Datasets:

---

ftopal

/

huggingface-models-processed

like 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: tingting\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: tingting\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\"/>" ]

[ 64, 79 ]

[ "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: tingting\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\"/>" ]

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

[]

[]

[ "# kisaragi_mix 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 \"kisaragimix\"\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\": \"kisaragimix\", \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", "# kisaragi_mix 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 \"kisaragimix\"\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\": \"kisaragimix\", \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" ]

[ 54, 13, 511 ]

[ "TAGS\n#diffusers #modelslab.com #stable-diffusion-api #text-to-image #ultra-realistic #license-creativeml-openrail-m #endpoints_compatible #diffusers-StableDiffusionPipeline #region-us \n# kisaragi_mix 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 \"kisaragimix\"\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\": \"kisaragimix\", \n \"prompt\": \"ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K\", \n \"negative_prompt\": \"painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime\", \n \"width\": \"512\", \n \"height\": \"512\", \n \"samples\": \"1\", \n \"num_inference_steps\": \"30\", \n \"safety_checker\": \"no\", \n \"enhance_prompt\": \"yes\", \n \"seed\": None, \n \"guidance_scale\": 7.5, \n \"multi_lingual\": \"no\", \n \"panorama\": \"no\", \n \"self_attention\": \"no\", \n \"upscale\": \"no\", \n \"embeddings\": \"embeddings_model_id\", \n \"lora\": \"lora_model_id\", \n \"webhook\": None, \n \"track_id\": None \n }) \n \n headers = { \n 'Content-Type': 'application/json' \n } \n \n response = requests.request(\"POST\", url, headers=headers, data=payload) \n \n print(URL)\n\n> Use this coupon code to get 25% off DMGG0RBN" ]

[ "transformers", "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" ]

[ 26, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "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" ]

[ 41, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "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" ]

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

[]

[]

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

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

[ 27, 38, 3, 3 ]

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

[ "gguf", "facebook", "meta", "pytorch", "llama", "llama-3", "axolotl", "GGUF", "text-generation", "en", "arxiv:2309.10400", "region:us" ]

[ "2309.10400" ]

[ "en" ]

[ "### About GGUF\n\n\nGGUF is a new format introduced by the URL team on August 21st 2023. It is a replacement for GGML, which is no longer supported by URL.\nHere is an incomplete list of clients and libraries that are known to support GGUF:\n\n\n* URL. This is the source project for GGUF, providing both a Command Line Interface (CLI) and a server option.\n* text-generation-webui, Known as the most widely used web UI, this project boasts numerous features and powerful extensions, and supports GPU acceleration.\n* Ollama Ollama is a lightweight and extensible framework designed for building and running language models locally. It features a simple API for creating, managing, and executing models, along with a library of pre-built models for use in various applications​\n* KoboldCpp, A comprehensive web UI offering GPU acceleration across all platforms and architectures, particularly renowned for storytelling.\n* GPT4All, This is a free and open source GUI that runs locally, supporting Windows, Linux, and macOS with full GPU acceleration.\n* LM Studio An intuitive and powerful local GUI for Windows and macOS (Silicon), featuring GPU acceleration.\n* LoLLMS Web UI. A notable web UI with a variety of unique features, including a comprehensive model library for easy model selection.\n* URL, An attractive, user-friendly character-based chat GUI for Windows and macOS (both Silicon and Intel), also offering GPU acceleration.\n* llama-cpp-python, A Python library equipped with GPU acceleration, LangChain support, and an OpenAI-compatible API server.\n* candle, A Rust-based ML framework focusing on performance, including GPU support, and designed for ease of use.\n* ctransformers, A Python library featuring GPU acceleration, LangChain support, and an OpenAI-compatible AI server.\n* localGPT An open-source initiative enabling private conversations with documents.\n\n\nExplanation of quantisation methods\n-----------------------------------\n\n\n\nClick to see details\nThe new methods available are:\n* GGML\\_TYPE\\_Q2\\_K - \"type-1\" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)\n* GGML\\_TYPE\\_Q3\\_K - \"type-0\" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.\n* GGML\\_TYPE\\_Q4\\_K - \"type-1\" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.\n* GGML\\_TYPE\\_Q5\\_K - \"type-1\" 5-bit quantization. Same super-block structure as GGML\\_TYPE\\_Q4\\_K resulting in 5.5 bpw\n* GGML\\_TYPE\\_Q6\\_K - \"type-0\" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw.\n\n\n\nHow to download GGUF files\n--------------------------\n\n\nNote for manual downloaders: You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single folder.\n\n\nThe following clients/libraries will automatically download models for you, providing a list of available models to choose from:\n\n\n* LM Studio\n* LoLLMS Web UI\n* URL", "### In 'text-generation-webui'\n\n\nUnder Download Model, you can enter the model repo: LiteLLMs/Llama-3-8b-64k-PoSE-GGUF and below it, a specific filename to download, such as: Q4\\_0/Q4\\_0-URL.\n\n\nThen click Download.", "### On the command line, including multiple files at once\n\n\nI recommend using the 'huggingface-hub' Python library:\n\n\nThen you can download any individual model file to the current directory, at high speed, with a command like this:\n\n\n\nMore advanced huggingface-cli download usage (click to read)\nYou can also download multiple files at once with a pattern:\n\n\nFor more documentation on downloading with 'huggingface-cli', please see: HF -> Hub Python Library -> Download files -> Download from the CLI.\n\n\nTo accelerate downloads on fast connections (1Gbit/s or higher), install 'hf\\_transfer':\n\n\nAnd set environment variable 'HF\\_HUB\\_ENABLE\\_HF\\_TRANSFER' to '1':\n\n\nWindows Command Line users: You can set the environment variable by running 'set HF\\_HUB\\_ENABLE\\_HF\\_TRANSFER=1' before the download command.\n\n\n\nExample 'URL' command\n---------------------\n\n\nMake sure you are using 'URL' from commit d0cee0d or later.\n\n\nChange '-ngl 32' to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.\n\n\nChange '-c 8192' to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by URL automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.\n\n\nIf you want to have a chat-style conversation, replace the '-p ' argument with '-i -ins'\n\n\nFor other parameters and how to use them, please refer to the URL documentation\n\n\nHow to run in 'text-generation-webui'\n-------------------------------------\n\n\nFurther instructions can be found in the text-generation-webui documentation, here: text-generation-webui/docs/04 ‐ Model URL.\n\n\nHow to run from Python code\n---------------------------\n\n\nYou can use GGUF models from Python using the llama-cpp-python or ctransformers libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.", "### How to load this model in Python code, using llama-cpp-python\n\n\nFor full documentation, please see: llama-cpp-python docs.", "#### First install the package\n\n\nRun one of the following commands, according to your system:", "#### Simple llama-cpp-python example code\n\n\nHow to use with LangChain\n-------------------------\n\n\nHere are guides on using llama-cpp-python and ctransformers with LangChain:\n\n\n* LangChain + llama-cpp-python\n* LangChain + ctransformers\n\n\nOriginal model card: Llama-3-8b-64k-PoSE\n========================================\n\n\nLlama 3 8B 64K\n--------------\n\n\n<img src=\"URL alt=\"Built with Axolotl\" width=\"200\" height=\"32\"/>\n\n\n<img src=\"URL />\n\n\nThis model uses PoSE to extend Llama's context length from 8k to 64k @ rope\\_theta: 500000.0.\nWe used PoSE with continued pretraining on 300M tokens from the RedPajama V1 dataset using data between 6k-8k tokens.\n\n\nWe have further set rope\\_theta to 2M after continued pre-training to potentially further extend the context past 64k.\n\n\nThis was trained on a subset of the RedPajama v1 dataset with text between 6k-8k context. We trained a rank stabilized LoRA of rank 256. WandB\n\n\nModel Details\n-------------\n\n\nMeta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. Further, in developing these models, we took great care to optimize helpfulness and safety.\n\n\nModel developers Meta\n\n\nVariations Llama 3 comes in two sizes — 8B and 70B parameters — in pre-trained and instruction tuned variants.\n\n\nInput Models input text only.\n\n\nOutput Models generate text and code only.\n\n\nModel Architecture Llama 3 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.\n\n\n\nLlama 3 family of models. Token counts refer to pretraining data only. Both the 8 and 70B versions use Grouped-Query Attention (GQA) for improved inference scalability.\n\n\nModel Release Date April 18, 2024.\n\n\nStatus This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback.\n\n\nLicense A custom commercial license is available at: URL\n\n\nWhere to send questions or comments about the model Instructions on how to provide feedback or comments on the model can be found in the model README. For more technical information about generation parameters and recipes for how to use Llama 3 in applications, please go here.\n\n\nIntended Use\n------------\n\n\nIntended Use Cases Llama 3 is intended for commercial and research use in English. Instruction tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.\n\n\nOut-of-scope Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3 Community License. Use in languages other than English.\n\n\nNote: Developers may fine-tune Llama 3 models for languages beyond English provided they comply with the Llama 3 Community License and the Acceptable Use Policy.\n\n\nHow to use\n----------\n\n\nThis repository contains two versions of Meta-Llama-3-8B, for use with transformers and with the original 'llama3' codebase.", "### Use with transformers\n\n\nSee the snippet below for usage with Transformers:", "### Use with 'llama3'\n\n\nPlease, follow the instructions in the repository.\n\n\nTo download Original checkpoints, see the example command below leveraging 'huggingface-cli':\n\n\nFor Hugging Face support, we recommend using transformers or TGI, but a similar command works.\n\n\nHardware and Software\n---------------------\n\n\nTraining Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.\n\n\nCarbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.\n\n\n\nCO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.\n\n\nTraining Data\n-------------\n\n\nOverview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.\n\n\nData Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.\n\n\nBenchmarks\n----------\n\n\nIn this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see here.", "### Base pretrained models", "### Instruction tuned models", "### Responsibility & Safety\n\n\nWe believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.\n\n\nFoundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.\n\n\nRather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.\n\n\nAs part of the Llama 3 release, we updated our Responsible Use Guide to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including Meta Llama Guard 2 and Code Shield safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a reference implementation to get you started.", "#### Llama 3-Instruct\n\n\nAs outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.\n\n\nSafety\n\n\nFor our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.\n\n\nRefusals\n\n\nIn addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.\n\n\nWe built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.", "#### Responsible release\n\n\nIn addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.\n\n\nMisuse\n\n\nIf you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at URL", "#### Critical risks\n\n\nCBRNE (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)\n\n\nWe have conducted a two fold assessment of the safety of the model in this area:\n\n\n* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.\n* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).", "### Cyber Security\n\n\nWe have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of equivalent coding capability.", "### Child Safety\n\n\nChild Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.", "### Community\n\n\nGenerative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our Github repository.\n\n\nFinally, we put in place a set of resources including an output reporting mechanism and bug bounty program to continuously improve the Llama technology with the help of the community.\n\n\nEthical Considerations and Limitations\n--------------------------------------\n\n\nThe core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.\n\n\nBut Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating Purple Llama solutions into your workflows and specifically Llama Guard which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.\n\n\nPlease see the Responsible Use Guide available at URL\n\n\ninstructions\n\n\n@article{llama3modelcard,\n\n\ntitle={Llama 3 Model Card},\n\n\nauthor={AI@Meta},\n\n\nyear={2024},\n\n\nurl = {URL\n\n\n}\n\n\nContributors\n------------\n\n\nAaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos" ]

[ "TAGS\n#gguf #facebook #meta #pytorch #llama #llama-3 #axolotl #GGUF #text-generation #en #arxiv-2309.10400 #region-us \n", "### About GGUF\n\n\nGGUF is a new format introduced by the URL team on August 21st 2023. It is a replacement for GGML, which is no longer supported by URL.\nHere is an incomplete list of clients and libraries that are known to support GGUF:\n\n\n* URL. This is the source project for GGUF, providing both a Command Line Interface (CLI) and a server option.\n* text-generation-webui, Known as the most widely used web UI, this project boasts numerous features and powerful extensions, and supports GPU acceleration.\n* Ollama Ollama is a lightweight and extensible framework designed for building and running language models locally. It features a simple API for creating, managing, and executing models, along with a library of pre-built models for use in various applications​\n* KoboldCpp, A comprehensive web UI offering GPU acceleration across all platforms and architectures, particularly renowned for storytelling.\n* GPT4All, This is a free and open source GUI that runs locally, supporting Windows, Linux, and macOS with full GPU acceleration.\n* LM Studio An intuitive and powerful local GUI for Windows and macOS (Silicon), featuring GPU acceleration.\n* LoLLMS Web UI. A notable web UI with a variety of unique features, including a comprehensive model library for easy model selection.\n* URL, An attractive, user-friendly character-based chat GUI for Windows and macOS (both Silicon and Intel), also offering GPU acceleration.\n* llama-cpp-python, A Python library equipped with GPU acceleration, LangChain support, and an OpenAI-compatible API server.\n* candle, A Rust-based ML framework focusing on performance, including GPU support, and designed for ease of use.\n* ctransformers, A Python library featuring GPU acceleration, LangChain support, and an OpenAI-compatible AI server.\n* localGPT An open-source initiative enabling private conversations with documents.\n\n\nExplanation of quantisation methods\n-----------------------------------\n\n\n\nClick to see details\nThe new methods available are:\n* GGML\\_TYPE\\_Q2\\_K - \"type-1\" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)\n* GGML\\_TYPE\\_Q3\\_K - \"type-0\" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.\n* GGML\\_TYPE\\_Q4\\_K - \"type-1\" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.\n* GGML\\_TYPE\\_Q5\\_K - \"type-1\" 5-bit quantization. Same super-block structure as GGML\\_TYPE\\_Q4\\_K resulting in 5.5 bpw\n* GGML\\_TYPE\\_Q6\\_K - \"type-0\" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw.\n\n\n\nHow to download GGUF files\n--------------------------\n\n\nNote for manual downloaders: You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single folder.\n\n\nThe following clients/libraries will automatically download models for you, providing a list of available models to choose from:\n\n\n* LM Studio\n* LoLLMS Web UI\n* URL", "### In 'text-generation-webui'\n\n\nUnder Download Model, you can enter the model repo: LiteLLMs/Llama-3-8b-64k-PoSE-GGUF and below it, a specific filename to download, such as: Q4\\_0/Q4\\_0-URL.\n\n\nThen click Download.", "### On the command line, including multiple files at once\n\n\nI recommend using the 'huggingface-hub' Python library:\n\n\nThen you can download any individual model file to the current directory, at high speed, with a command like this:\n\n\n\nMore advanced huggingface-cli download usage (click to read)\nYou can also download multiple files at once with a pattern:\n\n\nFor more documentation on downloading with 'huggingface-cli', please see: HF -> Hub Python Library -> Download files -> Download from the CLI.\n\n\nTo accelerate downloads on fast connections (1Gbit/s or higher), install 'hf\\_transfer':\n\n\nAnd set environment variable 'HF\\_HUB\\_ENABLE\\_HF\\_TRANSFER' to '1':\n\n\nWindows Command Line users: You can set the environment variable by running 'set HF\\_HUB\\_ENABLE\\_HF\\_TRANSFER=1' before the download command.\n\n\n\nExample 'URL' command\n---------------------\n\n\nMake sure you are using 'URL' from commit d0cee0d or later.\n\n\nChange '-ngl 32' to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.\n\n\nChange '-c 8192' to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by URL automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.\n\n\nIf you want to have a chat-style conversation, replace the '-p ' argument with '-i -ins'\n\n\nFor other parameters and how to use them, please refer to the URL documentation\n\n\nHow to run in 'text-generation-webui'\n-------------------------------------\n\n\nFurther instructions can be found in the text-generation-webui documentation, here: text-generation-webui/docs/04 ‐ Model URL.\n\n\nHow to run from Python code\n---------------------------\n\n\nYou can use GGUF models from Python using the llama-cpp-python or ctransformers libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.", "### How to load this model in Python code, using llama-cpp-python\n\n\nFor full documentation, please see: llama-cpp-python docs.", "#### First install the package\n\n\nRun one of the following commands, according to your system:", "#### Simple llama-cpp-python example code\n\n\nHow to use with LangChain\n-------------------------\n\n\nHere are guides on using llama-cpp-python and ctransformers with LangChain:\n\n\n* LangChain + llama-cpp-python\n* LangChain + ctransformers\n\n\nOriginal model card: Llama-3-8b-64k-PoSE\n========================================\n\n\nLlama 3 8B 64K\n--------------\n\n\n<img src=\"URL alt=\"Built with Axolotl\" width=\"200\" height=\"32\"/>\n\n\n<img src=\"URL />\n\n\nThis model uses PoSE to extend Llama's context length from 8k to 64k @ rope\\_theta: 500000.0.\nWe used PoSE with continued pretraining on 300M tokens from the RedPajama V1 dataset using data between 6k-8k tokens.\n\n\nWe have further set rope\\_theta to 2M after continued pre-training to potentially further extend the context past 64k.\n\n\nThis was trained on a subset of the RedPajama v1 dataset with text between 6k-8k context. We trained a rank stabilized LoRA of rank 256. WandB\n\n\nModel Details\n-------------\n\n\nMeta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. Further, in developing these models, we took great care to optimize helpfulness and safety.\n\n\nModel developers Meta\n\n\nVariations Llama 3 comes in two sizes — 8B and 70B parameters — in pre-trained and instruction tuned variants.\n\n\nInput Models input text only.\n\n\nOutput Models generate text and code only.\n\n\nModel Architecture Llama 3 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.\n\n\n\nLlama 3 family of models. Token counts refer to pretraining data only. Both the 8 and 70B versions use Grouped-Query Attention (GQA) for improved inference scalability.\n\n\nModel Release Date April 18, 2024.\n\n\nStatus This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback.\n\n\nLicense A custom commercial license is available at: URL\n\n\nWhere to send questions or comments about the model Instructions on how to provide feedback or comments on the model can be found in the model README. For more technical information about generation parameters and recipes for how to use Llama 3 in applications, please go here.\n\n\nIntended Use\n------------\n\n\nIntended Use Cases Llama 3 is intended for commercial and research use in English. Instruction tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.\n\n\nOut-of-scope Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3 Community License. Use in languages other than English.\n\n\nNote: Developers may fine-tune Llama 3 models for languages beyond English provided they comply with the Llama 3 Community License and the Acceptable Use Policy.\n\n\nHow to use\n----------\n\n\nThis repository contains two versions of Meta-Llama-3-8B, for use with transformers and with the original 'llama3' codebase.", "### Use with transformers\n\n\nSee the snippet below for usage with Transformers:", "### Use with 'llama3'\n\n\nPlease, follow the instructions in the repository.\n\n\nTo download Original checkpoints, see the example command below leveraging 'huggingface-cli':\n\n\nFor Hugging Face support, we recommend using transformers or TGI, but a similar command works.\n\n\nHardware and Software\n---------------------\n\n\nTraining Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.\n\n\nCarbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.\n\n\n\nCO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.\n\n\nTraining Data\n-------------\n\n\nOverview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.\n\n\nData Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.\n\n\nBenchmarks\n----------\n\n\nIn this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see here.", "### Base pretrained models", "### Instruction tuned models", "### Responsibility & Safety\n\n\nWe believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.\n\n\nFoundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.\n\n\nRather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.\n\n\nAs part of the Llama 3 release, we updated our Responsible Use Guide to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including Meta Llama Guard 2 and Code Shield safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a reference implementation to get you started.", "#### Llama 3-Instruct\n\n\nAs outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.\n\n\nSafety\n\n\nFor our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.\n\n\nRefusals\n\n\nIn addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.\n\n\nWe built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.", "#### Responsible release\n\n\nIn addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.\n\n\nMisuse\n\n\nIf you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at URL", "#### Critical risks\n\n\nCBRNE (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)\n\n\nWe have conducted a two fold assessment of the safety of the model in this area:\n\n\n* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.\n* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).", "### Cyber Security\n\n\nWe have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of equivalent coding capability.", "### Child Safety\n\n\nChild Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.", "### Community\n\n\nGenerative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our Github repository.\n\n\nFinally, we put in place a set of resources including an output reporting mechanism and bug bounty program to continuously improve the Llama technology with the help of the community.\n\n\nEthical Considerations and Limitations\n--------------------------------------\n\n\nThe core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.\n\n\nBut Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating Purple Llama solutions into your workflows and specifically Llama Guard which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.\n\n\nPlease see the Responsible Use Guide available at URL\n\n\ninstructions\n\n\n@article{llama3modelcard,\n\n\ntitle={Llama 3 Model Card},\n\n\nauthor={AI@Meta},\n\n\nyear={2024},\n\n\nurl = {URL\n\n\n}\n\n\nContributors\n------------\n\n\nAaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos" ]

[ 50, 877, 77, 578, 37, 20, 872, 17, 430, 8, 6, 270, 280, 72, 115, 118, 126, 2136 ]

[ "TAGS\n#gguf #facebook #meta #pytorch #llama #llama-3 #axolotl #GGUF #text-generation #en #arxiv-2309.10400 #region-us \n### About GGUF\n\n\nGGUF is a new format introduced by the URL team on August 21st 2023. It is a replacement for GGML, which is no longer supported by URL.\nHere is an incomplete list of clients and libraries that are known to support GGUF:\n\n\n* URL. This is the source project for GGUF, providing both a Command Line Interface (CLI) and a server option.\n* text-generation-webui, Known as the most widely used web UI, this project boasts numerous features and powerful extensions, and supports GPU acceleration.\n* Ollama Ollama is a lightweight and extensible framework designed for building and running language models locally. It features a simple API for creating, managing, and executing models, along with a library of pre-built models for use in various applications​\n* KoboldCpp, A comprehensive web UI offering GPU acceleration across all platforms and architectures, particularly renowned for storytelling.\n* GPT4All, This is a free and open source GUI that runs locally, supporting Windows, Linux, and macOS with full GPU acceleration.\n* LM Studio An intuitive and powerful local GUI for Windows and macOS (Silicon), featuring GPU acceleration.\n* LoLLMS Web UI. A notable web UI with a variety of unique features, including a comprehensive model library for easy model selection.\n* URL, An attractive, user-friendly character-based chat GUI for Windows and macOS (both Silicon and Intel), also offering GPU acceleration.\n* llama-cpp-python, A Python library equipped with GPU acceleration, LangChain support, and an OpenAI-compatible API server.\n* candle, A Rust-based ML framework focusing on performance, including GPU support, and designed for ease of use.\n* ctransformers, A Python library featuring GPU acceleration, LangChain support, and an OpenAI-compatible AI server.\n* localGPT An open-source initiative enabling private conversations with documents.\n\n\nExplanation of quantisation methods\n-----------------------------------\n\n\n\nClick to see details\nThe new methods available are:\n* GGML\\_TYPE\\_Q2\\_K - \"type-1\" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)\n* GGML\\_TYPE\\_Q3\\_K - \"type-0\" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.\n* GGML\\_TYPE\\_Q4\\_K - \"type-1\" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.\n* GGML\\_TYPE\\_Q5\\_K - \"type-1\" 5-bit quantization. Same super-block structure as GGML\\_TYPE\\_Q4\\_K resulting in 5.5 bpw\n* GGML\\_TYPE\\_Q6\\_K - \"type-0\" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw.\n\n\n\nHow to download GGUF files\n--------------------------\n\n\nNote for manual downloaders: You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single folder.\n\n\nThe following clients/libraries will automatically download models for you, providing a list of available models to choose from:\n\n\n* LM Studio\n* LoLLMS Web UI\n* URL### In 'text-generation-webui'\n\n\nUnder Download Model, you can enter the model repo: LiteLLMs/Llama-3-8b-64k-PoSE-GGUF and below it, a specific filename to download, such as: Q4\\_0/Q4\\_0-URL.\n\n\nThen click Download.### On the command line, including multiple files at once\n\n\nI recommend using the 'huggingface-hub' Python library:\n\n\nThen you can download any individual model file to the current directory, at high speed, with a command like this:\n\n\n\nMore advanced huggingface-cli download usage (click to read)\nYou can also download multiple files at once with a pattern:\n\n\nFor more documentation on downloading with 'huggingface-cli', please see: HF -> Hub Python Library -> Download files -> Download from the CLI.\n\n\nTo accelerate downloads on fast connections (1Gbit/s or higher), install 'hf\\_transfer':\n\n\nAnd set environment variable 'HF\\_HUB\\_ENABLE\\_HF\\_TRANSFER' to '1':\n\n\nWindows Command Line users: You can set the environment variable by running 'set HF\\_HUB\\_ENABLE\\_HF\\_TRANSFER=1' before the download command.\n\n\n\nExample 'URL' command\n---------------------\n\n\nMake sure you are using 'URL' from commit d0cee0d or later.\n\n\nChange '-ngl 32' to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.\n\n\nChange '-c 8192' to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by URL automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.\n\n\nIf you want to have a chat-style conversation, replace the '-p ' argument with '-i -ins'\n\n\nFor other parameters and how to use them, please refer to the URL documentation\n\n\nHow to run in 'text-generation-webui'\n-------------------------------------\n\n\nFurther instructions can be found in the text-generation-webui documentation, here: text-generation-webui/docs/04 ‐ Model URL.\n\n\nHow to run from Python code\n---------------------------\n\n\nYou can use GGUF models from Python using the llama-cpp-python or ctransformers libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.### How to load this model in Python code, using llama-cpp-python\n\n\nFor full documentation, please see: llama-cpp-python docs.#### First install the package\n\n\nRun one of the following commands, according to your system:#### Simple llama-cpp-python example code\n\n\nHow to use with LangChain\n-------------------------\n\n\nHere are guides on using llama-cpp-python and ctransformers with LangChain:\n\n\n* LangChain + llama-cpp-python\n* LangChain + ctransformers\n\n\nOriginal model card: Llama-3-8b-64k-PoSE\n========================================\n\n\nLlama 3 8B 64K\n--------------\n\n\n<img src=\"URL alt=\"Built with Axolotl\" width=\"200\" height=\"32\"/>\n\n\n<img src=\"URL />\n\n\nThis model uses PoSE to extend Llama's context length from 8k to 64k @ rope\\_theta: 500000.0.\nWe used PoSE with continued pretraining on 300M tokens from the RedPajama V1 dataset using data between 6k-8k tokens.\n\n\nWe have further set rope\\_theta to 2M after continued pre-training to potentially further extend the context past 64k.\n\n\nThis was trained on a subset of the RedPajama v1 dataset with text between 6k-8k context. We trained a rank stabilized LoRA of rank 256. WandB\n\n\nModel Details\n-------------\n\n\nMeta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. Further, in developing these models, we took great care to optimize helpfulness and safety.\n\n\nModel developers Meta\n\n\nVariations Llama 3 comes in two sizes — 8B and 70B parameters — in pre-trained and instruction tuned variants.\n\n\nInput Models input text only.\n\n\nOutput Models generate text and code only.\n\n\nModel Architecture Llama 3 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.\n\n\n\nLlama 3 family of models. Token counts refer to pretraining data only. Both the 8 and 70B versions use Grouped-Query Attention (GQA) for improved inference scalability.\n\n\nModel Release Date April 18, 2024.\n\n\nStatus This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback.\n\n\nLicense A custom commercial license is available at: URL\n\n\nWhere to send questions or comments about the model Instructions on how to provide feedback or comments on the model can be found in the model README. For more technical information about generation parameters and recipes for how to use Llama 3 in applications, please go here.\n\n\nIntended Use\n------------\n\n\nIntended Use Cases Llama 3 is intended for commercial and research use in English. Instruction tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.\n\n\nOut-of-scope Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3 Community License. Use in languages other than English.\n\n\nNote: Developers may fine-tune Llama 3 models for languages beyond English provided they comply with the Llama 3 Community License and the Acceptable Use Policy.\n\n\nHow to use\n----------\n\n\nThis repository contains two versions of Meta-Llama-3-8B, for use with transformers and with the original 'llama3' codebase.### Use with transformers\n\n\nSee the snippet below for usage with Transformers:### Use with 'llama3'\n\n\nPlease, follow the instructions in the repository.\n\n\nTo download Original checkpoints, see the example command below leveraging 'huggingface-cli':\n\n\nFor Hugging Face support, we recommend using transformers or TGI, but a similar command works.\n\n\nHardware and Software\n---------------------\n\n\nTraining Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.\n\n\nCarbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.\n\n\n\nCO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.\n\n\nTraining Data\n-------------\n\n\nOverview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.\n\n\nData Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.\n\n\nBenchmarks\n----------\n\n\nIn this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see here.### Base pretrained models### Instruction tuned models### Responsibility & Safety\n\n\nWe believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.\n\n\nFoundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.\n\n\nRather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.\n\n\nAs part of the Llama 3 release, we updated our Responsible Use Guide to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including Meta Llama Guard 2 and Code Shield safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a reference implementation to get you started.#### Llama 3-Instruct\n\n\nAs outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.\n\n\nSafety\n\n\nFor our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.\n\n\nRefusals\n\n\nIn addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.\n\n\nWe built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.#### Responsible release\n\n\nIn addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.\n\n\nMisuse\n\n\nIf you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at URL#### Critical risks\n\n\nCBRNE (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)\n\n\nWe have conducted a two fold assessment of the safety of the model in this area:\n\n\n* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.\n* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).### Cyber Security\n\n\nWe have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of equivalent coding capability.### Child Safety\n\n\nChild Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.### Community\n\n\nGenerative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our Github repository.\n\n\nFinally, we put in place a set of resources including an output reporting mechanism and bug bounty program to continuously improve the Llama technology with the help of the community.\n\n\nEthical Considerations and Limitations\n--------------------------------------\n\n\nThe core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.\n\n\nBut Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating Purple Llama solutions into your workflows and specifically Llama Guard which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.\n\n\nPlease see the Responsible Use Guide available at URL\n\n\ninstructions\n\n\n@article{llama3modelcard,\n\n\ntitle={Llama 3 Model Card},\n\n\nauthor={AI@Meta},\n\n\nyear={2024},\n\n\nurl = {URL\n\n\n}\n\n\nContributors\n------------\n\n\nAaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos" ]

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

[]

[ "en" ]

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

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

[ 62, 77 ]

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

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ 42, 100, 5, 52 ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000### Training results### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ 42, 100, 5, 52 ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000### Training results### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "transformers", "gguf", "code", "text-generation", "dataset:bigcode/self-oss-instruct-sc2-exec-filter-50k", "base_model:bigcode/starcoder2-15b", "license:bigcode-openrail-m", "model-index", "endpoints_compatible", "region:us" ]

[]

[]

[]

[ "TAGS\n#transformers #gguf #code #text-generation #dataset-bigcode/self-oss-instruct-sc2-exec-filter-50k #base_model-bigcode/starcoder2-15b #license-bigcode-openrail-m #model-index #endpoints_compatible #region-us \n" ]

[ 76 ]

[ "TAGS\n#transformers #gguf #code #text-generation #dataset-bigcode/self-oss-instruct-sc2-exec-filter-50k #base_model-bigcode/starcoder2-15b #license-bigcode-openrail-m #model-index #endpoints_compatible #region-us \n" ]

[ "transformers", "safetensors", "llama", "text-generation", "text-generation-inference", "unsloth", "trl", "en", "base_model:Faradaylab/ARIA-70B-V3", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "4-bit", "region:us" ]

[]

[ "en" ]

[ "# Uploaded model\n\n- Developed by: axel-rda\n- License: apache-2.0\n- Finetuned from model : Faradaylab/ARIA-70B-V3\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #text-generation-inference #unsloth #trl #en #base_model-Faradaylab/ARIA-70B-V3 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #4-bit #region-us \n", "# Uploaded model\n\n- Developed by: axel-rda\n- License: apache-2.0\n- Finetuned from model : Faradaylab/ARIA-70B-V3\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ 71, 75 ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #text-generation-inference #unsloth #trl #en #base_model-Faradaylab/ARIA-70B-V3 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #4-bit #region-us \n# Uploaded model\n\n- Developed by: axel-rda\n- License: apache-2.0\n- Finetuned from model : Faradaylab/ARIA-70B-V3\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ 42, 100, 5, 52 ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000### Training results### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

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

[ "1910.09700" ]

[]

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

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

[ 47, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

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

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

[]

[]

[ "# nagatsuki_mix 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 \"nagatsukimix\"\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\": \"nagatsukimix\", \n \"prompt\": \"ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K\", \n \"negative_prompt\": \"painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime\", \n \"width\": \"512\", \n \"height\": \"512\", \n \"samples\": \"1\", \n \"num_inference_steps\": \"30\", \n \"safety_checker\": \"no\", \n \"enhance_prompt\": \"yes\", \n \"seed\": None, \n \"guidance_scale\": 7.5, \n \"multi_lingual\": \"no\", \n \"panorama\": \"no\", \n \"self_attention\": \"no\", \n \"upscale\": \"no\", \n \"embeddings\": \"embeddings_model_id\", \n \"lora\": \"lora_model_id\", \n \"webhook\": None, \n \"track_id\": None \n }) \n \n headers = { \n 'Content-Type': 'application/json' \n } \n \n response = requests.request(\"POST\", url, headers=headers, data=payload) \n \n print(URL)\n\n> Use this coupon code to get 25% off DMGG0RBN" ]

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

[ 56, 13, 509 ]

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

[ "keras-nlp", "text-generation", "region:us" ]

[]

[]

[]

[ "TAGS\n#keras-nlp #text-generation #region-us \n" ]

[ 15 ]

[ "TAGS\n#keras-nlp #text-generation #region-us \n" ]

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

[ "1910.09700" ]

[]

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

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

[ 47, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

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

[ "transformers", "safetensors", "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: tingting\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: tingting\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\"/>" ]

[ 64, 79 ]

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

[ "transformers", "tensorboard", "safetensors", "whisper", "automatic-speech-recognition", "generated_from_trainer", "dataset:common_voice_11_0", "base_model:openai/whisper-base", "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: 1e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 32\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 500\n* training\\_steps: 4000\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 #whisper #automatic-speech-recognition #generated_from_trainer #dataset-common_voice_11_0 #base_model-openai/whisper-base #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: 1e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 32\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 500\n* training\\_steps: 4000\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" ]

[ 67, 149, 5, 44 ]

[ "TAGS\n#transformers #tensorboard #safetensors #whisper #automatic-speech-recognition #generated_from_trainer #dataset-common_voice_11_0 #base_model-openai/whisper-base #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: 1e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 32\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 500\n* training\\_steps: 4000\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" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ 42, 100, 5, 52 ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000### Training results### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ 42, 100, 5, 52 ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000### Training results### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

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

[ "1910.09700" ]

[]

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

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

[ 47, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

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

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ 42, 100, 5, 52 ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000### Training results### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ 42, 100, 5, 52 ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000### Training results### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ 42, 100, 5, 52 ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000### Training results### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ 42, 100, 5, 52 ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000### Training results### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ 42, 100, 5, 52 ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000### Training results### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "transformers", "safetensors", "distilbert", "question-answering", "generated_from_trainer", "ar", "base_model:distilbert-base-cased", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[ "ar" ]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 10\n* eval\\_batch\\_size: 10\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 40\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: 4", "### 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 #safetensors #distilbert #question-answering #generated_from_trainer #ar #base_model-distilbert-base-cased #license-apache-2.0 #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 10\n* eval\\_batch\\_size: 10\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 40\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: 4", "### 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" ]

[ 53, 142, 5, 44 ]

[ "TAGS\n#transformers #safetensors #distilbert #question-answering #generated_from_trainer #ar #base_model-distilbert-base-cased #license-apache-2.0 #endpoints_compatible #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 10\n* eval\\_batch\\_size: 10\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 40\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: 4### 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", "mistral", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "1910.09700" ]

[]

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

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

[ 47, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

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

[ "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" ]

[ 35, 33 ]

[ "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", "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: 64\n* eval\\_batch\\_size: 64\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 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 #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: 64\n* eval\\_batch\\_size: 64\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 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" ]

[ 56, 101, 5, 44 ]

[ "TAGS\n#transformers #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: 64\n* eval\\_batch\\_size: 64\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 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" ]

[ "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" ]

[ 26, 31 ]

[ "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" ]

[ "transformers", "safetensors", "xlm-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 #safetensors #xlm-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" ]

[ 35, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #xlm-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" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ 42, 100, 5, 52 ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000### Training results### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ 42, 100, 5, 52 ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000### Training results### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "diffusers", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]

[]

[]

[ "### vesttieandtux2 Dreambooth model trained by enriq3 with TheLastBen's fast-DreamBooth notebook" ]

[ "TAGS\n#diffusers #endpoints_compatible #diffusers-StableDiffusionPipeline #region-us \n", "### vesttieandtux2 Dreambooth model trained by enriq3 with TheLastBen's fast-DreamBooth notebook" ]

[ 23, 32 ]

[ "TAGS\n#diffusers #endpoints_compatible #diffusers-StableDiffusionPipeline #region-us \n### vesttieandtux2 Dreambooth model trained by enriq3 with TheLastBen's fast-DreamBooth notebook" ]

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

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 5", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #gpt2 #text-generation #generated_from_trainer #base_model-gpt2 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 5", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ 56, 101, 5, 44 ]

[ "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### 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: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 5### Training results### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ 42, 100, 5, 52 ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000### Training results### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

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

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #distilbert #question-answering #generated_from_trainer #base_model-distilbert-base-uncased #license-apache-2.0 #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ 54, 101, 5, 44 ]

[ "TAGS\n#transformers #tensorboard #safetensors #distilbert #question-answering #generated_from_trainer #base_model-distilbert-base-uncased #license-apache-2.0 #endpoints_compatible #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3### Training results### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

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

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #llama #text-generation-inference #text-generation #en #license-cc-by-nc-sa-4.0 #endpoints_compatible #region-us \n" ]

[ 45 ]

[ "TAGS\n#transformers #gguf #llama #text-generation-inference #text-generation #en #license-cc-by-nc-sa-4.0 #endpoints_compatible #region-us \n" ]

[ "safetensors", "generated_from_trainer", "base_model:allenai/OLMo-1B", "license:apache-2.0", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0003\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 16\n* total\\_train\\_batch\\_size: 128\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\\_with\\_restarts\n* lr\\_scheduler\\_warmup\\_steps: 80\n* num\\_epochs: 3\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.36.0.dev0\n* Pytorch 2.1.2+cu121\n* Datasets 2.14.6\n* Tokenizers 0.14.1" ]

[ "TAGS\n#safetensors #generated_from_trainer #base_model-allenai/OLMo-1B #license-apache-2.0 #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: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 16\n* total\\_train\\_batch\\_size: 128\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\\_with\\_restarts\n* lr\\_scheduler\\_warmup\\_steps: 80\n* num\\_epochs: 3\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.36.0.dev0\n* Pytorch 2.1.2+cu121\n* Datasets 2.14.6\n* Tokenizers 0.14.1" ]

[ 35, 160, 5, 47 ]

[ "TAGS\n#safetensors #generated_from_trainer #base_model-allenai/OLMo-1B #license-apache-2.0 #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: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 16\n* total\\_train\\_batch\\_size: 128\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\\_with\\_restarts\n* lr\\_scheduler\\_warmup\\_steps: 80\n* num\\_epochs: 3\n* mixed\\_precision\\_training: Native AMP### Training results### Framework versions\n\n\n* Transformers 4.36.0.dev0\n* Pytorch 2.1.2+cu121\n* Datasets 2.14.6\n* Tokenizers 0.14.1" ]

[ "safetensors", "generated_from_trainer", "base_model:allenai/OLMo-1B", "license:apache-2.0", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0003\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 16\n* total\\_train\\_batch\\_size: 128\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\\_with\\_restarts\n* lr\\_scheduler\\_warmup\\_steps: 80\n* num\\_epochs: 3\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.36.0.dev0\n* Pytorch 2.1.2+cu121\n* Datasets 2.14.6\n* Tokenizers 0.14.1" ]

[ "TAGS\n#safetensors #generated_from_trainer #base_model-allenai/OLMo-1B #license-apache-2.0 #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: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 16\n* total\\_train\\_batch\\_size: 128\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\\_with\\_restarts\n* lr\\_scheduler\\_warmup\\_steps: 80\n* num\\_epochs: 3\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.36.0.dev0\n* Pytorch 2.1.2+cu121\n* Datasets 2.14.6\n* Tokenizers 0.14.1" ]

[ 35, 160, 5, 47 ]

[ "TAGS\n#safetensors #generated_from_trainer #base_model-allenai/OLMo-1B #license-apache-2.0 #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: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 16\n* total\\_train\\_batch\\_size: 128\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\\_with\\_restarts\n* lr\\_scheduler\\_warmup\\_steps: 80\n* num\\_epochs: 3\n* mixed\\_precision\\_training: Native AMP### Training results### Framework versions\n\n\n* Transformers 4.36.0.dev0\n* Pytorch 2.1.2+cu121\n* Datasets 2.14.6\n* Tokenizers 0.14.1" ]

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

[ "1910.09700" ]

[]

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

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

[ 47, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

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

[ "peft", "pytorch", "llama", "text2text-generation", "en", "dataset:theblackcat102/evol-codealpaca-v1", "license:cc-by-nc-4.0", "region:us" ]

[]

[ "en" ]

[ "## llama-2-13b-code-alpaca\n<img src=\"URL alt=\"Built with Axolotl\" width=\"200\" height=\"32\"/>\n\nTrained for 3 epochs on 'theblackcat102/evol-codealpaca-v1' dataset, scored decent on locally run perplexity at 4.36.", "## Axolotl config used\n\n\n\nAnd then merged with Axolotl via:", "## Training procedure\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16", "### Framework versions\n- PEFT 0.5.0.dev0" ]

[ "TAGS\n#peft #pytorch #llama #text2text-generation #en #dataset-theblackcat102/evol-codealpaca-v1 #license-cc-by-nc-4.0 #region-us \n", "## llama-2-13b-code-alpaca\n<img src=\"URL alt=\"Built with Axolotl\" width=\"200\" height=\"32\"/>\n\nTrained for 3 epochs on 'theblackcat102/evol-codealpaca-v1' dataset, scored decent on locally run perplexity at 4.36.", "## Axolotl config used\n\n\n\nAnd then merged with Axolotl via:", "## Training procedure\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16", "### Framework versions\n- PEFT 0.5.0.dev0" ]

[ 57, 86, 18, 572, 16 ]

[ "TAGS\n#peft #pytorch #llama #text2text-generation #en #dataset-theblackcat102/evol-codealpaca-v1 #license-cc-by-nc-4.0 #region-us \n## llama-2-13b-code-alpaca\n<img src=\"URL alt=\"Built with Axolotl\" width=\"200\" height=\"32\"/>\n\nTrained for 3 epochs on 'theblackcat102/evol-codealpaca-v1' dataset, scored decent on locally run perplexity at 4.36.## Axolotl config used\n\n\n\nAnd then merged with Axolotl via:## Training procedure\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16### Framework versions\n- PEFT 0.5.0.dev0" ]

[ "transformers", "safetensors", "llama", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]

[ "1910.09700" ]

[]

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

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

[ 48, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

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

[ "transformers", "safetensors", "llama", "text-generation", "mergekit", "merge", "conversational", "arxiv:2311.03099", "arxiv:2306.01708", "base_model:Undi95/Meta-Llama-3-8B-Instruct-hf", "license:llama3", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "2311.03099", "2306.01708" ]

[]

[ "### Merge Method\n\n\nThis model was merged using the DARE TIES merge method using Undi95/Meta-Llama-3-8B-Instruct-hf as a base.", "### Models Merged\n\n\nThe following models were included in the merge:\n\n\n* llama-3-8B-ultra-instruct/InstructPart\n* llama-3-8B-ultra-instruct/RPPart", "### Configuration\n\n\nThe following YAML configuration was used to produce this model:", "### Chat Template (Llama 3 Official)", "### Open LLM Leaderboard Evaluation Results\n\n\nDetailed results can be found here" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #mergekit #merge #conversational #arxiv-2311.03099 #arxiv-2306.01708 #base_model-Undi95/Meta-Llama-3-8B-Instruct-hf #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "### Merge Method\n\n\nThis model was merged using the DARE TIES merge method using Undi95/Meta-Llama-3-8B-Instruct-hf as a base.", "### Models Merged\n\n\nThe following models were included in the merge:\n\n\n* llama-3-8B-ultra-instruct/InstructPart\n* llama-3-8B-ultra-instruct/RPPart", "### Configuration\n\n\nThe following YAML configuration was used to produce this model:", "### Chat Template (Llama 3 Official)", "### Open LLM Leaderboard Evaluation Results\n\n\nDetailed results can be found here" ]

[ 96, 40, 49, 16, 11, 16 ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #mergekit #merge #conversational #arxiv-2311.03099 #arxiv-2306.01708 #base_model-Undi95/Meta-Llama-3-8B-Instruct-hf #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n### Merge Method\n\n\nThis model was merged using the DARE TIES merge method using Undi95/Meta-Llama-3-8B-Instruct-hf as a base.### Models Merged\n\n\nThe following models were included in the merge:\n\n\n* llama-3-8B-ultra-instruct/InstructPart\n* llama-3-8B-ultra-instruct/RPPart### Configuration\n\n\nThe following YAML configuration was used to produce this model:### Chat Template (Llama 3 Official)### Open LLM Leaderboard Evaluation Results\n\n\nDetailed results can be found here" ]

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

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 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: 2", "### Training results", "### Framework versions\n\n\n* Transformers 4.39.0.dev0\n* Pytorch 2.2.1+cu121\n* Datasets 2.16.1\n* Tokenizers 0.15.1" ]

[ "TAGS\n#transformers #safetensors #mbart #text2text-generation #generated_from_trainer #base_model-facebook/mbart-large-50 #license-mit #autotrain_compatible #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 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: 2", "### Training results", "### Framework versions\n\n\n* Transformers 4.39.0.dev0\n* Pytorch 2.2.1+cu121\n* Datasets 2.16.1\n* Tokenizers 0.15.1" ]

[ 53, 101, 5, 47 ]

[ "TAGS\n#transformers #safetensors #mbart #text2text-generation #generated_from_trainer #base_model-facebook/mbart-large-50 #license-mit #autotrain_compatible #endpoints_compatible #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 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: 2### Training results### Framework versions\n\n\n* Transformers 4.39.0.dev0\n* Pytorch 2.2.1+cu121\n* Datasets 2.16.1\n* Tokenizers 0.15.1" ]

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

[]

[]

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

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

[ 32, 46 ]

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

[ "peft", "safetensors", "mistral", "alignment-handbook", "trl", "dpo", "generated_from_trainer", "dataset:hugodk-sch/aftonposten_title_prefs", "base_model:NorLLM-AI/NorMistral-7B", "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: 4\n* eval\\_batch\\_size: 8\n* seed: 42\n* distributed\\_type: multi-GPU\n* gradient\\_accumulation\\_steps: 2\n* total\\_train\\_batch\\_size: 8\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\n* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 1", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.39.0.dev0\n* Pytorch 2.1.2+cu121\n* Datasets 2.14.6\n* Tokenizers 0.15.1" ]

[ "TAGS\n#peft #safetensors #mistral #alignment-handbook #trl #dpo #generated_from_trainer #dataset-hugodk-sch/aftonposten_title_prefs #base_model-NorLLM-AI/NorMistral-7B #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: 4\n* eval\\_batch\\_size: 8\n* seed: 42\n* distributed\\_type: multi-GPU\n* gradient\\_accumulation\\_steps: 2\n* total\\_train\\_batch\\_size: 8\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\n* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 1", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.39.0.dev0\n* Pytorch 2.1.2+cu121\n* Datasets 2.14.6\n* Tokenizers 0.15.1" ]

[ 72, 154, 5, 55 ]

[ "TAGS\n#peft #safetensors #mistral #alignment-handbook #trl #dpo #generated_from_trainer #dataset-hugodk-sch/aftonposten_title_prefs #base_model-NorLLM-AI/NorMistral-7B #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: 4\n* eval\\_batch\\_size: 8\n* seed: 42\n* distributed\\_type: multi-GPU\n* gradient\\_accumulation\\_steps: 2\n* total\\_train\\_batch\\_size: 8\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\n* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 1### Training results### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.39.0.dev0\n* Pytorch 2.1.2+cu121\n* Datasets 2.14.6\n* Tokenizers 0.15.1" ]

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

[ "1910.09700" ]

[]

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

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

[ 47, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

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

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

[ "1910.09700" ]

[]

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

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

[ 37, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

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

[ "transformers", "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" ]

[ 26, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "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", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ 42, 100, 5, 52 ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000### Training results### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ 42, 100, 5, 52 ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000### Training results### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "tensorboard", "safetensors", "trl", "sft", "generated_from_trainer", "base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0", "license:apache-2.0", "region:us" ]

[]

[]

[ "# EstigiaxLlama\n\nThis model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-Chat-v1.0 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: 16\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- training_steps: 250\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- PEFT 0.10.0\n- Transformers 4.40.0\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "TAGS\n#peft #tensorboard #safetensors #trl #sft #generated_from_trainer #base_model-TinyLlama/TinyLlama-1.1B-Chat-v1.0 #license-apache-2.0 #region-us \n", "# EstigiaxLlama\n\nThis model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-Chat-v1.0 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: 16\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- training_steps: 250\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- PEFT 0.10.0\n- Transformers 4.40.0\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ 58, 40, 7, 9, 9, 4, 120, 5, 52 ]

[ "TAGS\n#peft #tensorboard #safetensors #trl #sft #generated_from_trainer #base_model-TinyLlama/TinyLlama-1.1B-Chat-v1.0 #license-apache-2.0 #region-us \n# EstigiaxLlama\n\nThis model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-Chat-v1.0 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: 16\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- training_steps: 250\n- mixed_precision_training: Native AMP### Training results### Framework versions\n\n- PEFT 0.10.0\n- Transformers 4.40.0\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "region:us" ]

[]

[]

[ "# DDPO trained model\n num_epochs=20 \n\n train_gradient_accumulation_steps=1 \n\n sample_num_steps=30 \n\n sample_batch_size=8 \n \n train_batch_size=8 \n\n sample_num_batches_per_epoch=32 \n\n based off of stabilityai/stable-diffusion-2-base\n and then trained off of None" ]

[ "TAGS\n#region-us \n", "# DDPO trained model\n num_epochs=20 \n\n train_gradient_accumulation_steps=1 \n\n sample_num_steps=30 \n\n sample_batch_size=8 \n \n train_batch_size=8 \n\n sample_num_batches_per_epoch=32 \n\n based off of stabilityai/stable-diffusion-2-base\n and then trained off of None" ]

[ 5, 75 ]

[ "TAGS\n#region-us \n# DDPO trained model\n num_epochs=20 \n\n train_gradient_accumulation_steps=1 \n\n sample_num_steps=30 \n\n sample_batch_size=8 \n \n train_batch_size=8 \n\n sample_num_batches_per_epoch=32 \n\n based off of stabilityai/stable-diffusion-2-base\n and then trained off of None" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ 42, 100, 5, 52 ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000### Training results### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ 42, 100, 5, 52 ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000### Training results### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ 42, 100, 5, 52 ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000### Training results### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ 42, 100, 5, 52 ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000### Training results### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ 42, 100, 5, 52 ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000### Training results### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

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

[]

[ "en" ]

[ "## Exllama v2 Quantizations of NPC-LLM-3_8B\n\nUsing <a href=\"URL ExLlamaV2 v0.0.20</a> for quantization.\n\n<b>The \"main\" branch only contains the URL, download one of the other branches for the model (see below)</b>\n\nEach branch contains an individual bits per weight, with the main one containing only the URL for further conversions.\n\nConversion was done using the default calibration dataset.\n\nDefault arguments used except when the bits per weight is above 6.0, at that point the lm_head layer is quantized at 8 bits per weight instead of the default 6.\n\nOriginal model: URL\n\n\n<a href=\"URL bits per weight</a>\n\n<a href=\"URL bits per weight</a>\n\n<a href=\"URL bits per weight</a>\n\n<a href=\"URL bits per weight</a>\n\n<a href=\"URL bits per weight</a>", "## Download instructions\n\nWith git:\n\n\n\nWith huggingface hub (credit to TheBloke for instructions):\n\n\n\nTo download the 'main' (only useful if you only care about URL) branch to a folder called 'NPC-LLM-3_8B-exl2':\n\n\n\nTo download from a different branch, add the '--revision' parameter:\n\nLinux:\n\n\n\nWindows (which apparently doesn't like _ in folders sometimes?):" ]

[ "TAGS\n#text-generation #en #license-mit #region-us \n", "## Exllama v2 Quantizations of NPC-LLM-3_8B\n\nUsing <a href=\"URL ExLlamaV2 v0.0.20</a> for quantization.\n\n<b>The \"main\" branch only contains the URL, download one of the other branches for the model (see below)</b>\n\nEach branch contains an individual bits per weight, with the main one containing only the URL for further conversions.\n\nConversion was done using the default calibration dataset.\n\nDefault arguments used except when the bits per weight is above 6.0, at that point the lm_head layer is quantized at 8 bits per weight instead of the default 6.\n\nOriginal model: URL\n\n\n<a href=\"URL bits per weight</a>\n\n<a href=\"URL bits per weight</a>\n\n<a href=\"URL bits per weight</a>\n\n<a href=\"URL bits per weight</a>\n\n<a href=\"URL bits per weight</a>", "## Download instructions\n\nWith git:\n\n\n\nWith huggingface hub (credit to TheBloke for instructions):\n\n\n\nTo download the 'main' (only useful if you only care about URL) branch to a folder called 'NPC-LLM-3_8B-exl2':\n\n\n\nTo download from a different branch, add the '--revision' parameter:\n\nLinux:\n\n\n\nWindows (which apparently doesn't like _ in folders sometimes?):" ]

[ 15, 234, 95 ]

[ "TAGS\n#text-generation #en #license-mit #region-us \n## Exllama v2 Quantizations of NPC-LLM-3_8B\n\nUsing <a href=\"URL ExLlamaV2 v0.0.20</a> for quantization.\n\n<b>The \"main\" branch only contains the URL, download one of the other branches for the model (see below)</b>\n\nEach branch contains an individual bits per weight, with the main one containing only the URL for further conversions.\n\nConversion was done using the default calibration dataset.\n\nDefault arguments used except when the bits per weight is above 6.0, at that point the lm_head layer is quantized at 8 bits per weight instead of the default 6.\n\nOriginal model: URL\n\n\n<a href=\"URL bits per weight</a>\n\n<a href=\"URL bits per weight</a>\n\n<a href=\"URL bits per weight</a>\n\n<a href=\"URL bits per weight</a>\n\n<a href=\"URL bits per weight</a>## Download instructions\n\nWith git:\n\n\n\nWith huggingface hub (credit to TheBloke for instructions):\n\n\n\nTo download the 'main' (only useful if you only care about URL) branch to a folder called 'NPC-LLM-3_8B-exl2':\n\n\n\nTo download from a different branch, add the '--revision' parameter:\n\nLinux:\n\n\n\nWindows (which apparently doesn't like _ in folders sometimes?):" ]

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

[ "1910.09700" ]

[]

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

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

[ 47, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

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

[ "transformers", "safetensors", "mistral", "text-generation", "alignment-handbook", "generated_from_trainer", "trl", "dpo", "conversational", "dataset:updated", "dataset:original", "base_model:ShenaoZhang/0.01_4iters_bs256_nodpo_full6w_userresponse_iter_1", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# 0.01_4iters_bs256_nodpo_full6w_userresponse_iter_2\n\nThis model is a fine-tuned version of ShenaoZhang/0.01_4iters_bs256_nodpo_full6w_userresponse_iter_1 on the updated and the original datasets.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #alignment-handbook #generated_from_trainer #trl #dpo #conversational #dataset-updated #dataset-original #base_model-ShenaoZhang/0.01_4iters_bs256_nodpo_full6w_userresponse_iter_1 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# 0.01_4iters_bs256_nodpo_full6w_userresponse_iter_2\n\nThis model is a fine-tuned version of ShenaoZhang/0.01_4iters_bs256_nodpo_full6w_userresponse_iter_1 on the updated and the original datasets.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.15.2" ]

[ 105, 81, 7, 9, 9, 4, 155, 5, 44 ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #alignment-handbook #generated_from_trainer #trl #dpo #conversational #dataset-updated #dataset-original #base_model-ShenaoZhang/0.01_4iters_bs256_nodpo_full6w_userresponse_iter_1 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# 0.01_4iters_bs256_nodpo_full6w_userresponse_iter_2\n\nThis model is a fine-tuned version of ShenaoZhang/0.01_4iters_bs256_nodpo_full6w_userresponse_iter_1 on the updated and the original datasets.## Model description\n\nMore information needed## Intended uses & limitations\n\nMore information needed## Training and evaluation data\n\nMore information needed## Training procedure### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1### Training results### Framework versions\n\n- Transformers 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.15.2" ]

[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]

[ "1910.09700" ]

[]

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

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

[ 51, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

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

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ 42, 100, 5, 52 ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000### Training results### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ 42, 100, 5, 52 ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000### Training results### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ 42, 100, 5, 52 ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000### Training results### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ 42, 100, 5, 52 ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000### Training results### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "8-bit", "region:us" ]

[ "1910.09700" ]

[]

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

[ "TAGS\n#transformers #safetensors #llama #text-generation #conversational #arxiv-1910.09700 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #8-bit #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ 59, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #conversational #arxiv-1910.09700 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #8-bit #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.## How to Get Started with the Model\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact" ]

[ "peft", "safetensors", "arxiv:1910.09700", "base_model:mistralai/Mistral-7B-Instruct-v0.1", "region:us" ]

[ "1910.09700" ]

[]

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

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

[ 44, 6, 4, 50, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5, 13 ]

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

[ "gguf", "mergekit", "merge", "text-generation", "en", "fr", "de", "es", "it", "pt", "ja", "ko", "zh", "ar", "base_model:CohereForAI/c4ai-command-r-plus", "license:cc-by-nc-4.0", "region:us" ]

[]

[ "en", "fr", "de", "es", "it", "pt", "ja", "ko", "zh", "ar" ]

[]

[ "TAGS\n#gguf #mergekit #merge #text-generation #en #fr #de #es #it #pt #ja #ko #zh #ar #base_model-CohereForAI/c4ai-command-r-plus #license-cc-by-nc-4.0 #region-us \n" ]

[ 71 ]

[ "TAGS\n#gguf #mergekit #merge #text-generation #en #fr #de #es #it #pt #ja #ko #zh #ar #base_model-CohereForAI/c4ai-command-r-plus #license-cc-by-nc-4.0 #region-us \n" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ 42, 100, 5, 52 ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000### Training results### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

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

[ "1910.09700" ]

[]

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

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

[ 47, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

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

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ 42, 100, 5, 52 ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000### Training results### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "GGUF", "arxiv:2402.13228", "base_model:moreh/MoMo-72B-lora-1.8.7-DPO", "license:other", "region:us" ]

[ "2402.13228" ]

[]

[ "### About GGUF\n\n\nGGUF is a new format introduced by the URL team on August 21st 2023. It is a replacement for GGML, which is no longer supported by URL.\nHere is an incomplete list of clients and libraries that are known to support GGUF:\n\n\n* URL. This is the source project for GGUF, providing both a Command Line Interface (CLI) and a server option.\n* text-generation-webui, Known as the most widely used web UI, this project boasts numerous features and powerful extensions, and supports GPU acceleration.\n* Ollama Ollama is a lightweight and extensible framework designed for building and running language models locally. It features a simple API for creating, managing, and executing models, along with a library of pre-built models for use in various applications​\n* KoboldCpp, A comprehensive web UI offering GPU acceleration across all platforms and architectures, particularly renowned for storytelling.\n* GPT4All, This is a free and open source GUI that runs locally, supporting Windows, Linux, and macOS with full GPU acceleration.\n* LM Studio An intuitive and powerful local GUI for Windows and macOS (Silicon), featuring GPU acceleration.\n* LoLLMS Web UI. A notable web UI with a variety of unique features, including a comprehensive model library for easy model selection.\n* URL, An attractive, user-friendly character-based chat GUI for Windows and macOS (both Silicon and Intel), also offering GPU acceleration.\n* llama-cpp-python, A Python library equipped with GPU acceleration, LangChain support, and an OpenAI-compatible API server.\n* candle, A Rust-based ML framework focusing on performance, including GPU support, and designed for ease of use.\n* ctransformers, A Python library featuring GPU acceleration, LangChain support, and an OpenAI-compatible AI server.\n* localGPT An open-source initiative enabling private conversations with documents.\n\n\nExplanation of quantisation methods\n-----------------------------------\n\n\n\nClick to see details\nThe new methods available are:\n* GGML\\_TYPE\\_Q2\\_K - \"type-1\" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)\n* GGML\\_TYPE\\_Q3\\_K - \"type-0\" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.\n* GGML\\_TYPE\\_Q4\\_K - \"type-1\" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.\n* GGML\\_TYPE\\_Q5\\_K - \"type-1\" 5-bit quantization. Same super-block structure as GGML\\_TYPE\\_Q4\\_K resulting in 5.5 bpw\n* GGML\\_TYPE\\_Q6\\_K - \"type-0\" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw.\n\n\n\nHow to download GGUF files\n--------------------------\n\n\nNote for manual downloaders: You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single folder.\n\n\nThe following clients/libraries will automatically download models for you, providing a list of available models to choose from:\n\n\n* LM Studio\n* LoLLMS Web UI\n* URL", "### In 'text-generation-webui'\n\n\nUnder Download Model, you can enter the model repo: LiteLLMs/Smaug-72B-v0.1-GGUF and below it, a specific filename to download, such as: Q4\\_0/Q4\\_0-URL.\n\n\nThen click Download.", "### On the command line, including multiple files at once\n\n\nI recommend using the 'huggingface-hub' Python library:\n\n\nThen you can download any individual model file to the current directory, at high speed, with a command like this:\n\n\n\nMore advanced huggingface-cli download usage (click to read)\nYou can also download multiple files at once with a pattern:\n\n\nFor more documentation on downloading with 'huggingface-cli', please see: HF -> Hub Python Library -> Download files -> Download from the CLI.\n\n\nTo accelerate downloads on fast connections (1Gbit/s or higher), install 'hf\\_transfer':\n\n\nAnd set environment variable 'HF\\_HUB\\_ENABLE\\_HF\\_TRANSFER' to '1':\n\n\nWindows Command Line users: You can set the environment variable by running 'set HF\\_HUB\\_ENABLE\\_HF\\_TRANSFER=1' before the download command.\n\n\n\nExample 'URL' command\n---------------------\n\n\nMake sure you are using 'URL' from commit d0cee0d or later.\n\n\nChange '-ngl 32' to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.\n\n\nChange '-c 8192' to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by URL automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.\n\n\nIf you want to have a chat-style conversation, replace the '-p ' argument with '-i -ins'\n\n\nFor other parameters and how to use them, please refer to the URL documentation\n\n\nHow to run in 'text-generation-webui'\n-------------------------------------\n\n\nFurther instructions can be found in the text-generation-webui documentation, here: text-generation-webui/docs/04 ‐ Model URL.\n\n\nHow to run from Python code\n---------------------------\n\n\nYou can use GGUF models from Python using the llama-cpp-python or ctransformers libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.", "### How to load this model in Python code, using llama-cpp-python\n\n\nFor full documentation, please see: llama-cpp-python docs.", "#### First install the package\n\n\nRun one of the following commands, according to your system:", "#### Simple llama-cpp-python example code\n\n\nHow to use with LangChain\n-------------------------\n\n\nHere are guides on using llama-cpp-python and ctransformers with LangChain:\n\n\n* LangChain + llama-cpp-python\n* LangChain + ctransformers\n\n\nOriginal model card: Smaug-72B-v0.1\n===================================\n\n\n!image/png\n\n\n!image/png\n\n\nSmaug arrives!\n\n\nWe recently released Smaug-72B-v0.1 which has taken first place on the Open LLM Leaderboard by HuggingFace. It is the first open-source model to surpass an average score of 80%.\n\n\nSmaug-72B is finetuned directly from moreh/MoMo-72B-lora-1.8.7-DPO and is ultimately based on Qwen-72B.\n\n\nWe created Smaug-72B-v0.1 using a new fine-tuning technique, DPO-Positive (DPOP), and new pairwise preference versions of ARC, HellaSwag, and MetaMath (as well as other existing datasets). We introduce the technique and the full training details in our new paper: URL\n\n\nWe show that on datasets in which the edit distance between pairs of completions is low (such as in math-based datasets), standard DPO loss can lead to a reduction of the model's\nlikelihood of the preferred examples, as long as the relative probability between the preferred and dispreferred classes increases.\nUsing these insights, we design DPOP, a new loss function and training procedure which avoids this failure mode.\nSurprisingly, we also find that DPOP outperforms DPO across a wide variety of datasets and downstream tasks, including datasets with high edit distances between completions.\n\n\nWe believe this new approach is generally useful in training across a wide range of model types and downstream use cases, and it powers all of our Smaug models.\nWith the release of our paper and datasets, we are excited for the open source community to continue to build on and improve Smaug and spawn more dragons to dominate the LLM space!", "### Evaluation Results\n\n\n| Average | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K |\n| - | | - | -- |\n| 80.48 | 76.02 | 89.27 | 77.15 | 76.67 | 85.08 | 78.70 |", "#### MT-Bench\n\n\nWe ran MT-Bench with the llama-2 conversation template and the system prompt set to the Qwen system prompt. We got the following\nresults in single model mode:\n\n\n| First Turn | Second Turn | Average |\n| -- | - |\n| 8.18 | 7.34 | 7.76 |\n\n\nThe bottom of the card includes some sample responses from the model. We have selected responses that have high and low scores\nfrom the GPT-4 judge.", "### Contamination Results\n\n\nWe generate our contamination numbers using URL with Llama7B as our reference model.\nSmaug-72B has the following results:\n\n\nARC: 0.20, TruthfulQA: 0.39, GSM8K: 1.00\n\n\nNote that GSM8K often scores very highly on this contamination suite - we verified this by also running Llama-2-70B:\n\n\n| ARC | TruthfulQA | GSM8K |\n| - | ----- |\n| 0.22 | 0.51 | 0.89 |", "### Sample MT Bench results", "#### Example 1\n\n\nQuestion\n\n\nImagine you are writing a blog post comparing two popular smartphone models.\nDevelop an outline for the blog post, including key points and subheadings to effectively\ncompare and contrast the features, performance, and user experience of the two models.\nPlease answer in fewer than 200 words.\n\n\nResponse\n\n\nOutline:\n\n\n1. Introduction to the two smartphone models being compared (mention brand names and models)\n2. Design and Build Quality\n\t* Comparison of dimensions, weight, materials used, and overall aesthetic appeal\n\t* Water and dust resistance, if applicable\n3. Display and Screen Quality\n\t* Comparison of screen technology (OLED, IPS LCD, etc.)\n\t* Display resolution, refresh rate, and brightness levels\n4. Performance and Hardware\n\t* Processor, RAM, and storage configurations\n\t* Comparison of benchmark scores (e.g., AnTuTu, Geekbench)\n5. Camera System and Image Quality\n\t* Comparison of primary, ultra-wide, telephoto, and macro lenses (if available)\n\t* Comparison of low-light performance and image processing capabilities\n6. Battery Life and Charging\n\t* Battery capacity and estimated usage time\n\t* Charging technologies (wired, wireless, fast charging, reverse charging)\n7. Software and User Experience\n\t* Comparison of operating systems (iOS vs. Android) and their features\n\t* User interface, customization options, and app ecosystem\n8. Additional Features and Extras\n\t* Comparison of biometric authentication (fingerprint, face unlock, etc.)\n\t* Additional features like NFC, 5G connectivity, and audio quality\n9. Pricing and Value for Money\n\t* Comparison of retail prices and current offers\n\t* Assessment of overall value considering the features and performance\n10. Conclusion and recommendation for potential buyers based on their preferences", "#### Example 2\n\n\nQuestion\n\n\nIn a survey conducted at a local high school, preferences for a new school color were measured:\n58% of students liked the color blue, 45% preferred green, and 22% liked both colors.\nIf we randomly pick a student from the school, what's the probability that they would like neither blue nor green?\n\n\nAnswer\n\n\nTo find the probability that a randomly picked student would like neither blue nor green, we need to find the percentage of students who like only one color or neither color.\n\n\nFrom the given information, we know:\n\n\n* 58% like blue\n* 45% prefer green\n* 22% like both colors\n\n\nTo find the percentage of students who like only one color, we can subtract the percentage of students who like both colors from the sum of students who like blue and green:\n\n\n* 58% (blue) + 45% (green) - 22% (both) = 83%\n\n\nNow, to find the probability of a student liking neither blue nor green, we subtract the percentage of students who like at least one color from 100%:\n\n\n* 100% - 83% = 17%\n\n\nSo, the probability that a randomly picked student would like neither blue nor green is 17%.", "#### Example 3\n\n\nQuestion\n\n\nImplement a program to find the common elements in two arrays without using any extra data structures.\n\n\nAnswer\n\n\nFinding common elements in two arrays without using extra data structures can be achieved by using a simple algorithm. Here's a Python implementation of this problem:\n\n\nThis program iterates through the elements of the first array (arr1) and checks if each element is present in the second array (arr2). If it is, and the element hasn't been added to the common\\_elements list yet, it is appended. The function then returns the list of common elements.", "#### Example 4\n\n\nQuestion\n\n\nIdentify the named entities (people, organizations, locations) mentioned in the given news article.\nPlease generate a JSON dictionary that lists the named entities in three separate groups based on their entity types.\nThe key is the type of entity and the value is a list of strings.\n\n\nYesterday, Adamson Emerson, the CEO of Faraday, and Dieter Zetsche, the CEO of Daimler AG, announced plans to\nbuild a new Gigafactory in Berlin. The facility will be a joint venture between Faraday and Daimler, producing\nelectric vehicles and battery packs for both companies, creating thousands of job opportunities in the region.\nEmerson and Zetsche stated that the strategic location of Berlin, coupled with its skilled workforce and strong infrastructure,\nmakes it an ideal choice for expansion. The new Gigafactory aims to meet the growing demand for electric vehicles in Europe\nand contribute to a sustainable future. Volkswagen CEO Herbert Diess welcomed the news, saying greater collaboration will,\nbenefit the auto industry's transition to e-mobility.\n\n\nAnswer\n\n\nPlease cite the paper if you use data, model, or method in this repo." ]

[ "TAGS\n#GGUF #arxiv-2402.13228 #base_model-moreh/MoMo-72B-lora-1.8.7-DPO #license-other #region-us \n", "### About GGUF\n\n\nGGUF is a new format introduced by the URL team on August 21st 2023. It is a replacement for GGML, which is no longer supported by URL.\nHere is an incomplete list of clients and libraries that are known to support GGUF:\n\n\n* URL. This is the source project for GGUF, providing both a Command Line Interface (CLI) and a server option.\n* text-generation-webui, Known as the most widely used web UI, this project boasts numerous features and powerful extensions, and supports GPU acceleration.\n* Ollama Ollama is a lightweight and extensible framework designed for building and running language models locally. It features a simple API for creating, managing, and executing models, along with a library of pre-built models for use in various applications​\n* KoboldCpp, A comprehensive web UI offering GPU acceleration across all platforms and architectures, particularly renowned for storytelling.\n* GPT4All, This is a free and open source GUI that runs locally, supporting Windows, Linux, and macOS with full GPU acceleration.\n* LM Studio An intuitive and powerful local GUI for Windows and macOS (Silicon), featuring GPU acceleration.\n* LoLLMS Web UI. A notable web UI with a variety of unique features, including a comprehensive model library for easy model selection.\n* URL, An attractive, user-friendly character-based chat GUI for Windows and macOS (both Silicon and Intel), also offering GPU acceleration.\n* llama-cpp-python, A Python library equipped with GPU acceleration, LangChain support, and an OpenAI-compatible API server.\n* candle, A Rust-based ML framework focusing on performance, including GPU support, and designed for ease of use.\n* ctransformers, A Python library featuring GPU acceleration, LangChain support, and an OpenAI-compatible AI server.\n* localGPT An open-source initiative enabling private conversations with documents.\n\n\nExplanation of quantisation methods\n-----------------------------------\n\n\n\nClick to see details\nThe new methods available are:\n* GGML\\_TYPE\\_Q2\\_K - \"type-1\" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)\n* GGML\\_TYPE\\_Q3\\_K - \"type-0\" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.\n* GGML\\_TYPE\\_Q4\\_K - \"type-1\" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.\n* GGML\\_TYPE\\_Q5\\_K - \"type-1\" 5-bit quantization. Same super-block structure as GGML\\_TYPE\\_Q4\\_K resulting in 5.5 bpw\n* GGML\\_TYPE\\_Q6\\_K - \"type-0\" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw.\n\n\n\nHow to download GGUF files\n--------------------------\n\n\nNote for manual downloaders: You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single folder.\n\n\nThe following clients/libraries will automatically download models for you, providing a list of available models to choose from:\n\n\n* LM Studio\n* LoLLMS Web UI\n* URL", "### In 'text-generation-webui'\n\n\nUnder Download Model, you can enter the model repo: LiteLLMs/Smaug-72B-v0.1-GGUF and below it, a specific filename to download, such as: Q4\\_0/Q4\\_0-URL.\n\n\nThen click Download.", "### On the command line, including multiple files at once\n\n\nI recommend using the 'huggingface-hub' Python library:\n\n\nThen you can download any individual model file to the current directory, at high speed, with a command like this:\n\n\n\nMore advanced huggingface-cli download usage (click to read)\nYou can also download multiple files at once with a pattern:\n\n\nFor more documentation on downloading with 'huggingface-cli', please see: HF -> Hub Python Library -> Download files -> Download from the CLI.\n\n\nTo accelerate downloads on fast connections (1Gbit/s or higher), install 'hf\\_transfer':\n\n\nAnd set environment variable 'HF\\_HUB\\_ENABLE\\_HF\\_TRANSFER' to '1':\n\n\nWindows Command Line users: You can set the environment variable by running 'set HF\\_HUB\\_ENABLE\\_HF\\_TRANSFER=1' before the download command.\n\n\n\nExample 'URL' command\n---------------------\n\n\nMake sure you are using 'URL' from commit d0cee0d or later.\n\n\nChange '-ngl 32' to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.\n\n\nChange '-c 8192' to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by URL automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.\n\n\nIf you want to have a chat-style conversation, replace the '-p ' argument with '-i -ins'\n\n\nFor other parameters and how to use them, please refer to the URL documentation\n\n\nHow to run in 'text-generation-webui'\n-------------------------------------\n\n\nFurther instructions can be found in the text-generation-webui documentation, here: text-generation-webui/docs/04 ‐ Model URL.\n\n\nHow to run from Python code\n---------------------------\n\n\nYou can use GGUF models from Python using the llama-cpp-python or ctransformers libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.", "### How to load this model in Python code, using llama-cpp-python\n\n\nFor full documentation, please see: llama-cpp-python docs.", "#### First install the package\n\n\nRun one of the following commands, according to your system:", "#### Simple llama-cpp-python example code\n\n\nHow to use with LangChain\n-------------------------\n\n\nHere are guides on using llama-cpp-python and ctransformers with LangChain:\n\n\n* LangChain + llama-cpp-python\n* LangChain + ctransformers\n\n\nOriginal model card: Smaug-72B-v0.1\n===================================\n\n\n!image/png\n\n\n!image/png\n\n\nSmaug arrives!\n\n\nWe recently released Smaug-72B-v0.1 which has taken first place on the Open LLM Leaderboard by HuggingFace. It is the first open-source model to surpass an average score of 80%.\n\n\nSmaug-72B is finetuned directly from moreh/MoMo-72B-lora-1.8.7-DPO and is ultimately based on Qwen-72B.\n\n\nWe created Smaug-72B-v0.1 using a new fine-tuning technique, DPO-Positive (DPOP), and new pairwise preference versions of ARC, HellaSwag, and MetaMath (as well as other existing datasets). We introduce the technique and the full training details in our new paper: URL\n\n\nWe show that on datasets in which the edit distance between pairs of completions is low (such as in math-based datasets), standard DPO loss can lead to a reduction of the model's\nlikelihood of the preferred examples, as long as the relative probability between the preferred and dispreferred classes increases.\nUsing these insights, we design DPOP, a new loss function and training procedure which avoids this failure mode.\nSurprisingly, we also find that DPOP outperforms DPO across a wide variety of datasets and downstream tasks, including datasets with high edit distances between completions.\n\n\nWe believe this new approach is generally useful in training across a wide range of model types and downstream use cases, and it powers all of our Smaug models.\nWith the release of our paper and datasets, we are excited for the open source community to continue to build on and improve Smaug and spawn more dragons to dominate the LLM space!", "### Evaluation Results\n\n\n| Average | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K |\n| - | | - | -- |\n| 80.48 | 76.02 | 89.27 | 77.15 | 76.67 | 85.08 | 78.70 |", "#### MT-Bench\n\n\nWe ran MT-Bench with the llama-2 conversation template and the system prompt set to the Qwen system prompt. We got the following\nresults in single model mode:\n\n\n| First Turn | Second Turn | Average |\n| -- | - |\n| 8.18 | 7.34 | 7.76 |\n\n\nThe bottom of the card includes some sample responses from the model. We have selected responses that have high and low scores\nfrom the GPT-4 judge.", "### Contamination Results\n\n\nWe generate our contamination numbers using URL with Llama7B as our reference model.\nSmaug-72B has the following results:\n\n\nARC: 0.20, TruthfulQA: 0.39, GSM8K: 1.00\n\n\nNote that GSM8K often scores very highly on this contamination suite - we verified this by also running Llama-2-70B:\n\n\n| ARC | TruthfulQA | GSM8K |\n| - | ----- |\n| 0.22 | 0.51 | 0.89 |", "### Sample MT Bench results", "#### Example 1\n\n\nQuestion\n\n\nImagine you are writing a blog post comparing two popular smartphone models.\nDevelop an outline for the blog post, including key points and subheadings to effectively\ncompare and contrast the features, performance, and user experience of the two models.\nPlease answer in fewer than 200 words.\n\n\nResponse\n\n\nOutline:\n\n\n1. Introduction to the two smartphone models being compared (mention brand names and models)\n2. Design and Build Quality\n\t* Comparison of dimensions, weight, materials used, and overall aesthetic appeal\n\t* Water and dust resistance, if applicable\n3. Display and Screen Quality\n\t* Comparison of screen technology (OLED, IPS LCD, etc.)\n\t* Display resolution, refresh rate, and brightness levels\n4. Performance and Hardware\n\t* Processor, RAM, and storage configurations\n\t* Comparison of benchmark scores (e.g., AnTuTu, Geekbench)\n5. Camera System and Image Quality\n\t* Comparison of primary, ultra-wide, telephoto, and macro lenses (if available)\n\t* Comparison of low-light performance and image processing capabilities\n6. Battery Life and Charging\n\t* Battery capacity and estimated usage time\n\t* Charging technologies (wired, wireless, fast charging, reverse charging)\n7. Software and User Experience\n\t* Comparison of operating systems (iOS vs. Android) and their features\n\t* User interface, customization options, and app ecosystem\n8. Additional Features and Extras\n\t* Comparison of biometric authentication (fingerprint, face unlock, etc.)\n\t* Additional features like NFC, 5G connectivity, and audio quality\n9. Pricing and Value for Money\n\t* Comparison of retail prices and current offers\n\t* Assessment of overall value considering the features and performance\n10. Conclusion and recommendation for potential buyers based on their preferences", "#### Example 2\n\n\nQuestion\n\n\nIn a survey conducted at a local high school, preferences for a new school color were measured:\n58% of students liked the color blue, 45% preferred green, and 22% liked both colors.\nIf we randomly pick a student from the school, what's the probability that they would like neither blue nor green?\n\n\nAnswer\n\n\nTo find the probability that a randomly picked student would like neither blue nor green, we need to find the percentage of students who like only one color or neither color.\n\n\nFrom the given information, we know:\n\n\n* 58% like blue\n* 45% prefer green\n* 22% like both colors\n\n\nTo find the percentage of students who like only one color, we can subtract the percentage of students who like both colors from the sum of students who like blue and green:\n\n\n* 58% (blue) + 45% (green) - 22% (both) = 83%\n\n\nNow, to find the probability of a student liking neither blue nor green, we subtract the percentage of students who like at least one color from 100%:\n\n\n* 100% - 83% = 17%\n\n\nSo, the probability that a randomly picked student would like neither blue nor green is 17%.", "#### Example 3\n\n\nQuestion\n\n\nImplement a program to find the common elements in two arrays without using any extra data structures.\n\n\nAnswer\n\n\nFinding common elements in two arrays without using extra data structures can be achieved by using a simple algorithm. Here's a Python implementation of this problem:\n\n\nThis program iterates through the elements of the first array (arr1) and checks if each element is present in the second array (arr2). If it is, and the element hasn't been added to the common\\_elements list yet, it is appended. The function then returns the list of common elements.", "#### Example 4\n\n\nQuestion\n\n\nIdentify the named entities (people, organizations, locations) mentioned in the given news article.\nPlease generate a JSON dictionary that lists the named entities in three separate groups based on their entity types.\nThe key is the type of entity and the value is a list of strings.\n\n\nYesterday, Adamson Emerson, the CEO of Faraday, and Dieter Zetsche, the CEO of Daimler AG, announced plans to\nbuild a new Gigafactory in Berlin. The facility will be a joint venture between Faraday and Daimler, producing\nelectric vehicles and battery packs for both companies, creating thousands of job opportunities in the region.\nEmerson and Zetsche stated that the strategic location of Berlin, coupled with its skilled workforce and strong infrastructure,\nmakes it an ideal choice for expansion. The new Gigafactory aims to meet the growing demand for electric vehicles in Europe\nand contribute to a sustainable future. Volkswagen CEO Herbert Diess welcomed the news, saying greater collaboration will,\nbenefit the auto industry's transition to e-mobility.\n\n\nAnswer\n\n\nPlease cite the paper if you use data, model, or method in this repo." ]

[ 48, 877, 76, 578, 37, 20, 523, 70, 101, 119, 7, 344, 247, 126, 232 ]

[ "TAGS\n#GGUF #arxiv-2402.13228 #base_model-moreh/MoMo-72B-lora-1.8.7-DPO #license-other #region-us \n### About GGUF\n\n\nGGUF is a new format introduced by the URL team on August 21st 2023. It is a replacement for GGML, which is no longer supported by URL.\nHere is an incomplete list of clients and libraries that are known to support GGUF:\n\n\n* URL. This is the source project for GGUF, providing both a Command Line Interface (CLI) and a server option.\n* text-generation-webui, Known as the most widely used web UI, this project boasts numerous features and powerful extensions, and supports GPU acceleration.\n* Ollama Ollama is a lightweight and extensible framework designed for building and running language models locally. It features a simple API for creating, managing, and executing models, along with a library of pre-built models for use in various applications​\n* KoboldCpp, A comprehensive web UI offering GPU acceleration across all platforms and architectures, particularly renowned for storytelling.\n* GPT4All, This is a free and open source GUI that runs locally, supporting Windows, Linux, and macOS with full GPU acceleration.\n* LM Studio An intuitive and powerful local GUI for Windows and macOS (Silicon), featuring GPU acceleration.\n* LoLLMS Web UI. A notable web UI with a variety of unique features, including a comprehensive model library for easy model selection.\n* URL, An attractive, user-friendly character-based chat GUI for Windows and macOS (both Silicon and Intel), also offering GPU acceleration.\n* llama-cpp-python, A Python library equipped with GPU acceleration, LangChain support, and an OpenAI-compatible API server.\n* candle, A Rust-based ML framework focusing on performance, including GPU support, and designed for ease of use.\n* ctransformers, A Python library featuring GPU acceleration, LangChain support, and an OpenAI-compatible AI server.\n* localGPT An open-source initiative enabling private conversations with documents.\n\n\nExplanation of quantisation methods\n-----------------------------------\n\n\n\nClick to see details\nThe new methods available are:\n* GGML\\_TYPE\\_Q2\\_K - \"type-1\" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)\n* GGML\\_TYPE\\_Q3\\_K - \"type-0\" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.\n* GGML\\_TYPE\\_Q4\\_K - \"type-1\" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.\n* GGML\\_TYPE\\_Q5\\_K - \"type-1\" 5-bit quantization. Same super-block structure as GGML\\_TYPE\\_Q4\\_K resulting in 5.5 bpw\n* GGML\\_TYPE\\_Q6\\_K - \"type-0\" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw.\n\n\n\nHow to download GGUF files\n--------------------------\n\n\nNote for manual downloaders: You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single folder.\n\n\nThe following clients/libraries will automatically download models for you, providing a list of available models to choose from:\n\n\n* LM Studio\n* LoLLMS Web UI\n* URL### In 'text-generation-webui'\n\n\nUnder Download Model, you can enter the model repo: LiteLLMs/Smaug-72B-v0.1-GGUF and below it, a specific filename to download, such as: Q4\\_0/Q4\\_0-URL.\n\n\nThen click Download.### On the command line, including multiple files at once\n\n\nI recommend using the 'huggingface-hub' Python library:\n\n\nThen you can download any individual model file to the current directory, at high speed, with a command like this:\n\n\n\nMore advanced huggingface-cli download usage (click to read)\nYou can also download multiple files at once with a pattern:\n\n\nFor more documentation on downloading with 'huggingface-cli', please see: HF -> Hub Python Library -> Download files -> Download from the CLI.\n\n\nTo accelerate downloads on fast connections (1Gbit/s or higher), install 'hf\\_transfer':\n\n\nAnd set environment variable 'HF\\_HUB\\_ENABLE\\_HF\\_TRANSFER' to '1':\n\n\nWindows Command Line users: You can set the environment variable by running 'set HF\\_HUB\\_ENABLE\\_HF\\_TRANSFER=1' before the download command.\n\n\n\nExample 'URL' command\n---------------------\n\n\nMake sure you are using 'URL' from commit d0cee0d or later.\n\n\nChange '-ngl 32' to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.\n\n\nChange '-c 8192' to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by URL automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.\n\n\nIf you want to have a chat-style conversation, replace the '-p ' argument with '-i -ins'\n\n\nFor other parameters and how to use them, please refer to the URL documentation\n\n\nHow to run in 'text-generation-webui'\n-------------------------------------\n\n\nFurther instructions can be found in the text-generation-webui documentation, here: text-generation-webui/docs/04 ‐ Model URL.\n\n\nHow to run from Python code\n---------------------------\n\n\nYou can use GGUF models from Python using the llama-cpp-python or ctransformers libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.### How to load this model in Python code, using llama-cpp-python\n\n\nFor full documentation, please see: llama-cpp-python docs.#### First install the package\n\n\nRun one of the following commands, according to your system:#### Simple llama-cpp-python example code\n\n\nHow to use with LangChain\n-------------------------\n\n\nHere are guides on using llama-cpp-python and ctransformers with LangChain:\n\n\n* LangChain + llama-cpp-python\n* LangChain + ctransformers\n\n\nOriginal model card: Smaug-72B-v0.1\n===================================\n\n\n!image/png\n\n\n!image/png\n\n\nSmaug arrives!\n\n\nWe recently released Smaug-72B-v0.1 which has taken first place on the Open LLM Leaderboard by HuggingFace. It is the first open-source model to surpass an average score of 80%.\n\n\nSmaug-72B is finetuned directly from moreh/MoMo-72B-lora-1.8.7-DPO and is ultimately based on Qwen-72B.\n\n\nWe created Smaug-72B-v0.1 using a new fine-tuning technique, DPO-Positive (DPOP), and new pairwise preference versions of ARC, HellaSwag, and MetaMath (as well as other existing datasets). We introduce the technique and the full training details in our new paper: URL\n\n\nWe show that on datasets in which the edit distance between pairs of completions is low (such as in math-based datasets), standard DPO loss can lead to a reduction of the model's\nlikelihood of the preferred examples, as long as the relative probability between the preferred and dispreferred classes increases.\nUsing these insights, we design DPOP, a new loss function and training procedure which avoids this failure mode.\nSurprisingly, we also find that DPOP outperforms DPO across a wide variety of datasets and downstream tasks, including datasets with high edit distances between completions.\n\n\nWe believe this new approach is generally useful in training across a wide range of model types and downstream use cases, and it powers all of our Smaug models.\nWith the release of our paper and datasets, we are excited for the open source community to continue to build on and improve Smaug and spawn more dragons to dominate the LLM space!### Evaluation Results\n\n\n| Average | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K |\n| - | | - | -- |\n| 80.48 | 76.02 | 89.27 | 77.15 | 76.67 | 85.08 | 78.70 |#### MT-Bench\n\n\nWe ran MT-Bench with the llama-2 conversation template and the system prompt set to the Qwen system prompt. We got the following\nresults in single model mode:\n\n\n| First Turn | Second Turn | Average |\n| -- | - |\n| 8.18 | 7.34 | 7.76 |\n\n\nThe bottom of the card includes some sample responses from the model. We have selected responses that have high and low scores\nfrom the GPT-4 judge.### Contamination Results\n\n\nWe generate our contamination numbers using URL with Llama7B as our reference model.\nSmaug-72B has the following results:\n\n\nARC: 0.20, TruthfulQA: 0.39, GSM8K: 1.00\n\n\nNote that GSM8K often scores very highly on this contamination suite - we verified this by also running Llama-2-70B:\n\n\n| ARC | TruthfulQA | GSM8K |\n| - | ----- |\n| 0.22 | 0.51 | 0.89 |### Sample MT Bench results#### Example 1\n\n\nQuestion\n\n\nImagine you are writing a blog post comparing two popular smartphone models.\nDevelop an outline for the blog post, including key points and subheadings to effectively\ncompare and contrast the features, performance, and user experience of the two models.\nPlease answer in fewer than 200 words.\n\n\nResponse\n\n\nOutline:\n\n\n1. Introduction to the two smartphone models being compared (mention brand names and models)\n2. Design and Build Quality\n\t* Comparison of dimensions, weight, materials used, and overall aesthetic appeal\n\t* Water and dust resistance, if applicable\n3. Display and Screen Quality\n\t* Comparison of screen technology (OLED, IPS LCD, etc.)\n\t* Display resolution, refresh rate, and brightness levels\n4. Performance and Hardware\n\t* Processor, RAM, and storage configurations\n\t* Comparison of benchmark scores (e.g., AnTuTu, Geekbench)\n5. Camera System and Image Quality\n\t* Comparison of primary, ultra-wide, telephoto, and macro lenses (if available)\n\t* Comparison of low-light performance and image processing capabilities\n6. Battery Life and Charging\n\t* Battery capacity and estimated usage time\n\t* Charging technologies (wired, wireless, fast charging, reverse charging)\n7. Software and User Experience\n\t* Comparison of operating systems (iOS vs. Android) and their features\n\t* User interface, customization options, and app ecosystem\n8. Additional Features and Extras\n\t* Comparison of biometric authentication (fingerprint, face unlock, etc.)\n\t* Additional features like NFC, 5G connectivity, and audio quality\n9. Pricing and Value for Money\n\t* Comparison of retail prices and current offers\n\t* Assessment of overall value considering the features and performance\n10. Conclusion and recommendation for potential buyers based on their preferences#### Example 2\n\n\nQuestion\n\n\nIn a survey conducted at a local high school, preferences for a new school color were measured:\n58% of students liked the color blue, 45% preferred green, and 22% liked both colors.\nIf we randomly pick a student from the school, what's the probability that they would like neither blue nor green?\n\n\nAnswer\n\n\nTo find the probability that a randomly picked student would like neither blue nor green, we need to find the percentage of students who like only one color or neither color.\n\n\nFrom the given information, we know:\n\n\n* 58% like blue\n* 45% prefer green\n* 22% like both colors\n\n\nTo find the percentage of students who like only one color, we can subtract the percentage of students who like both colors from the sum of students who like blue and green:\n\n\n* 58% (blue) + 45% (green) - 22% (both) = 83%\n\n\nNow, to find the probability of a student liking neither blue nor green, we subtract the percentage of students who like at least one color from 100%:\n\n\n* 100% - 83% = 17%\n\n\nSo, the probability that a randomly picked student would like neither blue nor green is 17%.#### Example 3\n\n\nQuestion\n\n\nImplement a program to find the common elements in two arrays without using any extra data structures.\n\n\nAnswer\n\n\nFinding common elements in two arrays without using extra data structures can be achieved by using a simple algorithm. Here's a Python implementation of this problem:\n\n\nThis program iterates through the elements of the first array (arr1) and checks if each element is present in the second array (arr2). If it is, and the element hasn't been added to the common\\_elements list yet, it is appended. The function then returns the list of common elements.#### Example 4\n\n\nQuestion\n\n\nIdentify the named entities (people, organizations, locations) mentioned in the given news article.\nPlease generate a JSON dictionary that lists the named entities in three separate groups based on their entity types.\nThe key is the type of entity and the value is a list of strings.\n\n\nYesterday, Adamson Emerson, the CEO of Faraday, and Dieter Zetsche, the CEO of Daimler AG, announced plans to\nbuild a new Gigafactory in Berlin. The facility will be a joint venture between Faraday and Daimler, producing\nelectric vehicles and battery packs for both companies, creating thousands of job opportunities in the region.\nEmerson and Zetsche stated that the strategic location of Berlin, coupled with its skilled workforce and strong infrastructure,\nmakes it an ideal choice for expansion. The new Gigafactory aims to meet the growing demand for electric vehicles in Europe\nand contribute to a sustainable future. Volkswagen CEO Herbert Diess welcomed the news, saying greater collaboration will,\nbenefit the auto industry's transition to e-mobility.\n\n\nAnswer\n\n\nPlease cite the paper if you use data, model, or method in this repo." ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ 42, 100, 5, 52 ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000### Training results### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "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" ]

[ 41, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "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", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ 42, 100, 5, 52 ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000### Training results### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "transformers", "gguf", "text-generation-inference", "unsloth", "llama", "trl", "sft", "en", "base_model:Hugosh71/Llama-3-8B-Eden", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #text-generation-inference #unsloth #llama #trl #sft #en #base_model-Hugosh71/Llama-3-8B-Eden #license-apache-2.0 #endpoints_compatible #region-us \n" ]

[ 64 ]

[ "TAGS\n#transformers #gguf #text-generation-inference #unsloth #llama #trl #sft #en #base_model-Hugosh71/Llama-3-8B-Eden #license-apache-2.0 #endpoints_compatible #region-us \n" ]

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

[ "1910.09700" ]

[]

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

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

[ 47, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

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

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ 42, 100, 5, 52 ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000### Training results### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ 42, 100, 5, 52 ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000### Training results### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ 42, 100, 5, 52 ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000### Training results### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

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

[]

[ "en" ]

[]

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

[ 19 ]

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

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

[ "1910.09700" ]

[]

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

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

[ 31, 6, 4, 50, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5, 13 ]

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

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ 42, 100, 5, 52 ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000### Training results### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ 42, 100, 5, 52 ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000### Training results### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "span-marker", "tensorboard", "safetensors", "token-classification", "ner", "named-entity-recognition", "generated_from_span_marker_trainer", "en", "dataset:Jerado/enron_intangibles_ner", "base_model:roberta-large", "license:apache-2.0", "model-index", "region:us" ]

[]

[ "en" ]

[ "### Model Description\n\n\n* Model Type: SpanMarker\n* Encoder: roberta-large\n* Maximum Sequence Length: 256 tokens\n* Maximum Entity Length: 6 words\n* Training Dataset: Jerado/enron\\_intangibles\\_ner\n* Language: en\n* License: apache-2.0", "### Model Sources\n\n\n* Repository: SpanMarker on GitHub\n* Thesis: SpanMarker For Named Entity Recognition", "### Model Labels\n\n\n\nEvaluation\n----------", "### Metrics\n\n\n\nUses\n----", "### Direct Use for Inference", "### Downstream Use\n\n\nYou can finetune this model on your own dataset.\n\n\nClick to expand\n\nTraining Details\n----------------", "### Training Set Metrics", "### Training Hyperparameters\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 4\n* seed: 42\n* gradient\\_accumulation\\_steps: 2\n* total\\_train\\_batch\\_size: 8\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 11\n* mixed\\_precision\\_training: Native AMP", "### Training Results", "### Framework Versions\n\n\n* Python: 3.10.12\n* SpanMarker: 1.5.0\n* Transformers: 4.40.0\n* PyTorch: 2.2.1+cu121\n* Datasets: 2.19.0\n* Tokenizers: 0.19.1", "### BibTeX" ]

[ "TAGS\n#span-marker #tensorboard #safetensors #token-classification #ner #named-entity-recognition #generated_from_span_marker_trainer #en #dataset-Jerado/enron_intangibles_ner #base_model-roberta-large #license-apache-2.0 #model-index #region-us \n", "### Model Description\n\n\n* Model Type: SpanMarker\n* Encoder: roberta-large\n* Maximum Sequence Length: 256 tokens\n* Maximum Entity Length: 6 words\n* Training Dataset: Jerado/enron\\_intangibles\\_ner\n* Language: en\n* License: apache-2.0", "### Model Sources\n\n\n* Repository: SpanMarker on GitHub\n* Thesis: SpanMarker For Named Entity Recognition", "### Model Labels\n\n\n\nEvaluation\n----------", "### Metrics\n\n\n\nUses\n----", "### Direct Use for Inference", "### Downstream Use\n\n\nYou can finetune this model on your own dataset.\n\n\nClick to expand\n\nTraining Details\n----------------", "### Training Set Metrics", "### Training Hyperparameters\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 4\n* seed: 42\n* gradient\\_accumulation\\_steps: 2\n* total\\_train\\_batch\\_size: 8\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 11\n* mixed\\_precision\\_training: Native AMP", "### Training Results", "### Framework Versions\n\n\n* Python: 3.10.12\n* SpanMarker: 1.5.0\n* Transformers: 4.40.0\n* PyTorch: 2.2.1+cu121\n* Datasets: 2.19.0\n* Tokenizers: 0.19.1", "### BibTeX" ]

[ 79, 68, 25, 16, 10, 7, 39, 7, 142, 5, 66, 6 ]

[ "TAGS\n#span-marker #tensorboard #safetensors #token-classification #ner #named-entity-recognition #generated_from_span_marker_trainer #en #dataset-Jerado/enron_intangibles_ner #base_model-roberta-large #license-apache-2.0 #model-index #region-us \n### Model Description\n\n\n* Model Type: SpanMarker\n* Encoder: roberta-large\n* Maximum Sequence Length: 256 tokens\n* Maximum Entity Length: 6 words\n* Training Dataset: Jerado/enron\\_intangibles\\_ner\n* Language: en\n* License: apache-2.0### Model Sources\n\n\n* Repository: SpanMarker on GitHub\n* Thesis: SpanMarker For Named Entity Recognition### Model Labels\n\n\n\nEvaluation\n----------### Metrics\n\n\n\nUses\n----### Direct Use for Inference### Downstream Use\n\n\nYou can finetune this model on your own dataset.\n\n\nClick to expand\n\nTraining Details\n----------------### Training Set Metrics### Training Hyperparameters\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 4\n* seed: 42\n* gradient\\_accumulation\\_steps: 2\n* total\\_train\\_batch\\_size: 8\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 11\n* mixed\\_precision\\_training: Native AMP### Training Results### Framework Versions\n\n\n* Python: 3.10.12\n* SpanMarker: 1.5.0\n* Transformers: 4.40.0\n* PyTorch: 2.2.1+cu121\n* Datasets: 2.19.0\n* Tokenizers: 0.19.1### BibTeX" ]

[ "transformers", "tensorboard", "safetensors", "vit", "image-classification", "generated_from_trainer", "dataset:image_folder", "base_model:google/vit-base-patch16-224-in21k", "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: 5e-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* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 10", "### Training results", "### Framework versions\n\n\n* Transformers 4.36.0\n* Pytorch 2.0.0\n* Datasets 2.1.0\n* Tokenizers 0.15.0" ]

[ "TAGS\n#transformers #tensorboard #safetensors #vit #image-classification #generated_from_trainer #dataset-image_folder #base_model-google/vit-base-patch16-224-in21k #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: 5e-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* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 10", "### Training results", "### Framework versions\n\n\n* Transformers 4.36.0\n* Pytorch 2.0.0\n* Datasets 2.1.0\n* Tokenizers 0.15.0" ]

[ 76, 142, 5, 40 ]

[ "TAGS\n#transformers #tensorboard #safetensors #vit #image-classification #generated_from_trainer #dataset-image_folder #base_model-google/vit-base-patch16-224-in21k #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: 5e-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* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 10### Training results### Framework versions\n\n\n* Transformers 4.36.0\n* Pytorch 2.0.0\n* Datasets 2.1.0\n* Tokenizers 0.15.0" ]

[ "safetensors", "generated_from_trainer", "base_model:allenai/OLMo-1B", "license:apache-2.0", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0003\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 16\n* total\\_train\\_batch\\_size: 128\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\\_with\\_restarts\n* lr\\_scheduler\\_warmup\\_steps: 80\n* num\\_epochs: 3\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.36.0.dev0\n* Pytorch 2.1.2+cu121\n* Datasets 2.14.6\n* Tokenizers 0.14.1" ]

[ "TAGS\n#safetensors #generated_from_trainer #base_model-allenai/OLMo-1B #license-apache-2.0 #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: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 16\n* total\\_train\\_batch\\_size: 128\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\\_with\\_restarts\n* lr\\_scheduler\\_warmup\\_steps: 80\n* num\\_epochs: 3\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.36.0.dev0\n* Pytorch 2.1.2+cu121\n* Datasets 2.14.6\n* Tokenizers 0.14.1" ]

[ 35, 160, 5, 47 ]

[ "TAGS\n#safetensors #generated_from_trainer #base_model-allenai/OLMo-1B #license-apache-2.0 #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: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 16\n* total\\_train\\_batch\\_size: 128\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\\_with\\_restarts\n* lr\\_scheduler\\_warmup\\_steps: 80\n* num\\_epochs: 3\n* mixed\\_precision\\_training: Native AMP### Training results### Framework versions\n\n\n* Transformers 4.36.0.dev0\n* Pytorch 2.1.2+cu121\n* Datasets 2.14.6\n* Tokenizers 0.14.1" ]

[ "safetensors", "generated_from_trainer", "base_model:allenai/OLMo-1B", "license:apache-2.0", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0003\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 16\n* total\\_train\\_batch\\_size: 128\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\\_with\\_restarts\n* lr\\_scheduler\\_warmup\\_steps: 80\n* num\\_epochs: 3\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.36.0.dev0\n* Pytorch 2.1.2+cu121\n* Datasets 2.14.6\n* Tokenizers 0.14.1" ]

[ "TAGS\n#safetensors #generated_from_trainer #base_model-allenai/OLMo-1B #license-apache-2.0 #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: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 16\n* total\\_train\\_batch\\_size: 128\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\\_with\\_restarts\n* lr\\_scheduler\\_warmup\\_steps: 80\n* num\\_epochs: 3\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.36.0.dev0\n* Pytorch 2.1.2+cu121\n* Datasets 2.14.6\n* Tokenizers 0.14.1" ]

[ 35, 160, 5, 47 ]

[ "TAGS\n#safetensors #generated_from_trainer #base_model-allenai/OLMo-1B #license-apache-2.0 #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: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* gradient\\_accumulation\\_steps: 16\n* total\\_train\\_batch\\_size: 128\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\\_with\\_restarts\n* lr\\_scheduler\\_warmup\\_steps: 80\n* num\\_epochs: 3\n* mixed\\_precision\\_training: Native AMP### Training results### Framework versions\n\n\n* Transformers 4.36.0.dev0\n* Pytorch 2.1.2+cu121\n* Datasets 2.14.6\n* Tokenizers 0.14.1" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ 42, 100, 5, 52 ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000### Training results### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ 42, 100, 5, 52 ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000### Training results### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ 42, 100, 5, 52 ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000### Training results### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ 42, 100, 5, 52 ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000### Training results### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ 42, 100, 5, 52 ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000### Training results### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "transformers", "safetensors", "deberta-v2", "text-classification", "generated_from_trainer", "base_model:microsoft/deberta-v3-base", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "# output_dir\n\nThis model is a fine-tuned version of microsoft/deberta-v3-base on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- Loss: 0.0625\n- F Beta Score: 0.9639", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 2e-05\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\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: 3.0", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.2+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #safetensors #deberta-v2 #text-classification #generated_from_trainer #base_model-microsoft/deberta-v3-base #license-mit #autotrain_compatible #endpoints_compatible #region-us \n", "# output_dir\n\nThis model is a fine-tuned version of microsoft/deberta-v3-base on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- Loss: 0.0625\n- F Beta Score: 0.9639", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 2e-05\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\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: 3.0", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.2+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ 57, 56, 7, 9, 9, 4, 117, 5, 44 ]

[ "TAGS\n#transformers #safetensors #deberta-v2 #text-classification #generated_from_trainer #base_model-microsoft/deberta-v3-base #license-mit #autotrain_compatible #endpoints_compatible #region-us \n# output_dir\n\nThis model is a fine-tuned version of microsoft/deberta-v3-base on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- Loss: 0.0625\n- F Beta Score: 0.9639## Model description\n\nMore information needed## Intended uses & limitations\n\nMore information needed## Training and evaluation data\n\nMore information needed## Training procedure### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 2e-05\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\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: 3.0### Training results### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.2+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ 42, 100, 5, 52 ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000### Training results### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "transformers", "gguf", "mergekit", "merge", "en", "base_model:tanyakansal/WizardLM-Mistral-CodeLlama-7b", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #mergekit #merge #en #base_model-tanyakansal/WizardLM-Mistral-CodeLlama-7b #endpoints_compatible #region-us \n" ]

[ 44 ]

[ "TAGS\n#transformers #gguf #mergekit #merge #en #base_model-tanyakansal/WizardLM-Mistral-CodeLlama-7b #endpoints_compatible #region-us \n" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ 42, 100, 5, 52 ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_34M #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000### Training results### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]