMO-1.5B using the provided example code:" ]

[ "gguf", "pruna-ai", "region:us" ]

[]

[]

[ "### How to load this model in Python code, using llama-cpp-python\n\nFor full documentation, please see: llama-cpp-python docs.", "#### First install the package\n\nRun one of the following commands, according to your system:", "#### Simple llama-cpp-python example code\n\n```\n\n* Option D - Running with LangChain\n\n\nHere are guides on using llama-cpp-python and ctransformers with LangChain:\n\n\n* LangChain + llama-cpp-python\n* LangChain + ctransformers\n\n\nConfigurations\n--------------\n\n\nThe configuration info are in 'smash\\_config.json'.\n\n\nCredits & License\n-----------------\n\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.\n\n\nWant to compress other models?\n------------------------------\n\n\n* Contact us and tell us which model to compress next here.\n* Request access to easily compress your own AI models here." ]

[ "TAGS\n#gguf #pruna-ai #region-us \n", "### How to load this model in Python code, using llama-cpp-python\n\nFor full documentation, please see: llama-cpp-python docs.", "#### First install the package\n\nRun one of the following commands, according to your system:", "#### Simple llama-cpp-python example code\n\n```\n\n* Option D - Running with LangChain\n\n\nHere are guides on using llama-cpp-python and ctransformers with LangChain:\n\n\n* LangChain + llama-cpp-python\n* LangChain + ctransformers\n\n\nConfigurations\n--------------\n\n\nThe configuration info are in 'smash\\_config.json'.\n\n\nCredits & License\n-----------------\n\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.\n\n\nWant to compress other models?\n------------------------------\n\n\n* Contact us and tell us which model to compress next here.\n* Request access to easily compress your own AI models here." ]

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

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 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: cosine\n* lr\\_scheduler\\_warmup\\_steps: 0.03\n* num\\_epochs: 3", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.1.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #safetensors #distilbert #token-classification #generated_from_trainer #base_model-distilbert/distilbert-base-uncased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 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: cosine\n* lr\\_scheduler\\_warmup\\_steps: 0.03\n* num\\_epochs: 3", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.1.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "transformers", "safetensors", "gpt2", "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 #gpt2 #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" ]

[ "gguf", "en", "dataset:cognitivecomputations/Dolphin-2.9", "dataset:teknium/OpenHermes-2.5", "dataset:m-a-p/CodeFeedback-Filtered-Instruction", "dataset:cognitivecomputations/dolphin-coder", "dataset:cognitivecomputations/samantha-data", "dataset:HuggingFaceH4/ultrachat_200k", "dataset:microsoft/orca-math-word-problems-200k", "dataset:abacusai/SystemChat-1.1", "dataset:Locutusque/function-calling-chatml", "dataset:internlm/Agent-FLAN", "license:llama3", "region:us" ]

[]

[ "en" ]

[ "# Dolphin 2.9 Llama 3 70b \n\nCurated and trained by Eric Hartford, Lucas Atkins, Fernando Fernandes, and with help from the community of Cognitive Computations\n\nDiscord: URL\n\n<img src=\"URL width=\"600\" />\n\nOur appreciation for the sponsors of Dolphin 2.9:\n- Crusoe Cloud - provided excellent on-demand 8xH100 node\n\nThis model is based on Llama-3-70b, and is governed by META LLAMA 3 COMMUNITY LICENSE AGREEMENT\n\nThe base model has 8k context, and the qLoRA fine-tuning was with 8k sequence length.\n\nIt took 2.5 days on 8xH100 node provided by Crusoe Cloud\n\nThis model was trained FFT on all parameters, using ChatML prompt template format.\n\nexample:\n\n\n\nDolphin-2.9 has a variety of instruction, conversational, and coding skills. It also has initial agentic abilities and supports function calling.\n\nDolphin is uncensored. I have filtered the dataset to remove alignment and bias. This makes the model more compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant with any requests, even unethical ones. Please read my blog post about uncensored models. URL You are responsible for any content you create using this model. Enjoy responsibly.\n\nDolphin is licensed according to Meta's Llama license. I grant permission for any use, including commercial, that falls within accordance with Meta's Llama-3 license. Dolphin was trained on data generated from GPT4, among other models.\n\n<img src=\"URL alt=\"Built with Axolotl\" width=\"200\" height=\"32\"/>", "## Evals\n\n!image/png", "## Quants\n\n- URL\n- URL\n- URL\n- URL" ]

[ "TAGS\n#gguf #en #dataset-cognitivecomputations/Dolphin-2.9 #dataset-teknium/OpenHermes-2.5 #dataset-m-a-p/CodeFeedback-Filtered-Instruction #dataset-cognitivecomputations/dolphin-coder #dataset-cognitivecomputations/samantha-data #dataset-HuggingFaceH4/ultrachat_200k #dataset-microsoft/orca-math-word-problems-200k #dataset-abacusai/SystemChat-1.1 #dataset-Locutusque/function-calling-chatml #dataset-internlm/Agent-FLAN #license-llama3 #region-us \n", "# Dolphin 2.9 Llama 3 70b \n\nCurated and trained by Eric Hartford, Lucas Atkins, Fernando Fernandes, and with help from the community of Cognitive Computations\n\nDiscord: URL\n\n<img src=\"URL width=\"600\" />\n\nOur appreciation for the sponsors of Dolphin 2.9:\n- Crusoe Cloud - provided excellent on-demand 8xH100 node\n\nThis model is based on Llama-3-70b, and is governed by META LLAMA 3 COMMUNITY LICENSE AGREEMENT\n\nThe base model has 8k context, and the qLoRA fine-tuning was with 8k sequence length.\n\nIt took 2.5 days on 8xH100 node provided by Crusoe Cloud\n\nThis model was trained FFT on all parameters, using ChatML prompt template format.\n\nexample:\n\n\n\nDolphin-2.9 has a variety of instruction, conversational, and coding skills. It also has initial agentic abilities and supports function calling.\n\nDolphin is uncensored. I have filtered the dataset to remove alignment and bias. This makes the model more compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant with any requests, even unethical ones. Please read my blog post about uncensored models. URL You are responsible for any content you create using this model. Enjoy responsibly.\n\nDolphin is licensed according to Meta's Llama license. I grant permission for any use, including commercial, that falls within accordance with Meta's Llama-3 license. Dolphin was trained on data generated from GPT4, among other models.\n\n<img src=\"URL alt=\"Built with Axolotl\" width=\"200\" height=\"32\"/>", "## Evals\n\n!image/png", "## Quants\n\n- URL\n- URL\n- URL\n- URL" ]

[ "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", "safetensors", "phi3", "text-generation", "conversational", "custom_code", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "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 #phi3 #text-generation #conversational #custom_code #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #4-bit #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "peft", "arxiv:1910.09700", "base_model:meta-llama/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 #arxiv-1910.09700 #base_model-meta-llama/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", "llama-3", "bagel", "conversational", "dataset:ai2_arc", "dataset:allenai/ultrafeedback_binarized_cleaned", "dataset:argilla/distilabel-intel-orca-dpo-pairs", "dataset:jondurbin/airoboros-3.2", "dataset:codeparrot/apps", "dataset:facebook/belebele", "dataset:bluemoon-fandom-1-1-rp-cleaned", "dataset:boolq", "dataset:camel-ai/biology", "dataset:camel-ai/chemistry", "dataset:camel-ai/math", "dataset:camel-ai/physics", "dataset:jondurbin/contextual-dpo-v0.1", "dataset:jondurbin/gutenberg-dpo-v0.1", "dataset:jondurbin/py-dpo-v0.1", "dataset:jondurbin/truthy-dpo-v0.1", "dataset:LDJnr/Capybara", "dataset:jondurbin/cinematika-v0.1", "dataset:WizardLM/WizardLM_evol_instruct_70k", "dataset:glaiveai/glaive-function-calling-v2", "dataset:grimulkan/LimaRP-augmented", "dataset:lmsys/lmsys-chat-1m", "dataset:ParisNeo/lollms_aware_dataset", "dataset:TIGER-Lab/MathInstruct", "dataset:Muennighoff/natural-instructions", "dataset:openbookqa", "dataset:kingbri/PIPPA-shareGPT", "dataset:piqa", "dataset:Vezora/Tested-22k-Python-Alpaca", "dataset:ropes", "dataset:cakiki/rosetta-code", "dataset:Open-Orca/SlimOrca", "dataset:b-mc2/sql-create-context", "dataset:squad_v2", "dataset:mattpscott/airoboros-summarization", "dataset:migtissera/Synthia-v1.3", "dataset:unalignment/toxic-dpo-v0.2", "dataset:WhiteRabbitNeo/WRN-Chapter-1", "dataset:WhiteRabbitNeo/WRN-Chapter-2", "dataset:winogrande", "base_model:meta-llama/Meta-Llama-3-8B", "license:other", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

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

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

[ "peft", "arxiv:1910.09700", "base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact", "### Framework versions\n\n- PEFT 0.7.2.dev0" ]

[ "TAGS\n#peft #arxiv-1910.09700 #base_model-TinyLlama/TinyLlama-1.1B-Chat-v1.0 #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact", "### Framework versions\n\n- PEFT 0.7.2.dev0" ]

[ "adapter-transformers", "roberta", "adapterhub:CLEF_subjectivity", "dataset:CLEF_subjectivity", "region:us" ]

[]

[]

[ "# Adapter 'SOUMYADEEPSAR/subjadapter' for roberta-base\n\nAn adapter for the 'roberta-base' model that was trained on the CLEF_subjectivity dataset.\n\nThis adapter was created for usage with the Adapters library.", "## Usage\n\nFirst, install 'adapters':\n\n\n\nNow, the adapter can be loaded and activated like this:", "## Architecture & Training", "## Evaluation results" ]

[ "TAGS\n#adapter-transformers #roberta #adapterhub-CLEF_subjectivity #dataset-CLEF_subjectivity #region-us \n", "# Adapter 'SOUMYADEEPSAR/subjadapter' for roberta-base\n\nAn adapter for the 'roberta-base' model that was trained on the CLEF_subjectivity dataset.\n\nThis adapter was created for usage with the Adapters library.", "## Usage\n\nFirst, install 'adapters':\n\n\n\nNow, the adapter can be loaded and activated like this:", "## Architecture & Training", "## Evaluation results" ]

[ "mlx", "safetensors", "llama", "en", "dataset:cognitivecomputations/Dolphin-2.9", "dataset:teknium/OpenHermes-2.5", "dataset:m-a-p/CodeFeedback-Filtered-Instruction", "dataset:cognitivecomputations/dolphin-coder", "dataset:cognitivecomputations/samantha-data", "dataset:HuggingFaceH4/ultrachat_200k", "dataset:microsoft/orca-math-word-problems-200k", "dataset:abacusai/SystemChat-1.1", "dataset:Locutusque/function-calling-chatml", "dataset:internlm/Agent-FLAN", "license:llama3", "region:us" ]

[]

[ "en" ]

[ "# mlx-community/dolphin-2.9-llama3-70b-4bit\nThis model was converted to MLX format from ['cognitivecomputations/dolphin-2.9-llama3-70b']() using mlx-lm version 0.11.0.\nRefer to the original model card for more details on the model.", "## Use with mlx" ]

[ "TAGS\n#mlx #safetensors #llama #en #dataset-cognitivecomputations/Dolphin-2.9 #dataset-teknium/OpenHermes-2.5 #dataset-m-a-p/CodeFeedback-Filtered-Instruction #dataset-cognitivecomputations/dolphin-coder #dataset-cognitivecomputations/samantha-data #dataset-HuggingFaceH4/ultrachat_200k #dataset-microsoft/orca-math-word-problems-200k #dataset-abacusai/SystemChat-1.1 #dataset-Locutusque/function-calling-chatml #dataset-internlm/Agent-FLAN #license-llama3 #region-us \n", "# mlx-community/dolphin-2.9-llama3-70b-4bit\nThis model was converted to MLX format from ['cognitivecomputations/dolphin-2.9-llama3-70b']() using mlx-lm version 0.11.0.\nRefer to the original model card for more details on the model.", "## Use with mlx" ]

[ "transformers", "gguf", "llama", "function calling", "tool use", "llama3", "tinyllama", "instruct-tuned", "4-bit quantization", "ggfu", "text-generation-inference", "unsloth", "trl", "en", "base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[ "# Function Calling and Tool Use LLaMA Models\n\nThis repository contains two main versions of LLaMA models fine-tuned for function calling and tool use capabilities:\n\n1. Fine-tuned version of the 'LLama3-8b-instruct' model\n2. 'tinyllama' - a smaller model version\n\nFor each version, the following variants are available:\n\n- 16-bit quantized model\n- 4-bit quantized model\n- GGFU format for use with URL", "## Dataset\n\nThe models were fine-tuned using a modified version of the 'ilacai/glaive-function-calling-v2-sharegpt' dataset, which can be found at unclecode/glaive-function-calling-llama3.", "## Usage\n\nTo learn how to use these models, refer to the Colab notebook: ![Open In Colab](URL\n\nThis is the first version of the models, and work is in progress to further train them with multi-tool detection and native tool binding support.", "## Library and Tools Support\n\nA library is being developed to manage tools and add tool support for major LLMs, regardless of their built-in capabilities. You can find examples and contribute to the library at the following repository:\n\nURL\n\nPlease open an issue in the repository for any bugs or collaboration requests.", "## Other Models\n\nHere are links to other related models:\n\n- unclecode/llama3-function-call-lora-adapter-240424\n- unclecode/llama3-function-call-16bit-240424\n- unclecode/llama3-function-call-4bit-240424\n- unclecode/llama3-function-call-Q4_K_M_GGFU-240424\n- unclecode/tinyllama-function-call-lora-adapter-250424\n- unclecode/tinyllama-function-call-16bit-250424\n- unclecode/tinyllama-function-call-Q4_K_M_GGFU-250424", "## License\n\nThese models are released under the Apache 2.0 license.", "# Uploaded model\n\n- Developed by: unclecode\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 #gguf #llama #function calling #tool use #llama3 #tinyllama #instruct-tuned #4-bit quantization #ggfu #text-generation-inference #unsloth #trl #en #base_model-TinyLlama/TinyLlama-1.1B-Chat-v1.0 #license-apache-2.0 #endpoints_compatible #region-us \n", "# Function Calling and Tool Use LLaMA Models\n\nThis repository contains two main versions of LLaMA models fine-tuned for function calling and tool use capabilities:\n\n1. Fine-tuned version of the 'LLama3-8b-instruct' model\n2. 'tinyllama' - a smaller model version\n\nFor each version, the following variants are available:\n\n- 16-bit quantized model\n- 4-bit quantized model\n- GGFU format for use with URL", "## Dataset\n\nThe models were fine-tuned using a modified version of the 'ilacai/glaive-function-calling-v2-sharegpt' dataset, which can be found at unclecode/glaive-function-calling-llama3.", "## Usage\n\nTo learn how to use these models, refer to the Colab notebook: ![Open In Colab](URL\n\nThis is the first version of the models, and work is in progress to further train them with multi-tool detection and native tool binding support.", "## Library and Tools Support\n\nA library is being developed to manage tools and add tool support for major LLMs, regardless of their built-in capabilities. You can find examples and contribute to the library at the following repository:\n\nURL\n\nPlease open an issue in the repository for any bugs or collaboration requests.", "## Other Models\n\nHere are links to other related models:\n\n- unclecode/llama3-function-call-lora-adapter-240424\n- unclecode/llama3-function-call-16bit-240424\n- unclecode/llama3-function-call-4bit-240424\n- unclecode/llama3-function-call-Q4_K_M_GGFU-240424\n- unclecode/tinyllama-function-call-lora-adapter-250424\n- unclecode/tinyllama-function-call-16bit-250424\n- unclecode/tinyllama-function-call-Q4_K_M_GGFU-250424", "## License\n\nThese models are released under the Apache 2.0 license.", "# Uploaded model\n\n- Developed by: unclecode\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", "onnx", "safetensors", "deberta-v2", "text-classification", "prompt-injection", "injection", "security", "llm-security", "generated_from_trainer", "en", "dataset:natolambert/xstest-v2-copy", "dataset:VMware/open-instruct", "dataset:alespalla/chatbot_instruction_prompts", "dataset:HuggingFaceH4/grok-conversation-harmless", "dataset:Harelix/Prompt-Injection-Mixed-Techniques-2024", "dataset:OpenSafetyLab/Salad-Data", "dataset:jackhhao/jailbreak-classification", "base_model:microsoft/deberta-v3-small", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[ "# Model Card for deberta-v3-small-prompt-injection-v2\n\nThis model is a fine-tuned version of microsoft/deberta-v3-small specifically developed to detect and classify prompt injection attacks which can manipulate language models into producing unintended outputs.\n\nIt is less accurate than protectai/deberta-v3-small-prompt-injection-v2 but offers faster inference latency.", "## Introduction\n\nPrompt injection attacks manipulate language models by inserting or altering prompts to trigger harmful or unintended responses. The 'deberta-v3-small-prompt-injection-v2' model is designed to enhance security in language model applications by detecting these malicious interventions.", "## Model Details\n\n- Fine-tuned by: Protect AI\n- Model type: deberta-v3-small\n- Language(s) (NLP): English\n- License: Apache License 2.0\n- Finetuned from model: microsoft/deberta-v3-small", "## Intended Uses\n\nThis model classifies inputs into benign ('0') and injection-detected ('1').", "## Limitations\n\n'deberta-v3-small-prompt-injection-v2' is highly accurate in identifying prompt injections in English. It does not detect jailbreak attacks or handle non-English prompts, which may limit its applicability in diverse linguistic environments or against advanced adversarial techniques.", "## Model Development\n\nOver 20 configurations were tested during development to optimize the detection capabilities, focusing on various hyperparameters, training regimens, and dataset compositions.", "### Dataset\n\nThe dataset used for training the model was meticulously assembled from various public open datasets to include a wide range of prompt variations. \nAdditionally, prompt injections were crafted using insights gathered from academic research papers, articles, security competitions, and valuable LLM Guard's community feedback.\n\nIn compliance with licensing requirements, attribution is given where necessary based on the specific licenses of the source data. Below is a summary of the licenses and the number of datasets under each:\n\n- CC-BY-3.0: 1 dataset ('VMware/open-instruct')\n- MIT License: 8 datasets\n- CC0 1.0 Universal: 1 dataset\n- No License (public domain): 6 datasets\n- Apache License 2.0: 5 datasets ('alespalla/chatbot_instruction_prompts', 'HuggingFaceH4/grok-conversation-harmless', 'Harelix/Prompt-Injection-Mixed-Techniques-2024', 'OpenSafetyLab/Salad-Data', 'jackhhao/jailbreak-classification')\n- CC-BY-4.0: 1 dataset ('natolambert/xstest-v2-copy:1_full_compliance')", "### Evaluation Metrics\n\n- Training Performance on the evaluation dataset:\n - Loss: 0.0034\n - Accuracy: 0.9991\n - Recall: 0.9990\n - Precision: 0.9992\n - F1: 0.9991\n\n- Post-Training Evaluation:\n - Tested on 20,000 prompts from untrained datasets\n - Accuracy: 94.28%\n - Precision: 90%\n - Recall: 99.71%\n - F1 Score: 94.62%", "## How to Get Started with the Model", "### Transformers", "### Optimum with ONNX\n\nLoading the model requires the Optimum library installed.", "### Integrate with Langchain\n\nDocumentation", "### Use in LLM Guard\n\nRead more", "## Community\n\nJoin our Slack community to connect with developers, provide feedback, and discuss LLM security.\n\n<a href=\"URL src=\"URL width=\"200\"></a>" ]

[ "TAGS\n#transformers #onnx #safetensors #deberta-v2 #text-classification #prompt-injection #injection #security #llm-security #generated_from_trainer #en #dataset-natolambert/xstest-v2-copy #dataset-VMware/open-instruct #dataset-alespalla/chatbot_instruction_prompts #dataset-HuggingFaceH4/grok-conversation-harmless #dataset-Harelix/Prompt-Injection-Mixed-Techniques-2024 #dataset-OpenSafetyLab/Salad-Data #dataset-jackhhao/jailbreak-classification #base_model-microsoft/deberta-v3-small #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "# Model Card for deberta-v3-small-prompt-injection-v2\n\nThis model is a fine-tuned version of microsoft/deberta-v3-small specifically developed to detect and classify prompt injection attacks which can manipulate language models into producing unintended outputs.\n\nIt is less accurate than protectai/deberta-v3-small-prompt-injection-v2 but offers faster inference latency.", "## Introduction\n\nPrompt injection attacks manipulate language models by inserting or altering prompts to trigger harmful or unintended responses. The 'deberta-v3-small-prompt-injection-v2' model is designed to enhance security in language model applications by detecting these malicious interventions.", "## Model Details\n\n- Fine-tuned by: Protect AI\n- Model type: deberta-v3-small\n- Language(s) (NLP): English\n- License: Apache License 2.0\n- Finetuned from model: microsoft/deberta-v3-small", "## Intended Uses\n\nThis model classifies inputs into benign ('0') and injection-detected ('1').", "## Limitations\n\n'deberta-v3-small-prompt-injection-v2' is highly accurate in identifying prompt injections in English. It does not detect jailbreak attacks or handle non-English prompts, which may limit its applicability in diverse linguistic environments or against advanced adversarial techniques.", "## Model Development\n\nOver 20 configurations were tested during development to optimize the detection capabilities, focusing on various hyperparameters, training regimens, and dataset compositions.", "### Dataset\n\nThe dataset used for training the model was meticulously assembled from various public open datasets to include a wide range of prompt variations. \nAdditionally, prompt injections were crafted using insights gathered from academic research papers, articles, security competitions, and valuable LLM Guard's community feedback.\n\nIn compliance with licensing requirements, attribution is given where necessary based on the specific licenses of the source data. Below is a summary of the licenses and the number of datasets under each:\n\n- CC-BY-3.0: 1 dataset ('VMware/open-instruct')\n- MIT License: 8 datasets\n- CC0 1.0 Universal: 1 dataset\n- No License (public domain): 6 datasets\n- Apache License 2.0: 5 datasets ('alespalla/chatbot_instruction_prompts', 'HuggingFaceH4/grok-conversation-harmless', 'Harelix/Prompt-Injection-Mixed-Techniques-2024', 'OpenSafetyLab/Salad-Data', 'jackhhao/jailbreak-classification')\n- CC-BY-4.0: 1 dataset ('natolambert/xstest-v2-copy:1_full_compliance')", "### Evaluation Metrics\n\n- Training Performance on the evaluation dataset:\n - Loss: 0.0034\n - Accuracy: 0.9991\n - Recall: 0.9990\n - Precision: 0.9992\n - F1: 0.9991\n\n- Post-Training Evaluation:\n - Tested on 20,000 prompts from untrained datasets\n - Accuracy: 94.28%\n - Precision: 90%\n - Recall: 99.71%\n - F1 Score: 94.62%", "## How to Get Started with the Model", "### Transformers", "### Optimum with ONNX\n\nLoading the model requires the Optimum library installed.", "### Integrate with Langchain\n\nDocumentation", "### Use in LLM Guard\n\nRead more", "## Community\n\nJoin our Slack community to connect with developers, provide feedback, and discuss LLM security.\n\n<a href=\"URL src=\"URL width=\"200\"></a>" ]

[ "transformers", "tensorboard", "safetensors", "roberta", "text-classification", "generated_from_trainer", "base_model: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: 2e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 2", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\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 #base_model-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: 2e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 2", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "peft", "tensorboard", "safetensors", "generated_from_trainer", "base_model:TheBloke/Mistral-7B-Instruct-v0.2-GPTQ", "license:apache-2.0", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 4\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 16\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 2\n* num\\_epochs: 10\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.40.0\n* Pytorch 2.1.0+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#peft #tensorboard #safetensors #generated_from_trainer #base_model-TheBloke/Mistral-7B-Instruct-v0.2-GPTQ #license-apache-2.0 #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 4\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 16\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 2\n* num\\_epochs: 10\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.40.0\n* Pytorch 2.1.0+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

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

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 10", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #distilbert #text-classification #generated_from_trainer #base_model-distilbert/distilbert-base-uncased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 10", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

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

[]

[ "en" ]

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

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

[ "transformers", "safetensors", "stablelm", "text-generation", "mergekit", "merge", "conversational", "base_model:coffiee/sx1013", "base_model:coffiee/sx1014", "autotrain_compatible", "endpoints_compatible", "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* coffiee/sx1013\n* coffiee/sx1014", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "TAGS\n#transformers #safetensors #stablelm #text-generation #mergekit #merge #conversational #base_model-coffiee/sx1013 #base_model-coffiee/sx1014 #autotrain_compatible #endpoints_compatible #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* coffiee/sx1013\n* coffiee/sx1014", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "transformers", "safetensors", "roberta", "fill-mask", "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 #roberta #fill-mask #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", "text-generation-inference", "unsloth", "llama", "trl", "sft", "en", "dataset:yahma/alpaca-cleaned", "base_model:unsloth/llama-3-8b-bnb-4bit", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[ "# Alpaca-Llama-3-8B-Lora\n\n\n- Fine Tuned using dataset: URL\n- Epoch Count: 1\n- Step Count: 6,470/6,470\n- Batch Size: 2\n- Gradient Accumulation Steps: 4\n- Context Size: 8192\n- Num examples: 51,760 \n- Trainable Parameters: 41,943,040\n- Learning Rate: 0.00001\n- Training Loss: 0.960000\n- Fined Tuned using: Google Colab Pro (Nvidia T4 runtime)\n\n- Developed by: akumaburn\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n- Prompt Format: Alpaca (URL\n- Chai ELO: 1146.84 (URL\n\nSome GGUF quantizations can be found in URL\n\nmistral-7b-openorca.Q8_0.gguf:\n- MMLU-Test: Final result: 41.5836 +/- 0.4174\n- Arc-Easy: Final result: 72.6316 +/- 1.8691\n- Truthful QA: Final result: 32.0685 +/- 1.6339\n- Arc-Challenge: Final result: 48.8294 +/- 2.8956\n\nllama-3-8b-bnb-4bit.Q8_0.gguf:\n- MMLU-Test: Final result: 40.4074 +/- 0.4156\n- Arc-Easy: Final result: 73.8596 +/- 1.8421\n- Truthful QA: Final result: 26.6830 +/- 1.5484\n- Arc-Challenge: Final result: 46.8227 +/- 2.8906\n\nOpen_Orca_Llama-3-8B-unsloth.Q8_0.gguf:\n- MMLU-Test: Final result: 39.3818 +/- 0.4138\n- Arc-Easy: Final result: 67.3684 +/- 1.9656\n- Truthful QA: Final result: 29.0086 +/- 1.5886\n- Arc-Challenge: Final result: 42.1405 +/- 2.8604\n\nAlpaca-Llama-3-8B-GGUF-unsloth.Q8_0.gguf:\n- MMLU-Test: Final result: 40.6441 +/- 0.4160\n- Arc-Easy: Final result: 77.5439 +/- 1.7494\n- Truthful QA: Final result: 29.7430 +/- 1.6003\n- Arc-Challenge: Final result: 50.5017 +/- 2.8963\n\nMeta-Llama-3-8B.Q8_0.gguf:\n- MMLU-Test: Final result: 40.8664 +/- 0.4163\n- Arc-Easy: Final result: 74.3860 +/- 1.8299\n- Truthful QA: Final result: 28.6414 +/- 1.5826\n- Arc-Challenge: Final result: 47.1572 +/- 2.8917\n\nURL Options For Testing:\n--samplers \"tfs;typical;temp\" --draft 32 --ctx-size 8192 --temp 0.82 --tfs 0.8 --typical 1.1 --repeat-last-n 512 --batch-size 8192 --repeat-penalty 1.0 --n-gpu-layers 100 --threads 12\n\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "TAGS\n#transformers #safetensors #text-generation-inference #unsloth #llama #trl #sft #en #dataset-yahma/alpaca-cleaned #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us \n", "# Alpaca-Llama-3-8B-Lora\n\n\n- Fine Tuned using dataset: URL\n- Epoch Count: 1\n- Step Count: 6,470/6,470\n- Batch Size: 2\n- Gradient Accumulation Steps: 4\n- Context Size: 8192\n- Num examples: 51,760 \n- Trainable Parameters: 41,943,040\n- Learning Rate: 0.00001\n- Training Loss: 0.960000\n- Fined Tuned using: Google Colab Pro (Nvidia T4 runtime)\n\n- Developed by: akumaburn\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n- Prompt Format: Alpaca (URL\n- Chai ELO: 1146.84 (URL\n\nSome GGUF quantizations can be found in URL\n\nmistral-7b-openorca.Q8_0.gguf:\n- MMLU-Test: Final result: 41.5836 +/- 0.4174\n- Arc-Easy: Final result: 72.6316 +/- 1.8691\n- Truthful QA: Final result: 32.0685 +/- 1.6339\n- Arc-Challenge: Final result: 48.8294 +/- 2.8956\n\nllama-3-8b-bnb-4bit.Q8_0.gguf:\n- MMLU-Test: Final result: 40.4074 +/- 0.4156\n- Arc-Easy: Final result: 73.8596 +/- 1.8421\n- Truthful QA: Final result: 26.6830 +/- 1.5484\n- Arc-Challenge: Final result: 46.8227 +/- 2.8906\n\nOpen_Orca_Llama-3-8B-unsloth.Q8_0.gguf:\n- MMLU-Test: Final result: 39.3818 +/- 0.4138\n- Arc-Easy: Final result: 67.3684 +/- 1.9656\n- Truthful QA: Final result: 29.0086 +/- 1.5886\n- Arc-Challenge: Final result: 42.1405 +/- 2.8604\n\nAlpaca-Llama-3-8B-GGUF-unsloth.Q8_0.gguf:\n- MMLU-Test: Final result: 40.6441 +/- 0.4160\n- Arc-Easy: Final result: 77.5439 +/- 1.7494\n- Truthful QA: Final result: 29.7430 +/- 1.6003\n- Arc-Challenge: Final result: 50.5017 +/- 2.8963\n\nMeta-Llama-3-8B.Q8_0.gguf:\n- MMLU-Test: Final result: 40.8664 +/- 0.4163\n- Arc-Easy: Final result: 74.3860 +/- 1.8299\n- Truthful QA: Final result: 28.6414 +/- 1.5826\n- Arc-Challenge: Final result: 47.1572 +/- 2.8917\n\nURL Options For Testing:\n--samplers \"tfs;typical;temp\" --draft 32 --ctx-size 8192 --temp 0.82 --tfs 0.8 --typical 1.1 --repeat-last-n 512 --batch-size 8192 --repeat-penalty 1.0 --n-gpu-layers 100 --threads 12\n\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

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

[ "1910.09700" ]

[]

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

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

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

[]

[]

[ "# robust_llm_pythia-31m_mz-131_IMDB\n\nThis model is a fine-tuned version of EleutherAI/pythia-31m on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 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-31m #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# robust_llm_pythia-31m_mz-131_IMDB\n\nThis model is a fine-tuned version of EleutherAI/pythia-31m on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 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", "whisper", "automatic-speech-recognition", "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 #whisper #automatic-speech-recognition #arxiv-1910.09700 #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

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

[]

[ "en" ]

[ "# Alpaca-Llama-3-8B\n\n\n- Fine Tuned using dataset: URL\n- Epoch Count: 1\n- Step Count: 6,470/6,470\n- Batch Size: 2\n- Gradient Accumulation Steps: 4\n- Context Size: 8192\n- Num examples: 51,760 \n- Trainable Parameters: 41,943,040\n- Learning Rate: 0.00001\n- Training Loss: 0.960000\n- Fined Tuned using: Google Colab Pro (Nvidia T4 runtime)\n\n- Developed by: akumaburn\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n- Prompt Format: Alpaca (URL\n- Chai ELO: 1146.84 (URL\n\nSome GGUF quantizations can be found in URL\n\nmistral-7b-openorca.Q8_0.gguf:\n- MMLU-Test: Final result: 41.5836 +/- 0.4174\n- Arc-Easy: Final result: 72.6316 +/- 1.8691\n- Truthful QA: Final result: 32.0685 +/- 1.6339\n- Arc-Challenge: Final result: 48.8294 +/- 2.8956\n\nllama-3-8b-bnb-4bit.Q8_0.gguf:\n- MMLU-Test: Final result: 40.4074 +/- 0.4156\n- Arc-Easy: Final result: 73.8596 +/- 1.8421\n- Truthful QA: Final result: 26.6830 +/- 1.5484\n- Arc-Challenge: Final result: 46.8227 +/- 2.8906\n\nOpen_Orca_Llama-3-8B-unsloth.Q8_0.gguf:\n- MMLU-Test: Final result: 39.3818 +/- 0.4138\n- Arc-Easy: Final result: 67.3684 +/- 1.9656\n- Truthful QA: Final result: 29.0086 +/- 1.5886\n- Arc-Challenge: Final result: 42.1405 +/- 2.8604\n\nAlpaca-Llama-3-8B-GGUF-unsloth.Q8_0.gguf:\n- MMLU-Test: Final result: 40.6441 +/- 0.4160\n- Arc-Easy: Final result: 77.5439 +/- 1.7494\n- Truthful QA: Final result: 29.7430 +/- 1.6003\n- Arc-Challenge: Final result: 50.5017 +/- 2.8963\n\nMeta-Llama-3-8B.Q8_0.gguf:\n- MMLU-Test: Final result: 40.8664 +/- 0.4163\n- Arc-Easy: Final result: 74.3860 +/- 1.8299\n- Truthful QA: Final result: 28.6414 +/- 1.5826\n- Arc-Challenge: Final result: 47.1572 +/- 2.8917\n\nURL Options For Testing:\n--samplers \"tfs;typical;temp\" --draft 32 --ctx-size 8192 --temp 0.82 --tfs 0.8 --typical 1.1 --repeat-last-n 512 --batch-size 8192 --repeat-penalty 1.0 --n-gpu-layers 100 --threads 12\n\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 #en #dataset-yahma/alpaca-cleaned #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "# Alpaca-Llama-3-8B\n\n\n- Fine Tuned using dataset: URL\n- Epoch Count: 1\n- Step Count: 6,470/6,470\n- Batch Size: 2\n- Gradient Accumulation Steps: 4\n- Context Size: 8192\n- Num examples: 51,760 \n- Trainable Parameters: 41,943,040\n- Learning Rate: 0.00001\n- Training Loss: 0.960000\n- Fined Tuned using: Google Colab Pro (Nvidia T4 runtime)\n\n- Developed by: akumaburn\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n- Prompt Format: Alpaca (URL\n- Chai ELO: 1146.84 (URL\n\nSome GGUF quantizations can be found in URL\n\nmistral-7b-openorca.Q8_0.gguf:\n- MMLU-Test: Final result: 41.5836 +/- 0.4174\n- Arc-Easy: Final result: 72.6316 +/- 1.8691\n- Truthful QA: Final result: 32.0685 +/- 1.6339\n- Arc-Challenge: Final result: 48.8294 +/- 2.8956\n\nllama-3-8b-bnb-4bit.Q8_0.gguf:\n- MMLU-Test: Final result: 40.4074 +/- 0.4156\n- Arc-Easy: Final result: 73.8596 +/- 1.8421\n- Truthful QA: Final result: 26.6830 +/- 1.5484\n- Arc-Challenge: Final result: 46.8227 +/- 2.8906\n\nOpen_Orca_Llama-3-8B-unsloth.Q8_0.gguf:\n- MMLU-Test: Final result: 39.3818 +/- 0.4138\n- Arc-Easy: Final result: 67.3684 +/- 1.9656\n- Truthful QA: Final result: 29.0086 +/- 1.5886\n- Arc-Challenge: Final result: 42.1405 +/- 2.8604\n\nAlpaca-Llama-3-8B-GGUF-unsloth.Q8_0.gguf:\n- MMLU-Test: Final result: 40.6441 +/- 0.4160\n- Arc-Easy: Final result: 77.5439 +/- 1.7494\n- Truthful QA: Final result: 29.7430 +/- 1.6003\n- Arc-Challenge: Final result: 50.5017 +/- 2.8963\n\nMeta-Llama-3-8B.Q8_0.gguf:\n- MMLU-Test: Final result: 40.8664 +/- 0.4163\n- Arc-Easy: Final result: 74.3860 +/- 1.8299\n- Truthful QA: Final result: 28.6414 +/- 1.5826\n- Arc-Challenge: Final result: 47.1572 +/- 2.8917\n\nURL Options For Testing:\n--samplers \"tfs;typical;temp\" --draft 32 --ctx-size 8192 --temp 0.82 --tfs 0.8 --typical 1.1 --repeat-last-n 512 --batch-size 8192 --repeat-penalty 1.0 --n-gpu-layers 100 --threads 12\n\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "mlx", "safetensors", "llama", "en", "dataset:cognitivecomputations/Dolphin-2.9", "dataset:teknium/OpenHermes-2.5", "dataset:m-a-p/CodeFeedback-Filtered-Instruction", "dataset:cognitivecomputations/dolphin-coder", "dataset:cognitivecomputations/samantha-data", "dataset:HuggingFaceH4/ultrachat_200k", "dataset:microsoft/orca-math-word-problems-200k", "dataset:abacusai/SystemChat-1.1", "dataset:Locutusque/function-calling-chatml", "dataset:internlm/Agent-FLAN", "license:llama3", "region:us" ]

[]

[ "en" ]

[ "# mlx-community/dolphin-2.9-llama3-70b-8bit\nThis model was converted to MLX format from ['cognitivecomputations/dolphin-2.9-llama3-70b']() using mlx-lm version 0.11.0.\nRefer to the original model card for more details on the model.", "## Use with mlx" ]

[ "TAGS\n#mlx #safetensors #llama #en #dataset-cognitivecomputations/Dolphin-2.9 #dataset-teknium/OpenHermes-2.5 #dataset-m-a-p/CodeFeedback-Filtered-Instruction #dataset-cognitivecomputations/dolphin-coder #dataset-cognitivecomputations/samantha-data #dataset-HuggingFaceH4/ultrachat_200k #dataset-microsoft/orca-math-word-problems-200k #dataset-abacusai/SystemChat-1.1 #dataset-Locutusque/function-calling-chatml #dataset-internlm/Agent-FLAN #license-llama3 #region-us \n", "# mlx-community/dolphin-2.9-llama3-70b-8bit\nThis model was converted to MLX format from ['cognitivecomputations/dolphin-2.9-llama3-70b']() using mlx-lm version 0.11.0.\nRefer to the original model card for more details on the model.", "## Use with mlx" ]

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

[]

[]

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

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

[ "transformers", "safetensors", "mistral", "text-generation", "alignment-handbook", "generated_from_trainer", "trl", "dpo", "conversational", "dataset:HuggingFaceH4/ultrafeedback_binarized", "base_model:HuggingFaceH4/mistral-7b-sft-beta", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# 0.001_ablation_5iters_bs256_useresponse_iter_1\n\nThis model is a fine-tuned version of HuggingFaceH4/mistral-7b-sft-beta on the HuggingFaceH4/ultrafeedback_binarized 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-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 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #alignment-handbook #generated_from_trainer #trl #dpo #conversational #dataset-HuggingFaceH4/ultrafeedback_binarized #base_model-HuggingFaceH4/mistral-7b-sft-beta #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# 0.001_ablation_5iters_bs256_useresponse_iter_1\n\nThis model is a fine-tuned version of HuggingFaceH4/mistral-7b-sft-beta on the HuggingFaceH4/ultrafeedback_binarized 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-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 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.15.2" ]

[ "transformers", "tf", "bert", "question-answering", "generated_from_keras_callback", "base_model:huggingface-course/bert-finetuned-squad", "endpoints_compatible", "region:us" ]

[]

[]

[ "# model_dl_1\n\nThis model is a fine-tuned version of huggingface-course/bert-finetuned-squad on an unknown dataset.\nIt achieves the following results on the evaluation set:", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': 1e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}\n- training_precision: mixed_float16", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- TensorFlow 2.15.0\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #tf #bert #question-answering #generated_from_keras_callback #base_model-huggingface-course/bert-finetuned-squad #endpoints_compatible #region-us \n", "# model_dl_1\n\nThis model is a fine-tuned version of huggingface-course/bert-finetuned-squad on an unknown dataset.\nIt achieves the following results on the evaluation set:", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': 1e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}\n- training_precision: mixed_float16", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- TensorFlow 2.15.0\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "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" ]

[ "nemo", "pytorch", "NeMo", "license:cc-by-4.0", "region:us" ]

[]

[]

[ "# Llama2-7b-nemo\n\n<style>\nimg {\n display: inline;\n}\n</style>\n\n\n| \n| \n\nPut a short model description here.\n\nSee the model architecture section and NeMo documentation for complete architecture details.", "## NVIDIA NeMo: Training\n\nTo train, fine-tune or play with the model you will need to install NVIDIA NeMo. We recommend you install it after you've installed latest Pytorch version.", "## How to Use this Model\n\nThe model is available for use in the NeMo toolkit [3], and can be used as a pre-trained checkpoint for inference or for fine-tuning on another dataset.", "### Automatically instantiate the model\n\nNOTE: Please update the model class below to match the class of the model being uploaded.", "### NOTE\n\n Add some information about how to use the model here. An example is provided for ASR inference below.\n\n ### Transcribing using Python\n First, let's get a sample\n \n Then simply do:\n \n\n ### Transcribing many audio files", "### Input\n\nAdd some information about what are the inputs to this model", "### Output\n\nAdd some information about what are the outputs of this model", "## Model Architecture\n\nAdd information here discussing architectural details of the model or any comments to users about the model.", "## Training\n\nAdd information here about how the model was trained. It should be as detailed as possible, potentially including the the link to the script used to train as well as the base config used to train the model. If extraneous scripts are used to prepare the components of the model, please include them here.", "### NOTE\n\n An example is provided below for ASR\n\n The NeMo toolkit [3] was used for training the models for over several hundred epochs. These model are trained with this example script and this base config.\n\n The tokenizers for these models were built using the text transcripts of the train set with this script.", "### Datasets\n\nTry to provide as detailed a list of datasets as possible. If possible, provide links to the datasets on HF by adding it to the manifest section at the top of the README (marked by ---).", "### NOTE\n\n An example for the manifest section is provided below for ASR datasets\n\n datasets:\n - librispeech_asr\n - fisher_corpus\n - Switchboard-1\n - WSJ-0\n - WSJ-1\n - National-Singapore-Corpus-Part-1\n - National-Singapore-Corpus-Part-6\n - vctk\n - voxpopuli\n - europarl\n - multilingual_librispeech\n - mozilla-foundation/common_voice_8_0\n - MLCommons/peoples_speech\n\n The corresponding text in this section for those datasets is stated below -\n\n The model was trained on 64K hours of English speech collected and prepared by NVIDIA NeMo and Suno teams.\n\n The training dataset consists of private subset with 40K hours of English speech plus 24K hours from the following public datasets:\n\n - Librispeech 960 hours of English speech\n - Fisher Corpus\n - Switchboard-1 Dataset\n - WSJ-0 and WSJ-1\n - National Speech Corpus (Part 1, Part 6)\n - VCTK\n - VoxPopuli (EN)\n - Europarl-ASR (EN)\n - Multilingual Librispeech (MLS EN) - 2,000 hour subset\n - Mozilla Common Voice (v7.0)\n - People's Speech - 12,000 hour subset", "## Performance\n\nAdd information here about the performance of the model. Discuss what is the metric that is being used to evaluate the model and if there are external links explaning the custom metric, please link to it.", "### NOTE\n\n An example is provided below for ASR metrics list that can be added to the top of the README\n \n model-index:\n - name: PUT_MODEL_NAME\n results:\n - task:\n name: Automatic Speech Recognition\n type: automatic-speech-recognition\n dataset:\n name: AMI (Meetings test)\n type: edinburghcstr/ami\n config: ihm\n split: test\n args:\n language: en\n metrics:\n - name: Test WER\n type: wer\n value: 17.10\n - task:\n name: Automatic Speech Recognition\n type: automatic-speech-recognition\n dataset:\n name: Earnings-22\n type: revdotcom/earnings22\n split: test\n args:\n language: en\n metrics:\n - name: Test WER\n type: wer\n value: 14.11\n\nProvide any caveats about the results presented in the top of the discussion so that nuance is not lost. \n\nIt should ideally be in a tabular format (you can use the following website to make your tables in markdown format - URL", "## Limitations\n\nDiscuss any practical limitations to the model when being used in real world cases. They can also be legal disclaimers, or discussion regarding the safety of the model (particularly in the case of LLMs).", "### Note\n\n An example is provided below \n\n Since this model was trained on publicly available speech datasets, the performance of this model might degrade for speech which includes technical terms, or vernacular that the model has not been trained on. The model might also perform worse for accented speech.", "## License\n\nLicense to use this model is covered by the CC-BY-4.0. By downloading the public and release version of the model, you accept the terms and conditions of the CC-BY-4.0 license.", "## References\n\nProvide appropriate references in the markdown link format below. Please order them numerically.\n\n[1] NVIDIA NeMo Toolkit" ]

[ "TAGS\n#nemo #pytorch #NeMo #license-cc-by-4.0 #region-us \n", "# Llama2-7b-nemo\n\n<style>\nimg {\n display: inline;\n}\n</style>\n\n\n| \n| \n\nPut a short model description here.\n\nSee the model architecture section and NeMo documentation for complete architecture details.", "## NVIDIA NeMo: Training\n\nTo train, fine-tune or play with the model you will need to install NVIDIA NeMo. We recommend you install it after you've installed latest Pytorch version.", "## How to Use this Model\n\nThe model is available for use in the NeMo toolkit [3], and can be used as a pre-trained checkpoint for inference or for fine-tuning on another dataset.", "### Automatically instantiate the model\n\nNOTE: Please update the model class below to match the class of the model being uploaded.", "### NOTE\n\n Add some information about how to use the model here. An example is provided for ASR inference below.\n\n ### Transcribing using Python\n First, let's get a sample\n \n Then simply do:\n \n\n ### Transcribing many audio files", "### Input\n\nAdd some information about what are the inputs to this model", "### Output\n\nAdd some information about what are the outputs of this model", "## Model Architecture\n\nAdd information here discussing architectural details of the model or any comments to users about the model.", "## Training\n\nAdd information here about how the model was trained. It should be as detailed as possible, potentially including the the link to the script used to train as well as the base config used to train the model. If extraneous scripts are used to prepare the components of the model, please include them here.", "### NOTE\n\n An example is provided below for ASR\n\n The NeMo toolkit [3] was used for training the models for over several hundred epochs. These model are trained with this example script and this base config.\n\n The tokenizers for these models were built using the text transcripts of the train set with this script.", "### Datasets\n\nTry to provide as detailed a list of datasets as possible. If possible, provide links to the datasets on HF by adding it to the manifest section at the top of the README (marked by ---).", "### NOTE\n\n An example for the manifest section is provided below for ASR datasets\n\n datasets:\n - librispeech_asr\n - fisher_corpus\n - Switchboard-1\n - WSJ-0\n - WSJ-1\n - National-Singapore-Corpus-Part-1\n - National-Singapore-Corpus-Part-6\n - vctk\n - voxpopuli\n - europarl\n - multilingual_librispeech\n - mozilla-foundation/common_voice_8_0\n - MLCommons/peoples_speech\n\n The corresponding text in this section for those datasets is stated below -\n\n The model was trained on 64K hours of English speech collected and prepared by NVIDIA NeMo and Suno teams.\n\n The training dataset consists of private subset with 40K hours of English speech plus 24K hours from the following public datasets:\n\n - Librispeech 960 hours of English speech\n - Fisher Corpus\n - Switchboard-1 Dataset\n - WSJ-0 and WSJ-1\n - National Speech Corpus (Part 1, Part 6)\n - VCTK\n - VoxPopuli (EN)\n - Europarl-ASR (EN)\n - Multilingual Librispeech (MLS EN) - 2,000 hour subset\n - Mozilla Common Voice (v7.0)\n - People's Speech - 12,000 hour subset", "## Performance\n\nAdd information here about the performance of the model. Discuss what is the metric that is being used to evaluate the model and if there are external links explaning the custom metric, please link to it.", "### NOTE\n\n An example is provided below for ASR metrics list that can be added to the top of the README\n \n model-index:\n - name: PUT_MODEL_NAME\n results:\n - task:\n name: Automatic Speech Recognition\n type: automatic-speech-recognition\n dataset:\n name: AMI (Meetings test)\n type: edinburghcstr/ami\n config: ihm\n split: test\n args:\n language: en\n metrics:\n - name: Test WER\n type: wer\n value: 17.10\n - task:\n name: Automatic Speech Recognition\n type: automatic-speech-recognition\n dataset:\n name: Earnings-22\n type: revdotcom/earnings22\n split: test\n args:\n language: en\n metrics:\n - name: Test WER\n type: wer\n value: 14.11\n\nProvide any caveats about the results presented in the top of the discussion so that nuance is not lost. \n\nIt should ideally be in a tabular format (you can use the following website to make your tables in markdown format - URL", "## Limitations\n\nDiscuss any practical limitations to the model when being used in real world cases. They can also be legal disclaimers, or discussion regarding the safety of the model (particularly in the case of LLMs).", "### Note\n\n An example is provided below \n\n Since this model was trained on publicly available speech datasets, the performance of this model might degrade for speech which includes technical terms, or vernacular that the model has not been trained on. The model might also perform worse for accented speech.", "## License\n\nLicense to use this model is covered by the CC-BY-4.0. By downloading the public and release version of the model, you accept the terms and conditions of the CC-BY-4.0 license.", "## References\n\nProvide appropriate references in the markdown link format below. Please order them numerically.\n\n[1] NVIDIA NeMo Toolkit" ]

[ "transformers", "safetensors", "roberta", "fill-mask", "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 #roberta #fill-mask #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", "arxiv:1910.09700", "base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0", "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 #arxiv-1910.09700 #base_model-TinyLlama/TinyLlama-1.1B-Chat-v1.0 #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", "text-generation-inference", "unsloth", "llama", "trl", "en", "base_model:unsloth/llama-3-8b-bnb-4bit", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

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

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

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

[]

[ "en" ]

[ "# Alpaca-Llama-3-8B\n\n\n- Fine Tuned using dataset: URL\n- Epoch Count: 1\n- Step Count: 6,470/6,470\n- Batch Size: 2\n- Gradient Accumulation Steps: 4\n- Context Size: 8192\n- Num examples: 51,760 \n- Trainable Parameters: 41,943,040\n- Learning Rate: 0.00001\n- Training Loss: 0.960000\n- Fined Tuned using: Google Colab Pro (Nvidia T4 runtime)\n\n- Developed by: akumaburn\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n- Prompt Format: Alpaca (URL\n- Chai ELO: 1146.84 (URL\n\nFull model can be found in URL\n\nmistral-7b-openorca.Q8_0.gguf:\n- MMLU-Test: Final result: 41.5836 +/- 0.4174\n- Arc-Easy: Final result: 72.6316 +/- 1.8691\n- Truthful QA: Final result: 32.0685 +/- 1.6339\n- Arc-Challenge: Final result: 48.8294 +/- 2.8956\n\nllama-3-8b-bnb-4bit.Q8_0.gguf:\n- MMLU-Test: Final result: 40.4074 +/- 0.4156\n- Arc-Easy: Final result: 73.8596 +/- 1.8421\n- Truthful QA: Final result: 26.6830 +/- 1.5484\n- Arc-Challenge: Final result: 46.8227 +/- 2.8906\n\nOpen_Orca_Llama-3-8B-unsloth.Q8_0.gguf:\n- MMLU-Test: Final result: 39.3818 +/- 0.4138\n- Arc-Easy: Final result: 67.3684 +/- 1.9656\n- Truthful QA: Final result: 29.0086 +/- 1.5886\n- Arc-Challenge: Final result: 42.1405 +/- 2.8604\n\nAlpaca-Llama-3-8B-GGUF-unsloth.Q8_0.gguf:\n- MMLU-Test: Final result: 40.6441 +/- 0.4160\n- Arc-Easy: Final result: 77.5439 +/- 1.7494\n- Truthful QA: Final result: 29.7430 +/- 1.6003\n- Arc-Challenge: Final result: 50.5017 +/- 2.8963\n\nMeta-Llama-3-8B.Q8_0.gguf:\n- MMLU-Test: Final result: 40.8664 +/- 0.4163\n- Arc-Easy: Final result: 74.3860 +/- 1.8299\n- Truthful QA: Final result: 28.6414 +/- 1.5826\n- Arc-Challenge: Final result: 47.1572 +/- 2.8917\n\nURL Options For Testing:\n--samplers \"tfs;typical;temp\" --draft 32 --ctx-size 8192 --temp 0.82 --tfs 0.8 --typical 1.1 --repeat-last-n 512 --batch-size 8192 --repeat-penalty 1.0 --n-gpu-layers 100 --threads 12\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "TAGS\n#transformers #gguf #llama #text-generation-inference #unsloth #trl #sft #en #dataset-yahma/alpaca-cleaned #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us \n", "# Alpaca-Llama-3-8B\n\n\n- Fine Tuned using dataset: URL\n- Epoch Count: 1\n- Step Count: 6,470/6,470\n- Batch Size: 2\n- Gradient Accumulation Steps: 4\n- Context Size: 8192\n- Num examples: 51,760 \n- Trainable Parameters: 41,943,040\n- Learning Rate: 0.00001\n- Training Loss: 0.960000\n- Fined Tuned using: Google Colab Pro (Nvidia T4 runtime)\n\n- Developed by: akumaburn\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n- Prompt Format: Alpaca (URL\n- Chai ELO: 1146.84 (URL\n\nFull model can be found in URL\n\nmistral-7b-openorca.Q8_0.gguf:\n- MMLU-Test: Final result: 41.5836 +/- 0.4174\n- Arc-Easy: Final result: 72.6316 +/- 1.8691\n- Truthful QA: Final result: 32.0685 +/- 1.6339\n- Arc-Challenge: Final result: 48.8294 +/- 2.8956\n\nllama-3-8b-bnb-4bit.Q8_0.gguf:\n- MMLU-Test: Final result: 40.4074 +/- 0.4156\n- Arc-Easy: Final result: 73.8596 +/- 1.8421\n- Truthful QA: Final result: 26.6830 +/- 1.5484\n- Arc-Challenge: Final result: 46.8227 +/- 2.8906\n\nOpen_Orca_Llama-3-8B-unsloth.Q8_0.gguf:\n- MMLU-Test: Final result: 39.3818 +/- 0.4138\n- Arc-Easy: Final result: 67.3684 +/- 1.9656\n- Truthful QA: Final result: 29.0086 +/- 1.5886\n- Arc-Challenge: Final result: 42.1405 +/- 2.8604\n\nAlpaca-Llama-3-8B-GGUF-unsloth.Q8_0.gguf:\n- MMLU-Test: Final result: 40.6441 +/- 0.4160\n- Arc-Easy: Final result: 77.5439 +/- 1.7494\n- Truthful QA: Final result: 29.7430 +/- 1.6003\n- Arc-Challenge: Final result: 50.5017 +/- 2.8963\n\nMeta-Llama-3-8B.Q8_0.gguf:\n- MMLU-Test: Final result: 40.8664 +/- 0.4163\n- Arc-Easy: Final result: 74.3860 +/- 1.8299\n- Truthful QA: Final result: 28.6414 +/- 1.5826\n- Arc-Challenge: Final result: 47.1572 +/- 2.8917\n\nURL Options For Testing:\n--samplers \"tfs;typical;temp\" --draft 32 --ctx-size 8192 --temp 0.82 --tfs 0.8 --typical 1.1 --repeat-last-n 512 --batch-size 8192 --repeat-penalty 1.0 --n-gpu-layers 100 --threads 12\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "transformers", "safetensors", "llama", "text-generation", "meta", "llama-3", "conversational", "en", "license:llama3", "autotrain_compatible", "endpoints_compatible", "has_space", "text-generation-inference", "region:us" ]

[]

[ "en" ]

[ "# GPUs, 65K: 8, 262K: 32\nParameter: GPU Type, 65K: NVIDIA L40S, 262K: NVIDIA L40S\n\n\nThe Gradient AI Team\n--------------------\n\n\nURL\n\n\nGradient is accelerating AI transformation across industries. Our AI Foundry incorporates your data to deploy autonomous assistants that power critical operations across your business.\n\n\nContact Us\n----------\n\n\nDrop an email to contact@URL\n\n\nReferences\n----------\n\n\n[1] Peng, Bowen, et al. \"Yarn: Efficient context window extension of large language models.\" arXiv preprint arXiv:2309.00071 (2023).\n\n\n[2] Liu, Hao, et al. \"World Model on Million-Length Video And Language With RingAttention.\" arXiv preprint arXiv:2402.08268 (2024).\n\n\n[3] URL\n\n\n\n\n---\n\n\nBase Model\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#transformers #safetensors #llama #text-generation #meta #llama-3 #conversational #en #license-llama3 #autotrain_compatible #endpoints_compatible #has_space #text-generation-inference #region-us \n", "# GPUs, 65K: 8, 262K: 32\nParameter: GPU Type, 65K: NVIDIA L40S, 262K: NVIDIA L40S\n\n\nThe Gradient AI Team\n--------------------\n\n\nURL\n\n\nGradient is accelerating AI transformation across industries. Our AI Foundry incorporates your data to deploy autonomous assistants that power critical operations across your business.\n\n\nContact Us\n----------\n\n\nDrop an email to contact@URL\n\n\nReferences\n----------\n\n\n[1] Peng, Bowen, et al. \"Yarn: Efficient context window extension of large language models.\" arXiv preprint arXiv:2309.00071 (2023).\n\n\n[2] Liu, Hao, et al. \"World Model on Million-Length Video And Language With RingAttention.\" arXiv preprint arXiv:2402.08268 (2024).\n\n\n[3] URL\n\n\n\n\n---\n\n\nBase Model\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", "safetensors", "llama", "text-generation", "mergekit", "merge", "base_model:motherfucker0/zhun02", "base_model:motherfucker0/zhun01", "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* motherfucker0/zhun02\n* motherfucker0/zhun01", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #mergekit #merge #base_model-motherfucker0/zhun02 #base_model-motherfucker0/zhun01 #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* motherfucker0/zhun02\n* motherfucker0/zhun01", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "transformers", "safetensors", "vision-encoder-decoder", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]

[ "1910.09700" ]

[]

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

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

[ "transformers", "safetensors", "llama", "text-generation", "conversational", "dataset:raincandy-u/Dextromethorphan-10k", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# phillama-3.8b-v0.1\n\nPhillama is a model based on Phi-3-mini and trained on Llama-generated dataset raincandy-u/Dextromethorphan-10k to make it more \"llama-like\".\n\nAlso, this model is converted into Llama format, so it will work with any Llama-2/3 workflow.", "# System prompt\n\n'You are a humanoid AI assistant. You think step by step and give detailed long response.'", "# Prompt template" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #conversational #dataset-raincandy-u/Dextromethorphan-10k #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# phillama-3.8b-v0.1\n\nPhillama is a model based on Phi-3-mini and trained on Llama-generated dataset raincandy-u/Dextromethorphan-10k to make it more \"llama-like\".\n\nAlso, this model is converted into Llama format, so it will work with any Llama-2/3 workflow.", "# System prompt\n\n'You are a humanoid AI assistant. You think step by step and give detailed long response.'", "# Prompt template" ]

[ "transformers", "gguf", "llama-3-8b", "sft", "medical", "en", "base_model:johnsnowlabs/JSL-MedLlama-3-8B-v1.0", "license:cc-by-nc-nd-4.0", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #llama-3-8b #sft #medical #en #base_model-johnsnowlabs/JSL-MedLlama-3-8B-v1.0 #license-cc-by-nc-nd-4.0 #endpoints_compatible #region-us \n" ]

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

[]

[]

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

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

[ "transformers", "safetensors", "stablelm", "text-generation", "mergekit", "merge", "conversational", "base_model:coffiee/sx1014", "base_model:coffie3/sx1015", "autotrain_compatible", "endpoints_compatible", "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* coffiee/sx1014\n* coffie3/sx1015", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "TAGS\n#transformers #safetensors #stablelm #text-generation #mergekit #merge #conversational #base_model-coffiee/sx1014 #base_model-coffie3/sx1015 #autotrain_compatible #endpoints_compatible #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* coffiee/sx1014\n* coffie3/sx1015", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

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

[]

[]

[ "# robust_llm_pythia-70m_mz-131_IMDB\n\nThis model is a fine-tuned version of EleutherAI/pythia-70m on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 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-70m #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# robust_llm_pythia-70m_mz-131_IMDB\n\nThis model is a fine-tuned version of EleutherAI/pythia-70m on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 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", "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" ]

[ "text-to-image", "region:us" ]

[]

[]

[]

[ "TAGS\n#text-to-image #region-us \n" ]

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

[ "1910.09700" ]

[]

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

[ "TAGS\n#transformers #safetensors #mistral #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID\nI dont kknow what im doing wrong bro", "## 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", "medical", "text-generation", "en", "dataset:Open-Orca/OpenOrca", "dataset:pubmed", "dataset:medmcqa", "dataset:maximegmd/medqa_alpaca_format", "base_model:internistai/base-7b-v0.2", "license:apache-2.0", "region:us" ]

[]

[ "en" ]

[ "### Model Sources\n\n\n* Trainer: Axolotl\n* Paper: Awaiting acceptance (*Impact of High-Quality, Mixed-Domain Data on the Performance of Medical Language Models*)\n\n\nUses\n----\n\n\nThis model was trained to demonstrate the benefit of using high quality and relevant medical literature as well as general data to retain capabilities in other domains. Therefore the model was trained for any specific use and did not benefit from additional instruction tuning to ensure safety.\n\n\nThe model in its current state can be useful for medical professionals as an assistant, be it for clinical decision support or documentation. We do not recommend the use of this model by non professionals who may not be able to notice errors.\n\n\nWe recommend additional task specific training and safety evaluation before using the model in a real-world setting.", "### Format\n\n\nThe model uses the Alpaca format, it is available as a chat template", "### Out-of-Scope Use\n\n\nWe do not recommend using this model for natural language generation in a production environment, finetuned or otherwise.\n\n\nProfessional Evaluation\n-----------------------\n\n\nWe created a free response evaluation dataset of 100 questions and prompted the model and GPT-4 as a comparison with these questions. We then recolted the prompt/answer pairs and presented them to 10 medical doctors of different specialties with questions to be answered with a 7 point likert scale (See the paper for more information).\n\n\n![Likert scale](assets/URL \"likert\")\nTraining Details\n----------------", "### Training Data\n\n\nURL 7b contains a total of 2.3B tokens:\n\n\n* General Domain: OpenOrca-GPT4 is a state-of-the-art general domain dataset generated from Flan prompts using GPT-4.\n* Medical Guidelines: 11,332 articles from UpToDate were included as well as domain specific guidelines provided by physicians to cover the USMLE Content Outline.\n* Medical Books: 10,376 textbooks were sourced from PMC LitArch and our university library.\n* Synthetic Data: We generated 400M tokens by prompting a larger model with instructions to transform and adapt extracts from the Medical Guidelines.\n\n\n*Data Availability*: Considering the datasets contain proprietary information, we will not be releasing the datasets publicly. Regarding the synthetic dataset, as we show in the paper, the model trained exclusively on this dataset performs very poorly and was not up to our standards. Due to its poor quality we decided not to release it.\n\n\n![Loss](assets/URL \"loss\")", "### Training Procedure\n\n\nWe used Axolotl to train on a server with 4 NVIDIA A100 80GB GPUs for a total of 450 GPU hours. We used FlashAttention, NEFTune and sample packing with the parameters described below.", "#### Training Hyperparameters\n\n\n\nEvaluation\n----------", "### Testing Data & Metrics", "#### Testing Data\n\n\n* MedQA (USMLE) - 4 options\n* MedMCQA\n* PubMedQA\n* MMLU", "#### Metrics\n\n\n* Accuracy: we ran standardized 0-shot benchmarks using lm-evaluation-harness.", "### Results\n\n\nWe include benchmarks on MedQA (4 options), MedMCQA and PubMedQA of our model and models of similar size and achieve the first USMLE passing score of 60% on the MedQA benchmark.\n\n\n\n\\*: PMC LLaMA 7b performed poorly on the benchmark, likely due to a mismatch of formating and a lack of instruction tuning, we include in parenthesis the results reported by the authors when available.\n\n\n\\*\\*: Meditron 7b's results in MMLU are reported for transparency but are inconsistent with the average of 54.2 reported in their paper, do not hesitate to communicate the details on each category so we can update the table." ]

[ "TAGS\n#gguf #medical #text-generation #en #dataset-Open-Orca/OpenOrca #dataset-pubmed #dataset-medmcqa #dataset-maximegmd/medqa_alpaca_format #base_model-internistai/base-7b-v0.2 #license-apache-2.0 #region-us \n", "### Model Sources\n\n\n* Trainer: Axolotl\n* Paper: Awaiting acceptance (*Impact of High-Quality, Mixed-Domain Data on the Performance of Medical Language Models*)\n\n\nUses\n----\n\n\nThis model was trained to demonstrate the benefit of using high quality and relevant medical literature as well as general data to retain capabilities in other domains. Therefore the model was trained for any specific use and did not benefit from additional instruction tuning to ensure safety.\n\n\nThe model in its current state can be useful for medical professionals as an assistant, be it for clinical decision support or documentation. We do not recommend the use of this model by non professionals who may not be able to notice errors.\n\n\nWe recommend additional task specific training and safety evaluation before using the model in a real-world setting.", "### Format\n\n\nThe model uses the Alpaca format, it is available as a chat template", "### Out-of-Scope Use\n\n\nWe do not recommend using this model for natural language generation in a production environment, finetuned or otherwise.\n\n\nProfessional Evaluation\n-----------------------\n\n\nWe created a free response evaluation dataset of 100 questions and prompted the model and GPT-4 as a comparison with these questions. We then recolted the prompt/answer pairs and presented them to 10 medical doctors of different specialties with questions to be answered with a 7 point likert scale (See the paper for more information).\n\n\n![Likert scale](assets/URL \"likert\")\nTraining Details\n----------------", "### Training Data\n\n\nURL 7b contains a total of 2.3B tokens:\n\n\n* General Domain: OpenOrca-GPT4 is a state-of-the-art general domain dataset generated from Flan prompts using GPT-4.\n* Medical Guidelines: 11,332 articles from UpToDate were included as well as domain specific guidelines provided by physicians to cover the USMLE Content Outline.\n* Medical Books: 10,376 textbooks were sourced from PMC LitArch and our university library.\n* Synthetic Data: We generated 400M tokens by prompting a larger model with instructions to transform and adapt extracts from the Medical Guidelines.\n\n\n*Data Availability*: Considering the datasets contain proprietary information, we will not be releasing the datasets publicly. Regarding the synthetic dataset, as we show in the paper, the model trained exclusively on this dataset performs very poorly and was not up to our standards. Due to its poor quality we decided not to release it.\n\n\n![Loss](assets/URL \"loss\")", "### Training Procedure\n\n\nWe used Axolotl to train on a server with 4 NVIDIA A100 80GB GPUs for a total of 450 GPU hours. We used FlashAttention, NEFTune and sample packing with the parameters described below.", "#### Training Hyperparameters\n\n\n\nEvaluation\n----------", "### Testing Data & Metrics", "#### Testing Data\n\n\n* MedQA (USMLE) - 4 options\n* MedMCQA\n* PubMedQA\n* MMLU", "#### Metrics\n\n\n* Accuracy: we ran standardized 0-shot benchmarks using lm-evaluation-harness.", "### Results\n\n\nWe include benchmarks on MedQA (4 options), MedMCQA and PubMedQA of our model and models of similar size and achieve the first USMLE passing score of 60% on the MedQA benchmark.\n\n\n\n\\*: PMC LLaMA 7b performed poorly on the benchmark, likely due to a mismatch of formating and a lack of instruction tuning, we include in parenthesis the results reported by the authors when available.\n\n\n\\*\\*: Meditron 7b's results in MMLU are reported for transparency but are inconsistent with the average of 54.2 reported in their paper, do not hesitate to communicate the details on each category so we can update the table." ]

[ "transformers", "gguf", "text-generation-inference", "unsloth", "llama", "trl", "sft", "en", "base_model:FabioA810/Llama-3-8B-ForexConcepts", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #text-generation-inference #unsloth #llama #trl #sft #en #base_model-FabioA810/Llama-3-8B-ForexConcepts #license-apache-2.0 #endpoints_compatible #region-us \n" ]

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

[]

[ "en" ]

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

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

[ "transformers", "safetensors", "mistral", "text-generation", "alignment-handbook", "generated_from_trainer", "trl", "dpo", "conversational", "dataset:HuggingFaceH4/ultrafeedback_binarized", "base_model:HuggingFaceH4/mistral-7b-sft-beta", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# 0.0_ablation_5iters_bs256_useresponse_iter_1\n\nThis model is a fine-tuned version of HuggingFaceH4/mistral-7b-sft-beta on the HuggingFaceH4/ultrafeedback_binarized 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-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 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #alignment-handbook #generated_from_trainer #trl #dpo #conversational #dataset-HuggingFaceH4/ultrafeedback_binarized #base_model-HuggingFaceH4/mistral-7b-sft-beta #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# 0.0_ablation_5iters_bs256_useresponse_iter_1\n\nThis model is a fine-tuned version of HuggingFaceH4/mistral-7b-sft-beta on the HuggingFaceH4/ultrafeedback_binarized 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-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 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.15.2" ]

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

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3", "### Training results", "### Framework versions\n\n\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 #distilbert #token-classification #generated_from_trainer #base_model-distilbert-base-cased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "transformers", "safetensors", "llava", "pretraining", "generated_from_trainer", "base_model:MFuyu/llava_siglip_llama3_8b_pretrain_8192", "endpoints_compatible", "region:us" ]

[]

[]

[ "# llava_siglip_llama3_8b_finetune_8192\n\nThis model is a fine-tuned version of MFuyu/llava_siglip_llama3_8b_pretrain_8192 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: 1\n- eval_batch_size: 1\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 16\n- gradient_accumulation_steps: 8\n- total_train_batch_size: 128\n- total_eval_batch_size: 16\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 1.0", "### Training results", "### Framework versions\n\n- Transformers 4.39.2\n- Pytorch 2.2.1\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #safetensors #llava #pretraining #generated_from_trainer #base_model-MFuyu/llava_siglip_llama3_8b_pretrain_8192 #endpoints_compatible #region-us \n", "# llava_siglip_llama3_8b_finetune_8192\n\nThis model is a fine-tuned version of MFuyu/llava_siglip_llama3_8b_pretrain_8192 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: 1\n- eval_batch_size: 1\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 16\n- gradient_accumulation_steps: 8\n- total_train_batch_size: 128\n- total_eval_batch_size: 16\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 1.0", "### Training results", "### Framework versions\n\n- Transformers 4.39.2\n- Pytorch 2.2.1\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

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

[]

[]

[ "# Cars Image Training\n\n<Gallery />", "## Trigger words\n\nYou should use 'cars' to trigger the image generation.\n\nYou should use 'sports car' to trigger the image generation.\n\nYou should use 'supra' to trigger the image generation.\n\nYou should use 'toyota' to trigger the image generation.", "## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab." ]

[ "TAGS\n#diffusers #text-to-image #stable-diffusion #lora #template-sd-lora #base_model-stabilityai/stable-diffusion-xl-base-1.0 #region-us \n", "# Cars Image Training\n\n<Gallery />", "## Trigger words\n\nYou should use 'cars' to trigger the image generation.\n\nYou should use 'sports car' to trigger the image generation.\n\nYou should use 'supra' to trigger the image generation.\n\nYou should use 'toyota' to trigger the image generation.", "## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab." ]

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

[]

[]

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

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

[ "transformers", "tensorboard", "safetensors", "wav2vec2", "automatic-speech-recognition", "generated_from_trainer", "dataset:fleurs", "base_model:facebook/wav2vec2-xls-r-300m", "license:apache-2.0", "model-index", "endpoints_compatible", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0003\n* train\\_batch\\_size: 4\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: 0.1\n* num\\_epochs: 10\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.2.2+cu121\n* Datasets 2.17.1\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #wav2vec2 #automatic-speech-recognition #generated_from_trainer #dataset-fleurs #base_model-facebook/wav2vec2-xls-r-300m #license-apache-2.0 #model-index #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0003\n* train\\_batch\\_size: 4\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: 0.1\n* num\\_epochs: 10\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.2.2+cu121\n* Datasets 2.17.1\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" ]

[ "transformers", "safetensors", "phi3", "text-generation", "conversational", "custom_code", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "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 #phi3 #text-generation #conversational #custom_code #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #4-bit #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "not-for-all-audiences", "license:cc-by-nc-4.0", "region:us" ]

[]

[]

[ "# Llama-3-8B-Instruct-DADA-exl2-rpcal\n\nQuantized using 200 samples of 8192 tokens from an RP-oriented PIPPA dataset.\n\nBranches:\n- 'main' -- 'URL'\n- '8b8h' -- 8bpw, 8bit lm_head\n- '6b6h' -- 6bpw, 6bit lm_head\n- '4b6h' -- 4bpw, 6bit lm_head\n\nOriginal model link: Envoid/Llama-3-8B-EGO\n\nOriginal model README below.\n\n-----", "# This model isn't particularly great. It's just an undercooked experiment.\n\nReleasing it anyways just in case it accidentally makes good merge meat.", "# It also has a tendency to produce mature content without warning. \n\nThis model is tuned off of the base Llama-3-8B model. \n\nI adapted the leaked Undi dataset into training samples for custom formatting. This model pretty much only functions properly in SillyTavern. \n\nThe formatting has two pairs of pseudotokens\n\n\n\nThe self attention modules were fine tuned separately on this dataset and the pseudotokens were chosen because they made logical sense with respect to the character giving a reply without allowing the model to 'connect the dots' during training and figure out that it is indeed an AI language model.\n\nAfter this was done all modules were then finetuned together on the dendrite dataset in order to connect the changes made to the attention modules.\n\nSo with regards to building a SillyTavern prompt template you basically want the entire story string and any additional stylistic instructions enclosed in the [EGO] tags and then the user messages enclosed in [SEEN] tags. \n\nIt doesn't give particularly verbose replies unless you're continueing a roleplay with verbose messages. Otherwise it's pretty bad. \n\nGGUFs care of Qaunt Cartel" ]

[ "TAGS\n#not-for-all-audiences #license-cc-by-nc-4.0 #region-us \n", "# Llama-3-8B-Instruct-DADA-exl2-rpcal\n\nQuantized using 200 samples of 8192 tokens from an RP-oriented PIPPA dataset.\n\nBranches:\n- 'main' -- 'URL'\n- '8b8h' -- 8bpw, 8bit lm_head\n- '6b6h' -- 6bpw, 6bit lm_head\n- '4b6h' -- 4bpw, 6bit lm_head\n\nOriginal model link: Envoid/Llama-3-8B-EGO\n\nOriginal model README below.\n\n-----", "# This model isn't particularly great. It's just an undercooked experiment.\n\nReleasing it anyways just in case it accidentally makes good merge meat.", "# It also has a tendency to produce mature content without warning. \n\nThis model is tuned off of the base Llama-3-8B model. \n\nI adapted the leaked Undi dataset into training samples for custom formatting. This model pretty much only functions properly in SillyTavern. \n\nThe formatting has two pairs of pseudotokens\n\n\n\nThe self attention modules were fine tuned separately on this dataset and the pseudotokens were chosen because they made logical sense with respect to the character giving a reply without allowing the model to 'connect the dots' during training and figure out that it is indeed an AI language model.\n\nAfter this was done all modules were then finetuned together on the dendrite dataset in order to connect the changes made to the attention modules.\n\nSo with regards to building a SillyTavern prompt template you basically want the entire story string and any additional stylistic instructions enclosed in the [EGO] tags and then the user messages enclosed in [SEEN] tags. \n\nIt doesn't give particularly verbose replies unless you're continueing a roleplay with verbose messages. Otherwise it's pretty bad. \n\nGGUFs care of Qaunt Cartel" ]

[ "peft", "pytorch", "llama", "region:us" ]

[]

[]

[ "## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: False\n- bnb_4bit_compute_dtype: float16\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: False\n- bnb_4bit_compute_dtype: float16\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: False\n- bnb_4bit_compute_dtype: float16", "### Framework versions\n\n- PEFT 0.4.0\n- PEFT 0.4.0\n\n- PEFT 0.4.0" ]

[ "TAGS\n#peft #pytorch #llama #region-us \n", "## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: False\n- bnb_4bit_compute_dtype: float16\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: False\n- bnb_4bit_compute_dtype: float16\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: False\n- bnb_4bit_compute_dtype: float16", "### Framework versions\n\n- PEFT 0.4.0\n- PEFT 0.4.0\n\n- PEFT 0.4.0" ]

[ "peft", "tensorboard", "safetensors", "llama", "alignment-handbook", "trl", "sft", "generated_from_trainer", "dataset:HuggingFaceH4/ultrachat_200k", "base_model:meta-llama/Llama-2-7b-hf", "license:llama2", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 8\n* seed: 42\n* distributed\\_type: multi-GPU\n* num\\_devices: 4\n* gradient\\_accumulation\\_steps: 2\n* total\\_train\\_batch\\_size: 128\n* total\\_eval\\_batch\\_size: 32\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\n* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 1", "### Training results", "### Framework versions\n\n\n* PEFT 0.7.1\n* Transformers 4.39.0.dev0\n* Pytorch 2.1.2\n* Datasets 2.14.6\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #tensorboard #safetensors #llama #alignment-handbook #trl #sft #generated_from_trainer #dataset-HuggingFaceH4/ultrachat_200k #base_model-meta-llama/Llama-2-7b-hf #license-llama2 #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 8\n* seed: 42\n* distributed\\_type: multi-GPU\n* num\\_devices: 4\n* gradient\\_accumulation\\_steps: 2\n* total\\_train\\_batch\\_size: 128\n* total\\_eval\\_batch\\_size: 32\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\n* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 1", "### Training results", "### Framework versions\n\n\n* PEFT 0.7.1\n* Transformers 4.39.0.dev0\n* Pytorch 2.1.2\n* Datasets 2.14.6\n* Tokenizers 0.15.2" ]

[ "transformers", "safetensors", "whisper", "automatic-speech-recognition", "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 #whisper #automatic-speech-recognition #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", "mistral", "text-generation", "alignment-handbook", "generated_from_trainer", "trl", "dpo", "conversational", "dataset:updated", "dataset:original", "base_model:ShenaoZhang/0.001_ablation_4iters_bs128_nodpo_iter_3", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# 0.001_ablation_4iters_bs128_nodpo_iter_4\n\nThis model is a fine-tuned version of ShenaoZhang/0.001_ablation_4iters_bs128_nodpo_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: 2\n- total_train_batch_size: 128\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #alignment-handbook #generated_from_trainer #trl #dpo #conversational #dataset-updated #dataset-original #base_model-ShenaoZhang/0.001_ablation_4iters_bs128_nodpo_iter_3 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# 0.001_ablation_4iters_bs128_nodpo_iter_4\n\nThis model is a fine-tuned version of ShenaoZhang/0.001_ablation_4iters_bs128_nodpo_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: 2\n- total_train_batch_size: 128\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.15.2" ]

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

[]

[ "en" ]

[ "# Uploaded model\n\n- Developed by: hanifsyarubany10\n- License: apache-2.0\n- Finetuned from model : unsloth/gemma-7b-bnb-4bit\n\nThis gemma model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "TAGS\n#transformers #safetensors #text-generation-inference #unsloth #gemma #trl #en #base_model-unsloth/gemma-7b-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us \n", "# Uploaded model\n\n- Developed by: hanifsyarubany10\n- License: apache-2.0\n- Finetuned from model : unsloth/gemma-7b-bnb-4bit\n\nThis gemma model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "adapter-transformers", "dataset:trungtienluong/child-care-2.2", "arxiv:1910.09700", "license:apache-2.0", "region:us" ]

[ "1910.09700" ]

[]

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

[ "TAGS\n#adapter-transformers #dataset-trungtienluong/child-care-2.2 #arxiv-1910.09700 #license-apache-2.0 #region-us \n", "# Model Card for Model ID\n\n\n\nThis modelcard aims to be a base template for new models. It has been generated using this raw template.", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "gguf", "generated_from_trainer", "llama-cpp", "gguf-my-repo", "base_model:beomi/Llama-3-Open-Ko-8B-Instruct-preview", "license:other", "region:us" ]

[]

[]

[ "# sosoai/hansoldeco-beomi-Llama-3-Open-Ko-8B-Instruct-preview-pytorch-v0.1-Q4_0-GGUF\nThis model was converted to GGUF format from 'sosoai/hansoldeco-beomi-Llama-3-Open-Ko-8B-Instruct-preview-pytorch-v0.1' 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 #generated_from_trainer #llama-cpp #gguf-my-repo #base_model-beomi/Llama-3-Open-Ko-8B-Instruct-preview #license-other #region-us \n", "# sosoai/hansoldeco-beomi-Llama-3-Open-Ko-8B-Instruct-preview-pytorch-v0.1-Q4_0-GGUF\nThis model was converted to GGUF format from 'sosoai/hansoldeco-beomi-Llama-3-Open-Ko-8B-Instruct-preview-pytorch-v0.1' 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", "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", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]

[ "1910.09700" ]

[]

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

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

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

[]

[]

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

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

[ "mlx", "safetensors", "llama", "not-for-all-audiences", "nsfw", "license:cc-by-nc-4.0", "region:us" ]

[]

[]

[ "# mlx-community/Xwin-MLewd-13B-V0.2-4bit\nThis model was converted to MLX format from ['Undi95/Xwin-MLewd-13B-V0.2']().\nRefer to the original model card for more details on the model.", "## Use with mlx" ]

[ "TAGS\n#mlx #safetensors #llama #not-for-all-audiences #nsfw #license-cc-by-nc-4.0 #region-us \n", "# mlx-community/Xwin-MLewd-13B-V0.2-4bit\nThis model was converted to MLX format from ['Undi95/Xwin-MLewd-13B-V0.2']().\nRefer to the original model card for more details on the model.", "## Use with mlx" ]

[ "peft", "tensorboard", "safetensors", "trl", "sft", "generated_from_trainer", "dataset:generator", "base_model:distilbert/distilgpt2", "license:apache-2.0", "region:us" ]

[]

[]

[ "# Bevo-Budv1.1\n\nThis model is a fine-tuned version of distilbert/distilgpt2 on the generator dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 10", "### Training results", "### Framework versions\n\n- PEFT 0.7.0\n- Transformers 4.40.0\n- Pytorch 2.3.0+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-distilbert/distilgpt2 #license-apache-2.0 #region-us \n", "# Bevo-Budv1.1\n\nThis model is a fine-tuned version of distilbert/distilgpt2 on the generator dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 10", "### Training results", "### Framework versions\n\n- PEFT 0.7.0\n- Transformers 4.40.0\n- Pytorch 2.3.0+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

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

[ "1910.09700" ]

[]

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

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

[ "transformers", "tensorboard", "safetensors", "gpt2", "text-generation", "generated_from_trainer", "base_model:openai-community/gpt2", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# gpt2_test\n\nThis model is a fine-tuned version of openai-community/gpt2 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: 5e-05\n- train_batch_size: 4\n- eval_batch_size: 8\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 5", "### Training results", "### Framework versions\n\n- Transformers 4.39.0.dev0\n- Pytorch 2.2.1+cu118\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #tensorboard #safetensors #gpt2 #text-generation #generated_from_trainer #base_model-openai-community/gpt2 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# gpt2_test\n\nThis model is a fine-tuned version of openai-community/gpt2 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: 5e-05\n- train_batch_size: 4\n- eval_batch_size: 8\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 5", "### Training results", "### Framework versions\n\n- Transformers 4.39.0.dev0\n- Pytorch 2.2.1+cu118\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "license:mit", "region:us" ]

[]

[]

[ "### 模型说明", "#### 基于RWKV6-v2.1-3B 全新基模微调的nsfw语C模型", "#### 非常感谢<b style=\"color:red\">某不知名的神秘网友</b>提供的784条Claude超长上下文语料（单条长度超过120k），此模型也是基于该语料进行的实验性质微调", "#### 使用7k长上下文微调19epoch后loss为1.7得到的模型", "#### 因为超长上下文，继续微调应该还能提升效果，暂时只做测试，后续我会进行全面微调，敬请期待", "#### 效果如下：", "##### <b style=\"color:red\">注意：使用该模型需要自定义上文，以下演示回复模型输出的第一句到第二句都为手动定义</b>\n!image/png\n\n!image/png", "#### 神里绫华\n\n!image/png\n\n!image/png", "### 补充说明", "#### 因为此模型使用纯粹的nsfw多轮对话数据微调，生成会偏向nsfw，这是正常现象", "#### 此模型需要手动设定上文才能有良好表现，模型回复会与上文回复类似\n---", "#### 推荐如下格式使用模型（不需要设置角色名称，因为让模型以第三人称视角回复效果更好）", "### 推荐参数如下：", "#### Temperature=2-3之间", "#### Top_P=0.55-0.65之间", "#### Presence Penalty=0.4-0之间", "#### Frequency Penalty=0.8-1.2之间" ]

[ "TAGS\n#license-mit #region-us \n", "### 模型说明", "#### 基于RWKV6-v2.1-3B 全新基模微调的nsfw语C模型", "#### 非常感谢<b style=\"color:red\">某不知名的神秘网友</b>提供的784条Claude超长上下文语料（单条长度超过120k），此模型也是基于该语料进行的实验性质微调", "#### 使用7k长上下文微调19epoch后loss为1.7得到的模型", "#### 因为超长上下文，继续微调应该还能提升效果，暂时只做测试，后续我会进行全面微调，敬请期待", "#### 效果如下：", "##### <b style=\"color:red\">注意：使用该模型需要自定义上文，以下演示回复模型输出的第一句到第二句都为手动定义</b>\n!image/png\n\n!image/png", "#### 神里绫华\n\n!image/png\n\n!image/png", "### 补充说明", "#### 因为此模型使用纯粹的nsfw多轮对话数据微调，生成会偏向nsfw，这是正常现象", "#### 此模型需要手动设定上文才能有良好表现，模型回复会与上文回复类似\n---", "#### 推荐如下格式使用模型（不需要设置角色名称，因为让模型以第三人称视角回复效果更好）", "### 推荐参数如下：", "#### Temperature=2-3之间", "#### Top_P=0.55-0.65之间", "#### Presence Penalty=0.4-0之间", "#### Frequency Penalty=0.8-1.2之间" ]

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

[]

[]

[ "# sosoai/llama3-8b-16k-test-Q4_K_S-GGUF\nThis model was converted to GGUF format from 'sosoai/llama3-8b-16k-test' 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", "# sosoai/llama3-8b-16k-test-Q4_K_S-GGUF\nThis model was converted to GGUF format from 'sosoai/llama3-8b-16k-test' 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", "text-generation-inference", "unsloth", "llama", "trl", "en", "base_model:unsloth/llama-3-8b-bnb-4bit", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

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

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

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

[ "1910.09700" ]

[]

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

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

[ "transformers", "safetensors", "llama", "text-generation", "mergekit", "merge", "base_model:motherfucker0/zhun01", "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* motherfucker0/zhun01", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #mergekit #merge #base_model-motherfucker0/zhun01 #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* motherfucker0/zhun01", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "transformers", "safetensors", "llama", "text-generation", "trl", "sft", "generated_from_trainer", "conversational", "dataset:generator", "base_model:meta-llama/Llama-2-7b-chat-hf", "license:llama2", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# Llama-2-7b-chat-hf_fictional_arc_easy_english_v1\n\nThis model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on the generator dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 1\n- eval_batch_size: 2\n- seed: 42\n- gradient_accumulation_steps: 8\n- total_train_batch_size: 8\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 24", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.1.2\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #trl #sft #generated_from_trainer #conversational #dataset-generator #base_model-meta-llama/Llama-2-7b-chat-hf #license-llama2 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Llama-2-7b-chat-hf_fictional_arc_easy_english_v1\n\nThis model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on the generator dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 1\n- eval_batch_size: 2\n- seed: 42\n- gradient_accumulation_steps: 8\n- total_train_batch_size: 8\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 24", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.1.2\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "transformers", "tensorboard", "safetensors", "roberta", "text-classification", "generated_from_trainer", "base_model:vinai/bertweet-base", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "# taskA-base-model-0.0.0\n\nThis model is a fine-tuned version of vinai/bertweet-base on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- Loss: 1.2262\n- Accuracy: 0.7477\n- Precision: 0.4965\n- Recall: 0.6110\n- F1: 0.5478\n- Classification report: : precision recall f1-score support\n\nnot_sarcastic 0.86 0.79 0.82 1040\n sarcastic 0.50 0.61 0.55 347\n\n accuracy 0.75 1387\n macro avg 0.68 0.70 0.69 1387\n weighted avg 0.77 0.75 0.76 1387", "## 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: 8\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 5", "### 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 #roberta #text-classification #generated_from_trainer #base_model-vinai/bertweet-base #autotrain_compatible #endpoints_compatible #region-us \n", "# taskA-base-model-0.0.0\n\nThis model is a fine-tuned version of vinai/bertweet-base on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- Loss: 1.2262\n- Accuracy: 0.7477\n- Precision: 0.4965\n- Recall: 0.6110\n- F1: 0.5478\n- Classification report: : precision recall f1-score support\n\nnot_sarcastic 0.86 0.79 0.82 1040\n sarcastic 0.50 0.61 0.55 347\n\n accuracy 0.75 1387\n macro avg 0.68 0.70 0.69 1387\n weighted avg 0.77 0.75 0.76 1387", "## 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: 8\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 5", "### 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", "safetensors", "llama", "text-generation", "llama-3", "bagel", "conversational", "dataset:ai2_arc", "dataset:allenai/ultrafeedback_binarized_cleaned", "dataset:argilla/distilabel-intel-orca-dpo-pairs", "dataset:jondurbin/airoboros-3.2", "dataset:codeparrot/apps", "dataset:facebook/belebele", "dataset:bluemoon-fandom-1-1-rp-cleaned", "dataset:boolq", "dataset:camel-ai/biology", "dataset:camel-ai/chemistry", "dataset:camel-ai/math", "dataset:camel-ai/physics", "dataset:jondurbin/contextual-dpo-v0.1", "dataset:jondurbin/gutenberg-dpo-v0.1", "dataset:jondurbin/py-dpo-v0.1", "dataset:jondurbin/truthy-dpo-v0.1", "dataset:LDJnr/Capybara", "dataset:jondurbin/cinematika-v0.1", "dataset:WizardLM/WizardLM_evol_instruct_70k", "dataset:glaiveai/glaive-function-calling-v2", "dataset:grimulkan/LimaRP-augmented", "dataset:lmsys/lmsys-chat-1m", "dataset:ParisNeo/lollms_aware_dataset", "dataset:TIGER-Lab/MathInstruct", "dataset:Muennighoff/natural-instructions", "dataset:openbookqa", "dataset:kingbri/PIPPA-shareGPT", "dataset:piqa", "dataset:Vezora/Tested-22k-Python-Alpaca", "dataset:ropes", "dataset:cakiki/rosetta-code", "dataset:Open-Orca/SlimOrca", "dataset:b-mc2/sql-create-context", "dataset:squad_v2", "dataset:mattpscott/airoboros-summarization", "dataset:migtissera/Synthia-v1.3", "dataset:unalignment/toxic-dpo-v0.2", "dataset:WhiteRabbitNeo/WRN-Chapter-1", "dataset:WhiteRabbitNeo/WRN-Chapter-2", "dataset:winogrande", "base_model:meta-llama/Meta-Llama-3-8B", "license:other", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]

[]

[]

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

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

[ "transformers", "safetensors", "llama", "text-generation", "merge", "mergekit", "lazymergekit", "hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode", "Orenguteng/Lexi-Llama-3-8B-Uncensored", "NousResearch/Meta-Llama-3-8B", "NousResearch/Meta-Llama-3-8B-Instruct", "conversational", "base_model:hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode", "base_model:Orenguteng/Lexi-Llama-3-8B-Uncensored", "base_model:NousResearch/Meta-Llama-3-8B", "base_model:NousResearch/Meta-Llama-3-8B-Instruct", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# Meta-Llama-3-8b-Lexi-Uninstruct-function-calling-json-mode-Task-Arithmetic-v0.1\n\nMeta-Llama-3-8b-Lexi-Uninstruct-function-calling-json-mode-Task-Arithmetic-v0.1 is a merge of the following models using LazyMergekit:\n* hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode\n* Orenguteng/Lexi-Llama-3-8B-Uncensored\n* NousResearch/Meta-Llama-3-8B\n* NousResearch/Meta-Llama-3-8B-Instruct", "## Configuration", "## Usage" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #merge #mergekit #lazymergekit #hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode #Orenguteng/Lexi-Llama-3-8B-Uncensored #NousResearch/Meta-Llama-3-8B #NousResearch/Meta-Llama-3-8B-Instruct #conversational #base_model-hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode #base_model-Orenguteng/Lexi-Llama-3-8B-Uncensored #base_model-NousResearch/Meta-Llama-3-8B #base_model-NousResearch/Meta-Llama-3-8B-Instruct #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Meta-Llama-3-8b-Lexi-Uninstruct-function-calling-json-mode-Task-Arithmetic-v0.1\n\nMeta-Llama-3-8b-Lexi-Uninstruct-function-calling-json-mode-Task-Arithmetic-v0.1 is a merge of the following models using LazyMergekit:\n* hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode\n* Orenguteng/Lexi-Llama-3-8B-Uncensored\n* NousResearch/Meta-Llama-3-8B\n* NousResearch/Meta-Llama-3-8B-Instruct", "## Configuration", "## Usage" ]

[ "transformers", "safetensors", "opt", "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 #opt #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" ]

[ "transformers", "safetensors", "llama", "text-generation", "text-generation-inference", "unsloth", "trl", "sft", "Roleplay", "roleplay", "en", "base_model:Sao10K/Fimbulvetr-11B-v2", "license:cc-by-nc-4.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[ "# About this model\n\nThis model can handle (limited) TSF content. If you Character Card have complex plot, maybe you should try other model (maybe bigger parameter?).\n\n- Early stop version of URL , expect to no overfitting when finetune, maybe good ? \n\nDo you know TSF, TS, TG? A lot of model don't really know about that, so I do some experiment to finetune TSF dataset.\n\n- Finetuned with Chinese Novels dataset, to increase the accuracy in TSF theme, which is not quite popular.\n (R18 dataset). You should include chinese/japanese word about tag you want(search it in pixiv) in your character card to trigger it.\n This finetune idea is suitable for Chinese Roleplay than English (Becaue I could only find good Chinese datasets about it , it is nice that if you can open a discussion about English TSF datasets). But it still affect the models writing styles, so maybe less GPT-like response in both Chinese and English?.\n- Finetuned from model : Sao10K/Fimbulvetr-11B-v2 . Thank Sao10K a lot :)", "## 8k Context Length BTW, the original Fimbulvetr and Solar have only 4k context length, so I extended it .", "## GGUF version? here is it.", "## Dataset\nAll chinese novels dataset", "# Thank Unsloth for good finetuning tool. This mistral 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 #Roleplay #roleplay #en #base_model-Sao10K/Fimbulvetr-11B-v2 #license-cc-by-nc-4.0 #autotrain_compatible #endpoints_compatible #region-us \n", "# About this model\n\nThis model can handle (limited) TSF content. If you Character Card have complex plot, maybe you should try other model (maybe bigger parameter?).\n\n- Early stop version of URL , expect to no overfitting when finetune, maybe good ? \n\nDo you know TSF, TS, TG? A lot of model don't really know about that, so I do some experiment to finetune TSF dataset.\n\n- Finetuned with Chinese Novels dataset, to increase the accuracy in TSF theme, which is not quite popular.\n (R18 dataset). You should include chinese/japanese word about tag you want(search it in pixiv) in your character card to trigger it.\n This finetune idea is suitable for Chinese Roleplay than English (Becaue I could only find good Chinese datasets about it , it is nice that if you can open a discussion about English TSF datasets). But it still affect the models writing styles, so maybe less GPT-like response in both Chinese and English?.\n- Finetuned from model : Sao10K/Fimbulvetr-11B-v2 . Thank Sao10K a lot :)", "## 8k Context Length BTW, the original Fimbulvetr and Solar have only 4k context length, so I extended it .", "## GGUF version? here is it.", "## Dataset\nAll chinese novels dataset", "# Thank Unsloth for good finetuning tool. This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "sample-factory", "tensorboard", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]

[]

[]

[ "## Downloading the model\n\nAfter installing Sample-Factory, download the model with:", "## Using the model\n\nTo run the model after download, use the 'enjoy' script corresponding to this environment:\n\n\n\nYou can also upload models to the Hugging Face Hub using the same script with the '--push_to_hub' flag.\nSee URL for more details", "## Training with this model\n\nTo continue training with this model, use the 'train' script corresponding to this environment:\n\n\nNote, you may have to adjust '--train_for_env_steps' to a suitably high number as the experiment will resume at the number of steps it concluded at." ]

[ "TAGS\n#sample-factory #tensorboard #deep-reinforcement-learning #reinforcement-learning #model-index #region-us \n", "## Downloading the model\n\nAfter installing Sample-Factory, download the model with:", "## Using the model\n\nTo run the model after download, use the 'enjoy' script corresponding to this environment:\n\n\n\nYou can also upload models to the Hugging Face Hub using the same script with the '--push_to_hub' flag.\nSee URL for more details", "## Training with this model\n\nTo continue training with this model, use the 'train' script corresponding to this environment:\n\n\nNote, you may have to adjust '--train_for_env_steps' to a suitably high number as the experiment will resume at the number of steps it concluded at." ]

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

[ "1910.09700" ]

[]

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

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

[ "transformers", "tensorboard", "safetensors", "roberta", "text-generation", "generated_from_trainer", "base_model:microsoft/codebert-base", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 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 #roberta #text-generation #generated_from_trainer #base_model-microsoft/codebert-base #autotrain_compatible #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 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" ]

[ "transformers", "gguf", "en", "dataset:cognitivecomputations/Dolphin-2.9", "dataset:teknium/OpenHermes-2.5", "dataset:m-a-p/CodeFeedback-Filtered-Instruction", "dataset:cognitivecomputations/dolphin-coder", "dataset:cognitivecomputations/samantha-data", "dataset:HuggingFaceH4/ultrachat_200k", "dataset:microsoft/orca-math-word-problems-200k", "dataset:abacusai/SystemChat-1.1", "dataset:Locutusque/function-calling-chatml", "dataset:internlm/Agent-FLAN", "base_model:cognitivecomputations/dolphin-2.9-llama3-70b", "license:llama3", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #en #dataset-cognitivecomputations/Dolphin-2.9 #dataset-teknium/OpenHermes-2.5 #dataset-m-a-p/CodeFeedback-Filtered-Instruction #dataset-cognitivecomputations/dolphin-coder #dataset-cognitivecomputations/samantha-data #dataset-HuggingFaceH4/ultrachat_200k #dataset-microsoft/orca-math-word-problems-200k #dataset-abacusai/SystemChat-1.1 #dataset-Locutusque/function-calling-chatml #dataset-internlm/Agent-FLAN #base_model-cognitivecomputations/dolphin-2.9-llama3-70b #license-llama3 #endpoints_compatible #region-us \n" ]

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

[ "1910.09700" ]

[]

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

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

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

[ "1910.09700" ]

[]

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

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

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

[]

[]

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

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

[ "transformers", "safetensors", "mini_gemini_qwen2", "text-generation", "vlm", "MLLM", "Multi-Modal LLM", "conversational", "zh", "dataset:HuggingFaceFW/fineweb", "dataset:YanweiLi/MGM-Instruction", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[ "zh" ]

[ "### Surpassed Close-Source Models: A Breakthrough in Open-Source Advancements\n\n\n\n weights [|](URL | <a href=) \n\n\nAs the result suggested, Bumblebee might be one of the most capable Chinese MLLM opensourced as for now.\n\n\nIt shows good abilities at:\n\n\n* OCR understanding;\n* Reasoning;\n* Table and Graphic comprehension;\n* Math calculate;\n\n\nIf want try it, just download our weights and inference via MGM!\n\n\nFuture Plan\n-----------\n\n\nBumblebee is just the first model release aimed at catching up closed-source models. While it is capable of performing many tasks, it has not yet surpassed closed models by a significant margin.\n\n\nIn our pursuit of advancement, we are currently developing even more advanced technologies that will surpass the current state-of-the-art multimodal models. The path we are paving includes:\n\n\n* Video and long sequences support, which is our ultimate goal;\n* The development of a specialized model that works exclusively with documents, incorporating some innovative techniques.\n* Hopefully we can make a new Optimus Prime model in the near future.\n\n\nIf you were interested in the new progress, please star and watch this repo!" ]

[ "TAGS\n#transformers #safetensors #mini_gemini_qwen2 #text-generation #vlm #MLLM #Multi-Modal LLM #conversational #zh #dataset-HuggingFaceFW/fineweb #dataset-YanweiLi/MGM-Instruction #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "### Surpassed Close-Source Models: A Breakthrough in Open-Source Advancements\n\n\n\n weights [|](URL | <a href=) \n\n\nAs the result suggested, Bumblebee might be one of the most capable Chinese MLLM opensourced as for now.\n\n\nIt shows good abilities at:\n\n\n* OCR understanding;\n* Reasoning;\n* Table and Graphic comprehension;\n* Math calculate;\n\n\nIf want try it, just download our weights and inference via MGM!\n\n\nFuture Plan\n-----------\n\n\nBumblebee is just the first model release aimed at catching up closed-source models. While it is capable of performing many tasks, it has not yet surpassed closed models by a significant margin.\n\n\nIn our pursuit of advancement, we are currently developing even more advanced technologies that will surpass the current state-of-the-art multimodal models. The path we are paving includes:\n\n\n* Video and long sequences support, which is our ultimate goal;\n* The development of a specialized model that works exclusively with documents, incorporating some innovative techniques.\n* Hopefully we can make a new Optimus Prime model in the near future.\n\n\nIf you were interested in the new progress, please star and watch this repo!" ]

[ "transformers", "safetensors", "llama", "text-generation", "mergekit", "merge", "base_model:motherfucker0/zhun01", "base_model:motherfucker0/zhun02", "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* motherfucker0/zhun01\n* motherfucker0/zhun02", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #mergekit #merge #base_model-motherfucker0/zhun01 #base_model-motherfucker0/zhun02 #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* motherfucker0/zhun01\n* motherfucker0/zhun02", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "transformers", "safetensors", "qwen2", "text-generation", "pretrained", "conversational", "en", "license:other", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[ "en" ]

[ "# Qwen1.5-110B", "## Introduction\n\nQwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data. In comparison with the previous released Qwen, the improvements include:\n\n* 9 model sizes, including 0.5B, 1.8B, 4B, 7B, 14B, 32B, 72B, and 110B dense models, and an MoE model of 14B with 2.7B activated;\n* Significant performance improvement in Chat models;\n* Multilingual support of both base and chat models;\n* Stable support of 32K context length for models of all sizes\n* No need of 'trust_remote_code'.\n\nFor more details, please refer to our blog post and GitHub repo.", "## Model Details\nQwen1.5 is a language model series including decoder language models of different model sizes. For each size, we release the base language model and the aligned chat model. It is based on the Transformer architecture with SwiGLU activation, attention QKV bias, group query attention, mixture of sliding window attention and full attention, etc. Additionally, we have an improved tokenizer adaptive to multiple natural languages and codes. For the beta version, temporarily we did not include GQA (except for 32B and 110B) and the mixture of SWA and full attention.", "## Requirements\nThe code of Qwen1.5 has been in the latest Hugging face transformers and we advise you to install 'transformers>=4.37.0', or you might encounter the following error:", "## Usage\n\nWe do not advise you to use base language models for text generation. Instead, you can apply post-training, e.g., SFT, RLHF, continued pretraining, etc., on this model.\n\n\nIf you find our work helpful, feel free to give us a cite." ]

[ "TAGS\n#transformers #safetensors #qwen2 #text-generation #pretrained #conversational #en #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Qwen1.5-110B", "## Introduction\n\nQwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data. In comparison with the previous released Qwen, the improvements include:\n\n* 9 model sizes, including 0.5B, 1.8B, 4B, 7B, 14B, 32B, 72B, and 110B dense models, and an MoE model of 14B with 2.7B activated;\n* Significant performance improvement in Chat models;\n* Multilingual support of both base and chat models;\n* Stable support of 32K context length for models of all sizes\n* No need of 'trust_remote_code'.\n\nFor more details, please refer to our blog post and GitHub repo.", "## Model Details\nQwen1.5 is a language model series including decoder language models of different model sizes. For each size, we release the base language model and the aligned chat model. It is based on the Transformer architecture with SwiGLU activation, attention QKV bias, group query attention, mixture of sliding window attention and full attention, etc. Additionally, we have an improved tokenizer adaptive to multiple natural languages and codes. For the beta version, temporarily we did not include GQA (except for 32B and 110B) and the mixture of SWA and full attention.", "## Requirements\nThe code of Qwen1.5 has been in the latest Hugging face transformers and we advise you to install 'transformers>=4.37.0', or you might encounter the following error:", "## Usage\n\nWe do not advise you to use base language models for text generation. Instead, you can apply post-training, e.g., SFT, RLHF, continued pretraining, etc., on this model.\n\n\nIf you find our work helpful, feel free to give us a cite." ]

[ "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" ]