mradermacher/boundary-4x7b-moe-i1-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "NotAiLOL/Boundary-4x7b-MoE",
    "language": [
      "en"
    ],
    "library_name": "transformers",
    "license": "apache-2.0",
    "quantized_by": "mradermacher",
    "tags": [
      "moe",
      "merge",
      "mergekit",
      "HuggingFaceH4/zephyr-7b-beta",
      "mistralai/Mistral-7B-Instruct-v0.2",
      "teknium/OpenHermes-2.5-Mistral-7B",
      "meta-math/MetaMath-Mistral-7B",
      "Mistral"
    ],
    "frontmatter": {
      "base_model": "NotAiLOL/Boundary-4x7b-MoE",
      "language": [
        "en"
      ],
      "library_name": "transformers",
      "license": "apache-2.0",
      "quantized_by": "mradermacher",
      "tags": [
        "moe",
        "merge",
        "mergekit",
        "HuggingFaceH4/zephyr-7b-beta",
        "mistralai/Mistral-7B-Instruct-v0.2",
        "teknium/OpenHermes-2.5-Mistral-7B",
        "meta-math/MetaMath-Mistral-7B",
        "Mistral"
      ]
    },
    "hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
    "summary": "## About     weighted/imatrix quants of https://huggingface.co/NotAiLOL/Boundary-4x7b-MoE  static quants are available at https://huggingface.co/mradermacher/Boundary-4x7b-MoE-GGUF",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: NotAiLOL/Boundary-4x7b-MoE\nlanguage:\n- en\nlibrary_name: transformers\nlicense: apache-2.0\nquantized_by: mradermacher\ntags:\n- moe\n- merge\n- mergekit\n- HuggingFaceH4/zephyr-7b-beta\n- mistralai/Mistral-7B-Instruct-v0.2\n- teknium/OpenHermes-2.5-Mistral-7B\n- meta-math/MetaMath-Mistral-7B\n- Mistral\n---\n## About\n\n<!-- ### quantize_version: 1 -->\n<!-- ### output_tensor_quantised: 1 -->\n<!-- ### convert_type:  -->\n<!-- ### vocab_type:  -->\nweighted/imatrix quants of https://huggingface.co/NotAiLOL/Boundary-4x7b-MoE\n\n<!-- provided-files -->\nstatic quants are available at https://huggingface.co/mradermacher/Boundary-4x7b-MoE-GGUF\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/Boundary-4x7b-MoE-i1-GGUF/resolve/main/Boundary-4x7b-MoE.i1-IQ1_S.gguf) | i1-IQ1_S | 5.1 | for the desperate |\n| [GGUF](https://huggingface.co/mradermacher/Boundary-4x7b-MoE-i1-GGUF/resolve/main/Boundary-4x7b-MoE.i1-IQ1_M.gguf) | i1-IQ1_M | 5.6 | mostly desperate |\n| [GGUF](https://huggingface.co/mradermacher/Boundary-4x7b-MoE-i1-GGUF/resolve/main/Boundary-4x7b-MoE.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 6.5 |  |\n| [GGUF](https://huggingface.co/mradermacher/Boundary-4x7b-MoE-i1-GGUF/resolve/main/Boundary-4x7b-MoE.i1-IQ2_XS.gguf) | i1-IQ2_XS | 7.2 |  |\n| [GGUF](https://huggingface.co/mradermacher/Boundary-4x7b-MoE-i1-GGUF/resolve/main/Boundary-4x7b-MoE.i1-IQ2_S.gguf) | i1-IQ2_S | 7.4 |  |\n| [GGUF](https://huggingface.co/mradermacher/Boundary-4x7b-MoE-i1-GGUF/resolve/main/Boundary-4x7b-MoE.i1-IQ2_M.gguf) | i1-IQ2_M | 8.1 |  |\n| [GGUF](https://huggingface.co/mradermacher/Boundary-4x7b-MoE-i1-GGUF/resolve/main/Boundary-4x7b-MoE.i1-Q2_K.gguf) | i1-Q2_K | 8.9 | IQ3_XXS probably better |\n| [GGUF](https://huggingface.co/mradermacher/Boundary-4x7b-MoE-i1-GGUF/resolve/main/Boundary-4x7b-MoE.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 9.4 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/Boundary-4x7b-MoE-i1-GGUF/resolve/main/Boundary-4x7b-MoE.i1-IQ3_XS.gguf) | i1-IQ3_XS | 10.0 |  |\n| [GGUF](https://huggingface.co/mradermacher/Boundary-4x7b-MoE-i1-GGUF/resolve/main/Boundary-4x7b-MoE.i1-Q3_K_S.gguf) | i1-Q3_K_S | 10.5 | IQ3_XS probably better |\n| [GGUF](https://huggingface.co/mradermacher/Boundary-4x7b-MoE-i1-GGUF/resolve/main/Boundary-4x7b-MoE.i1-IQ3_S.gguf) | i1-IQ3_S | 10.6 | beats Q3_K* |\n| [GGUF](https://huggingface.co/mradermacher/Boundary-4x7b-MoE-i1-GGUF/resolve/main/Boundary-4x7b-MoE.i1-IQ3_M.gguf) | i1-IQ3_M | 10.7 |  |\n| [GGUF](https://huggingface.co/mradermacher/Boundary-4x7b-MoE-i1-GGUF/resolve/main/Boundary-4x7b-MoE.i1-Q3_K_M.gguf) | i1-Q3_K_M | 11.7 | IQ3_S probably better |\n| [GGUF](https://huggingface.co/mradermacher/Boundary-4x7b-MoE-i1-GGUF/resolve/main/Boundary-4x7b-MoE.i1-Q3_K_L.gguf) | i1-Q3_K_L | 12.6 | IQ3_M probably better |\n| [GGUF](https://huggingface.co/mradermacher/Boundary-4x7b-MoE-i1-GGUF/resolve/main/Boundary-4x7b-MoE.i1-IQ4_XS.gguf) | i1-IQ4_XS | 13.0 |  |\n| [GGUF](https://huggingface.co/mradermacher/Boundary-4x7b-MoE-i1-GGUF/resolve/main/Boundary-4x7b-MoE.i1-Q4_0.gguf) | i1-Q4_0 | 13.8 | fast, low quality |\n| [GGUF](https://huggingface.co/mradermacher/Boundary-4x7b-MoE-i1-GGUF/resolve/main/Boundary-4x7b-MoE.i1-Q4_K_S.gguf) | i1-Q4_K_S | 13.8 | optimal size/speed/quality |\n| [GGUF](https://huggingface.co/mradermacher/Boundary-4x7b-MoE-i1-GGUF/resolve/main/Boundary-4x7b-MoE.i1-Q4_K_M.gguf) | i1-Q4_K_M | 14.7 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/Boundary-4x7b-MoE-i1-GGUF/resolve/main/Boundary-4x7b-MoE.i1-Q5_K_S.gguf) | i1-Q5_K_S | 16.7 |  |\n| [GGUF](https://huggingface.co/mradermacher/Boundary-4x7b-MoE-i1-GGUF/resolve/main/Boundary-4x7b-MoE.i1-Q5_K_M.gguf) | i1-Q5_K_M | 17.2 |  |\n| [GGUF](https://huggingface.co/mradermacher/Boundary-4x7b-MoE-i1-GGUF/resolve/main/Boundary-4x7b-MoE.i1-Q6_K.gguf) | i1-Q6_K | 19.9 | practically like static Q6_K |\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",
    "moe",
    "merge",
    "mergekit",
    "HuggingFaceH4/zephyr-7b-beta",
    "mistralai/Mistral-7B-Instruct-v0.2",
    "teknium/OpenHermes-2.5-Mistral-7B",
    "meta-math/MetaMath-Mistral-7B",
    "Mistral",
    "en",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 241,
  "gated": false,
  "private": false,
  "last_modified": "2024-05-06T04:40:55.000Z",
  "created_at": "2024-04-18T08:30:12.000Z",
  "pipeline_tag": "",
  "library_name": "transformers"
}

{
  "_id": "6620da14b6b17117b95370a3",
  "id": "mradermacher/Boundary-4x7b-MoE-i1-GGUF",
  "modelId": "mradermacher/Boundary-4x7b-MoE-i1-GGUF",
  "sha": "48fa01a47c4e8218d3024ecfa040ac8dd541486c",
  "createdAt": "2024-04-18T08:30:12.000Z",
  "lastModified": "2024-05-06T04:40:55.000Z",
  "author": "mradermacher",
  "downloads": 241,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "transformers",
  "siblings_count": 24
}