inferenceillusionist/fimbulvetr-11b-v2-imat-gguf overview

{
  "metadata": {},
  "card_data": {
    "tags": [
      "gguf",
      "iMat",
      "conversational",
      "storywriting"
    ],
    "license": "cc-by-nc-4.0",
    "frontmatter": {
      "tags": [
        "gguf",
        "iMat",
        "conversational",
        "storywriting"
      ],
      "license": "cc-by-nc-4.0"
    },
    "hero_image_url": "https://i.imgur.com/P68dXux.png",
    "summary": "Prompt Formats - Alpaca or Vicuna. Either one works fine. Recommended SillyTavern Presets - Universal Light Alpaca: `` ### Instruction:  ### Input:  ### Response: ` Vicuna: ` System:  User:  Assistant: `` **** Changelogs: 25/2 - repo renamed to remove test, model card redone. Model's officially out. 15/2 - Heavy testing complete. Good feedback. *** Rant - Kept For Historical Reasons Ramble to meet minimum length requirements: Tbh i wonder if this shit is even worth doing. Like im just some broke guy lmao I've spent so much. And for what? I guess creds. Feels good when a model gets good feedback, but it seems like im invisible sometimes. I should be probably advertising myself and my models on other places but I rarely have the time to. Probably just internal jealousy sparking up here and now. Wahtever I guess. Anyway cool EMT vocation I'm doing is cool except it pays peanuts, damn bruh 1.1k per month lmao. Government to broke to pay for shit. Pays the bills I suppose. Anyway cool beans, I'm either going to continue the Solar Train or go to Mixtral / Yi when I get paid. You still here?",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\ntags:\n- gguf\n- iMat\n- conversational\n- storywriting\nlicense: cc-by-nc-4.0\n---\n<img src=\"https://i.imgur.com/P68dXux.png\" width=\"400\"/>\n\n<h3> Model Card for Fimbulvetr-11B-v2-iMat-GGUF</h3>\n\n* Model creator: [Sao10K](https://huggingface.co/Sao10K/)\n* Original model: [Fimbulvetr-11B-v2](https://huggingface.co/Sao10K/Fimbulvetr-11B-v2)\n\n<b>Update 4/15/24: Added a few missing quants to the list </b>\n\nTested on latest llama.cpp & koboldcpp v.1.60.\n\n<h4> This model fits a whole lot into its size! Impressed by its understanding of other languages</h4>\n<img src=\"https://huggingface.co/InferenceIllusionist/Fimbulvetr-11B-v2-iMat-GGUF/resolve/main/Fimbulvetr-11B-v2%20IQ4_XS.JPG\" width=\"850\"/>\n\n<b>Tip: Select the biggest size that you can fit in VRAM while still allowing some space for context</b>\n\n\nAll credits to Sao10K for the original model. This is just a quick test of the new quantization types such as IQ_3S in an attempt to further reduce VRAM requirements.\n\n\n\nQuantized from fp16 with love. Importance matrix file [Fimbulvetr-11B-v2-imatrix.dat](https://huggingface.co/InferenceIllusionist/Fimbulvetr-11B-v2-iMat-GGUF/blob/main/Fimbulvetr-11B-v2-imatrix.dat) was calculated using Q8_0. \n\n\n<i>Looking for Q3/Q4/Q5 quants? See the link in the original model card below.</i>\n\n--- \n\n\n![Fox1](https://huggingface.co/Sao10K/Fimbulvetr-11B-v2/resolve/main/cute1.jpg)\n\n*Cute girl to catch your attention.*\n\n**https://huggingface.co/Sao10K/Fimbulvetr-11B-v2-GGUF <------ GGUF**\n\n# Fimbulvetr-v2 - A Solar-Based Model\n\nPrompt Formats - Alpaca or Vicuna. Either one works fine.\nRecommended SillyTavern Presets - Universal Light \n\nAlpaca:\n```\n### Instruction:\n<Prompt>\n### Input:\n<Insert Context Here>\n### Response:\n```\n\nVicuna:\n```\nSystem: <Prompt>\n\nUser: <Input>\n\nAssistant:\n```\n\n\n****\n\nChangelogs:\n\n25/2 - repo renamed to remove test, model card redone. Model's officially out.\n<br>15/2 - Heavy testing complete. Good feedback.\n\n***\n\n<details><summary>Rant - Kept For Historical Reasons</summary>\n\nRamble to meet minimum length requirements:\n\nTbh i wonder if this shit is even worth doing. Like im just some broke guy lmao I've spent so much. And for what? I guess creds. Feels good when a model gets good feedback, but it seems like im invisible sometimes. I should be probably advertising myself and my models on other places but I rarely have the time to. Probably just internal jealousy sparking up here and now. Wahtever I guess.\n\nAnyway cool EMT vocation I'm doing is cool except it pays peanuts, damn bruh 1.1k per month lmao. Government to broke to pay for shit. Pays the bills I suppose.\n\nAnyway cool beans, I'm either going to continue the Solar Train or go to Mixtral / Yi when I get paid.\n\nYou still here?\n</details><br>",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "iMat",
    "conversational",
    "storywriting",
    "license:cc-by-nc-4.0",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 16,
  "downloads": 227,
  "gated": false,
  "private": false,
  "last_modified": "2024-04-15T10:03:27.000Z",
  "created_at": "2024-02-25T18:48:19.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "65db8b733b82823265bae62b",
  "id": "InferenceIllusionist/Fimbulvetr-11B-v2-iMat-GGUF",
  "modelId": "InferenceIllusionist/Fimbulvetr-11B-v2-iMat-GGUF",
  "sha": "38f43563022e751c34c7a5db0fc64c42c622721b",
  "createdAt": "2024-02-25T18:48:19.000Z",
  "lastModified": "2024-04-15T10:03:27.000Z",
  "author": "InferenceIllusionist",
  "downloads": 227,
  "likes": 16,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 21
}