richarderkhov/saishf_-_fett-eris-mix-7b-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "This is a merge of pre-trained language models created using mergekit.",
    "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\nFett-Eris-Mix-7B - GGUF\n- Model creator: https://huggingface.co/saishf/\n- Original model: https://huggingface.co/saishf/Fett-Eris-Mix-7B/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [Fett-Eris-Mix-7B.Q2_K.gguf](https://huggingface.co/RichardErkhov/saishf_-_Fett-Eris-Mix-7B-gguf/blob/main/Fett-Eris-Mix-7B.Q2_K.gguf) | Q2_K | 2.53GB |\n| [Fett-Eris-Mix-7B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/saishf_-_Fett-Eris-Mix-7B-gguf/blob/main/Fett-Eris-Mix-7B.IQ3_XS.gguf) | IQ3_XS | 2.81GB |\n| [Fett-Eris-Mix-7B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/saishf_-_Fett-Eris-Mix-7B-gguf/blob/main/Fett-Eris-Mix-7B.IQ3_S.gguf) | IQ3_S | 2.96GB |\n| [Fett-Eris-Mix-7B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/saishf_-_Fett-Eris-Mix-7B-gguf/blob/main/Fett-Eris-Mix-7B.Q3_K_S.gguf) | Q3_K_S | 2.95GB |\n| [Fett-Eris-Mix-7B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/saishf_-_Fett-Eris-Mix-7B-gguf/blob/main/Fett-Eris-Mix-7B.IQ3_M.gguf) | IQ3_M | 3.06GB |\n| [Fett-Eris-Mix-7B.Q3_K.gguf](https://huggingface.co/RichardErkhov/saishf_-_Fett-Eris-Mix-7B-gguf/blob/main/Fett-Eris-Mix-7B.Q3_K.gguf) | Q3_K | 3.28GB |\n| [Fett-Eris-Mix-7B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/saishf_-_Fett-Eris-Mix-7B-gguf/blob/main/Fett-Eris-Mix-7B.Q3_K_M.gguf) | Q3_K_M | 3.28GB |\n| [Fett-Eris-Mix-7B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/saishf_-_Fett-Eris-Mix-7B-gguf/blob/main/Fett-Eris-Mix-7B.Q3_K_L.gguf) | Q3_K_L | 3.56GB |\n| [Fett-Eris-Mix-7B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/saishf_-_Fett-Eris-Mix-7B-gguf/blob/main/Fett-Eris-Mix-7B.IQ4_XS.gguf) | IQ4_XS | 3.67GB |\n| [Fett-Eris-Mix-7B.Q4_0.gguf](https://huggingface.co/RichardErkhov/saishf_-_Fett-Eris-Mix-7B-gguf/blob/main/Fett-Eris-Mix-7B.Q4_0.gguf) | Q4_0 | 3.83GB |\n| [Fett-Eris-Mix-7B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/saishf_-_Fett-Eris-Mix-7B-gguf/blob/main/Fett-Eris-Mix-7B.IQ4_NL.gguf) | IQ4_NL | 3.87GB |\n| [Fett-Eris-Mix-7B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/saishf_-_Fett-Eris-Mix-7B-gguf/blob/main/Fett-Eris-Mix-7B.Q4_K_S.gguf) | Q4_K_S | 3.86GB |\n| [Fett-Eris-Mix-7B.Q4_K.gguf](https://huggingface.co/RichardErkhov/saishf_-_Fett-Eris-Mix-7B-gguf/blob/main/Fett-Eris-Mix-7B.Q4_K.gguf) | Q4_K | 4.07GB |\n| [Fett-Eris-Mix-7B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/saishf_-_Fett-Eris-Mix-7B-gguf/blob/main/Fett-Eris-Mix-7B.Q4_K_M.gguf) | Q4_K_M | 4.07GB |\n| [Fett-Eris-Mix-7B.Q4_1.gguf](https://huggingface.co/RichardErkhov/saishf_-_Fett-Eris-Mix-7B-gguf/blob/main/Fett-Eris-Mix-7B.Q4_1.gguf) | Q4_1 | 4.24GB |\n| [Fett-Eris-Mix-7B.Q5_0.gguf](https://huggingface.co/RichardErkhov/saishf_-_Fett-Eris-Mix-7B-gguf/blob/main/Fett-Eris-Mix-7B.Q5_0.gguf) | Q5_0 | 4.65GB |\n| [Fett-Eris-Mix-7B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/saishf_-_Fett-Eris-Mix-7B-gguf/blob/main/Fett-Eris-Mix-7B.Q5_K_S.gguf) | Q5_K_S | 4.65GB |\n| [Fett-Eris-Mix-7B.Q5_K.gguf](https://huggingface.co/RichardErkhov/saishf_-_Fett-Eris-Mix-7B-gguf/blob/main/Fett-Eris-Mix-7B.Q5_K.gguf) | Q5_K | 4.78GB |\n| [Fett-Eris-Mix-7B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/saishf_-_Fett-Eris-Mix-7B-gguf/blob/main/Fett-Eris-Mix-7B.Q5_K_M.gguf) | Q5_K_M | 4.78GB |\n| [Fett-Eris-Mix-7B.Q5_1.gguf](https://huggingface.co/RichardErkhov/saishf_-_Fett-Eris-Mix-7B-gguf/blob/main/Fett-Eris-Mix-7B.Q5_1.gguf) | Q5_1 | 5.07GB |\n| [Fett-Eris-Mix-7B.Q6_K.gguf](https://huggingface.co/RichardErkhov/saishf_-_Fett-Eris-Mix-7B-gguf/blob/main/Fett-Eris-Mix-7B.Q6_K.gguf) | Q6_K | 5.53GB |\n| [Fett-Eris-Mix-7B.Q8_0.gguf](https://huggingface.co/RichardErkhov/saishf_-_Fett-Eris-Mix-7B-gguf/blob/main/Fett-Eris-Mix-7B.Q8_0.gguf) | Q8_0 | 7.17GB |\n\n\n\n\nOriginal model description:\n---\nlanguage:\n- en\nlicense: cc-by-nc-4.0\nlibrary_name: transformers\ntags:\n- mergekit\n- merge\nbase_model:\n- Epiculous/Fett-uccine-7B\n- eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO-v2\n- OpenPipe/mistral-ft-optimized-1227\n- ChaoticNeutrals/Eris_7B\npipeline_tag: text-generation\nmodel-index:\n- name: Fett-Eris-Mix-7B\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: 68.77\n      name: normalized accuracy\n    source:\n      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Fett-Eris-Mix-7B\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: 87.33\n      name: normalized accuracy\n    source:\n      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Fett-Eris-Mix-7B\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: 63.65\n      name: accuracy\n    source:\n      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Fett-Eris-Mix-7B\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: 71.91\n    source:\n      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Fett-Eris-Mix-7B\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: 80.82\n      name: accuracy\n    source:\n      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Fett-Eris-Mix-7B\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: 57.47\n      name: accuracy\n    source:\n      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Fett-Eris-Mix-7B\n      name: Open LLM Leaderboard\n---\n# merge\n\nThis is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).\n\n## Merge Details\n* This model is an attempt at making a smart rp model with the finesse of [Epiculous/Fett-uccine-7B](https://huggingface.co/Epiculous/Fett-uccine-7B).\n* From limited testing i've found it to be my favourite of my personal 7B models. It stays pretty coherent at 8k+ ctx.\n* I like to use \"Alpaca\" format with \"Universal-Light\" for longer messages. Switching to ChatML causes the messages to be much shorter? I haven't a clue why but sometimes it's nice.\n* It doesn't seem to show many issues but i'd be willing to try to fix any problems or bugs as it shows some potential. \n### Merge Method\n\nThis model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [OpenPipe/mistral-ft-optimized-1227](https://huggingface.co/OpenPipe/mistral-ft-optimized-1227) as a base.\n\n### Models Merged\n\nThe following models were included in the merge:\n* [Epiculous/Fett-uccine-7B](https://huggingface.co/Epiculous/Fett-uccine-7B)\n* [eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO-v2](https://huggingface.co/eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO-v2)\n* [ChaoticNeutrals/Eris_7B](https://huggingface.co/ChaoticNeutrals/Eris_7B)\n\n### Configuration\n\nThe following YAML configuration was used to produce this model:\n\n```yaml\nmodels:\n  - model: OpenPipe/mistral-ft-optimized-1227\n    # No parameters necessary for base model\n  - model: Epiculous/Fett-uccine-7B\n    parameters:\n      density: 0.53\n      weight: 0.4\n  - model: eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO-v2\n    parameters:\n      density: 0.53\n      weight: 0.35\n  - model: ChaoticNeutrals/Eris_7B\n    parameters:\n      density: 0.53\n      weight: 0.25\nmerge_method: dare_ties\nbase_model: OpenPipe/mistral-ft-optimized-1227\nparameters:\n  int8_mask: true\ndtype: bfloat16\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_saishf__Fett-Eris-Mix-7B)\n\n|             Metric              |Value|\n|---------------------------------|----:|\n|Avg.                             |71.66|\n|AI2 Reasoning Challenge (25-Shot)|68.77|\n|HellaSwag (10-Shot)              |87.33|\n|MMLU (5-Shot)                    |63.65|\n|TruthfulQA (0-shot)              |71.91|\n|Winogrande (5-shot)              |80.82|\n|GSM8k (5-shot)                   |57.47|\n\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "arxiv:2311.03099",
    "arxiv:2306.01708",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 0,
  "downloads": 81,
  "gated": false,
  "private": false,
  "last_modified": "2024-09-11T16:35:07.000Z",
  "created_at": "2024-09-11T09:12:28.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "66e15efca533df3d8281ab6b",
  "id": "RichardErkhov/saishf_-_Fett-Eris-Mix-7B-gguf",
  "modelId": "RichardErkhov/saishf_-_Fett-Eris-Mix-7B-gguf",
  "sha": "f412c7083324e8ed23ea35ceb95152e9be8bf6b2",
  "createdAt": "2024-09-11T09:12:28.000Z",
  "lastModified": "2024-09-11T16:35:07.000Z",
  "author": "RichardErkhov",
  "downloads": 81,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}