brittlewis12/kunoichi-dpo-v2-7b-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "SanjiWatsuki/Kunoichi-DPO-v2-7B",
    "inference": false,
    "language": [
      "en"
    ],
    "license": "cc-by-nc-4.0",
    "model_creator": "SanjiWatsuki",
    "model_name": "Kunoichi-DPO-v2-7B",
    "model_type": "mistral",
    "pipeline_tag": "text-generation",
    "prompt_template": "{{system_message}}\n\n\n### Instruction:\n{{prompt}}\n\n\n### Response:\n",
    "quantized_by": "brittlewis12",
    "frontmatter": {
      "base_model": "SanjiWatsuki/Kunoichi-DPO-v2-7B",
      "inference": "false",
      "language": [
        "en"
      ],
      "license": "cc-by-nc-4.0",
      "model_creator": "SanjiWatsuki",
      "model_name": "Kunoichi-DPO-v2-7B",
      "model_type": "mistral",
      "pipeline_tag": "text-generation",
      "prompt_template": "\"{{system_message}}",
      "quantized_by": "brittlewis12"
    },
    "hero_image_url": "https://huggingface.co/SanjiWatsuki/Kunoichi-7B/resolve/main/assets/kunoichi.png",
    "summary": "!Kunoichi-7B Original model: Kunoichi-DPO-v2-7B Model creator: SanjiWatsuki This repo contains GGUF format model files for SanjiWatsuki’s Kunoichi-DPO-v2-7B. Updated as of 2024-05-01. ### 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 build 2780 (revision b0d943de) ### Prompt template: Unknown (Alpaca) Alpaca-style was the prompt format for the original Kunoichi-7B. `` Below is an instruction that describes a task. Write a response that appropriately completes the request. ### Instruction: {{prompt}} ### Response: `` ---",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: SanjiWatsuki/Kunoichi-DPO-v2-7B\ninference: false\nlanguage:\n  - en\nlicense: cc-by-nc-4.0\nmodel_creator: SanjiWatsuki\nmodel_name: Kunoichi-DPO-v2-7B\nmodel_type: mistral\npipeline_tag: text-generation\nprompt_template: \"{{system_message}}\n\n  \n\n  ### Instruction:\n\n  {{prompt}}\n\n  \n\n  ### Response:\n\n  \"\nquantized_by: brittlewis12\n---\n\n# Kunoichi-DPO-v2-7B GGUF\n\n![Kunoichi-7B](https://huggingface.co/SanjiWatsuki/Kunoichi-7B/resolve/main/assets/kunoichi.png)\n\nOriginal model: [Kunoichi-DPO-v2-7B](https://huggingface.co/SanjiWatsuki/Kunoichi-DPO-v2-7B)\nModel creator: [SanjiWatsuki](https://huggingface.co/SanjiWatsuki)\n\nThis repo contains GGUF format model files for SanjiWatsuki’s Kunoichi-DPO-v2-7B. Updated as of 2024-05-01.\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 build 2780 (revision [b0d943de](https://github.com/ggerganov/llama.cpp/commit/b0d943de))\n\n### Prompt template: Unknown (Alpaca)\n\n[Alpaca-style](https://huggingface.co/SanjiWatsuki/Kunoichi-7B#prompt-template-custom-format-or-alpaca) was the prompt format for the original [Kunoichi-7B](https://huggingface.co/SanjiWatsuki/Kunoichi-7B).\n\n```\nBelow is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{{prompt}}\n\n### Response:\n\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| Model                | MT Bench | EQ Bench | MMLU   | Logic Test |\n|----------------------|----------|----------|---------|-------------|\n| GPT-4-Turbo         | 9.32     | -        | -       | -           |\n| GPT-4               | 8.99     | 62.52    | 86.4    | 0.86        |\n| **Kunoichi-DPO-v2-7B** | **8.51**     | **42.18**    | -    | **0.58**        |\n| Mixtral-8x7B-Instruct| 8.30     | 44.81    | 70.6    | 0.75        |\n| **Kunoichi-DPO-7B** | **8.29**     | **41.60**    | **64.83**    | **0.59**        |\n| **Kunoichi-7B**     | **8.14**     | **44.32**    | **64.9**    | **0.58**            |\n| Starling-7B         | 8.09     | -        | 63.9    | 0.51        |\n| Claude-2            | 8.06     | 52.14    | 78.5    | -           |\n| Silicon-Maid-7B     | 7.96     | 40.44    | 64.7    | 0.54           |\n| Loyal-Macaroni-Maid-7B | 7.95     | 38.66    | 64.9   | 0.57        |\n| GPT-3.5-Turbo       | 7.94     | 50.28    | 70      | 0.57        |\n| Claude-1            | 7.9       | -        | 77      | -           |\n| Openchat-3.5        | 7.81     | 37.08    | 64.3    | 0.39        |\n| Dolphin-2.6-DPO     | 7.74     | 42.88    | 61.9    | 0.53        |\n| Zephyr-7B-beta      | 7.34     | 38.71    | 61.4    | 0.30        |\n| Llama-2-70b-chat-hf | 6.86     | 51.56    | 63      | -           |\n| Neural-chat-7b-v3-1 | 6.84     | 43.61    | 62.4    | 0.30        |\n\n| Model | Average | AGIEval | GPT4All | TruthfulQA | Bigbench |\n|---|---:|---:|---:|---:|---:|\n| **Kunoichi-DPO-7B**|**58.4**|  45.08 |  74|     66.99|   47.52|\n| **Kunoichi-DPO-v2-7B**|**58.31**|  44.85|  75.05|     65.69|   47.65|\n| [Kunoichi-7B](https://huggingface.co/SanjiWatsuki/Kunoichi-7B)|57.54|  44.99|  74.86|     63.72|   46.58|\n| [OpenPipe/mistral-ft-optimized-1218](https://huggingface.co/OpenPipe/mistral-ft-optimized-1218)| 56.85 | 44.74 | 75.6 | 59.89 | 47.17 |\n| [Silicon-Maid-7B](https://huggingface.co/SanjiWatsuki/Silicon-Maid-7B) | 56.45|  44.74|  74.26|      61.5|   45.32|\n| [mlabonne/NeuralHermes-2.5-Mistral-7B](https://huggingface.co/mlabonne/NeuralHermes-2.5-Mistral-7B) | 53.51 | 43.67 | 73.24 | 55.37 | 41.76 |\n| [teknium/OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B)  | 52.42 | 42.75 | 72.99 | 52.99 | 40.94 |\n| [openchat/openchat_3.5](https://huggingface.co/openchat/openchat_3.5) | 51.34 | 42.67 | 72.92 | 47.27 | 42.51 |\n| [berkeley-nest/Starling-LM-7B-alpha](https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha) | 51.16 | 42.06 | 72.72 | 47.33 | 42.53 |\n| [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) | 50.99 | 37.33 | 71.83 | 55.1 | 39.7 |\n\n| Model                       | AlpacaEval2 | Length |\n| --------------------------- | ----------- | ------ |\n| GPT-4                       | 23.58%      | 1365   |\n| GPT-4 0314                  | 22.07%      | 1371   |\n| Mistral Medium              | 21.86%      | 1500   |\n| Mixtral 8x7B v0.1           | 18.26%      | 1465   |\n| **Kunoichi-DPO-v2**         | **17.19%**  | 1785   |\n| Claude 2                    | 17.19%      | 1069   |\n| Claude                      | 16.99%      | 1082   |\n| Gemini Pro                  | 16.85%      | 1315   |\n| GPT-4 0613                  | 15.76%      | 1140   |\n| Claude 2.1                  | 15.73%      | 1096   |\n| Mistral 7B v0.2             | 14.72%      | 1676   |\n| GPT 3.5 Turbo 0613          | 14.13%      | 1328   |\n| LLaMA2 Chat 70B             | 13.87%      | 1790   |\n| LMCocktail-10.7B-v1         | 13.15%      | 1203   |\n| WizardLM 13B V1.1           | 11.23%      | 1525   |\n| Zephyr 7B Beta              | 10.99%      | 1444   |\n| OpenHermes-2.5-Mistral (7B) | 10.34%      | 1107   |\n| GPT 3.5 Turbo 0301          | 9.62%       | 827    |\n| **Kunoichi-7B**             | **9.38%**   | 1492   |\n| GPT 3.5 Turbo 1106          | 9.18%       | 796    |\n| GPT-3.5                     | 8.56%       | 1018   |\n| Phi-2 DPO                   | 7.76%       | 1687   |\n| LLaMA2 Chat 13B             | 7.70%       | 1513   |",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "text-generation",
    "en",
    "base_model:SanjiWatsuki/Kunoichi-DPO-v2-7B",
    "base_model:quantized:SanjiWatsuki/Kunoichi-DPO-v2-7B",
    "license:cc-by-nc-4.0",
    "region:us"
  ],
  "likes": 86,
  "downloads": 3895,
  "gated": false,
  "private": false,
  "last_modified": "2024-05-02T19:16:54.000Z",
  "created_at": "2024-01-16T16:33:41.000Z",
  "pipeline_tag": "text-generation",
  "library_name": ""
}

{
  "_id": "65a6afe53efe2c547c273c69",
  "id": "brittlewis12/Kunoichi-DPO-v2-7B-GGUF",
  "modelId": "brittlewis12/Kunoichi-DPO-v2-7B-GGUF",
  "sha": "379db0ed3dab28014e08c29021094f07ba41a8e6",
  "createdAt": "2024-01-16T16:33:41.000Z",
  "lastModified": "2024-05-02T19:16:54.000Z",
  "author": "brittlewis12",
  "downloads": 3895,
  "likes": 86,
  "gated": false,
  "private": false,
  "pipeline_tag": "text-generation",
  "library_name": "",
  "siblings_count": 30
}