richarderkhov/notasi_-_finetome-v1.5-llama3.2-3b-1007-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\nFineTome-v1.5-Llama3.2-3B-1007 - GGUF\n- Model creator: https://huggingface.co/NotASI/\n- Original model: https://huggingface.co/NotASI/FineTome-v1.5-Llama3.2-3B-1007/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [FineTome-v1.5-Llama3.2-3B-1007.Q2_K.gguf](https://huggingface.co/RichardErkhov/NotASI_-_FineTome-v1.5-Llama3.2-3B-1007-gguf/blob/main/FineTome-v1.5-Llama3.2-3B-1007.Q2_K.gguf) | Q2_K | 1.27GB |\n| [FineTome-v1.5-Llama3.2-3B-1007.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/NotASI_-_FineTome-v1.5-Llama3.2-3B-1007-gguf/blob/main/FineTome-v1.5-Llama3.2-3B-1007.IQ3_XS.gguf) | IQ3_XS | 1.38GB |\n| [FineTome-v1.5-Llama3.2-3B-1007.IQ3_S.gguf](https://huggingface.co/RichardErkhov/NotASI_-_FineTome-v1.5-Llama3.2-3B-1007-gguf/blob/main/FineTome-v1.5-Llama3.2-3B-1007.IQ3_S.gguf) | IQ3_S | 1.44GB |\n| [FineTome-v1.5-Llama3.2-3B-1007.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/NotASI_-_FineTome-v1.5-Llama3.2-3B-1007-gguf/blob/main/FineTome-v1.5-Llama3.2-3B-1007.Q3_K_S.gguf) | Q3_K_S | 1.44GB |\n| [FineTome-v1.5-Llama3.2-3B-1007.IQ3_M.gguf](https://huggingface.co/RichardErkhov/NotASI_-_FineTome-v1.5-Llama3.2-3B-1007-gguf/blob/main/FineTome-v1.5-Llama3.2-3B-1007.IQ3_M.gguf) | IQ3_M | 1.49GB |\n| [FineTome-v1.5-Llama3.2-3B-1007.Q3_K.gguf](https://huggingface.co/RichardErkhov/NotASI_-_FineTome-v1.5-Llama3.2-3B-1007-gguf/blob/main/FineTome-v1.5-Llama3.2-3B-1007.Q3_K.gguf) | Q3_K | 1.57GB |\n| [FineTome-v1.5-Llama3.2-3B-1007.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/NotASI_-_FineTome-v1.5-Llama3.2-3B-1007-gguf/blob/main/FineTome-v1.5-Llama3.2-3B-1007.Q3_K_M.gguf) | Q3_K_M | 1.57GB |\n| [FineTome-v1.5-Llama3.2-3B-1007.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/NotASI_-_FineTome-v1.5-Llama3.2-3B-1007-gguf/blob/main/FineTome-v1.5-Llama3.2-3B-1007.Q3_K_L.gguf) | Q3_K_L | 1.69GB |\n| [FineTome-v1.5-Llama3.2-3B-1007.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/NotASI_-_FineTome-v1.5-Llama3.2-3B-1007-gguf/blob/main/FineTome-v1.5-Llama3.2-3B-1007.IQ4_XS.gguf) | IQ4_XS | 1.71GB |\n| [FineTome-v1.5-Llama3.2-3B-1007.Q4_0.gguf](https://huggingface.co/RichardErkhov/NotASI_-_FineTome-v1.5-Llama3.2-3B-1007-gguf/blob/main/FineTome-v1.5-Llama3.2-3B-1007.Q4_0.gguf) | Q4_0 | 1.79GB |\n| [FineTome-v1.5-Llama3.2-3B-1007.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/NotASI_-_FineTome-v1.5-Llama3.2-3B-1007-gguf/blob/main/FineTome-v1.5-Llama3.2-3B-1007.IQ4_NL.gguf) | IQ4_NL | 1.79GB |\n| [FineTome-v1.5-Llama3.2-3B-1007.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/NotASI_-_FineTome-v1.5-Llama3.2-3B-1007-gguf/blob/main/FineTome-v1.5-Llama3.2-3B-1007.Q4_K_S.gguf) | Q4_K_S | 1.8GB |\n| [FineTome-v1.5-Llama3.2-3B-1007.Q4_K.gguf](https://huggingface.co/RichardErkhov/NotASI_-_FineTome-v1.5-Llama3.2-3B-1007-gguf/blob/main/FineTome-v1.5-Llama3.2-3B-1007.Q4_K.gguf) | Q4_K | 1.88GB |\n| [FineTome-v1.5-Llama3.2-3B-1007.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/NotASI_-_FineTome-v1.5-Llama3.2-3B-1007-gguf/blob/main/FineTome-v1.5-Llama3.2-3B-1007.Q4_K_M.gguf) | Q4_K_M | 1.88GB |\n| [FineTome-v1.5-Llama3.2-3B-1007.Q4_1.gguf](https://huggingface.co/RichardErkhov/NotASI_-_FineTome-v1.5-Llama3.2-3B-1007-gguf/blob/main/FineTome-v1.5-Llama3.2-3B-1007.Q4_1.gguf) | Q4_1 | 1.95GB |\n| [FineTome-v1.5-Llama3.2-3B-1007.Q5_0.gguf](https://huggingface.co/RichardErkhov/NotASI_-_FineTome-v1.5-Llama3.2-3B-1007-gguf/blob/main/FineTome-v1.5-Llama3.2-3B-1007.Q5_0.gguf) | Q5_0 | 2.11GB |\n| [FineTome-v1.5-Llama3.2-3B-1007.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/NotASI_-_FineTome-v1.5-Llama3.2-3B-1007-gguf/blob/main/FineTome-v1.5-Llama3.2-3B-1007.Q5_K_S.gguf) | Q5_K_S | 2.11GB |\n| [FineTome-v1.5-Llama3.2-3B-1007.Q5_K.gguf](https://huggingface.co/RichardErkhov/NotASI_-_FineTome-v1.5-Llama3.2-3B-1007-gguf/blob/main/FineTome-v1.5-Llama3.2-3B-1007.Q5_K.gguf) | Q5_K | 2.16GB |\n| [FineTome-v1.5-Llama3.2-3B-1007.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/NotASI_-_FineTome-v1.5-Llama3.2-3B-1007-gguf/blob/main/FineTome-v1.5-Llama3.2-3B-1007.Q5_K_M.gguf) | Q5_K_M | 2.16GB |\n| [FineTome-v1.5-Llama3.2-3B-1007.Q5_1.gguf](https://huggingface.co/RichardErkhov/NotASI_-_FineTome-v1.5-Llama3.2-3B-1007-gguf/blob/main/FineTome-v1.5-Llama3.2-3B-1007.Q5_1.gguf) | Q5_1 | 2.28GB |\n| [FineTome-v1.5-Llama3.2-3B-1007.Q6_K.gguf](https://huggingface.co/RichardErkhov/NotASI_-_FineTome-v1.5-Llama3.2-3B-1007-gguf/blob/main/FineTome-v1.5-Llama3.2-3B-1007.Q6_K.gguf) | Q6_K | 2.46GB |\n| [FineTome-v1.5-Llama3.2-3B-1007.Q8_0.gguf](https://huggingface.co/RichardErkhov/NotASI_-_FineTome-v1.5-Llama3.2-3B-1007-gguf/blob/main/FineTome-v1.5-Llama3.2-3B-1007.Q8_0.gguf) | Q8_0 | 3.19GB |\n\n\n\n\nOriginal model description:\n---\nlicense: llama3.2\nlibrary_name: transformers\ntags:\n- mergekit\n- merge\nbase_model:\n- unsloth/Llama-3.2-3B-Instruct\n- NotASI/FineTome-Llama3.2-3B-1002\nmodel-index:\n- name: FineTome-v1.5-Llama3.2-3B-1007\n  results:\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: IFEval (0-Shot)\n      type: HuggingFaceH4/ifeval\n      args:\n        num_few_shot: 0\n    metrics:\n    - type: inst_level_strict_acc and prompt_level_strict_acc\n      value: 55.08\n      name: strict accuracy\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=NotASI/FineTome-v1.5-Llama3.2-3B-1007\n      name: Open LLM Leaderboard\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: BBH (3-Shot)\n      type: BBH\n      args:\n        num_few_shot: 3\n    metrics:\n    - type: acc_norm\n      value: 19.46\n      name: normalized accuracy\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=NotASI/FineTome-v1.5-Llama3.2-3B-1007\n      name: Open LLM Leaderboard\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: MATH Lvl 5 (4-Shot)\n      type: hendrycks/competition_math\n      args:\n        num_few_shot: 4\n    metrics:\n    - type: exact_match\n      value: 5.14\n      name: exact match\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=NotASI/FineTome-v1.5-Llama3.2-3B-1007\n      name: Open LLM Leaderboard\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: GPQA (0-shot)\n      type: Idavidrein/gpqa\n      args:\n        num_few_shot: 0\n    metrics:\n    - type: acc_norm\n      value: 1.57\n      name: acc_norm\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=NotASI/FineTome-v1.5-Llama3.2-3B-1007\n      name: Open LLM Leaderboard\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: MuSR (0-shot)\n      type: TAUR-Lab/MuSR\n      args:\n        num_few_shot: 0\n    metrics:\n    - type: acc_norm\n      value: 4.07\n      name: acc_norm\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=NotASI/FineTome-v1.5-Llama3.2-3B-1007\n      name: Open LLM Leaderboard\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: MMLU-PRO (5-shot)\n      type: TIGER-Lab/MMLU-Pro\n      config: main\n      split: test\n      args:\n        num_few_shot: 5\n    metrics:\n    - type: acc\n      value: 16.09\n      name: accuracy\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=NotASI/FineTome-v1.5-Llama3.2-3B-1007\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 [TIES](https://arxiv.org/abs/2306.01708) merge method using [unsloth/Llama-3.2-3B-Instruct](https://huggingface.co/unsloth/Llama-3.2-3B-Instruct) as a base.\n\n### Models Merged\n\nThe following models were included in the merge:\n* [NotASI/FineTome-Llama3.2-3B-1002](https://huggingface.co/NotASI/FineTome-Llama3.2-3B-1002)\n\n### Configuration\n\nThe following YAML configuration was used to produce this model:\n\n```yaml\nmodels:\n  - model: NotASI/FineTome-Llama3.2-3B-1002\n    parameters:\n      weight: 1\n  - model: unsloth/Llama-3.2-3B-Instruct\n    parameters:\n      weight: 1\nmerge_method: ties\nbase_model: unsloth/Llama-3.2-3B-Instruct\nparameters:\n  normalize: true\n  int8_mask: true\ndtype: bfloat16\n```\n# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)\nDetailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_NotASI__FineTome-v1.5-Llama3.2-3B-1007)\n\n|      Metric       |Value|\n|-------------------|----:|\n|Avg.               |16.90|\n|IFEval (0-Shot)    |55.08|\n|BBH (3-Shot)       |19.46|\n|MATH Lvl 5 (4-Shot)| 5.14|\n|GPQA (0-shot)      | 1.57|\n|MuSR (0-shot)      | 4.07|\n|MMLU-PRO (5-shot)  |16.09|\n\n\n\n\nAdditional thanks to @nicoboss for giving me access to his private supercomputer, enabling me to provide many more quants, at much higher speed, than I would otherwise be able to.",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "arxiv:2306.01708",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 154,
  "gated": false,
  "private": false,
  "last_modified": "2024-10-21T09:18:11.000Z",
  "created_at": "2024-10-21T08:52:46.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "6716165eccf654d1b7c0a51f",
  "id": "RichardErkhov/NotASI_-_FineTome-v1.5-Llama3.2-3B-1007-gguf",
  "modelId": "RichardErkhov/NotASI_-_FineTome-v1.5-Llama3.2-3B-1007-gguf",
  "sha": "b3278f22676d57c0d6619c21bbf7e2a9c79bc6d7",
  "createdAt": "2024-10-21T08:52:46.000Z",
  "lastModified": "2024-10-21T09:18:11.000Z",
  "author": "RichardErkhov",
  "downloads": 154,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}