davidau/darkforest-20b-v3-ultra-quality-imatp2-gguf overview

{
  "metadata": {},
  "card_data": {
    "license": "apache-2.0",
    "language": [
      "en"
    ],
    "tags": [
      "story",
      "roleplay",
      "creative",
      "rp",
      "fantasy",
      "story telling",
      "32 bit upscale",
      "ultra high precision",
      "nsfw"
    ],
    "pipeline_tag": "text-generation",
    "frontmatter": {
      "license": "apache-2.0",
      "language": [
        "en"
      ],
      "tags": [
        "story",
        "roleplay",
        "creative",
        "rp",
        "fantasy",
        "story telling",
        "32 bit upscale",
        "ultra high precision",
        "nsfw"
      ],
      "pipeline_tag": "text-generation"
    },
    "hero_image_url": "dark-forest.jpg",
    "summary": "Ultra High Quality - 20 B Dark Forest Version 3.0 - 32 bit upscale - Imatrix Plus 2  Fully rebuilt from master files, including full merge(s) to maintain full 32 bit precision right up until it is compressed into GGUF files which results on a top to bottom upgrade. The result is superior performance in instruction following, reasoning, depth, nuance and emotion. This is the Imatrix Plus 2 repo. Imatrix Plus 2 uses the Ultra Quality 32 bit upscale as a base with applied in house datasets to further enhance the model's quality and performance. NOTE: There are three original versions of \"Dark Forest 20B\", this is an upscale of the third version, with links below to 1st and 2nd versions also upscaled.  On average this means a q4km operates at Q6 levels and Q6 and Q8 exceeds original model full precision performance. Perplexity drop (lower is better) is close to 10% (over 752 points for q4km) for all quants. That means precision has been enhanced for all 20 billion parameters which affects \"brain density\" / \"function\", instruction following and output quality. Imatrix quants to follow shortly. For more details, including a list of enhancements see our other 32 bit upscale of \"Space Whale 20B\" rebuild here: [ https://huggingface.co/DavidAU/Psyonic-Cetacean-Ultra-Quality-20b-GGUF ] For Version 1 of Dark Forest Ultra Quality 32 bit upscale please go here: [ https://huggingface.co/DavidAU/Dark-Forest-V1-Ultra-Quality-20b-GGUF ] For Version 1 of Dark Forest Ultra Quality 32 bit upscale please go here: [ https://huggingface.co/TeeZee/DarkForest-20B-v2.0 ] Special thanks to \"TEEZEE\" for making a both fantasic models of \"Dark Forest\".  Info from the original model card:  Warning: This model can produce NSFW content! Results: For original model spec and information please visit: [ https://huggingface.co/TeeZee/DarkForest-20B-v3.0 ] Highest Quality Settings / Optimal Operation Guide / Parameters and Samplers This a \"Class 2\" model: For all settings used for this model (including specifics for its \"class\"), including example generation(s) and for advanced settings guide (which many times addresses any model issue(s)), including methods to improve model performance for all use case(s) as well as chat, roleplay and other use case(s) please see: [ https://huggingface.co/DavidAU/Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters ]",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: apache-2.0\nlanguage:\n- en\ntags:\n- story\n- roleplay\n- creative\n- rp\n- fantasy\n- story telling\n- 32 bit upscale\n- ultra high precision\n- nsfw\npipeline_tag: text-generation\n---\n<B> Ultra High Quality - 20 B Dark Forest Version 3.0 - 32 bit upscale - Imatrix Plus 2 </b>\n\nFully rebuilt from master files, including full merge(s) to maintain full 32 bit precision right\nup until it is compressed into GGUF files which results on a top to bottom upgrade.\n\nThe result is superior performance in instruction following, reasoning, depth, nuance and emotion.\n\nThis is the Imatrix Plus 2 repo. Imatrix Plus 2 uses the Ultra Quality 32 bit upscale as a base with\napplied in house datasets to further enhance the model's quality and performance.\n\nNOTE: There are three original versions of \"Dark Forest 20B\", this is an upscale of the third version, with\nlinks below to 1st and 2nd versions also upscaled.\n\n<img src=\"dark-forest.jpg\">\n\nOn average this means a q4km operates at Q6 levels and Q6 and Q8 exceeds original model full precision performance.\n\nPerplexity drop (lower is better) is close to 10% (over 752 points for q4km) for all quants.\n\nThat means precision has been enhanced for all 20 billion parameters which affects \"brain density\" / \"function\", \ninstruction following and output quality.\n\nImatrix quants to follow shortly.\n\nFor more details, including a list of enhancements see our other 32 bit \nupscale of \"Space Whale 20B\" rebuild here:\n\n[ https://huggingface.co/DavidAU/Psyonic-Cetacean-Ultra-Quality-20b-GGUF ]\n\nFor Version 1 of Dark Forest Ultra Quality 32 bit upscale please go here:\n\n[ https://huggingface.co/DavidAU/Dark-Forest-V1-Ultra-Quality-20b-GGUF ]\n\nFor Version 1 of Dark Forest Ultra Quality 32 bit upscale please go here:\n\n[ https://huggingface.co/TeeZee/DarkForest-20B-v2.0 ]\n\nSpecial thanks to \"TEEZEE\" for making a both fantasic models of \"Dark Forest\".\n\n<b> Info from the original model card: </B>\n\nWarning: This model can produce NSFW content!\n\nResults:\n    \n    - main difference to v1.0 - model has much better sense of humor.\n    - produces SFW nad NSFW content without issues, switches context seamlessly.\n    - good at following instructions.\n    - good at tracking multiple characters in one scene.\n    - very creative, scenarios produced are mature and complicated, model doesn't shy from writing about PTSD, menatal issues or complicated relationships.\n    - NSFW output is more creative and suprising than typical limaRP output.\n    - definitely for mature audiences, not only because of vivid NSFW content but also because of overall maturity of stories it produces.\n    - This is NOT Harry Potter level storytelling.\n\n\nFor original model spec and information please visit:\n\n[ https://huggingface.co/TeeZee/DarkForest-20B-v3.0 ]\n\n<B>Highest Quality Settings / Optimal Operation Guide / Parameters and Samplers</B>\n\nThis a \"Class 2\" model:\n\nFor all settings used for this model (including specifics for its \"class\"), including example generation(s) and for advanced settings guide (which many times addresses any model issue(s)), including methods to improve model performance for all use case(s) as well as chat, roleplay and other use case(s) please see:\n\n[ https://huggingface.co/DavidAU/Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters ]\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "story",
    "roleplay",
    "creative",
    "rp",
    "fantasy",
    "story telling",
    "32 bit upscale",
    "ultra high precision",
    "nsfw",
    "text-generation",
    "en",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "imatrix"
  ],
  "likes": 8,
  "downloads": 163,
  "gated": false,
  "private": false,
  "last_modified": "2024-11-14T05:35:00.000Z",
  "created_at": "2024-06-18T01:09:40.000Z",
  "pipeline_tag": "text-generation",
  "library_name": ""
}

{
  "_id": "6670de543dd872e666ccf695",
  "id": "DavidAU/DarkForest-20B-V3-Ultra-Quality-ImatP2-GGUF",
  "modelId": "DavidAU/DarkForest-20B-V3-Ultra-Quality-ImatP2-GGUF",
  "sha": "2969a07bfbb73af3a1c1aada5979560bbfdd5080",
  "createdAt": "2024-06-18T01:09:40.000Z",
  "lastModified": "2024-11-14T05:35:00.000Z",
  "author": "DavidAU",
  "downloads": 163,
  "likes": 8,
  "gated": false,
  "private": false,
  "pipeline_tag": "text-generation",
  "library_name": "",
  "siblings_count": 16
}