quant-cartel/llama-3.05-nemotron-tenyxchat-storybreaker-70b-imat-gguf overview

{
  "metadata": {},
  "card_data": {
    "license": "cc-by-nc-4.0",
    "base_model_relation": "quantized",
    "quantized_by": "Quant-Cartel",
    "base_model": "Envoid/Llama-3.05-Nemotron-Tenyxchat-Storybreaker-70B",
    "pipeline_tag": "text-generation",
    "tags": [
      "iMat",
      "GGUF",
      "merge"
    ],
    "frontmatter": {
      "license": "cc-by-nc-4.0",
      "base_model_relation": "quantized",
      "quantized_by": "Quant-Cartel",
      "base_model": "Envoid/Llama-3.05-Nemotron-Tenyxchat-Storybreaker-70B",
      "pipeline_tag": "text-generation",
      "tags": [
        "iMat",
        "GGUF",
        "merge"
      ]
    },
    "hero_image_url": "https://files.catbox.moe/07cjw5.jpg",
    "summary": "Quantized with love from fp16. Original model author: Envoid * Importance Matrix calculated using groups_merged.txt *  88 chunks *  n_ctx=512 *  Calculation uses f16 precision model weights Original model README here and below: ![](https://files.catbox.moe/07cjw5.jpg) # Llama-3.05-Nemotron-Tenyxchat-Storybreaker-70B is a 40/60 SLERP Merge of Envoid/Llama-3-TenyxChat-DaybreakStorywriter-70B onto nvidia/Llama-3.1-Nemotron-70B-Instruct-HF utilizing the following config: `` models: merge_method: slerp base_model: ./nvidia_Llama-3.1-Nemotron-70B-Instruct-HF parameters: t: dtype: bfloat16 ``",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: cc-by-nc-4.0\nbase_model_relation: quantized\nquantized_by: Quant-Cartel\nbase_model: Envoid/Llama-3.05-Nemotron-Tenyxchat-Storybreaker-70B\npipeline_tag: text-generation\ntags:\n- iMat\n- GGUF\n- merge\n---\n```\n  e88 88e                               d8     \n d888 888b  8888 8888  ,\"Y88b 888 8e   d88     \nC8888 8888D 8888 8888 \"8\" 888 888 88b d88888   \n Y888 888P  Y888 888P ,ee 888 888 888  888     \n  \"88 88\"    \"88 88\"  \"88 888 888 888  888     \n      b                                        \n      8b,                                      \n \n  e88'Y88                  d8           888    \n d888  'Y  ,\"Y88b 888,8,  d88    ,e e,  888    \nC8888     \"8\" 888 888 \"  d88888 d88 88b 888    \n Y888  ,d ,ee 888 888     888   888   , 888    \n  \"88,d88 \"88 888 888     888    \"YeeP\" 888    \n                                               \nPROUDLY PRESENTS         \n```\n# Llama-3.05-Nemotron-Tenyxchat-Storybreaker-70B-iMat-GGUF\n\nQuantized with love from fp16.\n\nOriginal model author: [Envoid](https://huggingface.co/Envoid/)\n\n* Importance Matrix calculated using [groups_merged.txt](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384)\n*  88 chunks\n*  n_ctx=512\n*  Calculation uses f16 precision model weights\n\nOriginal model README [here](https://huggingface.co/Envoid/Llama-3.05-Nemotron-Tenyxchat-Storybreaker-70B) and below:\n\n![](https://files.catbox.moe/07cjw5.jpg)\n\n# Llama-3.05-Nemotron-Tenyxchat-Storybreaker-70B\n\nis a 40/60 SLERP Merge of [Envoid/Llama-3-TenyxChat-DaybreakStorywriter-70B](https://huggingface.co/Envoid/Llama-3-TenyxChat-DaybreakStorywriter-70B?not-for-all-audiences=true) onto [nvidia/Llama-3.1-Nemotron-70B-Instruct-HF](https://huggingface.co/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF) utilizing the following config:\n```\nmodels:\n  - model: ./Envoid_Llama-3-TenyxChat-DaybreakStorywriter-70B\n  - model: ./nvidia_Llama-3.1-Nemotron-70B-Instruct-HF\nmerge_method: slerp\nbase_model: ./nvidia_Llama-3.1-Nemotron-70B-Instruct-HF\nparameters:\n  t:\n    - value: 0.4\ndtype: bfloat16\n```\n## Caution: As is always the case with SLERP merges there may be edge cases inwhich certain unintended model behaviors emerge. So always use with caution.\n\nThe 'sloppiness' of Nemotron seems to be somewhat reigned in (but still exists) while maintaining its personable assistant personality and safety (In assistant mode it will still prompt you with a warning before producing sensitive content).\n\nOverall it provides a solid option for RP and creative writing while still functioning as an assistant model, if desired. If used to continue a roleplay it will generally follow the ongoing cadence of the conversation.\n\n### It utilizes the Llama 3 prompt format.\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "iMat",
    "GGUF",
    "merge",
    "text-generation",
    "base_model:Envoid/Llama-3.05-Nemotron-Tenyxchat-Storybreaker-70B",
    "base_model:quantized:Envoid/Llama-3.05-Nemotron-Tenyxchat-Storybreaker-70B",
    "license:cc-by-nc-4.0",
    "endpoints_compatible",
    "region:us",
    "imatrix",
    "conversational"
  ],
  "likes": 1,
  "downloads": 112,
  "gated": false,
  "private": false,
  "last_modified": "2024-10-19T10:29:27.000Z",
  "created_at": "2024-10-17T15:58:33.000Z",
  "pipeline_tag": "text-generation",
  "library_name": ""
}

{
  "_id": "67113429cc054ebaac22ac78",
  "id": "Quant-Cartel/Llama-3.05-Nemotron-Tenyxchat-Storybreaker-70B-iMat-GGUF",
  "modelId": "Quant-Cartel/Llama-3.05-Nemotron-Tenyxchat-Storybreaker-70B-iMat-GGUF",
  "sha": "7754210a2144773eacf199b2806362c7fe86b9c6",
  "createdAt": "2024-10-17T15:58:33.000Z",
  "lastModified": "2024-10-19T10:29:27.000Z",
  "author": "Quant-Cartel",
  "downloads": 112,
  "likes": 1,
  "gated": false,
  "private": false,
  "pipeline_tag": "text-generation",
  "library_name": "",
  "siblings_count": 25
}