richarderkhov/vhab10_-_llama-3.1-8b-base-instruct-slerp-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-3.1-8B-Base-Instruct-SLERP - GGUF\n- Model creator: https://huggingface.co/vhab10/\n- Original model: https://huggingface.co/vhab10/Llama-3.1-8B-Base-Instruct-SLERP/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [Llama-3.1-8B-Base-Instruct-SLERP.Q2_K.gguf](https://huggingface.co/RichardErkhov/vhab10_-_Llama-3.1-8B-Base-Instruct-SLERP-gguf/blob/main/Llama-3.1-8B-Base-Instruct-SLERP.Q2_K.gguf) | Q2_K | 2.96GB |\n| [Llama-3.1-8B-Base-Instruct-SLERP.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/vhab10_-_Llama-3.1-8B-Base-Instruct-SLERP-gguf/blob/main/Llama-3.1-8B-Base-Instruct-SLERP.IQ3_XS.gguf) | IQ3_XS | 3.28GB |\n| [Llama-3.1-8B-Base-Instruct-SLERP.IQ3_S.gguf](https://huggingface.co/RichardErkhov/vhab10_-_Llama-3.1-8B-Base-Instruct-SLERP-gguf/blob/main/Llama-3.1-8B-Base-Instruct-SLERP.IQ3_S.gguf) | IQ3_S | 3.43GB |\n| [Llama-3.1-8B-Base-Instruct-SLERP.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/vhab10_-_Llama-3.1-8B-Base-Instruct-SLERP-gguf/blob/main/Llama-3.1-8B-Base-Instruct-SLERP.Q3_K_S.gguf) | Q3_K_S | 3.41GB |\n| [Llama-3.1-8B-Base-Instruct-SLERP.IQ3_M.gguf](https://huggingface.co/RichardErkhov/vhab10_-_Llama-3.1-8B-Base-Instruct-SLERP-gguf/blob/main/Llama-3.1-8B-Base-Instruct-SLERP.IQ3_M.gguf) | IQ3_M | 3.52GB |\n| [Llama-3.1-8B-Base-Instruct-SLERP.Q3_K.gguf](https://huggingface.co/RichardErkhov/vhab10_-_Llama-3.1-8B-Base-Instruct-SLERP-gguf/blob/main/Llama-3.1-8B-Base-Instruct-SLERP.Q3_K.gguf) | Q3_K | 3.74GB |\n| [Llama-3.1-8B-Base-Instruct-SLERP.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/vhab10_-_Llama-3.1-8B-Base-Instruct-SLERP-gguf/blob/main/Llama-3.1-8B-Base-Instruct-SLERP.Q3_K_M.gguf) | Q3_K_M | 3.74GB |\n| [Llama-3.1-8B-Base-Instruct-SLERP.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/vhab10_-_Llama-3.1-8B-Base-Instruct-SLERP-gguf/blob/main/Llama-3.1-8B-Base-Instruct-SLERP.Q3_K_L.gguf) | Q3_K_L | 4.03GB |\n| [Llama-3.1-8B-Base-Instruct-SLERP.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/vhab10_-_Llama-3.1-8B-Base-Instruct-SLERP-gguf/blob/main/Llama-3.1-8B-Base-Instruct-SLERP.IQ4_XS.gguf) | IQ4_XS | 4.18GB |\n| [Llama-3.1-8B-Base-Instruct-SLERP.Q4_0.gguf](https://huggingface.co/RichardErkhov/vhab10_-_Llama-3.1-8B-Base-Instruct-SLERP-gguf/blob/main/Llama-3.1-8B-Base-Instruct-SLERP.Q4_0.gguf) | Q4_0 | 4.34GB |\n| [Llama-3.1-8B-Base-Instruct-SLERP.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/vhab10_-_Llama-3.1-8B-Base-Instruct-SLERP-gguf/blob/main/Llama-3.1-8B-Base-Instruct-SLERP.IQ4_NL.gguf) | IQ4_NL | 4.38GB |\n| [Llama-3.1-8B-Base-Instruct-SLERP.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/vhab10_-_Llama-3.1-8B-Base-Instruct-SLERP-gguf/blob/main/Llama-3.1-8B-Base-Instruct-SLERP.Q4_K_S.gguf) | Q4_K_S | 4.37GB |\n| [Llama-3.1-8B-Base-Instruct-SLERP.Q4_K.gguf](https://huggingface.co/RichardErkhov/vhab10_-_Llama-3.1-8B-Base-Instruct-SLERP-gguf/blob/main/Llama-3.1-8B-Base-Instruct-SLERP.Q4_K.gguf) | Q4_K | 4.58GB |\n| [Llama-3.1-8B-Base-Instruct-SLERP.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/vhab10_-_Llama-3.1-8B-Base-Instruct-SLERP-gguf/blob/main/Llama-3.1-8B-Base-Instruct-SLERP.Q4_K_M.gguf) | Q4_K_M | 4.58GB |\n| [Llama-3.1-8B-Base-Instruct-SLERP.Q4_1.gguf](https://huggingface.co/RichardErkhov/vhab10_-_Llama-3.1-8B-Base-Instruct-SLERP-gguf/blob/main/Llama-3.1-8B-Base-Instruct-SLERP.Q4_1.gguf) | Q4_1 | 4.78GB |\n| [Llama-3.1-8B-Base-Instruct-SLERP.Q5_0.gguf](https://huggingface.co/RichardErkhov/vhab10_-_Llama-3.1-8B-Base-Instruct-SLERP-gguf/blob/main/Llama-3.1-8B-Base-Instruct-SLERP.Q5_0.gguf) | Q5_0 | 5.21GB |\n| [Llama-3.1-8B-Base-Instruct-SLERP.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/vhab10_-_Llama-3.1-8B-Base-Instruct-SLERP-gguf/blob/main/Llama-3.1-8B-Base-Instruct-SLERP.Q5_K_S.gguf) | Q5_K_S | 5.21GB |\n| [Llama-3.1-8B-Base-Instruct-SLERP.Q5_K.gguf](https://huggingface.co/RichardErkhov/vhab10_-_Llama-3.1-8B-Base-Instruct-SLERP-gguf/blob/main/Llama-3.1-8B-Base-Instruct-SLERP.Q5_K.gguf) | Q5_K | 5.34GB |\n| [Llama-3.1-8B-Base-Instruct-SLERP.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/vhab10_-_Llama-3.1-8B-Base-Instruct-SLERP-gguf/blob/main/Llama-3.1-8B-Base-Instruct-SLERP.Q5_K_M.gguf) | Q5_K_M | 5.34GB |\n| [Llama-3.1-8B-Base-Instruct-SLERP.Q5_1.gguf](https://huggingface.co/RichardErkhov/vhab10_-_Llama-3.1-8B-Base-Instruct-SLERP-gguf/blob/main/Llama-3.1-8B-Base-Instruct-SLERP.Q5_1.gguf) | Q5_1 | 5.65GB |\n| [Llama-3.1-8B-Base-Instruct-SLERP.Q6_K.gguf](https://huggingface.co/RichardErkhov/vhab10_-_Llama-3.1-8B-Base-Instruct-SLERP-gguf/blob/main/Llama-3.1-8B-Base-Instruct-SLERP.Q6_K.gguf) | Q6_K | 6.14GB |\n| [Llama-3.1-8B-Base-Instruct-SLERP.Q8_0.gguf](https://huggingface.co/RichardErkhov/vhab10_-_Llama-3.1-8B-Base-Instruct-SLERP-gguf/blob/main/Llama-3.1-8B-Base-Instruct-SLERP.Q8_0.gguf) | Q8_0 | 7.95GB |\n\n\n\n\nOriginal model description:\n---\nlicense: mit\nlibrary_name: transformers\ntags:\n- mergekit\n- merge\nbase_model:\n- meta-llama/Meta-Llama-3.1-8B\nmodel-index:\n- name: Llama-3.1-8B-Base-Instruct-SLERP\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: 29.07\n      name: strict accuracy\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vhab10/Llama-3.1-8B-Base-Instruct-SLERP\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: 29.93\n      name: normalized accuracy\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vhab10/Llama-3.1-8B-Base-Instruct-SLERP\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: 10.5\n      name: exact match\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vhab10/Llama-3.1-8B-Base-Instruct-SLERP\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: 6.15\n      name: acc_norm\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vhab10/Llama-3.1-8B-Base-Instruct-SLERP\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: 9.37\n      name: acc_norm\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vhab10/Llama-3.1-8B-Base-Instruct-SLERP\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: 29.12\n      name: accuracy\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vhab10/Llama-3.1-8B-Base-Instruct-SLERP\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* [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B)\n* [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct)\n\n### Configuration\n\nThe following YAML configuration was used to produce this model:\n\n```yaml\nslices:\n- sources:\n  - model: meta-llama/Meta-Llama-3.1-8B\n    layer_range:\n    - 0\n    - 32\n  - model: meta-llama/Meta-Llama-3.1-8B-Instruct\n    layer_range:\n    - 0\n    - 32\nmerge_method: slerp\nbase_model: meta-llama/Meta-Llama-3.1-8B\nparameters:\n  t:\n  - filter: self_attn\n    value:\n    - 0\n    - 0.5\n    - 0.3\n    - 0.7\n    - 1\n  - filter: mlp\n    value:\n    - 1\n    - 0.5\n    - 0.7\n    - 0.3\n    - 0\n  - value: 0.5\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_vhab10__Llama-3.1-8B-Base-Instruct-SLERP)\n\n|      Metric       |Value|\n|-------------------|----:|\n|Avg.               |19.02|\n|IFEval (0-Shot)    |29.07|\n|BBH (3-Shot)       |29.93|\n|MATH Lvl 5 (4-Shot)|10.50|\n|GPQA (0-shot)      | 6.15|\n|MuSR (0-shot)      | 9.37|\n|MMLU-PRO (5-shot)  |29.12|\n\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 0,
  "downloads": 169,
  "gated": false,
  "private": false,
  "last_modified": "2024-10-10T13:42:24.000Z",
  "created_at": "2024-10-10T10:07:55.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "6707a77b7a7373199338a2be",
  "id": "RichardErkhov/vhab10_-_Llama-3.1-8B-Base-Instruct-SLERP-gguf",
  "modelId": "RichardErkhov/vhab10_-_Llama-3.1-8B-Base-Instruct-SLERP-gguf",
  "sha": "ca9e5740c660e33d79fbd5f7dfc68f6922a1619a",
  "createdAt": "2024-10-10T10:07:55.000Z",
  "lastModified": "2024-10-10T13:42:24.000Z",
  "author": "RichardErkhov",
  "downloads": 169,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}