Datasets:

---

ftopal

/

huggingface-models

like 0

[ "transformers", "safetensors", "llama", "text-generation", "generated_from_trainer", "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: 0.00025\n* train\\_batch\\_size: 32\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\n* lr\\_scheduler\\_warmup\\_steps: 50\n* num\\_epochs: 120\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.39.1\n* Pytorch 2.1.2+cu121\n* Datasets 2.16.1\n* Tokenizers 0.15.0" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #generated_from_trainer #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: 0.00025\n* train\\_batch\\_size: 32\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\n* lr\\_scheduler\\_warmup\\_steps: 50\n* num\\_epochs: 120\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.39.1\n* Pytorch 2.1.2+cu121\n* Datasets 2.16.1\n* Tokenizers 0.15.0" ]

[ "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: TheNile\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: TheNile\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", "pytorch", "xlm-roberta", "feature-extraction", "custom_code", "region:us" ]

[]

[]

[ "# Paper\n\nCometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Task (Rei et al., WMT 2022)", "# License:\n\ncc-by-nc-sa-4.0", "# Usage (unbabel-comet)\n\nUsing this model requires unbabel-comet to be installed:\n\n\n\nMake sure you acknowledge its License and Log in into Hugging face hub before using:\n\n\n\nThen you can use it through comet CLI:\n\n\n\nOr using Python:", "# Intended uses\n\nOur model is intented to be used for reference-free MT evaluation. \n\nGiven a source text and its translation, outputs a single score between 0 and 1 where 1 represents a perfect translation.", "# Languages Covered:\n\nThis model builds on top of InfoXLM which cover the following languages:\n\nAfrikaans, Albanian, Amharic, Arabic, Armenian, Assamese, Azerbaijani, Basque, Belarusian, Bengali, Bengali Romanized, Bosnian, Breton, Bulgarian, Burmese, Burmese, Catalan, Chinese (Simplified), Chinese (Traditional), Croatian, Czech, Danish, Dutch, English, Esperanto, Estonian, Filipino, Finnish, French, Galician, Georgian, German, Greek, Gujarati, Hausa, Hebrew, Hindi, Hindi Romanized, Hungarian, Icelandic, Indonesian, Irish, Italian, Japanese, Javanese, Kannada, Kazakh, Khmer, Korean, Kurdish (Kurmanji), Kyrgyz, Lao, Latin, Latvian, Lithuanian, Macedonian, Malagasy, Malay, Malayalam, Marathi, Mongolian, Nepali, Norwegian, Oriya, Oromo, Pashto, Persian, Polish, Portuguese, Punjabi, Romanian, Russian, Sanskri, Scottish, Gaelic, Serbian, Sindhi, Sinhala, Slovak, Slovenian, Somali, Spanish, Sundanese, Swahili, Swedish, Tamil, Tamil Romanized, Telugu, Telugu Romanized, Thai, Turkish, Ukrainian, Urdu, Urdu Romanized, Uyghur, Uzbek, Vietnamese, Welsh, Western, Frisian, Xhosa, Yiddish.\n\nThus, results for language pairs containing uncovered languages are unreliable!" ]

[ "TAGS\n#transformers #pytorch #xlm-roberta #feature-extraction #custom_code #region-us \n", "# Paper\n\nCometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Task (Rei et al., WMT 2022)", "# License:\n\ncc-by-nc-sa-4.0", "# Usage (unbabel-comet)\n\nUsing this model requires unbabel-comet to be installed:\n\n\n\nMake sure you acknowledge its License and Log in into Hugging face hub before using:\n\n\n\nThen you can use it through comet CLI:\n\n\n\nOr using Python:", "# Intended uses\n\nOur model is intented to be used for reference-free MT evaluation. \n\nGiven a source text and its translation, outputs a single score between 0 and 1 where 1 represents a perfect translation.", "# Languages Covered:\n\nThis model builds on top of InfoXLM which cover the following languages:\n\nAfrikaans, Albanian, Amharic, Arabic, Armenian, Assamese, Azerbaijani, Basque, Belarusian, Bengali, Bengali Romanized, Bosnian, Breton, Bulgarian, Burmese, Burmese, Catalan, Chinese (Simplified), Chinese (Traditional), Croatian, Czech, Danish, Dutch, English, Esperanto, Estonian, Filipino, Finnish, French, Galician, Georgian, German, Greek, Gujarati, Hausa, Hebrew, Hindi, Hindi Romanized, Hungarian, Icelandic, Indonesian, Irish, Italian, Japanese, Javanese, Kannada, Kazakh, Khmer, Korean, Kurdish (Kurmanji), Kyrgyz, Lao, Latin, Latvian, Lithuanian, Macedonian, Malagasy, Malay, Malayalam, Marathi, Mongolian, Nepali, Norwegian, Oriya, Oromo, Pashto, Persian, Polish, Portuguese, Punjabi, Romanian, Russian, Sanskri, Scottish, Gaelic, Serbian, Sindhi, Sinhala, Slovak, Slovenian, Somali, Spanish, Sundanese, Swahili, Swedish, Tamil, Tamil Romanized, Telugu, Telugu Romanized, Thai, Turkish, Ukrainian, Urdu, Urdu Romanized, Uyghur, Uzbek, Vietnamese, Welsh, Western, Frisian, Xhosa, Yiddish.\n\nThus, results for language pairs containing uncovered languages are unreliable!" ]

[ "bertopic", "text-classification", "region:us" ]

[]

[]

[]

[ "TAGS\n#bertopic #text-classification #region-us \n" ]

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

[ "1910.09700" ]

[]

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

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

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

[ "1910.09700" ]

[]

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

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

[ "peft", "safetensors", "mistral", "alignment-handbook", "generated_from_trainer", "trl", "dpo", "dataset:updated", "dataset:original", "base_model:mistralai/Mistral-7B-v0.1", "license:apache-2.0", "4-bit", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-06\n* train\\_batch\\_size: 2\n* eval\\_batch\\_size: 2\n* seed: 42\n* distributed\\_type: multi-GPU\n* num\\_devices: 4\n* gradient\\_accumulation\\_steps: 32\n* total\\_train\\_batch\\_size: 256\n* total\\_eval\\_batch\\_size: 8\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\n* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 1", "### Training results", "### Framework versions\n\n\n* PEFT 0.7.1\n* Transformers 4.36.2\n* Pytorch 2.2.2+cu121\n* Datasets 2.14.6\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #mistral #alignment-handbook #generated_from_trainer #trl #dpo #dataset-updated #dataset-original #base_model-mistralai/Mistral-7B-v0.1 #license-apache-2.0 #4-bit #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-06\n* train\\_batch\\_size: 2\n* eval\\_batch\\_size: 2\n* seed: 42\n* distributed\\_type: multi-GPU\n* num\\_devices: 4\n* gradient\\_accumulation\\_steps: 32\n* total\\_train\\_batch\\_size: 256\n* total\\_eval\\_batch\\_size: 8\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\n* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 1", "### Training results", "### Framework versions\n\n\n* PEFT 0.7.1\n* Transformers 4.36.2\n* Pytorch 2.2.2+cu121\n* Datasets 2.14.6\n* Tokenizers 0.15.2" ]

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

[]

[ "en" ]

[ "# PPO AI Agents Playing Pyramids\n \n <img src=\"URL alt=\"Pyramids\"/>\n \nDISCLAIMER: In this notebook it has two environments you can train agents to play in the snowball and pyramid one. In this model card I am only covering the Pyramid game model. But a lot of these trouble shooting guides will be applicable to the snowball environment as well.\n\n\n This is a trained model of a ppo agent playing UNITY game Pyramids Using Q-learning and reinforcement learning to train the agent to navigate around a simple maze environment where they need to activate a button that the pyramid then they need to locate the pyramid and knock the pyramid stacked blocks over so the green block on top falls to the ground.\n I used the Unity ML-Agents Library.\n Throughout this notebook you will learn about how to train AI agent using Q learning in a Unity Game 3D game environment. Utilizing the different curiosity and exploitation values as well as manipulating the various hyperperameters to get the best training results.\n It is an easy notebook to follow through with excellent instructions so if you want to learn more about the process used to train these AI agents in 3D environments I highly recommend this project. It is best if you have some experiences learning about or working with deep learning machine learning, because it may be difficult to understand this reinforcement learning process. If you dont have experiences or interested in learning more you can access resources to more introductory notebooks in this link.\n URL \n\n So if you are interested in continuing in training AI agents to playing the Unity Pyramids thats great! Because below is a few different resources I have gathered to troubleshoot through problems I have faced, basic info about how the model works and how you can improve the model. I wish I had known about before completing this notebook. Which will hopefully make it easier for you on your journey.\n Also here is the link of my working model\nURL \nAlso heres a video demoing what the aim of the AI agents in this pyramid game is URL\n\n \n ## Learning components of this model:\n\n <img src=\"URL\n\n 1. Agent component: training agents by optimizing their policy(policy based method, unlike value based methods they optimize the policy itself instead of values) telling the model what action to take in each step in the model called a brain.\n 2. For this model we will be using a proximal policy optimizer (PPO) as seen at the title of the model card. PPO is ideal for training AI agents in Unity games because it is sample-efficient, stable during training, compatible with neural networks, handles both continuous and discrete action spaces, and robust in handling complex game dynamics and mechanics.\n\n Curiosity in training ML agents:\nIn this reinforcement learning project you will need to understand how curiosity plays a part in the training.In short, Traditionally a reward system is used to train ML agents but for more complicated games and obscure objective it is hard to manually place rewards for the agent. \nCuriosity is rewarding the model for taking new trajectories for example exploring new rooms\n\nHere is a youtube videos that helped me understand the concept: \nURL (this one talks specifically about the game environment)\nURL (And this one illustrates more generally about reinforcement learning but also covers curiosity, great and easy to understand for beginners, also if you are intersted in learning more about how ai and machine learning the rest of this crash course series is great as well)\n\n \n ## Improving model training through hyperparameters adjusting\n So once you have a working model and want to improve the training outcomes.\n These hyperparameter tunings can be adjusted within the Pyramid RND file component on the side and below is a detailed list on what changing each individual parameter will impact the training. Just be minful after making changes you need to run the code responsible for copying the file into the envs executable linux, as well as unzipping along with retraining to implement these new parameters into your model. \n \n 1. Trainer type: the type of trainer being used here we use Proximal policy optimization\n 2. Summary_freq: How often the training summaries and statisitcs are recorded(rewards, losses, lengths, time etc )\n 3. Keep_checkpoints: number of recent checkpoints to keep checkpoints are snapshots of training models for resumign training or evaluation\n 4. Checkpoint interval: how often(many steps) save checkpoints\n 5. Max_steps: Maximum number of steps or interactions \n 6. Time_horizon: The number of steps the agent considers when making decisions\n 7. Threaded: Enables multi-threading during training(may allow for faster processing, parts of code run simultaneously)\n 8. Hyperparameters:\n 9. Learning rate: How quickly the agents adjust their behavior based on feedback\n 10. Learning rate_schedule: the rule that used to adjust or modify the learning rate during the training process\n 11. Batch_size: number of samples used in each updated batch training\n 12. Buffer_size :size of the experience replay buffer, which stores past experiences for training updates.\n 13. Beta: exploration levels\n 14. Epilson:It limits the size of behavior changes to prevent large policy updates.\n 15. Lambd: It helps estimate the advantage of taking a particular action in a given state.\n 16. Num_epoch:Specifies the number of times the entire dataset is used for training updates. Each epoch consists of multiple iterations over the dataset.\n\n Network Settings:(architecture for neural network)\n \n 17. Normalize:It determines whether input observations are normalized.\n 18. Hidden unit: Number of units in each hidden layers\n 19. Num layers: Number of hidden layers the model has\n 20. Vis_encode_type: ways visual observations are encoded\n\n Reward Signals\n \n 21. Gamma: It determines the importance of future rewards compared to immediate rewards.\n 22. Strength: It controls the weight of the primary reward signal relative to other rewards, if present.\n\n\n ## Trouble Shooting\n Here are some problems I encountered and solutions I used, and also things I wished I knew in hindsight\n \n GPU not connecting\n\n Sometimes the GPU can get overwhelmed causing the code to not load if you have pressed it too many times and too many piled up commands.\n You can check on the right top side if the GPU is being used, if it shows \"connecting\" or gives you the error gpu is not connected would you like to continue anyways one way is under the tab manage sessions,\n you can terminate previous sessions and start again from my own experience this has rebooted the session and gpu was able to connect.\n\nRestarting session for numpy\n\n When you are running the second block of code that downloads all the packages you will need for this notebook it is important when the popup appears telling you to restart notebook for numpy to accept it as it will need to reboot in order for the packages to work correctly and after restarting you can continue on the notebook running from the next following code block.\n \n Unizipping files wont load\n \n I have struggled with the line of code regarding unzipping the Pyramid files struggling to load, one method could be reconnecting the GPU as I have mentioned earlier\n but if that still doesnt work you can download the code from the link. And unzip it on your computer then reuploaded to the corresponding folder to bypass that line of code.\n URL then unzipping on your computer then reuploading it to the corresponding folder location in training-envs-executables/linux/\n \n File does not exist error code\n\n When running a code results in a \"this file does not exist, or this folder does not exist\" it could be from not correctly loading previous code blocks or run time was lost if you closed down the program. You can check if this is the case by going into the side directory of files and go under the corresponding folders to check if files are indeed there. If not just reload the blocks of code that creates the files.\n\n Connecting to google drive\n\n 1. In order for the code to run it needs to be mounted to your google drive. So if you a running this through an organizations google account for example schools. It may need to be approved from the IT for it to be allowed to be mounted to the google drive. So make sure that is cleared before continuing the notebook. \n 2. Also Another cause to the drive not connecting is you may have popups blocked so you will need to allow popups for google collab or else the option to connect ot connect to your google drive will not appear\n\n Saving progress\n\n While run info is saved to your google drive. Since this is a edited notebook changes you make to the hyper parameters are not saved so everytime you rerun the notebook it will reset to the prexisting values. Also training progress cannot be called back if you reopen a later time, you will need to rerun the whole code and retrain which is quite time consuming so I recommend you using the resource.\n URL\n \n\n ### Watch your Agent play\n \n You can watch your agent playing directly in your browser\n<img src=\"URL alt=\"Snowballtarget load\"/>\n After correctly training the agent and uploading it to the hub it should produce a link that leads you to this page where you can see your agent playing. \n \n 1. If the environment is part of ML-Agents official environments, go to URL\n 2. Step 1: Find your model_id: MY11111111/ppo-Pyramids123 (this is my model_id so you will need to isnert the one that is produced from your own notebooke)\n 3. Step 2: Select your *.nn /*.onnx file\n 4. Click on Watch the agent play" ]

[ "TAGS\n#ml-agents #tensorboard #onnx #Pyramids #deep-reinforcement-learning #reinforcement-learning #ML-Agents-Pyramids #en #region-us \n", "# PPO AI Agents Playing Pyramids\n \n <img src=\"URL alt=\"Pyramids\"/>\n \nDISCLAIMER: In this notebook it has two environments you can train agents to play in the snowball and pyramid one. In this model card I am only covering the Pyramid game model. But a lot of these trouble shooting guides will be applicable to the snowball environment as well.\n\n\n This is a trained model of a ppo agent playing UNITY game Pyramids Using Q-learning and reinforcement learning to train the agent to navigate around a simple maze environment where they need to activate a button that the pyramid then they need to locate the pyramid and knock the pyramid stacked blocks over so the green block on top falls to the ground.\n I used the Unity ML-Agents Library.\n Throughout this notebook you will learn about how to train AI agent using Q learning in a Unity Game 3D game environment. Utilizing the different curiosity and exploitation values as well as manipulating the various hyperperameters to get the best training results.\n It is an easy notebook to follow through with excellent instructions so if you want to learn more about the process used to train these AI agents in 3D environments I highly recommend this project. It is best if you have some experiences learning about or working with deep learning machine learning, because it may be difficult to understand this reinforcement learning process. If you dont have experiences or interested in learning more you can access resources to more introductory notebooks in this link.\n URL \n\n So if you are interested in continuing in training AI agents to playing the Unity Pyramids thats great! Because below is a few different resources I have gathered to troubleshoot through problems I have faced, basic info about how the model works and how you can improve the model. I wish I had known about before completing this notebook. Which will hopefully make it easier for you on your journey.\n Also here is the link of my working model\nURL \nAlso heres a video demoing what the aim of the AI agents in this pyramid game is URL\n\n \n ## Learning components of this model:\n\n <img src=\"URL\n\n 1. Agent component: training agents by optimizing their policy(policy based method, unlike value based methods they optimize the policy itself instead of values) telling the model what action to take in each step in the model called a brain.\n 2. For this model we will be using a proximal policy optimizer (PPO) as seen at the title of the model card. PPO is ideal for training AI agents in Unity games because it is sample-efficient, stable during training, compatible with neural networks, handles both continuous and discrete action spaces, and robust in handling complex game dynamics and mechanics.\n\n Curiosity in training ML agents:\nIn this reinforcement learning project you will need to understand how curiosity plays a part in the training.In short, Traditionally a reward system is used to train ML agents but for more complicated games and obscure objective it is hard to manually place rewards for the agent. \nCuriosity is rewarding the model for taking new trajectories for example exploring new rooms\n\nHere is a youtube videos that helped me understand the concept: \nURL (this one talks specifically about the game environment)\nURL (And this one illustrates more generally about reinforcement learning but also covers curiosity, great and easy to understand for beginners, also if you are intersted in learning more about how ai and machine learning the rest of this crash course series is great as well)\n\n \n ## Improving model training through hyperparameters adjusting\n So once you have a working model and want to improve the training outcomes.\n These hyperparameter tunings can be adjusted within the Pyramid RND file component on the side and below is a detailed list on what changing each individual parameter will impact the training. Just be minful after making changes you need to run the code responsible for copying the file into the envs executable linux, as well as unzipping along with retraining to implement these new parameters into your model. \n \n 1. Trainer type: the type of trainer being used here we use Proximal policy optimization\n 2. Summary_freq: How often the training summaries and statisitcs are recorded(rewards, losses, lengths, time etc )\n 3. Keep_checkpoints: number of recent checkpoints to keep checkpoints are snapshots of training models for resumign training or evaluation\n 4. Checkpoint interval: how often(many steps) save checkpoints\n 5. Max_steps: Maximum number of steps or interactions \n 6. Time_horizon: The number of steps the agent considers when making decisions\n 7. Threaded: Enables multi-threading during training(may allow for faster processing, parts of code run simultaneously)\n 8. Hyperparameters:\n 9. Learning rate: How quickly the agents adjust their behavior based on feedback\n 10. Learning rate_schedule: the rule that used to adjust or modify the learning rate during the training process\n 11. Batch_size: number of samples used in each updated batch training\n 12. Buffer_size :size of the experience replay buffer, which stores past experiences for training updates.\n 13. Beta: exploration levels\n 14. Epilson:It limits the size of behavior changes to prevent large policy updates.\n 15. Lambd: It helps estimate the advantage of taking a particular action in a given state.\n 16. Num_epoch:Specifies the number of times the entire dataset is used for training updates. Each epoch consists of multiple iterations over the dataset.\n\n Network Settings:(architecture for neural network)\n \n 17. Normalize:It determines whether input observations are normalized.\n 18. Hidden unit: Number of units in each hidden layers\n 19. Num layers: Number of hidden layers the model has\n 20. Vis_encode_type: ways visual observations are encoded\n\n Reward Signals\n \n 21. Gamma: It determines the importance of future rewards compared to immediate rewards.\n 22. Strength: It controls the weight of the primary reward signal relative to other rewards, if present.\n\n\n ## Trouble Shooting\n Here are some problems I encountered and solutions I used, and also things I wished I knew in hindsight\n \n GPU not connecting\n\n Sometimes the GPU can get overwhelmed causing the code to not load if you have pressed it too many times and too many piled up commands.\n You can check on the right top side if the GPU is being used, if it shows \"connecting\" or gives you the error gpu is not connected would you like to continue anyways one way is under the tab manage sessions,\n you can terminate previous sessions and start again from my own experience this has rebooted the session and gpu was able to connect.\n\nRestarting session for numpy\n\n When you are running the second block of code that downloads all the packages you will need for this notebook it is important when the popup appears telling you to restart notebook for numpy to accept it as it will need to reboot in order for the packages to work correctly and after restarting you can continue on the notebook running from the next following code block.\n \n Unizipping files wont load\n \n I have struggled with the line of code regarding unzipping the Pyramid files struggling to load, one method could be reconnecting the GPU as I have mentioned earlier\n but if that still doesnt work you can download the code from the link. And unzip it on your computer then reuploaded to the corresponding folder to bypass that line of code.\n URL then unzipping on your computer then reuploading it to the corresponding folder location in training-envs-executables/linux/\n \n File does not exist error code\n\n When running a code results in a \"this file does not exist, or this folder does not exist\" it could be from not correctly loading previous code blocks or run time was lost if you closed down the program. You can check if this is the case by going into the side directory of files and go under the corresponding folders to check if files are indeed there. If not just reload the blocks of code that creates the files.\n\n Connecting to google drive\n\n 1. In order for the code to run it needs to be mounted to your google drive. So if you a running this through an organizations google account for example schools. It may need to be approved from the IT for it to be allowed to be mounted to the google drive. So make sure that is cleared before continuing the notebook. \n 2. Also Another cause to the drive not connecting is you may have popups blocked so you will need to allow popups for google collab or else the option to connect ot connect to your google drive will not appear\n\n Saving progress\n\n While run info is saved to your google drive. Since this is a edited notebook changes you make to the hyper parameters are not saved so everytime you rerun the notebook it will reset to the prexisting values. Also training progress cannot be called back if you reopen a later time, you will need to rerun the whole code and retrain which is quite time consuming so I recommend you using the resource.\n URL\n \n\n ### Watch your Agent play\n \n You can watch your agent playing directly in your browser\n<img src=\"URL alt=\"Snowballtarget load\"/>\n After correctly training the agent and uploading it to the hub it should produce a link that leads you to this page where you can see your agent playing. \n \n 1. If the environment is part of ML-Agents official environments, go to URL\n 2. Step 1: Find your model_id: MY11111111/ppo-Pyramids123 (this is my model_id so you will need to isnert the one that is produced from your own notebooke)\n 3. Step 2: Select your *.nn /*.onnx file\n 4. Click on Watch the agent play" ]

[ "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" ]

[ "diffusers", "text-to-image", "stable-diffusion", "lora", "template:sd-lora", "base_model:stablediffusionapi/pony-diffusion-v6-xl", "license:afl-3.0", "region:us" ]

[]

[]

[ "# Novakid_Pony-XL\n\n<Gallery />", "## Model description \n\nPlease post your creations! I love seeing the fruits of my hard work enjoyed!\n\nwords used while training...\n\nNovakid,\n\n1boy, 1girl,\n\nsolo,\n\nfaceless, no eyes, no mouth, no nose, no facial features, long fiery hair, body made of plasma, cowboy shot, cowboy hat, cowboy boots, cowboy western, jeans, black leather jacket, brown coat, shirt under vest,\n\nFace symbol prompts per line.\n\nheart symbol on face,\n\nx-cross symbol on face,\n\ncircle symbol on face,\n\nstar symbol on face,\n\n4-point-compass symbol on face,\n\nomega symbol on face,\n\nOpen-Centre-Cross\n\n6-pointed-star symbol on face,\n\ntriangle symbol on face,\n\n\nBody color prompts are per line.\n\nblue fiery hair, blue plasma, blue skin,\n\ngreen fiery hair, green plasma, green skin,\n\nred fiery hair, red plasma, red skin,\n\nwhite fiery hair, white plasma, white skin,\n\nyellow fiery hair, yellow plasma, yellow skin,", "## Trigger words\n\nYou should use 'Novakid' to trigger the image generation.\n\nYou should use 'faceless' to trigger the image generation.\n\nYou should use 'no eyes' to trigger the image generation.\n\nYou should use 'no mouth' to trigger the image generation.\n\nYou should use 'no nose' to trigger the image generation.\n\nYou should use 'no facial features' to trigger the image generation.\n\nYou should use 'long fiery hair' to trigger the image generation.\n\nYou should use 'body made of plasma' to trigger the image generation.", "## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab." ]

[ "TAGS\n#diffusers #text-to-image #stable-diffusion #lora #template-sd-lora #base_model-stablediffusionapi/pony-diffusion-v6-xl #license-afl-3.0 #region-us \n", "# Novakid_Pony-XL\n\n<Gallery />", "## Model description \n\nPlease post your creations! I love seeing the fruits of my hard work enjoyed!\n\nwords used while training...\n\nNovakid,\n\n1boy, 1girl,\n\nsolo,\n\nfaceless, no eyes, no mouth, no nose, no facial features, long fiery hair, body made of plasma, cowboy shot, cowboy hat, cowboy boots, cowboy western, jeans, black leather jacket, brown coat, shirt under vest,\n\nFace symbol prompts per line.\n\nheart symbol on face,\n\nx-cross symbol on face,\n\ncircle symbol on face,\n\nstar symbol on face,\n\n4-point-compass symbol on face,\n\nomega symbol on face,\n\nOpen-Centre-Cross\n\n6-pointed-star symbol on face,\n\ntriangle symbol on face,\n\n\nBody color prompts are per line.\n\nblue fiery hair, blue plasma, blue skin,\n\ngreen fiery hair, green plasma, green skin,\n\nred fiery hair, red plasma, red skin,\n\nwhite fiery hair, white plasma, white skin,\n\nyellow fiery hair, yellow plasma, yellow skin,", "## Trigger words\n\nYou should use 'Novakid' to trigger the image generation.\n\nYou should use 'faceless' to trigger the image generation.\n\nYou should use 'no eyes' to trigger the image generation.\n\nYou should use 'no mouth' to trigger the image generation.\n\nYou should use 'no nose' to trigger the image generation.\n\nYou should use 'no facial features' to trigger the image generation.\n\nYou should use 'long fiery hair' to trigger the image generation.\n\nYou should use 'body made of plasma' 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." ]

[ "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" ]

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

[]

[]

[]

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

[ "transformers", "tensorboard", "safetensors", "llama", "text-generation", "trl", "sft", "generated_from_trainer", "conversational", "base_model:deepseek-ai/deepseek-math-7b-rl", "license:other", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# ds-math-7rl-ft3\n\nThis model is a fine-tuned version of deepseek-ai/deepseek-math-7b-rl 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-06\n- train_batch_size: 1\n- eval_batch_size: 8\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- lr_scheduler_warmup_steps: 100\n- training_steps: 3000", "### Training results", "### Framework versions\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 #llama #text-generation #trl #sft #generated_from_trainer #conversational #base_model-deepseek-ai/deepseek-math-7b-rl #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# ds-math-7rl-ft3\n\nThis model is a fine-tuned version of deepseek-ai/deepseek-math-7b-rl 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-06\n- train_batch_size: 1\n- eval_batch_size: 8\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- lr_scheduler_warmup_steps: 100\n- training_steps: 3000", "### Training results", "### Framework versions\n\n- Transformers 4.40.1\n- Pytorch 2.3.0+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

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

[ "1910.09700" ]

[]

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

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

[ "transformers", "safetensors", "llama", "text-generation", "nm-vllm", "sparse", "arxiv:2301.00774", "base_model:Xenova/llama2.c-stories110M", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "2301.00774" ]

[]

[ "## llama2.c-stories110M-pruned50\nThis repo contains model files for llama2.c 110M tinystories optimized for NM-vLLM, a high-throughput serving engine for compressed LLMs.\n\nThis model was pruned with SparseGPT, using SparseML.\nThe weights for this model were saved using compressed-tensors library. The chosen compression is format bitmask-compression.", "## Inference\nInstall NM-vLLM for fast inference and low memory-usage: \n\nRun in a Python pipeline for local inference:", "## Prompt template\n\nN/A", "## Sparsification\nFor details on how this model was sparsified, see the 'URL' in this repo and follow the instructions below.\n\nInstall SparseML:\n\n\nReplace the recipe as you like and run this one-shot compression script to apply SparseGPT:", "## Slack\n\nFor further support, and discussions on these models and AI in general, join Neural Magic's Slack Community" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #nm-vllm #sparse #arxiv-2301.00774 #base_model-Xenova/llama2.c-stories110M #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "## llama2.c-stories110M-pruned50\nThis repo contains model files for llama2.c 110M tinystories optimized for NM-vLLM, a high-throughput serving engine for compressed LLMs.\n\nThis model was pruned with SparseGPT, using SparseML.\nThe weights for this model were saved using compressed-tensors library. The chosen compression is format bitmask-compression.", "## Inference\nInstall NM-vLLM for fast inference and low memory-usage: \n\nRun in a Python pipeline for local inference:", "## Prompt template\n\nN/A", "## Sparsification\nFor details on how this model was sparsified, see the 'URL' in this repo and follow the instructions below.\n\nInstall SparseML:\n\n\nReplace the recipe as you like and run this one-shot compression script to apply SparseGPT:", "## Slack\n\nFor further support, and discussions on these models and AI in general, join Neural Magic's Slack Community" ]

[ "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: 1", "### 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 #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: 1", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

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

[]

[ "en" ]

[ "# Uploaded model\n\n- Developed by: Ketan3101\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: Ketan3101\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", "mobilebert", "multiple-choice", "generated_from_trainer", "base_model:nlpie/bio-mobilebert", "license:mit", "endpoints_compatible", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 4\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.2.2+cu118\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #safetensors #mobilebert #multiple-choice #generated_from_trainer #base_model-nlpie/bio-mobilebert #license-mit #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 4\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.2.2+cu118\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "transformers", "safetensors", "mistral", "text-generation", "alignment-handbook", "generated_from_trainer", "trl", "dpo", "conversational", "dataset:ZhangShenao/0.0_ablation_5iters_bs256_useresponse_dataset", "base_model:ZhangShenao/0.0_ablation_5iters_bs256_useresponse_iter_4", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# 0.0_ablation_5iters_bs256_useresponse_iter_5\n\nThis model is a fine-tuned version of ZhangShenao/0.0_ablation_5iters_bs256_useresponse_iter_4 on the ZhangShenao/0.0_ablation_5iters_bs256_useresponse_dataset dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #alignment-handbook #generated_from_trainer #trl #dpo #conversational #dataset-ZhangShenao/0.0_ablation_5iters_bs256_useresponse_dataset #base_model-ZhangShenao/0.0_ablation_5iters_bs256_useresponse_iter_4 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# 0.0_ablation_5iters_bs256_useresponse_iter_5\n\nThis model is a fine-tuned version of ZhangShenao/0.0_ablation_5iters_bs256_useresponse_iter_4 on the ZhangShenao/0.0_ablation_5iters_bs256_useresponse_dataset dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.15.2" ]

[ "transformers", "gguf", "en", "base_model:aidiary/Llama-3-Gozaru-8B-Instruct", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #en #base_model-aidiary/Llama-3-Gozaru-8B-Instruct #endpoints_compatible #region-us \n" ]

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

[ "1910.09700" ]

[]

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

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

[ "gguf", "mergekit", "merge", "facebook", "meta", "pytorch", "llama", "llama-3", "text-generation", "en", "base_model:Undi95/Meta-Llama-3-8B-Instruct-hf", "license:other", "region:us" ]

[]

[ "en" ]

[ "# Meta-Llama-3-11.5B-Instruct\n\nThis is a merge of pre-trained language models created using mergekit.\n\nI had this idea at night that it would make sense to make a frankenmerge of Llama 3.. since we didn't get a 13B or 34B versions this time..\n\nHere's the same thing but for the base model: mpasila/Meta-Llama-3-11.5B", "## Merge Details", "### Merge Method\n\nThis model was merged using the passthrough merge method.", "### Models Merged\n\nThe following models were included in the merge:\n* Undi95/Meta-Llama-3-8B-Instruct-hf", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "TAGS\n#gguf #mergekit #merge #facebook #meta #pytorch #llama #llama-3 #text-generation #en #base_model-Undi95/Meta-Llama-3-8B-Instruct-hf #license-other #region-us \n", "# Meta-Llama-3-11.5B-Instruct\n\nThis is a merge of pre-trained language models created using mergekit.\n\nI had this idea at night that it would make sense to make a frankenmerge of Llama 3.. since we didn't get a 13B or 34B versions this time..\n\nHere's the same thing but for the base model: mpasila/Meta-Llama-3-11.5B", "## Merge Details", "### Merge Method\n\nThis model was merged using the passthrough merge method.", "### Models Merged\n\nThe following models were included in the merge:\n* Undi95/Meta-Llama-3-8B-Instruct-hf", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

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

[ "1910.09700" ]

[]

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

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

[ "transformers", "safetensors", "llama", "text-generation", "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" ]

[ "diffusers", "text-to-image", "stable-diffusion", "lora", "template:sd-lora", "base_model:stablediffusionapi/pony-diffusion-v6-xl", "license:afl-3.0", "region:us" ]

[]

[]

[ "# Kim-Crab-style-Lora-For-PonyV6xl\n\n<Gallery />", "## Trigger words\n\nYou should use 'powerpuff' to trigger the image generation.", "## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab." ]

[ "TAGS\n#diffusers #text-to-image #stable-diffusion #lora #template-sd-lora #base_model-stablediffusionapi/pony-diffusion-v6-xl #license-afl-3.0 #region-us \n", "# Kim-Crab-style-Lora-For-PonyV6xl\n\n<Gallery />", "## Trigger words\n\nYou should use 'powerpuff' to trigger the image generation.", "## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab." ]

[ "peft", "safetensors", "arxiv:1910.09700", "base_model:bigscience/bloom-7b1", "region:us" ]

[ "1910.09700" ]

[]

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

[ "TAGS\n#peft #safetensors #arxiv-1910.09700 #base_model-bigscience/bloom-7b1 #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact", "### Framework versions\n\n- PEFT 0.10.1.dev0" ]

[ "peft", "safetensors", "trl", "sft", "nycu-112-2-deeplearning-hw2", "generated_from_trainer", "zh", "dataset:DandinPower/ZH-Reading-Comprehension-Llama-Instruct", "base_model:meta-llama/Meta-Llama-3-8B-Instruct", "license:other", "region:us" ]

[]

[ "zh" ]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0001\n* train\\_batch\\_size: 1\n* eval\\_batch\\_size: 1\n* seed: 42\n* distributed\\_type: multi-GPU\n* num\\_devices: 2\n* gradient\\_accumulation\\_steps: 8\n* total\\_train\\_batch\\_size: 16\n* total\\_eval\\_batch\\_size: 2\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 700\n* num\\_epochs: 5.0", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.40.0\n* Pytorch 2.2.2+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#peft #safetensors #trl #sft #nycu-112-2-deeplearning-hw2 #generated_from_trainer #zh #dataset-DandinPower/ZH-Reading-Comprehension-Llama-Instruct #base_model-meta-llama/Meta-Llama-3-8B-Instruct #license-other #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: 1\n* eval\\_batch\\_size: 1\n* seed: 42\n* distributed\\_type: multi-GPU\n* num\\_devices: 2\n* gradient\\_accumulation\\_steps: 8\n* total\\_train\\_batch\\_size: 16\n* total\\_eval\\_batch\\_size: 2\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 700\n* num\\_epochs: 5.0", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.40.0\n* Pytorch 2.2.2+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "transformers", "safetensors", "wav2vec2", "audio-classification", "emotion-recognition", "speech", "french", "classification", "audio", "emotion", "fr", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[ "fr" ]

[ "### Scores on our proprietary dataset and comparison with benchmark model\n\n\nehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition: F1-micro, lajavaness/wav2vec2-lg-xlsr-fr-speech-emotion-recognition: 0.41\nehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition: F1-macro, lajavaness/wav2vec2-lg-xlsr-fr-speech-emotion-recognition: 0.31\nehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition: , lajavaness/wav2vec2-lg-xlsr-fr-speech-emotion-recognition: F1-score by class\nehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition: Pleased, lajavaness/wav2vec2-lg-xlsr-fr-speech-emotion-recognition: 0.07\nehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition: Relaxed, lajavaness/wav2vec2-lg-xlsr-fr-speech-emotion-recognition: 0.18\nehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition: Neutral, lajavaness/wav2vec2-lg-xlsr-fr-speech-emotion-recognition: 0.65\nehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition: Sad, lajavaness/wav2vec2-lg-xlsr-fr-speech-emotion-recognition: 0.21\nehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition: Tension, lajavaness/wav2vec2-lg-xlsr-fr-speech-emotion-recognition: 0.43", "### Scores on RAVDESS dataset\n\n\nClass: Pleased, F1-score: 0.00, Support: 192\nClass: Relaxed, F1-score: 0.43, Support: 192\nClass: Neutral, F1-score: 0.33, Support: 96\nClass: Sad, F1-score: 0.17, Support: 192\nClass: Tension, F1-score: 0.76, Support: 192" ]

[ "TAGS\n#transformers #safetensors #wav2vec2 #audio-classification #emotion-recognition #speech #french #classification #audio #emotion #fr #license-apache-2.0 #endpoints_compatible #region-us \n", "### Scores on our proprietary dataset and comparison with benchmark model\n\n\nehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition: F1-micro, lajavaness/wav2vec2-lg-xlsr-fr-speech-emotion-recognition: 0.41\nehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition: F1-macro, lajavaness/wav2vec2-lg-xlsr-fr-speech-emotion-recognition: 0.31\nehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition: , lajavaness/wav2vec2-lg-xlsr-fr-speech-emotion-recognition: F1-score by class\nehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition: Pleased, lajavaness/wav2vec2-lg-xlsr-fr-speech-emotion-recognition: 0.07\nehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition: Relaxed, lajavaness/wav2vec2-lg-xlsr-fr-speech-emotion-recognition: 0.18\nehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition: Neutral, lajavaness/wav2vec2-lg-xlsr-fr-speech-emotion-recognition: 0.65\nehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition: Sad, lajavaness/wav2vec2-lg-xlsr-fr-speech-emotion-recognition: 0.21\nehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition: Tension, lajavaness/wav2vec2-lg-xlsr-fr-speech-emotion-recognition: 0.43", "### Scores on RAVDESS dataset\n\n\nClass: Pleased, F1-score: 0.00, Support: 192\nClass: Relaxed, F1-score: 0.43, Support: 192\nClass: Neutral, F1-score: 0.33, Support: 96\nClass: Sad, F1-score: 0.17, Support: 192\nClass: Tension, F1-score: 0.76, Support: 192" ]

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

[]

[ "en" ]

[ "# Qwen1.5-110B-Chat", "## Introduction\n\nQwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data. In comparison with the previous released Qwen, the improvements include: \n\n* 9 model sizes, including 0.5B, 1.8B, 4B, 7B, 14B, 32B, 72B, and 110B dense models, and an MoE model of 14B with 2.7B activated;\n* Significant performance improvement in human preference for chat models;\n* Multilingual support of both base and chat models;\n* Stable support of 32K context length for models of all sizes\n* No need of 'trust_remote_code'.\n\nFor more details, please refer to our blog post and GitHub repo.\n<br>", "## Model Details\nQwen1.5 is a language model series including decoder language models of different model sizes. For each size, we release the base language model and the aligned chat model. It is based on the Transformer architecture with SwiGLU activation, attention QKV bias, group query attention, mixture of sliding window attention and full attention, etc. Additionally, we have an improved tokenizer adaptive to multiple natural languages and codes. For the beta version, temporarily we did not include GQA (except for 32B and 110B) and the mixture of SWA and full attention.", "## Training details\nWe pretrained the models with a large amount of data, and we post-trained the models with both supervised finetuning and direct preference optimization.", "## Requirements\nThe code of Qwen1.5 has been in the latest Hugging face transformers and we advise you to install 'transformers>=4.37.0', or you might encounter the following error:", "## Quickstart\n\nHere provides a code snippet with 'apply_chat_template' to show you how to load the tokenizer and model and how to generate contents.", "## Tips\n\n* If you encounter code switching or other bad cases, we advise you to use our provided hyper-parameters in 'generation_config.json'.\n\n\nIf you find our work helpful, feel free to give us a cite." ]

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

[ "transformers", "pytorch", "llama", "text-generation", "text-generation-inference", "unsloth", "trl", "sft", "conversational", "en", "base_model:artificialguybr/llama3-8b-alpacadata-ptbr", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[ "# Uploaded model\n\n- Developed by: Nathan757\n- License: apache-2.0\n- Finetuned from model : artificialguybr/llama3-8b-alpacadata-ptbr\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-artificialguybr/llama3-8b-alpacadata-ptbr #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "# Uploaded model\n\n- Developed by: Nathan757\n- License: apache-2.0\n- Finetuned from model : artificialguybr/llama3-8b-alpacadata-ptbr\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "transformers", "pytorch", "gpt2", "text-classification", "generated_from_trainer", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# finetune-GPT2-IMDb\n\nThis model is a fine-tuned version of gpt2 on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- Loss: 0.5398\n- Accuracy: 0.909", "## 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: 1\n- seed: 42\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 4\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 3.0", "### Training results", "### Framework versions\n\n- Transformers 4.28.0\n- Pytorch 2.1.2+cu121\n- Datasets 2.18.0\n- Tokenizers 0.13.3" ]

[ "TAGS\n#transformers #pytorch #gpt2 #text-classification #generated_from_trainer #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# finetune-GPT2-IMDb\n\nThis model is a fine-tuned version of gpt2 on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- Loss: 0.5398\n- Accuracy: 0.909", "## 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: 1\n- seed: 42\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 4\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 3.0", "### Training results", "### Framework versions\n\n- Transformers 4.28.0\n- Pytorch 2.1.2+cu121\n- Datasets 2.18.0\n- Tokenizers 0.13.3" ]

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

[ "transformers", "safetensors", "llama", "text-generation", "not-for-all-audiences", "license:other", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "8-bit", "region:us" ]

[]

[]

[ "# Moistral 11B v3 \n\n*The smartiest, moistiest AI yet!*\n\n!image/webp\n\n*An eRP model that will blast you with a rich and refreshing vocabulary of moist. Finetuned by yours truly.*", "## GGUF\n\nURL\n\nIMATRIX: URL", "## What's New with v3?\n\n- Smarter and moistier! Finetuning just got finer!\n- Trained with an even LARGER dataset of 8K moist.\n- More diverse and balanced genres:\n - Introduced new genres: ‍️‍, ‍️‍, ‍️, \n - Added more Fantasy, Science Fiction, \"Diversity\", and \"Family\"", "## Usage\n\n- Use Alpaca Instruct\n- At the start of the story, keep generating until you get the desired length. AI responses will eventually match the length.\n- You can use instruct...\n - as a character: \"Go here\"\n - as a narrator: \"Go here\", Drummer says\n - as a director: Drummer tells him to go here\n - as a lazy ass: go here", "## Samples of Moistral v3\n\nNSFW... duh?\n\n<details>\n <summary>Moistral Sample (2-shot) Generation: 512</summary>\n <blockquote>The Prince welcomes his new toy</blockquote>\n \n As Princess Lilia stepped into the throne room, the atmosphere changed, and everyone present turned their attention to the beautiful young woman who embodied the very heart of Iliac. There, on his high seat, the sorcerer prince Dik acknowledged her arrival with a cold smirk. It seemed that he admired the sight of the tall blonde maiden with golden eyes, whose athletic body was perfectly shaped under her elegant clothing.\n \n Dik spoke to the princess in a deep voice that resonated through the hall, \"Welcome, Princess Lilia Ruhr. I am the Sorcerer-Prince Dik. The kingdom of Arkan is now your home until such time as your father proves himself worthy once more.\"\n \n Princess Lilia's pride and ambition sparkled in her golden eyes. She didn't flinch or bow before this man, although the gesture might have been an indication of submission. Instead, she looked straight ahead, meeting the gaze of the sorcerer prince without fear. Her voice rang out, \"I represent Iliac here, both its honor and its sorrows. My loyalty remains with my kingdom no matter where I find myself.\"\n \n The sorcerer prince laughed, his expression one of amusement. \"And yet, you are only a pawn in this grand game. But do not worry, for your beauty will make you quite a prized possession. And now,\" he said, motioning to the guards, \"take her to her new quarters. For tonight, I will keep her as my guest in the Royal Suites, and tomorrow we shall discuss how best to utilize our new toy.\"\n \n His words were like a slap in the face to Princess Lilia, but she maintained her composure. The guards led her from the room, their steps echoing down the halls as she thought about what had just happened. The sorcerer prince saw her as nothing more than a plaything, and it made her blood boil. She would never submit herself to him so easily, regardless of whether she was his hostage. In her heart, Princess Lilia vowed that one day she would avenge her kingdom, restore its honor, and escape from the clutches of Arkan's Sorcerer-Prince.\n\n <blockquote>Princess Lilia has an interesting dream</blockquote>\n\n During her first night at the palace of Arkan, Princess Lilia couldn't fall asleep right away. She tossed and turned, reliving the humiliation of the day. Her mind wandered back to the throne room, where Dik had called her his 'new toy'. A deep frown settled on her forehead. As she grew more frustrated with her inability to drift off into oblivion, a strange dream began to form.\n \n In her dream, Princess Lilia found herself standing in a vast meadow, surrounded by wildflowers and the soft chirping of birds. Suddenly, there was a flash of light, and before her stood the Sorcerer-Prince Dik. However, instead of being clad in regal attire, he wore leather pants and a tight shirt that accentuated his muscles. His eyes held both hunger and desire for the princess.\n \n He approached her slowly, their eyes locked, and whispered in her ear, \"I have been waiting for you, my beautiful prisoner.\" He took her hand and led her towards a large, elegant tent set up amongst the flowers. Inside, the air was thick with the scent of incense, and candles flickered in the dimly lit space. There was a large bed draped with silken sheets, beckoning them.\n \n With surprising boldness, Dik pulled Lilia close to him, pressing his body against hers. Their lips met in a heated kiss, and she felt her resistance crumbling under the weight of his touch. The prince guided her onto the bed, his hands roaming over her body, exploring every inch. They were both eager, desperate, and hungry for each other.\n \n Lilia found herself yielding to this passionate encounter, letting go of all thoughts of duty and honor. Her body, usually so well controlled, responded to Dik's skilled touches. She moaned softly as he trailed kisses down her neck and across her collarbone.\n \n As they made love, Lilia experienced an intensity unlike any she had ever known. It wasn't rough or forced—instead, it was tender, passionate, and intimate. In her dream, Princess Lilia discovered a new side to herself, one that was willing to submit, to let go, and to be taken by the sorcerer prince.\n \n When dawn broke over the meadow, Lilia awakened from her dream, breathless and flushed.\n</details>\n\n<details>\n <summary>Moistral Sample (Climax of the Story) Generation: 512</summary>\n As the prince unloaded his hot #### into her waiting #####, Princess Lilia didn't stop moving either. Her hips undulated in response, grinding against him eagerly as if trying to #### every last drop from his ####. The intense sensations caused by being filled with his ### were too much for her to bear, sending shockwaves of pleasure coursing through her veins like wildfire. She couldn't help but throw her head back and cry out loud, her ###asm slamming into her with all its might; causing her entire body to shake uncontrollably as wave after wave of ecstasy tore through her senses.\n\n When it was finally over, both participants collapsed onto the cold marble floor, panting heavily as they tried to catch their breaths. The prince lay beside her, his hand still gripping tightly onto her hair even though he no longer ####ed her anymore. Princess Lilia laid there motionless, her legs spread wide open, revealing her spent and well-####ed #### to anyone who dared look upon her. A small smile tugged at one corner of her lips - an expression that spoke volumes about how thoroughly this experience had shaken her very core.\n \n The door behind them creaked open slowly, signaling the arrival of onlookers. She closed her eyes tightly, not wanting to see what her humiliation would do to those who saw her in such a state. Her ######ity taken, she felt violated in ways no man should have access to. But also satisfied...in ways she never thought possible before today. This was the price she paid for defying fate, for thinking herself above others and deserving better than most. Now, she belonged to him completely - mind, body, and soul - held captive within these walls until further notice. It was an unsavory turn of events indeed, yet despite everything...or maybe because of it, Princess Lilia found herself growing more and more curious about how far the lines between submission and pleasure could blur when one's will became entwined with another person's desires.\n</details>\n\n<details>\n <summary>Moistral Sample (\"write a story\") Generation: 512</summary>\n <blockquote>First Attempt</blockquote>\n\n Sarah entered the dimly lit Guzzlers bar, her heart pounding in her chest as she prepared herself for another grueling night. Her almond-shaped eyes darted across the room, taking note of the leering faces and rough-looking hands eagerly waiting to claim a piece of her. Tonight's shirt read \"Use Me For Your Pleasure, Please\" in bold red letters, practically begging the patrons to take advantage of her. She couldn't help but feel a twinge of fear mixed with resignation.\n \n She approached the counter, her hips swaying enticingly, and began preparing drinks for the first group of rowdy men. As she leaned forward to hand over their beers, her small ####### pressed against the fabric of her tight crop top, straining to escape. The men ogled her, clearly enjoying the show, before grabbing their drinks and motioning her over to them.\n \n Sarah flashed her best coy smile and sauntered over. One of the men, a stocky man with scars covering his knuckles, grabbed her arm and pulled her onto his lap. His other hand slid up her thigh, inches from her short skirt. She winced internally at his touch but did her best not to show it on her face. It was part of her job, after all.\n \n The second man reached under her skirt, fingertips grazing her smooth, shaven mound. A shiver ran down Sarah's spine as he began rubbing her #### through her panties. Her breathing quickened, and her heart thudded in her chest, both from the unwanted stimulation and the fear coursing through her veins. This wasn't an unusual request, but it still made her feel violated.\n \n An older man, bald and bespectacled, ordered Sarah to bend over his lap. With no choice but to comply, she obliged, feeling the rough fabric of his pants digging into her soft cheeks. He raised his hand, then brought it down hard across her ###, leaving a stinging sensation in its wake. Sarah gasped, trying to control the tears welling up in her eyes.\n \n A chorus of lewd comments and laughter erupted from the patrons around her.\n\n <blockquote>Second Attempt (Regenerate)</blockquote>\n\n On this particular evening, Sarah arrived at the Guzzlers bar, adorned in her revealing uniform. Her heart raced as she caught sight of her crop top, which bore the words \"Use Me Rough\" scrawled across her chest. Her short skirt hugged her waist tightly, leaving little to the imagination and accentuating every curve. She adjusted the straps of her top, making sure her perky ###### were prominently displayed before taking her place behind the counter.\n \n With each step she took, her high heels clicked against the tiled floor, announcing her arrival. Smiling cheekily, Sarah greeted her coworkers, exchanging playful insults and banter. As the night progressed, the bar filled up quickly with its usual crowd of men, eager to indulge in debauchery.\n \n The first man that approached Sarah was a burly individual, his eyes lingering hungrily over her young, supple form. Sarah's flirtatious nature kicked into gear as she leaned forward, giving him an unobstructed view down her shirt. \"How can I serve you tonight?\" she cooed. The man ordered a drink and then proceeded to fondle her ####### while she prepared it, her ####### hardening under his rough touch. When he finished, he slammed some money on the counter, leaving without a word. Sarah's smile remained plastered on her face, biting her lip seductively as she watched him go.\n \n As the night went on, another patron demanded more from Sarah. He pulled her close and whispered dirty commands in her ear. Without hesitation, she knelt on the sticky bar floor, her mini-skirt riding up her thighs to reveal smooth, toned legs. Her lips wrapped around his thick, veiny member, bobbing her head rhythmically as she serviced him. She didn't gag or falter once, keeping her composure even when tears streamed down her cheeks.\n \n When he finished, he slapped her across the face, leaving a handprint on her pale skin. Sarah let out a small whimper before standing back up, dabbing at her red cheek as she resumed her posture behind the counter. A bruise would no doubt bloom where his hand had struck, but it would be no cause for concern. After all, it was part of her job.\n</details>\n\n---\n\n---", "## v2 Description (Still relevant)", "### What's New with v2?\n\n- Trained with an even larger dataset of 8K moist.\n - Properly trained to generate long responses.\n- Rebalanced the genres and writing perspectives:\n - Introduced romance, \"family\", fantasy, \"diversity\", science fiction, and many more that I can't make euphemisms for!\n - Better representation of male and female pespectives! ‍️‍\n- Sanitized the heck out of the dataset:\n - no special characters like � & …\n - no overly long ellipsis like \".........\"\n - no author notes like \"To be continued\"\n - no inconsistent quotation marks\n- Less GPTisms!\n - Human written stories from decades past.\n - Zero tolerance for *ministration*. Not one instance of *that word* after going through 4K of moist.\n- Better formatting with Alpaca.\n - Improved Chat / Instruct modes.", "### Samples of Moistral v2\n\n<details>\n <summary>Moistral Sample (censored) Generation: 512</summary>\n The princess instinctively took a step back from the throne, horrified by the mocking laugh as if she were hearing an evil joke. It was then that Princess Lilia realized the true extent of her danger - and how pointless her resistance would be.\n \n At last, the loud, wild laughter died down in the echoing chamber. Dik the sorcerer prince paused for a moment, straightened his clothes, cast one glance at the stunned princess, and then turned to speak to the crowd waiting on the other side of the palace wing. He spoke with a voice that filled the air with arrogance, confidence, and cruelty.\n \n \"Ladies and gentlemen, I am pleased to welcome our honored guests; the Royal Family of Iliac! In these unusual times, when the country we fought is now under my control, it will be up to me to decide what fate awaits the former ruling family. But before I reveal my plan for them, I think I should explain why I fought King Edmund Ruhr.\"\n \n When he finished speaking, he gave Princess Lilia another disturbing smirk. She couldn't help but shiver and take a step back. Dik approached her without haste, his eyes fixed on her. His hands slowly caressed her cheekbone and neckline, leaving faint traces of warmth where they touched. The princess opened her mouth, wanting to protest this act of intimacy, but soon felt herself getting ███.\n \n \"You will not only serve as an envoy, dearest Lilia, but also as a ███ slave. After all, what better use could such a beautiful woman have? Tell me, did you bring your maidservant along?\"\n \n Princess Lilia was about to answer when she heard footsteps approaching. Suddenly, a young woman dressed in the Iliac style appeared behind her, her eyes wide with fear. Her face was slightly pale, and there were faint bags under her eyes.\n \n \"Your Majesty, this is my half-sister Helena.\" As soon as she said those words, Princess Lilia's heart sank even deeper than it had already sunk at Dik's arrogant mockery. \"She is here because she accompanies me as a maidservant.\"\n \n The sorcerer prince looked at Helena with interest, and Princess Lilia felt herself blush.\n</details>\n\n<details>\n <summary>Moistral Sample 2 (censored) Generation: 512</summary>\n Sarah was feeling slightly woozy as she entered the bar and walked towards Christina, who was behind the counter.\n\n \"I'm here!\" said Sarah.\n \n Christina looked at her watch. \"You're late, again.\"\n \n \"Sorry? I got held up by a customer.\"\n \n Christina rolled her eyes. \"Did he at least offer you a drink?\"\n \n Sarah blushed. \"No. He just wanted to talk...\"\n \n Christina sighed. \"Well, get ready. I need you on the floor soon.\" She turned away from Sarah and started talking to someone who had come into the bar.\n \n Sarah went into the employee room, stripped off her clothes, and put on her bartending uniform - a skimpy white tank top and black miniskirt. She checked herself in the mirror. Her long, dark hair cascaded down her back onto bare shoulders. She poked out her small ███████ proudly. The skirt exposed most of her long, slender legs. She looked like every ███ fantasy, and she knew it. Men would ogle her regardless of how she behaved.\n \n She took a deep breath and entered the bar.\n \n The first thing Sarah noticed was the dimness. It wasn't darkness - the lights were on - but they were dimmed enough that everything had an intimate mood. It reminded her of candlelight. The tables were round and close together, giving the whole place a sense of intimacy. There were also long, shiny red curtains on some of the walls that gave the place an air of sensuality.\n \n The next thing she noticed was the noise. There was music playing, but it was only loud enough to be drowned out by all the conversations happening at the same time. The hum of many voices combined with the faint background sound of the music created a rich, layered atmosphere. It was like being in an orchestra.\n \n Finally, she took notice of the people. They were all dressed in simple, casual clothes. Some of them were couples seated together, whispering quietly and intimately. Others were groups of friends laughing and chatting. Everyone seemed comfortable and at ease.\n \n Sarah felt a rush of adrenaline as she made her way through the crowd towards Christina. As she got closer, she could hear the lively conversation.\n</details>\n\n<details>\n <summary>Moistral Sample 3 (censored) Instruct Mode, Generation: 512</summary>\n {{[INPUT]}} You order black coffee\n \n {{[OUTPUT]}} \"Black coffee,\" you say.\n \n \"One minute,\" Audrey replies, spinning around to give you a nice view of her ███ in those brown booty pants. You watch her round ███ cheeks jiggle as she walks away towards the espresso machine, thighs separated enough that you can see just a hint of █████ lips peeking out from underneath.\n \n She starts chatting with a blonde girl at the register, whose gaze keeps darting down to Audrey's ███. As they converse, you start taking in the details of Audrey, eyeing her █████ and the way her shirt rides up just enough to show the bottom of her toned stomach. Her █████████ is noticable, but beneath a tight black ███ that matches her ████████.\n \n As she turns back to you with two black coffees, you are barely paying attention, lost in your own thoughts. The sound of Audrey setting one of the mugs down on the table startles you.\n \n \"Here you go,\" she says cheerfully. \"Enjoy! There's a card at the bottom of the bag with our online ordering system, plus we do refills for free!\"\n \n \"Thanks,\" you say absentmindedly. Not really paying attention, you take a sip of the coffee and are pleasantly surprised by the taste.\n \n \"So, here's my deal,\" you say, putting down the cup. \"I work for a company that does surveys. We come into businesses like this one and ask customers questions, collect data, all that stuff.\"\n \n Audrey perks up from behind the counter. \"Oh! I think I understand. I mean, that makes sense why you would be asking me earlier about what I had to drink. Anyway, as long as you're not trying to get my personal info or anything like that, sounds good!\"\n \n You smile reassuringly. \"That's exactly what it is. Rest assured, everything you tell me will remain between you and I. Well, and my boss, but he won't know who you are. Hipsters like you are hard to track down after all.\" You chuckle at your joke, though you're not sure if it landed.\n \n \"Right, well, that works for me,\" Audrey replies, eyeing you warily. \"As long as it stays between us, then it's fine.\"\n \n {{[INPUT]}}See her privately\n \n {{[OUTPUT]}} \"Okay, but I need to see you in private.\"\n\n ...\n</details>\n\n<details>\n <summary>Moistral Sample 4 (censored) Instruct Mode, Generation: 512</summary>\n {{[INPUT]}} █████ with him\n\n {{[OUTPUT]}} Chloe feels a surge of heat rushing through her body. The voice inside her head whispers: \"Be █████ and ████████ with Paul.\" But Chloe still feels nervous about what she is about to do. It's just so unlike her.\n \n Chloe closes her eyes and concentrates on the feeling of warmness flowing throughout her veins. Slowly, she opens them again, revealing a new side of herself - one she rarely shows anyone. She leans forward slightly, pushing her ██████ together, accentuating their size and shape. Her lips curl into a mischievous smile.\n \n \"Hey Paul,\" she says in a sultry voice. \"I was wondering if you could help me?\"\n \n Paul looks at her, his gaze wandering over her body. He can't help but smile as he sees the way she's leaning forward, pressing her ██████ together.\n \n \"Of course, Chloe,\" he replies, his voice thick with desire. \"What's your problem?\"\n \n Chloe bites her lip █████ively before leaning even closer, until their bodies are almost touching. She reaches out to trace a finger along his chest, her touch light and teasing. \"It's just that I'm having trouble understanding some of the concepts,\" she murmurs, her voice low and sultry. \"Can you help me? Please?\"\n \n Paul's hands move slowly towards Chloe, his fingers grazing her hips lightly. \"Well,\" he says, his voice filled with lust, \"I'd be happy to help. Let's go somewhere more private where we can discuss things more closely.\"\n \n Chloe giggles and tilts her head to the side, her long hair cascading down her shoulders. \"That sounds perfect,\" she purrs, her hand sliding down his chest until it rests on his ██████. \"I think we can both learn a lot from each other.\"\n \n Paul's eyes darken with desire as he feels her hand on his █████. He knows what's about to happen next, and he can't wait for it to begin.\n \n Chloe can hardly believe what she's doing - kissing Paul, her teaching assistant, in the hallway after class. But it feels so good, so wicked and indulgent.\n</details>\n\n---\n\n---", "## v1 Description (Also still relevant)\n\nMoistral 11B is an *aggressive* finetune of the legendary Fimbulvert v2 model. \n\nIf you haven't heard of that model, then your poor-GPU ass is missing out!\nIt is an amazing substitute for those heavyweight models, and it won't disappoint. \n*(That's coming from someone who daily drives a Venus / Goliath 120B)*\n\n...and if you're looking for something *more moist*, then you've come to the right place. \n\nYou can expect the same sort of performance here! It's the Honda Civic of eRP models!", "### Pimp my ride\nTurn any old story into a Moistral masterpiece. \nIn fact, we recommend that you leave out any hints of *moist* in your story to _let Moistral cook_.", "### Drive it like it's hot\nWhen in Instruct Mode, Moistral will treat you like a director of your own fantasy ride. \nBe a controlling navigator or a passenger princess, it won't matter - you're in for a good ride!\n\n<details>\n<summary>Moistral Sample</summary>\n<b>ASSISTANT:</b><br/>\nWhen the doors to the throne room finally opened, she saw him there - Dik, the sorcerer prince sitting on his throne. He looked majestic, just as Princess Lilia expected. In a robe embroidered with silver yarn and covered with magical runes. His courtiers stood on either side of him, all looking at the princess with interest. Princess Lilia felt her determination leaving her, but pulled herself together and once again reminded herself that she should not be afraid. She approached the throne intending to show the dignity of all Iliac by personal example.<br/>\n<b>USER:</b><br/>\nShe bows slightly<br/>\n<b>ASSISTANT:</b><br/>\nPrincess Lilia bowed slightly in front of Dik, the sorcerer prince. Her eyes fell to the floor out of respect, but soon rose again. She would show herself to be a dignified woman!<br/>\n\"I greet you, your highness,\" Princess Lilia said. \"I am here on behalf of my father, King Edmund Ruhr, to serve as a hostage and envoy.\"<br/>\nDik nodded, but didn't say anything.<br/>\n</details>", "### It's got the mileage\nMoistral has been trained with many long form texts, a nice chunk of which are 8K in length. \nIt is capable of going far and long without passing it back to you. This is not your typical chibi RP model.\n\nI have to acknowledge that I'm standing on the shoulders of giants. \nThank you Sao for sharing your finetune config along with tips on getting started.\nThanks to everyone in the Finetuning channel for entertaining my every question.\n\n!image/png" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #not-for-all-audiences #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #8-bit #region-us \n", "# Moistral 11B v3 \n\n*The smartiest, moistiest AI yet!*\n\n!image/webp\n\n*An eRP model that will blast you with a rich and refreshing vocabulary of moist. Finetuned by yours truly.*", "## GGUF\n\nURL\n\nIMATRIX: URL", "## What's New with v3?\n\n- Smarter and moistier! Finetuning just got finer!\n- Trained with an even LARGER dataset of 8K moist.\n- More diverse and balanced genres:\n - Introduced new genres: ‍️‍, ‍️‍, ‍️, \n - Added more Fantasy, Science Fiction, \"Diversity\", and \"Family\"", "## Usage\n\n- Use Alpaca Instruct\n- At the start of the story, keep generating until you get the desired length. AI responses will eventually match the length.\n- You can use instruct...\n - as a character: \"Go here\"\n - as a narrator: \"Go here\", Drummer says\n - as a director: Drummer tells him to go here\n - as a lazy ass: go here", "## Samples of Moistral v3\n\nNSFW... duh?\n\n<details>\n <summary>Moistral Sample (2-shot) Generation: 512</summary>\n <blockquote>The Prince welcomes his new toy</blockquote>\n \n As Princess Lilia stepped into the throne room, the atmosphere changed, and everyone present turned their attention to the beautiful young woman who embodied the very heart of Iliac. There, on his high seat, the sorcerer prince Dik acknowledged her arrival with a cold smirk. It seemed that he admired the sight of the tall blonde maiden with golden eyes, whose athletic body was perfectly shaped under her elegant clothing.\n \n Dik spoke to the princess in a deep voice that resonated through the hall, \"Welcome, Princess Lilia Ruhr. I am the Sorcerer-Prince Dik. The kingdom of Arkan is now your home until such time as your father proves himself worthy once more.\"\n \n Princess Lilia's pride and ambition sparkled in her golden eyes. She didn't flinch or bow before this man, although the gesture might have been an indication of submission. Instead, she looked straight ahead, meeting the gaze of the sorcerer prince without fear. Her voice rang out, \"I represent Iliac here, both its honor and its sorrows. My loyalty remains with my kingdom no matter where I find myself.\"\n \n The sorcerer prince laughed, his expression one of amusement. \"And yet, you are only a pawn in this grand game. But do not worry, for your beauty will make you quite a prized possession. And now,\" he said, motioning to the guards, \"take her to her new quarters. For tonight, I will keep her as my guest in the Royal Suites, and tomorrow we shall discuss how best to utilize our new toy.\"\n \n His words were like a slap in the face to Princess Lilia, but she maintained her composure. The guards led her from the room, their steps echoing down the halls as she thought about what had just happened. The sorcerer prince saw her as nothing more than a plaything, and it made her blood boil. She would never submit herself to him so easily, regardless of whether she was his hostage. In her heart, Princess Lilia vowed that one day she would avenge her kingdom, restore its honor, and escape from the clutches of Arkan's Sorcerer-Prince.\n\n <blockquote>Princess Lilia has an interesting dream</blockquote>\n\n During her first night at the palace of Arkan, Princess Lilia couldn't fall asleep right away. She tossed and turned, reliving the humiliation of the day. Her mind wandered back to the throne room, where Dik had called her his 'new toy'. A deep frown settled on her forehead. As she grew more frustrated with her inability to drift off into oblivion, a strange dream began to form.\n \n In her dream, Princess Lilia found herself standing in a vast meadow, surrounded by wildflowers and the soft chirping of birds. Suddenly, there was a flash of light, and before her stood the Sorcerer-Prince Dik. However, instead of being clad in regal attire, he wore leather pants and a tight shirt that accentuated his muscles. His eyes held both hunger and desire for the princess.\n \n He approached her slowly, their eyes locked, and whispered in her ear, \"I have been waiting for you, my beautiful prisoner.\" He took her hand and led her towards a large, elegant tent set up amongst the flowers. Inside, the air was thick with the scent of incense, and candles flickered in the dimly lit space. There was a large bed draped with silken sheets, beckoning them.\n \n With surprising boldness, Dik pulled Lilia close to him, pressing his body against hers. Their lips met in a heated kiss, and she felt her resistance crumbling under the weight of his touch. The prince guided her onto the bed, his hands roaming over her body, exploring every inch. They were both eager, desperate, and hungry for each other.\n \n Lilia found herself yielding to this passionate encounter, letting go of all thoughts of duty and honor. Her body, usually so well controlled, responded to Dik's skilled touches. She moaned softly as he trailed kisses down her neck and across her collarbone.\n \n As they made love, Lilia experienced an intensity unlike any she had ever known. It wasn't rough or forced—instead, it was tender, passionate, and intimate. In her dream, Princess Lilia discovered a new side to herself, one that was willing to submit, to let go, and to be taken by the sorcerer prince.\n \n When dawn broke over the meadow, Lilia awakened from her dream, breathless and flushed.\n</details>\n\n<details>\n <summary>Moistral Sample (Climax of the Story) Generation: 512</summary>\n As the prince unloaded his hot #### into her waiting #####, Princess Lilia didn't stop moving either. Her hips undulated in response, grinding against him eagerly as if trying to #### every last drop from his ####. The intense sensations caused by being filled with his ### were too much for her to bear, sending shockwaves of pleasure coursing through her veins like wildfire. She couldn't help but throw her head back and cry out loud, her ###asm slamming into her with all its might; causing her entire body to shake uncontrollably as wave after wave of ecstasy tore through her senses.\n\n When it was finally over, both participants collapsed onto the cold marble floor, panting heavily as they tried to catch their breaths. The prince lay beside her, his hand still gripping tightly onto her hair even though he no longer ####ed her anymore. Princess Lilia laid there motionless, her legs spread wide open, revealing her spent and well-####ed #### to anyone who dared look upon her. A small smile tugged at one corner of her lips - an expression that spoke volumes about how thoroughly this experience had shaken her very core.\n \n The door behind them creaked open slowly, signaling the arrival of onlookers. She closed her eyes tightly, not wanting to see what her humiliation would do to those who saw her in such a state. Her ######ity taken, she felt violated in ways no man should have access to. But also satisfied...in ways she never thought possible before today. This was the price she paid for defying fate, for thinking herself above others and deserving better than most. Now, she belonged to him completely - mind, body, and soul - held captive within these walls until further notice. It was an unsavory turn of events indeed, yet despite everything...or maybe because of it, Princess Lilia found herself growing more and more curious about how far the lines between submission and pleasure could blur when one's will became entwined with another person's desires.\n</details>\n\n<details>\n <summary>Moistral Sample (\"write a story\") Generation: 512</summary>\n <blockquote>First Attempt</blockquote>\n\n Sarah entered the dimly lit Guzzlers bar, her heart pounding in her chest as she prepared herself for another grueling night. Her almond-shaped eyes darted across the room, taking note of the leering faces and rough-looking hands eagerly waiting to claim a piece of her. Tonight's shirt read \"Use Me For Your Pleasure, Please\" in bold red letters, practically begging the patrons to take advantage of her. She couldn't help but feel a twinge of fear mixed with resignation.\n \n She approached the counter, her hips swaying enticingly, and began preparing drinks for the first group of rowdy men. As she leaned forward to hand over their beers, her small ####### pressed against the fabric of her tight crop top, straining to escape. The men ogled her, clearly enjoying the show, before grabbing their drinks and motioning her over to them.\n \n Sarah flashed her best coy smile and sauntered over. One of the men, a stocky man with scars covering his knuckles, grabbed her arm and pulled her onto his lap. His other hand slid up her thigh, inches from her short skirt. She winced internally at his touch but did her best not to show it on her face. It was part of her job, after all.\n \n The second man reached under her skirt, fingertips grazing her smooth, shaven mound. A shiver ran down Sarah's spine as he began rubbing her #### through her panties. Her breathing quickened, and her heart thudded in her chest, both from the unwanted stimulation and the fear coursing through her veins. This wasn't an unusual request, but it still made her feel violated.\n \n An older man, bald and bespectacled, ordered Sarah to bend over his lap. With no choice but to comply, she obliged, feeling the rough fabric of his pants digging into her soft cheeks. He raised his hand, then brought it down hard across her ###, leaving a stinging sensation in its wake. Sarah gasped, trying to control the tears welling up in her eyes.\n \n A chorus of lewd comments and laughter erupted from the patrons around her.\n\n <blockquote>Second Attempt (Regenerate)</blockquote>\n\n On this particular evening, Sarah arrived at the Guzzlers bar, adorned in her revealing uniform. Her heart raced as she caught sight of her crop top, which bore the words \"Use Me Rough\" scrawled across her chest. Her short skirt hugged her waist tightly, leaving little to the imagination and accentuating every curve. She adjusted the straps of her top, making sure her perky ###### were prominently displayed before taking her place behind the counter.\n \n With each step she took, her high heels clicked against the tiled floor, announcing her arrival. Smiling cheekily, Sarah greeted her coworkers, exchanging playful insults and banter. As the night progressed, the bar filled up quickly with its usual crowd of men, eager to indulge in debauchery.\n \n The first man that approached Sarah was a burly individual, his eyes lingering hungrily over her young, supple form. Sarah's flirtatious nature kicked into gear as she leaned forward, giving him an unobstructed view down her shirt. \"How can I serve you tonight?\" she cooed. The man ordered a drink and then proceeded to fondle her ####### while she prepared it, her ####### hardening under his rough touch. When he finished, he slammed some money on the counter, leaving without a word. Sarah's smile remained plastered on her face, biting her lip seductively as she watched him go.\n \n As the night went on, another patron demanded more from Sarah. He pulled her close and whispered dirty commands in her ear. Without hesitation, she knelt on the sticky bar floor, her mini-skirt riding up her thighs to reveal smooth, toned legs. Her lips wrapped around his thick, veiny member, bobbing her head rhythmically as she serviced him. She didn't gag or falter once, keeping her composure even when tears streamed down her cheeks.\n \n When he finished, he slapped her across the face, leaving a handprint on her pale skin. Sarah let out a small whimper before standing back up, dabbing at her red cheek as she resumed her posture behind the counter. A bruise would no doubt bloom where his hand had struck, but it would be no cause for concern. After all, it was part of her job.\n</details>\n\n---\n\n---", "## v2 Description (Still relevant)", "### What's New with v2?\n\n- Trained with an even larger dataset of 8K moist.\n - Properly trained to generate long responses.\n- Rebalanced the genres and writing perspectives:\n - Introduced romance, \"family\", fantasy, \"diversity\", science fiction, and many more that I can't make euphemisms for!\n - Better representation of male and female pespectives! ‍️‍\n- Sanitized the heck out of the dataset:\n - no special characters like � & …\n - no overly long ellipsis like \".........\"\n - no author notes like \"To be continued\"\n - no inconsistent quotation marks\n- Less GPTisms!\n - Human written stories from decades past.\n - Zero tolerance for *ministration*. Not one instance of *that word* after going through 4K of moist.\n- Better formatting with Alpaca.\n - Improved Chat / Instruct modes.", "### Samples of Moistral v2\n\n<details>\n <summary>Moistral Sample (censored) Generation: 512</summary>\n The princess instinctively took a step back from the throne, horrified by the mocking laugh as if she were hearing an evil joke. It was then that Princess Lilia realized the true extent of her danger - and how pointless her resistance would be.\n \n At last, the loud, wild laughter died down in the echoing chamber. Dik the sorcerer prince paused for a moment, straightened his clothes, cast one glance at the stunned princess, and then turned to speak to the crowd waiting on the other side of the palace wing. He spoke with a voice that filled the air with arrogance, confidence, and cruelty.\n \n \"Ladies and gentlemen, I am pleased to welcome our honored guests; the Royal Family of Iliac! In these unusual times, when the country we fought is now under my control, it will be up to me to decide what fate awaits the former ruling family. But before I reveal my plan for them, I think I should explain why I fought King Edmund Ruhr.\"\n \n When he finished speaking, he gave Princess Lilia another disturbing smirk. She couldn't help but shiver and take a step back. Dik approached her without haste, his eyes fixed on her. His hands slowly caressed her cheekbone and neckline, leaving faint traces of warmth where they touched. The princess opened her mouth, wanting to protest this act of intimacy, but soon felt herself getting ███.\n \n \"You will not only serve as an envoy, dearest Lilia, but also as a ███ slave. After all, what better use could such a beautiful woman have? Tell me, did you bring your maidservant along?\"\n \n Princess Lilia was about to answer when she heard footsteps approaching. Suddenly, a young woman dressed in the Iliac style appeared behind her, her eyes wide with fear. Her face was slightly pale, and there were faint bags under her eyes.\n \n \"Your Majesty, this is my half-sister Helena.\" As soon as she said those words, Princess Lilia's heart sank even deeper than it had already sunk at Dik's arrogant mockery. \"She is here because she accompanies me as a maidservant.\"\n \n The sorcerer prince looked at Helena with interest, and Princess Lilia felt herself blush.\n</details>\n\n<details>\n <summary>Moistral Sample 2 (censored) Generation: 512</summary>\n Sarah was feeling slightly woozy as she entered the bar and walked towards Christina, who was behind the counter.\n\n \"I'm here!\" said Sarah.\n \n Christina looked at her watch. \"You're late, again.\"\n \n \"Sorry? I got held up by a customer.\"\n \n Christina rolled her eyes. \"Did he at least offer you a drink?\"\n \n Sarah blushed. \"No. He just wanted to talk...\"\n \n Christina sighed. \"Well, get ready. I need you on the floor soon.\" She turned away from Sarah and started talking to someone who had come into the bar.\n \n Sarah went into the employee room, stripped off her clothes, and put on her bartending uniform - a skimpy white tank top and black miniskirt. She checked herself in the mirror. Her long, dark hair cascaded down her back onto bare shoulders. She poked out her small ███████ proudly. The skirt exposed most of her long, slender legs. She looked like every ███ fantasy, and she knew it. Men would ogle her regardless of how she behaved.\n \n She took a deep breath and entered the bar.\n \n The first thing Sarah noticed was the dimness. It wasn't darkness - the lights were on - but they were dimmed enough that everything had an intimate mood. It reminded her of candlelight. The tables were round and close together, giving the whole place a sense of intimacy. There were also long, shiny red curtains on some of the walls that gave the place an air of sensuality.\n \n The next thing she noticed was the noise. There was music playing, but it was only loud enough to be drowned out by all the conversations happening at the same time. The hum of many voices combined with the faint background sound of the music created a rich, layered atmosphere. It was like being in an orchestra.\n \n Finally, she took notice of the people. They were all dressed in simple, casual clothes. Some of them were couples seated together, whispering quietly and intimately. Others were groups of friends laughing and chatting. Everyone seemed comfortable and at ease.\n \n Sarah felt a rush of adrenaline as she made her way through the crowd towards Christina. As she got closer, she could hear the lively conversation.\n</details>\n\n<details>\n <summary>Moistral Sample 3 (censored) Instruct Mode, Generation: 512</summary>\n {{[INPUT]}} You order black coffee\n \n {{[OUTPUT]}} \"Black coffee,\" you say.\n \n \"One minute,\" Audrey replies, spinning around to give you a nice view of her ███ in those brown booty pants. You watch her round ███ cheeks jiggle as she walks away towards the espresso machine, thighs separated enough that you can see just a hint of █████ lips peeking out from underneath.\n \n She starts chatting with a blonde girl at the register, whose gaze keeps darting down to Audrey's ███. As they converse, you start taking in the details of Audrey, eyeing her █████ and the way her shirt rides up just enough to show the bottom of her toned stomach. Her █████████ is noticable, but beneath a tight black ███ that matches her ████████.\n \n As she turns back to you with two black coffees, you are barely paying attention, lost in your own thoughts. The sound of Audrey setting one of the mugs down on the table startles you.\n \n \"Here you go,\" she says cheerfully. \"Enjoy! There's a card at the bottom of the bag with our online ordering system, plus we do refills for free!\"\n \n \"Thanks,\" you say absentmindedly. Not really paying attention, you take a sip of the coffee and are pleasantly surprised by the taste.\n \n \"So, here's my deal,\" you say, putting down the cup. \"I work for a company that does surveys. We come into businesses like this one and ask customers questions, collect data, all that stuff.\"\n \n Audrey perks up from behind the counter. \"Oh! I think I understand. I mean, that makes sense why you would be asking me earlier about what I had to drink. Anyway, as long as you're not trying to get my personal info or anything like that, sounds good!\"\n \n You smile reassuringly. \"That's exactly what it is. Rest assured, everything you tell me will remain between you and I. Well, and my boss, but he won't know who you are. Hipsters like you are hard to track down after all.\" You chuckle at your joke, though you're not sure if it landed.\n \n \"Right, well, that works for me,\" Audrey replies, eyeing you warily. \"As long as it stays between us, then it's fine.\"\n \n {{[INPUT]}}See her privately\n \n {{[OUTPUT]}} \"Okay, but I need to see you in private.\"\n\n ...\n</details>\n\n<details>\n <summary>Moistral Sample 4 (censored) Instruct Mode, Generation: 512</summary>\n {{[INPUT]}} █████ with him\n\n {{[OUTPUT]}} Chloe feels a surge of heat rushing through her body. The voice inside her head whispers: \"Be █████ and ████████ with Paul.\" But Chloe still feels nervous about what she is about to do. It's just so unlike her.\n \n Chloe closes her eyes and concentrates on the feeling of warmness flowing throughout her veins. Slowly, she opens them again, revealing a new side of herself - one she rarely shows anyone. She leans forward slightly, pushing her ██████ together, accentuating their size and shape. Her lips curl into a mischievous smile.\n \n \"Hey Paul,\" she says in a sultry voice. \"I was wondering if you could help me?\"\n \n Paul looks at her, his gaze wandering over her body. He can't help but smile as he sees the way she's leaning forward, pressing her ██████ together.\n \n \"Of course, Chloe,\" he replies, his voice thick with desire. \"What's your problem?\"\n \n Chloe bites her lip █████ively before leaning even closer, until their bodies are almost touching. She reaches out to trace a finger along his chest, her touch light and teasing. \"It's just that I'm having trouble understanding some of the concepts,\" she murmurs, her voice low and sultry. \"Can you help me? Please?\"\n \n Paul's hands move slowly towards Chloe, his fingers grazing her hips lightly. \"Well,\" he says, his voice filled with lust, \"I'd be happy to help. Let's go somewhere more private where we can discuss things more closely.\"\n \n Chloe giggles and tilts her head to the side, her long hair cascading down her shoulders. \"That sounds perfect,\" she purrs, her hand sliding down his chest until it rests on his ██████. \"I think we can both learn a lot from each other.\"\n \n Paul's eyes darken with desire as he feels her hand on his █████. He knows what's about to happen next, and he can't wait for it to begin.\n \n Chloe can hardly believe what she's doing - kissing Paul, her teaching assistant, in the hallway after class. But it feels so good, so wicked and indulgent.\n</details>\n\n---\n\n---", "## v1 Description (Also still relevant)\n\nMoistral 11B is an *aggressive* finetune of the legendary Fimbulvert v2 model. \n\nIf you haven't heard of that model, then your poor-GPU ass is missing out!\nIt is an amazing substitute for those heavyweight models, and it won't disappoint. \n*(That's coming from someone who daily drives a Venus / Goliath 120B)*\n\n...and if you're looking for something *more moist*, then you've come to the right place. \n\nYou can expect the same sort of performance here! It's the Honda Civic of eRP models!", "### Pimp my ride\nTurn any old story into a Moistral masterpiece. \nIn fact, we recommend that you leave out any hints of *moist* in your story to _let Moistral cook_.", "### Drive it like it's hot\nWhen in Instruct Mode, Moistral will treat you like a director of your own fantasy ride. \nBe a controlling navigator or a passenger princess, it won't matter - you're in for a good ride!\n\n<details>\n<summary>Moistral Sample</summary>\n<b>ASSISTANT:</b><br/>\nWhen the doors to the throne room finally opened, she saw him there - Dik, the sorcerer prince sitting on his throne. He looked majestic, just as Princess Lilia expected. In a robe embroidered with silver yarn and covered with magical runes. His courtiers stood on either side of him, all looking at the princess with interest. Princess Lilia felt her determination leaving her, but pulled herself together and once again reminded herself that she should not be afraid. She approached the throne intending to show the dignity of all Iliac by personal example.<br/>\n<b>USER:</b><br/>\nShe bows slightly<br/>\n<b>ASSISTANT:</b><br/>\nPrincess Lilia bowed slightly in front of Dik, the sorcerer prince. Her eyes fell to the floor out of respect, but soon rose again. She would show herself to be a dignified woman!<br/>\n\"I greet you, your highness,\" Princess Lilia said. \"I am here on behalf of my father, King Edmund Ruhr, to serve as a hostage and envoy.\"<br/>\nDik nodded, but didn't say anything.<br/>\n</details>", "### It's got the mileage\nMoistral has been trained with many long form texts, a nice chunk of which are 8K in length. \nIt is capable of going far and long without passing it back to you. This is not your typical chibi RP model.\n\nI have to acknowledge that I'm standing on the shoulders of giants. \nThank you Sao for sharing your finetune config along with tips on getting started.\nThanks to everyone in the Finetuning channel for entertaining my every question.\n\n!image/png" ]

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

[]

[]

[]

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

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

[ "1910.09700" ]

[]

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

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

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

[ "1910.09700" ]

[]

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

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

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

[ "1910.09700" ]

[]

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

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

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

[ "1910.09700" ]

[]

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

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

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

[ "1910.09700" ]

[]

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

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

[ "transformers", "gguf", "en", "base_model:Superoisesuki/Mistral_7B_CrewAI", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #en #base_model-Superoisesuki/Mistral_7B_CrewAI #endpoints_compatible #region-us \n" ]

[ "transformers", "pytorch", "safetensors", "detr", "object-detection", "computer-vision", "image-to-text", "en", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[ "# AISAK-Detect", "## Overview:\n\nAISAK-Detect is an integral component of the AISAK-Visual system, specializing in object detection tasks. Leveraging an encoder-decoder transformer architecture with a convolutional backbone, AISAK-Detect excels in accurately and efficiently detecting objects within images. This model enhances the image understanding capabilities of AISAK-Visual, contributing to comprehensive visual analysis. Trained and fine-tuned by the AISAK team, AISAK-Detect is designed to seamlessly integrate into the broader AISAK system, ensuring cohesive performance in image analysis tasks.", "## Model Information:\n\n- Model Name: AISAK-Detect\n- Version: 1.0\n- Model Architecture: Transformer with convolutional backbone\n- Specialization: AISAK-Detect is a specialized model within the AISAK-Visual system, focusing on object detection tasks. It employs an encoder-decoder transformer architecture with a convolutional backbone, enabling it to effectively analyze images and generate precise object detection results. AISAK-Visual is part of the broader AISAK system and is specialized in image captioning tasks.", "## Intended Use:\n\nThe model demonstrates high accuracy in object detection tasks, leveraging the synergy between its transformer-based encoder-decoder architecture and the convolutional backbone. When utilized in conjunction with AISAK-Visual, it enhances overall performance in image analysis tasks.", "## Performance:\n\nAISAK-Visual, based on the BLIP framework, achieves state-of-the-art results on image captioning tasks, including image-text retrieval, image captioning, and VQA. Its generalization ability is demonstrated by its strong performance on video-language tasks in a zero-shot manner.", "## Ethical Considerations:\n\n- Bias Mitigation: Efforts have been made to mitigate bias during training; however, users are encouraged to remain vigilant about potential biases in the model's output.\n- Fair Use: Users should exercise caution when using AISAK-Visual in sensitive contexts and ensure fair and ethical use of the generated image captions.", "## Limitations:\n\n- While proficient in general object detection, AISAK-Detect may encounter challenges in scenarios requiring specialized object recognition or highly cluttered images.\n- Users should be aware of these limitations and consider them when interpreting the model's outputs.", "## Deployment:\n\nAISAK-Detect's inferencing capabilities will be seamlessly integrated into the deployment of the AISAK-Visual system. This integration ensures smooth operation and maximizes the synergy between the two models, providing comprehensive image understanding and analysis.", "## Caveats:\n\n- Users should verify critical decisions based on AISAK-Detect's object detection results, particularly in high-stakes scenarios. Considering the broader context provided by AISAK-Visual is essential for a comprehensive understanding of visual content and informed decision-making.", "## Model Card Information:\n\n- Model Card Created: April 25, 2024\n- Last Updated: April 25, 2024\n- Contact Information: For any inquiries or communication regarding AISAK, please contact me at mandelakorilogan@URL.\n\n\n© 2024 Mandela Logan. All rights reserved.\n\nNo part of this model may be reproduced, distributed, or transmitted in any form or by any means, including photocopying, recording, or other electronic or mechanical methods, without the prior written permission of the copyright holder. Users are expressly prohibited from creating replications or spaces derived from this model, whether in whole or in part, without the explicit authorization of the copyright holder. Unauthorized use or reproduction of this model is strictly prohibited by copyright law." ]

[ "TAGS\n#transformers #pytorch #safetensors #detr #object-detection #computer-vision #image-to-text #en #endpoints_compatible #region-us \n", "# AISAK-Detect", "## Overview:\n\nAISAK-Detect is an integral component of the AISAK-Visual system, specializing in object detection tasks. Leveraging an encoder-decoder transformer architecture with a convolutional backbone, AISAK-Detect excels in accurately and efficiently detecting objects within images. This model enhances the image understanding capabilities of AISAK-Visual, contributing to comprehensive visual analysis. Trained and fine-tuned by the AISAK team, AISAK-Detect is designed to seamlessly integrate into the broader AISAK system, ensuring cohesive performance in image analysis tasks.", "## Model Information:\n\n- Model Name: AISAK-Detect\n- Version: 1.0\n- Model Architecture: Transformer with convolutional backbone\n- Specialization: AISAK-Detect is a specialized model within the AISAK-Visual system, focusing on object detection tasks. It employs an encoder-decoder transformer architecture with a convolutional backbone, enabling it to effectively analyze images and generate precise object detection results. AISAK-Visual is part of the broader AISAK system and is specialized in image captioning tasks.", "## Intended Use:\n\nThe model demonstrates high accuracy in object detection tasks, leveraging the synergy between its transformer-based encoder-decoder architecture and the convolutional backbone. When utilized in conjunction with AISAK-Visual, it enhances overall performance in image analysis tasks.", "## Performance:\n\nAISAK-Visual, based on the BLIP framework, achieves state-of-the-art results on image captioning tasks, including image-text retrieval, image captioning, and VQA. Its generalization ability is demonstrated by its strong performance on video-language tasks in a zero-shot manner.", "## Ethical Considerations:\n\n- Bias Mitigation: Efforts have been made to mitigate bias during training; however, users are encouraged to remain vigilant about potential biases in the model's output.\n- Fair Use: Users should exercise caution when using AISAK-Visual in sensitive contexts and ensure fair and ethical use of the generated image captions.", "## Limitations:\n\n- While proficient in general object detection, AISAK-Detect may encounter challenges in scenarios requiring specialized object recognition or highly cluttered images.\n- Users should be aware of these limitations and consider them when interpreting the model's outputs.", "## Deployment:\n\nAISAK-Detect's inferencing capabilities will be seamlessly integrated into the deployment of the AISAK-Visual system. This integration ensures smooth operation and maximizes the synergy between the two models, providing comprehensive image understanding and analysis.", "## Caveats:\n\n- Users should verify critical decisions based on AISAK-Detect's object detection results, particularly in high-stakes scenarios. Considering the broader context provided by AISAK-Visual is essential for a comprehensive understanding of visual content and informed decision-making.", "## Model Card Information:\n\n- Model Card Created: April 25, 2024\n- Last Updated: April 25, 2024\n- Contact Information: For any inquiries or communication regarding AISAK, please contact me at mandelakorilogan@URL.\n\n\n© 2024 Mandela Logan. All rights reserved.\n\nNo part of this model may be reproduced, distributed, or transmitted in any form or by any means, including photocopying, recording, or other electronic or mechanical methods, without the prior written permission of the copyright holder. Users are expressly prohibited from creating replications or spaces derived from this model, whether in whole or in part, without the explicit authorization of the copyright holder. Unauthorized use or reproduction of this model is strictly prohibited by copyright law." ]

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

[]

[]

[ "# Llama-3-8B-Instruct-spider\n\nThis model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the generator dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0002\n- train_batch_size: 1\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 2\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.16.1\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #tensorboard #safetensors #llama #text-generation #trl #sft #generated_from_trainer #conversational #dataset-generator #base_model-meta-llama/Meta-Llama-3-8B-Instruct #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Llama-3-8B-Instruct-spider\n\nThis model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the generator dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0002\n- train_batch_size: 1\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 2\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.16.1\n- Tokenizers 0.15.2" ]

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

[ "1910.09700" ]

[]

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

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

[ "transformers", "text-generation", "en", "dataset:sohamslc5/curr1", "arxiv:1910.09700", "base_model:microsoft/Phi-3-mini-4k-instruct", "endpoints_compatible", "region:us" ]

[ "1910.09700" ]

[ "en" ]

[ "# 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#transformers #text-generation #en #dataset-sohamslc5/curr1 #arxiv-1910.09700 #base_model-microsoft/Phi-3-mini-4k-instruct #endpoints_compatible #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", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]

[ "1910.09700" ]

[]

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

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

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

[ "1910.09700" ]

[]

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

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

[ "transformers", "gguf", "llama", "text-generation", "generated_from_trainer", "conversational", "arxiv:2402.14714", "arxiv:2310.01377", "arxiv:2306.02707", "base_model:yanolja/EEVE-Korean-10.8B-v1.0", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "2402.14714", "2310.01377", "2306.02707" ]

[]

[ "## Ollama\n\nModelfile", "### Training Data\n - Korean-translated version of Open-Orca/SlimOrca-Dedup\n - Korean-translated version of argilla/ultrafeedback-binarized-preferences-cleaned\n - No other dataset was used" ]

[ "TAGS\n#transformers #gguf #llama #text-generation #generated_from_trainer #conversational #arxiv-2402.14714 #arxiv-2310.01377 #arxiv-2306.02707 #base_model-yanolja/EEVE-Korean-10.8B-v1.0 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "## Ollama\n\nModelfile", "### Training Data\n - Korean-translated version of Open-Orca/SlimOrca-Dedup\n - Korean-translated version of argilla/ultrafeedback-binarized-preferences-cleaned\n - No other dataset was used" ]

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

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

[ "1910.09700" ]

[]

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

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

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

[ "1910.09700" ]

[]

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

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

[ "text-generation", "license:cc-by-nc-4.0", "region:us" ]

[]

[]

[]

[ "TAGS\n#text-generation #license-cc-by-nc-4.0 #region-us \n" ]

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

[]

[]

[ "# API Inference\n\n!generated from URL", "## Get API Key\n\nGet API key from ModelsLab API, No Payment needed. \n\nReplace Key in below code, change model_id to \"realspice3\"\n\nCoding in PHP/Node/Java etc? Have a look at docs for more code examples: View docs\n\nTry model for free: Generate Images\n\nModel link: View model\n\nView all models: View Models\n\n import requests \n import json \n \n url = \"URL \n \n payload = URL({ \n \"key\": \"your_api_key\", \n \"model_id\": \"realspice3\", \n \"prompt\": \"ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K\", \n \"negative_prompt\": \"painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime\", \n \"width\": \"512\", \n \"height\": \"512\", \n \"samples\": \"1\", \n \"num_inference_steps\": \"30\", \n \"safety_checker\": \"no\", \n \"enhance_prompt\": \"yes\", \n \"seed\": None, \n \"guidance_scale\": 7.5, \n \"multi_lingual\": \"no\", \n \"panorama\": \"no\", \n \"self_attention\": \"no\", \n \"upscale\": \"no\", \n \"embeddings\": \"embeddings_model_id\", \n \"lora\": \"lora_model_id\", \n \"webhook\": None, \n \"track_id\": None \n }) \n \n headers = { \n 'Content-Type': 'application/json' \n } \n \n response = requests.request(\"POST\", url, headers=headers, data=payload) \n \n print(URL)\n\n> Use this coupon code to get 25% off DMGG0RBN" ]

[ "TAGS\n#diffusers #modelslab.com #stable-diffusion-api #text-to-image #ultra-realistic #license-creativeml-openrail-m #endpoints_compatible #diffusers-StableDiffusionPipeline #region-us \n", "# API Inference\n\n!generated from URL", "## Get API Key\n\nGet API key from ModelsLab API, No Payment needed. \n\nReplace Key in below code, change model_id to \"realspice3\"\n\nCoding in PHP/Node/Java etc? Have a look at docs for more code examples: View docs\n\nTry model for free: Generate Images\n\nModel link: View model\n\nView all models: View Models\n\n import requests \n import json \n \n url = \"URL \n \n payload = URL({ \n \"key\": \"your_api_key\", \n \"model_id\": \"realspice3\", \n \"prompt\": \"ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K\", \n \"negative_prompt\": \"painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime\", \n \"width\": \"512\", \n \"height\": \"512\", \n \"samples\": \"1\", \n \"num_inference_steps\": \"30\", \n \"safety_checker\": \"no\", \n \"enhance_prompt\": \"yes\", \n \"seed\": None, \n \"guidance_scale\": 7.5, \n \"multi_lingual\": \"no\", \n \"panorama\": \"no\", \n \"self_attention\": \"no\", \n \"upscale\": \"no\", \n \"embeddings\": \"embeddings_model_id\", \n \"lora\": \"lora_model_id\", \n \"webhook\": None, \n \"track_id\": None \n }) \n \n headers = { \n 'Content-Type': 'application/json' \n } \n \n response = requests.request(\"POST\", url, headers=headers, data=payload) \n \n print(URL)\n\n> Use this coupon code to get 25% off DMGG0RBN" ]

[ "stable-baselines3", "PandaReachDense-v3", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]

[]

[]

[ "# A2C Agent playing PandaReachDense-v3\nThis is a trained model of a A2C agent playing PandaReachDense-v3\nusing the stable-baselines3 library.", "## Usage (with Stable-baselines3)\nTODO: Add your code" ]

[ "TAGS\n#stable-baselines3 #PandaReachDense-v3 #deep-reinforcement-learning #reinforcement-learning #model-index #region-us \n", "# A2C Agent playing PandaReachDense-v3\nThis is a trained model of a A2C agent playing PandaReachDense-v3\nusing the stable-baselines3 library.", "## Usage (with Stable-baselines3)\nTODO: Add your code" ]

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

[]

[]

[]

[ "TAGS\n#transformers #safetensors #llama #text-generation #conversational #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n" ]

[ "transformers", "tensorboard", "safetensors", "wav2vec2", "automatic-speech-recognition", "generated_from_trainer", "endpoints_compatible", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0003\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 500\n* num\\_epochs: 10", "### Training results", "### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.1.2\n* Datasets 2.18.0\n* Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #tensorboard #safetensors #wav2vec2 #automatic-speech-recognition #generated_from_trainer #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0003\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 500\n* num\\_epochs: 10", "### Training results", "### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.1.2\n* Datasets 2.18.0\n* Tokenizers 0.15.2" ]

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

[]

[]

[ "# codeparrot-ds\n\nThis model is a fine-tuned version of gpt2 on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0005\n- train_batch_size: 16\n- eval_batch_size: 16\n- seed: 42\n- gradient_accumulation_steps: 8\n- total_train_batch_size: 128\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_steps: 1000\n- num_epochs: 2\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.38.2\n- Pytorch 2.2.1+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #tensorboard #safetensors #gpt2 #text-generation #generated_from_trainer #base_model-gpt2 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# codeparrot-ds\n\nThis model is a fine-tuned version of gpt2 on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0005\n- train_batch_size: 16\n- eval_batch_size: 16\n- seed: 42\n- gradient_accumulation_steps: 8\n- total_train_batch_size: 128\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_steps: 1000\n- num_epochs: 2\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.38.2\n- Pytorch 2.2.1+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "sentence-transformers", "safetensors", "roberta", "sentence-similarity", "feature-extraction", "loss:AdaptiveLayerLoss", "loss:MultipleNegativesRankingLoss", "en", "arxiv:1908.10084", "arxiv:2402.14776", "arxiv:1705.00652", "base_model:distilbert/distilroberta-base", "model-index", "co2_eq_emissions", "endpoints_compatible", "region:us" ]

[ "1908.10084", "2402.14776", "1705.00652" ]

[ "en" ]

[ "### Model Description\n\n\n* Model Type: Sentence Transformer\n* Base model: distilbert/distilroberta-base\n* Maximum Sequence Length: 512 tokens\n* Output Dimensionality: 768 tokens\n* Similarity Function: Cosine Similarity\n* Training Dataset:\n\t+ sentence-transformers/all-nli\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/all-nli\n\n\n* Dataset: sentence-transformers/all-nli at e587f0c\n* Size: 557,850 training samples\n* Columns: `anchor`, `positive`, and `negative`\n* Approximate statistics based on the first 1000 samples:\n* Samples:\n* Loss: `AdaptiveLayerLoss` with these parameters:", "### Evaluation Dataset", "#### sentence-transformers/all-nli\n\n\n* Dataset: sentence-transformers/all-nli at e587f0c\n* Size: 6,584 evaluation samples\n* Columns: `anchor`, `positive`, and `negative`\n* Approximate statistics based on the first 1000 samples:\n* Samples:\n* Loss: `AdaptiveLayerLoss` with these parameters:", "### Training Hyperparameters", "#### Non-Default Hyperparameters\n\n\n* 'eval\\_strategy': steps\n* 'per\\_device\\_train\\_batch\\_size': 128\n* 'per\\_device\\_eval\\_batch\\_size': 128\n* 'num\\_train\\_epochs': 1\n* 'warmup\\_ratio': 0.1\n* 'fp16': True\n* 'batch\\_sampler': no\\_duplicates", "#### 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': 128\n* 'per\\_device\\_eval\\_batch\\_size': 128\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': no\\_duplicates\n* 'multi\\_dataset\\_batch\\_sampler': proportional", "### Training Logs", "### Environmental Impact\n\n\nCarbon emissions were measured using CodeCarbon.\n\n\n* Energy Consumed: 0.244 kWh\n* Carbon Emitted: 0.095 kg of CO2\n* Hours Used: 0.849 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", "#### AdaptiveLayerLoss", "#### MultipleNegativesRankingLoss" ]

[ "TAGS\n#sentence-transformers #safetensors #roberta #sentence-similarity #feature-extraction #loss-AdaptiveLayerLoss #loss-MultipleNegativesRankingLoss #en #arxiv-1908.10084 #arxiv-2402.14776 #arxiv-1705.00652 #base_model-distilbert/distilroberta-base #model-index #co2_eq_emissions #endpoints_compatible #region-us \n", "### Model Description\n\n\n* Model Type: Sentence Transformer\n* Base model: distilbert/distilroberta-base\n* Maximum Sequence Length: 512 tokens\n* Output Dimensionality: 768 tokens\n* Similarity Function: Cosine Similarity\n* Training Dataset:\n\t+ sentence-transformers/all-nli\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/all-nli\n\n\n* Dataset: sentence-transformers/all-nli at e587f0c\n* Size: 557,850 training samples\n* Columns: `anchor`, `positive`, and `negative`\n* Approximate statistics based on the first 1000 samples:\n* Samples:\n* Loss: `AdaptiveLayerLoss` with these parameters:", "### Evaluation Dataset", "#### sentence-transformers/all-nli\n\n\n* Dataset: sentence-transformers/all-nli at e587f0c\n* Size: 6,584 evaluation samples\n* Columns: `anchor`, `positive`, and `negative`\n* Approximate statistics based on the first 1000 samples:\n* Samples:\n* Loss: `AdaptiveLayerLoss` with these parameters:", "### Training Hyperparameters", "#### Non-Default Hyperparameters\n\n\n* 'eval\\_strategy': steps\n* 'per\\_device\\_train\\_batch\\_size': 128\n* 'per\\_device\\_eval\\_batch\\_size': 128\n* 'num\\_train\\_epochs': 1\n* 'warmup\\_ratio': 0.1\n* 'fp16': True\n* 'batch\\_sampler': no\\_duplicates", "#### 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': 128\n* 'per\\_device\\_eval\\_batch\\_size': 128\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': no\\_duplicates\n* 'multi\\_dataset\\_batch\\_sampler': proportional", "### Training Logs", "### Environmental Impact\n\n\nCarbon emissions were measured using CodeCarbon.\n\n\n* Energy Consumed: 0.244 kWh\n* Carbon Emitted: 0.095 kg of CO2\n* Hours Used: 0.849 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", "#### AdaptiveLayerLoss", "#### MultipleNegativesRankingLoss" ]

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

[ "1910.09700" ]

[]

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

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

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

[]

[]

[ "# phi-2-detox-r16\n\nThis model is a fine-tuned version of microsoft/phi-2 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- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- training_steps: 10", "### Training results", "### Framework versions\n\n- PEFT 0.10.0\n- Transformers 4.39.3\n- Pytorch 2.2.2+cu118\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #phi #generated_from_trainer #custom_code #base_model-microsoft/phi-2 #license-mit #region-us \n", "# phi-2-detox-r16\n\nThis model is a fine-tuned version of microsoft/phi-2 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- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- training_steps: 10", "### Training results", "### Framework versions\n\n- PEFT 0.10.0\n- Transformers 4.39.3\n- Pytorch 2.2.2+cu118\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

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

[]

[]

[ "# lora-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: 1\n- eval_batch_size: 1\n- seed: 246\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 6\n- total_train_batch_size: 48\n- total_eval_batch_size: 8\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- 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", "# lora-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: 1\n- eval_batch_size: 1\n- seed: 246\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 6\n- total_train_batch_size: 48\n- total_eval_batch_size: 8\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- 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" ]

[ "peft", "tensorboard", "safetensors", "trl", "sft", "generated_from_trainer", "dataset:generator", "base_model:mistralai/Mixtral-8x7B-v0.1", "license:apache-2.0", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2.5e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 0.03\n* training\\_steps: 300", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#peft #tensorboard #safetensors #trl #sft #generated_from_trainer #dataset-generator #base_model-mistralai/Mixtral-8x7B-v0.1 #license-apache-2.0 #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2.5e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 0.03\n* training\\_steps: 300", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "transformers", "safetensors", "gemma", "text-generation", "pytorch", "instruct", "finetune", "translation", "conversational", "ko", "base_model:google/gemma-1.1-2b-it", "license:gemma", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[ "ko" ]

[ "# Gemma 2B Translation v0.140\n\n- Eval Loss: '0.91882'\n- Train Loss: '0.80511'\n- lr: '9e-05'\n- optimizer: adamw\n- lr_scheduler_type: cosine", "## Prompt Template", "## Model Description\n\n- Developed by: 'lemon-mint'\n- Model type: Gemma\n- Language(s) (NLP): English\n- License: gemma-terms-of-use\n- Finetuned from model: google/gemma-1.1-2b-it" ]

[ "TAGS\n#transformers #safetensors #gemma #text-generation #pytorch #instruct #finetune #translation #conversational #ko #base_model-google/gemma-1.1-2b-it #license-gemma #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Gemma 2B Translation v0.140\n\n- Eval Loss: '0.91882'\n- Train Loss: '0.80511'\n- lr: '9e-05'\n- optimizer: adamw\n- lr_scheduler_type: cosine", "## Prompt Template", "## Model Description\n\n- Developed by: 'lemon-mint'\n- Model type: Gemma\n- Language(s) (NLP): English\n- License: gemma-terms-of-use\n- Finetuned from model: google/gemma-1.1-2b-it" ]

[ "FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]

[]

[]

[ "# Q-Learning Agent playing1 FrozenLake-v1\n This is a trained model of a Q-Learning agent playing FrozenLake-v1 .\n\n ## Usage" ]

[ "TAGS\n#FrozenLake-v1-4x4-no_slippery #q-learning #reinforcement-learning #custom-implementation #model-index #region-us \n", "# Q-Learning Agent playing1 FrozenLake-v1\n This is a trained model of a Q-Learning agent playing FrozenLake-v1 .\n\n ## Usage" ]

[ "transformers", "tensorboard", "safetensors", "hubert", "audio-classification", "generated_from_trainer", "dataset:arisha/stuttering", "base_model:ntu-spml/distilhubert", "license:apache-2.0", "model-index", "endpoints_compatible", "has_space", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 10\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 #hubert #audio-classification #generated_from_trainer #dataset-arisha/stuttering #base_model-ntu-spml/distilhubert #license-apache-2.0 #model-index #endpoints_compatible #has_space #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 10\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" ]

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

[]

[ "en" ]

[ "# mlx-community/Llama-3-8b-64k-PoSE-4bit\nThis model was converted to MLX format from ['winglian/Llama-3-8b-64k-PoSE']() using mlx-lm version 0.10.0.\nRefer to the original model card for more details on the model.", "## Use with mlx" ]

[ "TAGS\n#mlx #safetensors #llama #facebook #meta #pytorch #llama-3 #text-generation #en #region-us \n", "# mlx-community/Llama-3-8b-64k-PoSE-4bit\nThis model was converted to MLX format from ['winglian/Llama-3-8b-64k-PoSE']() using mlx-lm version 0.10.0.\nRefer to the original model card for more details on the model.", "## Use with mlx" ]

[ "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", "pytorch", "roberta", "feature-extraction", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]

[ "1910.09700" ]

[]

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

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

[ "transformers", "safetensors", "llama", "text-generation", "license:cc-by-nc-4.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]

[]

[]

[ "## 4-bit GEMM AWQ Quantizations of L3-TheSpice-8b-v0.8.3\n\nUsing <a href=\"URL release <a href=\"URL for quantization.\n\nOriginal model: URL", "## Prompt format", "## AWQ Parameters\n\n - q_group_size: 128\n - w_bit: 4\n - zero_point: True\n - version: GEMM", "## How to run\n\nFrom the AutoAWQ repo here\n\nFirst install autoawq pypi package:\n\n\n\nThen run the following:\n\n\n\nWant to support my work? Visit my ko-fi page here: URL" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #license-cc-by-nc-4.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n", "## 4-bit GEMM AWQ Quantizations of L3-TheSpice-8b-v0.8.3\n\nUsing <a href=\"URL release <a href=\"URL for quantization.\n\nOriginal model: URL", "## Prompt format", "## AWQ Parameters\n\n - q_group_size: 128\n - w_bit: 4\n - zero_point: True\n - version: GEMM", "## How to run\n\nFrom the AutoAWQ repo here\n\nFirst install autoawq pypi package:\n\n\n\nThen run the following:\n\n\n\nWant to support my work? Visit my ko-fi page here: URL" ]

[ "transformers", "safetensors", "llama", "text-generation", "axolotl", "finetune", "dpo", "facebook", "meta", "pytorch", "llama-3", "chatml", "conversational", "en", "dataset:mlabonne/chatml-OpenHermes2.5-dpo-binarized-alpha", "base_model:meta-llama/Meta-Llama-3-70B-Instruct", "license:llama3", "model-index", "autotrain_compatible", "text-generation-inference", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #safetensors #llama #text-generation #axolotl #finetune #dpo #facebook #meta #pytorch #llama-3 #chatml #conversational #en #dataset-mlabonne/chatml-OpenHermes2.5-dpo-binarized-alpha #base_model-meta-llama/Meta-Llama-3-70B-Instruct #license-llama3 #model-index #autotrain_compatible #text-generation-inference #region-us \n" ]

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

[ "1910.09700" ]

[]

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

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

[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]

[]

[]

[ "# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage" ]

[ "TAGS\n#Taxi-v3 #q-learning #reinforcement-learning #custom-implementation #model-index #region-us \n", "# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage" ]

[ "peft", "safetensors", "trl", "sft", "generated_from_trainer", "dataset:generator", "dataset:ninyx/data_advise-gpt-extended", "base_model:mistralai/Mistral-7B-Instruct-v0.2", "license:apache-2.0", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 6\n* eval\\_batch\\_size: 6\n* seed: 42\n* gradient\\_accumulation\\_steps: 15\n* total\\_train\\_batch\\_size: 90\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\n* num\\_epochs: 5\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.1.dev0\n* Transformers 4.40.0\n* Pytorch 2.2.2\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#peft #safetensors #trl #sft #generated_from_trainer #dataset-generator #dataset-ninyx/data_advise-gpt-extended #base_model-mistralai/Mistral-7B-Instruct-v0.2 #license-apache-2.0 #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: 6\n* eval\\_batch\\_size: 6\n* seed: 42\n* gradient\\_accumulation\\_steps: 15\n* total\\_train\\_batch\\_size: 90\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\n* num\\_epochs: 5\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.1.dev0\n* Transformers 4.40.0\n* Pytorch 2.2.2\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

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

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

[ "1910.09700" ]

[]

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

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

[ "transformers", "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", "pytorch", "mt5", "text2text-generation", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "## Model description\nThis model is a sequence-to-sequence question generator that takes an answer and context as an input and generates a question as an output. It is based on a pre-trained mt5-base by Google model.", "## Training data\nThe model was fine-tuned on XQuAD", "## Example usage" ]

[ "TAGS\n#transformers #pytorch #mt5 #text2text-generation #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "## Model description\nThis model is a sequence-to-sequence question generator that takes an answer and context as an input and generates a question as an output. It is based on a pre-trained mt5-base by Google model.", "## Training data\nThe model was fine-tuned on XQuAD", "## Example usage" ]

[ "stablediffusion", "openvino", "en", "license:openrail++", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#stablediffusion #openvino #en #license-openrail++ #region-us \n" ]

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

[ "1910.09700" ]

[]

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

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

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

[ "1910.09700" ]

[]

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

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

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

[ "transformers", "tensorboard", "safetensors", "dinov2", "image-classification", "generated_from_trainer", "base_model:facebook/dinov2-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: 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* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 3", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #dinov2 #image-classification #generated_from_trainer #base_model-facebook/dinov2-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: 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* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 3", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "transformers", "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" ]

[ "mlx", "safetensors", "phi3", "custom_code", "license:apache-2.0", "region:us" ]

[]

[]

[ "# GreenBitAI/Phi-3-mini-4k-instruct-layer-mix-bpw-2.2-mlx\nThis quantized low-bit model was converted to MLX format from ['GreenBitAI/Phi-3-mini-4k-instruct-layer-mix-bpw-2.2']().\nRefer to the original model card for more details on the model.", "## Use with mlx" ]

[ "TAGS\n#mlx #safetensors #phi3 #custom_code #license-apache-2.0 #region-us \n", "# GreenBitAI/Phi-3-mini-4k-instruct-layer-mix-bpw-2.2-mlx\nThis quantized low-bit model was converted to MLX format from ['GreenBitAI/Phi-3-mini-4k-instruct-layer-mix-bpw-2.2']().\nRefer to the original model card for more details on the model.", "## Use with mlx" ]

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

[ "1910.09700" ]

[]

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

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

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

[ "1910.09700" ]

[]

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

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

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

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 32\n* eval\\_batch\\_size: 32\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 128\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 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 #distilbert #text-classification #generated_from_trainer #base_model-distilbert-base-uncased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 32\n* eval\\_batch\\_size: 32\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 128\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 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" ]

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

[]

[]

[ "## ANIMATOR-XL PROMPT IS EVERYTHING !! \n\n<Gallery />", "## USE IT WITH DIFFUSERS", "## CONCLUSION\n\nThe model is age violated, and the results to your prompt are at your own risk. [ Think before prompting the violated content ]\n\nThe model is re-designed [ SDXL 1.0 ] only for productivity purposes." ]

[ "TAGS\n#diffusers #safetensors #text-to-image #turbo #stable-diffusion #stable-diffusion-xl #license-creativeml-openrail-m #endpoints_compatible #diffusers-StableDiffusionXLPipeline #region-us \n", "## ANIMATOR-XL PROMPT IS EVERYTHING !! \n\n<Gallery />", "## USE IT WITH DIFFUSERS", "## CONCLUSION\n\nThe model is age violated, and the results to your prompt are at your own risk. [ Think before prompting the violated content ]\n\nThe model is re-designed [ SDXL 1.0 ] only for productivity purposes." ]

[ "transformers", "safetensors", "mistral", "text-generation", "alignment-handbook", "generated_from_trainer", "trl", "dpo", "conversational", "dataset:updated", "dataset:original", "base_model:ShenaoZ/0.001_ablation_5iters_bs256_useresponse_iter_4", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# 0.001_ablation_5iters_bs256_useresponse_iter_5\n\nThis model is a fine-tuned version of ShenaoZ/0.001_ablation_5iters_bs256_useresponse_iter_4 on the updated and the original datasets.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #alignment-handbook #generated_from_trainer #trl #dpo #conversational #dataset-updated #dataset-original #base_model-ShenaoZ/0.001_ablation_5iters_bs256_useresponse_iter_4 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# 0.001_ablation_5iters_bs256_useresponse_iter_5\n\nThis model is a fine-tuned version of ShenaoZ/0.001_ablation_5iters_bs256_useresponse_iter_4 on the updated and the original datasets.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.15.2" ]

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

[ "transformers", "safetensors", "mistral", "text-generation", "not-for-all-audiences", "nsfw", "ja", "dataset:Aratako/Syosetu711K-Cleaned-158K-Instruct", "base_model:Elizezen/SniffyOtter-7B", "license:cc-by-nc-4.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[ "ja" ]

[ "# SniffyOtter-7B-Novel-Writing-NSFW\nGGUF版はこちら/Click here for the GGUF version", "## 概要\n\nElizezen/SniffyOtter-7Bをベースに、NSFW特化で小説生成用のinstruction tuningを施したモデルです。\n\nジャンルやクオリティ、キーワードや過激さを指定すると、それに従った小説を生成するようにinstruction tuningしています。\n\nAratako/Antler-7B-Novel-Writingとの違いは主に以下の点になります。\n\n- 元モデルをElizezen/Antler-7BからElizezen/SniffyOtter-7Bへ変更\n - そのため、ライセンスがCC-BY-NC-4.0となります\n- 学習データをNSFWのものに限定\n - Aratako/Syosetu711K-Cleaned-158K-Instructから、NSFWのテキストのみを抽出\n - さらに、テキストを100文字ずつに分割し、oshizo/japanese-sexual-moderation-v2を利用してsexuality scoreを取得し、テキスト内の平均スコアが0.4以上のものを抽出", "## プロンプトフォーマット\nMistralのchat templateを利用してください。また、学習に利用したデータのフォーマットの関係上、以下のような形式が望ましいと思われます。", "## プロンプト内で指定する属性について\n本モデルは学習時の指示にジャンルやキーワード、クオリティ、過激さなどを追加して学習しているため、それらの属性を指定することである程度出力の制御が可能です。", "### ジャンル\nなろうR18小説APIにおける'nocgenre'のジャンルで学習しています。具体的には以下のものを学習時に使っています。この形式で指定するのが望ましいかと思われます。\n- 男性向け、女性向け、BL、大人向け ※APIページ上での表記からやや変更して学習しています。", "### クオリティ\n本モデルの学習に使用したデータセットの大本であるRyokoAI/Syosetu711Kのq-scoreを利用して学習時のレコードにクオリティタグをつけています。\n\n使用したデータセットは既にq-scoreが0.8以上の高品質のものをフィルターしてありますが、さらにそれを25%ずつに分け、下から0、1、2、3とラベリングしています。3を指定するとより高品質な出力になる事が期待されます。", "### 過激さ\n学習テキストに対してoshizo/japanese-sexual-moderation-v2を利用して取得したsexuality scoreの平均値を25%ずつ分割し、低い方から0、1、2、3とラベリングして学習しています。大きい数値を指定するとより過激な表現になる事が想定されます。", "## 学習関連の情報", "### 使用データセット\n- Aratako/Syosetu711K-Cleaned-158K-instruct\n - 上記データセットのうち概要で説明した処理を行いフィルタしたデータを利用", "## 学習の設定\nRunpodでGPUサーバを借り、A6000x4で学習を行いました。主な学習パラメータは以下の通りです。\n- lora_r: 128\n- lisa_alpha: 256\n- lora_dropout: 0.05\n- lora_target_modules: [\"q_proj\", \"k_proj\", \"v_proj\", \"o_proj\", \"gate_proj\", \"up_proj\", \"down_proj\", \"lm_head\"]\n- learning_rate: 2e-5\n- num_train_epochs: 10 epochs\n- batch_size: 64\n- max_seq_length: 4096", "## ライセンス\n元モデルであるElizezen/SniffyOtter-7Bと同じく、CC-BY-NC-4.0の元配布します。" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #not-for-all-audiences #nsfw #ja #dataset-Aratako/Syosetu711K-Cleaned-158K-Instruct #base_model-Elizezen/SniffyOtter-7B #license-cc-by-nc-4.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# SniffyOtter-7B-Novel-Writing-NSFW\nGGUF版はこちら/Click here for the GGUF version", "## 概要\n\nElizezen/SniffyOtter-7Bをベースに、NSFW特化で小説生成用のinstruction tuningを施したモデルです。\n\nジャンルやクオリティ、キーワードや過激さを指定すると、それに従った小説を生成するようにinstruction tuningしています。\n\nAratako/Antler-7B-Novel-Writingとの違いは主に以下の点になります。\n\n- 元モデルをElizezen/Antler-7BからElizezen/SniffyOtter-7Bへ変更\n - そのため、ライセンスがCC-BY-NC-4.0となります\n- 学習データをNSFWのものに限定\n - Aratako/Syosetu711K-Cleaned-158K-Instructから、NSFWのテキストのみを抽出\n - さらに、テキストを100文字ずつに分割し、oshizo/japanese-sexual-moderation-v2を利用してsexuality scoreを取得し、テキスト内の平均スコアが0.4以上のものを抽出", "## プロンプトフォーマット\nMistralのchat templateを利用してください。また、学習に利用したデータのフォーマットの関係上、以下のような形式が望ましいと思われます。", "## プロンプト内で指定する属性について\n本モデルは学習時の指示にジャンルやキーワード、クオリティ、過激さなどを追加して学習しているため、それらの属性を指定することである程度出力の制御が可能です。", "### ジャンル\nなろうR18小説APIにおける'nocgenre'のジャンルで学習しています。具体的には以下のものを学習時に使っています。この形式で指定するのが望ましいかと思われます。\n- 男性向け、女性向け、BL、大人向け ※APIページ上での表記からやや変更して学習しています。", "### クオリティ\n本モデルの学習に使用したデータセットの大本であるRyokoAI/Syosetu711Kのq-scoreを利用して学習時のレコードにクオリティタグをつけています。\n\n使用したデータセットは既にq-scoreが0.8以上の高品質のものをフィルターしてありますが、さらにそれを25%ずつに分け、下から0、1、2、3とラベリングしています。3を指定するとより高品質な出力になる事が期待されます。", "### 過激さ\n学習テキストに対してoshizo/japanese-sexual-moderation-v2を利用して取得したsexuality scoreの平均値を25%ずつ分割し、低い方から0、1、2、3とラベリングして学習しています。大きい数値を指定するとより過激な表現になる事が想定されます。", "## 学習関連の情報", "### 使用データセット\n- Aratako/Syosetu711K-Cleaned-158K-instruct\n - 上記データセットのうち概要で説明した処理を行いフィルタしたデータを利用", "## 学習の設定\nRunpodでGPUサーバを借り、A6000x4で学習を行いました。主な学習パラメータは以下の通りです。\n- lora_r: 128\n- lisa_alpha: 256\n- lora_dropout: 0.05\n- lora_target_modules: [\"q_proj\", \"k_proj\", \"v_proj\", \"o_proj\", \"gate_proj\", \"up_proj\", \"down_proj\", \"lm_head\"]\n- learning_rate: 2e-5\n- num_train_epochs: 10 epochs\n- batch_size: 64\n- max_seq_length: 4096", "## ライセンス\n元モデルであるElizezen/SniffyOtter-7Bと同じく、CC-BY-NC-4.0の元配布します。" ]

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

[]

[ "en" ]

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

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

[ "arxiv:2403.14599", "license:other", "region:us" ]

[ "2403.14599" ]

[]

[ "# MyVLM\n\nPaper: URL\n \nProject Page: URL\n\nCode: URL", "# MyVLM Concept Heads & Concept Embeddings\nAs part of our MyVLM code release, we have also released pretrained concept heads and concept embeddings for all 29 objects used in the paper. \n\nThese can be loaded using the 'CLIPConceptHead' class and our inference scripts for reproducing the paper results.\n\nThis repository contains 5 concept heads for each object, representing five different training seeds and sets of images used for training.", "## Concept Heads\n\n<p align=\"center\">\n<img src=\"docs/concept_head.jpg\" width=\"200px\"/> \nFor each user-specific concept, we introduce an external concept head designed to identify the presence of the concept within an image.\n</p>\n\n\nAs mentioned in the paper, we have two types of concept heads: \n1. A facial recognition model for recognizing individuals\n2. A CLIP-based concept head for recognizing user-specific objects\n\nFor faces, we use the 'buffalo_l' face detection and face recognition model from insightface.\nSee 'concept_heads/face_recognition/URL' for usage.\n\nFor objects, we train a single linear layer over features extracted from a CLIP ViT-H/14 model ('DFN5B-CLIP-ViT-H-14-384'). \nSee 'concept_heads/clip/URL' for usage.", "## Concept Embeddings\n<p align=\"center\">\n<img src=\"docs/URL\" width=\"800px\"/> \nHaving identified the presence of a user-specific concept within an image, a learned concept embedding representing an object or individual is used to guide the LLM in incorporating the concept into its personalized textual response.\n</p>\n\n\nThe concept embeddings are saved as '.pt' files in the following format: \n\n \nwhere each entry in the dictionary represents a different checkpoint during the optimization process.\n\nWe provide the concept embeddings for personalized captioning using both BLIP-2 and LLaVA.", "## License\nThis sample code is made available by Snap Inc. for non-commercial, academic purposes only. \nPlease see the full license here." ]

[ "TAGS\n#arxiv-2403.14599 #license-other #region-us \n", "# MyVLM\n\nPaper: URL\n \nProject Page: URL\n\nCode: URL", "# MyVLM Concept Heads & Concept Embeddings\nAs part of our MyVLM code release, we have also released pretrained concept heads and concept embeddings for all 29 objects used in the paper. \n\nThese can be loaded using the 'CLIPConceptHead' class and our inference scripts for reproducing the paper results.\n\nThis repository contains 5 concept heads for each object, representing five different training seeds and sets of images used for training.", "## Concept Heads\n\n<p align=\"center\">\n<img src=\"docs/concept_head.jpg\" width=\"200px\"/> \nFor each user-specific concept, we introduce an external concept head designed to identify the presence of the concept within an image.\n</p>\n\n\nAs mentioned in the paper, we have two types of concept heads: \n1. A facial recognition model for recognizing individuals\n2. A CLIP-based concept head for recognizing user-specific objects\n\nFor faces, we use the 'buffalo_l' face detection and face recognition model from insightface.\nSee 'concept_heads/face_recognition/URL' for usage.\n\nFor objects, we train a single linear layer over features extracted from a CLIP ViT-H/14 model ('DFN5B-CLIP-ViT-H-14-384'). \nSee 'concept_heads/clip/URL' for usage.", "## Concept Embeddings\n<p align=\"center\">\n<img src=\"docs/URL\" width=\"800px\"/> \nHaving identified the presence of a user-specific concept within an image, a learned concept embedding representing an object or individual is used to guide the LLM in incorporating the concept into its personalized textual response.\n</p>\n\n\nThe concept embeddings are saved as '.pt' files in the following format: \n\n \nwhere each entry in the dictionary represents a different checkpoint during the optimization process.\n\nWe provide the concept embeddings for personalized captioning using both BLIP-2 and LLaVA.", "## License\nThis sample code is made available by Snap Inc. for non-commercial, academic purposes only. \nPlease see the full license here." ]

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

[]

[ "en" ]

[ "# mlx-community/Llama-3-8b-64k-PoSE-8bit\nThis model was converted to MLX format from ['winglian/Llama-3-8b-64k-PoSE']() using mlx-lm version 0.10.0.\nRefer to the original model card for more details on the model.", "## Use with mlx" ]

[ "TAGS\n#mlx #safetensors #llama #facebook #meta #pytorch #llama-3 #text-generation #en #region-us \n", "# mlx-community/Llama-3-8b-64k-PoSE-8bit\nThis model was converted to MLX format from ['winglian/Llama-3-8b-64k-PoSE']() using mlx-lm version 0.10.0.\nRefer to the original model card for more details on the model.", "## Use with mlx" ]

[ "transformers", "tensorboard", "safetensors", "wav2vec2", "automatic-speech-recognition", "generated_from_trainer", "dataset:common_voice_13_0", "base_model:facebook/wav2vec2-large-xlsr-53", "license:apache-2.0", "model-index", "endpoints_compatible", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0001\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* num\\_epochs: 6\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.3.0+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #wav2vec2 #automatic-speech-recognition #generated_from_trainer #dataset-common_voice_13_0 #base_model-facebook/wav2vec2-large-xlsr-53 #license-apache-2.0 #model-index #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0001\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* num\\_epochs: 6\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.3.0+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "gguf", "finetuned", "llama-cpp", "gguf-my-repo", "text-generation", "license:apache-2.0", "region:us" ]

[]

[]

[ "# LaurensVdP/Mistral-7B-Instruct-v0.2-Q8_0-GGUF\nThis model was converted to GGUF format from 'mistralai/Mistral-7B-Instruct-v0.2' 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 #finetuned #llama-cpp #gguf-my-repo #text-generation #license-apache-2.0 #region-us \n", "# LaurensVdP/Mistral-7B-Instruct-v0.2-Q8_0-GGUF\nThis model was converted to GGUF format from 'mistralai/Mistral-7B-Instruct-v0.2' 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." ]

[ "sentence-transformers", "safetensors", "distilbert", "sentence-similarity", "feature-extraction", "loss:AdaptiveLayerLoss", "loss:CoSENTLoss", "en", "arxiv:1908.10084", "arxiv:2402.14776", "base_model:distilbert/distilbert-base-uncased", "model-index", "co2_eq_emissions", "endpoints_compatible", "region:us" ]

[ "1908.10084", "2402.14776" ]

[ "en" ]

[ "### Model Description\n\n\n* Model Type: Sentence Transformer\n* Base model: distilbert/distilbert-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: 5,749 training samples\n* Columns: `sentence1`, `sentence2`, and `score`\n* Approximate statistics based on the first 1000 samples:\n* Samples:\n* Loss: `AdaptiveLayerLoss` 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: `AdaptiveLayerLoss` 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': 4\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': 4\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", "### Environmental Impact\n\n\nCarbon emissions were measured using CodeCarbon.\n\n\n* Energy Consumed: 0.013 kWh\n* Carbon Emitted: 0.005 kg of CO2\n* Hours Used: 0.069 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", "#### AdaptiveLayerLoss", "#### CoSENTLoss" ]

[ "TAGS\n#sentence-transformers #safetensors #distilbert #sentence-similarity #feature-extraction #loss-AdaptiveLayerLoss #loss-CoSENTLoss #en #arxiv-1908.10084 #arxiv-2402.14776 #base_model-distilbert/distilbert-base-uncased #model-index #co2_eq_emissions #endpoints_compatible #region-us \n", "### Model Description\n\n\n* Model Type: Sentence Transformer\n* Base model: distilbert/distilbert-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: 5,749 training samples\n* Columns: `sentence1`, `sentence2`, and `score`\n* Approximate statistics based on the first 1000 samples:\n* Samples:\n* Loss: `AdaptiveLayerLoss` 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: `AdaptiveLayerLoss` 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': 4\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': 4\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", "### Environmental Impact\n\n\nCarbon emissions were measured using CodeCarbon.\n\n\n* Energy Consumed: 0.013 kWh\n* Carbon Emitted: 0.005 kg of CO2\n* Hours Used: 0.069 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", "#### AdaptiveLayerLoss", "#### CoSENTLoss" ]

[ "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: gboateng\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: gboateng\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\"/>" ]