mradermacher/moe-girl-800ma-3bt-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "allura-org/MoE-Girl-800MA-3BT",
    "language": [
      "en"
    ],
    "library_name": "transformers",
    "license": "apache-2.0",
    "no_imatrix": "Missing importance matrix for tensor blk.0.ffn_gate_exps.weight in a very low-bit quantization",
    "quantized_by": "mradermacher",
    "tags": [
      "axolotl",
      "moe",
      "roleplay"
    ],
    "frontmatter": {
      "base_model": "allura-org/MoE-Girl-800MA-3BT",
      "language": [
        "en"
      ],
      "library_name": "transformers",
      "license": "apache-2.0",
      "no_imatrix": "Missing importance matrix for tensor blk.0.ffn_gate_exps.weight in a very",
      "quantized_by": "mradermacher",
      "tags": [
        "axolotl",
        "moe",
        "roleplay"
      ]
    },
    "hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
    "summary": "## About      static quants of https://huggingface.co/allura-org/MoE-Girl-800MA-3BT",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: allura-org/MoE-Girl-800MA-3BT\nlanguage:\n- en\nlibrary_name: transformers\nlicense: apache-2.0\nno_imatrix: Missing importance matrix for tensor blk.0.ffn_gate_exps.weight in a very\n  low-bit quantization\nquantized_by: mradermacher\ntags:\n- axolotl\n- moe\n- roleplay\n---\n## About\n\n<!-- ### quantize_version: 2 -->\n<!-- ### output_tensor_quantised: 1 -->\n<!-- ### convert_type: hf -->\n<!-- ### vocab_type:  -->\n<!-- ### tags:  -->\nstatic quants of https://huggingface.co/allura-org/MoE-Girl-800MA-3BT\n\n<!-- provided-files -->\n## Usage\n\nIf you are unsure how to use GGUF files, refer to one of [TheBloke's\nREADMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for\nmore details, including on how to concatenate multi-part files.\n\n## Provided Quants\n\n(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)\n\n| Link | Type | Size/GB | Notes |\n|:-----|:-----|--------:|:------|\n| [GGUF](https://huggingface.co/mradermacher/MoE-Girl-800MA-3BT-GGUF/resolve/main/MoE-Girl-800MA-3BT.Q2_K.gguf) | Q2_K | 1.4 |  |\n| [GGUF](https://huggingface.co/mradermacher/MoE-Girl-800MA-3BT-GGUF/resolve/main/MoE-Girl-800MA-3BT.Q3_K_S.gguf) | Q3_K_S | 1.6 |  |\n| [GGUF](https://huggingface.co/mradermacher/MoE-Girl-800MA-3BT-GGUF/resolve/main/MoE-Girl-800MA-3BT.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/MoE-Girl-800MA-3BT-GGUF/resolve/main/MoE-Girl-800MA-3BT.Q3_K_L.gguf) | Q3_K_L | 1.9 |  |\n| [GGUF](https://huggingface.co/mradermacher/MoE-Girl-800MA-3BT-GGUF/resolve/main/MoE-Girl-800MA-3BT.IQ4_XS.gguf) | IQ4_XS | 1.9 |  |\n| [GGUF](https://huggingface.co/mradermacher/MoE-Girl-800MA-3BT-GGUF/resolve/main/MoE-Girl-800MA-3BT.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/MoE-Girl-800MA-3BT-GGUF/resolve/main/MoE-Girl-800MA-3BT.Q4_K_M.gguf) | Q4_K_M | 2.2 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/MoE-Girl-800MA-3BT-GGUF/resolve/main/MoE-Girl-800MA-3BT.Q5_K_S.gguf) | Q5_K_S | 2.4 |  |\n| [GGUF](https://huggingface.co/mradermacher/MoE-Girl-800MA-3BT-GGUF/resolve/main/MoE-Girl-800MA-3BT.Q5_K_M.gguf) | Q5_K_M | 2.5 |  |\n| [GGUF](https://huggingface.co/mradermacher/MoE-Girl-800MA-3BT-GGUF/resolve/main/MoE-Girl-800MA-3BT.Q6_K.gguf) | Q6_K | 2.9 | very good quality |\n| [GGUF](https://huggingface.co/mradermacher/MoE-Girl-800MA-3BT-GGUF/resolve/main/MoE-Girl-800MA-3BT.Q8_0.gguf) | Q8_0 | 3.7 | fast, best quality |\n| [GGUF](https://huggingface.co/mradermacher/MoE-Girl-800MA-3BT-GGUF/resolve/main/MoE-Girl-800MA-3BT.f16.gguf) | f16 | 6.9 | 16 bpw, overkill |\n\nHere is a handy graph by ikawrakow comparing some lower-quality quant\ntypes (lower is better):\n\n![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)\n\nAnd here are Artefact2's thoughts on the matter:\nhttps://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9\n\n## FAQ / Model Request\n\nSee https://huggingface.co/mradermacher/model_requests for some answers to\nquestions you might have and/or if you want some other model quantized.\n\n## Thanks\n\nI thank my company, [nethype GmbH](https://www.nethype.de/), for letting\nme use its servers and providing upgrades to my workstation to enable\nthis work in my free time.\n\n<!-- end -->\n",
    "related_quantizations": []
  },
  "tags": [
    "transformers",
    "gguf",
    "axolotl",
    "moe",
    "roleplay",
    "en",
    "base_model:allura-org/MoE-Girl-800MA-3BT",
    "base_model:quantized:allura-org/MoE-Girl-800MA-3BT",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 4,
  "downloads": 617,
  "gated": false,
  "private": false,
  "last_modified": "2024-10-28T04:55:57.000Z",
  "created_at": "2024-10-27T11:26:37.000Z",
  "pipeline_tag": "",
  "library_name": "transformers"
}

{
  "_id": "671e236d692c424f3aca95af",
  "id": "mradermacher/MoE-Girl-800MA-3BT-GGUF",
  "modelId": "mradermacher/MoE-Girl-800MA-3BT-GGUF",
  "sha": "bb48642a0dd6ea92dd11a6820f92335101415175",
  "createdAt": "2024-10-27T11:26:37.000Z",
  "lastModified": "2024-10-28T04:55:57.000Z",
  "author": "mradermacher",
  "downloads": 617,
  "likes": 4,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "transformers",
  "siblings_count": 14
}