richarderkhov/saishf_-_kuro-lotus-10.7b-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\nKuro-Lotus-10.7B - GGUF\n- Model creator: https://huggingface.co/saishf/\n- Original model: https://huggingface.co/saishf/Kuro-Lotus-10.7B/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [Kuro-Lotus-10.7B.Q2_K.gguf](https://huggingface.co/RichardErkhov/saishf_-_Kuro-Lotus-10.7B-gguf/blob/main/Kuro-Lotus-10.7B.Q2_K.gguf) | Q2_K | 3.73GB |\n| [Kuro-Lotus-10.7B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/saishf_-_Kuro-Lotus-10.7B-gguf/blob/main/Kuro-Lotus-10.7B.IQ3_XS.gguf) | IQ3_XS | 4.14GB |\n| [Kuro-Lotus-10.7B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/saishf_-_Kuro-Lotus-10.7B-gguf/blob/main/Kuro-Lotus-10.7B.IQ3_S.gguf) | IQ3_S | 4.37GB |\n| [Kuro-Lotus-10.7B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/saishf_-_Kuro-Lotus-10.7B-gguf/blob/main/Kuro-Lotus-10.7B.Q3_K_S.gguf) | Q3_K_S | 4.34GB |\n| [Kuro-Lotus-10.7B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/saishf_-_Kuro-Lotus-10.7B-gguf/blob/main/Kuro-Lotus-10.7B.IQ3_M.gguf) | IQ3_M | 4.51GB |\n| [Kuro-Lotus-10.7B.Q3_K.gguf](https://huggingface.co/RichardErkhov/saishf_-_Kuro-Lotus-10.7B-gguf/blob/main/Kuro-Lotus-10.7B.Q3_K.gguf) | Q3_K | 4.84GB |\n| [Kuro-Lotus-10.7B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/saishf_-_Kuro-Lotus-10.7B-gguf/blob/main/Kuro-Lotus-10.7B.Q3_K_M.gguf) | Q3_K_M | 4.84GB |\n| [Kuro-Lotus-10.7B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/saishf_-_Kuro-Lotus-10.7B-gguf/blob/main/Kuro-Lotus-10.7B.Q3_K_L.gguf) | Q3_K_L | 5.26GB |\n| [Kuro-Lotus-10.7B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/saishf_-_Kuro-Lotus-10.7B-gguf/blob/main/Kuro-Lotus-10.7B.IQ4_XS.gguf) | IQ4_XS | 5.43GB |\n| [Kuro-Lotus-10.7B.Q4_0.gguf](https://huggingface.co/RichardErkhov/saishf_-_Kuro-Lotus-10.7B-gguf/blob/main/Kuro-Lotus-10.7B.Q4_0.gguf) | Q4_0 | 5.66GB |\n| [Kuro-Lotus-10.7B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/saishf_-_Kuro-Lotus-10.7B-gguf/blob/main/Kuro-Lotus-10.7B.IQ4_NL.gguf) | IQ4_NL | 5.72GB |\n| [Kuro-Lotus-10.7B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/saishf_-_Kuro-Lotus-10.7B-gguf/blob/main/Kuro-Lotus-10.7B.Q4_K_S.gguf) | Q4_K_S | 5.7GB |\n| [Kuro-Lotus-10.7B.Q4_K.gguf](https://huggingface.co/RichardErkhov/saishf_-_Kuro-Lotus-10.7B-gguf/blob/main/Kuro-Lotus-10.7B.Q4_K.gguf) | Q4_K | 6.02GB |\n| [Kuro-Lotus-10.7B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/saishf_-_Kuro-Lotus-10.7B-gguf/blob/main/Kuro-Lotus-10.7B.Q4_K_M.gguf) | Q4_K_M | 6.02GB |\n| [Kuro-Lotus-10.7B.Q4_1.gguf](https://huggingface.co/RichardErkhov/saishf_-_Kuro-Lotus-10.7B-gguf/blob/main/Kuro-Lotus-10.7B.Q4_1.gguf) | Q4_1 | 6.27GB |\n| [Kuro-Lotus-10.7B.Q5_0.gguf](https://huggingface.co/RichardErkhov/saishf_-_Kuro-Lotus-10.7B-gguf/blob/main/Kuro-Lotus-10.7B.Q5_0.gguf) | Q5_0 | 6.89GB |\n| [Kuro-Lotus-10.7B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/saishf_-_Kuro-Lotus-10.7B-gguf/blob/main/Kuro-Lotus-10.7B.Q5_K_S.gguf) | Q5_K_S | 6.89GB |\n| [Kuro-Lotus-10.7B.Q5_K.gguf](https://huggingface.co/RichardErkhov/saishf_-_Kuro-Lotus-10.7B-gguf/blob/main/Kuro-Lotus-10.7B.Q5_K.gguf) | Q5_K | 7.08GB |\n| [Kuro-Lotus-10.7B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/saishf_-_Kuro-Lotus-10.7B-gguf/blob/main/Kuro-Lotus-10.7B.Q5_K_M.gguf) | Q5_K_M | 7.08GB |\n| [Kuro-Lotus-10.7B.Q5_1.gguf](https://huggingface.co/RichardErkhov/saishf_-_Kuro-Lotus-10.7B-gguf/blob/main/Kuro-Lotus-10.7B.Q5_1.gguf) | Q5_1 | 7.51GB |\n| [Kuro-Lotus-10.7B.Q6_K.gguf](https://huggingface.co/RichardErkhov/saishf_-_Kuro-Lotus-10.7B-gguf/blob/main/Kuro-Lotus-10.7B.Q6_K.gguf) | Q6_K | 8.2GB |\n| [Kuro-Lotus-10.7B.Q8_0.gguf](https://huggingface.co/RichardErkhov/saishf_-_Kuro-Lotus-10.7B-gguf/blob/main/Kuro-Lotus-10.7B.Q8_0.gguf) | Q8_0 | 10.62GB |\n\n\n\n\nOriginal model description:\n---\nlicense: cc-by-nc-4.0\ntags:\n- mergekit\n- merge\nbase_model:\n- BlueNipples/SnowLotus-v2-10.7B\n- Himitsui/KuroMitsu-11B\nmodel-index:\n- name: Kuro-Lotus-10.7B\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: 68.69\n      name: normalized accuracy\n    source:\n      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Kuro-Lotus-10.7B\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: 87.51\n      name: normalized accuracy\n    source:\n      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Kuro-Lotus-10.7B\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: 66.64\n      name: accuracy\n    source:\n      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Kuro-Lotus-10.7B\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: 58.27\n    source:\n      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Kuro-Lotus-10.7B\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: 84.21\n      name: accuracy\n    source:\n      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Kuro-Lotus-10.7B\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: 66.11\n      name: accuracy\n    source:\n      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Kuro-Lotus-10.7B\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### Merge Method\n\nThis model was merged using the SLERP merge method.\n\n### Models Merged\n\nThe following models were included in the merge:\n* [BlueNipples/SnowLotus-v2-10.7B](https://huggingface.co/BlueNipples/SnowLotus-v2-10.7B)\n* [Himitsui/KuroMitsu-11B](https://huggingface.co/Himitsui/KuroMitsu-11B)\n\n### Configuration\n\nThe following YAML configuration was used to produce this model:\n\n```yaml\nslices:\n  - sources:\n      - model: Himitsui/KuroMitsu-11B\n        layer_range: [0, 48]\n      - model: BlueNipples/SnowLotus-v2-10.7B\n        layer_range: [0, 48]\nmerge_method: slerp\nbase_model: Himitsui/KuroMitsu-11B\nparameters:\n  t:\n    - filter: self_attn\n      value: [0.6, 0.7, 0.8, 0.9, 1]\n    - filter: mlp\n      value: [0.4, 0.3, 0.2, 0.1, 0]\n    - value: 0.5\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__Kuro-Lotus-10.7B)\n\n|             Metric              |Value|\n|---------------------------------|----:|\n|Avg.                             |71.90|\n|AI2 Reasoning Challenge (25-Shot)|68.69|\n|HellaSwag (10-Shot)              |87.51|\n|MMLU (5-Shot)                    |66.64|\n|TruthfulQA (0-shot)              |58.27|\n|Winogrande (5-shot)              |84.21|\n|GSM8k (5-shot)                   |66.11|\n\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 0,
  "downloads": 666,
  "gated": false,
  "private": false,
  "last_modified": "2024-07-28T02:52:22.000Z",
  "created_at": "2024-07-27T20:24:29.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "66a5577d98dbd1d7e9e782d8",
  "id": "RichardErkhov/saishf_-_Kuro-Lotus-10.7B-gguf",
  "modelId": "RichardErkhov/saishf_-_Kuro-Lotus-10.7B-gguf",
  "sha": "229e49cbefe05e0025b263352ba02164a35f973e",
  "createdAt": "2024-07-27T20:24:29.000Z",
  "lastModified": "2024-07-28T02:52:22.000Z",
  "author": "RichardErkhov",
  "downloads": 666,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}