brittlewis12/snorkel-mistral-pairrm-dpo-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "snorkelai/Snorkel-Mistral-PairRM-DPO",
    "datasets": [
      "snorkelai/Snorkel-Mistral-PairRM-DPO-Dataset",
      "HuggingFaceH4/ultrafeedback_binarized"
    ],
    "license": "apache-2.0",
    "language": [
      "en"
    ],
    "model_creator": "snorkelai",
    "model_name": "Snorkel-Mistral-PairRM-DPO",
    "model_type": "mistral",
    "inference": false,
    "pipeline_tag": "text-generation",
    "prompt_template": "<|im_start|>system\n{{system_message}}<|im_end|>\n<|im_start|>user\n{{prompt}}<|im_end|>\n<|im_start|>assistant\n",
    "quantized_by": "brittlewis12",
    "frontmatter": {
      "base_model": "snorkelai/Snorkel-Mistral-PairRM-DPO",
      "datasets": [
        "snorkelai/Snorkel-Mistral-PairRM-DPO-Dataset",
        "HuggingFaceH4/ultrafeedback_binarized"
      ],
      "license": "apache-2.0",
      "language": [
        "en"
      ],
      "model_creator": "snorkelai",
      "model_name": "Snorkel-Mistral-PairRM-DPO",
      "model_type": "mistral",
      "inference": "false",
      "pipeline_tag": "text-generation",
      "prompt_template": "|",
      "quantized_by": "brittlewis12"
    },
    "hero_image_url": "https://pbs.twimg.com/profile_images/1744049151241797632/0mIP-P9e_400x400.jpg",
    "summary": "Original model: Snorkel-Mistral-PairRM-DPO Model creator: Snorkel AI This repo contains GGUF format model files for Snorkel AI’s Snorkel-Mistral-PairRM-DPO. > With this demonstration, we focus on the general approach to alignment. Thus, we use a general-purpose reward model - the performant PairRM model. We use the Mistral-7B-Instruct-v0.2 model as our base LLM. ### What is GGUF? GGUF is a file format for representing AI models. It is the third version of the format, introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. Converted using llama.cpp b1960 (26d6076) ### Prompt template: ChatML `` system {{system_message}} user {{prompt}} assistant `` ---",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: snorkelai/Snorkel-Mistral-PairRM-DPO\ndatasets:\n- snorkelai/Snorkel-Mistral-PairRM-DPO-Dataset\n- HuggingFaceH4/ultrafeedback_binarized\nlicense: apache-2.0\nlanguage:\n- en\nmodel_creator: snorkelai\nmodel_name: Snorkel-Mistral-PairRM-DPO\nmodel_type: mistral\ninference: false\npipeline_tag: text-generation\nprompt_template: |\n  <|im_start|>system\n  {{system_message}}<|im_end|>\n  <|im_start|>user\n  {{prompt}}<|im_end|>\n  <|im_start|>assistant\n  \nquantized_by: brittlewis12\n---\n\n# Snorkel-Mistral-PairRM-DPO GGUF\n\nOriginal model: [Snorkel-Mistral-PairRM-DPO](https://huggingface.co/snorkelai/Snorkel-Mistral-PairRM-DPO)\nModel creator: [Snorkel AI](https://huggingface.co/snorkelai)\n\nThis repo contains GGUF format model files for Snorkel AI’s Snorkel-Mistral-PairRM-DPO.\n\n> With this demonstration, we focus on the general approach to alignment. Thus, we use a general-purpose reward model - the performant PairRM model. We use the Mistral-7B-Instruct-v0.2 model as our base LLM.\n\n\n\n### What is GGUF?\n\nGGUF is a file format for representing AI models. It is the third version of the format, introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.\nConverted using llama.cpp b1960 ([26d6076](https://github.com/ggerganov/llama.cpp/commits/26d607608d794efa56df3bdb6043a2f94c1d632c))\n\n### Prompt template: ChatML\n\n```\n<|im_start|>system\n{{system_message}}<|im_end|>\n<|im_start|>user\n{{prompt}}<|im_end|>\n<|im_start|>assistant\n```\n\n---\n\n## Download & run with [cnvrs](https://twitter.com/cnvrsai) on iPhone, iPad, and Mac!\n\n![cnvrs.ai](https://pbs.twimg.com/profile_images/1744049151241797632/0mIP-P9e_400x400.jpg)\n\n[cnvrs](https://testflight.apple.com/join/sFWReS7K) is the best app for private, local AI on your device:\n- create & save **Characters** with custom system prompts & temperature settings\n- download and experiment with any **GGUF model** you can [find on HuggingFace](https://huggingface.co/models?library=gguf)!\n- make it your own with custom **Theme colors**\n- powered by Metal ⚡️ & [Llama.cpp](https://github.com/ggerganov/llama.cpp), with **haptics** during response streaming!\n- **try it out** yourself today, on [Testflight](https://testflight.apple.com/join/sFWReS7K)!\n- follow [cnvrs on twitter](https://twitter.com/cnvrsai) to stay up to date\n\n---\n\n## Original Model Evaluations:\n\n> On [**Alpaca-Eval 2.0**](https://tatsu-lab.github.io/alpaca_eval/):\n> - The base model: [Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) scored **14.72**.\n> \n> After applying the above methodology:\n> - This model scored **30.22** - ranked 3rd and the highest for an open-source base model at the time of publication.\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "text-generation",
    "en",
    "dataset:snorkelai/Snorkel-Mistral-PairRM-DPO-Dataset",
    "dataset:HuggingFaceH4/ultrafeedback_binarized",
    "base_model:snorkelai/Snorkel-Mistral-PairRM-DPO",
    "base_model:quantized:snorkelai/Snorkel-Mistral-PairRM-DPO",
    "license:apache-2.0",
    "region:us",
    "conversational"
  ],
  "likes": 5,
  "downloads": 125,
  "gated": false,
  "private": false,
  "last_modified": "2024-01-24T06:02:16.000Z",
  "created_at": "2024-01-23T21:17:20.000Z",
  "pipeline_tag": "text-generation",
  "library_name": ""
}

{
  "_id": "65b02ce096123888c8eae100",
  "id": "brittlewis12/Snorkel-Mistral-PairRM-DPO-GGUF",
  "modelId": "brittlewis12/Snorkel-Mistral-PairRM-DPO-GGUF",
  "sha": "7dcb18d11c7f5f15963d323b41a94e72bb6d5ae9",
  "createdAt": "2024-01-23T21:17:20.000Z",
  "lastModified": "2024-01-24T06:02:16.000Z",
  "author": "brittlewis12",
  "downloads": 125,
  "likes": 5,
  "gated": false,
  "private": false,
  "pipeline_tag": "text-generation",
  "library_name": "",
  "siblings_count": 13
}