mradermacher/llama-2-70b-hf-i1-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "NousResearch/Llama-2-70b-hf",
    "extra_gated_button_content": "Submit",
    "extra_gated_fields": {
      "I agree to share my name, email address and username with Meta and confirm that I have already been granted download access on the Meta website": "checkbox"
    },
    "extra_gated_heading": "Access Llama 2 on Hugging Face",
    "language": [
      "en"
    ],
    "library_name": "transformers",
    "quantized_by": "mradermacher",
    "tags": [
      "facebook",
      "meta",
      "pytorch",
      "llama",
      "llama-2"
    ],
    "frontmatter": {
      "base_model": "NousResearch/Llama-2-70b-hf",
      "extra_gated_button_content": "Submit",
      "extra_gated_fields": [],
      "extra_gated_heading": "Access Llama 2 on Hugging Face",
      "language": [
        "en"
      ],
      "library_name": "transformers",
      "quantized_by": "mradermacher",
      "tags": [
        "facebook",
        "meta",
        "pytorch",
        "llama",
        "llama-2"
      ]
    },
    "hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
    "summary": "## About      weighted/imatrix quants of https://huggingface.co/NousResearch/Llama-2-70b-hf  static quants are available at https://huggingface.co/mradermacher/Llama-2-70b-hf-GGUF",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: NousResearch/Llama-2-70b-hf\nextra_gated_button_content: Submit\nextra_gated_fields:\n  ? I agree to share my name, email address and username with Meta and confirm that\n    I have already been granted download access on the Meta website\n  : checkbox\nextra_gated_heading: Access Llama 2 on Hugging Face\nlanguage:\n- en\nlibrary_name: transformers\nquantized_by: mradermacher\ntags:\n- facebook\n- meta\n- pytorch\n- llama\n- llama-2\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/NousResearch/Llama-2-70b-hf\n\n<!-- provided-files -->\nstatic quants are available at https://huggingface.co/mradermacher/Llama-2-70b-hf-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/Llama-2-70b-hf-i1-GGUF/resolve/main/Llama-2-70b-hf.i1-IQ1_S.gguf) | i1-IQ1_S | 14.6 | for the desperate |\n| [GGUF](https://huggingface.co/mradermacher/Llama-2-70b-hf-i1-GGUF/resolve/main/Llama-2-70b-hf.i1-IQ1_M.gguf) | i1-IQ1_M | 16.0 | mostly desperate |\n| [GGUF](https://huggingface.co/mradermacher/Llama-2-70b-hf-i1-GGUF/resolve/main/Llama-2-70b-hf.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 18.4 |  |\n| [GGUF](https://huggingface.co/mradermacher/Llama-2-70b-hf-i1-GGUF/resolve/main/Llama-2-70b-hf.i1-IQ2_XS.gguf) | i1-IQ2_XS | 20.4 |  |\n| [GGUF](https://huggingface.co/mradermacher/Llama-2-70b-hf-i1-GGUF/resolve/main/Llama-2-70b-hf.i1-IQ2_S.gguf) | i1-IQ2_S | 21.5 |  |\n| [GGUF](https://huggingface.co/mradermacher/Llama-2-70b-hf-i1-GGUF/resolve/main/Llama-2-70b-hf.i1-IQ2_M.gguf) | i1-IQ2_M | 23.3 |  |\n| [GGUF](https://huggingface.co/mradermacher/Llama-2-70b-hf-i1-GGUF/resolve/main/Llama-2-70b-hf.i1-Q2_K.gguf) | i1-Q2_K | 25.6 | IQ3_XXS probably better |\n| [GGUF](https://huggingface.co/mradermacher/Llama-2-70b-hf-i1-GGUF/resolve/main/Llama-2-70b-hf.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 26.7 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/Llama-2-70b-hf-i1-GGUF/resolve/main/Llama-2-70b-hf.i1-IQ3_XS.gguf) | i1-IQ3_XS | 28.4 |  |\n| [GGUF](https://huggingface.co/mradermacher/Llama-2-70b-hf-i1-GGUF/resolve/main/Llama-2-70b-hf.i1-IQ3_S.gguf) | i1-IQ3_S | 30.0 | beats Q3_K* |\n| [GGUF](https://huggingface.co/mradermacher/Llama-2-70b-hf-i1-GGUF/resolve/main/Llama-2-70b-hf.i1-Q3_K_S.gguf) | i1-Q3_K_S | 30.0 | IQ3_XS probably better |\n| [GGUF](https://huggingface.co/mradermacher/Llama-2-70b-hf-i1-GGUF/resolve/main/Llama-2-70b-hf.i1-IQ3_M.gguf) | i1-IQ3_M | 31.0 |  |\n| [GGUF](https://huggingface.co/mradermacher/Llama-2-70b-hf-i1-GGUF/resolve/main/Llama-2-70b-hf.i1-Q3_K_M.gguf) | i1-Q3_K_M | 33.4 | IQ3_S probably better |\n| [GGUF](https://huggingface.co/mradermacher/Llama-2-70b-hf-i1-GGUF/resolve/main/Llama-2-70b-hf.i1-Q3_K_L.gguf) | i1-Q3_K_L | 36.2 | IQ3_M probably better |\n| [GGUF](https://huggingface.co/mradermacher/Llama-2-70b-hf-i1-GGUF/resolve/main/Llama-2-70b-hf.i1-IQ4_XS.gguf) | i1-IQ4_XS | 36.9 |  |\n| [GGUF](https://huggingface.co/mradermacher/Llama-2-70b-hf-i1-GGUF/resolve/main/Llama-2-70b-hf.i1-Q4_0.gguf) | i1-Q4_0 | 39.1 | fast, low quality |\n| [GGUF](https://huggingface.co/mradermacher/Llama-2-70b-hf-i1-GGUF/resolve/main/Llama-2-70b-hf.i1-Q4_K_S.gguf) | i1-Q4_K_S | 39.3 | optimal size/speed/quality |\n| [GGUF](https://huggingface.co/mradermacher/Llama-2-70b-hf-i1-GGUF/resolve/main/Llama-2-70b-hf.i1-Q4_K_M.gguf) | i1-Q4_K_M | 41.5 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/Llama-2-70b-hf-i1-GGUF/resolve/main/Llama-2-70b-hf.i1-Q5_K_S.gguf) | i1-Q5_K_S | 47.6 |  |\n| [GGUF](https://huggingface.co/mradermacher/Llama-2-70b-hf-i1-GGUF/resolve/main/Llama-2-70b-hf.i1-Q5_K_M.gguf) | i1-Q5_K_M | 48.9 |  |\n| [PART 1](https://huggingface.co/mradermacher/Llama-2-70b-hf-i1-GGUF/resolve/main/Llama-2-70b-hf.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-2-70b-hf-i1-GGUF/resolve/main/Llama-2-70b-hf.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 56.7 | 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",
    "facebook",
    "meta",
    "pytorch",
    "llama",
    "llama-2",
    "en",
    "base_model:NousResearch/Llama-2-70b-hf",
    "base_model:quantized:NousResearch/Llama-2-70b-hf",
    "endpoints_compatible",
    "region:us",
    "imatrix"
  ],
  "likes": 0,
  "downloads": 83,
  "gated": false,
  "private": false,
  "last_modified": "2024-09-10T09:02:09.000Z",
  "created_at": "2024-09-08T22:00:59.000Z",
  "pipeline_tag": "",
  "library_name": "transformers"
}

{
  "_id": "66de1e9b89340783871f59d8",
  "id": "mradermacher/Llama-2-70b-hf-i1-GGUF",
  "modelId": "mradermacher/Llama-2-70b-hf-i1-GGUF",
  "sha": "27f6a5372abdddd22f9449fd51f49a370aff3b98",
  "createdAt": "2024-09-08T22:00:59.000Z",
  "lastModified": "2024-09-10T09:02:09.000Z",
  "author": "mradermacher",
  "downloads": 83,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "transformers",
  "siblings_count": 25
}