devingulliver/mamba-gguf overview

{
  "metadata": {},
  "card_data": {
    "license": "apache-2.0",
    "pipeline_tag": "text-generation",
    "tags": [
      "merge"
    ],
    "base_model": [
      "state-spaces/mamba-130m",
      "state-spaces/mamba-370m",
      "state-spaces/mamba-790m",
      "state-spaces/mamba-1.4b",
      "state-spaces/mamba-2.8b",
      "state-spaces/mamba-2.8b-slimpj"
    ],
    "frontmatter": {
      "license": "apache-2.0",
      "pipeline_tag": "text-generation",
      "tags": [
        "merge"
      ],
      "base_model": [
        "state-spaces/mamba-130m",
        "state-spaces/mamba-370m",
        "state-spaces/mamba-790m",
        "state-spaces/mamba-1.4b",
        "state-spaces/mamba-2.8b",
        "state-spaces/mamba-2.8b-slimpj"
      ]
    },
    "hero_image_url": "",
    "summary": "These are the Mamba base models, converted to GGUF for use with llama.cpp, in a variety of precisions (2, 3, 4, 5, 6, 8, 16, and 32-bit). Please click \"Files and versions\" at the top of the page to choose your desired model size, and then click the \"📦LFS      ↓\" button next to your desired quantization. Here is a table adapted from TheBloke explaining the various precisions: | Quant method | Use case | | ---- | ---- | | Q2_K | significant quality loss - not recommended for most purposes | | Q3_K_S | very small, high quality loss | | Q3_K_M | very small, high quality loss | | Q3_K_L | small, substantial quality loss | | Q4_0 | legacy; small, very high quality loss - prefer using Q3_K_M | | Q4_K_S | small, greater quality loss | | Q4_K_M | medium, balanced quality - recommended | | Q5_0 | legacy; medium, balanced quality - prefer using Q4_K_M | | Q5_K_S | large, low quality loss - recommended | | Q5_K_M | large, very low quality loss - recommended | | Q6_K | very large, extremely low quality loss | | Q8_0 | very large, extremely low quality loss - not recommended | | F16 | half precision - almost identical to the original | | F32 | original precision - recommended by the Mamba authors |",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: apache-2.0\npipeline_tag: text-generation\ntags:\n- merge\nbase_model:\n- state-spaces/mamba-130m\n- state-spaces/mamba-370m\n- state-spaces/mamba-790m\n- state-spaces/mamba-1.4b\n- state-spaces/mamba-2.8b\n- state-spaces/mamba-2.8b-slimpj\n---\n\n# Mamba GGUF\n\nThese are the Mamba base models, converted to GGUF for use with [llama.cpp](https://github.com/ggerganov/llama.cpp), in a variety of precisions (2, 3, 4, 5, 6, 8, 16, and 32-bit).\n\nPlease click \"Files and versions\" at the top of the page to choose your desired model size, and then click the \"`📦LFS  `  `  ↓`\" button next to your desired quantization.\n\nHere is a table adapted from [TheBloke](https://huggingface.co/TheBloke) explaining the various precisions:\n\n| Quant method | Use case |\n| ---- | ---- |\n| Q2_K | significant quality loss - not recommended for most purposes |\n| Q3_K_S | very small, high quality loss |\n| Q3_K_M | very small, high quality loss |\n| Q3_K_L | small, substantial quality loss |\n| Q4_0 | legacy; small, very high quality loss - prefer using Q3_K_M |\n| Q4_K_S | small, greater quality loss |\n| Q4_K_M | medium, balanced quality - recommended |\n| Q5_0 | legacy; medium, balanced quality - prefer using Q4_K_M |\n| Q5_K_S | large, low quality loss - recommended |\n| Q5_K_M | large, very low quality loss - recommended |\n| Q6_K | very large, extremely low quality loss |\n| Q8_0 | very large, extremely low quality loss - not recommended |\n| F16 | half precision - almost identical to the original |\n| F32 | original precision - recommended by the Mamba authors |",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "merge",
    "text-generation",
    "base_model:state-spaces/mamba-1.4b",
    "base_model:merge:state-spaces/mamba-1.4b",
    "base_model:state-spaces/mamba-130m",
    "base_model:merge:state-spaces/mamba-130m",
    "base_model:state-spaces/mamba-2.8b",
    "base_model:merge:state-spaces/mamba-2.8b",
    "base_model:state-spaces/mamba-2.8b-slimpj",
    "base_model:merge:state-spaces/mamba-2.8b-slimpj",
    "base_model:state-spaces/mamba-370m",
    "base_model:merge:state-spaces/mamba-370m",
    "base_model:state-spaces/mamba-790m",
    "base_model:merge:state-spaces/mamba-790m",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 2,
  "downloads": 258,
  "gated": false,
  "private": false,
  "last_modified": "2024-03-12T20:14:30.000Z",
  "created_at": "2024-03-12T17:10:36.000Z",
  "pipeline_tag": "text-generation",
  "library_name": ""
}

{
  "_id": "65f08c8c0268a75eac4fb8b3",
  "id": "devingulliver/mamba-gguf",
  "modelId": "devingulliver/mamba-gguf",
  "sha": "4f5fc95be23f5aefa5dd1ccd639eabe35c47193b",
  "createdAt": "2024-03-12T17:10:36.000Z",
  "lastModified": "2024-03-12T20:14:30.000Z",
  "author": "devingulliver",
  "downloads": 258,
  "likes": 2,
  "gated": false,
  "private": false,
  "pipeline_tag": "text-generation",
  "library_name": "",
  "siblings_count": 86
}