inferenceillusionist/magnum-12b-v2.5-kto-imat-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "anthracite-org/magnum-12b-v2.5-kto",
    "library_name": "transformers",
    "quantized_by": "InferenceIllusionist",
    "tags": [
      "iMat",
      "gguf",
      "Mistral"
    ],
    "license": "apache-2.0",
    "frontmatter": {
      "base_model": "anthracite-org/magnum-12b-v2.5-kto",
      "library_name": "transformers",
      "quantized_by": "InferenceIllusionist",
      "tags": [
        "iMat",
        "gguf",
        "Mistral"
      ],
      "license": "apache-2.0"
    },
    "hero_image_url": "https://i.imgur.com/P68dXux.png",
    "summary": "> [!WARNING] >Important Note: Inferencing in llama.cpp has now been merged in PR #8604. Please ensure you are on release b3438 or newer. Text-generation-web-ui (Ooba) is also working as of 7/23. Kobold.cpp working as of  v1.71.  Quantized from magnum-12b-v2.5-kto fp16 * Weighted quantizations were creating using fp16 GGUF and groups_merged.txt (special thanks to Kalomaze) in 92 chunks and n_ctx=512 * Static fp16 will also be included in repo * For a brief rundown of iMatrix quant performance please see this PR * All quants are verified working prior to uploading to repo for your safety and convenience KL-Divergence Reference Chart (Click on image to view in full size)  > [!TIP] >Quant-specific Tips: >* If you are getting a cudaMalloc failed: out of memory error, try passing an argument for lower context in llama.cpp, e.g. for 8k: -c 8192 >* If you have all ampere generation or newer cards, you can use flash attention like so: -fa >* Provided Flash Attention is enabled you can also use quantized cache to save on VRAM e.g. for 8-bit: -ctk q8_0 -ctv q8_0 Original model card can be found here",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: anthracite-org/magnum-12b-v2.5-kto\nlibrary_name: transformers\nquantized_by: InferenceIllusionist\ntags:\n- iMat\n- gguf\n- Mistral\nlicense: apache-2.0\n---\n<img src=\"https://i.imgur.com/P68dXux.png\" width=\"400\"/>\n\n# magnum-12b-v2.5-kto-iMat-GGUF\n\n> [!WARNING]\n><b>Important Note:</b> Inferencing in llama.cpp has now been merged in [PR #8604](https://github.com/ggerganov/llama.cpp/pull/8604). Please ensure you are on release [b3438](https://github.com/ggerganov/llama.cpp/releases/tag/b3438) or newer. Text-generation-web-ui (Ooba) is also working as of 7/23. Kobold.cpp working as of  [v1.71](https://github.com/LostRuins/koboldcpp/releases/tag/v1.71). </b>\n\nQuantized from magnum-12b-v2.5-kto fp16\n* Weighted quantizations were creating using fp16 GGUF and [groups_merged.txt](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384) (special thanks to [Kalomaze](https://huggingface.co/kalomaze)) in 92 chunks and n_ctx=512\n* Static fp16 will also be included in repo\n* For a brief rundown of iMatrix quant performance please see this [PR](https://github.com/ggerganov/llama.cpp/pull/5747)\n* <i>All quants are verified working prior to uploading to repo for your safety and convenience</i>\n\n<b>KL-Divergence Reference Chart</b>\n (Click on image to view in full size)\n[<img src=\"https://i.imgur.com/mV0nYdA.png\" width=\"920\"/>](https://i.imgur.com/mV0nYdA.png)\n\n> [!TIP]\n><b>Quant-specific Tips:</b>\n>* If you are getting a `cudaMalloc failed: out of memory` error, try passing an argument for lower context in llama.cpp, e.g. for 8k: `-c 8192`\n>* If you have all ampere generation or newer cards, you can use flash attention like so: `-fa`\n>* Provided Flash Attention is enabled you can also use quantized cache to save on VRAM e.g. for 8-bit: `-ctk q8_0 -ctv q8_0`\n\n\nOriginal model card can be found [here](https://huggingface.co/anthracite-org/magnum-12b-v2.5-kto)",
    "related_quantizations": []
  },
  "tags": [
    "transformers",
    "gguf",
    "iMat",
    "Mistral",
    "base_model:anthracite-org/magnum-v2.5-12b-kto",
    "base_model:quantized:anthracite-org/magnum-v2.5-12b-kto",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 2,
  "downloads": 185,
  "gated": false,
  "private": false,
  "last_modified": "2024-08-15T10:12:58.000Z",
  "created_at": "2024-08-15T03:57:55.000Z",
  "pipeline_tag": "",
  "library_name": "transformers"
}

{
  "_id": "66bd7cc3d9a7974122e93422",
  "id": "InferenceIllusionist/magnum-12b-v2.5-kto-iMat-GGUF",
  "modelId": "InferenceIllusionist/magnum-12b-v2.5-kto-iMat-GGUF",
  "sha": "cc0e2e841349928b161b60e355859b25c9b140e6",
  "createdAt": "2024-08-15T03:57:55.000Z",
  "lastModified": "2024-08-15T10:12:58.000Z",
  "author": "InferenceIllusionist",
  "downloads": 185,
  "likes": 2,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "transformers",
  "siblings_count": 20
}