mradermacher/deepseek-v2-lite-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "ZZichen/DeepSeek-V2-Lite",
    "language": [
      "en"
    ],
    "library_name": "transformers",
    "no_imatrix": "GGML_ASSERT: llama.cpp/ggml-cuda/concat.cu:107: ggml_is_contiguous(src0)",
    "quantized_by": "mradermacher",
    "frontmatter": {
      "base_model": "ZZichen/DeepSeek-V2-Lite",
      "language": [
        "en"
      ],
      "library_name": "transformers",
      "no_imatrix": "'GGML_ASSERT: llama.cpp/ggml-cuda/concat.cu:107: ggml_is_contiguous(src0)'",
      "quantized_by": "mradermacher"
    },
    "hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
    "summary": "## About      static quants of https://huggingface.co/ZZichen/DeepSeek-V2-Lite",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: ZZichen/DeepSeek-V2-Lite\nlanguage:\n- en\nlibrary_name: transformers\nno_imatrix: 'GGML_ASSERT: llama.cpp/ggml-cuda/concat.cu:107: ggml_is_contiguous(src0)'\nquantized_by: mradermacher\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/ZZichen/DeepSeek-V2-Lite\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/DeepSeek-V2-Lite-GGUF/resolve/main/DeepSeek-V2-Lite.Q2_K.gguf) | Q2_K | 6.5 |  |\n| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V2-Lite-GGUF/resolve/main/DeepSeek-V2-Lite.IQ3_XS.gguf) | IQ3_XS | 7.2 |  |\n| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V2-Lite-GGUF/resolve/main/DeepSeek-V2-Lite.IQ3_S.gguf) | IQ3_S | 7.6 | beats Q3_K* |\n| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V2-Lite-GGUF/resolve/main/DeepSeek-V2-Lite.Q3_K_S.gguf) | Q3_K_S | 7.6 |  |\n| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V2-Lite-GGUF/resolve/main/DeepSeek-V2-Lite.IQ3_M.gguf) | IQ3_M | 7.7 |  |\n| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V2-Lite-GGUF/resolve/main/DeepSeek-V2-Lite.Q3_K_M.gguf) | Q3_K_M | 8.2 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V2-Lite-GGUF/resolve/main/DeepSeek-V2-Lite.Q3_K_L.gguf) | Q3_K_L | 8.6 |  |\n| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V2-Lite-GGUF/resolve/main/DeepSeek-V2-Lite.IQ4_XS.gguf) | IQ4_XS | 8.7 |  |\n| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V2-Lite-GGUF/resolve/main/DeepSeek-V2-Lite.Q4_K_S.gguf) | Q4_K_S | 9.6 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V2-Lite-GGUF/resolve/main/DeepSeek-V2-Lite.Q4_K_M.gguf) | Q4_K_M | 10.5 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V2-Lite-GGUF/resolve/main/DeepSeek-V2-Lite.Q5_K_S.gguf) | Q5_K_S | 11.2 |  |\n| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V2-Lite-GGUF/resolve/main/DeepSeek-V2-Lite.Q5_K_M.gguf) | Q5_K_M | 12.0 |  |\n| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V2-Lite-GGUF/resolve/main/DeepSeek-V2-Lite.Q6_K.gguf) | Q6_K | 14.2 | very good quality |\n| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V2-Lite-GGUF/resolve/main/DeepSeek-V2-Lite.Q8_0.gguf) | Q8_0 | 16.8 | fast, best quality |\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",
    "en",
    "base_model:ZZichen/DeepSeek-V2-Lite",
    "base_model:quantized:ZZichen/DeepSeek-V2-Lite",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 5,
  "downloads": 1111,
  "gated": false,
  "private": false,
  "last_modified": "2024-05-31T09:01:27.000Z",
  "created_at": "2024-05-31T06:42:54.000Z",
  "pipeline_tag": "",
  "library_name": "transformers"
}

{
  "_id": "6659716edeaa741cf3171d55",
  "id": "mradermacher/DeepSeek-V2-Lite-GGUF",
  "modelId": "mradermacher/DeepSeek-V2-Lite-GGUF",
  "sha": "0f37fdf276e8094747457f0ae4d40f2e8d2521f9",
  "createdAt": "2024-05-31T06:42:54.000Z",
  "lastModified": "2024-05-31T09:01:27.000Z",
  "author": "mradermacher",
  "downloads": 1111,
  "likes": 5,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "transformers",
  "siblings_count": 16
}