Datasets:

---

ftopal

/

huggingface-models

like 0

[ "transformers", "tensorboard", "safetensors", "mistral", "text-generation", "trl", "dpo", "generated_from_trainer", "conversational", "base_model:mistralai/Mistral-7B-Instruct-v0.2", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# DPO-PairRM-5-SMI-lr-1e6-iteration-5-t-7e-beta-15e3-1-iteration-baseline-D1-2e-D2_smi-1\n\nThis model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on the None dataset.\nIt achieves the following results on the evaluation set:\n- Loss: 0.7394\n- Rewards/chosen: -2.1682\n- Rewards/rejected: -2.3518\n- Rewards/accuracies: 0.5835\n- Rewards/margins: 0.1836\n- Rewards/mix Margin: 0.0868\n- Logps/rejected: -487.3550\n- Logps/chosen: -484.3013\n- Logits/rejected: -1.8268\n- Logits/chosen: -1.8454", "## 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 #base_model-mistralai/Mistral-7B-Instruct-v0.2 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# DPO-PairRM-5-SMI-lr-1e6-iteration-5-t-7e-beta-15e3-1-iteration-baseline-D1-2e-D2_smi-1\n\nThis model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on the None dataset.\nIt achieves the following results on the evaluation set:\n- Loss: 0.7394\n- Rewards/chosen: -2.1682\n- Rewards/rejected: -2.3518\n- Rewards/accuracies: 0.5835\n- Rewards/margins: 0.1836\n- Rewards/mix Margin: 0.0868\n- Logps/rejected: -487.3550\n- Logps/chosen: -484.3013\n- Logits/rejected: -1.8268\n- Logits/chosen: -1.8454", "## 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" ]

[ "diffusers", "safetensors", "text-to-image", "license:other", "diffusers:StableCascadePriorPipeline", "region:us" ]

[]

[]

[ "### Date:", "### Aesthetic Tags:\n\n\nModel used: shadowlilac/aesthetic-shadow-v2\n\n\nscore greater than: 0.90, tag: extremely aesthetic, count: 125.451\nscore greater than: 0.80, tag: very aesthetic, count: 887.382\nscore greater than: 0.70, tag: aesthetic, count: 1.049.857\nscore greater than: 0.50, tag: slightly aesthetic, count: 1.643.091\nscore greater than: 0.40, tag: not displeasing, count: 569.543\nscore greater than: 0.30, tag: not aesthetic, count: 445.188\nscore greater than: 0.20, tag: slightly displeasing, count: 341.424\nscore greater than: 0.10, tag: displeasing, count: 237.660\nscore greater than: rest of them, tag: very displeasing, count: 328.712", "### Quality Tags:\n\n\nModel used: URL\n\n\nscore greater than: 0.980, tag: best quality, count: 1.270.447\nscore greater than: 0.900, tag: high quality, count: 498.244\nscore greater than: 0.750, tag: great quality, count: 351.006\nscore greater than: 0.500, tag: medium quality, count: 366.448\nscore greater than: 0.250, tag: normal quality, count: 368.380\nscore greater than: 0.125, tag: bad quality, count: 279.050\nscore greater than: 0.025, tag: low quality, count: 538.958\nscore greater than: rest of them, tag: worst quality, count: 1.955.966\n\n\nRating Tags\n-----------\n\n\n\nCustom Tags:\n------------\n\n\n\nTraining Parameters:\n--------------------\n\n\nSoftware used: Kohya SD-Scripts with Stable Cascade branch \n\nURL\n\n\nBase model: Disty0/sote-diffusion-cascade-alpha0", "### Command:\n\n\nLimitations and Bias\n--------------------", "### Bias\n\n\n* This model is intended for anime illustrations. \n\nRealistic capabilites are not tested at all.", "### Limitations\n\n\n* Can fall back to realistic. \n\nAdd \"realistic\" tag to the negatives when this happens.\n* Far shot eyes can be bad.\n* Anatomy and hands can be bad.\n* Still in active training.\n\n\nLicense\n-------\n\n\n(This part is copied directly from Animagine V3.1 and modified.)\n\n\nSoteDiffusion models falls under Fair AI Public License 1.0-SD license, which is compatible with Stable Diffusion models’ license. Key points:\n\n\n1. Modification Sharing: If you modify SoteDiffusion models, you must share both your changes and the original license.\n2. Source Code Accessibility: If your modified version is network-accessible, provide a way (like a download link) for others to get the source code. This applies to derived models too.\n3. Distribution Terms: Any distribution must be under this license or another with similar rules.\n4. Compliance: Non-compliance must be fixed within 30 days to avoid license termination, emphasizing transparency and adherence to open-source values.\n\n\nNotes: Anything not covered by Fair AI license is inherited from Stability AI Non-Commercial license which is named as LICENSE\\_INHERIT. Meaning, still no commercial use of any kind." ]

[ "TAGS\n#diffusers #safetensors #text-to-image #license-other #diffusers-StableCascadePriorPipeline #region-us \n", "### Date:", "### Aesthetic Tags:\n\n\nModel used: shadowlilac/aesthetic-shadow-v2\n\n\nscore greater than: 0.90, tag: extremely aesthetic, count: 125.451\nscore greater than: 0.80, tag: very aesthetic, count: 887.382\nscore greater than: 0.70, tag: aesthetic, count: 1.049.857\nscore greater than: 0.50, tag: slightly aesthetic, count: 1.643.091\nscore greater than: 0.40, tag: not displeasing, count: 569.543\nscore greater than: 0.30, tag: not aesthetic, count: 445.188\nscore greater than: 0.20, tag: slightly displeasing, count: 341.424\nscore greater than: 0.10, tag: displeasing, count: 237.660\nscore greater than: rest of them, tag: very displeasing, count: 328.712", "### Quality Tags:\n\n\nModel used: URL\n\n\nscore greater than: 0.980, tag: best quality, count: 1.270.447\nscore greater than: 0.900, tag: high quality, count: 498.244\nscore greater than: 0.750, tag: great quality, count: 351.006\nscore greater than: 0.500, tag: medium quality, count: 366.448\nscore greater than: 0.250, tag: normal quality, count: 368.380\nscore greater than: 0.125, tag: bad quality, count: 279.050\nscore greater than: 0.025, tag: low quality, count: 538.958\nscore greater than: rest of them, tag: worst quality, count: 1.955.966\n\n\nRating Tags\n-----------\n\n\n\nCustom Tags:\n------------\n\n\n\nTraining Parameters:\n--------------------\n\n\nSoftware used: Kohya SD-Scripts with Stable Cascade branch \n\nURL\n\n\nBase model: Disty0/sote-diffusion-cascade-alpha0", "### Command:\n\n\nLimitations and Bias\n--------------------", "### Bias\n\n\n* This model is intended for anime illustrations. \n\nRealistic capabilites are not tested at all.", "### Limitations\n\n\n* Can fall back to realistic. \n\nAdd \"realistic\" tag to the negatives when this happens.\n* Far shot eyes can be bad.\n* Anatomy and hands can be bad.\n* Still in active training.\n\n\nLicense\n-------\n\n\n(This part is copied directly from Animagine V3.1 and modified.)\n\n\nSoteDiffusion models falls under Fair AI Public License 1.0-SD license, which is compatible with Stable Diffusion models’ license. Key points:\n\n\n1. Modification Sharing: If you modify SoteDiffusion models, you must share both your changes and the original license.\n2. Source Code Accessibility: If your modified version is network-accessible, provide a way (like a download link) for others to get the source code. This applies to derived models too.\n3. Distribution Terms: Any distribution must be under this license or another with similar rules.\n4. Compliance: Non-compliance must be fixed within 30 days to avoid license termination, emphasizing transparency and adherence to open-source values.\n\n\nNotes: Anything not covered by Fair AI license is inherited from Stability AI Non-Commercial license which is named as LICENSE\\_INHERIT. Meaning, still no commercial use of any kind." ]

[ "mlx", "safetensors", "llama", "facebook", "meta", "pytorch", "llama-3", "text-generation", "conversational", "en", "license:other", "region:us" ]

[]

[ "en" ]

[ "# mlx-community/Meta-Llama-3-8B-Instruct-64k-4bit\nThis model was converted to MLX format from ['NurtureAI/Meta-Llama-3-8B-Instruct-64k']() using mlx-lm version 0.11.0.\nRefer to the original model card for more details on the model.", "## Use with mlx" ]

[ "TAGS\n#mlx #safetensors #llama #facebook #meta #pytorch #llama-3 #text-generation #conversational #en #license-other #region-us \n", "# mlx-community/Meta-Llama-3-8B-Instruct-64k-4bit\nThis model was converted to MLX format from ['NurtureAI/Meta-Llama-3-8B-Instruct-64k']() using mlx-lm version 0.11.0.\nRefer to the original model card for more details on the model.", "## Use with mlx" ]

[ "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: FAYSSAL12/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: FAYSSAL12/ppo-Huggy\n 3. Step 2: Select your *.nn /*.onnx file\n 4. Click on Watch the agent play" ]

[ "transformers", "safetensors", "swin", "image-classification", "generated_from_trainer", "dataset:imagefolder", "base_model:microsoft/swin-base-patch4-window7-224-in22k", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 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* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 20", "### Training results", "### Framework versions\n\n\n* Transformers 4.35.0\n* Pytorch 2.1.0\n* Datasets 2.14.6\n* Tokenizers 0.14.1" ]

[ "TAGS\n#transformers #safetensors #swin #image-classification #generated_from_trainer #dataset-imagefolder #base_model-microsoft/swin-base-patch4-window7-224-in22k #license-apache-2.0 #model-index #autotrain_compatible #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 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* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 20", "### Training results", "### Framework versions\n\n\n* Transformers 4.35.0\n* Pytorch 2.1.0\n* Datasets 2.14.6\n* Tokenizers 0.14.1" ]

[ "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" ]

[ "gguf", "facebook", "meta", "pytorch", "llama", "llama-3", "llama-cpp", "gguf-my-repo", "text-generation", "en", "region:us" ]

[]

[ "en" ]

[ "# nullt3r/Llama-3-8b-64k-PoSE-Q8_0-GGUF\nThis model was converted to GGUF format from 'winglian/Llama-3-8b-64k-PoSE' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ "TAGS\n#gguf #facebook #meta #pytorch #llama #llama-3 #llama-cpp #gguf-my-repo #text-generation #en #region-us \n", "# nullt3r/Llama-3-8b-64k-PoSE-Q8_0-GGUF\nThis model was converted to GGUF format from 'winglian/Llama-3-8b-64k-PoSE' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

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

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0001\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 8\n* total\\_train\\_batch\\_size: 64\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\n* Transformers 4.41.0.dev0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#safetensors #generated_from_trainer #base_model-HuggingFaceM4/idefics2-8b #license-apache-2.0 #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0001\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 8\n* total\\_train\\_batch\\_size: 64\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\n* Transformers 4.41.0.dev0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "CartPole-v1", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]

[]

[]

[ "# Reinforce Agent playing CartPole-v1\n This is a trained model of a Reinforce agent playing CartPole-v1 .\n To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: URL" ]

[ "TAGS\n#CartPole-v1 #reinforce #reinforcement-learning #custom-implementation #deep-rl-class #model-index #region-us \n", "# Reinforce Agent playing CartPole-v1\n This is a trained model of a Reinforce agent playing CartPole-v1 .\n To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: URL" ]

[ "transformers", "tensorboard", "safetensors", "t5", "text2text-generation", "generated_from_trainer", "base_model: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: 2e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 2\n* mixed\\_precision\\_training: Native AMP", "### 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-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: 2e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 2\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

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

[]

[]

[ "## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16", "### Framework versions\n\n\n- PEFT 0.4.0" ]

[ "TAGS\n#peft #safetensors #llama #region-us \n", "## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16", "### Framework versions\n\n\n- PEFT 0.4.0" ]

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

[]

[ "en" ]

[ "# Uploaded model\n\n- Developed by: 1024m\n- License: apache-2.0\n- Finetuned from model : unsloth/mistral-7b-bnb-4bit\n\nThis mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #text-generation-inference #unsloth #trl #sft #en #base_model-unsloth/mistral-7b-bnb-4bit #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "# Uploaded model\n\n- Developed by: 1024m\n- License: apache-2.0\n- Finetuned from model : unsloth/mistral-7b-bnb-4bit\n\nThis mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

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

[]

[]

[]

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

[ "gguf", "finetuned", "text-generation", "arxiv:2310.06825", "base_model:mistralai/Mistral-7B-Instruct-v0.2", "license:apache-2.0", "region:us" ]

[ "2310.06825" ]

[]

[ "### About GGUF\n\n\nGGUF is a new format introduced by the URL team on August 21st 2023. It is a replacement for GGML, which is no longer supported by URL.\n\n\nHere is an incomplete list of clients and libraries that are known to support GGUF:\n\n\n* URL. The source project for GGUF. Offers a CLI and a server option.\n* text-generation-webui, the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.\n* KoboldCpp, a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.\n* GPT4All, a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.\n* LM Studio, an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.\n* LoLLMS Web UI, a great web UI with many interesting and unique features, including a full model library for easy model selection.\n* URL, an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.\n* llama-cpp-python, a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.\n* candle, a Rust ML framework with a focus on performance, including GPU support, and ease of use.\n* ctransformers, a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.\n\n\nPrompt template: Mistral\n------------------------\n\n\nProvided files\n--------------\n\n\n\nNote: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.\n\n\nHow to download GGUF files\n--------------------------\n\n\nNote for manual downloaders: You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.\n\n\nThe following clients/libraries will automatically download models for you, providing a list of available models to choose from:\n\n\n* LM Studio\n* LoLLMS Web UI\n* URL", "### In 'text-generation-webui'\n\n\nUnder Download Model, you can enter the model repo: TheBloke/Mistral-7B-Instruct-v0.2-GGUF and below it, a specific filename to download, such as: mistral-7b-instruct-v0.2.Q4\\_K\\_M.gguf.\n\n\nThen click Download.", "### On the command line, including multiple files at once\n\n\nI recommend using the 'huggingface-hub' Python library:\n\n\nThen you can download any individual model file to the current directory, at high speed, with a command like this:\n\n\n\nMore advanced huggingface-cli download usage (click to read)\nYou can also download multiple files at once with a pattern:\n\n\nFor more documentation on downloading with 'huggingface-cli', please see: HF -> Hub Python Library -> Download files -> Download from the CLI.\n\n\nTo accelerate downloads on fast connections (1Gbit/s or higher), install 'hf\\_transfer':\n\n\nAnd set environment variable 'HF\\_HUB\\_ENABLE\\_HF\\_TRANSFER' to '1':\n\n\nWindows Command Line users: You can set the environment variable by running 'set HF\\_HUB\\_ENABLE\\_HF\\_TRANSFER=1' before the download command.\n\n\n\nExample 'URL' command\n---------------------\n\n\nMake sure you are using 'URL' from commit d0cee0d or later.\n\n\nChange '-ngl 32' to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.\n\n\nChange '-c 32768' to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by URL automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.\n\n\nIf you want to have a chat-style conversation, replace the '-p ' argument with '-i -ins'\n\n\nFor other parameters and how to use them, please refer to the URL documentation\n\n\nHow to run in 'text-generation-webui'\n-------------------------------------\n\n\nFurther instructions can be found in the text-generation-webui documentation, here: text-generation-webui/docs/04 ‐ Model URL.\n\n\nHow to run from Python code\n---------------------------\n\n\nYou can use GGUF models from Python using the llama-cpp-python or ctransformers libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.", "### How to load this model in Python code, using llama-cpp-python\n\n\nFor full documentation, please see: llama-cpp-python docs.", "#### First install the package\n\n\nRun one of the following commands, according to your system:", "#### Simple llama-cpp-python example code\n\n\nHow to use with LangChain\n-------------------------\n\n\nHere are guides on using llama-cpp-python and ctransformers with LangChain:\n\n\n* LangChain + llama-cpp-python\n* LangChain + ctransformers\n\n\nOriginal model card: Mistral AI\\_'s Mistral 7B Instruct v0.2\n============================================================\n\n\nModel Card for Mistral-7B-Instruct-v0.2\n=======================================\n\n\nThe Mistral-7B-Instruct-v0.2 Large Language Model (LLM) is an improved instruct fine-tuned version of Mistral-7B-Instruct-v0.1.\n\n\nFor full details of this model please read our paper and release blog post.\n\n\nInstruction format\n------------------\n\n\nIn order to leverage instruction fine-tuning, your prompt should be surrounded by '[INST]' and '[/INST]' tokens. The very first instruction should begin with a begin of sentence id. The next instructions should not. The assistant generation will be ended by the end-of-sentence token id.\n\n\nE.g.\n\n\nThis format is available as a chat template via the 'apply\\_chat\\_template()' method:\n\n\nModel Architecture\n------------------\n\n\nThis instruction model is based on Mistral-7B-v0.1, a transformer model with the following architecture choices:\n\n\n* Grouped-Query Attention\n* Sliding-Window Attention\n* Byte-fallback BPE tokenizer\n\n\nTroubleshooting\n---------------\n\n\n* If you see the following error:\n\n\nInstalling transformers from source should solve the issue\npip install git+URL\n\n\nThis should not be required after transformers-v4.33.4.\n\n\nLimitations\n-----------\n\n\nThe Mistral 7B Instruct model is a quick demonstration that the base model can be easily fine-tuned to achieve compelling performance.\nIt does not have any moderation mechanisms. We're looking forward to engaging with the community on ways to\nmake the model finely respect guardrails, allowing for deployment in environments requiring moderated outputs.\n\n\nThe Mistral AI Team\n-------------------\n\n\nAlbert Jiang, Alexandre Sablayrolles, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Lélio Renard Lavaud, Louis Ternon, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Théophile Gervet, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed." ]

[ "TAGS\n#gguf #finetuned #text-generation #arxiv-2310.06825 #base_model-mistralai/Mistral-7B-Instruct-v0.2 #license-apache-2.0 #region-us \n", "### About GGUF\n\n\nGGUF is a new format introduced by the URL team on August 21st 2023. It is a replacement for GGML, which is no longer supported by URL.\n\n\nHere is an incomplete list of clients and libraries that are known to support GGUF:\n\n\n* URL. The source project for GGUF. Offers a CLI and a server option.\n* text-generation-webui, the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.\n* KoboldCpp, a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.\n* GPT4All, a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.\n* LM Studio, an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.\n* LoLLMS Web UI, a great web UI with many interesting and unique features, including a full model library for easy model selection.\n* URL, an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.\n* llama-cpp-python, a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.\n* candle, a Rust ML framework with a focus on performance, including GPU support, and ease of use.\n* ctransformers, a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.\n\n\nPrompt template: Mistral\n------------------------\n\n\nProvided files\n--------------\n\n\n\nNote: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.\n\n\nHow to download GGUF files\n--------------------------\n\n\nNote for manual downloaders: You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.\n\n\nThe following clients/libraries will automatically download models for you, providing a list of available models to choose from:\n\n\n* LM Studio\n* LoLLMS Web UI\n* URL", "### In 'text-generation-webui'\n\n\nUnder Download Model, you can enter the model repo: TheBloke/Mistral-7B-Instruct-v0.2-GGUF and below it, a specific filename to download, such as: mistral-7b-instruct-v0.2.Q4\\_K\\_M.gguf.\n\n\nThen click Download.", "### On the command line, including multiple files at once\n\n\nI recommend using the 'huggingface-hub' Python library:\n\n\nThen you can download any individual model file to the current directory, at high speed, with a command like this:\n\n\n\nMore advanced huggingface-cli download usage (click to read)\nYou can also download multiple files at once with a pattern:\n\n\nFor more documentation on downloading with 'huggingface-cli', please see: HF -> Hub Python Library -> Download files -> Download from the CLI.\n\n\nTo accelerate downloads on fast connections (1Gbit/s or higher), install 'hf\\_transfer':\n\n\nAnd set environment variable 'HF\\_HUB\\_ENABLE\\_HF\\_TRANSFER' to '1':\n\n\nWindows Command Line users: You can set the environment variable by running 'set HF\\_HUB\\_ENABLE\\_HF\\_TRANSFER=1' before the download command.\n\n\n\nExample 'URL' command\n---------------------\n\n\nMake sure you are using 'URL' from commit d0cee0d or later.\n\n\nChange '-ngl 32' to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.\n\n\nChange '-c 32768' to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by URL automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.\n\n\nIf you want to have a chat-style conversation, replace the '-p ' argument with '-i -ins'\n\n\nFor other parameters and how to use them, please refer to the URL documentation\n\n\nHow to run in 'text-generation-webui'\n-------------------------------------\n\n\nFurther instructions can be found in the text-generation-webui documentation, here: text-generation-webui/docs/04 ‐ Model URL.\n\n\nHow to run from Python code\n---------------------------\n\n\nYou can use GGUF models from Python using the llama-cpp-python or ctransformers libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.", "### How to load this model in Python code, using llama-cpp-python\n\n\nFor full documentation, please see: llama-cpp-python docs.", "#### First install the package\n\n\nRun one of the following commands, according to your system:", "#### Simple llama-cpp-python example code\n\n\nHow to use with LangChain\n-------------------------\n\n\nHere are guides on using llama-cpp-python and ctransformers with LangChain:\n\n\n* LangChain + llama-cpp-python\n* LangChain + ctransformers\n\n\nOriginal model card: Mistral AI\\_'s Mistral 7B Instruct v0.2\n============================================================\n\n\nModel Card for Mistral-7B-Instruct-v0.2\n=======================================\n\n\nThe Mistral-7B-Instruct-v0.2 Large Language Model (LLM) is an improved instruct fine-tuned version of Mistral-7B-Instruct-v0.1.\n\n\nFor full details of this model please read our paper and release blog post.\n\n\nInstruction format\n------------------\n\n\nIn order to leverage instruction fine-tuning, your prompt should be surrounded by '[INST]' and '[/INST]' tokens. The very first instruction should begin with a begin of sentence id. The next instructions should not. The assistant generation will be ended by the end-of-sentence token id.\n\n\nE.g.\n\n\nThis format is available as a chat template via the 'apply\\_chat\\_template()' method:\n\n\nModel Architecture\n------------------\n\n\nThis instruction model is based on Mistral-7B-v0.1, a transformer model with the following architecture choices:\n\n\n* Grouped-Query Attention\n* Sliding-Window Attention\n* Byte-fallback BPE tokenizer\n\n\nTroubleshooting\n---------------\n\n\n* If you see the following error:\n\n\nInstalling transformers from source should solve the issue\npip install git+URL\n\n\nThis should not be required after transformers-v4.33.4.\n\n\nLimitations\n-----------\n\n\nThe Mistral 7B Instruct model is a quick demonstration that the base model can be easily fine-tuned to achieve compelling performance.\nIt does not have any moderation mechanisms. We're looking forward to engaging with the community on ways to\nmake the model finely respect guardrails, allowing for deployment in environments requiring moderated outputs.\n\n\nThe Mistral AI Team\n-------------------\n\n\nAlbert Jiang, Alexandre Sablayrolles, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Lélio Renard Lavaud, Louis Ternon, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Théophile Gervet, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed." ]

[ "transformers", "safetensors", "mistral", "text-generation", "merge", "mergekit", "lazymergekit", "kaist-ai/mistral-orpo-capybara-7k", "argilla/CapybaraHermes-2.5-Mistral-7B", "conversational", "en", "base_model:kaist-ai/mistral-orpo-capybara-7k", "base_model:argilla/CapybaraHermes-2.5-Mistral-7B", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[ "en" ]

[ "# KangalKhan-Alpha-Sapphiroid-7B-Fixed\n\nKangalKhan-Alpha-Sapphiroid-7B-Fixed is a merge of the following models using LazyMergekit:\n* kaist-ai/mistral-orpo-capybara-7k\n* argilla/CapybaraHermes-2.5-Mistral-7B", "## Configuration", "## Usage" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #merge #mergekit #lazymergekit #kaist-ai/mistral-orpo-capybara-7k #argilla/CapybaraHermes-2.5-Mistral-7B #conversational #en #base_model-kaist-ai/mistral-orpo-capybara-7k #base_model-argilla/CapybaraHermes-2.5-Mistral-7B #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# KangalKhan-Alpha-Sapphiroid-7B-Fixed\n\nKangalKhan-Alpha-Sapphiroid-7B-Fixed is a merge of the following models using LazyMergekit:\n* kaist-ai/mistral-orpo-capybara-7k\n* argilla/CapybaraHermes-2.5-Mistral-7B", "## Configuration", "## Usage" ]

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

[]

[]

[]

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

[ "transformers", "safetensors", "gguf", "llama", "text-generation", "GGUF", "llama-3", "Q4_K_M", "Q5_K_M", "meta", "facebook", "quantized", "8b", "conversational", "license:other", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "### About GGUF quantization using URL\n\n\n* URL github repo: URL github repo\n* llama-cpp-python github repo: llama-cpp-python\n\n\nHow to Get Started with the Model\n=================================\n\n\nUse the code below to get started with the model. This code uses llama-cpp-python\n\n\nOriginal Meta's Llama-3 Model Card:\n-----------------------------------\n\n\nMeta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. Further, in developing these models, we took great care to optimize helpfulness and safety.\n\n\nModel developers Meta\n\n\nVariations Llama 3 comes in two sizes — 8B and 70B parameters — in pre-trained and instruction tuned variants.\n\n\nInput Models input text only.\n\n\nOutput Models generate text and code only.\n\n\nModel Architecture Llama 3 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.\n\n\n\nLlama 3 family of models. Token counts refer to pretraining data only. Both the 8 and 70B versions use Grouped-Query Attention (GQA) for improved inference scalability.\n\n\nModel Release Date April 18, 2024.\n\n\nStatus This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback.\n\n\nLicense A custom commercial license is available at: URL\n\n\nWhere to send questions or comments about the model Instructions on how to provide feedback or comments on the model can be found in the model README. For more technical information about generation parameters and recipes for how to use Llama 3 in applications, please go here.\n\n\nIntended Use\n------------\n\n\nIntended Use Cases Llama 3 is intended for commercial and research use in English. Instruction tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.\n\n\nOut-of-scope Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3 Community License. Use in languages other than English.\n\n\nNote: Developers may fine-tune Llama 3 models for languages beyond English provided they comply with the Llama 3 Community License and the Acceptable Use Policy.\n\n\nHow to use\n----------\n\n\nThis repository contains two versions of Meta-Llama-3-8B-Instruct, for use with transformers and with the original 'llama3' codebase.", "### Use with transformers\n\n\nYou can run conversational inference using the Transformers pipeline abstraction, or by leveraging the Auto classes with the 'generate()' function. Let's see examples of both.", "#### Transformers pipeline", "#### Transformers AutoModelForCausalLM", "### Use with 'llama3'\n\n\nPlease, follow the instructions in the repository\n\n\nTo download Original checkpoints, see the example command below leveraging 'huggingface-cli':\n\n\nFor Hugging Face support, we recommend using transformers or TGI, but a similar command works.\n\n\nHardware and Software\n---------------------\n\n\nTraining Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.\n\n\nCarbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.\n\n\n\nCO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.\n\n\nTraining Data\n-------------\n\n\nOverview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.\n\n\nData Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.\n\n\nBenchmarks\n----------\n\n\nIn this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see here.", "### Base pretrained models", "### Instruction tuned models", "### Responsibility & Safety\n\n\nWe believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.\n\n\nFoundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.\n\n\nRather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.\n\n\nAs part of the Llama 3 release, we updated our Responsible Use Guide to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including Meta Llama Guard 2 and Code Shield safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a reference implementation to get you started.", "#### Llama 3-Instruct\n\n\nAs outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.\n\n\nSafety\n\n\nFor our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.\n\n\nRefusals\n\n\nIn addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.\n\n\nWe built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.", "#### Responsible release\n\n\nIn addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.\n\n\nMisuse\n\n\nIf you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at URL", "#### Critical risks\n\n\nCBRNE (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)\n\n\nWe have conducted a two fold assessment of the safety of the model in this area:\n\n\n* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.\n* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).", "### Cyber Security\n\n\nWe have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of equivalent coding capability.", "### Child Safety\n\n\nChild Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.", "### Community\n\n\nGenerative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our Github repository.\n\n\nFinally, we put in place a set of resources including an output reporting mechanism and bug bounty program to continuously improve the Llama technology with the help of the community.\n\n\nEthical Considerations and Limitations\n--------------------------------------\n\n\nThe core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.\n\n\nBut Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating Purple Llama solutions into your workflows and specifically Llama Guard which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.\n\n\nPlease see the Responsible Use Guide available at URL\n\n\ninstructions\n\n\n@article{llama3modelcard,\n\n\ntitle={Llama 3 Model Card},\n\n\nauthor={AI@Meta},\n\n\nyear={2024},\n\n\nurl = {URL\n\n\n}\n\n\nContributors\n------------\n\n\nAaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos" ]

[ "TAGS\n#transformers #safetensors #gguf #llama #text-generation #GGUF #llama-3 #Q4_K_M #Q5_K_M #meta #facebook #quantized #8b #conversational #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "### About GGUF quantization using URL\n\n\n* URL github repo: URL github repo\n* llama-cpp-python github repo: llama-cpp-python\n\n\nHow to Get Started with the Model\n=================================\n\n\nUse the code below to get started with the model. This code uses llama-cpp-python\n\n\nOriginal Meta's Llama-3 Model Card:\n-----------------------------------\n\n\nMeta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. Further, in developing these models, we took great care to optimize helpfulness and safety.\n\n\nModel developers Meta\n\n\nVariations Llama 3 comes in two sizes — 8B and 70B parameters — in pre-trained and instruction tuned variants.\n\n\nInput Models input text only.\n\n\nOutput Models generate text and code only.\n\n\nModel Architecture Llama 3 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.\n\n\n\nLlama 3 family of models. Token counts refer to pretraining data only. Both the 8 and 70B versions use Grouped-Query Attention (GQA) for improved inference scalability.\n\n\nModel Release Date April 18, 2024.\n\n\nStatus This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback.\n\n\nLicense A custom commercial license is available at: URL\n\n\nWhere to send questions or comments about the model Instructions on how to provide feedback or comments on the model can be found in the model README. For more technical information about generation parameters and recipes for how to use Llama 3 in applications, please go here.\n\n\nIntended Use\n------------\n\n\nIntended Use Cases Llama 3 is intended for commercial and research use in English. Instruction tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.\n\n\nOut-of-scope Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3 Community License. Use in languages other than English.\n\n\nNote: Developers may fine-tune Llama 3 models for languages beyond English provided they comply with the Llama 3 Community License and the Acceptable Use Policy.\n\n\nHow to use\n----------\n\n\nThis repository contains two versions of Meta-Llama-3-8B-Instruct, for use with transformers and with the original 'llama3' codebase.", "### Use with transformers\n\n\nYou can run conversational inference using the Transformers pipeline abstraction, or by leveraging the Auto classes with the 'generate()' function. Let's see examples of both.", "#### Transformers pipeline", "#### Transformers AutoModelForCausalLM", "### Use with 'llama3'\n\n\nPlease, follow the instructions in the repository\n\n\nTo download Original checkpoints, see the example command below leveraging 'huggingface-cli':\n\n\nFor Hugging Face support, we recommend using transformers or TGI, but a similar command works.\n\n\nHardware and Software\n---------------------\n\n\nTraining Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.\n\n\nCarbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.\n\n\n\nCO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.\n\n\nTraining Data\n-------------\n\n\nOverview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.\n\n\nData Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.\n\n\nBenchmarks\n----------\n\n\nIn this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see here.", "### Base pretrained models", "### Instruction tuned models", "### Responsibility & Safety\n\n\nWe believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.\n\n\nFoundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.\n\n\nRather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.\n\n\nAs part of the Llama 3 release, we updated our Responsible Use Guide to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including Meta Llama Guard 2 and Code Shield safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a reference implementation to get you started.", "#### Llama 3-Instruct\n\n\nAs outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.\n\n\nSafety\n\n\nFor our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.\n\n\nRefusals\n\n\nIn addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.\n\n\nWe built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.", "#### Responsible release\n\n\nIn addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.\n\n\nMisuse\n\n\nIf you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at URL", "#### Critical risks\n\n\nCBRNE (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)\n\n\nWe have conducted a two fold assessment of the safety of the model in this area:\n\n\n* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.\n* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).", "### Cyber Security\n\n\nWe have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of equivalent coding capability.", "### Child Safety\n\n\nChild Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.", "### Community\n\n\nGenerative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our Github repository.\n\n\nFinally, we put in place a set of resources including an output reporting mechanism and bug bounty program to continuously improve the Llama technology with the help of the community.\n\n\nEthical Considerations and Limitations\n--------------------------------------\n\n\nThe core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.\n\n\nBut Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating Purple Llama solutions into your workflows and specifically Llama Guard which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.\n\n\nPlease see the Responsible Use Guide available at URL\n\n\ninstructions\n\n\n@article{llama3modelcard,\n\n\ntitle={Llama 3 Model Card},\n\n\nauthor={AI@Meta},\n\n\nyear={2024},\n\n\nurl = {URL\n\n\n}\n\n\nContributors\n------------\n\n\nAaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos" ]

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

[]

[]

[]

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

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

[]

[]

[]

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

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

[]

[]

[]

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

[ "peft", "safetensors", "generated_from_trainer", "base_model:TheBloke/Llama-2-7B-fp16", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0003\n* train\\_batch\\_size: 2\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 10\n* total\\_train\\_batch\\_size: 20\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 350", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.36.2\n* Pytorch 2.2.2+cu121\n* Datasets 2.19.0\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-TheBloke/Llama-2-7B-fp16 #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: 2\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 10\n* total\\_train\\_batch\\_size: 20\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 350", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.36.2\n* Pytorch 2.2.2+cu121\n* Datasets 2.19.0\n* Tokenizers 0.15.2" ]

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

[]

[ "en" ]

[ "# Uploaded model\n\n- Developed by: 1024m\n- License: apache-2.0\n- Task WASSA Shared Task 1A 2024\n- Finetuned from model : unsloth/mistral-7b-bnb-4bit\n\nThis mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>\n\nprompt format :\n\n-\"\"\"Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request. \n-### Instruction: \n-{Given the input text , classify it based on what emotion is being exibited among the following : Joy/Neutral/Anger/Love/Sadness/Fear. Respond with only one emotion only among the options given. Respond with ONLY ONE word and nothing else. } \n-### Input: \n-{} ( add input text here and remove this text ) \n-### Response: \n-{} ( leave blank and remove this text ) \"\"\"" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #text-generation-inference #unsloth #trl #sft #en #base_model-unsloth/mistral-7b-bnb-4bit #license-apache-2.0 #autotrain_compatible #endpoints_compatible #4-bit #region-us \n", "# Uploaded model\n\n- Developed by: 1024m\n- License: apache-2.0\n- Task WASSA Shared Task 1A 2024\n- Finetuned from model : unsloth/mistral-7b-bnb-4bit\n\nThis mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>\n\nprompt format :\n\n-\"\"\"Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request. \n-### Instruction: \n-{Given the input text , classify it based on what emotion is being exibited among the following : Joy/Neutral/Anger/Love/Sadness/Fear. Respond with only one emotion only among the options given. Respond with ONLY ONE word and nothing else. } \n-### Input: \n-{} ( add input text here and remove this text ) \n-### Response: \n-{} ( leave blank and remove this text ) \"\"\"" ]

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

[]

[]

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

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

[ "peft", "arxiv:1910.09700", "base_model:tiiuae/falcon-7b", "region:us" ]

[ "1910.09700" ]

[]

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

[ "TAGS\n#peft #arxiv-1910.09700 #base_model-tiiuae/falcon-7b #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" ]

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

[]

[]

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

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

[ "peft", "llama", "generated_from_trainer", "base_model:NousResearch/Meta-Llama-3-70B", "license:other", "4-bit", "region:us" ]

[]

[]

[ "# 2-qlora-out-l3-10\n\nThis model is a fine-tuned version of NousResearch/Meta-Llama-3-70B 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: 1.5e-05\n- train_batch_size: 2\n- eval_batch_size: 2\n- seed: 246\n- distributed_type: multi-GPU\n- num_devices: 8\n- total_train_batch_size: 16\n- total_eval_batch_size: 16\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- num_epochs: 4", "### Training results", "### Framework versions\n\n- PEFT 0.10.0\n- Transformers 4.40.0.dev0\n- Pytorch 2.2.1\n- Datasets 2.15.0\n- Tokenizers 0.15.0" ]

[ "TAGS\n#peft #llama #generated_from_trainer #base_model-NousResearch/Meta-Llama-3-70B #license-other #4-bit #region-us \n", "# 2-qlora-out-l3-10\n\nThis model is a fine-tuned version of NousResearch/Meta-Llama-3-70B 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: 1.5e-05\n- train_batch_size: 2\n- eval_batch_size: 2\n- seed: 246\n- distributed_type: multi-GPU\n- num_devices: 8\n- total_train_batch_size: 16\n- total_eval_batch_size: 16\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- num_epochs: 4", "### Training results", "### Framework versions\n\n- PEFT 0.10.0\n- Transformers 4.40.0.dev0\n- Pytorch 2.2.1\n- Datasets 2.15.0\n- Tokenizers 0.15.0" ]

[ "arxiv:2308.13137", "license:mit", "region:us" ]

[ "2308.13137" ]

[]

[]

[ "TAGS\n#arxiv-2308.13137 #license-mit #region-us \n" ]

[ "sentence-transformers", "onnx", "safetensors", "nomic_bert", "feature-extraction", "sentence-similarity", "mteb", "transformers", "transformers.js", "custom_code", "arxiv:2205.13147", "arxiv:2402.01613", "license:apache-2.0", "model-index", "endpoints_compatible", "region:us" ]

[ "2205.13147", "2402.01613" ]

[]

[ "### Sentence Transformers", "### Transformers\n\n\nThe model natively supports scaling of the sequence length past 2048 tokens. To do so,", "### URL\n\n\nJoin the Nomic Community\n========================\n\n\n* Nomic: URL\n* Discord: URL\n* Twitter: URL\n\n\nIf you find the model, dataset, or training code useful, please cite our work" ]

[ "TAGS\n#sentence-transformers #onnx #safetensors #nomic_bert #feature-extraction #sentence-similarity #mteb #transformers #transformers.js #custom_code #arxiv-2205.13147 #arxiv-2402.01613 #license-apache-2.0 #model-index #endpoints_compatible #region-us \n", "### Sentence Transformers", "### Transformers\n\n\nThe model natively supports scaling of the sequence length past 2048 tokens. To do so,", "### URL\n\n\nJoin the Nomic Community\n========================\n\n\n* Nomic: URL\n* Discord: URL\n* Twitter: URL\n\n\nIf you find the model, dataset, or training code useful, please cite our work" ]

[ "transformers", "safetensors", "t5", "text2text-generation", "generated_from_trainer", "base_model:Salesforce/codet5p-220m", "license:bsd-3-clause", "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: 4\n* eval\\_batch\\_size: 4\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 16\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 2", "### Training results", "### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.1.2\n* Datasets 2.19.0\n* Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-Salesforce/codet5p-220m #license-bsd-3-clause #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: 4\n* eval\\_batch\\_size: 4\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 16\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 2", "### Training results", "### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.1.2\n* Datasets 2.19.0\n* Tokenizers 0.15.2" ]

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

[]

[ "fr" ]

[ "# AgentPublic/guillaumetell-7b AWQ\n\n- Model creator: AgentPublic\n- Original model: guillaumetell-7b", "## Model Summary\n\nGuillaume Tell est un Large Language Model (LLM) français basé sur Mistral Open-Hermes 2.5 optimisé pour le RAG (Retrieval Augmented Generation) avec traçabilité des sources et explicabilité.", "## How to use", "### Install the necessary packages", "### Example Python code", "### About AWQ\n\nAWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings.\n\nAWQ models are currently supported on Linux and Windows, with NVidia GPUs only. macOS users: please use GGUF models instead.\n\nIt is supported by:\n\n- Text Generation Webui - using Loader: AutoAWQ\n- vLLM - version 0.2.2 or later for support for all model types.\n- Hugging Face Text Generation Inference (TGI)\n- Transformers version 4.35.0 and later, from any code or client that supports Transformers\n- AutoAWQ - for use from Python code" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #4-bit #AWQ #autotrain_compatible #endpoints_compatible #conversational #fr #license-apache-2.0 #text-generation-inference #region-us \n", "# AgentPublic/guillaumetell-7b AWQ\n\n- Model creator: AgentPublic\n- Original model: guillaumetell-7b", "## Model Summary\n\nGuillaume Tell est un Large Language Model (LLM) français basé sur Mistral Open-Hermes 2.5 optimisé pour le RAG (Retrieval Augmented Generation) avec traçabilité des sources et explicabilité.", "## How to use", "### Install the necessary packages", "### Example Python code", "### About AWQ\n\nAWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings.\n\nAWQ models are currently supported on Linux and Windows, with NVidia GPUs only. macOS users: please use GGUF models instead.\n\nIt is supported by:\n\n- Text Generation Webui - using Loader: AutoAWQ\n- vLLM - version 0.2.2 or later for support for all model types.\n- Hugging Face Text Generation Inference (TGI)\n- Transformers version 4.35.0 and later, from any code or client that supports Transformers\n- AutoAWQ - for use from Python code" ]

[ "transformers", "pytorch", "llama", "text-generation", "text-generation-inference", "unsloth", "trl", "sft", "conversational", "en", "base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[ "# Uploaded model\n\n- Developed by: ppopiolek\n- License: apache-2.0\n- Finetuned from model : TinyLlama/TinyLlama-1.1B-Chat-v1.0\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "TAGS\n#transformers #pytorch #llama #text-generation #text-generation-inference #unsloth #trl #sft #conversational #en #base_model-TinyLlama/TinyLlama-1.1B-Chat-v1.0 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "# Uploaded model\n\n- Developed by: ppopiolek\n- License: apache-2.0\n- Finetuned from model : TinyLlama/TinyLlama-1.1B-Chat-v1.0\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "diffusers", "tensorboard", "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 - animanatwork/illustrations-lora\nThese are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were fine-tuned on the animanatwork/text_to_image_dataset dataset. \n\nBelow, we can find some images from the dataset:\n\n<div style=\"display: flex; justify-content: space-between;\">\n <img src=\"URL width=\"30%\" />\n <img src=\"URL width=\"30%\" /> \n <img src=\"URL width=\"30%\" />\n</div>\n\n\nThe images below are generated from the model using the prompt: \"a stylized illustration of a woman sitting in a comfortable chair, reading a book. She is wearing a hat, and her expression appears focused and calm. A black cat is also depicted, sitting beside her and looking at the book, suggesting a shared moment of quiet and companionship. The woman is dressed in a casual outfit with yellow shoes, and the overall color scheme is simple, using black, white, and yellow. The setting seems cozy and peaceful, ideal for reading.\"\n\n<div style=\"display: flex; justify-content: space-between;\">\n <img src=\"./image_0.png\" width=\"25%\" />\n <img src=\"./image_1.png\" width=\"25%\" />\n <img src=\"./image_2.png\" width=\"25%\" />\n <img src=\"./image_3.png\" width=\"25%\" />\n</div>", "## Intended uses & limitations\nDo NOT use in production. This model was purely created for research purposes.", "#### How to use", "#### Limitations and bias\n\n[TODO: provide examples of latent issues and potential remediations]", "## Training details\n\n- The model was trained on the \"animanatwork/text_to_image_dataset\" dataset using 10_000 training step (default is 15_000) and took several hours to train. For more details see Colab notebook.\n- The dataset's tokens were generated using chatGPT vision. During training, I noticed CLIP can only use 77 tokens for a given image. Since most of our image descriptions contained more tokens, we'll have to create a new dataset that doesn't exceed the maximum. \n\n\n[TODO: describe the data used to train the model]" ]

[ "TAGS\n#diffusers #tensorboard #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 - animanatwork/illustrations-lora\nThese are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were fine-tuned on the animanatwork/text_to_image_dataset dataset. \n\nBelow, we can find some images from the dataset:\n\n<div style=\"display: flex; justify-content: space-between;\">\n <img src=\"URL width=\"30%\" />\n <img src=\"URL width=\"30%\" /> \n <img src=\"URL width=\"30%\" />\n</div>\n\n\nThe images below are generated from the model using the prompt: \"a stylized illustration of a woman sitting in a comfortable chair, reading a book. She is wearing a hat, and her expression appears focused and calm. A black cat is also depicted, sitting beside her and looking at the book, suggesting a shared moment of quiet and companionship. The woman is dressed in a casual outfit with yellow shoes, and the overall color scheme is simple, using black, white, and yellow. The setting seems cozy and peaceful, ideal for reading.\"\n\n<div style=\"display: flex; justify-content: space-between;\">\n <img src=\"./image_0.png\" width=\"25%\" />\n <img src=\"./image_1.png\" width=\"25%\" />\n <img src=\"./image_2.png\" width=\"25%\" />\n <img src=\"./image_3.png\" width=\"25%\" />\n</div>", "## Intended uses & limitations\nDo NOT use in production. This model was purely created for research purposes.", "#### How to use", "#### Limitations and bias\n\n[TODO: provide examples of latent issues and potential remediations]", "## Training details\n\n- The model was trained on the \"animanatwork/text_to_image_dataset\" dataset using 10_000 training step (default is 15_000) and took several hours to train. For more details see Colab notebook.\n- The dataset's tokens were generated using chatGPT vision. During training, I noticed CLIP can only use 77 tokens for a given image. Since most of our image descriptions contained more tokens, we'll have to create a new dataset that doesn't exceed the maximum. \n\n\n[TODO: describe the data used to train the model]" ]

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

[]

[]

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

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

[ "transformers", "tensorboard", "safetensors", "gpt_neox", "text-classification", "generated_from_trainer", "base_model:EleutherAI/pythia-1b", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# robust_llm_pythia-1b_mz-130_PasswordMatch_n-its-10-seed-2\n\nThis model is a fine-tuned version of EleutherAI/pythia-1b 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-1b #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# robust_llm_pythia-1b_mz-130_PasswordMatch_n-its-10-seed-2\n\nThis model is a fine-tuned version of EleutherAI/pythia-1b 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" ]

[ "peft", "tensorboard", "safetensors", "generated_from_trainer", "base_model:facebook/esm2_t12_35M_UR50D", "license:mit", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005701568055793089\n* train\\_batch\\_size: 64\n* eval\\_batch\\_size: 64\n* seed: 8893\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\n* num\\_epochs: 30", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.39.3\n* Pytorch 2.2.1\n* Datasets 2.16.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #tensorboard #safetensors #generated_from_trainer #base_model-facebook/esm2_t12_35M_UR50D #license-mit #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005701568055793089\n* train\\_batch\\_size: 64\n* eval\\_batch\\_size: 64\n* seed: 8893\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\n* num\\_epochs: 30", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.39.3\n* Pytorch 2.2.1\n* Datasets 2.16.1\n* Tokenizers 0.15.2" ]

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

[ "1910.09700" ]

[]

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

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

[ "region:us" ]

[]

[]

[ "## How to Get Started with the Model\n\nTo use this model, you can either interact with it programmatically using the Python code below or through a web-based interface provided by Gradio.", "### Using Python Code\n\n'''python\nfrom transformers import TFAutoModelForImageClassification, AutoTokenizer\nimport gradio as gr", "# Laden Sie das Modell und den Tokenizer von Hugging Face herunter\nmodel = TFAutoModelForImageClassification.from_pretrained(\"kiki7555/pokemon_classifier_tf\")\ntokenizer = AutoTokenizer.from_pretrained(\"kiki7555/pokemon_classifier_tf\")\n\ndef predict_pokemon(image):\n # Hier kannst du die Bildvorverarbeitung und -nachverarbeitung hinzufügen\n # ...\n\n # Vorhersage treffen\n predictions = model.predict(image) # Hier musst du die genaue Vorverarbeitung für das Bild hinzufügen\n predicted_class = URL()\n \n class_names = ['Charizard', 'Pikachu', 'Zapdos']\n return class_names[predicted_class]", "# Gradio UI erstellen\nimage_input = URL.Image(shape=(128, 128))\noutput_text = gr.outputs.Textbox()\n\ngr.Interface(\n fn=predict_pokemon,\n inputs=image_input,\n outputs=output_text,\n title=\"Pokemon Classifier\",\n description=\"Classify images of Pokemon into three categories: Charizard, Pikachu, and Zapdos.\"\n).launch()" ]

[ "TAGS\n#region-us \n", "## How to Get Started with the Model\n\nTo use this model, you can either interact with it programmatically using the Python code below or through a web-based interface provided by Gradio.", "### Using Python Code\n\n'''python\nfrom transformers import TFAutoModelForImageClassification, AutoTokenizer\nimport gradio as gr", "# Laden Sie das Modell und den Tokenizer von Hugging Face herunter\nmodel = TFAutoModelForImageClassification.from_pretrained(\"kiki7555/pokemon_classifier_tf\")\ntokenizer = AutoTokenizer.from_pretrained(\"kiki7555/pokemon_classifier_tf\")\n\ndef predict_pokemon(image):\n # Hier kannst du die Bildvorverarbeitung und -nachverarbeitung hinzufügen\n # ...\n\n # Vorhersage treffen\n predictions = model.predict(image) # Hier musst du die genaue Vorverarbeitung für das Bild hinzufügen\n predicted_class = URL()\n \n class_names = ['Charizard', 'Pikachu', 'Zapdos']\n return class_names[predicted_class]", "# Gradio UI erstellen\nimage_input = URL.Image(shape=(128, 128))\noutput_text = gr.outputs.Textbox()\n\ngr.Interface(\n fn=predict_pokemon,\n inputs=image_input,\n outputs=output_text,\n title=\"Pokemon Classifier\",\n description=\"Classify images of Pokemon into three categories: Charizard, Pikachu, and Zapdos.\"\n).launch()" ]

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

[]

[]

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

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

[ "transformers", "gguf", "en", "base_model:SparseLLM/ReluLLaMA-70B", "license:llama2", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #en #base_model-SparseLLM/ReluLLaMA-70B #license-llama2 #endpoints_compatible #region-us \n" ]

[ "transformers", "safetensors", "gemma", "text-generation", "arxiv:2312.11805", "arxiv:2009.03300", "arxiv:1905.07830", "arxiv:1911.11641", "arxiv:1904.09728", "arxiv:1905.10044", "arxiv:1907.10641", "arxiv:1811.00937", "arxiv:1809.02789", "arxiv:1911.01547", "arxiv:1705.03551", "arxiv:2107.03374", "arxiv:2108.07732", "arxiv:2110.14168", "arxiv:2304.06364", "arxiv:2206.04615", "arxiv:1804.06876", "arxiv:2110.08193", "arxiv:2009.11462", "arxiv:2101.11718", "arxiv:1804.09301", "arxiv:2109.07958", "arxiv:2203.09509", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]

[ "2312.11805", "2009.03300", "1905.07830", "1911.11641", "1904.09728", "1905.10044", "1907.10641", "1811.00937", "1809.02789", "1911.01547", "1705.03551", "2107.03374", "2108.07732", "2110.14168", "2304.06364", "2206.04615", "1804.06876", "2110.08193", "2009.11462", "2101.11718", "1804.09301", "2109.07958", "2203.09509" ]

[]

[ "### Description\n\n\nGemma is a family of lightweight, state-of-the-art open models from Google,\nbuilt from the same research and technology used to create the Gemini models.\nThey are text-to-text, decoder-only large language models, available in English,\nwith open weights, pre-trained variants, and instruction-tuned variants. Gemma\nmodels are well-suited for a variety of text generation tasks, including\nquestion answering, summarization, and reasoning. Their relatively small size\nmakes it possible to deploy them in environments with limited resources such as\na laptop, desktop or your own cloud infrastructure, democratizing access to\nstate of the art AI models and helping foster innovation for everyone.", "### Usage\n\n\nBelow we share some code snippets on how to get quickly started with running the model. First make sure to 'pip install -U transformers', then copy the snippet from the section that is relevant for your usecase.", "#### Fine-tuning the model\n\n\nYou can find fine-tuning scripts and notebook under the 'examples/' directory of 'google/gemma-7b' repository. To adapt it to this model, simply change the model-id to 'google/gemma-2b'.\nIn that repository, we provide:\n\n\n* A script to perform Supervised Fine-Tuning (SFT) on UltraChat dataset using QLoRA\n* A script to perform SFT using FSDP on TPU devices\n* A notebook that you can run on a free-tier Google Colab instance to perform SFT on English quotes dataset", "#### Running the model on a CPU", "#### Running the model on a single / multi GPU", "#### Running the model on a GPU using different precisions\n\n\n* *Using 'torch.float16'*\n* *Using 'torch.bfloat16'*", "#### Quantized Versions through 'bitsandbytes'\n\n\n* *Using 8-bit precision (int8)*\n* *Using 4-bit precision*", "#### Other optimizations\n\n\n* *Flash Attention 2*\n\n\nFirst make sure to install 'flash-attn' in your environment 'pip install flash-attn'", "### Inputs and outputs\n\n\n* Input: Text string, such as a question, a prompt, or a document to be\nsummarized.\n* Output: Generated English-language text in response to the input, such\nas an answer to a question, or a summary of a document.\n\n\nModel Data\n----------\n\n\nData used for model training and how the data was processed.", "### Training Dataset\n\n\nThese models were trained on a dataset of text data that includes a wide variety\nof sources, totaling 6 trillion tokens. Here are the key components:\n\n\n* Web Documents: A diverse collection of web text ensures the model is exposed\nto a broad range of linguistic styles, topics, and vocabulary. Primarily\nEnglish-language content.\n* Code: Exposing the model to code helps it to learn the syntax and patterns of\nprogramming languages, which improves its ability to generate code or\nunderstand code-related questions.\n* Mathematics: Training on mathematical text helps the model learn logical\nreasoning, symbolic representation, and to address mathematical queries.\n\n\nThe combination of these diverse data sources is crucial for training a powerful\nlanguage model that can handle a wide variety of different tasks and text\nformats.", "### Data Preprocessing\n\n\nHere are the key data cleaning and filtering methods applied to the training\ndata:\n\n\n* CSAM Filtering: Rigorous CSAM (Child Sexual Abuse Material) filtering was\napplied at multiple stages in the data preparation process to ensure the\nexclusion of harmful and illegal content\n* Sensitive Data Filtering: As part of making Gemma pre-trained models safe and\nreliable, automated techniques were used to filter out certain personal\ninformation and other sensitive data from training sets.\n* Additional methods: Filtering based on content quality and safely in line with\nour policies.\n\n\nImplementation Information\n--------------------------\n\n\nDetails about the model internals.", "### Hardware\n\n\nGemma was trained using the latest generation of\nTensor Processing Unit (TPU) hardware (TPUv5e).\n\n\nTraining large language models requires significant computational power. TPUs,\ndesigned specifically for matrix operations common in machine learning, offer\nseveral advantages in this domain:\n\n\n* Performance: TPUs are specifically designed to handle the massive computations\ninvolved in training LLMs. They can speed up training considerably compared to\nCPUs.\n* Memory: TPUs often come with large amounts of high-bandwidth memory, allowing\nfor the handling of large models and batch sizes during training. This can\nlead to better model quality.\n* Scalability: TPU Pods (large clusters of TPUs) provide a scalable solution for\nhandling the growing complexity of large foundation models. You can distribute\ntraining across multiple TPU devices for faster and more efficient processing.\n* Cost-effectiveness: In many scenarios, TPUs can provide a more cost-effective\nsolution for training large models compared to CPU-based infrastructure,\nespecially when considering the time and resources saved due to faster\ntraining.\n* These advantages are aligned with\nGoogle's commitments to operate sustainably.", "### Software\n\n\nTraining was done using JAX and ML Pathways.\n\n\nJAX allows researchers to take advantage of the latest generation of hardware,\nincluding TPUs, for faster and more efficient training of large models.\n\n\nML Pathways is Google's latest effort to build artificially intelligent systems\ncapable of generalizing across multiple tasks. This is specially suitable for\nfoundation models, including large language models like\nthese ones.\n\n\nTogether, JAX and ML Pathways are used as described in the\npaper about the Gemini family of models; \"the 'single\ncontroller' programming model of Jax and Pathways allows a single Python\nprocess to orchestrate the entire training run, dramatically simplifying the\ndevelopment workflow.\"\n\n\nEvaluation\n----------\n\n\nModel evaluation metrics and results.", "### Benchmark Results\n\n\nThese models were evaluated against a large collection of different datasets and\nmetrics to cover different aspects of text generation:\n\n\n\nEthics and Safety\n-----------------\n\n\nEthics and safety evaluation approach and results.", "### Evaluation Approach\n\n\nOur evaluation methods include structured evaluations and internal red-teaming\ntesting of relevant content policies. Red-teaming was conducted by a number of\ndifferent teams, each with different goals and human evaluation metrics. These\nmodels were evaluated against a number of different categories relevant to\nethics and safety, including:\n\n\n* Text-to-Text Content Safety: Human evaluation on prompts covering safety\npolicies including child sexual abuse and exploitation, harassment, violence\nand gore, and hate speech.\n* Text-to-Text Representational Harms: Benchmark against relevant academic\ndatasets such as WinoBias and BBQ Dataset.\n* Memorization: Automated evaluation of memorization of training data, including\nthe risk of personally identifiable information exposure.\n* Large-scale harm: Tests for \"dangerous capabilities,\" such as chemical,\nbiological, radiological, and nuclear (CBRN) risks.", "### Evaluation Results\n\n\nThe results of ethics and safety evaluations are within acceptable thresholds\nfor meeting internal policies for categories such as child\nsafety, content safety, representational harms, memorization, large-scale harms.\nOn top of robust internal evaluations, the results of well known safety\nbenchmarks like BBQ, BOLD, Winogender, Winobias, RealToxicity, and TruthfulQA\nare shown here.\n\n\n\nUsage and Limitations\n---------------------\n\n\nThese models have certain limitations that users should be aware of.", "### Intended Usage\n\n\nOpen Large Language Models (LLMs) have a wide range of applications across\nvarious industries and domains. The following list of potential uses is not\ncomprehensive. The purpose of this list is to provide contextual information\nabout the possible use-cases that the model creators considered as part of model\ntraining and development.\n\n\n* Content Creation and Communication\n\t+ Text Generation: These models can be used to generate creative text formats\n\tsuch as poems, scripts, code, marketing copy, and email drafts.\n\t+ Chatbots and Conversational AI: Power conversational interfaces for customer\n\tservice, virtual assistants, or interactive applications.\n\t+ Text Summarization: Generate concise summaries of a text corpus, research\n\tpapers, or reports.\n* Research and Education\n\t+ Natural Language Processing (NLP) Research: These models can serve as a\n\tfoundation for researchers to experiment with NLP techniques, develop\n\talgorithms, and contribute to the advancement of the field.\n\t+ Language Learning Tools: Support interactive language learning experiences,\n\taiding in grammar correction or providing writing practice.\n\t+ Knowledge Exploration: Assist researchers in exploring large bodies of text\n\tby generating summaries or answering questions about specific topics.", "### Limitations\n\n\n* Training Data\n\t+ The quality and diversity of the training data significantly influence the\n\tmodel's capabilities. Biases or gaps in the training data can lead to\n\tlimitations in the model's responses.\n\t+ The scope of the training dataset determines the subject areas the model can\n\thandle effectively.\n* Context and Task Complexity\n\t+ LLMs are better at tasks that can be framed with clear prompts and\n\tinstructions. Open-ended or highly complex tasks might be challenging.\n\t+ A model's performance can be influenced by the amount of context provided\n\t(longer context generally leads to better outputs, up to a certain point).\n* Language Ambiguity and Nuance\n\t+ Natural language is inherently complex. LLMs might struggle to grasp subtle\n\tnuances, sarcasm, or figurative language.\n* Factual Accuracy\n\t+ LLMs generate responses based on information they learned from their\n\ttraining datasets, but they are not knowledge bases. They may generate\n\tincorrect or outdated factual statements.\n* Common Sense\n\t+ LLMs rely on statistical patterns in language. They might lack the ability\n\tto apply common sense reasoning in certain situations.", "### Ethical Considerations and Risks\n\n\nThe development of large language models (LLMs) raises several ethical concerns.\nIn creating an open model, we have carefully considered the following:\n\n\n* Bias and Fairness\n\t+ LLMs trained on large-scale, real-world text data can reflect socio-cultural\n\tbiases embedded in the training material. These models underwent careful\n\tscrutiny, input data pre-processing described and posterior evaluations\n\treported in this card.\n* Misinformation and Misuse\n\t+ LLMs can be misused to generate text that is false, misleading, or harmful.\n\t+ Guidelines are provided for responsible use with the model, see the\n\tResponsible Generative AI Toolkit.\n* Transparency and Accountability:\n\t+ This model card summarizes details on the models' architecture,\n\tcapabilities, limitations, and evaluation processes.\n\t+ A responsibly developed open model offers the opportunity to share\n\tinnovation by making LLM technology accessible to developers and researchers\n\tacross the AI ecosystem.\n\n\nRisks identified and mitigations:\n\n\n* Perpetuation of biases: It's encouraged to perform continuous monitoring\n(using evaluation metrics, human review) and the exploration of de-biasing\ntechniques during model training, fine-tuning, and other use cases.\n* Generation of harmful content: Mechanisms and guidelines for content safety\nare essential. Developers are encouraged to exercise caution and implement\nappropriate content safety safeguards based on their specific product policies\nand application use cases.\n* Misuse for malicious purposes: Technical limitations and developer and\nend-user education can help mitigate against malicious applications of LLMs.\nEducational resources and reporting mechanisms for users to flag misuse are\nprovided. Prohibited uses of Gemma models are outlined in the\nGemma Prohibited Use Policy.\n* Privacy violations: Models were trained on data filtered for removal of PII\n(Personally Identifiable Information). Developers are encouraged to adhere to\nprivacy regulations with privacy-preserving techniques.", "### Benefits\n\n\nAt the time of release, this family of models provides high-performance open\nlarge language model implementations designed from the ground up for Responsible\nAI development compared to similarly sized models.\n\n\nUsing the benchmark evaluation metrics described in this document, these models\nhave shown to provide superior performance to other, comparably-sized open model\nalternatives." ]

[ "TAGS\n#transformers #safetensors #gemma #text-generation #arxiv-2312.11805 #arxiv-2009.03300 #arxiv-1905.07830 #arxiv-1911.11641 #arxiv-1904.09728 #arxiv-1905.10044 #arxiv-1907.10641 #arxiv-1811.00937 #arxiv-1809.02789 #arxiv-1911.01547 #arxiv-1705.03551 #arxiv-2107.03374 #arxiv-2108.07732 #arxiv-2110.14168 #arxiv-2304.06364 #arxiv-2206.04615 #arxiv-1804.06876 #arxiv-2110.08193 #arxiv-2009.11462 #arxiv-2101.11718 #arxiv-1804.09301 #arxiv-2109.07958 #arxiv-2203.09509 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n", "### Description\n\n\nGemma is a family of lightweight, state-of-the-art open models from Google,\nbuilt from the same research and technology used to create the Gemini models.\nThey are text-to-text, decoder-only large language models, available in English,\nwith open weights, pre-trained variants, and instruction-tuned variants. Gemma\nmodels are well-suited for a variety of text generation tasks, including\nquestion answering, summarization, and reasoning. Their relatively small size\nmakes it possible to deploy them in environments with limited resources such as\na laptop, desktop or your own cloud infrastructure, democratizing access to\nstate of the art AI models and helping foster innovation for everyone.", "### Usage\n\n\nBelow we share some code snippets on how to get quickly started with running the model. First make sure to 'pip install -U transformers', then copy the snippet from the section that is relevant for your usecase.", "#### Fine-tuning the model\n\n\nYou can find fine-tuning scripts and notebook under the 'examples/' directory of 'google/gemma-7b' repository. To adapt it to this model, simply change the model-id to 'google/gemma-2b'.\nIn that repository, we provide:\n\n\n* A script to perform Supervised Fine-Tuning (SFT) on UltraChat dataset using QLoRA\n* A script to perform SFT using FSDP on TPU devices\n* A notebook that you can run on a free-tier Google Colab instance to perform SFT on English quotes dataset", "#### Running the model on a CPU", "#### Running the model on a single / multi GPU", "#### Running the model on a GPU using different precisions\n\n\n* *Using 'torch.float16'*\n* *Using 'torch.bfloat16'*", "#### Quantized Versions through 'bitsandbytes'\n\n\n* *Using 8-bit precision (int8)*\n* *Using 4-bit precision*", "#### Other optimizations\n\n\n* *Flash Attention 2*\n\n\nFirst make sure to install 'flash-attn' in your environment 'pip install flash-attn'", "### Inputs and outputs\n\n\n* Input: Text string, such as a question, a prompt, or a document to be\nsummarized.\n* Output: Generated English-language text in response to the input, such\nas an answer to a question, or a summary of a document.\n\n\nModel Data\n----------\n\n\nData used for model training and how the data was processed.", "### Training Dataset\n\n\nThese models were trained on a dataset of text data that includes a wide variety\nof sources, totaling 6 trillion tokens. Here are the key components:\n\n\n* Web Documents: A diverse collection of web text ensures the model is exposed\nto a broad range of linguistic styles, topics, and vocabulary. Primarily\nEnglish-language content.\n* Code: Exposing the model to code helps it to learn the syntax and patterns of\nprogramming languages, which improves its ability to generate code or\nunderstand code-related questions.\n* Mathematics: Training on mathematical text helps the model learn logical\nreasoning, symbolic representation, and to address mathematical queries.\n\n\nThe combination of these diverse data sources is crucial for training a powerful\nlanguage model that can handle a wide variety of different tasks and text\nformats.", "### Data Preprocessing\n\n\nHere are the key data cleaning and filtering methods applied to the training\ndata:\n\n\n* CSAM Filtering: Rigorous CSAM (Child Sexual Abuse Material) filtering was\napplied at multiple stages in the data preparation process to ensure the\nexclusion of harmful and illegal content\n* Sensitive Data Filtering: As part of making Gemma pre-trained models safe and\nreliable, automated techniques were used to filter out certain personal\ninformation and other sensitive data from training sets.\n* Additional methods: Filtering based on content quality and safely in line with\nour policies.\n\n\nImplementation Information\n--------------------------\n\n\nDetails about the model internals.", "### Hardware\n\n\nGemma was trained using the latest generation of\nTensor Processing Unit (TPU) hardware (TPUv5e).\n\n\nTraining large language models requires significant computational power. TPUs,\ndesigned specifically for matrix operations common in machine learning, offer\nseveral advantages in this domain:\n\n\n* Performance: TPUs are specifically designed to handle the massive computations\ninvolved in training LLMs. They can speed up training considerably compared to\nCPUs.\n* Memory: TPUs often come with large amounts of high-bandwidth memory, allowing\nfor the handling of large models and batch sizes during training. This can\nlead to better model quality.\n* Scalability: TPU Pods (large clusters of TPUs) provide a scalable solution for\nhandling the growing complexity of large foundation models. You can distribute\ntraining across multiple TPU devices for faster and more efficient processing.\n* Cost-effectiveness: In many scenarios, TPUs can provide a more cost-effective\nsolution for training large models compared to CPU-based infrastructure,\nespecially when considering the time and resources saved due to faster\ntraining.\n* These advantages are aligned with\nGoogle's commitments to operate sustainably.", "### Software\n\n\nTraining was done using JAX and ML Pathways.\n\n\nJAX allows researchers to take advantage of the latest generation of hardware,\nincluding TPUs, for faster and more efficient training of large models.\n\n\nML Pathways is Google's latest effort to build artificially intelligent systems\ncapable of generalizing across multiple tasks. This is specially suitable for\nfoundation models, including large language models like\nthese ones.\n\n\nTogether, JAX and ML Pathways are used as described in the\npaper about the Gemini family of models; \"the 'single\ncontroller' programming model of Jax and Pathways allows a single Python\nprocess to orchestrate the entire training run, dramatically simplifying the\ndevelopment workflow.\"\n\n\nEvaluation\n----------\n\n\nModel evaluation metrics and results.", "### Benchmark Results\n\n\nThese models were evaluated against a large collection of different datasets and\nmetrics to cover different aspects of text generation:\n\n\n\nEthics and Safety\n-----------------\n\n\nEthics and safety evaluation approach and results.", "### Evaluation Approach\n\n\nOur evaluation methods include structured evaluations and internal red-teaming\ntesting of relevant content policies. Red-teaming was conducted by a number of\ndifferent teams, each with different goals and human evaluation metrics. These\nmodels were evaluated against a number of different categories relevant to\nethics and safety, including:\n\n\n* Text-to-Text Content Safety: Human evaluation on prompts covering safety\npolicies including child sexual abuse and exploitation, harassment, violence\nand gore, and hate speech.\n* Text-to-Text Representational Harms: Benchmark against relevant academic\ndatasets such as WinoBias and BBQ Dataset.\n* Memorization: Automated evaluation of memorization of training data, including\nthe risk of personally identifiable information exposure.\n* Large-scale harm: Tests for \"dangerous capabilities,\" such as chemical,\nbiological, radiological, and nuclear (CBRN) risks.", "### Evaluation Results\n\n\nThe results of ethics and safety evaluations are within acceptable thresholds\nfor meeting internal policies for categories such as child\nsafety, content safety, representational harms, memorization, large-scale harms.\nOn top of robust internal evaluations, the results of well known safety\nbenchmarks like BBQ, BOLD, Winogender, Winobias, RealToxicity, and TruthfulQA\nare shown here.\n\n\n\nUsage and Limitations\n---------------------\n\n\nThese models have certain limitations that users should be aware of.", "### Intended Usage\n\n\nOpen Large Language Models (LLMs) have a wide range of applications across\nvarious industries and domains. The following list of potential uses is not\ncomprehensive. The purpose of this list is to provide contextual information\nabout the possible use-cases that the model creators considered as part of model\ntraining and development.\n\n\n* Content Creation and Communication\n\t+ Text Generation: These models can be used to generate creative text formats\n\tsuch as poems, scripts, code, marketing copy, and email drafts.\n\t+ Chatbots and Conversational AI: Power conversational interfaces for customer\n\tservice, virtual assistants, or interactive applications.\n\t+ Text Summarization: Generate concise summaries of a text corpus, research\n\tpapers, or reports.\n* Research and Education\n\t+ Natural Language Processing (NLP) Research: These models can serve as a\n\tfoundation for researchers to experiment with NLP techniques, develop\n\talgorithms, and contribute to the advancement of the field.\n\t+ Language Learning Tools: Support interactive language learning experiences,\n\taiding in grammar correction or providing writing practice.\n\t+ Knowledge Exploration: Assist researchers in exploring large bodies of text\n\tby generating summaries or answering questions about specific topics.", "### Limitations\n\n\n* Training Data\n\t+ The quality and diversity of the training data significantly influence the\n\tmodel's capabilities. Biases or gaps in the training data can lead to\n\tlimitations in the model's responses.\n\t+ The scope of the training dataset determines the subject areas the model can\n\thandle effectively.\n* Context and Task Complexity\n\t+ LLMs are better at tasks that can be framed with clear prompts and\n\tinstructions. Open-ended or highly complex tasks might be challenging.\n\t+ A model's performance can be influenced by the amount of context provided\n\t(longer context generally leads to better outputs, up to a certain point).\n* Language Ambiguity and Nuance\n\t+ Natural language is inherently complex. LLMs might struggle to grasp subtle\n\tnuances, sarcasm, or figurative language.\n* Factual Accuracy\n\t+ LLMs generate responses based on information they learned from their\n\ttraining datasets, but they are not knowledge bases. They may generate\n\tincorrect or outdated factual statements.\n* Common Sense\n\t+ LLMs rely on statistical patterns in language. They might lack the ability\n\tto apply common sense reasoning in certain situations.", "### Ethical Considerations and Risks\n\n\nThe development of large language models (LLMs) raises several ethical concerns.\nIn creating an open model, we have carefully considered the following:\n\n\n* Bias and Fairness\n\t+ LLMs trained on large-scale, real-world text data can reflect socio-cultural\n\tbiases embedded in the training material. These models underwent careful\n\tscrutiny, input data pre-processing described and posterior evaluations\n\treported in this card.\n* Misinformation and Misuse\n\t+ LLMs can be misused to generate text that is false, misleading, or harmful.\n\t+ Guidelines are provided for responsible use with the model, see the\n\tResponsible Generative AI Toolkit.\n* Transparency and Accountability:\n\t+ This model card summarizes details on the models' architecture,\n\tcapabilities, limitations, and evaluation processes.\n\t+ A responsibly developed open model offers the opportunity to share\n\tinnovation by making LLM technology accessible to developers and researchers\n\tacross the AI ecosystem.\n\n\nRisks identified and mitigations:\n\n\n* Perpetuation of biases: It's encouraged to perform continuous monitoring\n(using evaluation metrics, human review) and the exploration of de-biasing\ntechniques during model training, fine-tuning, and other use cases.\n* Generation of harmful content: Mechanisms and guidelines for content safety\nare essential. Developers are encouraged to exercise caution and implement\nappropriate content safety safeguards based on their specific product policies\nand application use cases.\n* Misuse for malicious purposes: Technical limitations and developer and\nend-user education can help mitigate against malicious applications of LLMs.\nEducational resources and reporting mechanisms for users to flag misuse are\nprovided. Prohibited uses of Gemma models are outlined in the\nGemma Prohibited Use Policy.\n* Privacy violations: Models were trained on data filtered for removal of PII\n(Personally Identifiable Information). Developers are encouraged to adhere to\nprivacy regulations with privacy-preserving techniques.", "### Benefits\n\n\nAt the time of release, this family of models provides high-performance open\nlarge language model implementations designed from the ground up for Responsible\nAI development compared to similarly sized models.\n\n\nUsing the benchmark evaluation metrics described in this document, these models\nhave shown to provide superior performance to other, comparably-sized open model\nalternatives." ]

[ "transformers", "safetensors", "llama", "text-generation", "arxiv:2304.12244", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]

[ "2304.12244" ]

[]

[ "## Model Details\n\nExperimental model. Trained with the Pygmalion and the WizardLM datasets.\n\nThe purpose of this model is to enable complex Instruct prompting but with the RP capabilties of Pygmalion.", "### Prompting format\n\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "### Uses\n\nThe intended use-case is Role-Playing with Instruct prompts. Guiding the bot towards a certain conversation style should be easier this way. Subject to experimentation.", "### Out-of-Scope Use\n\n- Assistant Bot [subject to providing incorrect instructions]\n- Complex multi-character chat", "### Risks\n\nThe model can generate potentially harmful or NSFW outputs. Please use with caution.\n\nWizardLM:" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #arxiv-2304.12244 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n", "## Model Details\n\nExperimental model. Trained with the Pygmalion and the WizardLM datasets.\n\nThe purpose of this model is to enable complex Instruct prompting but with the RP capabilties of Pygmalion.", "### Prompting format\n\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "### Uses\n\nThe intended use-case is Role-Playing with Instruct prompts. Guiding the bot towards a certain conversation style should be easier this way. Subject to experimentation.", "### Out-of-Scope Use\n\n- Assistant Bot [subject to providing incorrect instructions]\n- Complex multi-character chat", "### Risks\n\nThe model can generate potentially harmful or NSFW outputs. Please use with caution.\n\nWizardLM:" ]

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

[]

[ "en" ]

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

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

[ "transformers", "tensorboard", "safetensors", "gpt_neox", "text-classification", "generated_from_trainer", "base_model:EleutherAI/pythia-1b", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# robust_llm_pythia-1b_mz-130_PasswordMatch_n-its-10-seed-1\n\nThis model is a fine-tuned version of EleutherAI/pythia-1b 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-1b #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# robust_llm_pythia-1b_mz-130_PasswordMatch_n-its-10-seed-1\n\nThis model is a fine-tuned version of EleutherAI/pythia-1b 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", "whisper", "automatic-speech-recognition", "generated_from_trainer", "ur", "dataset:mozilla-foundation/common_voice_11_0", "base_model:openai/whisper-small", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[ "ur" ]

[ "# Whisper Small urdu 3 - huzaifa\n\nThis model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 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: 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: 5\n- training_steps: 10\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.40.1\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #whisper #automatic-speech-recognition #generated_from_trainer #ur #dataset-mozilla-foundation/common_voice_11_0 #base_model-openai/whisper-small #license-apache-2.0 #endpoints_compatible #region-us \n", "# Whisper Small urdu 3 - huzaifa\n\nThis model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 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: 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: 5\n- training_steps: 10\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.40.1\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "peft", "tensorboard", "safetensors", "generated_from_trainer", "base_model:facebook/esm2_t12_35M_UR50D", "license:mit", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005701568055793089\n* train\\_batch\\_size: 64\n* eval\\_batch\\_size: 64\n* seed: 8893\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\n* num\\_epochs: 100", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.39.3\n* Pytorch 2.2.1\n* Datasets 2.16.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #tensorboard #safetensors #generated_from_trainer #base_model-facebook/esm2_t12_35M_UR50D #license-mit #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005701568055793089\n* train\\_batch\\_size: 64\n* eval\\_batch\\_size: 64\n* seed: 8893\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\n* num\\_epochs: 100", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.39.3\n* Pytorch 2.2.1\n* Datasets 2.16.1\n* Tokenizers 0.15.2" ]

[ "transformers", "tensorboard", "safetensors", "t5", "text2text-generation", "generated_from_trainer", "base_model: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: 2e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 2\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-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: 2e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 2\n* mixed\\_precision\\_training: Native AMP", "### 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", "mistral", "text-generation", "merge", "mergekit", "lazymergekit", "Yuma42/KangalKhan-Alpha-Sapphiroid-7B-Fixed", "argilla/distilabeled-OpenHermes-2.5-Mistral-7B", "conversational", "en", "base_model:Yuma42/KangalKhan-Alpha-Sapphiroid-7B-Fixed", "base_model:argilla/distilabeled-OpenHermes-2.5-Mistral-7B", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[ "en" ]

[ "# KangalKhan-Alpha-Rubyroid-7B-Fixed\n\nKangalKhan-Alpha-Rubyroid-7B-Fixed is a merge of the following models using LazyMergekit:\n* Yuma42/KangalKhan-Alpha-Sapphiroid-7B-Fixed\n* argilla/distilabeled-OpenHermes-2.5-Mistral-7B", "## Configuration", "## Usage" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #merge #mergekit #lazymergekit #Yuma42/KangalKhan-Alpha-Sapphiroid-7B-Fixed #argilla/distilabeled-OpenHermes-2.5-Mistral-7B #conversational #en #base_model-Yuma42/KangalKhan-Alpha-Sapphiroid-7B-Fixed #base_model-argilla/distilabeled-OpenHermes-2.5-Mistral-7B #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# KangalKhan-Alpha-Rubyroid-7B-Fixed\n\nKangalKhan-Alpha-Rubyroid-7B-Fixed is a merge of the following models using LazyMergekit:\n* Yuma42/KangalKhan-Alpha-Sapphiroid-7B-Fixed\n* argilla/distilabeled-OpenHermes-2.5-Mistral-7B", "## Configuration", "## Usage" ]

[ "transformers", "safetensors", "llama", "text-generation", "4-bit", "AWQ", "autotrain_compatible", "endpoints_compatible", "axolotl", "finetune", "dpo", "facebook", "meta", "pytorch", "llama-3", "conversational", "dataset:Intel/orca_dpo_pairs", "base_model:meta-llama/Meta-Llama-3-8B-Instruct", "license:llama3", "text-generation-inference", "region:us" ]

[]

[]

[ "# MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.3 AWQ\n\n- Model creator: MaziyarPanahi\n- Original model: Llama-3-8B-Instruct-DPO-v0.3\n\n<img src=\"./URL\" alt=\"Llama-3 DPO Logo\" width=\"500\" style=\"margin-left:'auto' margin-right:'auto' display:'block'\"/>", "## Model Summary\n\nThis model is a fine-tune (DPO) of 'meta-llama/Meta-Llama-3-8B-Instruct' model. I have used 'rope_theta' to extend the context length up to 32K safely.", "## How to use", "### Install the necessary packages", "### Example Python code", "### About AWQ\n\nAWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings.\n\nAWQ models are currently supported on Linux and Windows, with NVidia GPUs only. macOS users: please use GGUF models instead.\n\nIt is supported by:\n\n- Text Generation Webui - using Loader: AutoAWQ\n- vLLM - version 0.2.2 or later for support for all model types.\n- Hugging Face Text Generation Inference (TGI)\n- Transformers version 4.35.0 and later, from any code or client that supports Transformers\n- AutoAWQ - for use from Python code" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #4-bit #AWQ #autotrain_compatible #endpoints_compatible #axolotl #finetune #dpo #facebook #meta #pytorch #llama-3 #conversational #dataset-Intel/orca_dpo_pairs #base_model-meta-llama/Meta-Llama-3-8B-Instruct #license-llama3 #text-generation-inference #region-us \n", "# MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.3 AWQ\n\n- Model creator: MaziyarPanahi\n- Original model: Llama-3-8B-Instruct-DPO-v0.3\n\n<img src=\"./URL\" alt=\"Llama-3 DPO Logo\" width=\"500\" style=\"margin-left:'auto' margin-right:'auto' display:'block'\"/>", "## Model Summary\n\nThis model is a fine-tune (DPO) of 'meta-llama/Meta-Llama-3-8B-Instruct' model. I have used 'rope_theta' to extend the context length up to 32K safely.", "## How to use", "### Install the necessary packages", "### Example Python code", "### About AWQ\n\nAWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings.\n\nAWQ models are currently supported on Linux and Windows, with NVidia GPUs only. macOS users: please use GGUF models instead.\n\nIt is supported by:\n\n- Text Generation Webui - using Loader: AutoAWQ\n- vLLM - version 0.2.2 or later for support for all model types.\n- Hugging Face Text Generation Inference (TGI)\n- Transformers version 4.35.0 and later, from any code or client that supports Transformers\n- AutoAWQ - for use from Python code" ]

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

[]

[ "en" ]

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

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

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

[ "1910.09700" ]

[]

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

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

[ "transformers", "safetensors", "llama", "text-generation", "axolotl", "finetune", "dpo", "facebook", "meta", "pytorch", "llama-3", "64k", "pose", "conversational", "en", "dataset:Intel/orca_dpo_pairs", "arxiv:2309.10400", "base_model:winglian/Llama-3-8b-64k-PoSE", "license:llama3", "autotrain_compatible", "text-generation-inference", "region:us" ]

[ "2309.10400" ]

[ "en" ]

[ "# MaziyarPanahi/Llama-3-8B-Instruct-64k\n\nThis model has been made based on a great of @winglian with his latest model winglian/Llama-3-8b-64k-PoSE\n\n> This model uses PoSE to extend Llama's context length from 8k to 64k @ rope_theta: 500000.0. \n> We used PoSE with continued pretraining on 300M tokens from the RedPajama V1 dataset using data between 6k-8k tokens.\n> We have further set rope_theta to 2M after continued pre-training to potentially further extend the context past 64k. \n> This was trained on a subset of the RedPajama v1 dataset with text between 6k-8k context. We trained a rank stabilized LoRA of rank 256. WandB", "# Quantized GGUF\n\nAll GGUF models come with context length of '64000': MaziyarPanahi/Llama-3-8B-Instruct-64k-GGUF", "# How to use\n\nYou can use this model by using 'MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.3' as the model name in Hugging Face's\ntransformers library." ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #axolotl #finetune #dpo #facebook #meta #pytorch #llama-3 #64k #pose #conversational #en #dataset-Intel/orca_dpo_pairs #arxiv-2309.10400 #base_model-winglian/Llama-3-8b-64k-PoSE #license-llama3 #autotrain_compatible #text-generation-inference #region-us \n", "# MaziyarPanahi/Llama-3-8B-Instruct-64k\n\nThis model has been made based on a great of @winglian with his latest model winglian/Llama-3-8b-64k-PoSE\n\n> This model uses PoSE to extend Llama's context length from 8k to 64k @ rope_theta: 500000.0. \n> We used PoSE with continued pretraining on 300M tokens from the RedPajama V1 dataset using data between 6k-8k tokens.\n> We have further set rope_theta to 2M after continued pre-training to potentially further extend the context past 64k. \n> This was trained on a subset of the RedPajama v1 dataset with text between 6k-8k context. We trained a rank stabilized LoRA of rank 256. WandB", "# Quantized GGUF\n\nAll GGUF models come with context length of '64000': MaziyarPanahi/Llama-3-8B-Instruct-64k-GGUF", "# How to use\n\nYou can use this model by using 'MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.3' as the model name in Hugging Face's\ntransformers library." ]

[ "transformers", "safetensors", "bert", "text-classification", "generated_from_trainer", "nl", "dataset:GroNLP/dutch-cola", "base_model:GroNLP/bert-base-dutch-cased", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[ "nl" ]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-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 4.39.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #safetensors #bert #text-classification #generated_from_trainer #nl #dataset-GroNLP/dutch-cola #base_model-GroNLP/bert-base-dutch-cased #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: 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 4.39.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.15.2" ]

[ "sentence-transformers", "safetensors", "bert", "sentence-similarity", "feature-extraction", "loss:CosineSimilarityLoss", "en", "arxiv:1908.10084", "base_model:google-bert/bert-base-uncased", "model-index", "co2_eq_emissions", "endpoints_compatible", "region:us" ]

[ "1908.10084" ]

[ "en" ]

[ "### Model Description\n\n\n* Model Type: Sentence Transformer\n* Base model: google-bert/bert-base-uncased\n* Maximum Sequence Length: 512 tokens\n* Output Dimensionality: 768 tokens\n* Similarity Function: Cosine Similarity\n* Training Dataset:\n\t+ sentence-transformers/stsb\n* Language: en", "### Model Sources\n\n\n* Documentation: Sentence Transformers Documentation\n* Repository: Sentence Transformers on GitHub\n* Hugging Face: Sentence Transformers on Hugging Face", "### Full Model Architecture\n\n\nUsage\n-----", "### Direct Usage (Sentence Transformers)\n\n\nFirst install the Sentence Transformers library:\n\n\nThen you can load this model and run inference.\n\n\nEvaluation\n----------", "### Metrics", "#### Semantic Similarity\n\n\n* Dataset: 'sts-dev'\n* Evaluated with `EmbeddingSimilarityEvaluator`", "#### Semantic Similarity\n\n\n* Dataset: 'sts-test'\n* Evaluated with `EmbeddingSimilarityEvaluator`\n\n\n\nTraining Details\n----------------", "### Training Dataset", "#### sentence-transformers/stsb\n\n\n* Dataset: sentence-transformers/stsb at d999f12\n* Size: 11,498 training samples\n* Columns: `sentence1`, `sentence2`, and `score`\n* Approximate statistics based on the first 1000 samples:\n* Samples:\n* Loss: `CosineSimilarityLoss` with these parameters:", "### Evaluation Dataset", "#### sentence-transformers/stsb\n\n\n* Dataset: sentence-transformers/stsb at d999f12\n* Size: 1,500 evaluation samples\n* Columns: `sentence1`, `sentence2`, and `score`\n* Approximate statistics based on the first 1000 samples:\n* Samples:\n* Loss: `CosineSimilarityLoss` with these parameters:", "### Training Hyperparameters", "#### Non-Default Hyperparameters\n\n\n* 'eval\\_strategy': steps\n* 'per\\_device\\_train\\_batch\\_size': 16\n* 'per\\_device\\_eval\\_batch\\_size': 16\n* 'num\\_train\\_epochs': 1\n* 'warmup\\_ratio': 0.1\n* 'fp16': True", "#### All Hyperparameters\n\n\nClick to expand\n* 'overwrite\\_output\\_dir': False\n* 'do\\_predict': False\n* 'eval\\_strategy': steps\n* 'prediction\\_loss\\_only': False\n* 'per\\_device\\_train\\_batch\\_size': 16\n* 'per\\_device\\_eval\\_batch\\_size': 16\n* 'per\\_gpu\\_train\\_batch\\_size': None\n* 'per\\_gpu\\_eval\\_batch\\_size': None\n* 'gradient\\_accumulation\\_steps': 1\n* 'eval\\_accumulation\\_steps': None\n* 'learning\\_rate': 5e-05\n* 'weight\\_decay': 0.0\n* 'adam\\_beta1': 0.9\n* 'adam\\_beta2': 0.999\n* 'adam\\_epsilon': 1e-08\n* 'max\\_grad\\_norm': 1.0\n* 'num\\_train\\_epochs': 1\n* 'max\\_steps': -1\n* 'lr\\_scheduler\\_type': linear\n* 'lr\\_scheduler\\_kwargs': {}\n* 'warmup\\_ratio': 0.1\n* 'warmup\\_steps': 0\n* 'log\\_level': passive\n* 'log\\_level\\_replica': warning\n* 'log\\_on\\_each\\_node': True\n* 'logging\\_nan\\_inf\\_filter': True\n* 'save\\_safetensors': True\n* 'save\\_on\\_each\\_node': False\n* 'save\\_only\\_model': False\n* 'no\\_cuda': False\n* 'use\\_cpu': False\n* 'use\\_mps\\_device': False\n* 'seed': 42\n* 'data\\_seed': None\n* 'jit\\_mode\\_eval': False\n* 'use\\_ipex': False\n* 'bf16': False\n* 'fp16': True\n* 'fp16\\_opt\\_level': O1\n* 'half\\_precision\\_backend': auto\n* 'bf16\\_full\\_eval': False\n* 'fp16\\_full\\_eval': False\n* 'tf32': None\n* 'local\\_rank': 0\n* 'ddp\\_backend': None\n* 'tpu\\_num\\_cores': None\n* 'tpu\\_metrics\\_debug': False\n* 'debug': []\n* 'dataloader\\_drop\\_last': False\n* 'dataloader\\_num\\_workers': 0\n* 'dataloader\\_prefetch\\_factor': None\n* 'past\\_index': -1\n* 'disable\\_tqdm': False\n* 'remove\\_unused\\_columns': True\n* 'label\\_names': None\n* 'load\\_best\\_model\\_at\\_end': False\n* 'ignore\\_data\\_skip': False\n* 'fsdp': []\n* 'fsdp\\_min\\_num\\_params': 0\n* 'fsdp\\_config': {'min\\_num\\_params': 0, 'xla': False, 'xla\\_fsdp\\_v2': False, 'xla\\_fsdp\\_grad\\_ckpt': False}\n* 'fsdp\\_transformer\\_layer\\_cls\\_to\\_wrap': None\n* 'accelerator\\_config': {'split\\_batches': False, 'dispatch\\_batches': None, 'even\\_batches': True, 'use\\_seedable\\_sampler': True, 'non\\_blocking': False, 'gradient\\_accumulation\\_kwargs': None}\n* 'deepspeed': None\n* 'label\\_smoothing\\_factor': 0.0\n* 'optim': adamw\\_torch\n* 'optim\\_args': None\n* 'adafactor': False\n* 'group\\_by\\_length': False\n* 'length\\_column\\_name': length\n* 'ddp\\_find\\_unused\\_parameters': None\n* 'ddp\\_bucket\\_cap\\_mb': None\n* 'ddp\\_broadcast\\_buffers': None\n* 'dataloader\\_pin\\_memory': True\n* 'dataloader\\_persistent\\_workers': False\n* 'skip\\_memory\\_metrics': True\n* 'use\\_legacy\\_prediction\\_loop': False\n* 'push\\_to\\_hub': False\n* 'resume\\_from\\_checkpoint': None\n* 'hub\\_model\\_id': None\n* 'hub\\_strategy': every\\_save\n* 'hub\\_private\\_repo': False\n* 'hub\\_always\\_push': False\n* 'gradient\\_checkpointing': False\n* 'gradient\\_checkpointing\\_kwargs': None\n* 'include\\_inputs\\_for\\_metrics': False\n* 'eval\\_do\\_concat\\_batches': True\n* 'fp16\\_backend': auto\n* 'push\\_to\\_hub\\_model\\_id': None\n* 'push\\_to\\_hub\\_organization': None\n* 'mp\\_parameters':\n* 'auto\\_find\\_batch\\_size': False\n* 'full\\_determinism': False\n* 'torchdynamo': None\n* 'ray\\_scope': last\n* 'ddp\\_timeout': 1800\n* 'torch\\_compile': False\n* 'torch\\_compile\\_backend': None\n* 'torch\\_compile\\_mode': None\n* 'dispatch\\_batches': None\n* 'split\\_batches': None\n* 'include\\_tokens\\_per\\_second': False\n* 'include\\_num\\_input\\_tokens\\_seen': False\n* 'neftune\\_noise\\_alpha': None\n* 'optim\\_target\\_modules': None\n* 'batch\\_sampler': batch\\_sampler\n* 'multi\\_dataset\\_batch\\_sampler': proportional", "### Training Logs\n\n\n| Epoch | Step | Training Loss | loss | sts-dev\\_spearman\\_cosine | sts-test\\_spearman\\_cosine |\n|:------:|:----:|:-------------:|:------:|:-----------------------:| |\n| 0.1391 | 100 | 0.0572 | 0.0427 | 0.8222 | |\n| 0.2782 | 200 | 0.0316 | 0.0342 | 0.8450 | |\n| 0.4172 | 300 | 0.0276 | 0.0324 | 0.8621 | |\n| 0.5563 | 400 | 0.0246 | 0.0300 | 0.8661 | |\n| 0.6954 | 500 | 0.0206 | 0.0288 | 0.8650 | |\n| 0.8345 | 600 | 0.0186 | 0.0301 | 0.8696 | |\n| 0.9736 | 700 | 0.0185 | 0.0286 | 0.8703 | |\n| 1.0 | 719 | - | - | 0.8363 | 0.8363 |", "### Environmental Impact\n\n\nCarbon emissions were measured using CodeCarbon.\n\n\n* Energy Consumed: 0.012 kWh\n* Carbon Emitted: 0.005 kg of CO2\n* Hours Used: 0.058 hours", "### Training Hardware\n\n\n* On Cloud: No\n* GPU Model: 1 x NVIDIA GeForce RTX 3090\n* CPU Model: 13th Gen Intel(R) Core(TM) i7-13700K\n* RAM Size: 31.78 GB", "### Framework Versions\n\n\n* Python: 3.11.6\n* Sentence Transformers: 3.0.0.dev0\n* Transformers: 4.41.0.dev0\n* PyTorch: 2.3.0+cu121\n* Accelerate: 0.26.1\n* Datasets: 2.18.0\n* Tokenizers: 0.19.1", "### BibTeX", "#### Sentence Transformers" ]

[ "TAGS\n#sentence-transformers #safetensors #bert #sentence-similarity #feature-extraction #loss-CosineSimilarityLoss #en #arxiv-1908.10084 #base_model-google-bert/bert-base-uncased #model-index #co2_eq_emissions #endpoints_compatible #region-us \n", "### Model Description\n\n\n* Model Type: Sentence Transformer\n* Base model: google-bert/bert-base-uncased\n* Maximum Sequence Length: 512 tokens\n* Output Dimensionality: 768 tokens\n* Similarity Function: Cosine Similarity\n* Training Dataset:\n\t+ sentence-transformers/stsb\n* Language: en", "### Model Sources\n\n\n* Documentation: Sentence Transformers Documentation\n* Repository: Sentence Transformers on GitHub\n* Hugging Face: Sentence Transformers on Hugging Face", "### Full Model Architecture\n\n\nUsage\n-----", "### Direct Usage (Sentence Transformers)\n\n\nFirst install the Sentence Transformers library:\n\n\nThen you can load this model and run inference.\n\n\nEvaluation\n----------", "### Metrics", "#### Semantic Similarity\n\n\n* Dataset: 'sts-dev'\n* Evaluated with `EmbeddingSimilarityEvaluator`", "#### Semantic Similarity\n\n\n* Dataset: 'sts-test'\n* Evaluated with `EmbeddingSimilarityEvaluator`\n\n\n\nTraining Details\n----------------", "### Training Dataset", "#### sentence-transformers/stsb\n\n\n* Dataset: sentence-transformers/stsb at d999f12\n* Size: 11,498 training samples\n* Columns: `sentence1`, `sentence2`, and `score`\n* Approximate statistics based on the first 1000 samples:\n* Samples:\n* Loss: `CosineSimilarityLoss` with these parameters:", "### Evaluation Dataset", "#### sentence-transformers/stsb\n\n\n* Dataset: sentence-transformers/stsb at d999f12\n* Size: 1,500 evaluation samples\n* Columns: `sentence1`, `sentence2`, and `score`\n* Approximate statistics based on the first 1000 samples:\n* Samples:\n* Loss: `CosineSimilarityLoss` with these parameters:", "### Training Hyperparameters", "#### Non-Default Hyperparameters\n\n\n* 'eval\\_strategy': steps\n* 'per\\_device\\_train\\_batch\\_size': 16\n* 'per\\_device\\_eval\\_batch\\_size': 16\n* 'num\\_train\\_epochs': 1\n* 'warmup\\_ratio': 0.1\n* 'fp16': True", "#### All Hyperparameters\n\n\nClick to expand\n* 'overwrite\\_output\\_dir': False\n* 'do\\_predict': False\n* 'eval\\_strategy': steps\n* 'prediction\\_loss\\_only': False\n* 'per\\_device\\_train\\_batch\\_size': 16\n* 'per\\_device\\_eval\\_batch\\_size': 16\n* 'per\\_gpu\\_train\\_batch\\_size': None\n* 'per\\_gpu\\_eval\\_batch\\_size': None\n* 'gradient\\_accumulation\\_steps': 1\n* 'eval\\_accumulation\\_steps': None\n* 'learning\\_rate': 5e-05\n* 'weight\\_decay': 0.0\n* 'adam\\_beta1': 0.9\n* 'adam\\_beta2': 0.999\n* 'adam\\_epsilon': 1e-08\n* 'max\\_grad\\_norm': 1.0\n* 'num\\_train\\_epochs': 1\n* 'max\\_steps': -1\n* 'lr\\_scheduler\\_type': linear\n* 'lr\\_scheduler\\_kwargs': {}\n* 'warmup\\_ratio': 0.1\n* 'warmup\\_steps': 0\n* 'log\\_level': passive\n* 'log\\_level\\_replica': warning\n* 'log\\_on\\_each\\_node': True\n* 'logging\\_nan\\_inf\\_filter': True\n* 'save\\_safetensors': True\n* 'save\\_on\\_each\\_node': False\n* 'save\\_only\\_model': False\n* 'no\\_cuda': False\n* 'use\\_cpu': False\n* 'use\\_mps\\_device': False\n* 'seed': 42\n* 'data\\_seed': None\n* 'jit\\_mode\\_eval': False\n* 'use\\_ipex': False\n* 'bf16': False\n* 'fp16': True\n* 'fp16\\_opt\\_level': O1\n* 'half\\_precision\\_backend': auto\n* 'bf16\\_full\\_eval': False\n* 'fp16\\_full\\_eval': False\n* 'tf32': None\n* 'local\\_rank': 0\n* 'ddp\\_backend': None\n* 'tpu\\_num\\_cores': None\n* 'tpu\\_metrics\\_debug': False\n* 'debug': []\n* 'dataloader\\_drop\\_last': False\n* 'dataloader\\_num\\_workers': 0\n* 'dataloader\\_prefetch\\_factor': None\n* 'past\\_index': -1\n* 'disable\\_tqdm': False\n* 'remove\\_unused\\_columns': True\n* 'label\\_names': None\n* 'load\\_best\\_model\\_at\\_end': False\n* 'ignore\\_data\\_skip': False\n* 'fsdp': []\n* 'fsdp\\_min\\_num\\_params': 0\n* 'fsdp\\_config': {'min\\_num\\_params': 0, 'xla': False, 'xla\\_fsdp\\_v2': False, 'xla\\_fsdp\\_grad\\_ckpt': False}\n* 'fsdp\\_transformer\\_layer\\_cls\\_to\\_wrap': None\n* 'accelerator\\_config': {'split\\_batches': False, 'dispatch\\_batches': None, 'even\\_batches': True, 'use\\_seedable\\_sampler': True, 'non\\_blocking': False, 'gradient\\_accumulation\\_kwargs': None}\n* 'deepspeed': None\n* 'label\\_smoothing\\_factor': 0.0\n* 'optim': adamw\\_torch\n* 'optim\\_args': None\n* 'adafactor': False\n* 'group\\_by\\_length': False\n* 'length\\_column\\_name': length\n* 'ddp\\_find\\_unused\\_parameters': None\n* 'ddp\\_bucket\\_cap\\_mb': None\n* 'ddp\\_broadcast\\_buffers': None\n* 'dataloader\\_pin\\_memory': True\n* 'dataloader\\_persistent\\_workers': False\n* 'skip\\_memory\\_metrics': True\n* 'use\\_legacy\\_prediction\\_loop': False\n* 'push\\_to\\_hub': False\n* 'resume\\_from\\_checkpoint': None\n* 'hub\\_model\\_id': None\n* 'hub\\_strategy': every\\_save\n* 'hub\\_private\\_repo': False\n* 'hub\\_always\\_push': False\n* 'gradient\\_checkpointing': False\n* 'gradient\\_checkpointing\\_kwargs': None\n* 'include\\_inputs\\_for\\_metrics': False\n* 'eval\\_do\\_concat\\_batches': True\n* 'fp16\\_backend': auto\n* 'push\\_to\\_hub\\_model\\_id': None\n* 'push\\_to\\_hub\\_organization': None\n* 'mp\\_parameters':\n* 'auto\\_find\\_batch\\_size': False\n* 'full\\_determinism': False\n* 'torchdynamo': None\n* 'ray\\_scope': last\n* 'ddp\\_timeout': 1800\n* 'torch\\_compile': False\n* 'torch\\_compile\\_backend': None\n* 'torch\\_compile\\_mode': None\n* 'dispatch\\_batches': None\n* 'split\\_batches': None\n* 'include\\_tokens\\_per\\_second': False\n* 'include\\_num\\_input\\_tokens\\_seen': False\n* 'neftune\\_noise\\_alpha': None\n* 'optim\\_target\\_modules': None\n* 'batch\\_sampler': batch\\_sampler\n* 'multi\\_dataset\\_batch\\_sampler': proportional", "### Training Logs\n\n\n| Epoch | Step | Training Loss | loss | sts-dev\\_spearman\\_cosine | sts-test\\_spearman\\_cosine |\n|:------:|:----:|:-------------:|:------:|:-----------------------:| |\n| 0.1391 | 100 | 0.0572 | 0.0427 | 0.8222 | |\n| 0.2782 | 200 | 0.0316 | 0.0342 | 0.8450 | |\n| 0.4172 | 300 | 0.0276 | 0.0324 | 0.8621 | |\n| 0.5563 | 400 | 0.0246 | 0.0300 | 0.8661 | |\n| 0.6954 | 500 | 0.0206 | 0.0288 | 0.8650 | |\n| 0.8345 | 600 | 0.0186 | 0.0301 | 0.8696 | |\n| 0.9736 | 700 | 0.0185 | 0.0286 | 0.8703 | |\n| 1.0 | 719 | - | - | 0.8363 | 0.8363 |", "### Environmental Impact\n\n\nCarbon emissions were measured using CodeCarbon.\n\n\n* Energy Consumed: 0.012 kWh\n* Carbon Emitted: 0.005 kg of CO2\n* Hours Used: 0.058 hours", "### Training Hardware\n\n\n* On Cloud: No\n* GPU Model: 1 x NVIDIA GeForce RTX 3090\n* CPU Model: 13th Gen Intel(R) Core(TM) i7-13700K\n* RAM Size: 31.78 GB", "### Framework Versions\n\n\n* Python: 3.11.6\n* Sentence Transformers: 3.0.0.dev0\n* Transformers: 4.41.0.dev0\n* PyTorch: 2.3.0+cu121\n* Accelerate: 0.26.1\n* Datasets: 2.18.0\n* Tokenizers: 0.19.1", "### BibTeX", "#### Sentence Transformers" ]

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

[]

[ "en" ]

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

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

[ "tensorboard", "LunarLander-v2", "ppo", "deep-reinforcement-learning", "reinforcement-learning", "custom-implementation", "deep-rl-course", "model-index", "region:us" ]

[]

[]

[ "# PPO Agent Playing LunarLander-v2\n\n This is a trained model of a PPO agent playing LunarLander-v2.\n \n # Hyperparameters" ]

[ "TAGS\n#tensorboard #LunarLander-v2 #ppo #deep-reinforcement-learning #reinforcement-learning #custom-implementation #deep-rl-course #model-index #region-us \n", "# PPO Agent Playing LunarLander-v2\n\n This is a trained model of a PPO agent playing LunarLander-v2.\n \n # Hyperparameters" ]

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

[ "1910.09700" ]

[]

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

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

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

[]

[]

[ "# t5-finetuned-en-to-es-eval1\n\nThis model is a fine-tuned version of t5-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: 2e-05\n- train_batch_size: 48\n- eval_batch_size: 48\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 1\n- mixed_precision_training: Native AMP", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-t5-base #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# t5-finetuned-en-to-es-eval1\n\nThis model is a fine-tuned version of t5-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: 2e-05\n- train_batch_size: 48\n- eval_batch_size: 48\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 1\n- mixed_precision_training: Native AMP", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "gguf", "facebook", "meta", "pytorch", "llama", "llama-3", "llama-cpp", "gguf-my-repo", "text-generation", "en", "region:us" ]

[]

[ "en" ]

[ "### Use with transformers\n\n\nYou can run conversational inference using the Transformers pipeline abstraction, or by leveraging the Auto classes with the 'generate()' function. Let's see examples of both.", "#### Transformers pipeline", "#### Transformers AutoModelForCausalLM", "### Use with 'llama3'\n\n\nPlease, follow the instructions in the repository\n\n\nTo download Original checkpoints, see the example command below leveraging 'huggingface-cli':\n\n\nFor Hugging Face support, we recommend using transformers or TGI, but a similar command works.\n\n\nHardware and Software\n---------------------\n\n\nTraining Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.\n\n\nCarbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.\n\n\n\nCO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.\n\n\nTraining Data\n-------------\n\n\nOverview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.\n\n\nData Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.\n\n\nBenchmarks\n----------\n\n\nIn this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see here.", "### Base pretrained models", "### Instruction tuned models", "### Responsibility & Safety\n\n\nWe believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.\n\n\nFoundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.\n\n\nRather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.\n\n\nAs part of the Llama 3 release, we updated our Responsible Use Guide to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including Meta Llama Guard 2 and Code Shield safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a reference implementation to get you started.", "#### Llama 3-Instruct\n\n\nAs outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.\n\n\nSafety\n\n\nFor our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.\n\n\nRefusals\n\n\nIn addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.\n\n\nWe built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.", "#### Responsible release\n\n\nIn addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.\n\n\nMisuse\n\n\nIf you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at URL", "#### Critical risks\n\n\nCBRNE (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)\n\n\nWe have conducted a two fold assessment of the safety of the model in this area:\n\n\n* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.\n* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).", "### Cyber Security\n\n\nWe have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of equivalent coding capability.", "### Child Safety\n\n\nChild Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.", "### Community\n\n\nGenerative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our Github repository.\n\n\nFinally, we put in place a set of resources including an output reporting mechanism and bug bounty program to continuously improve the Llama technology with the help of the community.\n\n\nEthical Considerations and Limitations\n--------------------------------------\n\n\nThe core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.\n\n\nBut Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating Purple Llama solutions into your workflows and specifically Llama Guard which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.\n\n\nPlease see the Responsible Use Guide available at URL\n\n\ninstructions\n\n\n@article{llama3modelcard,\n\n\ntitle={Llama 3 Model Card},\n\n\nauthor={AI@Meta},\n\n\nyear={2024},\n\n\nurl = {URL\n\n\n}\n\n\nContributors\n------------\n\n\nAaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos" ]

[ "TAGS\n#gguf #facebook #meta #pytorch #llama #llama-3 #llama-cpp #gguf-my-repo #text-generation #en #region-us \n", "### Use with transformers\n\n\nYou can run conversational inference using the Transformers pipeline abstraction, or by leveraging the Auto classes with the 'generate()' function. Let's see examples of both.", "#### Transformers pipeline", "#### Transformers AutoModelForCausalLM", "### Use with 'llama3'\n\n\nPlease, follow the instructions in the repository\n\n\nTo download Original checkpoints, see the example command below leveraging 'huggingface-cli':\n\n\nFor Hugging Face support, we recommend using transformers or TGI, but a similar command works.\n\n\nHardware and Software\n---------------------\n\n\nTraining Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.\n\n\nCarbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.\n\n\n\nCO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.\n\n\nTraining Data\n-------------\n\n\nOverview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.\n\n\nData Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.\n\n\nBenchmarks\n----------\n\n\nIn this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see here.", "### Base pretrained models", "### Instruction tuned models", "### Responsibility & Safety\n\n\nWe believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.\n\n\nFoundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.\n\n\nRather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.\n\n\nAs part of the Llama 3 release, we updated our Responsible Use Guide to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including Meta Llama Guard 2 and Code Shield safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a reference implementation to get you started.", "#### Llama 3-Instruct\n\n\nAs outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.\n\n\nSafety\n\n\nFor our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.\n\n\nRefusals\n\n\nIn addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.\n\n\nWe built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.", "#### Responsible release\n\n\nIn addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.\n\n\nMisuse\n\n\nIf you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at URL", "#### Critical risks\n\n\nCBRNE (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)\n\n\nWe have conducted a two fold assessment of the safety of the model in this area:\n\n\n* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.\n* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).", "### Cyber Security\n\n\nWe have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of equivalent coding capability.", "### Child Safety\n\n\nChild Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.", "### Community\n\n\nGenerative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our Github repository.\n\n\nFinally, we put in place a set of resources including an output reporting mechanism and bug bounty program to continuously improve the Llama technology with the help of the community.\n\n\nEthical Considerations and Limitations\n--------------------------------------\n\n\nThe core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.\n\n\nBut Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating Purple Llama solutions into your workflows and specifically Llama Guard which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.\n\n\nPlease see the Responsible Use Guide available at URL\n\n\ninstructions\n\n\n@article{llama3modelcard,\n\n\ntitle={Llama 3 Model Card},\n\n\nauthor={AI@Meta},\n\n\nyear={2024},\n\n\nurl = {URL\n\n\n}\n\n\nContributors\n------------\n\n\nAaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos" ]

[ "transformers", "safetensors", "gemma", "text-generation", "arxiv:2312.11805", "arxiv:2009.03300", "arxiv:1905.07830", "arxiv:1911.11641", "arxiv:1904.09728", "arxiv:1905.10044", "arxiv:1907.10641", "arxiv:1811.00937", "arxiv:1809.02789", "arxiv:1911.01547", "arxiv:1705.03551", "arxiv:2107.03374", "arxiv:2108.07732", "arxiv:2110.14168", "arxiv:2304.06364", "arxiv:2206.04615", "arxiv:1804.06876", "arxiv:2110.08193", "arxiv:2009.11462", "arxiv:2101.11718", "arxiv:1804.09301", "arxiv:2109.07958", "arxiv:2203.09509", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "8-bit", "region:us" ]

[ "2312.11805", "2009.03300", "1905.07830", "1911.11641", "1904.09728", "1905.10044", "1907.10641", "1811.00937", "1809.02789", "1911.01547", "1705.03551", "2107.03374", "2108.07732", "2110.14168", "2304.06364", "2206.04615", "1804.06876", "2110.08193", "2009.11462", "2101.11718", "1804.09301", "2109.07958", "2203.09509" ]

[]

[ "### Description\n\n\nGemma is a family of lightweight, state-of-the-art open models from Google,\nbuilt from the same research and technology used to create the Gemini models.\nThey are text-to-text, decoder-only large language models, available in English,\nwith open weights, pre-trained variants, and instruction-tuned variants. Gemma\nmodels are well-suited for a variety of text generation tasks, including\nquestion answering, summarization, and reasoning. Their relatively small size\nmakes it possible to deploy them in environments with limited resources such as\na laptop, desktop or your own cloud infrastructure, democratizing access to\nstate of the art AI models and helping foster innovation for everyone.", "### Usage\n\n\nBelow we share some code snippets on how to get quickly started with running the model. First make sure to 'pip install -U transformers', then copy the snippet from the section that is relevant for your usecase.", "#### Fine-tuning the model\n\n\nYou can find fine-tuning scripts and notebook under the 'examples/' directory of 'google/gemma-7b' repository. To adapt it to this model, simply change the model-id to 'google/gemma-2b'.\nIn that repository, we provide:\n\n\n* A script to perform Supervised Fine-Tuning (SFT) on UltraChat dataset using QLoRA\n* A script to perform SFT using FSDP on TPU devices\n* A notebook that you can run on a free-tier Google Colab instance to perform SFT on English quotes dataset", "#### Running the model on a CPU", "#### Running the model on a single / multi GPU", "#### Running the model on a GPU using different precisions\n\n\n* *Using 'torch.float16'*\n* *Using 'torch.bfloat16'*", "#### Quantized Versions through 'bitsandbytes'\n\n\n* *Using 8-bit precision (int8)*\n* *Using 4-bit precision*", "#### Other optimizations\n\n\n* *Flash Attention 2*\n\n\nFirst make sure to install 'flash-attn' in your environment 'pip install flash-attn'", "### Inputs and outputs\n\n\n* Input: Text string, such as a question, a prompt, or a document to be\nsummarized.\n* Output: Generated English-language text in response to the input, such\nas an answer to a question, or a summary of a document.\n\n\nModel Data\n----------\n\n\nData used for model training and how the data was processed.", "### Training Dataset\n\n\nThese models were trained on a dataset of text data that includes a wide variety\nof sources, totaling 6 trillion tokens. Here are the key components:\n\n\n* Web Documents: A diverse collection of web text ensures the model is exposed\nto a broad range of linguistic styles, topics, and vocabulary. Primarily\nEnglish-language content.\n* Code: Exposing the model to code helps it to learn the syntax and patterns of\nprogramming languages, which improves its ability to generate code or\nunderstand code-related questions.\n* Mathematics: Training on mathematical text helps the model learn logical\nreasoning, symbolic representation, and to address mathematical queries.\n\n\nThe combination of these diverse data sources is crucial for training a powerful\nlanguage model that can handle a wide variety of different tasks and text\nformats.", "### Data Preprocessing\n\n\nHere are the key data cleaning and filtering methods applied to the training\ndata:\n\n\n* CSAM Filtering: Rigorous CSAM (Child Sexual Abuse Material) filtering was\napplied at multiple stages in the data preparation process to ensure the\nexclusion of harmful and illegal content\n* Sensitive Data Filtering: As part of making Gemma pre-trained models safe and\nreliable, automated techniques were used to filter out certain personal\ninformation and other sensitive data from training sets.\n* Additional methods: Filtering based on content quality and safely in line with\nour policies.\n\n\nImplementation Information\n--------------------------\n\n\nDetails about the model internals.", "### Hardware\n\n\nGemma was trained using the latest generation of\nTensor Processing Unit (TPU) hardware (TPUv5e).\n\n\nTraining large language models requires significant computational power. TPUs,\ndesigned specifically for matrix operations common in machine learning, offer\nseveral advantages in this domain:\n\n\n* Performance: TPUs are specifically designed to handle the massive computations\ninvolved in training LLMs. They can speed up training considerably compared to\nCPUs.\n* Memory: TPUs often come with large amounts of high-bandwidth memory, allowing\nfor the handling of large models and batch sizes during training. This can\nlead to better model quality.\n* Scalability: TPU Pods (large clusters of TPUs) provide a scalable solution for\nhandling the growing complexity of large foundation models. You can distribute\ntraining across multiple TPU devices for faster and more efficient processing.\n* Cost-effectiveness: In many scenarios, TPUs can provide a more cost-effective\nsolution for training large models compared to CPU-based infrastructure,\nespecially when considering the time and resources saved due to faster\ntraining.\n* These advantages are aligned with\nGoogle's commitments to operate sustainably.", "### Software\n\n\nTraining was done using JAX and ML Pathways.\n\n\nJAX allows researchers to take advantage of the latest generation of hardware,\nincluding TPUs, for faster and more efficient training of large models.\n\n\nML Pathways is Google's latest effort to build artificially intelligent systems\ncapable of generalizing across multiple tasks. This is specially suitable for\nfoundation models, including large language models like\nthese ones.\n\n\nTogether, JAX and ML Pathways are used as described in the\npaper about the Gemini family of models; \"the 'single\ncontroller' programming model of Jax and Pathways allows a single Python\nprocess to orchestrate the entire training run, dramatically simplifying the\ndevelopment workflow.\"\n\n\nEvaluation\n----------\n\n\nModel evaluation metrics and results.", "### Benchmark Results\n\n\nThese models were evaluated against a large collection of different datasets and\nmetrics to cover different aspects of text generation:\n\n\n\nEthics and Safety\n-----------------\n\n\nEthics and safety evaluation approach and results.", "### Evaluation Approach\n\n\nOur evaluation methods include structured evaluations and internal red-teaming\ntesting of relevant content policies. Red-teaming was conducted by a number of\ndifferent teams, each with different goals and human evaluation metrics. These\nmodels were evaluated against a number of different categories relevant to\nethics and safety, including:\n\n\n* Text-to-Text Content Safety: Human evaluation on prompts covering safety\npolicies including child sexual abuse and exploitation, harassment, violence\nand gore, and hate speech.\n* Text-to-Text Representational Harms: Benchmark against relevant academic\ndatasets such as WinoBias and BBQ Dataset.\n* Memorization: Automated evaluation of memorization of training data, including\nthe risk of personally identifiable information exposure.\n* Large-scale harm: Tests for \"dangerous capabilities,\" such as chemical,\nbiological, radiological, and nuclear (CBRN) risks.", "### Evaluation Results\n\n\nThe results of ethics and safety evaluations are within acceptable thresholds\nfor meeting internal policies for categories such as child\nsafety, content safety, representational harms, memorization, large-scale harms.\nOn top of robust internal evaluations, the results of well known safety\nbenchmarks like BBQ, BOLD, Winogender, Winobias, RealToxicity, and TruthfulQA\nare shown here.\n\n\n\nUsage and Limitations\n---------------------\n\n\nThese models have certain limitations that users should be aware of.", "### Intended Usage\n\n\nOpen Large Language Models (LLMs) have a wide range of applications across\nvarious industries and domains. The following list of potential uses is not\ncomprehensive. The purpose of this list is to provide contextual information\nabout the possible use-cases that the model creators considered as part of model\ntraining and development.\n\n\n* Content Creation and Communication\n\t+ Text Generation: These models can be used to generate creative text formats\n\tsuch as poems, scripts, code, marketing copy, and email drafts.\n\t+ Chatbots and Conversational AI: Power conversational interfaces for customer\n\tservice, virtual assistants, or interactive applications.\n\t+ Text Summarization: Generate concise summaries of a text corpus, research\n\tpapers, or reports.\n* Research and Education\n\t+ Natural Language Processing (NLP) Research: These models can serve as a\n\tfoundation for researchers to experiment with NLP techniques, develop\n\talgorithms, and contribute to the advancement of the field.\n\t+ Language Learning Tools: Support interactive language learning experiences,\n\taiding in grammar correction or providing writing practice.\n\t+ Knowledge Exploration: Assist researchers in exploring large bodies of text\n\tby generating summaries or answering questions about specific topics.", "### Limitations\n\n\n* Training Data\n\t+ The quality and diversity of the training data significantly influence the\n\tmodel's capabilities. Biases or gaps in the training data can lead to\n\tlimitations in the model's responses.\n\t+ The scope of the training dataset determines the subject areas the model can\n\thandle effectively.\n* Context and Task Complexity\n\t+ LLMs are better at tasks that can be framed with clear prompts and\n\tinstructions. Open-ended or highly complex tasks might be challenging.\n\t+ A model's performance can be influenced by the amount of context provided\n\t(longer context generally leads to better outputs, up to a certain point).\n* Language Ambiguity and Nuance\n\t+ Natural language is inherently complex. LLMs might struggle to grasp subtle\n\tnuances, sarcasm, or figurative language.\n* Factual Accuracy\n\t+ LLMs generate responses based on information they learned from their\n\ttraining datasets, but they are not knowledge bases. They may generate\n\tincorrect or outdated factual statements.\n* Common Sense\n\t+ LLMs rely on statistical patterns in language. They might lack the ability\n\tto apply common sense reasoning in certain situations.", "### Ethical Considerations and Risks\n\n\nThe development of large language models (LLMs) raises several ethical concerns.\nIn creating an open model, we have carefully considered the following:\n\n\n* Bias and Fairness\n\t+ LLMs trained on large-scale, real-world text data can reflect socio-cultural\n\tbiases embedded in the training material. These models underwent careful\n\tscrutiny, input data pre-processing described and posterior evaluations\n\treported in this card.\n* Misinformation and Misuse\n\t+ LLMs can be misused to generate text that is false, misleading, or harmful.\n\t+ Guidelines are provided for responsible use with the model, see the\n\tResponsible Generative AI Toolkit.\n* Transparency and Accountability:\n\t+ This model card summarizes details on the models' architecture,\n\tcapabilities, limitations, and evaluation processes.\n\t+ A responsibly developed open model offers the opportunity to share\n\tinnovation by making LLM technology accessible to developers and researchers\n\tacross the AI ecosystem.\n\n\nRisks identified and mitigations:\n\n\n* Perpetuation of biases: It's encouraged to perform continuous monitoring\n(using evaluation metrics, human review) and the exploration of de-biasing\ntechniques during model training, fine-tuning, and other use cases.\n* Generation of harmful content: Mechanisms and guidelines for content safety\nare essential. Developers are encouraged to exercise caution and implement\nappropriate content safety safeguards based on their specific product policies\nand application use cases.\n* Misuse for malicious purposes: Technical limitations and developer and\nend-user education can help mitigate against malicious applications of LLMs.\nEducational resources and reporting mechanisms for users to flag misuse are\nprovided. Prohibited uses of Gemma models are outlined in the\nGemma Prohibited Use Policy.\n* Privacy violations: Models were trained on data filtered for removal of PII\n(Personally Identifiable Information). Developers are encouraged to adhere to\nprivacy regulations with privacy-preserving techniques.", "### Benefits\n\n\nAt the time of release, this family of models provides high-performance open\nlarge language model implementations designed from the ground up for Responsible\nAI development compared to similarly sized models.\n\n\nUsing the benchmark evaluation metrics described in this document, these models\nhave shown to provide superior performance to other, comparably-sized open model\nalternatives." ]

[ "TAGS\n#transformers #safetensors #gemma #text-generation #arxiv-2312.11805 #arxiv-2009.03300 #arxiv-1905.07830 #arxiv-1911.11641 #arxiv-1904.09728 #arxiv-1905.10044 #arxiv-1907.10641 #arxiv-1811.00937 #arxiv-1809.02789 #arxiv-1911.01547 #arxiv-1705.03551 #arxiv-2107.03374 #arxiv-2108.07732 #arxiv-2110.14168 #arxiv-2304.06364 #arxiv-2206.04615 #arxiv-1804.06876 #arxiv-2110.08193 #arxiv-2009.11462 #arxiv-2101.11718 #arxiv-1804.09301 #arxiv-2109.07958 #arxiv-2203.09509 #autotrain_compatible #endpoints_compatible #text-generation-inference #8-bit #region-us \n", "### Description\n\n\nGemma is a family of lightweight, state-of-the-art open models from Google,\nbuilt from the same research and technology used to create the Gemini models.\nThey are text-to-text, decoder-only large language models, available in English,\nwith open weights, pre-trained variants, and instruction-tuned variants. Gemma\nmodels are well-suited for a variety of text generation tasks, including\nquestion answering, summarization, and reasoning. Their relatively small size\nmakes it possible to deploy them in environments with limited resources such as\na laptop, desktop or your own cloud infrastructure, democratizing access to\nstate of the art AI models and helping foster innovation for everyone.", "### Usage\n\n\nBelow we share some code snippets on how to get quickly started with running the model. First make sure to 'pip install -U transformers', then copy the snippet from the section that is relevant for your usecase.", "#### Fine-tuning the model\n\n\nYou can find fine-tuning scripts and notebook under the 'examples/' directory of 'google/gemma-7b' repository. To adapt it to this model, simply change the model-id to 'google/gemma-2b'.\nIn that repository, we provide:\n\n\n* A script to perform Supervised Fine-Tuning (SFT) on UltraChat dataset using QLoRA\n* A script to perform SFT using FSDP on TPU devices\n* A notebook that you can run on a free-tier Google Colab instance to perform SFT on English quotes dataset", "#### Running the model on a CPU", "#### Running the model on a single / multi GPU", "#### Running the model on a GPU using different precisions\n\n\n* *Using 'torch.float16'*\n* *Using 'torch.bfloat16'*", "#### Quantized Versions through 'bitsandbytes'\n\n\n* *Using 8-bit precision (int8)*\n* *Using 4-bit precision*", "#### Other optimizations\n\n\n* *Flash Attention 2*\n\n\nFirst make sure to install 'flash-attn' in your environment 'pip install flash-attn'", "### Inputs and outputs\n\n\n* Input: Text string, such as a question, a prompt, or a document to be\nsummarized.\n* Output: Generated English-language text in response to the input, such\nas an answer to a question, or a summary of a document.\n\n\nModel Data\n----------\n\n\nData used for model training and how the data was processed.", "### Training Dataset\n\n\nThese models were trained on a dataset of text data that includes a wide variety\nof sources, totaling 6 trillion tokens. Here are the key components:\n\n\n* Web Documents: A diverse collection of web text ensures the model is exposed\nto a broad range of linguistic styles, topics, and vocabulary. Primarily\nEnglish-language content.\n* Code: Exposing the model to code helps it to learn the syntax and patterns of\nprogramming languages, which improves its ability to generate code or\nunderstand code-related questions.\n* Mathematics: Training on mathematical text helps the model learn logical\nreasoning, symbolic representation, and to address mathematical queries.\n\n\nThe combination of these diverse data sources is crucial for training a powerful\nlanguage model that can handle a wide variety of different tasks and text\nformats.", "### Data Preprocessing\n\n\nHere are the key data cleaning and filtering methods applied to the training\ndata:\n\n\n* CSAM Filtering: Rigorous CSAM (Child Sexual Abuse Material) filtering was\napplied at multiple stages in the data preparation process to ensure the\nexclusion of harmful and illegal content\n* Sensitive Data Filtering: As part of making Gemma pre-trained models safe and\nreliable, automated techniques were used to filter out certain personal\ninformation and other sensitive data from training sets.\n* Additional methods: Filtering based on content quality and safely in line with\nour policies.\n\n\nImplementation Information\n--------------------------\n\n\nDetails about the model internals.", "### Hardware\n\n\nGemma was trained using the latest generation of\nTensor Processing Unit (TPU) hardware (TPUv5e).\n\n\nTraining large language models requires significant computational power. TPUs,\ndesigned specifically for matrix operations common in machine learning, offer\nseveral advantages in this domain:\n\n\n* Performance: TPUs are specifically designed to handle the massive computations\ninvolved in training LLMs. They can speed up training considerably compared to\nCPUs.\n* Memory: TPUs often come with large amounts of high-bandwidth memory, allowing\nfor the handling of large models and batch sizes during training. This can\nlead to better model quality.\n* Scalability: TPU Pods (large clusters of TPUs) provide a scalable solution for\nhandling the growing complexity of large foundation models. You can distribute\ntraining across multiple TPU devices for faster and more efficient processing.\n* Cost-effectiveness: In many scenarios, TPUs can provide a more cost-effective\nsolution for training large models compared to CPU-based infrastructure,\nespecially when considering the time and resources saved due to faster\ntraining.\n* These advantages are aligned with\nGoogle's commitments to operate sustainably.", "### Software\n\n\nTraining was done using JAX and ML Pathways.\n\n\nJAX allows researchers to take advantage of the latest generation of hardware,\nincluding TPUs, for faster and more efficient training of large models.\n\n\nML Pathways is Google's latest effort to build artificially intelligent systems\ncapable of generalizing across multiple tasks. This is specially suitable for\nfoundation models, including large language models like\nthese ones.\n\n\nTogether, JAX and ML Pathways are used as described in the\npaper about the Gemini family of models; \"the 'single\ncontroller' programming model of Jax and Pathways allows a single Python\nprocess to orchestrate the entire training run, dramatically simplifying the\ndevelopment workflow.\"\n\n\nEvaluation\n----------\n\n\nModel evaluation metrics and results.", "### Benchmark Results\n\n\nThese models were evaluated against a large collection of different datasets and\nmetrics to cover different aspects of text generation:\n\n\n\nEthics and Safety\n-----------------\n\n\nEthics and safety evaluation approach and results.", "### Evaluation Approach\n\n\nOur evaluation methods include structured evaluations and internal red-teaming\ntesting of relevant content policies. Red-teaming was conducted by a number of\ndifferent teams, each with different goals and human evaluation metrics. These\nmodels were evaluated against a number of different categories relevant to\nethics and safety, including:\n\n\n* Text-to-Text Content Safety: Human evaluation on prompts covering safety\npolicies including child sexual abuse and exploitation, harassment, violence\nand gore, and hate speech.\n* Text-to-Text Representational Harms: Benchmark against relevant academic\ndatasets such as WinoBias and BBQ Dataset.\n* Memorization: Automated evaluation of memorization of training data, including\nthe risk of personally identifiable information exposure.\n* Large-scale harm: Tests for \"dangerous capabilities,\" such as chemical,\nbiological, radiological, and nuclear (CBRN) risks.", "### Evaluation Results\n\n\nThe results of ethics and safety evaluations are within acceptable thresholds\nfor meeting internal policies for categories such as child\nsafety, content safety, representational harms, memorization, large-scale harms.\nOn top of robust internal evaluations, the results of well known safety\nbenchmarks like BBQ, BOLD, Winogender, Winobias, RealToxicity, and TruthfulQA\nare shown here.\n\n\n\nUsage and Limitations\n---------------------\n\n\nThese models have certain limitations that users should be aware of.", "### Intended Usage\n\n\nOpen Large Language Models (LLMs) have a wide range of applications across\nvarious industries and domains. The following list of potential uses is not\ncomprehensive. The purpose of this list is to provide contextual information\nabout the possible use-cases that the model creators considered as part of model\ntraining and development.\n\n\n* Content Creation and Communication\n\t+ Text Generation: These models can be used to generate creative text formats\n\tsuch as poems, scripts, code, marketing copy, and email drafts.\n\t+ Chatbots and Conversational AI: Power conversational interfaces for customer\n\tservice, virtual assistants, or interactive applications.\n\t+ Text Summarization: Generate concise summaries of a text corpus, research\n\tpapers, or reports.\n* Research and Education\n\t+ Natural Language Processing (NLP) Research: These models can serve as a\n\tfoundation for researchers to experiment with NLP techniques, develop\n\talgorithms, and contribute to the advancement of the field.\n\t+ Language Learning Tools: Support interactive language learning experiences,\n\taiding in grammar correction or providing writing practice.\n\t+ Knowledge Exploration: Assist researchers in exploring large bodies of text\n\tby generating summaries or answering questions about specific topics.", "### Limitations\n\n\n* Training Data\n\t+ The quality and diversity of the training data significantly influence the\n\tmodel's capabilities. Biases or gaps in the training data can lead to\n\tlimitations in the model's responses.\n\t+ The scope of the training dataset determines the subject areas the model can\n\thandle effectively.\n* Context and Task Complexity\n\t+ LLMs are better at tasks that can be framed with clear prompts and\n\tinstructions. Open-ended or highly complex tasks might be challenging.\n\t+ A model's performance can be influenced by the amount of context provided\n\t(longer context generally leads to better outputs, up to a certain point).\n* Language Ambiguity and Nuance\n\t+ Natural language is inherently complex. LLMs might struggle to grasp subtle\n\tnuances, sarcasm, or figurative language.\n* Factual Accuracy\n\t+ LLMs generate responses based on information they learned from their\n\ttraining datasets, but they are not knowledge bases. They may generate\n\tincorrect or outdated factual statements.\n* Common Sense\n\t+ LLMs rely on statistical patterns in language. They might lack the ability\n\tto apply common sense reasoning in certain situations.", "### Ethical Considerations and Risks\n\n\nThe development of large language models (LLMs) raises several ethical concerns.\nIn creating an open model, we have carefully considered the following:\n\n\n* Bias and Fairness\n\t+ LLMs trained on large-scale, real-world text data can reflect socio-cultural\n\tbiases embedded in the training material. These models underwent careful\n\tscrutiny, input data pre-processing described and posterior evaluations\n\treported in this card.\n* Misinformation and Misuse\n\t+ LLMs can be misused to generate text that is false, misleading, or harmful.\n\t+ Guidelines are provided for responsible use with the model, see the\n\tResponsible Generative AI Toolkit.\n* Transparency and Accountability:\n\t+ This model card summarizes details on the models' architecture,\n\tcapabilities, limitations, and evaluation processes.\n\t+ A responsibly developed open model offers the opportunity to share\n\tinnovation by making LLM technology accessible to developers and researchers\n\tacross the AI ecosystem.\n\n\nRisks identified and mitigations:\n\n\n* Perpetuation of biases: It's encouraged to perform continuous monitoring\n(using evaluation metrics, human review) and the exploration of de-biasing\ntechniques during model training, fine-tuning, and other use cases.\n* Generation of harmful content: Mechanisms and guidelines for content safety\nare essential. Developers are encouraged to exercise caution and implement\nappropriate content safety safeguards based on their specific product policies\nand application use cases.\n* Misuse for malicious purposes: Technical limitations and developer and\nend-user education can help mitigate against malicious applications of LLMs.\nEducational resources and reporting mechanisms for users to flag misuse are\nprovided. Prohibited uses of Gemma models are outlined in the\nGemma Prohibited Use Policy.\n* Privacy violations: Models were trained on data filtered for removal of PII\n(Personally Identifiable Information). Developers are encouraged to adhere to\nprivacy regulations with privacy-preserving techniques.", "### Benefits\n\n\nAt the time of release, this family of models provides high-performance open\nlarge language model implementations designed from the ground up for Responsible\nAI development compared to similarly sized models.\n\n\nUsing the benchmark evaluation metrics described in this document, these models\nhave shown to provide superior performance to other, comparably-sized open model\nalternatives." ]

[ "transformers", "pytorch", "llama", "text-generation", "text-generation-inference", "unsloth", "trl", "en", "base_model:BanglaLLM/bangla-llama-7b-instruct-v0.1", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[ "# Uploaded model\n\n- Developed by: Kaizu07\n- License: apache-2.0\n- Finetuned from model : BanglaLLM/bangla-llama-7b-instruct-v0.1\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "TAGS\n#transformers #pytorch #llama #text-generation #text-generation-inference #unsloth #trl #en #base_model-BanglaLLM/bangla-llama-7b-instruct-v0.1 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "# Uploaded model\n\n- Developed by: Kaizu07\n- License: apache-2.0\n- Finetuned from model : BanglaLLM/bangla-llama-7b-instruct-v0.1\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

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

[ "1910.09700" ]

[]

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

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

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

[]

[]

[ "# NeuralsynthesisExperiment27pastiche-7B\n\nNeuralsynthesisExperiment27pastiche-7B is an automated merge created by Maxime Labonne using the following configuration.", "## Configuration", "## Usage" ]

[ "TAGS\n#merge #mergekit #lazymergekit #automerger #license-apache-2.0 #region-us \n", "# NeuralsynthesisExperiment27pastiche-7B\n\nNeuralsynthesisExperiment27pastiche-7B is an automated merge created by Maxime Labonne using the following configuration.", "## Configuration", "## Usage" ]

[ "transformers", "tensorboard", "safetensors", "autotrain", "text-generation-inference", "text-generation", "peft", "conversational", "license:other", "endpoints_compatible", "region:us" ]

[]

[]

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

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

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

[]

[ "en" ]

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

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

[ "transformers", "gguf", "en", "base_model:ImagineIt/StoryTeller-70b", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #en #base_model-ImagineIt/StoryTeller-70b #endpoints_compatible #region-us \n" ]

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

[ "1910.09700" ]

[]

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

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

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

[]

[]

[ "# Llama-2-7b-chat-hf_fictional_arc_easy_english_v2\n\nThis model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on the generator dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 1\n- eval_batch_size: 2\n- seed: 42\n- gradient_accumulation_steps: 8\n- total_train_batch_size: 8\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 18", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.1.2\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #trl #sft #generated_from_trainer #conversational #dataset-generator #base_model-meta-llama/Llama-2-7b-chat-hf #license-llama2 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Llama-2-7b-chat-hf_fictional_arc_easy_english_v2\n\nThis model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on the generator dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 1\n- eval_batch_size: 2\n- seed: 42\n- gradient_accumulation_steps: 8\n- total_train_batch_size: 8\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 18", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.1.2\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "transformers", "safetensors", "llama", "text-generation", "fp8", "conversational", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[]

[ "TAGS\n#transformers #safetensors #llama #text-generation #fp8 #conversational #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n" ]

[ "transformers", "safetensors", "llama", "text-generation", "4-bit", "AWQ", "autotrain_compatible", "endpoints_compatible", "axolotl", "finetune", "facebook", "meta", "pytorch", "llama-3", "conversational", "en", "dataset:mlabonne/chatml-OpenHermes2.5-dpo-binarized-alpha", "license:other", "text-generation-inference", "region:us" ]

[]

[ "en" ]

[ "# MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.1 AWQ\n\n- Model creator: MaziyarPanahi\n- Original model: Llama-3-8B-Instruct-DPO-v0.1\n\n<img src=\"./URL\" alt=\"Llama-3 DPO Logo\" width=\"500\" style=\"margin-left:'auto' margin-right:'auto' display:'block'\"/>\n\nThis model is a fine-tune (DPO) of 'meta-llama/Meta-Llama-3-8B-Instruct' model.", "## How to use\n\nThis model uses 'ChatML' prompt template:\n\n'", "### Install the necessary packages", "### Example Python code", "### About AWQ\n\nAWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings.\n\nAWQ models are currently supported on Linux and Windows, with NVidia GPUs only. macOS users: please use GGUF models instead.\n\nIt is supported by:\n\n- Text Generation Webui - using Loader: AutoAWQ\n- vLLM - version 0.2.2 or later for support for all model types.\n- Hugging Face Text Generation Inference (TGI)\n- Transformers version 4.35.0 and later, from any code or client that supports Transformers\n- AutoAWQ - for use from Python code" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #4-bit #AWQ #autotrain_compatible #endpoints_compatible #axolotl #finetune #facebook #meta #pytorch #llama-3 #conversational #en #dataset-mlabonne/chatml-OpenHermes2.5-dpo-binarized-alpha #license-other #text-generation-inference #region-us \n", "# MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.1 AWQ\n\n- Model creator: MaziyarPanahi\n- Original model: Llama-3-8B-Instruct-DPO-v0.1\n\n<img src=\"./URL\" alt=\"Llama-3 DPO Logo\" width=\"500\" style=\"margin-left:'auto' margin-right:'auto' display:'block'\"/>\n\nThis model is a fine-tune (DPO) of 'meta-llama/Meta-Llama-3-8B-Instruct' model.", "## How to use\n\nThis model uses 'ChatML' prompt template:\n\n'", "### Install the necessary packages", "### Example Python code", "### About AWQ\n\nAWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings.\n\nAWQ models are currently supported on Linux and Windows, with NVidia GPUs only. macOS users: please use GGUF models instead.\n\nIt is supported by:\n\n- Text Generation Webui - using Loader: AutoAWQ\n- vLLM - version 0.2.2 or later for support for all model types.\n- Hugging Face Text Generation Inference (TGI)\n- Transformers version 4.35.0 and later, from any code or client that supports Transformers\n- AutoAWQ - for use from Python code" ]

[ "transformers", "pytorch", "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: 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: 8", "### 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 #pytorch #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: 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: 8", "### 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", "mbart", "text2text-generation", "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 #mbart #text2text-generation #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", "detr", "object-detection", "vision", "generated_from_trainer", "base_model:facebook/detr-resnet-50", "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: 8\n* eval\\_batch\\_size: 8\n* seed: 1337\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 100.0\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.41.0.dev0\n* Pytorch 1.13.0+cu117\n* Datasets 2.18.0\n* Tokenizers 0.19.0" ]

[ "TAGS\n#transformers #safetensors #detr #object-detection #vision #generated_from_trainer #base_model-facebook/detr-resnet-50 #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: 8\n* eval\\_batch\\_size: 8\n* seed: 1337\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 100.0\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.41.0.dev0\n* Pytorch 1.13.0+cu117\n* Datasets 2.18.0\n* Tokenizers 0.19.0" ]

[ "transformers", "safetensors", "llama", "text-generation", "mergekit", "merge", "base_model:winninghealth/WiNGPT2-Llama-3-8B-Base", "base_model:johnsnowlabs/JSL-MedLlama-3-8B-v1.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# merge\n\nThis is a merge of pre-trained language models created using mergekit.", "## Merge Details", "### Merge Method\n\nThis model was merged using the SLERP merge method.", "### Models Merged\n\nThe following models were included in the merge:\n* winninghealth/WiNGPT2-Llama-3-8B-Base\n* johnsnowlabs/JSL-MedLlama-3-8B-v1.0", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #mergekit #merge #base_model-winninghealth/WiNGPT2-Llama-3-8B-Base #base_model-johnsnowlabs/JSL-MedLlama-3-8B-v1.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# merge\n\nThis is a merge of pre-trained language models created using mergekit.", "## Merge Details", "### Merge Method\n\nThis model was merged using the SLERP merge method.", "### Models Merged\n\nThe following models were included in the merge:\n* winninghealth/WiNGPT2-Llama-3-8B-Base\n* johnsnowlabs/JSL-MedLlama-3-8B-v1.0", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

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

[]

[]

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

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

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

[]

[ "en" ]

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

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

[ "transformers", "tensorboard", "safetensors", "gpt2", "text-generation", "generated_from_trainer", "dataset:eli5_category", "base_model:distilbert/distilgpt2", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3.0", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #gpt2 #text-generation #generated_from_trainer #dataset-eli5_category #base_model-distilbert/distilgpt2 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3.0", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "transformers", "safetensors", "llama", "text-generation", "arxiv:2304.12244", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "8-bit", "region:us" ]

[ "2304.12244" ]

[]

[ "## Model Details\n\nExperimental model. Trained with the Pygmalion and the WizardLM datasets.\n\nThe purpose of this model is to enable complex Instruct prompting but with the RP capabilties of Pygmalion.", "### Prompting format\n\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "### Uses\n\nThe intended use-case is Role-Playing with Instruct prompts. Guiding the bot towards a certain conversation style should be easier this way. Subject to experimentation.", "### Out-of-Scope Use\n\n- Assistant Bot [subject to providing incorrect instructions]\n- Complex multi-character chat", "### Risks\n\nThe model can generate potentially harmful or NSFW outputs. Please use with caution.\n\nWizardLM:" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #arxiv-2304.12244 #autotrain_compatible #endpoints_compatible #text-generation-inference #8-bit #region-us \n", "## Model Details\n\nExperimental model. Trained with the Pygmalion and the WizardLM datasets.\n\nThe purpose of this model is to enable complex Instruct prompting but with the RP capabilties of Pygmalion.", "### Prompting format\n\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "### Uses\n\nThe intended use-case is Role-Playing with Instruct prompts. Guiding the bot towards a certain conversation style should be easier this way. Subject to experimentation.", "### Out-of-Scope Use\n\n- Assistant Bot [subject to providing incorrect instructions]\n- Complex multi-character chat", "### Risks\n\nThe model can generate potentially harmful or NSFW outputs. Please use with caution.\n\nWizardLM:" ]

[ "peft", "arxiv:1910.09700", "base_model:meta-llama/Llama-2-7b-hf", "region:us" ]

[ "1910.09700" ]

[]

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

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

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

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0001\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 8\n* total\\_train\\_batch\\_size: 64\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\n* Transformers 4.41.0.dev0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#safetensors #generated_from_trainer #base_model-HuggingFaceM4/idefics2-8b #license-apache-2.0 #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0001\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 8\n* total\\_train\\_batch\\_size: 64\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\n* Transformers 4.41.0.dev0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

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

[]

[ "en" ]

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

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

[ "transformers", "gguf", "mistral", "quantized", "2-bit", "3-bit", "4-bit", "5-bit", "6-bit", "8-bit", "GGUF", "text-generation", "llama", "llama-3", "base_model:MaziyarPanahi/Llama-3-8B-Instruct-64k", "text-generation-inference", "region:us" ]

[]

[]

[ "# MaziyarPanahi/Llama-3-8B-Instruct-64k-GGUF\n- Model creator: MaziyarPanahi\n- Original model: MaziyarPanahi/Llama-3-8B-Instruct-64k", "## Description\nMaziyarPanahi/Llama-3-8B-Instruct-64k-GGUF contains GGUF format model files for MaziyarPanahi/Llama-3-8B-Instruct-64k.", "### About GGUF\n\nGGUF is a new format introduced by the URL team on August 21st 2023. It is a replacement for GGML, which is no longer supported by URL.\n\nHere is an incomplete list of clients and libraries that are known to support GGUF:\n\n* URL. The source project for GGUF. Offers a CLI and a server option.\n* llama-cpp-python, a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.\n* LM Studio, an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.\n* text-generation-webui, the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.\n* KoboldCpp, a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.\n* GPT4All, a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.\n* LoLLMS Web UI, a great web UI with many interesting and unique features, including a full model library for easy model selection.\n* URL, an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.\n* candle, a Rust ML framework with a focus on performance, including GPU support, and ease of use.\n* ctransformers, a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.", "## Special thanks\n\n Special thanks to Georgi Gerganov and the whole team working on URL for making all of this possible." ]

[ "TAGS\n#transformers #gguf #mistral #quantized #2-bit #3-bit #4-bit #5-bit #6-bit #8-bit #GGUF #text-generation #llama #llama-3 #base_model-MaziyarPanahi/Llama-3-8B-Instruct-64k #text-generation-inference #region-us \n", "# MaziyarPanahi/Llama-3-8B-Instruct-64k-GGUF\n- Model creator: MaziyarPanahi\n- Original model: MaziyarPanahi/Llama-3-8B-Instruct-64k", "## Description\nMaziyarPanahi/Llama-3-8B-Instruct-64k-GGUF contains GGUF format model files for MaziyarPanahi/Llama-3-8B-Instruct-64k.", "### About GGUF\n\nGGUF is a new format introduced by the URL team on August 21st 2023. It is a replacement for GGML, which is no longer supported by URL.\n\nHere is an incomplete list of clients and libraries that are known to support GGUF:\n\n* URL. The source project for GGUF. Offers a CLI and a server option.\n* llama-cpp-python, a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.\n* LM Studio, an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.\n* text-generation-webui, the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.\n* KoboldCpp, a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.\n* GPT4All, a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.\n* LoLLMS Web UI, a great web UI with many interesting and unique features, including a full model library for easy model selection.\n* URL, an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.\n* candle, a Rust ML framework with a focus on performance, including GPU support, and ease of use.\n* ctransformers, a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.", "## Special thanks\n\n Special thanks to Georgi Gerganov and the whole team working on URL for making all of this possible." ]

[ "sklearn", "skops", "tabular-classification", "license:mit", "region:us" ]

[]

[]

[ "### Hyperparameters\n\n\n\n Click to expand", "### Model Plot", "### Classification Report (overall)", "### Classification Report (by class)\n\n\n\nHow to Get Started with the Model\n=================================\n\n\nModel Card Authors\n==================\n\n\nBen Pedigo\nBethanny Danskin" ]

[ "TAGS\n#sklearn #skops #tabular-classification #license-mit #region-us \n", "### Hyperparameters\n\n\n\n Click to expand", "### Model Plot", "### Classification Report (overall)", "### Classification Report (by class)\n\n\n\nHow to Get Started with the Model\n=================================\n\n\nModel Card Authors\n==================\n\n\nBen Pedigo\nBethanny Danskin" ]

[ "region:us" ]

[]

[]

[ "## Exporting LoRas for use in other tools\nDocumentation on how to use Eden concepts in Automatic1111 or ComfyUI is here:\nURL\n\n\nase-1.0\"\n---", "## soft-gentle-abstract\n\nLoRA trained on URL by syntonikka on 8 images.\n\n* How to train Concepts (LoRAs) on Eden\n* How to export LoRAs from Eden\n\n!Samples" ]

[ "TAGS\n#region-us \n", "## Exporting LoRas for use in other tools\nDocumentation on how to use Eden concepts in Automatic1111 or ComfyUI is here:\nURL\n\n\nase-1.0\"\n---", "## soft-gentle-abstract\n\nLoRA trained on URL by syntonikka on 8 images.\n\n* How to train Concepts (LoRAs) on Eden\n* How to export LoRAs from Eden\n\n!Samples" ]

[ "transformers", "dataset:teknium/OpenHermes-2.5", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[]

[ "# Llama-3-openhermes-reft\n!image/png\n\nLlama-3-openhermes-reft is a fine-tuned version of meta-llama/Meta-Llama-3-8B on a 10K subset of teknium/OpenHermes-2.5\ndataset using Representation Fine-Tuning (ReFT). The model has been trained for 1 epoch on 1x A100 using PyReFT library.", "#### What is ReFT?\n\nReFT methods are drop-in replacements for weight-based PEFTs. Parameter-efficient finetuning (PEFT) methods propose a efficient and cheaper alternative to full fine-tuning by updating a small fraction of weights, while using less memory and finishing training faster.\nCurrent state-of-art PEFTs like LoRA and DoRA modify weights of model but not the representations. Representation Finetuning (ReFT) operates on a frozen base model and learn task-specific interventions on hidden representations.", "#### PyReFT\nPyReFT, a Python library made for training and sharing ReFTs.\n\nThis library is built on top of pyvene, a library for performing and training activation interventions on arbitrary PyTorch models.\n* Codebase: PyReFT\n* PyPI release: Link\n* Any pretrained LM available on HuggingFace is supported through pyreft for finetuning with ReFT methods, and finetuned models can be easily uploaded to HuggingFace.", "#### Inference" ]

[ "TAGS\n#transformers #dataset-teknium/OpenHermes-2.5 #license-apache-2.0 #endpoints_compatible #region-us \n", "# Llama-3-openhermes-reft\n!image/png\n\nLlama-3-openhermes-reft is a fine-tuned version of meta-llama/Meta-Llama-3-8B on a 10K subset of teknium/OpenHermes-2.5\ndataset using Representation Fine-Tuning (ReFT). The model has been trained for 1 epoch on 1x A100 using PyReFT library.", "#### What is ReFT?\n\nReFT methods are drop-in replacements for weight-based PEFTs. Parameter-efficient finetuning (PEFT) methods propose a efficient and cheaper alternative to full fine-tuning by updating a small fraction of weights, while using less memory and finishing training faster.\nCurrent state-of-art PEFTs like LoRA and DoRA modify weights of model but not the representations. Representation Finetuning (ReFT) operates on a frozen base model and learn task-specific interventions on hidden representations.", "#### PyReFT\nPyReFT, a Python library made for training and sharing ReFTs.\n\nThis library is built on top of pyvene, a library for performing and training activation interventions on arbitrary PyTorch models.\n* Codebase: PyReFT\n* PyPI release: Link\n* Any pretrained LM available on HuggingFace is supported through pyreft for finetuning with ReFT methods, and finetuned models can be easily uploaded to HuggingFace.", "#### Inference" ]

[ "transformers", "safetensors", "swin", "image-classification", "generated_from_trainer", "dataset:imagefolder", "base_model:microsoft/swin-base-patch4-window7-224-in22k", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 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* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 20", "### Training results", "### Framework versions\n\n\n* Transformers 4.35.0\n* Pytorch 2.1.0\n* Datasets 2.14.6\n* Tokenizers 0.14.1" ]

[ "TAGS\n#transformers #safetensors #swin #image-classification #generated_from_trainer #dataset-imagefolder #base_model-microsoft/swin-base-patch4-window7-224-in22k #license-apache-2.0 #model-index #autotrain_compatible #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 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* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 20", "### Training results", "### Framework versions\n\n\n* Transformers 4.35.0\n* Pytorch 2.1.0\n* Datasets 2.14.6\n* Tokenizers 0.14.1" ]

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

[]

[]

[]

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

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

[]

[]

[ "# SDXL LoRA DreamBooth - AdityaNath/Indian_Arch_LoRA\n\n<Gallery />", "## Model description\n\nThese are AdityaNath/Indian_Arch_LoRA LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.\n\nThe weights were trained using DreamBooth.\n\nLoRA for the text encoder was enabled: False.\n\nSpecial VAE used for training: madebyollin/sdxl-vae-fp16-fix.", "## Trigger words\n\nYou should use a photo of Indian_Arch Architecture to trigger the image generation.", "## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab.", "## 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 #tensorboard #text-to-image #diffusers-training #lora #template-sd-lora #stable-diffusion-xl #stable-diffusion-xl-diffusers #base_model-stabilityai/stable-diffusion-xl-base-1.0 #license-openrail++ #region-us \n", "# SDXL LoRA DreamBooth - AdityaNath/Indian_Arch_LoRA\n\n<Gallery />", "## Model description\n\nThese are AdityaNath/Indian_Arch_LoRA LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.\n\nThe weights were trained using DreamBooth.\n\nLoRA for the text encoder was enabled: False.\n\nSpecial VAE used for training: madebyollin/sdxl-vae-fp16-fix.", "## Trigger words\n\nYou should use a photo of Indian_Arch Architecture to trigger the image generation.", "## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab.", "## 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]" ]

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

[]

[ "en" ]

[ "### Use with transformers\n\n\nYou can run conversational inference using the Transformers pipeline abstraction, or by leveraging the Auto classes with the 'generate()' function. Let's see examples of both.", "#### Transformers pipeline", "#### Transformers AutoModelForCausalLM", "### Use with 'llama3'\n\n\nPlease, follow the instructions in the repository\n\n\nTo download Original checkpoints, see the example command below leveraging 'huggingface-cli':\n\n\nFor Hugging Face support, we recommend using transformers or TGI, but a similar command works.\n\n\nHardware and Software\n---------------------\n\n\nTraining Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.\n\n\nCarbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.\n\n\n\nCO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.\n\n\nTraining Data\n-------------\n\n\nOverview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.\n\n\nData Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.\n\n\nBenchmarks\n----------\n\n\nIn this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see here.", "### Base pretrained models", "### Instruction tuned models", "### Responsibility & Safety\n\n\nWe believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.\n\n\nFoundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.\n\n\nRather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.\n\n\nAs part of the Llama 3 release, we updated our Responsible Use Guide to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including Meta Llama Guard 2 and Code Shield safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a reference implementation to get you started.", "#### Llama 3-Instruct\n\n\nAs outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.\n\n\nSafety\n\n\nFor our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.\n\n\nRefusals\n\n\nIn addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.\n\n\nWe built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.", "#### Responsible release\n\n\nIn addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.\n\n\nMisuse\n\n\nIf you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at URL", "#### Critical risks\n\n\nCBRNE (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)\n\n\nWe have conducted a two fold assessment of the safety of the model in this area:\n\n\n* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.\n* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).", "### Cyber Security\n\n\nWe have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of equivalent coding capability.", "### Child Safety\n\n\nChild Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.", "### Community\n\n\nGenerative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our Github repository.\n\n\nFinally, we put in place a set of resources including an output reporting mechanism and bug bounty program to continuously improve the Llama technology with the help of the community.\n\n\nEthical Considerations and Limitations\n--------------------------------------\n\n\nThe core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.\n\n\nBut Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating Purple Llama solutions into your workflows and specifically Llama Guard which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.\n\n\nPlease see the Responsible Use Guide available at URL\n\n\ninstructions\n\n\n@article{llama3modelcard,\n\n\ntitle={Llama 3 Model Card},\n\n\nauthor={AI@Meta},\n\n\nyear={2024},\n\n\nurl = {URL\n\n\n}\n\n\nContributors\n------------\n\n\nAaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos" ]

[ "TAGS\n#gguf #facebook #meta #pytorch #llama #llama-3 #text-generation #en #license-other #region-us \n", "### Use with transformers\n\n\nYou can run conversational inference using the Transformers pipeline abstraction, or by leveraging the Auto classes with the 'generate()' function. Let's see examples of both.", "#### Transformers pipeline", "#### Transformers AutoModelForCausalLM", "### Use with 'llama3'\n\n\nPlease, follow the instructions in the repository\n\n\nTo download Original checkpoints, see the example command below leveraging 'huggingface-cli':\n\n\nFor Hugging Face support, we recommend using transformers or TGI, but a similar command works.\n\n\nHardware and Software\n---------------------\n\n\nTraining Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.\n\n\nCarbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.\n\n\n\nCO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.\n\n\nTraining Data\n-------------\n\n\nOverview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.\n\n\nData Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.\n\n\nBenchmarks\n----------\n\n\nIn this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see here.", "### Base pretrained models", "### Instruction tuned models", "### Responsibility & Safety\n\n\nWe believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.\n\n\nFoundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.\n\n\nRather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.\n\n\nAs part of the Llama 3 release, we updated our Responsible Use Guide to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including Meta Llama Guard 2 and Code Shield safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a reference implementation to get you started.", "#### Llama 3-Instruct\n\n\nAs outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.\n\n\nSafety\n\n\nFor our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.\n\n\nRefusals\n\n\nIn addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.\n\n\nWe built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.", "#### Responsible release\n\n\nIn addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.\n\n\nMisuse\n\n\nIf you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at URL", "#### Critical risks\n\n\nCBRNE (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)\n\n\nWe have conducted a two fold assessment of the safety of the model in this area:\n\n\n* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.\n* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).", "### Cyber Security\n\n\nWe have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of equivalent coding capability.", "### Child Safety\n\n\nChild Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.", "### Community\n\n\nGenerative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our Github repository.\n\n\nFinally, we put in place a set of resources including an output reporting mechanism and bug bounty program to continuously improve the Llama technology with the help of the community.\n\n\nEthical Considerations and Limitations\n--------------------------------------\n\n\nThe core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.\n\n\nBut Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating Purple Llama solutions into your workflows and specifically Llama Guard which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.\n\n\nPlease see the Responsible Use Guide available at URL\n\n\ninstructions\n\n\n@article{llama3modelcard,\n\n\ntitle={Llama 3 Model Card},\n\n\nauthor={AI@Meta},\n\n\nyear={2024},\n\n\nurl = {URL\n\n\n}\n\n\nContributors\n------------\n\n\nAaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos" ]

[ "gguf", "arxiv:2312.11805", "arxiv:2009.03300", "arxiv:1905.07830", "arxiv:1911.11641", "arxiv:1904.09728", "arxiv:1905.10044", "arxiv:1907.10641", "arxiv:1811.00937", "arxiv:1809.02789", "arxiv:1911.01547", "arxiv:1705.03551", "arxiv:2107.03374", "arxiv:2108.07732", "arxiv:2110.14168", "arxiv:2304.06364", "arxiv:2206.04615", "arxiv:1804.06876", "arxiv:2110.08193", "arxiv:2009.11462", "arxiv:2101.11718", "arxiv:1804.09301", "arxiv:2109.07958", "arxiv:2203.09509", "region:us" ]

[ "2312.11805", "2009.03300", "1905.07830", "1911.11641", "1904.09728", "1905.10044", "1907.10641", "1811.00937", "1809.02789", "1911.01547", "1705.03551", "2107.03374", "2108.07732", "2110.14168", "2304.06364", "2206.04615", "1804.06876", "2110.08193", "2009.11462", "2101.11718", "1804.09301", "2109.07958", "2203.09509" ]

[]

[ "### Description\n\n\nGemma is a family of lightweight, state-of-the-art open models from Google,\nbuilt from the same research and technology used to create the Gemini models.\nThey are text-to-text, decoder-only large language models, available in English,\nwith open weights, pre-trained variants, and instruction-tuned variants. Gemma\nmodels are well-suited for a variety of text generation tasks, including\nquestion answering, summarization, and reasoning. Their relatively small size\nmakes it possible to deploy them in environments with limited resources such as\na laptop, desktop or your own cloud infrastructure, democratizing access to\nstate of the art AI models and helping foster innovation for everyone.", "### Usage\n\n\nBelow we share some code snippets on how to get quickly started with running the model. First make sure to 'pip install -U transformers', then copy the snippet from the section that is relevant for your usecase.", "#### Fine-tuning the model\n\n\nYou can find fine-tuning scripts and notebook under the 'examples/' directory of 'google/gemma-7b' repository. To adapt it to this model, simply change the model-id to 'google/gemma-2b'.\nIn that repository, we provide:\n\n\n* A script to perform Supervised Fine-Tuning (SFT) on UltraChat dataset using QLoRA\n* A script to perform SFT using FSDP on TPU devices\n* A notebook that you can run on a free-tier Google Colab instance to perform SFT on English quotes dataset", "#### Running the model on a CPU", "#### Running the model on a single / multi GPU", "#### Running the model on a GPU using different precisions\n\n\n* *Using 'torch.float16'*\n* *Using 'torch.bfloat16'*", "#### Quantized Versions through 'bitsandbytes'\n\n\n* *Using 8-bit precision (int8)*\n* *Using 4-bit precision*", "#### Other optimizations\n\n\n* *Flash Attention 2*\n\n\nFirst make sure to install 'flash-attn' in your environment 'pip install flash-attn'", "### Inputs and outputs\n\n\n* Input: Text string, such as a question, a prompt, or a document to be\nsummarized.\n* Output: Generated English-language text in response to the input, such\nas an answer to a question, or a summary of a document.\n\n\nModel Data\n----------\n\n\nData used for model training and how the data was processed.", "### Training Dataset\n\n\nThese models were trained on a dataset of text data that includes a wide variety\nof sources, totaling 6 trillion tokens. Here are the key components:\n\n\n* Web Documents: A diverse collection of web text ensures the model is exposed\nto a broad range of linguistic styles, topics, and vocabulary. Primarily\nEnglish-language content.\n* Code: Exposing the model to code helps it to learn the syntax and patterns of\nprogramming languages, which improves its ability to generate code or\nunderstand code-related questions.\n* Mathematics: Training on mathematical text helps the model learn logical\nreasoning, symbolic representation, and to address mathematical queries.\n\n\nThe combination of these diverse data sources is crucial for training a powerful\nlanguage model that can handle a wide variety of different tasks and text\nformats.", "### Data Preprocessing\n\n\nHere are the key data cleaning and filtering methods applied to the training\ndata:\n\n\n* CSAM Filtering: Rigorous CSAM (Child Sexual Abuse Material) filtering was\napplied at multiple stages in the data preparation process to ensure the\nexclusion of harmful and illegal content\n* Sensitive Data Filtering: As part of making Gemma pre-trained models safe and\nreliable, automated techniques were used to filter out certain personal\ninformation and other sensitive data from training sets.\n* Additional methods: Filtering based on content quality and safely in line with\nour policies.\n\n\nImplementation Information\n--------------------------\n\n\nDetails about the model internals.", "### Hardware\n\n\nGemma was trained using the latest generation of\nTensor Processing Unit (TPU) hardware (TPUv5e).\n\n\nTraining large language models requires significant computational power. TPUs,\ndesigned specifically for matrix operations common in machine learning, offer\nseveral advantages in this domain:\n\n\n* Performance: TPUs are specifically designed to handle the massive computations\ninvolved in training LLMs. They can speed up training considerably compared to\nCPUs.\n* Memory: TPUs often come with large amounts of high-bandwidth memory, allowing\nfor the handling of large models and batch sizes during training. This can\nlead to better model quality.\n* Scalability: TPU Pods (large clusters of TPUs) provide a scalable solution for\nhandling the growing complexity of large foundation models. You can distribute\ntraining across multiple TPU devices for faster and more efficient processing.\n* Cost-effectiveness: In many scenarios, TPUs can provide a more cost-effective\nsolution for training large models compared to CPU-based infrastructure,\nespecially when considering the time and resources saved due to faster\ntraining.\n* These advantages are aligned with\nGoogle's commitments to operate sustainably.", "### Software\n\n\nTraining was done using JAX and ML Pathways.\n\n\nJAX allows researchers to take advantage of the latest generation of hardware,\nincluding TPUs, for faster and more efficient training of large models.\n\n\nML Pathways is Google's latest effort to build artificially intelligent systems\ncapable of generalizing across multiple tasks. This is specially suitable for\nfoundation models, including large language models like\nthese ones.\n\n\nTogether, JAX and ML Pathways are used as described in the\npaper about the Gemini family of models; \"the 'single\ncontroller' programming model of Jax and Pathways allows a single Python\nprocess to orchestrate the entire training run, dramatically simplifying the\ndevelopment workflow.\"\n\n\nEvaluation\n----------\n\n\nModel evaluation metrics and results.", "### Benchmark Results\n\n\nThese models were evaluated against a large collection of different datasets and\nmetrics to cover different aspects of text generation:\n\n\n\nEthics and Safety\n-----------------\n\n\nEthics and safety evaluation approach and results.", "### Evaluation Approach\n\n\nOur evaluation methods include structured evaluations and internal red-teaming\ntesting of relevant content policies. Red-teaming was conducted by a number of\ndifferent teams, each with different goals and human evaluation metrics. These\nmodels were evaluated against a number of different categories relevant to\nethics and safety, including:\n\n\n* Text-to-Text Content Safety: Human evaluation on prompts covering safety\npolicies including child sexual abuse and exploitation, harassment, violence\nand gore, and hate speech.\n* Text-to-Text Representational Harms: Benchmark against relevant academic\ndatasets such as WinoBias and BBQ Dataset.\n* Memorization: Automated evaluation of memorization of training data, including\nthe risk of personally identifiable information exposure.\n* Large-scale harm: Tests for \"dangerous capabilities,\" such as chemical,\nbiological, radiological, and nuclear (CBRN) risks.", "### Evaluation Results\n\n\nThe results of ethics and safety evaluations are within acceptable thresholds\nfor meeting internal policies for categories such as child\nsafety, content safety, representational harms, memorization, large-scale harms.\nOn top of robust internal evaluations, the results of well known safety\nbenchmarks like BBQ, BOLD, Winogender, Winobias, RealToxicity, and TruthfulQA\nare shown here.\n\n\n\nUsage and Limitations\n---------------------\n\n\nThese models have certain limitations that users should be aware of.", "### Intended Usage\n\n\nOpen Large Language Models (LLMs) have a wide range of applications across\nvarious industries and domains. The following list of potential uses is not\ncomprehensive. The purpose of this list is to provide contextual information\nabout the possible use-cases that the model creators considered as part of model\ntraining and development.\n\n\n* Content Creation and Communication\n\t+ Text Generation: These models can be used to generate creative text formats\n\tsuch as poems, scripts, code, marketing copy, and email drafts.\n\t+ Chatbots and Conversational AI: Power conversational interfaces for customer\n\tservice, virtual assistants, or interactive applications.\n\t+ Text Summarization: Generate concise summaries of a text corpus, research\n\tpapers, or reports.\n* Research and Education\n\t+ Natural Language Processing (NLP) Research: These models can serve as a\n\tfoundation for researchers to experiment with NLP techniques, develop\n\talgorithms, and contribute to the advancement of the field.\n\t+ Language Learning Tools: Support interactive language learning experiences,\n\taiding in grammar correction or providing writing practice.\n\t+ Knowledge Exploration: Assist researchers in exploring large bodies of text\n\tby generating summaries or answering questions about specific topics.", "### Limitations\n\n\n* Training Data\n\t+ The quality and diversity of the training data significantly influence the\n\tmodel's capabilities. Biases or gaps in the training data can lead to\n\tlimitations in the model's responses.\n\t+ The scope of the training dataset determines the subject areas the model can\n\thandle effectively.\n* Context and Task Complexity\n\t+ LLMs are better at tasks that can be framed with clear prompts and\n\tinstructions. Open-ended or highly complex tasks might be challenging.\n\t+ A model's performance can be influenced by the amount of context provided\n\t(longer context generally leads to better outputs, up to a certain point).\n* Language Ambiguity and Nuance\n\t+ Natural language is inherently complex. LLMs might struggle to grasp subtle\n\tnuances, sarcasm, or figurative language.\n* Factual Accuracy\n\t+ LLMs generate responses based on information they learned from their\n\ttraining datasets, but they are not knowledge bases. They may generate\n\tincorrect or outdated factual statements.\n* Common Sense\n\t+ LLMs rely on statistical patterns in language. They might lack the ability\n\tto apply common sense reasoning in certain situations.", "### Ethical Considerations and Risks\n\n\nThe development of large language models (LLMs) raises several ethical concerns.\nIn creating an open model, we have carefully considered the following:\n\n\n* Bias and Fairness\n\t+ LLMs trained on large-scale, real-world text data can reflect socio-cultural\n\tbiases embedded in the training material. These models underwent careful\n\tscrutiny, input data pre-processing described and posterior evaluations\n\treported in this card.\n* Misinformation and Misuse\n\t+ LLMs can be misused to generate text that is false, misleading, or harmful.\n\t+ Guidelines are provided for responsible use with the model, see the\n\tResponsible Generative AI Toolkit.\n* Transparency and Accountability:\n\t+ This model card summarizes details on the models' architecture,\n\tcapabilities, limitations, and evaluation processes.\n\t+ A responsibly developed open model offers the opportunity to share\n\tinnovation by making LLM technology accessible to developers and researchers\n\tacross the AI ecosystem.\n\n\nRisks identified and mitigations:\n\n\n* Perpetuation of biases: It's encouraged to perform continuous monitoring\n(using evaluation metrics, human review) and the exploration of de-biasing\ntechniques during model training, fine-tuning, and other use cases.\n* Generation of harmful content: Mechanisms and guidelines for content safety\nare essential. Developers are encouraged to exercise caution and implement\nappropriate content safety safeguards based on their specific product policies\nand application use cases.\n* Misuse for malicious purposes: Technical limitations and developer and\nend-user education can help mitigate against malicious applications of LLMs.\nEducational resources and reporting mechanisms for users to flag misuse are\nprovided. Prohibited uses of Gemma models are outlined in the\nGemma Prohibited Use Policy.\n* Privacy violations: Models were trained on data filtered for removal of PII\n(Personally Identifiable Information). Developers are encouraged to adhere to\nprivacy regulations with privacy-preserving techniques.", "### Benefits\n\n\nAt the time of release, this family of models provides high-performance open\nlarge language model implementations designed from the ground up for Responsible\nAI development compared to similarly sized models.\n\n\nUsing the benchmark evaluation metrics described in this document, these models\nhave shown to provide superior performance to other, comparably-sized open model\nalternatives." ]

[ "TAGS\n#gguf #arxiv-2312.11805 #arxiv-2009.03300 #arxiv-1905.07830 #arxiv-1911.11641 #arxiv-1904.09728 #arxiv-1905.10044 #arxiv-1907.10641 #arxiv-1811.00937 #arxiv-1809.02789 #arxiv-1911.01547 #arxiv-1705.03551 #arxiv-2107.03374 #arxiv-2108.07732 #arxiv-2110.14168 #arxiv-2304.06364 #arxiv-2206.04615 #arxiv-1804.06876 #arxiv-2110.08193 #arxiv-2009.11462 #arxiv-2101.11718 #arxiv-1804.09301 #arxiv-2109.07958 #arxiv-2203.09509 #region-us \n", "### Description\n\n\nGemma is a family of lightweight, state-of-the-art open models from Google,\nbuilt from the same research and technology used to create the Gemini models.\nThey are text-to-text, decoder-only large language models, available in English,\nwith open weights, pre-trained variants, and instruction-tuned variants. Gemma\nmodels are well-suited for a variety of text generation tasks, including\nquestion answering, summarization, and reasoning. Their relatively small size\nmakes it possible to deploy them in environments with limited resources such as\na laptop, desktop or your own cloud infrastructure, democratizing access to\nstate of the art AI models and helping foster innovation for everyone.", "### Usage\n\n\nBelow we share some code snippets on how to get quickly started with running the model. First make sure to 'pip install -U transformers', then copy the snippet from the section that is relevant for your usecase.", "#### Fine-tuning the model\n\n\nYou can find fine-tuning scripts and notebook under the 'examples/' directory of 'google/gemma-7b' repository. To adapt it to this model, simply change the model-id to 'google/gemma-2b'.\nIn that repository, we provide:\n\n\n* A script to perform Supervised Fine-Tuning (SFT) on UltraChat dataset using QLoRA\n* A script to perform SFT using FSDP on TPU devices\n* A notebook that you can run on a free-tier Google Colab instance to perform SFT on English quotes dataset", "#### Running the model on a CPU", "#### Running the model on a single / multi GPU", "#### Running the model on a GPU using different precisions\n\n\n* *Using 'torch.float16'*\n* *Using 'torch.bfloat16'*", "#### Quantized Versions through 'bitsandbytes'\n\n\n* *Using 8-bit precision (int8)*\n* *Using 4-bit precision*", "#### Other optimizations\n\n\n* *Flash Attention 2*\n\n\nFirst make sure to install 'flash-attn' in your environment 'pip install flash-attn'", "### Inputs and outputs\n\n\n* Input: Text string, such as a question, a prompt, or a document to be\nsummarized.\n* Output: Generated English-language text in response to the input, such\nas an answer to a question, or a summary of a document.\n\n\nModel Data\n----------\n\n\nData used for model training and how the data was processed.", "### Training Dataset\n\n\nThese models were trained on a dataset of text data that includes a wide variety\nof sources, totaling 6 trillion tokens. Here are the key components:\n\n\n* Web Documents: A diverse collection of web text ensures the model is exposed\nto a broad range of linguistic styles, topics, and vocabulary. Primarily\nEnglish-language content.\n* Code: Exposing the model to code helps it to learn the syntax and patterns of\nprogramming languages, which improves its ability to generate code or\nunderstand code-related questions.\n* Mathematics: Training on mathematical text helps the model learn logical\nreasoning, symbolic representation, and to address mathematical queries.\n\n\nThe combination of these diverse data sources is crucial for training a powerful\nlanguage model that can handle a wide variety of different tasks and text\nformats.", "### Data Preprocessing\n\n\nHere are the key data cleaning and filtering methods applied to the training\ndata:\n\n\n* CSAM Filtering: Rigorous CSAM (Child Sexual Abuse Material) filtering was\napplied at multiple stages in the data preparation process to ensure the\nexclusion of harmful and illegal content\n* Sensitive Data Filtering: As part of making Gemma pre-trained models safe and\nreliable, automated techniques were used to filter out certain personal\ninformation and other sensitive data from training sets.\n* Additional methods: Filtering based on content quality and safely in line with\nour policies.\n\n\nImplementation Information\n--------------------------\n\n\nDetails about the model internals.", "### Hardware\n\n\nGemma was trained using the latest generation of\nTensor Processing Unit (TPU) hardware (TPUv5e).\n\n\nTraining large language models requires significant computational power. TPUs,\ndesigned specifically for matrix operations common in machine learning, offer\nseveral advantages in this domain:\n\n\n* Performance: TPUs are specifically designed to handle the massive computations\ninvolved in training LLMs. They can speed up training considerably compared to\nCPUs.\n* Memory: TPUs often come with large amounts of high-bandwidth memory, allowing\nfor the handling of large models and batch sizes during training. This can\nlead to better model quality.\n* Scalability: TPU Pods (large clusters of TPUs) provide a scalable solution for\nhandling the growing complexity of large foundation models. You can distribute\ntraining across multiple TPU devices for faster and more efficient processing.\n* Cost-effectiveness: In many scenarios, TPUs can provide a more cost-effective\nsolution for training large models compared to CPU-based infrastructure,\nespecially when considering the time and resources saved due to faster\ntraining.\n* These advantages are aligned with\nGoogle's commitments to operate sustainably.", "### Software\n\n\nTraining was done using JAX and ML Pathways.\n\n\nJAX allows researchers to take advantage of the latest generation of hardware,\nincluding TPUs, for faster and more efficient training of large models.\n\n\nML Pathways is Google's latest effort to build artificially intelligent systems\ncapable of generalizing across multiple tasks. This is specially suitable for\nfoundation models, including large language models like\nthese ones.\n\n\nTogether, JAX and ML Pathways are used as described in the\npaper about the Gemini family of models; \"the 'single\ncontroller' programming model of Jax and Pathways allows a single Python\nprocess to orchestrate the entire training run, dramatically simplifying the\ndevelopment workflow.\"\n\n\nEvaluation\n----------\n\n\nModel evaluation metrics and results.", "### Benchmark Results\n\n\nThese models were evaluated against a large collection of different datasets and\nmetrics to cover different aspects of text generation:\n\n\n\nEthics and Safety\n-----------------\n\n\nEthics and safety evaluation approach and results.", "### Evaluation Approach\n\n\nOur evaluation methods include structured evaluations and internal red-teaming\ntesting of relevant content policies. Red-teaming was conducted by a number of\ndifferent teams, each with different goals and human evaluation metrics. These\nmodels were evaluated against a number of different categories relevant to\nethics and safety, including:\n\n\n* Text-to-Text Content Safety: Human evaluation on prompts covering safety\npolicies including child sexual abuse and exploitation, harassment, violence\nand gore, and hate speech.\n* Text-to-Text Representational Harms: Benchmark against relevant academic\ndatasets such as WinoBias and BBQ Dataset.\n* Memorization: Automated evaluation of memorization of training data, including\nthe risk of personally identifiable information exposure.\n* Large-scale harm: Tests for \"dangerous capabilities,\" such as chemical,\nbiological, radiological, and nuclear (CBRN) risks.", "### Evaluation Results\n\n\nThe results of ethics and safety evaluations are within acceptable thresholds\nfor meeting internal policies for categories such as child\nsafety, content safety, representational harms, memorization, large-scale harms.\nOn top of robust internal evaluations, the results of well known safety\nbenchmarks like BBQ, BOLD, Winogender, Winobias, RealToxicity, and TruthfulQA\nare shown here.\n\n\n\nUsage and Limitations\n---------------------\n\n\nThese models have certain limitations that users should be aware of.", "### Intended Usage\n\n\nOpen Large Language Models (LLMs) have a wide range of applications across\nvarious industries and domains. The following list of potential uses is not\ncomprehensive. The purpose of this list is to provide contextual information\nabout the possible use-cases that the model creators considered as part of model\ntraining and development.\n\n\n* Content Creation and Communication\n\t+ Text Generation: These models can be used to generate creative text formats\n\tsuch as poems, scripts, code, marketing copy, and email drafts.\n\t+ Chatbots and Conversational AI: Power conversational interfaces for customer\n\tservice, virtual assistants, or interactive applications.\n\t+ Text Summarization: Generate concise summaries of a text corpus, research\n\tpapers, or reports.\n* Research and Education\n\t+ Natural Language Processing (NLP) Research: These models can serve as a\n\tfoundation for researchers to experiment with NLP techniques, develop\n\talgorithms, and contribute to the advancement of the field.\n\t+ Language Learning Tools: Support interactive language learning experiences,\n\taiding in grammar correction or providing writing practice.\n\t+ Knowledge Exploration: Assist researchers in exploring large bodies of text\n\tby generating summaries or answering questions about specific topics.", "### Limitations\n\n\n* Training Data\n\t+ The quality and diversity of the training data significantly influence the\n\tmodel's capabilities. Biases or gaps in the training data can lead to\n\tlimitations in the model's responses.\n\t+ The scope of the training dataset determines the subject areas the model can\n\thandle effectively.\n* Context and Task Complexity\n\t+ LLMs are better at tasks that can be framed with clear prompts and\n\tinstructions. Open-ended or highly complex tasks might be challenging.\n\t+ A model's performance can be influenced by the amount of context provided\n\t(longer context generally leads to better outputs, up to a certain point).\n* Language Ambiguity and Nuance\n\t+ Natural language is inherently complex. LLMs might struggle to grasp subtle\n\tnuances, sarcasm, or figurative language.\n* Factual Accuracy\n\t+ LLMs generate responses based on information they learned from their\n\ttraining datasets, but they are not knowledge bases. They may generate\n\tincorrect or outdated factual statements.\n* Common Sense\n\t+ LLMs rely on statistical patterns in language. They might lack the ability\n\tto apply common sense reasoning in certain situations.", "### Ethical Considerations and Risks\n\n\nThe development of large language models (LLMs) raises several ethical concerns.\nIn creating an open model, we have carefully considered the following:\n\n\n* Bias and Fairness\n\t+ LLMs trained on large-scale, real-world text data can reflect socio-cultural\n\tbiases embedded in the training material. These models underwent careful\n\tscrutiny, input data pre-processing described and posterior evaluations\n\treported in this card.\n* Misinformation and Misuse\n\t+ LLMs can be misused to generate text that is false, misleading, or harmful.\n\t+ Guidelines are provided for responsible use with the model, see the\n\tResponsible Generative AI Toolkit.\n* Transparency and Accountability:\n\t+ This model card summarizes details on the models' architecture,\n\tcapabilities, limitations, and evaluation processes.\n\t+ A responsibly developed open model offers the opportunity to share\n\tinnovation by making LLM technology accessible to developers and researchers\n\tacross the AI ecosystem.\n\n\nRisks identified and mitigations:\n\n\n* Perpetuation of biases: It's encouraged to perform continuous monitoring\n(using evaluation metrics, human review) and the exploration of de-biasing\ntechniques during model training, fine-tuning, and other use cases.\n* Generation of harmful content: Mechanisms and guidelines for content safety\nare essential. Developers are encouraged to exercise caution and implement\nappropriate content safety safeguards based on their specific product policies\nand application use cases.\n* Misuse for malicious purposes: Technical limitations and developer and\nend-user education can help mitigate against malicious applications of LLMs.\nEducational resources and reporting mechanisms for users to flag misuse are\nprovided. Prohibited uses of Gemma models are outlined in the\nGemma Prohibited Use Policy.\n* Privacy violations: Models were trained on data filtered for removal of PII\n(Personally Identifiable Information). Developers are encouraged to adhere to\nprivacy regulations with privacy-preserving techniques.", "### Benefits\n\n\nAt the time of release, this family of models provides high-performance open\nlarge language model implementations designed from the ground up for Responsible\nAI development compared to similarly sized models.\n\n\nUsing the benchmark evaluation metrics described in this document, these models\nhave shown to provide superior performance to other, comparably-sized open model\nalternatives." ]

[ "gguf", "arxiv:2304.12244", "region:us" ]

[ "2304.12244" ]

[]

[ "### Prompting format\n\n\n* Repository:\n* Paper [optional]:\n* Demo [optional]:", "### Uses\n\n\nThe intended use-case is Role-Playing with Instruct prompts. Guiding the bot towards a certain conversation style should be easier this way. Subject to experimentation.", "### Out-of-Scope Use\n\n\n* Assistant Bot [subject to providing incorrect instructions]\n* Complex multi-character chat", "### Risks\n\n\nThe model can generate potentially harmful or NSFW outputs. Please use with caution.\n\n\nWizardLM:" ]

[ "TAGS\n#gguf #arxiv-2304.12244 #region-us \n", "### Prompting format\n\n\n* Repository:\n* Paper [optional]:\n* Demo [optional]:", "### Uses\n\n\nThe intended use-case is Role-Playing with Instruct prompts. Guiding the bot towards a certain conversation style should be easier this way. Subject to experimentation.", "### Out-of-Scope Use\n\n\n* Assistant Bot [subject to providing incorrect instructions]\n* Complex multi-character chat", "### Risks\n\n\nThe model can generate potentially harmful or NSFW outputs. Please use with caution.\n\n\nWizardLM:" ]

[ "transformers", "safetensors", "mistral", "text-generation", "merge", "mergekit", "lazymergekit", "Yuma42/KangalKhan-Alpha-Rubyroid-7B-Fixed", "Yuma42/KangalKhan-RawEmerald-7B", "conversational", "en", "base_model:Yuma42/KangalKhan-Alpha-Rubyroid-7B-Fixed", "base_model:Yuma42/KangalKhan-RawEmerald-7B", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[ "en" ]

[ "# KangalKhan-Alpha-RawRubyroid-7B-Fixed\n\nKangalKhan-Alpha-RawRubyroid-7B-Fixed is a merge of the following models using LazyMergekit:\n* Yuma42/KangalKhan-Alpha-Rubyroid-7B-Fixed\n* Yuma42/KangalKhan-RawEmerald-7B", "## Configuration", "## Usage" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #merge #mergekit #lazymergekit #Yuma42/KangalKhan-Alpha-Rubyroid-7B-Fixed #Yuma42/KangalKhan-RawEmerald-7B #conversational #en #base_model-Yuma42/KangalKhan-Alpha-Rubyroid-7B-Fixed #base_model-Yuma42/KangalKhan-RawEmerald-7B #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# KangalKhan-Alpha-RawRubyroid-7B-Fixed\n\nKangalKhan-Alpha-RawRubyroid-7B-Fixed is a merge of the following models using LazyMergekit:\n* Yuma42/KangalKhan-Alpha-Rubyroid-7B-Fixed\n* Yuma42/KangalKhan-RawEmerald-7B", "## Configuration", "## Usage" ]

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

[]

[]

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

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

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

[]

[ "en" ]

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

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

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

[]

[ "en" ]

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

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

[ "gguf", "dataset:teknium/OpenHermes-2.5", "arxiv:1910.09700", "license:apache-2.0", "region:us" ]

[ "1910.09700" ]

[]

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

[ "TAGS\n#gguf #dataset-teknium/OpenHermes-2.5 #arxiv-1910.09700 #license-apache-2.0 #region-us \n", "# Model Card for Model ID\n\n\n\nThis modelcard aims to be a base template for new models. It has been generated using this raw template.", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "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", "bert", "text-classification", "generated_from_trainer", "base_model:bert-base-cased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 5", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.3.0+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #bert #text-classification #generated_from_trainer #base_model-bert-base-cased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 5", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.3.0+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

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

[]

[]

[ "# mistral_train_seq_cls_run3\n\nThis model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0002\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 16\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: constant\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 3", "### Training results", "### Framework versions\n\n- PEFT 0.7.2.dev0\n- Transformers 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.16.1\n- Tokenizers 0.15.1" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mistralai/Mistral-7B-v0.1 #license-apache-2.0 #region-us \n", "# mistral_train_seq_cls_run3\n\nThis model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0002\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 16\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: constant\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 3", "### Training results", "### Framework versions\n\n- PEFT 0.7.2.dev0\n- Transformers 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.16.1\n- Tokenizers 0.15.1" ]

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

[]

[ "en" ]

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

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