mradermacher/deepseek-v2-13b-math7k-expert-enhance-subset-expert-moe-32-experts-i1-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "HectorHe/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts",
    "datasets": "HectorHe/math7k",
    "language": [
      "en"
    ],
    "library_name": "transformers",
    "model_name": "Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts",
    "mradermacher": {
      "readme_rev": 1
    },
    "quantized_by": "mradermacher",
    "tags": [
      "generated_from_trainer",
      "open-r1",
      "trl",
      "expert_enhance_distillation"
    ],
    "frontmatter": {
      "base_model": "HectorHe/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts",
      "datasets": "HectorHe/math7k",
      "language": [
        "en"
      ],
      "library_name": "transformers",
      "model_name": "Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts",
      "mradermacher": [],
      "quantized_by": "mradermacher",
      "tags": [
        "generated_from_trainer",
        "open-r1",
        "trl",
        "expert_enhance_distillation"
      ]
    },
    "hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
    "summary": "## About         weighted/imatrix quants of https://huggingface.co/HectorHe/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts  ***For a convenient overview and download list, visit our model page for this model.*** static quants are available at https://huggingface.co/mradermacher/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts-GGUF",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: HectorHe/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts\ndatasets: HectorHe/math7k\nlanguage:\n- en\nlibrary_name: transformers\nmodel_name: Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts\nmradermacher:\n  readme_rev: 1\nquantized_by: mradermacher\ntags:\n- generated_from_trainer\n- open-r1\n- trl\n- expert_enhance_distillation\n---\n## About\n\n<!-- ### quantize_version: 2 -->\n<!-- ### output_tensor_quantised: 1 -->\n<!-- ### convert_type: hf -->\n<!-- ### vocab_type:  -->\n<!-- ### tags: nicoboss -->\n<!-- ### quants: Q2_K IQ3_M Q4_K_S IQ3_XXS Q3_K_M small-IQ4_NL Q4_K_M IQ2_M Q6_K IQ4_XS Q2_K_S IQ1_M Q3_K_S IQ2_XXS Q3_K_L IQ2_XS Q5_K_S IQ2_S IQ1_S Q5_K_M Q4_0 IQ3_XS Q4_1 IQ3_S -->\n<!-- ### quants_skip:  -->\n<!-- ### skip_mmproj:  -->\nweighted/imatrix quants of https://huggingface.co/HectorHe/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts\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#Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts-i1-GGUF).***\n\nstatic quants are available at https://huggingface.co/mradermacher/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts-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/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts-i1-GGUF/resolve/main/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) |\n| [GGUF](https://huggingface.co/mradermacher/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts-i1-GGUF/resolve/main/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts.i1-IQ1_S.gguf) | i1-IQ1_S | 5.1 | for the desperate |\n| [GGUF](https://huggingface.co/mradermacher/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts-i1-GGUF/resolve/main/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts.i1-IQ1_M.gguf) | i1-IQ1_M | 5.3 | mostly desperate |\n| [GGUF](https://huggingface.co/mradermacher/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts-i1-GGUF/resolve/main/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 5.7 |  |\n| [GGUF](https://huggingface.co/mradermacher/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts-i1-GGUF/resolve/main/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts.i1-IQ2_XS.gguf) | i1-IQ2_XS | 6.1 |  |\n| [GGUF](https://huggingface.co/mradermacher/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts-i1-GGUF/resolve/main/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts.i1-IQ2_S.gguf) | i1-IQ2_S | 6.1 |  |\n| [GGUF](https://huggingface.co/mradermacher/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts-i1-GGUF/resolve/main/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts.i1-IQ2_M.gguf) | i1-IQ2_M | 6.4 |  |\n| [GGUF](https://huggingface.co/mradermacher/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts-i1-GGUF/resolve/main/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts.i1-Q2_K.gguf) | i1-Q2_K | 6.5 | IQ3_XXS probably better |\n| [GGUF](https://huggingface.co/mradermacher/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts-i1-GGUF/resolve/main/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts.i1-Q2_K_S.gguf) | i1-Q2_K_S | 6.6 | very low quality |\n| [GGUF](https://huggingface.co/mradermacher/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts-i1-GGUF/resolve/main/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 7.1 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts-i1-GGUF/resolve/main/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts.i1-IQ3_XS.gguf) | i1-IQ3_XS | 7.2 |  |\n| [GGUF](https://huggingface.co/mradermacher/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts-i1-GGUF/resolve/main/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts.i1-IQ3_S.gguf) | i1-IQ3_S | 7.6 | beats Q3_K* |\n| [GGUF](https://huggingface.co/mradermacher/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts-i1-GGUF/resolve/main/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts.i1-Q3_K_S.gguf) | i1-Q3_K_S | 7.6 | IQ3_XS probably better |\n| [GGUF](https://huggingface.co/mradermacher/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts-i1-GGUF/resolve/main/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts.i1-IQ3_M.gguf) | i1-IQ3_M | 7.7 |  |\n| [GGUF](https://huggingface.co/mradermacher/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts-i1-GGUF/resolve/main/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts.i1-Q3_K_M.gguf) | i1-Q3_K_M | 8.2 | IQ3_S probably better |\n| [GGUF](https://huggingface.co/mradermacher/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts-i1-GGUF/resolve/main/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts.i1-Q3_K_L.gguf) | i1-Q3_K_L | 8.6 | IQ3_M probably better |\n| [GGUF](https://huggingface.co/mradermacher/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts-i1-GGUF/resolve/main/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts.i1-IQ4_XS.gguf) | i1-IQ4_XS | 8.7 |  |\n| [GGUF](https://huggingface.co/mradermacher/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts-i1-GGUF/resolve/main/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts.i1-IQ4_NL.gguf) | i1-IQ4_NL | 9.0 | prefer IQ4_XS |\n| [GGUF](https://huggingface.co/mradermacher/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts-i1-GGUF/resolve/main/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts.i1-Q4_0.gguf) | i1-Q4_0 | 9.0 | fast, low quality |\n| [GGUF](https://huggingface.co/mradermacher/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts-i1-GGUF/resolve/main/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts.i1-Q4_K_S.gguf) | i1-Q4_K_S | 9.6 | optimal size/speed/quality |\n| [GGUF](https://huggingface.co/mradermacher/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts-i1-GGUF/resolve/main/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts.i1-Q4_1.gguf) | i1-Q4_1 | 10.0 |  |\n| [GGUF](https://huggingface.co/mradermacher/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts-i1-GGUF/resolve/main/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts.i1-Q4_K_M.gguf) | i1-Q4_K_M | 10.5 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts-i1-GGUF/resolve/main/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts.i1-Q5_K_S.gguf) | i1-Q5_K_S | 11.2 |  |\n| [GGUF](https://huggingface.co/mradermacher/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts-i1-GGUF/resolve/main/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts.i1-Q5_K_M.gguf) | i1-Q5_K_M | 12.0 |  |\n| [GGUF](https://huggingface.co/mradermacher/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts-i1-GGUF/resolve/main/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts.i1-Q6_K.gguf) | i1-Q6_K | 14.2 | 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",
    "generated_from_trainer",
    "open-r1",
    "trl",
    "expert_enhance_distillation",
    "en",
    "dataset:HectorHe/math7k",
    "base_model:HectorHe/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts",
    "base_model:quantized:HectorHe/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts",
    "endpoints_compatible",
    "region:us",
    "imatrix",
    "conversational"
  ],
  "likes": 1,
  "downloads": 384,
  "gated": false,
  "private": false,
  "last_modified": "2025-12-14T22:34:44.000Z",
  "created_at": "2025-08-19T21:26:10.000Z",
  "pipeline_tag": "",
  "library_name": "transformers"
}

{
  "_id": "68a4ebf28f7d251c1b571d31",
  "id": "mradermacher/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts-i1-GGUF",
  "modelId": "mradermacher/Deepseek-V2-13B-Math7K-Expert-Enhance-Subset-Expert-MoE-32-experts-i1-GGUF",
  "sha": "2c05d26f4c6f8907a9d5e97eda6a5cb0c71b9a19",
  "createdAt": "2025-08-19T21:26:10.000Z",
  "lastModified": "2025-12-14T22:34:44.000Z",
  "author": "mradermacher",
  "downloads": 384,
  "likes": 1,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "transformers",
  "siblings_count": 27
}