Datasets:

---

ftopal

/

huggingface-models

like 0

[ "transformers", "pytorch", "vision-encoder-decoder", "generated_from_trainer", "dataset:imagefolder", "license:mit", "endpoints_compatible", "region:us" ]

[]

[]

[ "# DonutProcessor_Detail\n\nThis model is a fine-tuned version of naver-clova-ix/donut-base on the imagefolder dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 2e-05\n- train_batch_size: 2\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 4.30.2\n- Pytorch 1.13.1\n- Datasets 2.13.2\n- Tokenizers 0.13.3" ]

[ "TAGS\n#transformers #pytorch #vision-encoder-decoder #generated_from_trainer #dataset-imagefolder #license-mit #endpoints_compatible #region-us \n", "# DonutProcessor_Detail\n\nThis model is a fine-tuned version of naver-clova-ix/donut-base on the imagefolder dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 2e-05\n- train_batch_size: 2\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 4.30.2\n- Pytorch 1.13.1\n- Datasets 2.13.2\n- Tokenizers 0.13.3" ]

[ "gguf", "text-generation", "en", "zh", "base_model:UnicomLLM/Unichat-llama3-Chinese-8B", "license:apache-2.0", "region:us" ]

[]

[ "en", "zh" ]

[ "# Unichat-llama3-Chinese-8B- GGUF\n- This is quantized version of UnicomLLM/Unichat-llama3-Chinese-8B", "# Model Description (Translated)\n\n- China Unicom AI Innovation Center released the industry's first llama3 Chinese instruction fine-tuning model (full parameter fine-tuning), uploaded at 22:00 on April 19, 2024\n- This model is based on Meta Llama 3 , adds Chinese data for training, and achieves high-quality Chinese question and answer using the llama3 model.\n- The model context maintains the native length of 8K, and a version that supports 64K length will be released later.\n- Base model Meta-Llama-3-8B", "### Data\n\n- High-quality instruction data, covering multiple fields and industries, providing sufficient data support for model training\n- Fine-tuning instruction data undergoes strict manual screening to ensure high-quality instruction data is used for model fine-tuning.\n\nFor more details on models, datasets and training please refer to:\n* Github：Unichat-llama3-Chinese" ]

[ "TAGS\n#gguf #text-generation #en #zh #base_model-UnicomLLM/Unichat-llama3-Chinese-8B #license-apache-2.0 #region-us \n", "# Unichat-llama3-Chinese-8B- GGUF\n- This is quantized version of UnicomLLM/Unichat-llama3-Chinese-8B", "# Model Description (Translated)\n\n- China Unicom AI Innovation Center released the industry's first llama3 Chinese instruction fine-tuning model (full parameter fine-tuning), uploaded at 22:00 on April 19, 2024\n- This model is based on Meta Llama 3 , adds Chinese data for training, and achieves high-quality Chinese question and answer using the llama3 model.\n- The model context maintains the native length of 8K, and a version that supports 64K length will be released later.\n- Base model Meta-Llama-3-8B", "### Data\n\n- High-quality instruction data, covering multiple fields and industries, providing sufficient data support for model training\n- Fine-tuning instruction data undergoes strict manual screening to ensure high-quality instruction data is used for model fine-tuning.\n\nFor more details on models, datasets and training please refer to:\n* Github：Unichat-llama3-Chinese" ]

[ "transformers", "safetensors", "mistral", "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 #mistral #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" ]

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

[]

[]

[ "# LoRA text2image fine-tuning - azhang42/onepiece-lora\nThese are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were fine-tuned on the YaYaB/onepiece-blip-captions dataset. You can find some example images in the following. \n\n!img_0\n!img_1\n!img_2\n!img_3", "## Intended uses & limitations", "#### How to use", "#### Limitations and bias\n\n[TODO: provide examples of latent issues and potential remediations]", "## Training details\n\n[TODO: describe the data used to train the model]" ]

[ "TAGS\n#diffusers #safetensors #stable-diffusion #stable-diffusion-diffusers #text-to-image #diffusers-training #lora #base_model-runwayml/stable-diffusion-v1-5 #license-creativeml-openrail-m #region-us \n", "# LoRA text2image fine-tuning - azhang42/onepiece-lora\nThese are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were fine-tuned on the YaYaB/onepiece-blip-captions dataset. You can find some example images in the following. \n\n!img_0\n!img_1\n!img_2\n!img_3", "## Intended uses & limitations", "#### How to use", "#### Limitations and bias\n\n[TODO: provide examples of latent issues and potential remediations]", "## Training details\n\n[TODO: describe the data used to train the model]" ]

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

[]

[]

[ "# poca Agent playing SoccerTwos\n This is a trained model of a poca agent playing SoccerTwos\n using the Unity ML-Agents Library.\n\n ## Usage (with ML-Agents)\n The Documentation: URL\n\n We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:\n - A *short tutorial* where you teach Huggy the Dog to fetch the stick and then play with him directly in your\n browser: URL\n - A *longer tutorial* to understand how works ML-Agents:\n URL\n\n ### Resume the training\n \n\n ### Watch your Agent play\n You can watch your agent playing directly in your browser\n\n 1. If the environment is part of ML-Agents official environments, go to URL\n 2. Step 1: Find your model_id: phoenixaiden33/poca-SoccerTwos\n 3. Step 2: Select your *.nn /*.onnx file\n 4. Click on Watch the agent play" ]

[ "TAGS\n#ml-agents #tensorboard #onnx #SoccerTwos #deep-reinforcement-learning #reinforcement-learning #ML-Agents-SoccerTwos #region-us \n", "# poca Agent playing SoccerTwos\n This is a trained model of a poca agent playing SoccerTwos\n using the Unity ML-Agents Library.\n\n ## Usage (with ML-Agents)\n The Documentation: URL\n\n We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:\n - A *short tutorial* where you teach Huggy the Dog to fetch the stick and then play with him directly in your\n browser: URL\n - A *longer tutorial* to understand how works ML-Agents:\n URL\n\n ### Resume the training\n \n\n ### Watch your Agent play\n You can watch your agent playing directly in your browser\n\n 1. If the environment is part of ML-Agents official environments, go to URL\n 2. Step 1: Find your model_id: phoenixaiden33/poca-SoccerTwos\n 3. Step 2: Select your *.nn /*.onnx file\n 4. Click on Watch the agent play" ]

[ "transformers", "pytorch", "llama", "text-generation", "conversational", "dataset:kenshinx/netlab-blogs", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[]

[ "TAGS\n#transformers #pytorch #llama #text-generation #conversational #dataset-kenshinx/netlab-blogs #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n" ]

[ "safetensors", "generated_from_trainer", "base_model:HuggingFaceM4/idefics2-8b", "license:apache-2.0", "region:us" ]

[]

[]

[ "# working\n\nThis model is a fine-tuned version of HuggingFaceM4/idefics2-8b on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0001\n- train_batch_size: 2\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 8\n- total_train_batch_size: 16\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- lr_scheduler_warmup_steps: 10\n- num_epochs: 2\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.41.0.dev0\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.19.1" ]

[ "TAGS\n#safetensors #generated_from_trainer #base_model-HuggingFaceM4/idefics2-8b #license-apache-2.0 #region-us \n", "# working\n\nThis model is a fine-tuned version of HuggingFaceM4/idefics2-8b on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0001\n- train_batch_size: 2\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 8\n- total_train_batch_size: 16\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- lr_scheduler_warmup_steps: 10\n- num_epochs: 2\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.41.0.dev0\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.19.1" ]

[ "peft", "safetensors", "trl", "reward-trainer", "generated_from_trainer", "base_model:google/gemma-2b", "license:gemma", "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-google/gemma-2b #license-gemma #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", "gguf", "en", "dataset:Azure99/blossom-chat-v1", "dataset:Azure99/blossom-math-v2", "dataset:Azure99/blossom-wizard-v1", "dataset:Azure99/blossom-orca-v1", "base_model:Azure99/blossom-v3_1-yi-34b", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #en #dataset-Azure99/blossom-chat-v1 #dataset-Azure99/blossom-math-v2 #dataset-Azure99/blossom-wizard-v1 #dataset-Azure99/blossom-orca-v1 #base_model-Azure99/blossom-v3_1-yi-34b #license-apache-2.0 #endpoints_compatible #region-us \n" ]

[ "transformers", "gguf", "en", "base_model:camel-ai/CAMEL-33B-Combined-Data", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #en #base_model-camel-ai/CAMEL-33B-Combined-Data #endpoints_compatible #region-us \n" ]

[ "transformers", "gguf", "en", "base_model:rafaeloc15/Beyondrisk-Llama3-8B-FT", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #en #base_model-rafaeloc15/Beyondrisk-Llama3-8B-FT #endpoints_compatible #region-us \n" ]

[ "transformers", "safetensors", "llama", "text-generation", "merge", "roleplay", "exl2", "not-for-all-audiences", "license:other", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# Merged-Vicuna-RP-Stew-34B\n\nQuantized 4.65 exl2 of the model down below:\n\nURL\n\nSpecialized parquet used:\n\nURL", "## Merge Details\n\nIt's like RP Stew V2, but slightly different. Joint venture between me and MarinaraSpaghetti in trying to get context slightly longer in reach, while also lowering the flowery prose a tad that some users seemed to of had a problem with. Main difference? Just swapped Nontoxic-PiVoT-Bagel and Nyakura-CausalLM-RP's percentages in the recipe.", "### Settings\n\nTemperature @ 0.8\n\nMin-P @ 0.01\n\nTypical-P @ 0.95\n\nRepetition Penalty @ 1.07\n\nRepetition Range @ 4096\n\nSmoothing Factor @ 0.3\n\nEverything else @ off\n\nEarly Stopping = X\n\nDo Sample = \n\nAdd BOS Token = X\n\nBan EOS Token = \n\nSkip Special Tokens = X\n\nTemperature Last = \n\nCustom Stopping Strings: \"<|im_end|>\", \"< / s >\" (<---without spaces)", "### Prompt Format: Chat-Vicuna", "### Models Merged\n\nThe following models were included in the merge:\n\nURL\n\nURL\n\nURL\n\nURL\n\nURL\n\nURL\n\nURL", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #merge #roleplay #exl2 #not-for-all-audiences #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Merged-Vicuna-RP-Stew-34B\n\nQuantized 4.65 exl2 of the model down below:\n\nURL\n\nSpecialized parquet used:\n\nURL", "## Merge Details\n\nIt's like RP Stew V2, but slightly different. Joint venture between me and MarinaraSpaghetti in trying to get context slightly longer in reach, while also lowering the flowery prose a tad that some users seemed to of had a problem with. Main difference? Just swapped Nontoxic-PiVoT-Bagel and Nyakura-CausalLM-RP's percentages in the recipe.", "### Settings\n\nTemperature @ 0.8\n\nMin-P @ 0.01\n\nTypical-P @ 0.95\n\nRepetition Penalty @ 1.07\n\nRepetition Range @ 4096\n\nSmoothing Factor @ 0.3\n\nEverything else @ off\n\nEarly Stopping = X\n\nDo Sample = \n\nAdd BOS Token = X\n\nBan EOS Token = \n\nSkip Special Tokens = X\n\nTemperature Last = \n\nCustom Stopping Strings: \"<|im_end|>\", \"< / s >\" (<---without spaces)", "### Prompt Format: Chat-Vicuna", "### Models Merged\n\nThe following models were included in the merge:\n\nURL\n\nURL\n\nURL\n\nURL\n\nURL\n\nURL\n\nURL", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "transformers", "gguf", "en", "dataset:lemonilia/LimaRP", "dataset:grimulkan/theory-of-mind", "dataset:Epiculous/Gnosis", "base_model:Epiculous/Crunchy-onion", "license:agpl-3.0", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #en #dataset-lemonilia/LimaRP #dataset-grimulkan/theory-of-mind #dataset-Epiculous/Gnosis #base_model-Epiculous/Crunchy-onion #license-agpl-3.0 #endpoints_compatible #region-us \n" ]

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

[ "1910.09700" ]

[]

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

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

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

[]

[]

[ "# robust_llm_pythia-31m_mz-130_PasswordMatch_n-its-10-seed-4\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: 4\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.1\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #tensorboard #safetensors #gpt_neox #text-classification #generated_from_trainer #base_model-EleutherAI/pythia-31m #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# robust_llm_pythia-31m_mz-130_PasswordMatch_n-its-10-seed-4\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: 4\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.1\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

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

[]

[]

[ "# robust_llm_pythia-31m_mz-130_PasswordMatch_n-its-10-seed-3\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: 3\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.1\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #tensorboard #safetensors #gpt_neox #text-classification #generated_from_trainer #base_model-EleutherAI/pythia-31m #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# robust_llm_pythia-31m_mz-130_PasswordMatch_n-its-10-seed-3\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: 3\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.1\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "transformers", "gpt_neox", "text-generation", "en", "dataset:togethercomputer/RedPajama-Data-1T", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[ "en" ]

[ "# RedPajama-INCITE-7B-Base\n\nRedPajama-INCITE-7B-Base was developed by Together and leaders from the open-source AI community including URL, ETH DS3Lab, AAI CERC, Université de Montréal, MILA - Québec AI Institute, Stanford Center for Research on Foundation Models (CRFM), Stanford Hazy Research research group and LAION. \nThe training was done on 3,072 V100 GPUs provided as part of the INCITE 2023 project on Scalable Foundation Models for Transferrable Generalist AI, awarded to MILA, LAION, and EleutherAI in fall 2022, with support from the Oak Ridge Leadership Computing Facility (OLCF) and INCITE program. \n\n - Base Model: RedPajama-INCITE-7B-Base\n - Instruction-tuned Version: RedPajama-INCITE-7B-Instruct\n - Chat Version: RedPajama-INCITE-7B-Chat", "## Model Details\n- Developed by: Together Computer.\n- Model type: Language Model\n- Language(s): English\n- License: Apache 2.0\n- Model Description: A 6.9B parameter pretrained language model.", "# Quick Start\n\nPlease note that the model requires 'transformers' version >= 4.25.1.", "## GPU Inference\n\nThis requires a GPU with 16GB memory.", "## GPU Inference in Int8\n\nThis requires a GPU with 12GB memory.\n\nTo run inference with int8, please ensure you have installed accelerate and bitandbytes. You can install them with the following command:\n\n\n\nThen you can run inference with int8 as follows:", "## CPU Inference\n\n\n\nPlease note that since 'LayerNormKernelImpl' is not implemented in fp16 for CPU, we use 'bfloat16' for CPU inference.", "# Uses", "## Direct Use \n\nExcluded uses are described below.", "### Misuse, Malicious Use, and Out-of-Scope Use\n\nIt is the responsibility of the end user to ensure that the model is used in a responsible and ethical manner.", "#### Out-of-Scope Use\n\n'RedPajama-INCITE-7B-Base' is a language model and may not perform well for other use cases outside of its intended scope. \nFor example, it may not be suitable for use in safety-critical applications or for making decisions that have a significant impact on individuals or society. \nIt is important to consider the limitations of the model and to only use it for its intended purpose.", "#### Misuse and Malicious Use\n\n'RedPajama-INCITE-7B-Base' is designed for language modeling.\nMisuse of the model, such as using it to engage in illegal or unethical activities, is strictly prohibited and goes against the principles of the project.\n\nUsing the model to generate content that is cruel to individuals is a misuse of this model. This includes, but is not limited to:\n\n- Generating fake news, misinformation, or propaganda\n- Promoting hate speech, discrimination, or violence against individuals or groups\n- Impersonating individuals or organizations without their consent\n- Engaging in cyberbullying or harassment\n- Defamatory content\n- Spamming or scamming\n- Sharing confidential or sensitive information without proper authorization\n- Violating the terms of use of the model or the data used to train it\n- Creating automated bots for malicious purposes such as spreading malware, phishing scams, or spamming", "## Limitations\n\n'RedPajama-INCITE-7B-Base', like other language models, has limitations that should be taken into consideration. \nFor example, the model may not always provide accurate or relevant answers, particularly for questions that are complex, ambiguous, or outside of its training data. \nWe therefore welcome contributions from individuals and organizations, and encourage collaboration towards creating a more robust and inclusive chatbot.", "## Training\n\nTraining Data\n\nPlease refer to togethercomputer/RedPajama-Data-1T\n\nTraining Procedure\n\n- Hardware: 512 nodes of 6xV100 (IBM Power9), on the OLCF Summit cluster\n- Optimizer: Apex FusedAdam\n- Parallelism: Pipeline parallel 12, tensor parallel 2\n- Gradient Accumulations: 8 (global batch size 4M tokens)\n- Num of Tokens: 1.001T Tokens\n- Learning rate: 0.00012", "## Benchmark\n\nPlease refer to our blog post for benchmark results.", "## Intermediate Checkpoints\n\nWe provide 11 intermediate checkpoints that have been released for study.\nThe checkpoints are organized based on the number of tokens they contain, ranging from 240 billion tokens to 1 trillion tokens.\n\n- 240b_tokens\n- 280b_tokens\n- 400b_tokens\n- 440b_tokens\n- 500b_tokens\n- 600b_tokens\n- 700b_tokens\n- 720b_tokens\n- 960b_tokens\n- 1t_tokens\n- latest", "## Community\n\nJoin us on Together Discord" ]

[ "TAGS\n#transformers #gpt_neox #text-generation #en #dataset-togethercomputer/RedPajama-Data-1T #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# RedPajama-INCITE-7B-Base\n\nRedPajama-INCITE-7B-Base was developed by Together and leaders from the open-source AI community including URL, ETH DS3Lab, AAI CERC, Université de Montréal, MILA - Québec AI Institute, Stanford Center for Research on Foundation Models (CRFM), Stanford Hazy Research research group and LAION. \nThe training was done on 3,072 V100 GPUs provided as part of the INCITE 2023 project on Scalable Foundation Models for Transferrable Generalist AI, awarded to MILA, LAION, and EleutherAI in fall 2022, with support from the Oak Ridge Leadership Computing Facility (OLCF) and INCITE program. \n\n - Base Model: RedPajama-INCITE-7B-Base\n - Instruction-tuned Version: RedPajama-INCITE-7B-Instruct\n - Chat Version: RedPajama-INCITE-7B-Chat", "## Model Details\n- Developed by: Together Computer.\n- Model type: Language Model\n- Language(s): English\n- License: Apache 2.0\n- Model Description: A 6.9B parameter pretrained language model.", "# Quick Start\n\nPlease note that the model requires 'transformers' version >= 4.25.1.", "## GPU Inference\n\nThis requires a GPU with 16GB memory.", "## GPU Inference in Int8\n\nThis requires a GPU with 12GB memory.\n\nTo run inference with int8, please ensure you have installed accelerate and bitandbytes. You can install them with the following command:\n\n\n\nThen you can run inference with int8 as follows:", "## CPU Inference\n\n\n\nPlease note that since 'LayerNormKernelImpl' is not implemented in fp16 for CPU, we use 'bfloat16' for CPU inference.", "# Uses", "## Direct Use \n\nExcluded uses are described below.", "### Misuse, Malicious Use, and Out-of-Scope Use\n\nIt is the responsibility of the end user to ensure that the model is used in a responsible and ethical manner.", "#### Out-of-Scope Use\n\n'RedPajama-INCITE-7B-Base' is a language model and may not perform well for other use cases outside of its intended scope. \nFor example, it may not be suitable for use in safety-critical applications or for making decisions that have a significant impact on individuals or society. \nIt is important to consider the limitations of the model and to only use it for its intended purpose.", "#### Misuse and Malicious Use\n\n'RedPajama-INCITE-7B-Base' is designed for language modeling.\nMisuse of the model, such as using it to engage in illegal or unethical activities, is strictly prohibited and goes against the principles of the project.\n\nUsing the model to generate content that is cruel to individuals is a misuse of this model. This includes, but is not limited to:\n\n- Generating fake news, misinformation, or propaganda\n- Promoting hate speech, discrimination, or violence against individuals or groups\n- Impersonating individuals or organizations without their consent\n- Engaging in cyberbullying or harassment\n- Defamatory content\n- Spamming or scamming\n- Sharing confidential or sensitive information without proper authorization\n- Violating the terms of use of the model or the data used to train it\n- Creating automated bots for malicious purposes such as spreading malware, phishing scams, or spamming", "## Limitations\n\n'RedPajama-INCITE-7B-Base', like other language models, has limitations that should be taken into consideration. \nFor example, the model may not always provide accurate or relevant answers, particularly for questions that are complex, ambiguous, or outside of its training data. \nWe therefore welcome contributions from individuals and organizations, and encourage collaboration towards creating a more robust and inclusive chatbot.", "## Training\n\nTraining Data\n\nPlease refer to togethercomputer/RedPajama-Data-1T\n\nTraining Procedure\n\n- Hardware: 512 nodes of 6xV100 (IBM Power9), on the OLCF Summit cluster\n- Optimizer: Apex FusedAdam\n- Parallelism: Pipeline parallel 12, tensor parallel 2\n- Gradient Accumulations: 8 (global batch size 4M tokens)\n- Num of Tokens: 1.001T Tokens\n- Learning rate: 0.00012", "## Benchmark\n\nPlease refer to our blog post for benchmark results.", "## Intermediate Checkpoints\n\nWe provide 11 intermediate checkpoints that have been released for study.\nThe checkpoints are organized based on the number of tokens they contain, ranging from 240 billion tokens to 1 trillion tokens.\n\n- 240b_tokens\n- 280b_tokens\n- 400b_tokens\n- 440b_tokens\n- 500b_tokens\n- 600b_tokens\n- 700b_tokens\n- 720b_tokens\n- 960b_tokens\n- 1t_tokens\n- latest", "## Community\n\nJoin us on Together Discord" ]

[ "peft", "arxiv:1910.09700", "base_model:meta-llama/Llama-2-13b-chat-hf", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \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", "## 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: True\n- bnb_4bit_compute_dtype: bfloat16", "### Framework versions\n\n\n- PEFT 0.7.0.dev0", "## 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: True\n- bnb_4bit_compute_dtype: bfloat16", "### Framework versions\n\n\n- PEFT 0.7.0.dev0" ]

[ "TAGS\n#peft #arxiv-1910.09700 #base_model-meta-llama/Llama-2-13b-chat-hf #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \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", "## 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: True\n- bnb_4bit_compute_dtype: bfloat16", "### Framework versions\n\n\n- PEFT 0.7.0.dev0", "## 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: True\n- bnb_4bit_compute_dtype: bfloat16", "### Framework versions\n\n\n- PEFT 0.7.0.dev0" ]

[ "peft", "arxiv:1910.09700", "base_model:meta-llama/Llama-2-13b-chat-hf", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \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", "## 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: True\n- bnb_4bit_compute_dtype: bfloat16", "### Framework versions\n\n\n- PEFT 0.7.0.dev0" ]

[ "TAGS\n#peft #arxiv-1910.09700 #base_model-meta-llama/Llama-2-13b-chat-hf #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \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", "## 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: True\n- bnb_4bit_compute_dtype: bfloat16", "### Framework versions\n\n\n- PEFT 0.7.0.dev0" ]

[ "transformers", "llava", "text-generation", "dataset:liuhaotian/LLaVA-CC3M-Pretrain-595K", "autotrain_compatible", "region:us" ]

[]

[]

[ "# llava-v1.5-llama-3-8b-pretrain Model Card\n\nThis is a pretrained checkpoint with the MLP connector after LLaVA stage 1, you can use it to instruct tune your multimodal models.\nPlease follow my reproduced implementation LLaVA-Llama-3 for more details on fine-tuning LLaVA model with Llama-3 as the foundatiaon LLM.", "## Training dataset\n- 558K filtered image-text pairs from LAION/CC/SBU, captioned by BLIP.", "## Architecture\n- LLM: llama-3-8b (Frozen)\n- Vision-Language Adapter: MLP\n- Vision Encoder: CLIP-ViT-L-336px (Frozen)" ]

[ "TAGS\n#transformers #llava #text-generation #dataset-liuhaotian/LLaVA-CC3M-Pretrain-595K #autotrain_compatible #region-us \n", "# llava-v1.5-llama-3-8b-pretrain Model Card\n\nThis is a pretrained checkpoint with the MLP connector after LLaVA stage 1, you can use it to instruct tune your multimodal models.\nPlease follow my reproduced implementation LLaVA-Llama-3 for more details on fine-tuning LLaVA model with Llama-3 as the foundatiaon LLM.", "## Training dataset\n- 558K filtered image-text pairs from LAION/CC/SBU, captioned by BLIP.", "## Architecture\n- LLM: llama-3-8b (Frozen)\n- Vision-Language Adapter: MLP\n- Vision Encoder: CLIP-ViT-L-336px (Frozen)" ]

[ "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", "mistral", "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 #mistral #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", "tensorboard", "safetensors", "xlm-roberta", "multiple-choice", "generated_from_trainer", "base_model:FacebookAI/xlm-roberta-large", "license:mit", "endpoints_compatible", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 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 #xlm-roberta #multiple-choice #generated_from_trainer #base_model-FacebookAI/xlm-roberta-large #license-mit #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 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", "qwen2", "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 #qwen2 #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "transformers", "tensorboard", "safetensors", "wav2vec2", "automatic-speech-recognition", "generated_from_trainer", "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: 16\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 500\n* num\\_epochs: 10", "### Training results", "### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.1.2\n* Datasets 2.18.0\n* Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #tensorboard #safetensors #wav2vec2 #automatic-speech-recognition #generated_from_trainer #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: 16\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 500\n* num\\_epochs: 10", "### Training results", "### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.1.2\n* Datasets 2.18.0\n* Tokenizers 0.15.2" ]

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

[]

[]

[ "# Meta-Llama-3-8B-Uninstruct-function-calling-json-mode-model_stock-v0.1\n\nMeta-Llama-3-8B-Uninstruct-function-calling-json-mode-model_stock-v0.1 is a merge of the following models using LazyMergekit:\n* hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode\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 #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-NousResearch/Meta-Llama-3-8B #base_model-NousResearch/Meta-Llama-3-8B-Instruct #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Meta-Llama-3-8B-Uninstruct-function-calling-json-mode-model_stock-v0.1\n\nMeta-Llama-3-8B-Uninstruct-function-calling-json-mode-model_stock-v0.1 is a merge of the following models using LazyMergekit:\n* hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode\n* NousResearch/Meta-Llama-3-8B\n* NousResearch/Meta-Llama-3-8B-Instruct", "## Configuration", "## Usage" ]

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

[]

[]

[ "# robust_llm_0cfe7cd601f511efa831d63e49e237a3_from_EleutherAI_pythia-14m\n\nThis model is a fine-tuned version of EleutherAI/pythia-14m on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 0\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #safetensors #gpt_neox #text-classification #generated_from_trainer #base_model-EleutherAI/pythia-14m #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# robust_llm_0cfe7cd601f511efa831d63e49e237a3_from_EleutherAI_pythia-14m\n\nThis model is a fine-tuned version of EleutherAI/pythia-14m on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 0\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "transformers", "gguf", "code", "en", "dataset:verifiers-for-code/CodeNet-16K", "dataset:verifiers-for-code/CodeNet-Planner", "base_model:verifiers-for-code/Llama-3-LlamaPlanner", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #code #en #dataset-verifiers-for-code/CodeNet-16K #dataset-verifiers-for-code/CodeNet-Planner #base_model-verifiers-for-code/Llama-3-LlamaPlanner #license-apache-2.0 #endpoints_compatible #region-us \n" ]

[ "transformers", "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_2af87ec601f511ef91b4d63e49e237a3_from_EleutherAI_pythia-70m\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 2.2.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #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_2af87ec601f511ef91b4d63e49e237a3_from_EleutherAI_pythia-70m\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 2.2.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "transformers", "gguf", "agents", "agent", "llm", "llama", "text-generation", "en", "dataset:McGill-NLP/WebLINX", "base_model:McGill-NLP/Llama-3-8B-Web", "license:llama3", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #agents #agent #llm #llama #text-generation #en #dataset-McGill-NLP/WebLINX #base_model-McGill-NLP/Llama-3-8B-Web #license-llama3 #endpoints_compatible #region-us \n" ]

[ "transformers", "gguf", "en", "base_model:CroissantCrusader/FrenchBaguette", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #en #base_model-CroissantCrusader/FrenchBaguette #endpoints_compatible #region-us \n" ]

[ "transformers", "gguf", "mergekit", "merge", "en", "base_model:birgermoell/NorskGPT-ChimeraLlama-3", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #mergekit #merge #en #base_model-birgermoell/NorskGPT-ChimeraLlama-3 #endpoints_compatible #region-us \n" ]

[ "safetensors", "function calling", "tool use", "llama", "llama3", "tinyllama", "instruct-tuned", "4-bit quantization", "ggfu", "license:apache-2.0", "region:us" ]

[]

[]

[ "# 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." ]

[ "TAGS\n#safetensors #function calling #tool use #llama #llama3 #tinyllama #instruct-tuned #4-bit quantization #ggfu #license-apache-2.0 #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." ]

[ "transformers", "pytorch", "falcon", "text-generation", "custom_code", "en", "dataset:tiiuae/falcon-refinedweb", "arxiv:2205.14135", "arxiv:1911.02150", "arxiv:2005.14165", "arxiv:2104.09864", "arxiv:2306.01116", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "2205.14135", "1911.02150", "2005.14165", "2104.09864", "2306.01116" ]

[ "en" ]

[ "### Model Description\n\n\n* Developed by: URL;\n* Model type: Causal decoder-only;\n* Language(s) (NLP): English and French;\n* License: Apache 2.0;\n* Finetuned from model: Falcon-7B.", "### Model Source\n\n\n* Paper: *coming soon*.\n\n\nUses\n----", "### Direct Use\n\n\nFalcon-7B-Instruct has been finetuned on a mixture of instruct and chat datasets.", "### Out-of-Scope Use\n\n\nProduction use without adequate assessment of risks and mitigation; any use cases which may be considered irresponsible or harmful.\n\n\nBias, Risks, and Limitations\n----------------------------\n\n\nFalcon-7B-Instruct is mostly trained on English data, and will not generalize appropriately to other languages. Furthermore, as it is trained on a large-scale corpora representative of the web, it will carry the stereotypes and biases commonly encountered online.", "### Recommendations\n\n\nWe recommend users of Falcon-7B-Instruct to develop guardrails and to take appropriate precautions for any production use.\n\n\nHow to Get Started with the Model\n---------------------------------\n\n\nTraining Details\n----------------", "### Training Data\n\n\nFalcon-7B-Instruct was finetuned on a 250M tokens mixture of instruct/chat datasets.\n\n\n\nThe data was tokenized with the Falcon-7B/40B tokenizer.\n\n\nEvaluation\n----------\n\n\n*Paper coming soon.*\n\n\nSee the OpenLLM Leaderboard for early results.\n\n\nNote that this model variant is not optimized for NLP benchmarks.\n\n\nTechnical Specifications\n------------------------\n\n\nFor more information about pretraining, see Falcon-7B.", "### Model Architecture and Objective\n\n\nFalcon-7B is a causal decoder-only model trained on a causal language modeling task (i.e., predict the next token).\n\n\nThe architecture is broadly adapted from the GPT-3 paper (Brown et al., 2020), with the following differences:\n\n\n* Positionnal embeddings: rotary (Su et al., 2021);\n* Attention: multiquery (Shazeer et al., 2019) and FlashAttention (Dao et al., 2022);\n* Decoder-block: parallel attention/MLP with a single layer norm.\n\n\nHyperparameter: Layers, Value: 32, Comment: \nHyperparameter: 'd\\_model', Value: 4544, Comment: Increased to compensate for multiquery\nHyperparameter: 'head\\_dim', Value: 64, Comment: Reduced to optimise for FlashAttention\nHyperparameter: Vocabulary, Value: 65024, Comment: \nHyperparameter: Sequence length, Value: 2048, Comment:", "### Compute Infrastructure", "#### Hardware\n\n\nFalcon-7B-Instruct was trained on AWS SageMaker, on 32 A100 40GB GPUs in P4d instances.", "#### Software\n\n\nFalcon-7B-Instruct was trained a custom distributed training codebase, Gigatron. It uses a 3D parallelism approach combined with ZeRO and high-performance Triton kernels (FlashAttention, etc.)\n\n\n*Paper coming soon* . In the meanwhile, you can use the following information to cite:\n\n\nTo learn more about the pretraining dataset, see the RefinedWeb paper.\n\n\nLicense\n-------\n\n\nFalcon-7B-Instruct is made available under the Apache 2.0 license.\n\n\nContact\n-------\n\n\nfalconllm@URL" ]

[ "TAGS\n#transformers #pytorch #falcon #text-generation #custom_code #en #dataset-tiiuae/falcon-refinedweb #arxiv-2205.14135 #arxiv-1911.02150 #arxiv-2005.14165 #arxiv-2104.09864 #arxiv-2306.01116 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "### Model Description\n\n\n* Developed by: URL;\n* Model type: Causal decoder-only;\n* Language(s) (NLP): English and French;\n* License: Apache 2.0;\n* Finetuned from model: Falcon-7B.", "### Model Source\n\n\n* Paper: *coming soon*.\n\n\nUses\n----", "### Direct Use\n\n\nFalcon-7B-Instruct has been finetuned on a mixture of instruct and chat datasets.", "### Out-of-Scope Use\n\n\nProduction use without adequate assessment of risks and mitigation; any use cases which may be considered irresponsible or harmful.\n\n\nBias, Risks, and Limitations\n----------------------------\n\n\nFalcon-7B-Instruct is mostly trained on English data, and will not generalize appropriately to other languages. Furthermore, as it is trained on a large-scale corpora representative of the web, it will carry the stereotypes and biases commonly encountered online.", "### Recommendations\n\n\nWe recommend users of Falcon-7B-Instruct to develop guardrails and to take appropriate precautions for any production use.\n\n\nHow to Get Started with the Model\n---------------------------------\n\n\nTraining Details\n----------------", "### Training Data\n\n\nFalcon-7B-Instruct was finetuned on a 250M tokens mixture of instruct/chat datasets.\n\n\n\nThe data was tokenized with the Falcon-7B/40B tokenizer.\n\n\nEvaluation\n----------\n\n\n*Paper coming soon.*\n\n\nSee the OpenLLM Leaderboard for early results.\n\n\nNote that this model variant is not optimized for NLP benchmarks.\n\n\nTechnical Specifications\n------------------------\n\n\nFor more information about pretraining, see Falcon-7B.", "### Model Architecture and Objective\n\n\nFalcon-7B is a causal decoder-only model trained on a causal language modeling task (i.e., predict the next token).\n\n\nThe architecture is broadly adapted from the GPT-3 paper (Brown et al., 2020), with the following differences:\n\n\n* Positionnal embeddings: rotary (Su et al., 2021);\n* Attention: multiquery (Shazeer et al., 2019) and FlashAttention (Dao et al., 2022);\n* Decoder-block: parallel attention/MLP with a single layer norm.\n\n\nHyperparameter: Layers, Value: 32, Comment: \nHyperparameter: 'd\\_model', Value: 4544, Comment: Increased to compensate for multiquery\nHyperparameter: 'head\\_dim', Value: 64, Comment: Reduced to optimise for FlashAttention\nHyperparameter: Vocabulary, Value: 65024, Comment: \nHyperparameter: Sequence length, Value: 2048, Comment:", "### Compute Infrastructure", "#### Hardware\n\n\nFalcon-7B-Instruct was trained on AWS SageMaker, on 32 A100 40GB GPUs in P4d instances.", "#### Software\n\n\nFalcon-7B-Instruct was trained a custom distributed training codebase, Gigatron. It uses a 3D parallelism approach combined with ZeRO and high-performance Triton kernels (FlashAttention, etc.)\n\n\n*Paper coming soon* . In the meanwhile, you can use the following information to cite:\n\n\nTo learn more about the pretraining dataset, see the RefinedWeb paper.\n\n\nLicense\n-------\n\n\nFalcon-7B-Instruct is made available under the Apache 2.0 license.\n\n\nContact\n-------\n\n\nfalconllm@URL" ]

[ "transformers", "safetensors", "mistral", "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 #mistral #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", "gguf", "moe", "merge", "llama-3", "en", "base_model:Eurdem/Bombus_3x8B", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #moe #merge #llama-3 #en #base_model-Eurdem/Bombus_3x8B #license-apache-2.0 #endpoints_compatible #region-us \n" ]

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

[]

[]

[ "# Meta-Llama-3-8B-Instruct_fictional_Chinese_v3\n\nThis model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the generator dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 2\n- eval_batch_size: 2\n- seed: 42\n- gradient_accumulation_steps: 8\n- total_train_batch_size: 16\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 72", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #tensorboard #safetensors #llama #text-generation #trl #sft #generated_from_trainer #conversational #dataset-generator #base_model-meta-llama/Meta-Llama-3-8B-Instruct #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Meta-Llama-3-8B-Instruct_fictional_Chinese_v3\n\nThis model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the generator dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 2\n- eval_batch_size: 2\n- seed: 42\n- gradient_accumulation_steps: 8\n- total_train_batch_size: 16\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 72", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

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

[]

[]

[ "# API Inference\n\n!generated from URL", "## Get API Key\n\nGet API key from ModelsLab API, No Payment needed. \n\nReplace Key in below code, change model_id to \"realcartoon-special-sp1\"\n\nCoding in PHP/Node/Java etc? Have a look at docs for more code examples: View docs\n\nTry model for free: Generate Images\n\nModel link: View model\n\nView all models: View Models\n\n import requests \n import json \n \n url = \"URL \n \n payload = URL({ \n \"key\": \"your_api_key\", \n \"model_id\": \"realcartoon-special-sp1\", \n \"prompt\": \"ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K\", \n \"negative_prompt\": \"painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime\", \n \"width\": \"512\", \n \"height\": \"512\", \n \"samples\": \"1\", \n \"num_inference_steps\": \"30\", \n \"safety_checker\": \"no\", \n \"enhance_prompt\": \"yes\", \n \"seed\": None, \n \"guidance_scale\": 7.5, \n \"multi_lingual\": \"no\", \n \"panorama\": \"no\", \n \"self_attention\": \"no\", \n \"upscale\": \"no\", \n \"embeddings\": \"embeddings_model_id\", \n \"lora\": \"lora_model_id\", \n \"webhook\": None, \n \"track_id\": None \n }) \n \n headers = { \n 'Content-Type': 'application/json' \n } \n \n response = requests.request(\"POST\", url, headers=headers, data=payload) \n \n print(URL)\n\n> Use this coupon code to get 25% off DMGG0RBN" ]

[ "TAGS\n#diffusers #modelslab.com #stable-diffusion-api #text-to-image #ultra-realistic #license-creativeml-openrail-m #endpoints_compatible #diffusers-StableDiffusionPipeline #region-us \n", "# API Inference\n\n!generated from URL", "## Get API Key\n\nGet API key from ModelsLab API, No Payment needed. \n\nReplace Key in below code, change model_id to \"realcartoon-special-sp1\"\n\nCoding in PHP/Node/Java etc? Have a look at docs for more code examples: View docs\n\nTry model for free: Generate Images\n\nModel link: View model\n\nView all models: View Models\n\n import requests \n import json \n \n url = \"URL \n \n payload = URL({ \n \"key\": \"your_api_key\", \n \"model_id\": \"realcartoon-special-sp1\", \n \"prompt\": \"ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K\", \n \"negative_prompt\": \"painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime\", \n \"width\": \"512\", \n \"height\": \"512\", \n \"samples\": \"1\", \n \"num_inference_steps\": \"30\", \n \"safety_checker\": \"no\", \n \"enhance_prompt\": \"yes\", \n \"seed\": None, \n \"guidance_scale\": 7.5, \n \"multi_lingual\": \"no\", \n \"panorama\": \"no\", \n \"self_attention\": \"no\", \n \"upscale\": \"no\", \n \"embeddings\": \"embeddings_model_id\", \n \"lora\": \"lora_model_id\", \n \"webhook\": None, \n \"track_id\": None \n }) \n \n headers = { \n 'Content-Type': 'application/json' \n } \n \n response = requests.request(\"POST\", url, headers=headers, data=payload) \n \n print(URL)\n\n> Use this coupon code to get 25% off DMGG0RBN" ]

[ "peft", "safetensors", "arxiv:1910.09700", "base_model:mistralai/Mistral-7B-Instruct-v0.2", "region:us" ]

[ "1910.09700" ]

[]

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

[ "TAGS\n#peft #safetensors #arxiv-1910.09700 #base_model-mistralai/Mistral-7B-Instruct-v0.2 #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact", "### Framework versions\n\n- PEFT 0.10.0" ]

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

[]

[]

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

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

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

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 10\n* eval\\_batch\\_size: 10\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.1.2\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #distilbert #multiple-choice #generated_from_trainer #base_model-distilbert/distilbert-base-uncased #license-apache-2.0 #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 10\n* eval\\_batch\\_size: 10\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.1.2\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "transformers", "safetensors", "phi3", "text-generation", "conversational", "custom_code", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "# opus-samantha-phi-3-mini-4k\n\nopus-samantha-phi-3-mini-4k is an SFT fine-tuned version of microsoft/Phi-3-mini-4k-instruct using a custom training dataset.\nThis model was made with Phinetune", "## Process\n- Learning Rate: 2e-05\n- Maximum Sequence Length: 2048\n- Dataset: macadeliccc/opus_samantha\n- Split: train", "## Usage" ]

[ "TAGS\n#transformers #safetensors #phi3 #text-generation #conversational #custom_code #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "# opus-samantha-phi-3-mini-4k\n\nopus-samantha-phi-3-mini-4k is an SFT fine-tuned version of microsoft/Phi-3-mini-4k-instruct using a custom training dataset.\nThis model was made with Phinetune", "## Process\n- Learning Rate: 2e-05\n- Maximum Sequence Length: 2048\n- Dataset: macadeliccc/opus_samantha\n- Split: train", "## Usage" ]

[ "transformers", "tensorboard", "safetensors", "t5", "text2text-generation", "generated_from_trainer", "base_model:google/flan-t5-small", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 32\n* eval\\_batch\\_size: 32\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 #t5 #text2text-generation #generated_from_trainer #base_model-google/flan-t5-small #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 32\n* eval\\_batch\\_size: 32\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", "deberta-v2", "feature-extraction", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]

[ "1910.09700" ]

[]

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

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

[ "transformers", "tensorboard", "safetensors", "vision-encoder-decoder", "generated_from_trainer", "dataset:imagefolder", "base_model:naver-clova-ix/donut-base", "license:mit", "endpoints_compatible", "region:us" ]

[]

[]

[ "# MTT_Cipher\n\nThis model is a fine-tuned version of naver-clova-ix/donut-base on the imagefolder dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 2e-05\n- train_batch_size: 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: 3", "### Training results", "### Framework versions\n\n- Transformers 4.41.0.dev0\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #vision-encoder-decoder #generated_from_trainer #dataset-imagefolder #base_model-naver-clova-ix/donut-base #license-mit #endpoints_compatible #region-us \n", "# MTT_Cipher\n\nThis model is a fine-tuned version of naver-clova-ix/donut-base on the imagefolder dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 2e-05\n- train_batch_size: 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: 3", "### Training results", "### Framework versions\n\n- Transformers 4.41.0.dev0\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "transformers", "safetensors", "qwen2", "text-generation", "code", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "### Contact information\n\n\nFor personal communication related to this project, please contact Nha Nguyen Van (URL@URL)." ]

[ "TAGS\n#transformers #safetensors #qwen2 #text-generation #code #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "### Contact information\n\n\nFor personal communication related to this project, please contact Nha Nguyen Van (URL@URL)." ]

[ "gguf", "reasoning", "text-generation", "dataset:openbmb/UltraInteract_sft", "dataset:stingning/ultrachat", "dataset:openchat/openchat_sharegpt4_dataset", "dataset:Open-Orca/OpenOrca", "license:apache-2.0", "region:us" ]

[]

[]

[ "# Eurus-7b-sft-GGUF\n\n- This is quantized version of openbmb/Eurus-7b-sft created using URL", "# Model Description\n\nEurus-7B-SFT is fine-tuned from Mistral-7B on all correct actions in UltraInteract, mixing a small proportion of UltraChat, ShareGPT, and OpenOrca examples.\n\nIt achieves better performance than other open-source models of similar sizes and even outperforms specialized models in corresponding domains in many cases.", "## Usage\n\nWe apply tailored prompts for coding and math, consistent with UltraInteract data formats:\n\nCoding\n\n\nMath-CoT\n\n\n\nMath-PoT", "## Evaluation\n - Eurus, both the 7B and 70B variants, achieve the best overall performance among open-source models of similar sizes. Eurus even outperforms specialized models in corresponding domains in many cases. Notably, Eurus-7B outperforms baselines that are 5× larger, and Eurus-70B achieves better performance than GPT-3.5 Turbo.\n - Preference learning with UltraInteract can further improve performance, especially in math and the multi-turn ability.\n<img src=\"figures_main_exp.png\" alt=\"stats\" style=\"zoom: 40%;\" />" ]

[ "TAGS\n#gguf #reasoning #text-generation #dataset-openbmb/UltraInteract_sft #dataset-stingning/ultrachat #dataset-openchat/openchat_sharegpt4_dataset #dataset-Open-Orca/OpenOrca #license-apache-2.0 #region-us \n", "# Eurus-7b-sft-GGUF\n\n- This is quantized version of openbmb/Eurus-7b-sft created using URL", "# Model Description\n\nEurus-7B-SFT is fine-tuned from Mistral-7B on all correct actions in UltraInteract, mixing a small proportion of UltraChat, ShareGPT, and OpenOrca examples.\n\nIt achieves better performance than other open-source models of similar sizes and even outperforms specialized models in corresponding domains in many cases.", "## Usage\n\nWe apply tailored prompts for coding and math, consistent with UltraInteract data formats:\n\nCoding\n\n\nMath-CoT\n\n\n\nMath-PoT", "## Evaluation\n - Eurus, both the 7B and 70B variants, achieve the best overall performance among open-source models of similar sizes. Eurus even outperforms specialized models in corresponding domains in many cases. Notably, Eurus-7B outperforms baselines that are 5× larger, and Eurus-70B achieves better performance than GPT-3.5 Turbo.\n - Preference learning with UltraInteract can further improve performance, especially in math and the multi-turn ability.\n<img src=\"figures_main_exp.png\" alt=\"stats\" style=\"zoom: 40%;\" />" ]

[ "transformers", "gpt_neox", "text-generation", "en", "dataset:togethercomputer/RedPajama-Data-1T", "dataset:togethercomputer/RedPajama-Data-Instruct", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[ "en" ]

[ "# RedPajama-INCITE-7B-Instruct\n\nRedPajama-INCITE-7B-Instruct was developed by Together and leaders from the open-source AI community including URL, ETH DS3Lab, AAI CERC, Université de Montréal, MILA - Québec AI Institute, Stanford Center for Research on Foundation Models (CRFM), Stanford Hazy Research research group and LAION. \n\nThe model was fine-tuned for few-shot applications on the data of GPT-JT, with exclusion of tasks that overlap with the HELM core scenarios.\n\n - Base Model: RedPajama-INCITE-7B-Base\n - Instruction-tuned Version: RedPajama-INCITE-7B-Instruct\n - Chat Version: RedPajama-INCITE-7B-Chat", "## Model Details\n- Developed by: Together Computer.\n- Model type: Language Model\n- Language(s): English\n- License: Apache 2.0\n- Model Description: A 6.9B parameter pretrained language model.", "# Quick Start\n\nPlease note that the model requires 'transformers' version >= 4.25.1.", "## GPU Inference\n\nThis requires a GPU with 16GB memory.", "## GPU Inference in Int8\n\nThis requires a GPU with 12GB memory.\n\nTo run inference with int8, please ensure you have installed accelerate and bitandbytes. You can install them with the following command:\n\n\n\nThen you can run inference with int8 as follows:", "## CPU Inference\n\n\n\nPlease note that since 'LayerNormKernelImpl' is not implemented in fp16 for CPU, we use 'bfloat16' for CPU inference.", "# Uses", "## Direct Use \n\nExcluded uses are described below.", "### Misuse, Malicious Use, and Out-of-Scope Use\n\nIt is the responsibility of the end user to ensure that the model is used in a responsible and ethical manner.", "#### Out-of-Scope Use\n\nRedPajama-INCITE-7B-Instruct is a language model and may not perform well for other use cases outside of its intended scope. \nFor example, it may not be suitable for use in safety-critical applications or for making decisions that have a significant impact on individuals or society. \nIt is important to consider the limitations of the model and to only use it for its intended purpose.", "#### Misuse and Malicious Use\n\nRedPajama-INCITE-7B-Instruct is designed for language modeling.\nMisuse of the model, such as using it to engage in illegal or unethical activities, is strictly prohibited and goes against the principles of the project.\n\nUsing the model to generate content that is cruel to individuals is a misuse of this model. This includes, but is not limited to:\n\n- Generating fake news, misinformation, or propaganda\n- Promoting hate speech, discrimination, or violence against individuals or groups\n- Impersonating individuals or organizations without their consent\n- Engaging in cyberbullying or harassment\n- Defamatory content\n- Spamming or scamming\n- Sharing confidential or sensitive information without proper authorization\n- Violating the terms of use of the model or the data used to train it\n- Creating automated bots for malicious purposes such as spreading malware, phishing scams, or spamming", "## Limitations\n\nRedPajama-INCITE-7B-Instruct, like other language models, has limitations that should be taken into consideration. \nFor example, the model may not always provide accurate or relevant answers, particularly for questions that are complex, ambiguous, or outside of its training data. \nWe therefore welcome contributions from individuals and organizations, and encourage collaboration towards creating a more robust and inclusive chatbot.", "## Training\n\nTraining Data\n\nPlease refer to togethercomputer/RedPajama-Data-1T\n\nTraining Procedure\n\n- Hardware: 8 A100\n- Optimizer: Adam\n- Gradient Accumulations: 1\n- Num of Tokens: 1B tokens\n- Learning rate: 1e-5", "## Community\n\nJoin us on Together Discord" ]

[ "TAGS\n#transformers #gpt_neox #text-generation #en #dataset-togethercomputer/RedPajama-Data-1T #dataset-togethercomputer/RedPajama-Data-Instruct #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# RedPajama-INCITE-7B-Instruct\n\nRedPajama-INCITE-7B-Instruct was developed by Together and leaders from the open-source AI community including URL, ETH DS3Lab, AAI CERC, Université de Montréal, MILA - Québec AI Institute, Stanford Center for Research on Foundation Models (CRFM), Stanford Hazy Research research group and LAION. \n\nThe model was fine-tuned for few-shot applications on the data of GPT-JT, with exclusion of tasks that overlap with the HELM core scenarios.\n\n - Base Model: RedPajama-INCITE-7B-Base\n - Instruction-tuned Version: RedPajama-INCITE-7B-Instruct\n - Chat Version: RedPajama-INCITE-7B-Chat", "## Model Details\n- Developed by: Together Computer.\n- Model type: Language Model\n- Language(s): English\n- License: Apache 2.0\n- Model Description: A 6.9B parameter pretrained language model.", "# Quick Start\n\nPlease note that the model requires 'transformers' version >= 4.25.1.", "## GPU Inference\n\nThis requires a GPU with 16GB memory.", "## GPU Inference in Int8\n\nThis requires a GPU with 12GB memory.\n\nTo run inference with int8, please ensure you have installed accelerate and bitandbytes. You can install them with the following command:\n\n\n\nThen you can run inference with int8 as follows:", "## CPU Inference\n\n\n\nPlease note that since 'LayerNormKernelImpl' is not implemented in fp16 for CPU, we use 'bfloat16' for CPU inference.", "# Uses", "## Direct Use \n\nExcluded uses are described below.", "### Misuse, Malicious Use, and Out-of-Scope Use\n\nIt is the responsibility of the end user to ensure that the model is used in a responsible and ethical manner.", "#### Out-of-Scope Use\n\nRedPajama-INCITE-7B-Instruct is a language model and may not perform well for other use cases outside of its intended scope. \nFor example, it may not be suitable for use in safety-critical applications or for making decisions that have a significant impact on individuals or society. \nIt is important to consider the limitations of the model and to only use it for its intended purpose.", "#### Misuse and Malicious Use\n\nRedPajama-INCITE-7B-Instruct is designed for language modeling.\nMisuse of the model, such as using it to engage in illegal or unethical activities, is strictly prohibited and goes against the principles of the project.\n\nUsing the model to generate content that is cruel to individuals is a misuse of this model. This includes, but is not limited to:\n\n- Generating fake news, misinformation, or propaganda\n- Promoting hate speech, discrimination, or violence against individuals or groups\n- Impersonating individuals or organizations without their consent\n- Engaging in cyberbullying or harassment\n- Defamatory content\n- Spamming or scamming\n- Sharing confidential or sensitive information without proper authorization\n- Violating the terms of use of the model or the data used to train it\n- Creating automated bots for malicious purposes such as spreading malware, phishing scams, or spamming", "## Limitations\n\nRedPajama-INCITE-7B-Instruct, like other language models, has limitations that should be taken into consideration. \nFor example, the model may not always provide accurate or relevant answers, particularly for questions that are complex, ambiguous, or outside of its training data. \nWe therefore welcome contributions from individuals and organizations, and encourage collaboration towards creating a more robust and inclusive chatbot.", "## Training\n\nTraining Data\n\nPlease refer to togethercomputer/RedPajama-Data-1T\n\nTraining Procedure\n\n- Hardware: 8 A100\n- Optimizer: Adam\n- Gradient Accumulations: 1\n- Num of Tokens: 1B tokens\n- Learning rate: 1e-5", "## Community\n\nJoin us on Together Discord" ]

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

[]

[]

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

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

[ "transformers", "tensorboard", "safetensors", "deberta", "fill-mask", "generated_from_trainer", "base_model:microsoft/deberta-base", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "# Pretraining_MFM_v2\n\nThis model is a fine-tuned version of microsoft/deberta-base 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: 32\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: 50", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #tensorboard #safetensors #deberta #fill-mask #generated_from_trainer #base_model-microsoft/deberta-base #license-mit #autotrain_compatible #endpoints_compatible #region-us \n", "# Pretraining_MFM_v2\n\nThis model is a fine-tuned version of microsoft/deberta-base 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: 32\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: 50", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "transformers", "tensorboard", "safetensors", "mistral", "text-generation", "trl", "dpo", "generated_from_trainer", "conversational", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# DPO-PairRM-5-SMI-lr-1e6-iteration-5-t-7e-beta-15e3-2-iteration-change-ref\n\nThis model was trained from scratch on the None dataset.\nIt achieves the following results on the evaluation set:\n- Loss: 0.5849\n- Rewards/chosen: -2.3410\n- Rewards/rejected: -2.9843\n- Rewards/accuracies: 0.6706\n- Rewards/margins: 0.6433\n- Rewards/mix Margin: 0.2179\n- Logps/rejected: -580.8327\n- Logps/chosen: -486.8375\n- Logits/rejected: -1.4430\n- Logits/chosen: -1.5066", "## 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-06\n- train_batch_size: 1\n- eval_batch_size: 1\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 4\n- gradient_accumulation_steps: 16\n- total_train_batch_size: 64\n- total_eval_batch_size: 4\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\n- Datasets 2.17.1\n- Tokenizers 0.15.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #mistral #text-generation #trl #dpo #generated_from_trainer #conversational #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# DPO-PairRM-5-SMI-lr-1e6-iteration-5-t-7e-beta-15e3-2-iteration-change-ref\n\nThis model was trained from scratch on the None dataset.\nIt achieves the following results on the evaluation set:\n- Loss: 0.5849\n- Rewards/chosen: -2.3410\n- Rewards/rejected: -2.9843\n- Rewards/accuracies: 0.6706\n- Rewards/margins: 0.6433\n- Rewards/mix Margin: 0.2179\n- Logps/rejected: -580.8327\n- Logps/chosen: -486.8375\n- Logits/rejected: -1.4430\n- Logits/chosen: -1.5066", "## 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-06\n- train_batch_size: 1\n- eval_batch_size: 1\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 4\n- gradient_accumulation_steps: 16\n- total_train_batch_size: 64\n- total_eval_batch_size: 4\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\n- Datasets 2.17.1\n- Tokenizers 0.15.1" ]

[ "transformers", "safetensors", "mistral", "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 #mistral #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", "bert", "feature-extraction", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]

[ "1910.09700" ]

[]

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

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

[ "transformers", "tensorboard", "safetensors", "bart", "text2text-generation", "generated_from_trainer", "base_model:facebook/bart-base", "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: 4\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.1.2\n* Datasets 2.18.0\n* Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #tensorboard #safetensors #bart #text2text-generation #generated_from_trainer #base_model-facebook/bart-base #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: 4\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.1.2\n* Datasets 2.18.0\n* Tokenizers 0.15.2" ]

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

[ "1910.09700" ]

[]

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

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

[ "gguf", "reasoning", "preference_learning", "kto", "text-generation", "dataset:openbmb/UltraFeedback", "dataset:openbmb/UltraInteract_pair", "arxiv:2402.01306", "base_model:openbmb/Eurus-7b-kto", "license:apache-2.0", "region:us" ]

[ "2402.01306" ]

[]

[ "# openbmb/Eurus-7b-kto-GGUF\n\n- This is quantized version of openbmb/Eurus-7b-kto", "# Model Description\n\nEurus-7B-KTO is KTO fine-tuned from Eurus-7B-SFT on all multi-turn trajectory pairs in UltraInteract and all pairs in UltraFeedback.\n\nIt achieves the best overall performance among open-source models of similar sizes and even outperforms specialized models in corresponding domains in many cases. Notably, Eurus-7B-KTO outperforms baselines that are 5× larger.", "## Usage\n\nWe apply tailored prompts for coding and math, consistent with UltraInteract data formats:\n\nCoding\n\n\nMath-CoT\n\n\n\nMath-PoT", "## Evaluation\n - Eurus, both the 7B and 70B variants, achieve the best overall performance among open-source models of similar sizes. Eurus even outperforms specialized models in corresponding domains in many cases. Notably, Eurus-7B outperforms baselines that are 5× larger, and Eurus-70B achieves better performance than GPT-3.5 Turbo.\n - Preference learning with UltraInteract can further improve performance, especially in math and the multi-turn ability.\n<img src=\"figures_main_exp.png\" alt=\"stats\" style=\"zoom: 40%;\" />" ]

[ "TAGS\n#gguf #reasoning #preference_learning #kto #text-generation #dataset-openbmb/UltraFeedback #dataset-openbmb/UltraInteract_pair #arxiv-2402.01306 #base_model-openbmb/Eurus-7b-kto #license-apache-2.0 #region-us \n", "# openbmb/Eurus-7b-kto-GGUF\n\n- This is quantized version of openbmb/Eurus-7b-kto", "# Model Description\n\nEurus-7B-KTO is KTO fine-tuned from Eurus-7B-SFT on all multi-turn trajectory pairs in UltraInteract and all pairs in UltraFeedback.\n\nIt achieves the best overall performance among open-source models of similar sizes and even outperforms specialized models in corresponding domains in many cases. Notably, Eurus-7B-KTO outperforms baselines that are 5× larger.", "## Usage\n\nWe apply tailored prompts for coding and math, consistent with UltraInteract data formats:\n\nCoding\n\n\nMath-CoT\n\n\n\nMath-PoT", "## Evaluation\n - Eurus, both the 7B and 70B variants, achieve the best overall performance among open-source models of similar sizes. Eurus even outperforms specialized models in corresponding domains in many cases. Notably, Eurus-7B outperforms baselines that are 5× larger, and Eurus-70B achieves better performance than GPT-3.5 Turbo.\n - Preference learning with UltraInteract can further improve performance, especially in math and the multi-turn ability.\n<img src=\"figures_main_exp.png\" alt=\"stats\" style=\"zoom: 40%;\" />" ]

[ "transformers", "gguf", "nsfw", "not-for-all-audiences", "experimental", "en", "dataset:ResplendentAI/NSFW_RP_Format_NoQuote", "base_model:nbeerbower/llama-3-dragonmaid-8B", "license:other", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #nsfw #not-for-all-audiences #experimental #en #dataset-ResplendentAI/NSFW_RP_Format_NoQuote #base_model-nbeerbower/llama-3-dragonmaid-8B #license-other #endpoints_compatible #region-us \n" ]

[ "transformers", "gguf", "merge", "en", "base_model:timpal0l/dolphin-2.9-llama3-8b-flashback", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #merge #en #base_model-timpal0l/dolphin-2.9-llama3-8b-flashback #license-apache-2.0 #endpoints_compatible #region-us \n" ]

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

[ "1910.09700" ]

[]

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

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

[ "transformers", "gguf", "imatrix", "wizardlm", "text-generation", "en", "license:other", "region:us" ]

[]

[ "en" ]

[ "# From original readme", "## Usage\n\n<b>Note for model system prompts usage:</b>\n\n\n<b>WizardLM-2</b> adopts the prompt format from <b>Vicuna</b> and supports multi-turn conversation. The prompt should be as following:\n\n\n\n<b> Inference WizardLM-2 Demo Script</b>\n\nWe provide a WizardLM-2 inference demo code on our github." ]

[ "TAGS\n#transformers #gguf #imatrix #wizardlm #text-generation #en #license-other #region-us \n", "# From original readme", "## Usage\n\n<b>Note for model system prompts usage:</b>\n\n\n<b>WizardLM-2</b> adopts the prompt format from <b>Vicuna</b> and supports multi-turn conversation. The prompt should be as following:\n\n\n\n<b> Inference WizardLM-2 Demo Script</b>\n\nWe provide a WizardLM-2 inference demo code on our github." ]

[ "safetensors", "zh", "en", "base_model:meta-llama/Meta-Llama-3-8B", "license:apache-2.0", "region:us" ]

[]

[ "zh", "en" ]

[ "# Llama-3-Chinese-8B-LoRA\n\n<p align=\"center\">\n <a href=\"URL src=\"URL width=\"600\"/></a>\n</p>\n\nThis repository contains Llama-3-Chinese-8B-LoRA, which is further pre-trained on Meta-Llama-3-8B with 120 GB Chinese text corpora.\n\nNote: You must combine LoRA with the original Meta-Llama-3-8B to obtain full weight.\n\nFurther details (performance, usage, etc.) should refer to GitHub project page: URL", "## Others\n\n- For full model, please see: URL\n\n- For GGUF model (URL compatible), please see: URL\n\n- If you have questions/issues regarding this model, please submit an issue through URL" ]

[ "TAGS\n#safetensors #zh #en #base_model-meta-llama/Meta-Llama-3-8B #license-apache-2.0 #region-us \n", "# Llama-3-Chinese-8B-LoRA\n\n<p align=\"center\">\n <a href=\"URL src=\"URL width=\"600\"/></a>\n</p>\n\nThis repository contains Llama-3-Chinese-8B-LoRA, which is further pre-trained on Meta-Llama-3-8B with 120 GB Chinese text corpora.\n\nNote: You must combine LoRA with the original Meta-Llama-3-8B to obtain full weight.\n\nFurther details (performance, usage, etc.) should refer to GitHub project page: URL", "## Others\n\n- For full model, please see: URL\n\n- For GGUF model (URL compatible), please see: URL\n\n- If you have questions/issues regarding this model, please submit an issue through URL" ]

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

[]

[]

[ "# API Inference\n\n!generated from URL", "## Get API Key\n\nGet API key from ModelsLab API, No Payment needed. \n\nReplace Key in below code, change model_id to \"aniverse-v3-pruned\"\n\nCoding in PHP/Node/Java etc? Have a look at docs for more code examples: View docs\n\nTry model for free: Generate Images\n\nModel link: View model\n\nView all models: View Models\n\n import requests \n import json \n \n url = \"URL \n \n payload = URL({ \n \"key\": \"your_api_key\", \n \"model_id\": \"aniverse-v3-pruned\", \n \"prompt\": \"ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K\", \n \"negative_prompt\": \"painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime\", \n \"width\": \"512\", \n \"height\": \"512\", \n \"samples\": \"1\", \n \"num_inference_steps\": \"30\", \n \"safety_checker\": \"no\", \n \"enhance_prompt\": \"yes\", \n \"seed\": None, \n \"guidance_scale\": 7.5, \n \"multi_lingual\": \"no\", \n \"panorama\": \"no\", \n \"self_attention\": \"no\", \n \"upscale\": \"no\", \n \"embeddings\": \"embeddings_model_id\", \n \"lora\": \"lora_model_id\", \n \"webhook\": None, \n \"track_id\": None \n }) \n \n headers = { \n 'Content-Type': 'application/json' \n } \n \n response = requests.request(\"POST\", url, headers=headers, data=payload) \n \n print(URL)\n\n> Use this coupon code to get 25% off DMGG0RBN" ]

[ "TAGS\n#diffusers #modelslab.com #stable-diffusion-api #text-to-image #ultra-realistic #license-creativeml-openrail-m #endpoints_compatible #diffusers-StableDiffusionPipeline #region-us \n", "# API Inference\n\n!generated from URL", "## Get API Key\n\nGet API key from ModelsLab API, No Payment needed. \n\nReplace Key in below code, change model_id to \"aniverse-v3-pruned\"\n\nCoding in PHP/Node/Java etc? Have a look at docs for more code examples: View docs\n\nTry model for free: Generate Images\n\nModel link: View model\n\nView all models: View Models\n\n import requests \n import json \n \n url = \"URL \n \n payload = URL({ \n \"key\": \"your_api_key\", \n \"model_id\": \"aniverse-v3-pruned\", \n \"prompt\": \"ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K\", \n \"negative_prompt\": \"painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime\", \n \"width\": \"512\", \n \"height\": \"512\", \n \"samples\": \"1\", \n \"num_inference_steps\": \"30\", \n \"safety_checker\": \"no\", \n \"enhance_prompt\": \"yes\", \n \"seed\": None, \n \"guidance_scale\": 7.5, \n \"multi_lingual\": \"no\", \n \"panorama\": \"no\", \n \"self_attention\": \"no\", \n \"upscale\": \"no\", \n \"embeddings\": \"embeddings_model_id\", \n \"lora\": \"lora_model_id\", \n \"webhook\": None, \n \"track_id\": None \n }) \n \n headers = { \n 'Content-Type': 'application/json' \n } \n \n response = requests.request(\"POST\", url, headers=headers, data=payload) \n \n print(URL)\n\n> Use this coupon code to get 25% off DMGG0RBN" ]

[ "safetensors", "zh", "en", "base_model:hfl/llama-3-chinese-8b", "license:apache-2.0", "region:us" ]

[]

[ "zh", "en" ]

[ "# Llama-3-Chinese-8B-Instruct-LoRA\n\n<p align=\"center\">\n <a href=\"URL src=\"URL width=\"600\"/></a>\n</p>\n\nThis repository contains Llama-3-Chinese-8B-Instruct-LoRA, which is further tuned with 5M instruction data on Llama-3-Chinese-8B.\n\nNote: You must combine LoRA with the original Meta-Llama-3-8B to obtain full weight.\n\nFurther details (performance, usage, etc.) should refer to GitHub project page: URL", "## Others\n\n- For full model, please see: URL\n\n- For GGUF model (URL compatible), please see: URL\n\n- If you have questions/issues regarding this model, please submit an issue through URL" ]

[ "TAGS\n#safetensors #zh #en #base_model-hfl/llama-3-chinese-8b #license-apache-2.0 #region-us \n", "# Llama-3-Chinese-8B-Instruct-LoRA\n\n<p align=\"center\">\n <a href=\"URL src=\"URL width=\"600\"/></a>\n</p>\n\nThis repository contains Llama-3-Chinese-8B-Instruct-LoRA, which is further tuned with 5M instruction data on Llama-3-Chinese-8B.\n\nNote: You must combine LoRA with the original Meta-Llama-3-8B to obtain full weight.\n\nFurther details (performance, usage, etc.) should refer to GitHub project page: URL", "## Others\n\n- For full model, please see: URL\n\n- For GGUF model (URL compatible), please see: URL\n\n- If you have questions/issues regarding this model, please submit an issue through URL" ]

[ "transformers", "safetensors", "mistral", "text-generation", "alignment-handbook", "generated_from_trainer", "trl", "dpo", "conversational", "dataset:updated", "dataset:original", "base_model:ShenaoZ/0.001_ablation_5iters_bs256_nodpo_iter_2", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# 0.001_ablation_5iters_bs256_nodpo_iter_3\n\nThis model is a fine-tuned version of ShenaoZ/0.001_ablation_5iters_bs256_nodpo_iter_2 on the updated and the original datasets.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.36.2\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-ShenaoZ/0.001_ablation_5iters_bs256_nodpo_iter_2 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# 0.001_ablation_5iters_bs256_nodpo_iter_3\n\nThis model is a fine-tuned version of ShenaoZ/0.001_ablation_5iters_bs256_nodpo_iter_2 on the updated and the original datasets.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.15.2" ]

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

[]

[ "ko", "en" ]

[ "# Model Card for free-solar-evo-v0.11", "## Developed by : Freewheelin AI Technical Team", "## Method\n- We were inspired by this Sakana project", "## Base Model \n- free-solar-evo-model" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #ko #en #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for free-solar-evo-v0.11", "## Developed by : Freewheelin AI Technical Team", "## Method\n- We were inspired by this Sakana project", "## Base Model \n- free-solar-evo-model" ]

[ "transformers", "safetensors", "mistral", "text-generation", "alignment-handbook", "generated_from_trainer", "trl", "dpo", "conversational", "dataset:updated", "dataset:original", "base_model:ShenaoZ/0.01_ablation_5iters_bs256_nodpo_iter_2", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# 0.01_ablation_5iters_bs256_nodpo_iter_3\n\nThis model is a fine-tuned version of ShenaoZ/0.01_ablation_5iters_bs256_nodpo_iter_2 on the updated and the original datasets.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.36.2\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-ShenaoZ/0.01_ablation_5iters_bs256_nodpo_iter_2 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# 0.01_ablation_5iters_bs256_nodpo_iter_3\n\nThis model is a fine-tuned version of ShenaoZ/0.01_ablation_5iters_bs256_nodpo_iter_2 on the updated and the original datasets.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.15.2" ]

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

[]

[]

[ "# robust_llm_pythia-70m_mz-130_PasswordMatch_n-its-10-seed-1\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: 1\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.1\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #tensorboard #safetensors #gpt_neox #text-classification #generated_from_trainer #base_model-EleutherAI/pythia-70m #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# robust_llm_pythia-70m_mz-130_PasswordMatch_n-its-10-seed-1\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: 1\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.1\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

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

[]

[]

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

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

[ "transformers", "gguf", "en", "dataset:grimulkan/theory-of-mind", "base_model:jeiku/Average_Normie_l3_v1_8B", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #en #dataset-grimulkan/theory-of-mind #base_model-jeiku/Average_Normie_l3_v1_8B #license-apache-2.0 #endpoints_compatible #region-us \n" ]

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

[]

[]

[ "# 0.001_ablation_4iters_bs256_nodpo_sample2_iter_1\n\nThis model is a fine-tuned version of HuggingFaceH4/mistral-7b-sft-beta on the updated and the original datasets.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.36.2\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-HuggingFaceH4/mistral-7b-sft-beta #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# 0.001_ablation_4iters_bs256_nodpo_sample2_iter_1\n\nThis model is a fine-tuned version of HuggingFaceH4/mistral-7b-sft-beta on the updated and the original datasets.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.15.2" ]

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

[]

[]

[ "# poca Agent playing SoccerTwos\n This is a trained model of a poca agent playing SoccerTwos\n using the Unity ML-Agents Library.\n\n ## Usage (with ML-Agents)\n The Documentation: URL\n\n We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:\n - A *short tutorial* where you teach Huggy the Dog to fetch the stick and then play with him directly in your\n browser: URL\n - A *longer tutorial* to understand how works ML-Agents:\n URL\n\n ### Resume the training\n \n\n ### Watch your Agent play\n You can watch your agent playing directly in your browser\n\n 1. If the environment is part of ML-Agents official environments, go to URL\n 2. Step 1: Find your model_id: yy1636/SoccerTwos-base-15M\n 3. Step 2: Select your *.nn /*.onnx file\n 4. Click on Watch the agent play" ]

[ "TAGS\n#ml-agents #tensorboard #onnx #SoccerTwos #deep-reinforcement-learning #reinforcement-learning #ML-Agents-SoccerTwos #region-us \n", "# poca Agent playing SoccerTwos\n This is a trained model of a poca agent playing SoccerTwos\n using the Unity ML-Agents Library.\n\n ## Usage (with ML-Agents)\n The Documentation: URL\n\n We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:\n - A *short tutorial* where you teach Huggy the Dog to fetch the stick and then play with him directly in your\n browser: URL\n - A *longer tutorial* to understand how works ML-Agents:\n URL\n\n ### Resume the training\n \n\n ### Watch your Agent play\n You can watch your agent playing directly in your browser\n\n 1. If the environment is part of ML-Agents official environments, go to URL\n 2. Step 1: Find your model_id: yy1636/SoccerTwos-base-15M\n 3. Step 2: Select your *.nn /*.onnx file\n 4. Click on Watch the agent play" ]

[ "transformers", "gguf", "en", "base_model:TroyDoesAI/Mermaid-Llama-3-6B-Pruned", "license:cc-by-4.0", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #en #base_model-TroyDoesAI/Mermaid-Llama-3-6B-Pruned #license-cc-by-4.0 #endpoints_compatible #region-us \n" ]

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

[ "1910.09700" ]

[]

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

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

[ "transformers", "gguf", "llama", "text-generation", "base_model:taide/TAIDE-LX-7B", "endpoints_compatible", "region:us" ]

[]

[]

[]

[ "TAGS\n#transformers #gguf #llama #text-generation #base_model-taide/TAIDE-LX-7B #endpoints_compatible #region-us \n" ]

[ "gguf", "region:us" ]

[]

[]

[ "# To use the multimodal capabilities of this model and use vision you need to load the specified mmproj file, this can be found inside this model repo. Llava MMProj\n \n * You can load the mmproj by using the corresponding section in the interface:\n\n !image/png" ]

[ "TAGS\n#gguf #region-us \n", "# To use the multimodal capabilities of this model and use vision you need to load the specified mmproj file, this can be found inside this model repo. Llava MMProj\n \n * You can load the mmproj by using the corresponding section in the interface:\n\n !image/png" ]

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

[ "transformers", "safetensors", "mbart", "text2text-generation", "simplification", "generated_from_trainer", "base_model:facebook/mbart-large-50", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5.6e-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: 2", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #safetensors #mbart #text2text-generation #simplification #generated_from_trainer #base_model-facebook/mbart-large-50 #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: 5.6e-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: 2", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

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

[ "1910.09700" ]

[]

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

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

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

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 3e-06\n* train\\_batch\\_size: 2\n* eval\\_batch\\_size: 2\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05\n* lr\\_scheduler\\_type: cosine\n* lr\\_scheduler\\_warmup\\_steps: 100\n* num\\_epochs: 5", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0.dev0\n* Pytorch 2.1.1\n* Datasets 2.15.0\n* Tokenizers 0.15.0" ]

[ "TAGS\n#transformers #pytorch #phi3 #text-generation #generated_from_trainer #conversational #custom_code #base_model-microsoft/Phi-3-mini-128k-instruct #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: 3e-06\n* train\\_batch\\_size: 2\n* eval\\_batch\\_size: 2\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05\n* lr\\_scheduler\\_type: cosine\n* lr\\_scheduler\\_warmup\\_steps: 100\n* num\\_epochs: 5", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0.dev0\n* Pytorch 2.1.1\n* Datasets 2.15.0\n* Tokenizers 0.15.0" ]

[ "transformers", "gguf", "facebook", "meta", "pytorch", "llama", "llama-3", "en", "base_model:NurtureAI/Meta-Llama-3-70B-Instruct-64k", "license:other", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #facebook #meta #pytorch #llama #llama-3 #en #base_model-NurtureAI/Meta-Llama-3-70B-Instruct-64k #license-other #endpoints_compatible #region-us \n" ]

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

[ "1910.09700" ]

[]

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

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

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

[]

[]

[ "# llama3-8b-orpo\n\nThis model is a fine-tuned version of unsloth/llama-3-8b-bnb-4bit on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 2\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 4\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- num_epochs: 1\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\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 #trl #orpo #unsloth #generated_from_trainer #base_model-unsloth/llama-3-8b-bnb-4bit #license-llama2 #region-us \n", "# llama3-8b-orpo\n\nThis model is a fine-tuned version of unsloth/llama-3-8b-bnb-4bit on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 2\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 4\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- num_epochs: 1\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\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" ]

[ "ultralytics", "tensorboard", "v8", "ultralyticsplus", "yolov8", "yolo", "vision", "object-detection", "pytorch", "dataset:chanelcolgate/yenthienviet", "model-index", "has_space", "region:us" ]

[]

[]

[ "### Supported Labels", "### How to use\n\n- Install ultralyticsplus:\n\n\n\n- Load model and perform prediction:" ]

[ "TAGS\n#ultralytics #tensorboard #v8 #ultralyticsplus #yolov8 #yolo #vision #object-detection #pytorch #dataset-chanelcolgate/yenthienviet #model-index #has_space #region-us \n", "### Supported Labels", "### How to use\n\n- Install ultralyticsplus:\n\n\n\n- Load model and perform prediction:" ]

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

[ "1910.09700" ]

[]

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

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

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

[]

[ "en", "zh" ]

[ "### 推理", "### 提示\n\n\nWiNGPT-Llama-3-8B-Chat 使用了自定义的提示格式：\n\n\n用户角色：System/User/Assistant\n\n\nchat\\_template:\n\n\n指令提示示例：\n\n\n多轮对话示例：\n\n\n翻译功能示例：\n\n\n模型卡\n---", "#### 训练配置与参数", "#### 训练数据\n\n\n预训练数据约20G，指令微调对齐数据约50万条，详细内容 。\n\n\n中文医疗评测 - WiNEval\n----------------\n\n\n更新时间：2024-04-23\n\n\n\n*MCKQuiz（客观题）：17个科目分类13060选择题；输入问题和选项，让模型输出答案。根据标准答案判断对错，统计准确率。*\n\n\n*MSceQA（主观题）：由细分领域场景题目构成，包含八大业务场景，17个一级分类和32个二级分类。使用人工/模型对模型的回答进行准确性、相关性、一致性、完整性、权威性评价，并参照标准答案对模型生成的答案进行评分。*\n\n\n其他WiNEval评测结果", "### 企业服务\n\n\n通过WiNGPT测试平台申请密钥或与我们取得联系\n\n\n局限性与免责声明\n--------\n\n\n(a) WiNGPT2 是一个专业医疗领域的大语言模型，可为一般用户提供拟人化AI医生问诊和问答功能，以及一般医学领域的知识问答。对于专业医疗人士，WiNGPT2 提供关于患者病情的诊断、用药和健康建议等方面的回答的建议仅供参考。\n\n\n(b) 您应理解 WiNGPT2 仅提供信息和建议，不能替代医疗专业人士的意见、诊断或治疗建议。在使用 WiNGPT2 的信息之前，请寻求医生或其他医疗专业人员的建议，并独立评估所提供的信息。\n\n\n(c) WiNGPT2 的信息可能存在错误或不准确。卫宁健康不对 WiNGPT2 的准确性、可靠性、完整性、质量、安全性、及时性、性能或适用性提供任何明示或暗示的保证。使用 WiNGPT2 所产生的结果和决策由您自行承担。第三方原因而给您造成的损害结果承担责任。\n\n\n许可证\n---\n\n\n1. 本项目授权协议为 Apache License 2.0，模型权重需要遵守基础模型 Llama-3-8B 相关协议及其许可证，详细内容参照其网站。\n2. 使用本项目包括模型权重时请引用本项目：URL\n\n\n联系我们\n----\n\n\n网站：URL\n\n\n邮箱：wair@URL" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #medical #conversational #en #zh #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n", "### 推理", "### 提示\n\n\nWiNGPT-Llama-3-8B-Chat 使用了自定义的提示格式：\n\n\n用户角色：System/User/Assistant\n\n\nchat\\_template:\n\n\n指令提示示例：\n\n\n多轮对话示例：\n\n\n翻译功能示例：\n\n\n模型卡\n---", "#### 训练配置与参数", "#### 训练数据\n\n\n预训练数据约20G，指令微调对齐数据约50万条，详细内容 。\n\n\n中文医疗评测 - WiNEval\n----------------\n\n\n更新时间：2024-04-23\n\n\n\n*MCKQuiz（客观题）：17个科目分类13060选择题；输入问题和选项，让模型输出答案。根据标准答案判断对错，统计准确率。*\n\n\n*MSceQA（主观题）：由细分领域场景题目构成，包含八大业务场景，17个一级分类和32个二级分类。使用人工/模型对模型的回答进行准确性、相关性、一致性、完整性、权威性评价，并参照标准答案对模型生成的答案进行评分。*\n\n\n其他WiNEval评测结果", "### 企业服务\n\n\n通过WiNGPT测试平台申请密钥或与我们取得联系\n\n\n局限性与免责声明\n--------\n\n\n(a) WiNGPT2 是一个专业医疗领域的大语言模型，可为一般用户提供拟人化AI医生问诊和问答功能，以及一般医学领域的知识问答。对于专业医疗人士，WiNGPT2 提供关于患者病情的诊断、用药和健康建议等方面的回答的建议仅供参考。\n\n\n(b) 您应理解 WiNGPT2 仅提供信息和建议，不能替代医疗专业人士的意见、诊断或治疗建议。在使用 WiNGPT2 的信息之前，请寻求医生或其他医疗专业人员的建议，并独立评估所提供的信息。\n\n\n(c) WiNGPT2 的信息可能存在错误或不准确。卫宁健康不对 WiNGPT2 的准确性、可靠性、完整性、质量、安全性、及时性、性能或适用性提供任何明示或暗示的保证。使用 WiNGPT2 所产生的结果和决策由您自行承担。第三方原因而给您造成的损害结果承担责任。\n\n\n许可证\n---\n\n\n1. 本项目授权协议为 Apache License 2.0，模型权重需要遵守基础模型 Llama-3-8B 相关协议及其许可证，详细内容参照其网站。\n2. 使用本项目包括模型权重时请引用本项目：URL\n\n\n联系我们\n----\n\n\n网站：URL\n\n\n邮箱：wair@URL" ]

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

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3.0", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #gpt2 #text-generation #generated_from_trainer #base_model-distilgpt2 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3.0", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "transformers", "safetensors", "mt5", "text2text-generation", "legal", "vi", "dataset:NghiemAbe/doc2query", "arxiv:1904.08375", "arxiv:2104.08663", "arxiv:2112.07577", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "1904.08375", "2104.08663", "2112.07577" ]

[ "vi" ]

[ "# NghiemAbe/Law-Doc2Query\n\nThis is a doc2query model based on mT5 (also known as docT5query).\n\nIt can be used for:\n- Document expansion: You generate for your paragraphs 20-40 queries and index the paragraphs and the generates queries in a standard BM25 index like Elasticsearch, OpenSearch, or Lucene. The generated queries help to close the lexical gap of lexical search, as the generate queries contain synonyms. Further, it re-weights words giving important words a higher weight even if they appear seldomn in a paragraph. In our BEIR paper we showed that BM25+docT5query is a powerful search engine. In the BEIR repository we have an example how to use docT5query with Pyserini.\n- Domain Specific Training Data Generation: It can be used to generate training data to learn an embedding model. In our GPL-Paper / GPL Example on URL we have an example how to use the model to generate (query, text) pairs for a given collection of unlabeled texts. These pairs can then be used to train powerful dense embedding models.", "## Usage\n\n\nNote: 'model.generate()' is non-deterministic for top_k/top_n sampling. It produces different queries each time you run it.", "## Training\nThis model fine-tuned doc2query/msmarco-vietnamese-mt5-base-v1 for 4k training steps (4 epochs on the 2k5 training pairs from Legal)." ]

[ "TAGS\n#transformers #safetensors #mt5 #text2text-generation #legal #vi #dataset-NghiemAbe/doc2query #arxiv-1904.08375 #arxiv-2104.08663 #arxiv-2112.07577 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# NghiemAbe/Law-Doc2Query\n\nThis is a doc2query model based on mT5 (also known as docT5query).\n\nIt can be used for:\n- Document expansion: You generate for your paragraphs 20-40 queries and index the paragraphs and the generates queries in a standard BM25 index like Elasticsearch, OpenSearch, or Lucene. The generated queries help to close the lexical gap of lexical search, as the generate queries contain synonyms. Further, it re-weights words giving important words a higher weight even if they appear seldomn in a paragraph. In our BEIR paper we showed that BM25+docT5query is a powerful search engine. In the BEIR repository we have an example how to use docT5query with Pyserini.\n- Domain Specific Training Data Generation: It can be used to generate training data to learn an embedding model. In our GPL-Paper / GPL Example on URL we have an example how to use the model to generate (query, text) pairs for a given collection of unlabeled texts. These pairs can then be used to train powerful dense embedding models.", "## Usage\n\n\nNote: 'model.generate()' is non-deterministic for top_k/top_n sampling. It produces different queries each time you run it.", "## Training\nThis model fine-tuned doc2query/msmarco-vietnamese-mt5-base-v1 for 4k training steps (4 epochs on the 2k5 training pairs from Legal)." ]

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

[]

[]

[ "# robust_llm_pythia-31m_mz-130_PasswordMatch_n-its-10-seed-0\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-130_PasswordMatch_n-its-10-seed-0\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" ]

[ "safetensors", "region:us" ]

[]

[]

[ "# Hebrew Questions and Answers Dataset\n\nDataset created by Hebrew Question Answering Dataset\n\nAdjusted by Yuval Avidani, 2024", "## Description\nThis dataset is a comprehensive collection of Hebrew question and answer pairs covering a wide range of topics, derived from multiple reliable sources. It is specifically curated to support research and applications in the field of natural language processing, especially for Hebrew language understanding.", "### Source\nThis dataset has been compiled and adapted from the Hebrew Question Answering Dataset repository, which is available under the Creative Commons Attribution 4.0 International License.", "## Dataset Structure", "### Data Fields\n- 'question': The question text in Hebrew.\n- 'answer': The corresponding answer text in Hebrew.", "### Data Splits\nThe dataset is split into training, validation, and testing sets to facilitate machine learning applications and model evaluations.", "## Usage\nThis dataset can be utilized for a variety of NLP tasks, including but not limited to, question answering systems, chatbots, and other applications requiring understanding of natural language in Hebrew.", "## Licensing\nThis work is based on data from the Hebrew Question Answering Dataset and is licensed under the Creative Commons Attribution 4.0 International (CC BY 4.0) license. You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.", "### More about CC BY 4.0 License\nThis license lets others distribute, remix, adapt, and build upon this work, even commercially, as long as they credit the creator for the original creation. This is the most accommodating of licenses offered, in terms of what others can do with the works licensed under it.\n\nFor more details, see the full CC BY 4.0 License here: Creative Commons Attribution 4.0 International License.\n\nIf you use this dataset in your research, please cite it using the following format:", "## Contact\nFor any questions or issues, please open an issue on the dataset repository or contact Yuval Avidani at yuval.avidani@URL." ]

[ "TAGS\n#safetensors #region-us \n", "# Hebrew Questions and Answers Dataset\n\nDataset created by Hebrew Question Answering Dataset\n\nAdjusted by Yuval Avidani, 2024", "## Description\nThis dataset is a comprehensive collection of Hebrew question and answer pairs covering a wide range of topics, derived from multiple reliable sources. It is specifically curated to support research and applications in the field of natural language processing, especially for Hebrew language understanding.", "### Source\nThis dataset has been compiled and adapted from the Hebrew Question Answering Dataset repository, which is available under the Creative Commons Attribution 4.0 International License.", "## Dataset Structure", "### Data Fields\n- 'question': The question text in Hebrew.\n- 'answer': The corresponding answer text in Hebrew.", "### Data Splits\nThe dataset is split into training, validation, and testing sets to facilitate machine learning applications and model evaluations.", "## Usage\nThis dataset can be utilized for a variety of NLP tasks, including but not limited to, question answering systems, chatbots, and other applications requiring understanding of natural language in Hebrew.", "## Licensing\nThis work is based on data from the Hebrew Question Answering Dataset and is licensed under the Creative Commons Attribution 4.0 International (CC BY 4.0) license. You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.", "### More about CC BY 4.0 License\nThis license lets others distribute, remix, adapt, and build upon this work, even commercially, as long as they credit the creator for the original creation. This is the most accommodating of licenses offered, in terms of what others can do with the works licensed under it.\n\nFor more details, see the full CC BY 4.0 License here: Creative Commons Attribution 4.0 International License.\n\nIf you use this dataset in your research, please cite it using the following format:", "## Contact\nFor any questions or issues, please open an issue on the dataset repository or contact Yuval Avidani at yuval.avidani@URL." ]

[ "peft", "tensorboard", "safetensors", "mistral", "trl", "sft", "generated_from_trainer", "dataset:generator", "base_model:mistralai/Mistral-7B-Instruct-v0.2", "license:apache-2.0", "4-bit", "region:us" ]

[]

[]

[ "# sharan-coh-multi-docs-peft-3-mistral-7b-instruct-v0.2-v1\n\nThis model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on the generator dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0002\n- train_batch_size: 4\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 8\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: constant\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 20\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- PEFT 0.10.0\n- Transformers 4.40.1\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "TAGS\n#peft #tensorboard #safetensors #mistral #trl #sft #generated_from_trainer #dataset-generator #base_model-mistralai/Mistral-7B-Instruct-v0.2 #license-apache-2.0 #4-bit #region-us \n", "# sharan-coh-multi-docs-peft-3-mistral-7b-instruct-v0.2-v1\n\nThis model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on the generator dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0002\n- train_batch_size: 4\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 8\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: constant\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 20\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- PEFT 0.10.0\n- Transformers 4.40.1\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "transformers", "safetensors", "llama", "text-generation", "conversational", "en", "license:cc-by-nc-4.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[ "en" ]

[ "# WebSquareAI-Instruct-llama-3-8B-v0.5.39", "## Model Details\n\nDeveloped by \nInswave Systems UI Platform Team\n\nBase Model\nmeta-llama/Meta-Llama-3-8B\n\n---" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #conversational #en #license-cc-by-nc-4.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# WebSquareAI-Instruct-llama-3-8B-v0.5.39", "## Model Details\n\nDeveloped by \nInswave Systems UI Platform Team\n\nBase Model\nmeta-llama/Meta-Llama-3-8B\n\n---" ]

[ "transformers", "safetensors", "camembert", "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 #camembert #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", "pytorch", "bert", "text-classification", "en", "arxiv:2310.09219", "autotrain_compatible", "endpoints_compatible", "has_space", "region:us" ]

[ "2310.09219" ]

[ "en" ]

[ "# Language Agency Classifier\n\nThe Language Agency Classifier was created by (Wan et al., 2023) and aims to classify sentences based on the level of agency expressed in each sentence. \nClassifying sentence agency can help expose latent gender bias, where women may be \ndescribed with more communal (community-oriented) words and men may be described with more agentic (self/leadership-oriented) words.\n\nThe Language Agency Classifier is implemented with a BERT model architecture given an 80/10/10 train/dev/test split. We performed hyperparameter search\nand ended up with a learning rate of 2e^-5, train for 10 epochs, and have a batch size of 16.\n\nIn the dataset (Language Agency Classifier Dataset), the initial biography is \nsampled from the Bias in Bios dataset (De-Arteaga et al., 2019a), which is sourced from online biographies in the Common Crawl corpus. We prompt ChatGPT \nto rephrase the initial briography into two versions: one leaning towards agentic language style and another leaning towards communal language style.\n\nAn example usage of the model is below.", "### Model Sources\n\n\n\n- Repository: biases-llm-reference-letters\n- Paper: \"Kelly is a Warm Person, Joseph is a Role Model\"\n- Demo: LLMReferenceLetterBias", "## Model Card Authors\n\nThis repository is organized by Miri Liu (github: emmatliu)." ]

[ "TAGS\n#transformers #pytorch #bert #text-classification #en #arxiv-2310.09219 #autotrain_compatible #endpoints_compatible #has_space #region-us \n", "# Language Agency Classifier\n\nThe Language Agency Classifier was created by (Wan et al., 2023) and aims to classify sentences based on the level of agency expressed in each sentence. \nClassifying sentence agency can help expose latent gender bias, where women may be \ndescribed with more communal (community-oriented) words and men may be described with more agentic (self/leadership-oriented) words.\n\nThe Language Agency Classifier is implemented with a BERT model architecture given an 80/10/10 train/dev/test split. We performed hyperparameter search\nand ended up with a learning rate of 2e^-5, train for 10 epochs, and have a batch size of 16.\n\nIn the dataset (Language Agency Classifier Dataset), the initial biography is \nsampled from the Bias in Bios dataset (De-Arteaga et al., 2019a), which is sourced from online biographies in the Common Crawl corpus. We prompt ChatGPT \nto rephrase the initial briography into two versions: one leaning towards agentic language style and another leaning towards communal language style.\n\nAn example usage of the model is below.", "### Model Sources\n\n\n\n- Repository: biases-llm-reference-letters\n- Paper: \"Kelly is a Warm Person, Joseph is a Role Model\"\n- Demo: LLMReferenceLetterBias", "## Model Card Authors\n\nThis repository is organized by Miri Liu (github: emmatliu)." ]

[ "transformers", "gguf", "en", "base_model:LeroyDyer/Mixtral_AI_Llama", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #en #base_model-LeroyDyer/Mixtral_AI_Llama #endpoints_compatible #region-us \n" ]

[ "transformers", "tensorboard", "safetensors", "gpt2", "text-generation", "generated_from_trainer", "conversational", "base_model:microsoft/DialoGPT-small", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3.0", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #gpt2 #text-generation #generated_from_trainer #conversational #base_model-microsoft/DialoGPT-small #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3.0", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "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", "tf", "vit", "image-classification", "generated_from_keras_callback", "base_model:google/vit-base-patch16-224-in21k", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* optimizer: {'name': 'AdamWeightDecay', 'learning\\_rate': {'module': 'keras.optimizers.schedules', 'class\\_name': 'PolynomialDecay', 'config': {'initial\\_learning\\_rate': 3e-05, 'decay\\_steps': 40, 'end\\_learning\\_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered\\_name': None}, 'decay': 0.0, 'beta\\_1': 0.9, 'beta\\_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight\\_decay\\_rate': 0.01}\n* training\\_precision: float32", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* TensorFlow 2.15.0\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tf #vit #image-classification #generated_from_keras_callback #base_model-google/vit-base-patch16-224-in21k #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* optimizer: {'name': 'AdamWeightDecay', 'learning\\_rate': {'module': 'keras.optimizers.schedules', 'class\\_name': 'PolynomialDecay', 'config': {'initial\\_learning\\_rate': 3e-05, 'decay\\_steps': 40, 'end\\_learning\\_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered\\_name': None}, 'decay': 0.0, 'beta\\_1': 0.9, 'beta\\_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight\\_decay\\_rate': 0.01}\n* training\\_precision: float32", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* TensorFlow 2.15.0\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

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

[ "1910.09700" ]

[]

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

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

[ "transformers", "safetensors", "mistral", "text-generation", "question-answering", "en", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #question-answering #en #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n" ]

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

[]

[]

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

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