mradermacher/dse-qwen2-2b-mrl-v1-i1-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "MrLight/dse-qwen2-2b-mrl-v1",
    "datasets": [
      "Tevatron/docmatix-ir",
      "HuggingFaceM4/Docmatix",
      "Tevatron/msmarco-passage-aug",
      "vidore/colpali_train_set",
      "Tevatron/wiki-ss-nq"
    ],
    "language": [
      "en",
      "fr"
    ],
    "library_name": "transformers",
    "license": "apache-2.0",
    "mradermacher": {
      "readme_rev": 1
    },
    "quantized_by": "mradermacher",
    "tags": [
      "vidore"
    ],
    "frontmatter": {
      "base_model": "MrLight/dse-qwen2-2b-mrl-v1",
      "datasets": [
        "Tevatron/docmatix-ir",
        "HuggingFaceM4/Docmatix",
        "Tevatron/msmarco-passage-aug",
        "vidore/colpali_train_set",
        "Tevatron/wiki-ss-nq"
      ],
      "language": [
        "en",
        "fr"
      ],
      "library_name": "transformers",
      "license": "apache-2.0",
      "mradermacher": [],
      "quantized_by": "mradermacher",
      "tags": [
        "vidore"
      ]
    },
    "hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
    "summary": "## About      weighted/imatrix quants of https://huggingface.co/MrLight/dse-qwen2-2b-mrl-v1  ***For a convenient overview and download list, visit our model page for this model.*** static quants are available at https://huggingface.co/mradermacher/dse-qwen2-2b-mrl-v1-GGUF **This is a vision model - mmproj files (if any) will be in the static repository.**",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: MrLight/dse-qwen2-2b-mrl-v1\ndatasets:\n- Tevatron/docmatix-ir\n- HuggingFaceM4/Docmatix\n- Tevatron/msmarco-passage-aug\n- vidore/colpali_train_set\n- Tevatron/wiki-ss-nq\nlanguage:\n- en\n- fr\nlibrary_name: transformers\nlicense: apache-2.0\nmradermacher:\n  readme_rev: 1\nquantized_by: mradermacher\ntags:\n- vidore\n---\n## About\n\n<!-- ### quantize_version: 2 -->\n<!-- ### output_tensor_quantised: 1 -->\n<!-- ### convert_type: hf -->\n<!-- ### vocab_type:  -->\n<!-- ### tags: nicoboss -->\nweighted/imatrix quants of https://huggingface.co/MrLight/dse-qwen2-2b-mrl-v1\n\n<!-- provided-files -->\n\n***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#dse-qwen2-2b-mrl-v1-i1-GGUF).***\n\nstatic quants are available at https://huggingface.co/mradermacher/dse-qwen2-2b-mrl-v1-GGUF\n\n**This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/dse-qwen2-2b-mrl-v1-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/dse-qwen2-2b-mrl-v1-i1-GGUF/resolve/main/dse-qwen2-2b-mrl-v1.i1-IQ1_S.gguf) | i1-IQ1_S | 0.6 | for the desperate |\n| [GGUF](https://huggingface.co/mradermacher/dse-qwen2-2b-mrl-v1-i1-GGUF/resolve/main/dse-qwen2-2b-mrl-v1.i1-IQ1_M.gguf) | i1-IQ1_M | 0.6 | mostly desperate |\n| [GGUF](https://huggingface.co/mradermacher/dse-qwen2-2b-mrl-v1-i1-GGUF/resolve/main/dse-qwen2-2b-mrl-v1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.7 |  |\n| [GGUF](https://huggingface.co/mradermacher/dse-qwen2-2b-mrl-v1-i1-GGUF/resolve/main/dse-qwen2-2b-mrl-v1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.7 |  |\n| [GGUF](https://huggingface.co/mradermacher/dse-qwen2-2b-mrl-v1-i1-GGUF/resolve/main/dse-qwen2-2b-mrl-v1.i1-IQ2_S.gguf) | i1-IQ2_S | 0.8 |  |\n| [GGUF](https://huggingface.co/mradermacher/dse-qwen2-2b-mrl-v1-i1-GGUF/resolve/main/dse-qwen2-2b-mrl-v1.i1-IQ2_M.gguf) | i1-IQ2_M | 0.8 |  |\n| [GGUF](https://huggingface.co/mradermacher/dse-qwen2-2b-mrl-v1-i1-GGUF/resolve/main/dse-qwen2-2b-mrl-v1.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.8 | very low quality |\n| [GGUF](https://huggingface.co/mradermacher/dse-qwen2-2b-mrl-v1-i1-GGUF/resolve/main/dse-qwen2-2b-mrl-v1.i1-Q2_K.gguf) | i1-Q2_K | 0.9 | IQ3_XXS probably better |\n| [GGUF](https://huggingface.co/mradermacher/dse-qwen2-2b-mrl-v1-i1-GGUF/resolve/main/dse-qwen2-2b-mrl-v1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.9 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/dse-qwen2-2b-mrl-v1-i1-GGUF/resolve/main/dse-qwen2-2b-mrl-v1.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.9 |  |\n| [GGUF](https://huggingface.co/mradermacher/dse-qwen2-2b-mrl-v1-i1-GGUF/resolve/main/dse-qwen2-2b-mrl-v1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.0 | IQ3_XS probably better |\n| [GGUF](https://huggingface.co/mradermacher/dse-qwen2-2b-mrl-v1-i1-GGUF/resolve/main/dse-qwen2-2b-mrl-v1.i1-IQ3_S.gguf) | i1-IQ3_S | 1.0 | beats Q3_K* |\n| [GGUF](https://huggingface.co/mradermacher/dse-qwen2-2b-mrl-v1-i1-GGUF/resolve/main/dse-qwen2-2b-mrl-v1.i1-IQ3_M.gguf) | i1-IQ3_M | 1.0 |  |\n| [GGUF](https://huggingface.co/mradermacher/dse-qwen2-2b-mrl-v1-i1-GGUF/resolve/main/dse-qwen2-2b-mrl-v1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.0 | IQ3_S probably better |\n| [GGUF](https://huggingface.co/mradermacher/dse-qwen2-2b-mrl-v1-i1-GGUF/resolve/main/dse-qwen2-2b-mrl-v1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.1 | IQ3_M probably better |\n| [GGUF](https://huggingface.co/mradermacher/dse-qwen2-2b-mrl-v1-i1-GGUF/resolve/main/dse-qwen2-2b-mrl-v1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.1 |  |\n| [GGUF](https://huggingface.co/mradermacher/dse-qwen2-2b-mrl-v1-i1-GGUF/resolve/main/dse-qwen2-2b-mrl-v1.i1-IQ4_NL.gguf) | i1-IQ4_NL | 1.2 | prefer IQ4_XS |\n| [GGUF](https://huggingface.co/mradermacher/dse-qwen2-2b-mrl-v1-i1-GGUF/resolve/main/dse-qwen2-2b-mrl-v1.i1-Q4_0.gguf) | i1-Q4_0 | 1.2 | fast, low quality |\n| [GGUF](https://huggingface.co/mradermacher/dse-qwen2-2b-mrl-v1-i1-GGUF/resolve/main/dse-qwen2-2b-mrl-v1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.2 | optimal size/speed/quality |\n| [GGUF](https://huggingface.co/mradermacher/dse-qwen2-2b-mrl-v1-i1-GGUF/resolve/main/dse-qwen2-2b-mrl-v1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 1.2 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/dse-qwen2-2b-mrl-v1-i1-GGUF/resolve/main/dse-qwen2-2b-mrl-v1.i1-Q4_1.gguf) | i1-Q4_1 | 1.3 |  |\n| [GGUF](https://huggingface.co/mradermacher/dse-qwen2-2b-mrl-v1-i1-GGUF/resolve/main/dse-qwen2-2b-mrl-v1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 1.4 |  |\n| [GGUF](https://huggingface.co/mradermacher/dse-qwen2-2b-mrl-v1-i1-GGUF/resolve/main/dse-qwen2-2b-mrl-v1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 1.4 |  |\n| [GGUF](https://huggingface.co/mradermacher/dse-qwen2-2b-mrl-v1-i1-GGUF/resolve/main/dse-qwen2-2b-mrl-v1.i1-Q6_K.gguf) | i1-Q6_K | 1.6 | 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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.\n\n<!-- end -->\n",
    "related_quantizations": []
  },
  "tags": [
    "transformers",
    "gguf",
    "vidore",
    "en",
    "fr",
    "dataset:Tevatron/docmatix-ir",
    "dataset:HuggingFaceM4/Docmatix",
    "dataset:Tevatron/msmarco-passage-aug",
    "dataset:vidore/colpali_train_set",
    "dataset:Tevatron/wiki-ss-nq",
    "base_model:MrLight/dse-qwen2-2b-mrl-v1",
    "base_model:quantized:MrLight/dse-qwen2-2b-mrl-v1",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "imatrix",
    "conversational"
  ],
  "likes": 0,
  "downloads": 441,
  "gated": false,
  "private": false,
  "last_modified": "2025-07-11T12:24:14.000Z",
  "created_at": "2025-02-09T00:43:42.000Z",
  "pipeline_tag": "",
  "library_name": "transformers"
}

{
  "_id": "67a7fa3e1119ebde3a46bdfe",
  "id": "mradermacher/dse-qwen2-2b-mrl-v1-i1-GGUF",
  "modelId": "mradermacher/dse-qwen2-2b-mrl-v1-i1-GGUF",
  "sha": "12623a218fe2bd6c69ddcb7504e96aa894358666",
  "createdAt": "2025-02-09T00:43:42.000Z",
  "lastModified": "2025-07-11T12:24:14.000Z",
  "author": "mradermacher",
  "downloads": 441,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "transformers",
  "siblings_count": 27
}