GraySoft
Projects Models About FAQ Contact Download guIDE →

mmnga/fugaku-llm-13b-instruct-gguf IQ3_XS GGUF - Free GGUF Download is indexed on GraySoft with repository links, GGUF quant files, and Hugging Face metadata. This page helps you pick a local model for guIDE or other runtimes. See related models in the same shard below.

Model Intelligence Sheet

mmnga/fugaku-llm-13b-instruct-gguf overview

Fugaku-LLMさんが公開しているFugaku-LLM-13B-instructのggufフォーマット変換版です。 imatrixのデータはTFMC/imatrix-dataset-for-japanese-llmを使用して作成しました。

ggufgpt2enjadataset:TFMC/imatrix-dataset-for-japanese-llmlicense:otherendpoints_compatibleregion:usimatrix
mmnga/fugaku-llm-13b-instruct-gguf visual
Downloads
249
Likes
6
Pipeline
Library
Visibility
Public
Access
Open

Repository Files & Downloads

24 files detected
Direct downloads for all repository files
FileTypeQuantizationSizeLink
Fugaku-LLM-13B-instruct-IQ1_M.gguf GGUF IQ1_M 5.85 GB Download
Fugaku-LLM-13B-instruct-IQ1_S.gguf GGUF IQ1_S 5.77 GB Download
Fugaku-LLM-13B-instruct-IQ2_M.gguf GGUF IQ2_M 6.26 GB Download
Fugaku-LLM-13B-instruct-IQ2_S.gguf GGUF IQ2_S 6.15 GB Download
Fugaku-LLM-13B-instruct-IQ2_XS.gguf GGUF IQ2_XS 6.10 GB Download
Fugaku-LLM-13B-instruct-IQ2_XXS.gguf GGUF IQ2_XXS 5.99 GB Download
Fugaku-LLM-13B-instruct-IQ3_M.gguf GGUF IQ3_M 7.21 GB Download
Fugaku-LLM-13B-instruct-IQ3_S.gguf GGUF IQ3_S 6.64 GB Download
Fugaku-LLM-13B-instruct-IQ3_XS.gguf GGUF IQ3_XS 6.64 GB Download
Fugaku-LLM-13B-instruct-IQ3_XXS.gguf GGUF IQ3_XXS 6.45 GB Download
Fugaku-LLM-13B-instruct-IQ4_NL.gguf GGUF IQ4_NL 7.17 GB Download
Fugaku-LLM-13B-instruct-IQ4_XS.gguf GGUF IQ4_XS 7.05 GB Download
Fugaku-LLM-13B-instruct-Q2_K.gguf GGUF Q2_K 6.64 GB Download
Fugaku-LLM-13B-instruct-Q3_K_L.gguf GGUF Q3_K_L 8.24 GB Download
Fugaku-LLM-13B-instruct-Q3_K_M.gguf GGUF Q3_K_M 7.70 GB Download
Fugaku-LLM-13B-instruct-Q3_K_S.gguf GGUF Q3_K_S 6.64 GB Download
Fugaku-LLM-13B-instruct-Q4_0.gguf GGUF 7.17 GB Download
Fugaku-LLM-13B-instruct-Q4_K_M.gguf GGUF Q4_K_M 8.91 GB Download
Fugaku-LLM-13B-instruct-Q4_K_S.gguf GGUF Q4_K_S 8.27 GB Download
Fugaku-LLM-13B-instruct-Q5_0.gguf GGUF 8.71 GB Download
Fugaku-LLM-13B-instruct-Q5_K_M.gguf GGUF Q5_K_M 10.43 GB Download
Fugaku-LLM-13B-instruct-Q5_K_S.gguf GGUF Q5_K_S 9.22 GB Download
Fugaku-LLM-13B-instruct-Q6_K.gguf GGUF Q6_K 12.33 GB Download
Fugaku-LLM-13B-instruct-Q8_0.gguf GGUF 13.30 GB Download

Model Details Live

Model Slug
mmnga/fugaku-llm-13b-instruct-gguf
Author
mmnga
Pipeline Task
Library
Created
2024-05-10
Last Modified
2024-05-12
Gated
No
Private
No
HF SHA
de037693c2c69b90ee770507fbf18da93cfe67e8
License
other
Language
en, ja
Base Model
Unknown

Metadata Inspector

Normalized metadata (stored in metadata_json)
{
  "metadata": {},
  "card_data": {
    "license": "other",
    "license_name": "fugaku-llm-tou",
    "license_link": "https://huggingface.co/Fugaku-LLM/Fugaku-LLM-13B-instruct/blob/main/LICENSE",
    "language": [
      "en",
      "ja"
    ],
    "datasets": [
      "TFMC/imatrix-dataset-for-japanese-llm"
    ],
    "tags": [
      "gpt2"
    ],
    "frontmatter": {
      "license": "other",
      "license_name": "fugaku-llm-tou",
      "license_link": "https://huggingface.co/Fugaku-LLM/Fugaku-LLM-13B-instruct/blob/main/LICENSE",
      "language": [
        "en",
        "ja"
      ],
      "datasets": [
        "TFMC/imatrix-dataset-for-japanese-llm"
      ],
      "tags": [
        "gpt2"
      ]
    },
    "hero_image_url": "",
    "summary": "Fugaku-LLMさんが公開しているFugaku-LLM-13B-instructのggufフォーマット変換版です。 imatrixのデータはTFMC/imatrix-dataset-for-japanese-llmを使用して作成しました。",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: other\nlicense_name: fugaku-llm-tou\nlicense_link: https://huggingface.co/Fugaku-LLM/Fugaku-LLM-13B-instruct/blob/main/LICENSE\nlanguage:\n- en\n- ja\ndatasets:\n- TFMC/imatrix-dataset-for-japanese-llm\ntags:\n- gpt2\n---\n\n# Fugaku-LLM-13B-instruct-gguf\n[Fugaku-LLMさんが公開しているFugaku-LLM-13B-instruct](https://huggingface.co/Fugaku-LLM/Fugaku-LLM-13B-instruct)のggufフォーマット変換版です。  \n\nimatrixのデータは[TFMC/imatrix-dataset-for-japanese-llm](https://huggingface.co/datasets/TFMC/imatrix-dataset-for-japanese-llm)を使用して作成しました。  \n\n## License\nご使用の前に必ず利用規約をご確認ください。  \nご使用の際には[利用規約](https://huggingface.co/Fugaku-LLM/Fugaku-LLM-13B-instruct/blob/main/LICENSE)に同意したものとされます。\n\nPlease be sure to check the terms of use before use.\nBy using this service, you agree to the [Terms of Use](https://huggingface.co/Fugaku-LLM/Fugaku-LLM-13B-instruct/blob/main/LICENSE).\n\n## convert\n変換用スクリプトは[こちら](https://gist.github.com/mmnga/e70fbf78db8478e0215b733fe60685da)\n\n## Usage\n\n```\ngit clone https://github.com/ggerganov/llama.cpp.git\ncd llama.cpp\nmake -j\n./main -m 'Fugaku-LLM-13B-instruct-Q4_0.gguf' -n 128 -p '以下は、タスクを説明する指示です。要求を適切に満たす応答を書きなさい。\\n\\n### 指示:\\nスーパーコンピュータ「富岳」の名前の由来を教えてください。\\n\\n### 応答:\\n'\n```",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "gpt2",
    "en",
    "ja",
    "dataset:TFMC/imatrix-dataset-for-japanese-llm",
    "license:other",
    "endpoints_compatible",
    "region:us",
    "imatrix"
  ],
  "likes": 6,
  "downloads": 249,
  "gated": false,
  "private": false,
  "last_modified": "2024-05-12T06:06:51.000Z",
  "created_at": "2024-05-10T16:43:49.000Z",
  "pipeline_tag": "",
  "library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
  "_id": "663e4ec526dee534ebbf3610",
  "id": "mmnga/Fugaku-LLM-13B-instruct-gguf",
  "modelId": "mmnga/Fugaku-LLM-13B-instruct-gguf",
  "sha": "de037693c2c69b90ee770507fbf18da93cfe67e8",
  "createdAt": "2024-05-10T16:43:49.000Z",
  "lastModified": "2024-05-12T06:06:51.000Z",
  "author": "mmnga",
  "downloads": 249,
  "likes": 6,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 26
}