richarderkhov/zelk12_-_mt5-gemma-2-9b-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\nMT5-gemma-2-9B - GGUF\n- Model creator: https://huggingface.co/zelk12/\n- Original model: https://huggingface.co/zelk12/MT5-gemma-2-9B/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [MT5-gemma-2-9B.Q2_K.gguf](https://huggingface.co/RichardErkhov/zelk12_-_MT5-gemma-2-9B-gguf/blob/main/MT5-gemma-2-9B.Q2_K.gguf) | Q2_K | 3.54GB |\n| [MT5-gemma-2-9B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/zelk12_-_MT5-gemma-2-9B-gguf/blob/main/MT5-gemma-2-9B.IQ3_XS.gguf) | IQ3_XS | 3.86GB |\n| [MT5-gemma-2-9B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/zelk12_-_MT5-gemma-2-9B-gguf/blob/main/MT5-gemma-2-9B.IQ3_S.gguf) | IQ3_S | 4.04GB |\n| [MT5-gemma-2-9B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/zelk12_-_MT5-gemma-2-9B-gguf/blob/main/MT5-gemma-2-9B.Q3_K_S.gguf) | Q3_K_S | 4.04GB |\n| [MT5-gemma-2-9B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/zelk12_-_MT5-gemma-2-9B-gguf/blob/main/MT5-gemma-2-9B.IQ3_M.gguf) | IQ3_M | 4.19GB |\n| [MT5-gemma-2-9B.Q3_K.gguf](https://huggingface.co/RichardErkhov/zelk12_-_MT5-gemma-2-9B-gguf/blob/main/MT5-gemma-2-9B.Q3_K.gguf) | Q3_K | 4.43GB |\n| [MT5-gemma-2-9B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/zelk12_-_MT5-gemma-2-9B-gguf/blob/main/MT5-gemma-2-9B.Q3_K_M.gguf) | Q3_K_M | 4.43GB |\n| [MT5-gemma-2-9B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/zelk12_-_MT5-gemma-2-9B-gguf/blob/main/MT5-gemma-2-9B.Q3_K_L.gguf) | Q3_K_L | 4.78GB |\n| [MT5-gemma-2-9B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/zelk12_-_MT5-gemma-2-9B-gguf/blob/main/MT5-gemma-2-9B.IQ4_XS.gguf) | IQ4_XS | 4.86GB |\n| [MT5-gemma-2-9B.Q4_0.gguf](https://huggingface.co/RichardErkhov/zelk12_-_MT5-gemma-2-9B-gguf/blob/main/MT5-gemma-2-9B.Q4_0.gguf) | Q4_0 | 5.07GB |\n| [MT5-gemma-2-9B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/zelk12_-_MT5-gemma-2-9B-gguf/blob/main/MT5-gemma-2-9B.IQ4_NL.gguf) | IQ4_NL | 5.1GB |\n| [MT5-gemma-2-9B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/zelk12_-_MT5-gemma-2-9B-gguf/blob/main/MT5-gemma-2-9B.Q4_K_S.gguf) | Q4_K_S | 5.1GB |\n| [MT5-gemma-2-9B.Q4_K.gguf](https://huggingface.co/RichardErkhov/zelk12_-_MT5-gemma-2-9B-gguf/blob/main/MT5-gemma-2-9B.Q4_K.gguf) | Q4_K | 5.37GB |\n| [MT5-gemma-2-9B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/zelk12_-_MT5-gemma-2-9B-gguf/blob/main/MT5-gemma-2-9B.Q4_K_M.gguf) | Q4_K_M | 5.37GB |\n| [MT5-gemma-2-9B.Q4_1.gguf](https://huggingface.co/RichardErkhov/zelk12_-_MT5-gemma-2-9B-gguf/blob/main/MT5-gemma-2-9B.Q4_1.gguf) | Q4_1 | 5.55GB |\n| [MT5-gemma-2-9B.Q5_0.gguf](https://huggingface.co/RichardErkhov/zelk12_-_MT5-gemma-2-9B-gguf/blob/main/MT5-gemma-2-9B.Q5_0.gguf) | Q5_0 | 6.04GB |\n| [MT5-gemma-2-9B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/zelk12_-_MT5-gemma-2-9B-gguf/blob/main/MT5-gemma-2-9B.Q5_K_S.gguf) | Q5_K_S | 6.04GB |\n| [MT5-gemma-2-9B.Q5_K.gguf](https://huggingface.co/RichardErkhov/zelk12_-_MT5-gemma-2-9B-gguf/blob/main/MT5-gemma-2-9B.Q5_K.gguf) | Q5_K | 6.19GB |\n| [MT5-gemma-2-9B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/zelk12_-_MT5-gemma-2-9B-gguf/blob/main/MT5-gemma-2-9B.Q5_K_M.gguf) | Q5_K_M | 6.19GB |\n| [MT5-gemma-2-9B.Q5_1.gguf](https://huggingface.co/RichardErkhov/zelk12_-_MT5-gemma-2-9B-gguf/blob/main/MT5-gemma-2-9B.Q5_1.gguf) | Q5_1 | 6.52GB |\n| [MT5-gemma-2-9B.Q6_K.gguf](https://huggingface.co/RichardErkhov/zelk12_-_MT5-gemma-2-9B-gguf/blob/main/MT5-gemma-2-9B.Q6_K.gguf) | Q6_K | 7.07GB |\n| [MT5-gemma-2-9B.Q8_0.gguf](https://huggingface.co/RichardErkhov/zelk12_-_MT5-gemma-2-9B-gguf/blob/main/MT5-gemma-2-9B.Q8_0.gguf) | Q8_0 | 9.15GB |\n\n\n\n\nOriginal model description:\n---\nlibrary_name: transformers\ntags:\n- mergekit\n- merge\nbase_model:\n- zelk12/MT5-IGMAMU-gemma-2-9B\n- zelk12/MT5-MMB-gemma-2-9B\nmodel-index:\n- name: MT5-gemma-2-9B\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: 80.48\n      name: strict accuracy\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=zelk12/MT5-gemma-2-9B\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: 44.27\n      name: normalized accuracy\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=zelk12/MT5-gemma-2-9B\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: 8.61\n      name: exact match\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=zelk12/MT5-gemma-2-9B\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: 12.42\n      name: acc_norm\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=zelk12/MT5-gemma-2-9B\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: 11.48\n      name: acc_norm\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=zelk12/MT5-gemma-2-9B\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: 37.41\n      name: accuracy\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=zelk12/MT5-gemma-2-9B\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* [zelk12/MT5-IGMAMU-gemma-2-9B](https://huggingface.co/zelk12/MT5-IGMAMU-gemma-2-9B)\n* [zelk12/MT5-MMB-gemma-2-9B](https://huggingface.co/zelk12/MT5-MMB-gemma-2-9B)\n\n### Configuration\n\nThe following YAML configuration was used to produce this model:\n\n```yaml\nmodels:\n  - model: zelk12/MT5-MMB-gemma-2-9B\n  - model: zelk12/MT5-IGMAMU-gemma-2-9B\nmerge_method: slerp\nbase_model: zelk12/MT5-MMB-gemma-2-9B\ndtype: bfloat16\nparameters:\n  t: 0.5\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_zelk12__MT5-gemma-2-9B)\n\n|      Metric       |Value|\n|-------------------|----:|\n|Avg.               |32.44|\n|IFEval (0-Shot)    |80.48|\n|BBH (3-Shot)       |44.27|\n|MATH Lvl 5 (4-Shot)| 8.61|\n|GPQA (0-shot)      |12.42|\n|MuSR (0-shot)      |11.48|\n|MMLU-PRO (5-shot)  |37.41|\n\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 1003,
  "gated": false,
  "private": false,
  "last_modified": "2025-06-13T01:07:20.000Z",
  "created_at": "2025-06-12T22:58:28.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "684b5b94aef16192b91295ea",
  "id": "RichardErkhov/zelk12_-_MT5-gemma-2-9B-gguf",
  "modelId": "RichardErkhov/zelk12_-_MT5-gemma-2-9B-gguf",
  "sha": "9499c7f69bf20efed34a4f5d1a9fdac227cb462d",
  "createdAt": "2025-06-12T22:58:28.000Z",
  "lastModified": "2025-06-13T01:07:20.000Z",
  "author": "RichardErkhov",
  "downloads": 1003,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}