richarderkhov/davidau_-_l3-lumimaid-12.2b-v0.1-oas-instruct-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "This repo contains the full precision source code, in \"safe tensors\" format to generate GGUFs, GPTQ, EXL2, AWQ, HQQ and other formats. The source code can also be used directly. For full information about this model, including: Please go to: [ https://huggingface.co/DavidAU/L3-Lumimaid-v0.1-OAS-12.2B-INSTRUCT-ULTRA-F32-GGUF ] 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\nL3-Lumimaid-12.2B-v0.1-OAS-Instruct - GGUF\n- Model creator: https://huggingface.co/DavidAU/\n- Original model: https://huggingface.co/DavidAU/L3-Lumimaid-12.2B-v0.1-OAS-Instruct/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [L3-Lumimaid-12.2B-v0.1-OAS-Instruct.Q2_K.gguf](https://huggingface.co/RichardErkhov/DavidAU_-_L3-Lumimaid-12.2B-v0.1-OAS-Instruct-gguf/blob/main/L3-Lumimaid-12.2B-v0.1-OAS-Instruct.Q2_K.gguf) | Q2_K | 4.38GB |\n| [L3-Lumimaid-12.2B-v0.1-OAS-Instruct.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/DavidAU_-_L3-Lumimaid-12.2B-v0.1-OAS-Instruct-gguf/blob/main/L3-Lumimaid-12.2B-v0.1-OAS-Instruct.IQ3_XS.gguf) | IQ3_XS | 4.86GB |\n| [L3-Lumimaid-12.2B-v0.1-OAS-Instruct.IQ3_S.gguf](https://huggingface.co/RichardErkhov/DavidAU_-_L3-Lumimaid-12.2B-v0.1-OAS-Instruct-gguf/blob/main/L3-Lumimaid-12.2B-v0.1-OAS-Instruct.IQ3_S.gguf) | IQ3_S | 5.1GB |\n| [L3-Lumimaid-12.2B-v0.1-OAS-Instruct.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/DavidAU_-_L3-Lumimaid-12.2B-v0.1-OAS-Instruct-gguf/blob/main/L3-Lumimaid-12.2B-v0.1-OAS-Instruct.Q3_K_S.gguf) | Q3_K_S | 5.07GB |\n| [L3-Lumimaid-12.2B-v0.1-OAS-Instruct.IQ3_M.gguf](https://huggingface.co/RichardErkhov/DavidAU_-_L3-Lumimaid-12.2B-v0.1-OAS-Instruct-gguf/blob/main/L3-Lumimaid-12.2B-v0.1-OAS-Instruct.IQ3_M.gguf) | IQ3_M | 5.25GB |\n| [L3-Lumimaid-12.2B-v0.1-OAS-Instruct.Q3_K.gguf](https://huggingface.co/RichardErkhov/DavidAU_-_L3-Lumimaid-12.2B-v0.1-OAS-Instruct-gguf/blob/main/L3-Lumimaid-12.2B-v0.1-OAS-Instruct.Q3_K.gguf) | Q3_K | 5.6GB |\n| [L3-Lumimaid-12.2B-v0.1-OAS-Instruct.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/DavidAU_-_L3-Lumimaid-12.2B-v0.1-OAS-Instruct-gguf/blob/main/L3-Lumimaid-12.2B-v0.1-OAS-Instruct.Q3_K_M.gguf) | Q3_K_M | 5.6GB |\n| [L3-Lumimaid-12.2B-v0.1-OAS-Instruct.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/DavidAU_-_L3-Lumimaid-12.2B-v0.1-OAS-Instruct-gguf/blob/main/L3-Lumimaid-12.2B-v0.1-OAS-Instruct.Q3_K_L.gguf) | Q3_K_L | 6.05GB |\n| [L3-Lumimaid-12.2B-v0.1-OAS-Instruct.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/DavidAU_-_L3-Lumimaid-12.2B-v0.1-OAS-Instruct-gguf/blob/main/L3-Lumimaid-12.2B-v0.1-OAS-Instruct.IQ4_XS.gguf) | IQ4_XS | 6.26GB |\n| [L3-Lumimaid-12.2B-v0.1-OAS-Instruct.Q4_0.gguf](https://huggingface.co/RichardErkhov/DavidAU_-_L3-Lumimaid-12.2B-v0.1-OAS-Instruct-gguf/blob/main/L3-Lumimaid-12.2B-v0.1-OAS-Instruct.Q4_0.gguf) | Q4_0 | 6.51GB |\n| [L3-Lumimaid-12.2B-v0.1-OAS-Instruct.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/DavidAU_-_L3-Lumimaid-12.2B-v0.1-OAS-Instruct-gguf/blob/main/L3-Lumimaid-12.2B-v0.1-OAS-Instruct.IQ4_NL.gguf) | IQ4_NL | 6.58GB |\n| [L3-Lumimaid-12.2B-v0.1-OAS-Instruct.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/DavidAU_-_L3-Lumimaid-12.2B-v0.1-OAS-Instruct-gguf/blob/main/L3-Lumimaid-12.2B-v0.1-OAS-Instruct.Q4_K_S.gguf) | Q4_K_S | 6.56GB |\n| [L3-Lumimaid-12.2B-v0.1-OAS-Instruct.Q4_K.gguf](https://huggingface.co/RichardErkhov/DavidAU_-_L3-Lumimaid-12.2B-v0.1-OAS-Instruct-gguf/blob/main/L3-Lumimaid-12.2B-v0.1-OAS-Instruct.Q4_K.gguf) | Q4_K | 6.89GB |\n| [L3-Lumimaid-12.2B-v0.1-OAS-Instruct.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/DavidAU_-_L3-Lumimaid-12.2B-v0.1-OAS-Instruct-gguf/blob/main/L3-Lumimaid-12.2B-v0.1-OAS-Instruct.Q4_K_M.gguf) | Q4_K_M | 6.89GB |\n| [L3-Lumimaid-12.2B-v0.1-OAS-Instruct.Q4_1.gguf](https://huggingface.co/RichardErkhov/DavidAU_-_L3-Lumimaid-12.2B-v0.1-OAS-Instruct-gguf/blob/main/L3-Lumimaid-12.2B-v0.1-OAS-Instruct.Q4_1.gguf) | Q4_1 | 7.19GB |\n| [L3-Lumimaid-12.2B-v0.1-OAS-Instruct.Q5_0.gguf](https://huggingface.co/RichardErkhov/DavidAU_-_L3-Lumimaid-12.2B-v0.1-OAS-Instruct-gguf/blob/main/L3-Lumimaid-12.2B-v0.1-OAS-Instruct.Q5_0.gguf) | Q5_0 | 7.87GB |\n| [L3-Lumimaid-12.2B-v0.1-OAS-Instruct.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/DavidAU_-_L3-Lumimaid-12.2B-v0.1-OAS-Instruct-gguf/blob/main/L3-Lumimaid-12.2B-v0.1-OAS-Instruct.Q5_K_S.gguf) | Q5_K_S | 7.87GB |\n| [L3-Lumimaid-12.2B-v0.1-OAS-Instruct.Q5_K.gguf](https://huggingface.co/RichardErkhov/DavidAU_-_L3-Lumimaid-12.2B-v0.1-OAS-Instruct-gguf/blob/main/L3-Lumimaid-12.2B-v0.1-OAS-Instruct.Q5_K.gguf) | Q5_K | 8.06GB |\n| [L3-Lumimaid-12.2B-v0.1-OAS-Instruct.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/DavidAU_-_L3-Lumimaid-12.2B-v0.1-OAS-Instruct-gguf/blob/main/L3-Lumimaid-12.2B-v0.1-OAS-Instruct.Q5_K_M.gguf) | Q5_K_M | 8.06GB |\n| [L3-Lumimaid-12.2B-v0.1-OAS-Instruct.Q5_1.gguf](https://huggingface.co/RichardErkhov/DavidAU_-_L3-Lumimaid-12.2B-v0.1-OAS-Instruct-gguf/blob/main/L3-Lumimaid-12.2B-v0.1-OAS-Instruct.Q5_1.gguf) | Q5_1 | 8.55GB |\n| [L3-Lumimaid-12.2B-v0.1-OAS-Instruct.Q6_K.gguf](https://huggingface.co/RichardErkhov/DavidAU_-_L3-Lumimaid-12.2B-v0.1-OAS-Instruct-gguf/blob/main/L3-Lumimaid-12.2B-v0.1-OAS-Instruct.Q6_K.gguf) | Q6_K | 9.31GB |\n| [L3-Lumimaid-12.2B-v0.1-OAS-Instruct.Q8_0.gguf](https://huggingface.co/RichardErkhov/DavidAU_-_L3-Lumimaid-12.2B-v0.1-OAS-Instruct-gguf/blob/main/L3-Lumimaid-12.2B-v0.1-OAS-Instruct.Q8_0.gguf) | Q8_0 | 12.06GB |\n\n\n\n\nOriginal model description:\n---\nlibrary_name: transformers\ntags:\n- mergekit\n- merge\nbase_model: []\nmodel-index:\n- name: L3-Lumimaid-12.2B-v0.1-OAS-Instruct\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: 39.24\n      name: strict accuracy\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DavidAU/L3-Lumimaid-12.2B-v0.1-OAS-Instruct\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: 24.5\n      name: normalized accuracy\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DavidAU/L3-Lumimaid-12.2B-v0.1-OAS-Instruct\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: 3.85\n      name: exact match\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DavidAU/L3-Lumimaid-12.2B-v0.1-OAS-Instruct\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: 3.58\n      name: acc_norm\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DavidAU/L3-Lumimaid-12.2B-v0.1-OAS-Instruct\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: 11.26\n      name: acc_norm\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DavidAU/L3-Lumimaid-12.2B-v0.1-OAS-Instruct\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: 23.8\n      name: accuracy\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DavidAU/L3-Lumimaid-12.2B-v0.1-OAS-Instruct\n      name: Open LLM Leaderboard\n---\n# L3-Lumimaid-12.2B-v0.1-OAS-Instruct - Float32\n\nThis repo contains the full precision source code, in \"safe tensors\" format to generate GGUFs, GPTQ, EXL2, AWQ, HQQ and other formats.\nThe source code can also be used directly.\n\nFor full information about this model, including:\n\n- Details about this model and its use case(s).\n- Context limits\n- Special usage notes / settings.\n- Any model(s) used to create this model.\n- Template(s) used to access/use this model.\n- Example generation(s)\n- GGUF quants of this model\n\nPlease go to:\n\n[ https://huggingface.co/DavidAU/L3-Lumimaid-v0.1-OAS-12.2B-INSTRUCT-ULTRA-F32-GGUF ]\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 passthrough merge method.\n\n### Models Merged\n\nThe following models were included in the merge:\n* G:/7B/Meta-Llama-3-8B-Instruct\n* G:/7B/Llama-3-Lumimaid-8B-v0.1-OAS\n\n### Configuration\n\nThe following YAML configuration was used to produce this model:\n\n```yaml\nslices:\n - sources:\n   - model: G:/7B/Meta-Llama-3-8B-Instruct\n     layer_range: [0, 12]\n - sources:\n   - model: G:/7B/Llama-3-Lumimaid-8B-v0.1-OAS\n     layer_range: [6, 19]\n     parameters:\n       scale:\n         - filter: o_proj\n           value: 1\n         - filter: down_proj\n           value: 1\n         - value: 1\n - sources:\n   - model: G:/7B/Meta-Llama-3-8B-Instruct\n     layer_range: [12, 18]\n     parameters:\n       scale:\n         - filter: o_proj\n           value: .5\n         - filter: down_proj\n           value: .5\n         - value: 1\n - sources:\n   - model: G:/7B/Meta-Llama-3-8B-Instruct\n     layer_range: [18, 25]\n     parameters:\n       scale:\n         - filter: o_proj\n           value: .75\n         - filter: down_proj\n           value: .75\n         - value: 1\n - sources:\n   - model: G:/7B/Llama-3-Lumimaid-8B-v0.1-OAS\n     layer_range: [19, 32]\n     parameters:\n       scale:\n         - filter: o_proj\n           value: 1\n         - filter: down_proj\n           value: 1\n         - value: 1\nmerge_method: passthrough\ndtype: float32\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_DavidAU__L3-Lumimaid-12.2B-v0.1-OAS-Instruct)\n\n|      Metric       |Value|\n|-------------------|----:|\n|Avg.               |17.71|\n|IFEval (0-Shot)    |39.24|\n|BBH (3-Shot)       |24.50|\n|MATH Lvl 5 (4-Shot)| 3.85|\n|GPQA (0-shot)      | 3.58|\n|MuSR (0-shot)      |11.26|\n|MMLU-PRO (5-shot)  |23.80|\n\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 105,
  "gated": false,
  "private": false,
  "last_modified": "2024-10-04T06:18:43.000Z",
  "created_at": "2024-10-04T01:31:12.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "66ff456064acd6a2de897be2",
  "id": "RichardErkhov/DavidAU_-_L3-Lumimaid-12.2B-v0.1-OAS-Instruct-gguf",
  "modelId": "RichardErkhov/DavidAU_-_L3-Lumimaid-12.2B-v0.1-OAS-Instruct-gguf",
  "sha": "37c58ef4391ef1ea4f31e7b927c26349af04c3b3",
  "createdAt": "2024-10-04T01:31:12.000Z",
  "lastModified": "2024-10-04T06:18:43.000Z",
  "author": "RichardErkhov",
  "downloads": 105,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}