GraySoft
Projects Models About FAQ Contact Download guIDE →
Model Intelligence Sheet

mradermacher/swallow-13b-hf-i1-gguf overview

About weighted/imatrix quants of https://huggingface.co/tokyotech-llm/Swallow-13b-hf static quants are available at https://huggingface.co/mradermacher/Swallow-13b-hf-GGUF

transformersggufenjabase_model:tokyotech-llm/Swallow-13b-hfbase_model:quantized:tokyotech-llm/Swallow-13b-hflicense:llama2endpoints_compatibleregion:usimatrix
mradermacher/swallow-13b-hf-i1-gguf visual
Downloads
215
Likes
0
Pipeline
Library
transformers
Visibility
Public
Access
Open

Repository Files & Downloads

21 files detected
Direct downloads for all repository files
FileTypeQuantizationSizeLink
Swallow-13b-hf.i1-IQ1_M.gguf GGUF IQ1_M 2.98 GB Download
Swallow-13b-hf.i1-IQ1_S.gguf GGUF IQ1_S 2.75 GB Download
Swallow-13b-hf.i1-IQ2_M.gguf GGUF IQ2_M 4.27 GB Download
Swallow-13b-hf.i1-IQ2_S.gguf GGUF IQ2_S 3.97 GB Download
Swallow-13b-hf.i1-IQ2_XS.gguf GGUF IQ2_XS 3.68 GB Download
Swallow-13b-hf.i1-IQ2_XXS.gguf GGUF IQ2_XXS 3.35 GB Download
Swallow-13b-hf.i1-IQ3_M.gguf GGUF IQ3_M 5.64 GB Download
Swallow-13b-hf.i1-IQ3_S.gguf GGUF IQ3_S 5.34 GB Download
Swallow-13b-hf.i1-IQ3_XS.gguf GGUF IQ3_XS 5.06 GB Download
Swallow-13b-hf.i1-IQ3_XXS.gguf GGUF IQ3_XXS 4.68 GB Download
Swallow-13b-hf.i1-IQ4_XS.gguf GGUF IQ4_XS 6.56 GB Download
Swallow-13b-hf.i1-Q2_K.gguf GGUF Q2_K 4.58 GB Download
Swallow-13b-hf.i1-Q3_K_L.gguf GGUF Q3_K_L 6.52 GB Download
Swallow-13b-hf.i1-Q3_K_M.gguf GGUF Q3_K_M 5.97 GB Download
Swallow-13b-hf.i1-Q3_K_S.gguf GGUF Q3_K_S 5.34 GB Download
Swallow-13b-hf.i1-Q4_0.gguf GGUF 6.95 GB Download
Swallow-13b-hf.i1-Q4_K_M.gguf GGUF Q4_K_M 7.40 GB Download
Swallow-13b-hf.i1-Q4_K_S.gguf GGUF Q4_K_S 6.99 GB Download
Swallow-13b-hf.i1-Q5_K_M.gguf GGUF Q5_K_M 8.68 GB Download
Swallow-13b-hf.i1-Q5_K_S.gguf GGUF Q5_K_S 8.44 GB Download
Swallow-13b-hf.i1-Q6_K.gguf GGUF Q6_K 10.03 GB Download

Model Details Live

Model Slug
mradermacher/swallow-13b-hf-i1-gguf
Author
mradermacher
Pipeline Task
Library
transformers
Created
2024-06-30
Last Modified
2024-08-02
Gated
No
Private
No
HF SHA
7f21efb2e6d134a17fe08973afcd7f0f69d17912
License
llama2
Language
en, ja
Base Model
tokyotech-llm/Swallow-13b-hf

Metadata Inspector

Normalized metadata (stored in metadata_json)
{
  "metadata": {},
  "card_data": {
    "base_model": "tokyotech-llm/Swallow-13b-hf",
    "language": [
      "en",
      "ja"
    ],
    "library_name": "transformers",
    "license": "llama2",
    "model_type": "llama",
    "quantized_by": "mradermacher",
    "frontmatter": {
      "base_model": "tokyotech-llm/Swallow-13b-hf",
      "language": [
        "en",
        "ja"
      ],
      "library_name": "transformers",
      "license": "llama2",
      "model_type": "llama",
      "quantized_by": "mradermacher"
    },
    "hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
    "summary": "## About      weighted/imatrix quants of https://huggingface.co/tokyotech-llm/Swallow-13b-hf  static quants are available at https://huggingface.co/mradermacher/Swallow-13b-hf-GGUF",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: tokyotech-llm/Swallow-13b-hf\nlanguage:\n- en\n- ja\nlibrary_name: transformers\nlicense: llama2\nmodel_type: llama\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: nicoboss -->\nweighted/imatrix quants of https://huggingface.co/tokyotech-llm/Swallow-13b-hf\n\n<!-- provided-files -->\nstatic quants are available at https://huggingface.co/mradermacher/Swallow-13b-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/Swallow-13b-hf-i1-GGUF/resolve/main/Swallow-13b-hf.i1-IQ1_S.gguf) | i1-IQ1_S | 3.1 | for the desperate |\n| [GGUF](https://huggingface.co/mradermacher/Swallow-13b-hf-i1-GGUF/resolve/main/Swallow-13b-hf.i1-IQ1_M.gguf) | i1-IQ1_M | 3.3 | mostly desperate |\n| [GGUF](https://huggingface.co/mradermacher/Swallow-13b-hf-i1-GGUF/resolve/main/Swallow-13b-hf.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.7 |  |\n| [GGUF](https://huggingface.co/mradermacher/Swallow-13b-hf-i1-GGUF/resolve/main/Swallow-13b-hf.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.0 |  |\n| [GGUF](https://huggingface.co/mradermacher/Swallow-13b-hf-i1-GGUF/resolve/main/Swallow-13b-hf.i1-IQ2_S.gguf) | i1-IQ2_S | 4.4 |  |\n| [GGUF](https://huggingface.co/mradermacher/Swallow-13b-hf-i1-GGUF/resolve/main/Swallow-13b-hf.i1-IQ2_M.gguf) | i1-IQ2_M | 4.7 |  |\n| [GGUF](https://huggingface.co/mradermacher/Swallow-13b-hf-i1-GGUF/resolve/main/Swallow-13b-hf.i1-Q2_K.gguf) | i1-Q2_K | 5.0 | IQ3_XXS probably better |\n| [GGUF](https://huggingface.co/mradermacher/Swallow-13b-hf-i1-GGUF/resolve/main/Swallow-13b-hf.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 5.1 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/Swallow-13b-hf-i1-GGUF/resolve/main/Swallow-13b-hf.i1-IQ3_XS.gguf) | i1-IQ3_XS | 5.5 |  |\n| [GGUF](https://huggingface.co/mradermacher/Swallow-13b-hf-i1-GGUF/resolve/main/Swallow-13b-hf.i1-IQ3_S.gguf) | i1-IQ3_S | 5.8 | beats Q3_K* |\n| [GGUF](https://huggingface.co/mradermacher/Swallow-13b-hf-i1-GGUF/resolve/main/Swallow-13b-hf.i1-Q3_K_S.gguf) | i1-Q3_K_S | 5.8 | IQ3_XS probably better |\n| [GGUF](https://huggingface.co/mradermacher/Swallow-13b-hf-i1-GGUF/resolve/main/Swallow-13b-hf.i1-IQ3_M.gguf) | i1-IQ3_M | 6.2 |  |\n| [GGUF](https://huggingface.co/mradermacher/Swallow-13b-hf-i1-GGUF/resolve/main/Swallow-13b-hf.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.5 | IQ3_S probably better |\n| [GGUF](https://huggingface.co/mradermacher/Swallow-13b-hf-i1-GGUF/resolve/main/Swallow-13b-hf.i1-Q3_K_L.gguf) | i1-Q3_K_L | 7.1 | IQ3_M probably better |\n| [GGUF](https://huggingface.co/mradermacher/Swallow-13b-hf-i1-GGUF/resolve/main/Swallow-13b-hf.i1-IQ4_XS.gguf) | i1-IQ4_XS | 7.1 |  |\n| [GGUF](https://huggingface.co/mradermacher/Swallow-13b-hf-i1-GGUF/resolve/main/Swallow-13b-hf.i1-Q4_0.gguf) | i1-Q4_0 | 7.6 | fast, low quality |\n| [GGUF](https://huggingface.co/mradermacher/Swallow-13b-hf-i1-GGUF/resolve/main/Swallow-13b-hf.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.6 | optimal size/speed/quality |\n| [GGUF](https://huggingface.co/mradermacher/Swallow-13b-hf-i1-GGUF/resolve/main/Swallow-13b-hf.i1-Q4_K_M.gguf) | i1-Q4_K_M | 8.0 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/Swallow-13b-hf-i1-GGUF/resolve/main/Swallow-13b-hf.i1-Q5_K_S.gguf) | i1-Q5_K_S | 9.2 |  |\n| [GGUF](https://huggingface.co/mradermacher/Swallow-13b-hf-i1-GGUF/resolve/main/Swallow-13b-hf.i1-Q5_K_M.gguf) | i1-Q5_K_M | 9.4 |  |\n| [GGUF](https://huggingface.co/mradermacher/Swallow-13b-hf-i1-GGUF/resolve/main/Swallow-13b-hf.i1-Q6_K.gguf) | i1-Q6_K | 10.9 | 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. 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",
    "en",
    "ja",
    "base_model:tokyotech-llm/Swallow-13b-hf",
    "base_model:quantized:tokyotech-llm/Swallow-13b-hf",
    "license:llama2",
    "endpoints_compatible",
    "region:us",
    "imatrix"
  ],
  "likes": 0,
  "downloads": 215,
  "gated": false,
  "private": false,
  "last_modified": "2024-08-02T10:03:46.000Z",
  "created_at": "2024-06-30T07:18:54.000Z",
  "pipeline_tag": "",
  "library_name": "transformers"
}
Source payload excerpt (from Hugging Face API)
{
  "_id": "668106de20ee9ac41731c3ba",
  "id": "mradermacher/Swallow-13b-hf-i1-GGUF",
  "modelId": "mradermacher/Swallow-13b-hf-i1-GGUF",
  "sha": "7f21efb2e6d134a17fe08973afcd7f0f69d17912",
  "createdAt": "2024-06-30T07:18:54.000Z",
  "lastModified": "2024-08-02T10:03:46.000Z",
  "author": "mradermacher",
  "downloads": 215,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "transformers",
  "siblings_count": 24
}