s3nh/decapoda-research-antares-11b-v1-gguf overview

{
  "metadata": {},
  "card_data": {
    "license": "openrail",
    "pipeline_tag": "text-generation",
    "library_name": "transformers",
    "language": [
      "zh",
      "en"
    ],
    "frontmatter": {},
    "hero_image_url": "https://www.buymeacoffee.com/assets/img/guidelines/download-assets-sm-1.svg",
    "summary": "",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "\n---\nlicense: openrail\npipeline_tag: text-generation\nlibrary_name: transformers\nlanguage:\n- zh\n- en\n---\n\n\n## Original model card \n\nBuy me a coffee if you like this project ;)\n<a href=\"https://www.buymeacoffee.com/s3nh\"><img src=\"https://www.buymeacoffee.com/assets/img/guidelines/download-assets-sm-1.svg\" alt=\"\"></a>\n\n#### Description \n\nGGUF Format model files for [This project](https://huggingface.co/decapoda-research/Antares-11b-v1).\n\n### GGUF Specs \n\nGGUF is a format based on the existing GGJT, but makes a few changes to the format to make it more extensible and easier to use. The following features are desired:\n\nSingle-file deployment: they can be easily distributed and loaded, and do not require any external files for additional information.\nExtensible: new features can be added to GGML-based executors/new information can be added to GGUF models without breaking compatibility with existing models.\nmmap compatibility: models can be loaded using mmap for fast loading and saving.\nEasy to use: models can be easily loaded and saved using a small amount of code, with no need for external libraries, regardless of the language used.\nFull information: all information needed to load a model is contained in the model file, and no additional information needs to be provided by the user.\nThe key difference between GGJT and GGUF is the use of a key-value structure for the hyperparameters (now referred to as metadata), rather than a list of untyped values. \nThis allows for new metadata to be added without breaking compatibility with existing models, and to annotate the model with additional information that may be useful for\ninference or for identifying the model.\n\n### Perplexity params\n\nModel\tMeasure\tQ2_K\tQ3_K_S\tQ3_K_M\tQ3_K_L\tQ4_0\tQ4_1\tQ4_K_S\tQ4_K_M\tQ5_0\tQ5_1\tQ5_K_S\tQ5_K_M\tQ6_K\tQ8_0\tF16\n7B\tperplexity\t6.7764\t6.4571\t6.1503\t6.0869\t6.1565\t6.0912\t6.0215\t5.9601\t5.9862\t5.9481\t5.9419\t5.9208\t5.9110\t5.9070\t5.9066\n13B\tperplexity\t5.8545\t5.6033\t5.4498\t5.4063\t5.3860\t5.3608\t5.3404\t5.3002\t5.2856\t5.2706\t5.2785\t5.2638\t5.2568\t5.2548\t5.2543\n\n\n\n### inference \n\n\nTODO\n\n# Original model card\n",
    "related_quantizations": []
  },
  "tags": [
    "transformers",
    "gguf",
    "text-generation",
    "zh",
    "en",
    "license:openrail",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 1,
  "downloads": 92,
  "gated": false,
  "private": false,
  "last_modified": "2024-01-01T22:38:31.000Z",
  "created_at": "2024-01-01T21:31:46.000Z",
  "pipeline_tag": "text-generation",
  "library_name": "transformers"
}

{
  "_id": "65932f42cdc0c4099ba81953",
  "id": "s3nh/decapoda-research-Antares-11b-v1-GGUF",
  "modelId": "s3nh/decapoda-research-Antares-11b-v1-GGUF",
  "sha": "3959e733669c972c8a43b08696b2157c1455508d",
  "createdAt": "2024-01-01T21:31:46.000Z",
  "lastModified": "2024-01-01T22:38:31.000Z",
  "author": "s3nh",
  "downloads": 92,
  "likes": 1,
  "gated": false,
  "private": false,
  "pipeline_tag": "text-generation",
  "library_name": "transformers",
  "siblings_count": 9
}