mradermacher/nous-hermes-2-yi-34b-i1-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "NousResearch/Nous-Hermes-2-Yi-34B",
    "datasets": [
      "teknium/OpenHermes-2.5"
    ],
    "language": [
      "en"
    ],
    "library_name": "transformers",
    "license": "apache-2.0",
    "quantized_by": "mradermacher",
    "tags": [
      "yi",
      "instruct",
      "finetune",
      "chatml",
      "gpt4",
      "synthetic data",
      "distillation"
    ],
    "frontmatter": {
      "base_model": "NousResearch/Nous-Hermes-2-Yi-34B",
      "datasets": [
        "teknium/OpenHermes-2.5"
      ],
      "language": [
        "en"
      ],
      "library_name": "transformers",
      "license": "apache-2.0",
      "quantized_by": "mradermacher",
      "tags": [
        "yi",
        "instruct",
        "finetune",
        "chatml",
        "gpt4",
        "synthetic data",
        "distillation"
      ]
    },
    "hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
    "summary": "## About weighted/imatrix quants of https://huggingface.co/NousResearch/Nous-Hermes-2-Yi-34B",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: NousResearch/Nous-Hermes-2-Yi-34B\ndatasets:\n- teknium/OpenHermes-2.5\nlanguage:\n- en\nlibrary_name: transformers\nlicense: apache-2.0\nquantized_by: mradermacher\ntags:\n- yi\n- instruct\n- finetune\n- chatml\n- gpt4\n- synthetic data\n- distillation\n---\n## About\n\nweighted/imatrix quants of https://huggingface.co/NousResearch/Nous-Hermes-2-Yi-34B\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/Nous-Hermes-2-Yi-34B-i1-GGUF/resolve/main/Nous-Hermes-2-Yi-34B.i1-IQ1_S.gguf) | i1-IQ1_S | 8.2 | for the desperate |\n| [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-Yi-34B-i1-GGUF/resolve/main/Nous-Hermes-2-Yi-34B.i1-IQ1_M.gguf) | i1-IQ1_M | 8.3 | mostly desperate |\n| [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-Yi-34B-i1-GGUF/resolve/main/Nous-Hermes-2-Yi-34B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 10.0 |  |\n| [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-Yi-34B-i1-GGUF/resolve/main/Nous-Hermes-2-Yi-34B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 11.0 |  |\n| [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-Yi-34B-i1-GGUF/resolve/main/Nous-Hermes-2-Yi-34B.i1-IQ2_S.gguf) | i1-IQ2_S | 11.6 |  |\n| [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-Yi-34B-i1-GGUF/resolve/main/Nous-Hermes-2-Yi-34B.i1-IQ2_M.gguf) | i1-IQ2_M | 12.5 |  |\n| [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-Yi-34B-i1-GGUF/resolve/main/Nous-Hermes-2-Yi-34B.i1-Q2_K.gguf) | i1-Q2_K | 13.5 | IQ3_XXS probably better |\n| [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-Yi-34B-i1-GGUF/resolve/main/Nous-Hermes-2-Yi-34B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 14.0 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-Yi-34B-i1-GGUF/resolve/main/Nous-Hermes-2-Yi-34B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 14.8 |  |\n| [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-Yi-34B-i1-GGUF/resolve/main/Nous-Hermes-2-Yi-34B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 15.6 | IQ3_XS probably better |\n| [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-Yi-34B-i1-GGUF/resolve/main/Nous-Hermes-2-Yi-34B.i1-IQ3_S.gguf) | i1-IQ3_S | 15.7 | beats Q3_K* |\n| [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-Yi-34B-i1-GGUF/resolve/main/Nous-Hermes-2-Yi-34B.i1-IQ3_M.gguf) | i1-IQ3_M | 16.2 |  |\n| [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-Yi-34B-i1-GGUF/resolve/main/Nous-Hermes-2-Yi-34B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 17.3 | IQ3_S probably better |\n| [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-Yi-34B-i1-GGUF/resolve/main/Nous-Hermes-2-Yi-34B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 18.6 |  |\n| [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-Yi-34B-i1-GGUF/resolve/main/Nous-Hermes-2-Yi-34B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 18.8 | IQ3_M probably better |\n| [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-Yi-34B-i1-GGUF/resolve/main/Nous-Hermes-2-Yi-34B.i1-Q4_0.gguf) | i1-Q4_0 | 19.6 | fast, low quality |\n| [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-Yi-34B-i1-GGUF/resolve/main/Nous-Hermes-2-Yi-34B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 20.2 | optimal size/speed/quality |\n| [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-Yi-34B-i1-GGUF/resolve/main/Nous-Hermes-2-Yi-34B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 21.3 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-Yi-34B-i1-GGUF/resolve/main/Nous-Hermes-2-Yi-34B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 24.3 |  |\n| [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-Yi-34B-i1-GGUF/resolve/main/Nous-Hermes-2-Yi-34B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 25.0 |  |\n| [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-2-Yi-34B-i1-GGUF/resolve/main/Nous-Hermes-2-Yi-34B.i1-Q6_K.gguf) | i1-Q6_K | 28.9 | 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",
    "yi",
    "instruct",
    "finetune",
    "chatml",
    "gpt4",
    "synthetic data",
    "distillation",
    "en",
    "dataset:teknium/OpenHermes-2.5",
    "base_model:NousResearch/Nous-Hermes-2-Yi-34B",
    "base_model:quantized:NousResearch/Nous-Hermes-2-Yi-34B",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "imatrix",
    "conversational"
  ],
  "likes": 2,
  "downloads": 952,
  "gated": false,
  "private": false,
  "last_modified": "2024-05-08T04:45:59.000Z",
  "created_at": "2024-03-07T09:04:56.000Z",
  "pipeline_tag": "",
  "library_name": "transformers"
}

{
  "_id": "65e983380ba2a33b5aa3388f",
  "id": "mradermacher/Nous-Hermes-2-Yi-34B-i1-GGUF",
  "modelId": "mradermacher/Nous-Hermes-2-Yi-34B-i1-GGUF",
  "sha": "cc0531df694d31e46b4399b3c9c0b078a0de98ec",
  "createdAt": "2024-03-07T09:04:56.000Z",
  "lastModified": "2024-05-08T04:45:59.000Z",
  "author": "mradermacher",
  "downloads": 952,
  "likes": 2,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "transformers",
  "siblings_count": 24
}