richarderkhov/cloudyu_-_mixtral-8x7b-instruct-v0.1-dpo-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "mixtral-dpo.jpg",
    "summary": "* try to improve mistralai/Mixtral-8x7B-Instruct-v0.1 by DPO training * DPO Trainer Metrics improved by Truthful DPO traingin after 100 steps !Metrsc improment # Open LLM Leaderboard Evaluation Results Detailed results can be found here |             Metric              |Value| |---------------------------------|----:| |Avg.                             |73.44| |AI2 Reasoning Challenge (25-Shot)|69.80| |HellaSwag (10-Shot)              |87.83| |MMLU (5-Shot)                    |71.05| |TruthfulQA (0-shot)              |69.18| |Winogrande (5-shot)              |81.37| |GSM8k (5-shot)                   |61.41|",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "Quantization made by Richard Erkhov.\n\n[Github](https://github.com/RichardErkhov)\n\n[Discord](https://discord.gg/pvy7H8DZMG)\n\n[Request more models](https://github.com/RichardErkhov/quant_request)\n\n\nMixtral-8x7B-Instruct-v0.1-DPO - GGUF\n- Model creator: https://huggingface.co/cloudyu/\n- Original model: https://huggingface.co/cloudyu/Mixtral-8x7B-Instruct-v0.1-DPO/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [Mixtral-8x7B-Instruct-v0.1-DPO.Q2_K.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Mixtral-8x7B-Instruct-v0.1-DPO-gguf/blob/main/Mixtral-8x7B-Instruct-v0.1-DPO.Q2_K.gguf) | Q2_K | 16.12GB |\n| [Mixtral-8x7B-Instruct-v0.1-DPO.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Mixtral-8x7B-Instruct-v0.1-DPO-gguf/blob/main/Mixtral-8x7B-Instruct-v0.1-DPO.IQ3_XS.gguf) | IQ3_XS | 18.02GB |\n| [Mixtral-8x7B-Instruct-v0.1-DPO.IQ3_S.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Mixtral-8x7B-Instruct-v0.1-DPO-gguf/blob/main/Mixtral-8x7B-Instruct-v0.1-DPO.IQ3_S.gguf) | IQ3_S | 19.03GB |\n| [Mixtral-8x7B-Instruct-v0.1-DPO.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Mixtral-8x7B-Instruct-v0.1-DPO-gguf/blob/main/Mixtral-8x7B-Instruct-v0.1-DPO.Q3_K_S.gguf) | Q3_K_S | 19.03GB |\n| [Mixtral-8x7B-Instruct-v0.1-DPO.IQ3_M.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Mixtral-8x7B-Instruct-v0.1-DPO-gguf/blob/main/Mixtral-8x7B-Instruct-v0.1-DPO.IQ3_M.gguf) | IQ3_M | 19.96GB |\n| [Mixtral-8x7B-Instruct-v0.1-DPO.Q3_K.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Mixtral-8x7B-Instruct-v0.1-DPO-gguf/blob/main/Mixtral-8x7B-Instruct-v0.1-DPO.Q3_K.gguf) | Q3_K | 21.0GB |\n| [Mixtral-8x7B-Instruct-v0.1-DPO.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Mixtral-8x7B-Instruct-v0.1-DPO-gguf/blob/main/Mixtral-8x7B-Instruct-v0.1-DPO.Q3_K_M.gguf) | Q3_K_M | 21.0GB |\n| [Mixtral-8x7B-Instruct-v0.1-DPO.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Mixtral-8x7B-Instruct-v0.1-DPO-gguf/blob/main/Mixtral-8x7B-Instruct-v0.1-DPO.Q3_K_L.gguf) | Q3_K_L | 22.51GB |\n| [Mixtral-8x7B-Instruct-v0.1-DPO.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Mixtral-8x7B-Instruct-v0.1-DPO-gguf/blob/main/Mixtral-8x7B-Instruct-v0.1-DPO.IQ4_XS.gguf) | IQ4_XS | 23.63GB |\n| [Mixtral-8x7B-Instruct-v0.1-DPO.Q4_0.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Mixtral-8x7B-Instruct-v0.1-DPO-gguf/blob/main/Mixtral-8x7B-Instruct-v0.1-DPO.Q4_0.gguf) | Q4_0 | 24.63GB |\n| [Mixtral-8x7B-Instruct-v0.1-DPO.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Mixtral-8x7B-Instruct-v0.1-DPO-gguf/blob/main/Mixtral-8x7B-Instruct-v0.1-DPO.IQ4_NL.gguf) | IQ4_NL | 24.91GB |\n| [Mixtral-8x7B-Instruct-v0.1-DPO.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Mixtral-8x7B-Instruct-v0.1-DPO-gguf/blob/main/Mixtral-8x7B-Instruct-v0.1-DPO.Q4_K_S.gguf) | Q4_K_S | 24.91GB |\n| [Mixtral-8x7B-Instruct-v0.1-DPO.Q4_K.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Mixtral-8x7B-Instruct-v0.1-DPO-gguf/blob/main/Mixtral-8x7B-Instruct-v0.1-DPO.Q4_K.gguf) | Q4_K | 26.49GB |\n| [Mixtral-8x7B-Instruct-v0.1-DPO.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Mixtral-8x7B-Instruct-v0.1-DPO-gguf/blob/main/Mixtral-8x7B-Instruct-v0.1-DPO.Q4_K_M.gguf) | Q4_K_M | 26.49GB |\n| [Mixtral-8x7B-Instruct-v0.1-DPO.Q4_1.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Mixtral-8x7B-Instruct-v0.1-DPO-gguf/blob/main/Mixtral-8x7B-Instruct-v0.1-DPO.Q4_1.gguf) | Q4_1 | 27.32GB |\n| [Mixtral-8x7B-Instruct-v0.1-DPO.Q5_0.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Mixtral-8x7B-Instruct-v0.1-DPO-gguf/blob/main/Mixtral-8x7B-Instruct-v0.1-DPO.Q5_0.gguf) | Q5_0 | 30.02GB |\n| [Mixtral-8x7B-Instruct-v0.1-DPO.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Mixtral-8x7B-Instruct-v0.1-DPO-gguf/blob/main/Mixtral-8x7B-Instruct-v0.1-DPO.Q5_K_S.gguf) | Q5_K_S | 30.02GB |\n| [Mixtral-8x7B-Instruct-v0.1-DPO.Q5_K.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Mixtral-8x7B-Instruct-v0.1-DPO-gguf/blob/main/Mixtral-8x7B-Instruct-v0.1-DPO.Q5_K.gguf) | Q5_K | 30.95GB |\n| [Mixtral-8x7B-Instruct-v0.1-DPO.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Mixtral-8x7B-Instruct-v0.1-DPO-gguf/blob/main/Mixtral-8x7B-Instruct-v0.1-DPO.Q5_K_M.gguf) | Q5_K_M | 30.95GB |\n| [Mixtral-8x7B-Instruct-v0.1-DPO.Q5_1.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Mixtral-8x7B-Instruct-v0.1-DPO-gguf/blob/main/Mixtral-8x7B-Instruct-v0.1-DPO.Q5_1.gguf) | Q5_1 | 32.71GB |\n| [Mixtral-8x7B-Instruct-v0.1-DPO.Q6_K.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Mixtral-8x7B-Instruct-v0.1-DPO-gguf/blob/main/Mixtral-8x7B-Instruct-v0.1-DPO.Q6_K.gguf) | Q6_K | 35.74GB |\n| [Mixtral-8x7B-Instruct-v0.1-DPO.Q8_0.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Mixtral-8x7B-Instruct-v0.1-DPO-gguf/tree/main/) | Q8_0 | 46.22GB |\n\n\n\n\nOriginal model description:\n---\nlanguage:\n- fr\n- it\n- de\n- es\n- en\nlicense: apache-2.0\ntags:\n- moe\nmodel-index:\n- name: Mixtral-8x7B-Instruct-v0.1-DPO\n  results:\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: AI2 Reasoning Challenge (25-Shot)\n      type: ai2_arc\n      config: ARC-Challenge\n      split: test\n      args:\n        num_few_shot: 25\n    metrics:\n    - type: acc_norm\n      value: 69.8\n      name: normalized accuracy\n    source:\n      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral-8x7B-Instruct-v0.1-DPO\n      name: Open LLM Leaderboard\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: HellaSwag (10-Shot)\n      type: hellaswag\n      split: validation\n      args:\n        num_few_shot: 10\n    metrics:\n    - type: acc_norm\n      value: 87.83\n      name: normalized accuracy\n    source:\n      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral-8x7B-Instruct-v0.1-DPO\n      name: Open LLM Leaderboard\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: MMLU (5-Shot)\n      type: cais/mmlu\n      config: all\n      split: test\n      args:\n        num_few_shot: 5\n    metrics:\n    - type: acc\n      value: 71.05\n      name: accuracy\n    source:\n      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral-8x7B-Instruct-v0.1-DPO\n      name: Open LLM Leaderboard\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: TruthfulQA (0-shot)\n      type: truthful_qa\n      config: multiple_choice\n      split: validation\n      args:\n        num_few_shot: 0\n    metrics:\n    - type: mc2\n      value: 69.18\n    source:\n      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral-8x7B-Instruct-v0.1-DPO\n      name: Open LLM Leaderboard\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: Winogrande (5-shot)\n      type: winogrande\n      config: winogrande_xl\n      split: validation\n      args:\n        num_few_shot: 5\n    metrics:\n    - type: acc\n      value: 81.37\n      name: accuracy\n    source:\n      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral-8x7B-Instruct-v0.1-DPO\n      name: Open LLM Leaderboard\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: GSM8k (5-shot)\n      type: gsm8k\n      config: main\n      split: test\n      args:\n        num_few_shot: 5\n    metrics:\n    - type: acc\n      value: 61.41\n      name: accuracy\n    source:\n      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral-8x7B-Instruct-v0.1-DPO\n      name: Open LLM Leaderboard\n---\n# Model Card for cloudyu/Mixtral-8x7B-Instruct-v0.1-DPO\n\n * [try to improve mistralai/Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) by DPO training \n\n * [DPO Trainer](https://huggingface.co/docs/trl/main/en/dpo_trainer)\n\n\nMetrics improved by Truthful DPO traingin after 100 steps\n![Metrsc improment](mixtral-dpo.jpg)\n\n\n# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)\nDetailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_cloudyu__Mixtral-8x7B-Instruct-v0.1-DPO)\n\n|             Metric              |Value|\n|---------------------------------|----:|\n|Avg.                             |73.44|\n|AI2 Reasoning Challenge (25-Shot)|69.80|\n|HellaSwag (10-Shot)              |87.83|\n|MMLU (5-Shot)                    |71.05|\n|TruthfulQA (0-shot)              |69.18|\n|Winogrande (5-shot)              |81.37|\n|GSM8k (5-shot)                   |61.41|\n\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 162,
  "gated": false,
  "private": false,
  "last_modified": "2024-09-23T10:51:11.000Z",
  "created_at": "2024-09-23T00:52:31.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "66f0bbcfe4f01735dbe90434",
  "id": "RichardErkhov/cloudyu_-_Mixtral-8x7B-Instruct-v0.1-DPO-gguf",
  "modelId": "RichardErkhov/cloudyu_-_Mixtral-8x7B-Instruct-v0.1-DPO-gguf",
  "sha": "9f4616bfacda97f09a937d104bac928fb1a74017",
  "createdAt": "2024-09-23T00:52:31.000Z",
  "lastModified": "2024-09-23T10:51:11.000Z",
  "author": "RichardErkhov",
  "downloads": 162,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 25
}