richarderkhov/pjmixers-dev_-_llama-3.2-instruct-jankmixbread-v0.1-3b-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\nLLaMa-3.2-Instruct-JankMixBread-v0.1-3B - GGUF\n- Model creator: https://huggingface.co/PJMixers-Dev/\n- Original model: https://huggingface.co/PJMixers-Dev/LLaMa-3.2-Instruct-JankMixBread-v0.1-3B/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q2_K.gguf](https://huggingface.co/RichardErkhov/PJMixers-Dev_-_LLaMa-3.2-Instruct-JankMixBread-v0.1-3B-gguf/blob/main/LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q2_K.gguf) | Q2_K | 1.27GB |\n| [LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/PJMixers-Dev_-_LLaMa-3.2-Instruct-JankMixBread-v0.1-3B-gguf/blob/main/LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.IQ3_XS.gguf) | IQ3_XS | 1.38GB |\n| [LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/PJMixers-Dev_-_LLaMa-3.2-Instruct-JankMixBread-v0.1-3B-gguf/blob/main/LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.IQ3_S.gguf) | IQ3_S | 1.44GB |\n| [LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/PJMixers-Dev_-_LLaMa-3.2-Instruct-JankMixBread-v0.1-3B-gguf/blob/main/LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q3_K_S.gguf) | Q3_K_S | 1.44GB |\n| [LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/PJMixers-Dev_-_LLaMa-3.2-Instruct-JankMixBread-v0.1-3B-gguf/blob/main/LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.IQ3_M.gguf) | IQ3_M | 1.49GB |\n| [LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q3_K.gguf](https://huggingface.co/RichardErkhov/PJMixers-Dev_-_LLaMa-3.2-Instruct-JankMixBread-v0.1-3B-gguf/blob/main/LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q3_K.gguf) | Q3_K | 1.57GB |\n| [LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/PJMixers-Dev_-_LLaMa-3.2-Instruct-JankMixBread-v0.1-3B-gguf/blob/main/LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q3_K_M.gguf) | Q3_K_M | 1.57GB |\n| [LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/PJMixers-Dev_-_LLaMa-3.2-Instruct-JankMixBread-v0.1-3B-gguf/blob/main/LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q3_K_L.gguf) | Q3_K_L | 1.69GB |\n| [LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/PJMixers-Dev_-_LLaMa-3.2-Instruct-JankMixBread-v0.1-3B-gguf/blob/main/LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.IQ4_XS.gguf) | IQ4_XS | 1.71GB |\n| [LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q4_0.gguf](https://huggingface.co/RichardErkhov/PJMixers-Dev_-_LLaMa-3.2-Instruct-JankMixBread-v0.1-3B-gguf/blob/main/LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q4_0.gguf) | Q4_0 | 1.79GB |\n| [LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/PJMixers-Dev_-_LLaMa-3.2-Instruct-JankMixBread-v0.1-3B-gguf/blob/main/LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.IQ4_NL.gguf) | IQ4_NL | 1.79GB |\n| [LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/PJMixers-Dev_-_LLaMa-3.2-Instruct-JankMixBread-v0.1-3B-gguf/blob/main/LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q4_K_S.gguf) | Q4_K_S | 1.8GB |\n| [LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q4_K.gguf](https://huggingface.co/RichardErkhov/PJMixers-Dev_-_LLaMa-3.2-Instruct-JankMixBread-v0.1-3B-gguf/blob/main/LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q4_K.gguf) | Q4_K | 1.88GB |\n| [LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/PJMixers-Dev_-_LLaMa-3.2-Instruct-JankMixBread-v0.1-3B-gguf/blob/main/LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q4_K_M.gguf) | Q4_K_M | 1.88GB |\n| [LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q4_1.gguf](https://huggingface.co/RichardErkhov/PJMixers-Dev_-_LLaMa-3.2-Instruct-JankMixBread-v0.1-3B-gguf/blob/main/LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q4_1.gguf) | Q4_1 | 1.95GB |\n| [LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q5_0.gguf](https://huggingface.co/RichardErkhov/PJMixers-Dev_-_LLaMa-3.2-Instruct-JankMixBread-v0.1-3B-gguf/blob/main/LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q5_0.gguf) | Q5_0 | 2.11GB |\n| [LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/PJMixers-Dev_-_LLaMa-3.2-Instruct-JankMixBread-v0.1-3B-gguf/blob/main/LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q5_K_S.gguf) | Q5_K_S | 2.11GB |\n| [LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q5_K.gguf](https://huggingface.co/RichardErkhov/PJMixers-Dev_-_LLaMa-3.2-Instruct-JankMixBread-v0.1-3B-gguf/blob/main/LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q5_K.gguf) | Q5_K | 2.16GB |\n| [LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/PJMixers-Dev_-_LLaMa-3.2-Instruct-JankMixBread-v0.1-3B-gguf/blob/main/LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q5_K_M.gguf) | Q5_K_M | 2.16GB |\n| [LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q5_1.gguf](https://huggingface.co/RichardErkhov/PJMixers-Dev_-_LLaMa-3.2-Instruct-JankMixBread-v0.1-3B-gguf/blob/main/LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q5_1.gguf) | Q5_1 | 2.28GB |\n| [LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q6_K.gguf](https://huggingface.co/RichardErkhov/PJMixers-Dev_-_LLaMa-3.2-Instruct-JankMixBread-v0.1-3B-gguf/blob/main/LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q6_K.gguf) | Q6_K | 2.46GB |\n| [LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q8_0.gguf](https://huggingface.co/RichardErkhov/PJMixers-Dev_-_LLaMa-3.2-Instruct-JankMixBread-v0.1-3B-gguf/blob/main/LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.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- meta-llama/Llama-3.2-3B\n- meta-llama/Llama-3.2-3B-Instruct\n- PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B\nmodel-index:\n- name: LLaMa-3.2-Instruct-JankMixBread-v0.1-3B\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: 50.41\n      name: strict accuracy\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=PJMixers-Dev/LLaMa-3.2-Instruct-JankMixBread-v0.1-3B\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: 22.76\n      name: normalized accuracy\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=PJMixers-Dev/LLaMa-3.2-Instruct-JankMixBread-v0.1-3B\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: 10.73\n      name: exact match\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=PJMixers-Dev/LLaMa-3.2-Instruct-JankMixBread-v0.1-3B\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: 4.36\n      name: acc_norm\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=PJMixers-Dev/LLaMa-3.2-Instruct-JankMixBread-v0.1-3B\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: 4.68\n      name: acc_norm\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=PJMixers-Dev/LLaMa-3.2-Instruct-JankMixBread-v0.1-3B\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: 23.15\n      name: accuracy\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=PJMixers-Dev/LLaMa-3.2-Instruct-JankMixBread-v0.1-3B\n      name: Open LLM Leaderboard\n---\n# LLaMa-3.2-Instruct-JankMixBread-v0.1-3B\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 breadcrumbs_ties merge method using [meta-llama/Llama-3.2-3B](https://huggingface.co/meta-llama/Llama-3.2-3B) as a base.\n\n### Models Merged\n\nThe following models were included in the merge:\n* [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct)\n* [PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B](https://huggingface.co/PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B)\n\n### Configuration\n\nThe following YAML configuration was used to produce this model:\n\n```yaml\nmerge_method: breadcrumbs_ties\nbase_model: meta-llama/Llama-3.2-3B\ntokenizer_source: PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B\ndtype: bfloat16\nparameters:\n  normalize: true\nmodels:\n  - model: meta-llama/Llama-3.2-3B-Instruct\n    parameters:\n      weight: 1\n      density: 0.9\n      gamma: 0.01\n  - model: PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B\n    parameters:\n      weight: 1\n      density: 0.9\n      gamma: 0.01\n\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_PJMixers-Dev__LLaMa-3.2-Instruct-JankMixBread-v0.1-3B)\n\n|      Metric       |Value|\n|-------------------|----:|\n|Avg.               |19.35|\n|IFEval (0-Shot)    |50.41|\n|BBH (3-Shot)       |22.76|\n|MATH Lvl 5 (4-Shot)|10.73|\n|GPQA (0-shot)      | 4.36|\n|MuSR (0-shot)      | 4.68|\n|MMLU-PRO (5-shot)  |23.15|\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",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 320,
  "gated": false,
  "private": false,
  "last_modified": "2024-10-21T10:30:21.000Z",
  "created_at": "2024-10-21T10:05:24.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "67162764fc14a25260d88473",
  "id": "RichardErkhov/PJMixers-Dev_-_LLaMa-3.2-Instruct-JankMixBread-v0.1-3B-gguf",
  "modelId": "RichardErkhov/PJMixers-Dev_-_LLaMa-3.2-Instruct-JankMixBread-v0.1-3B-gguf",
  "sha": "8dcdca815d480b9d790376ea4cd9a5c40fae1ce0",
  "createdAt": "2024-10-21T10:05:24.000Z",
  "lastModified": "2024-10-21T10:30:21.000Z",
  "author": "RichardErkhov",
  "downloads": 320,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}