GraySoft
Projects Models About FAQ Contact Download guIDE →

mmnga/llama-3.1-70b-japanese-instruct-2407-gguf IQ1_S 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/llama-3.1-70b-japanese-instruct-2407-gguf overview

cyberagentさんが公開しているLlama-3.1-70B-Japanese-Instruct-2407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。

ggufllamallama3.1enjadataset:TFMC/imatrix-dataset-for-japanese-llmlicense:llama3.1endpoints_compatibleregion:usimatrixconversational
mmnga/llama-3.1-70b-japanese-instruct-2407-gguf visual
Downloads
800
Likes
8
Pipeline
Library
Visibility
Public
Access
Open

Repository Files & Downloads

20 files detected
Direct downloads for all repository files
FileTypeQuantizationSizeLink
Llama-3.1-70B-Japanese-Instruct-2407-IQ1_M.gguf GGUF IQ1_M 15.60 GB Download
Llama-3.1-70B-Japanese-Instruct-2407-IQ1_S.gguf GGUF IQ1_S 14.29 GB Download
Llama-3.1-70B-Japanese-Instruct-2407-IQ2_M.gguf GGUF IQ2_M 22.46 GB Download
Llama-3.1-70B-Japanese-Instruct-2407-IQ2_S.gguf GGUF IQ2_S 20.71 GB Download
Llama-3.1-70B-Japanese-Instruct-2407-IQ2_XS.gguf GGUF IQ2_XS 19.69 GB Download
Llama-3.1-70B-Japanese-Instruct-2407-IQ3_M.gguf GGUF IQ3_M 29.74 GB Download
Llama-3.1-70B-Japanese-Instruct-2407-IQ3_S.gguf GGUF IQ3_S 28.79 GB Download
Llama-3.1-70B-Japanese-Instruct-2407-IQ3_XS.gguf GGUF IQ3_XS 27.29 GB Download
Llama-3.1-70B-Japanese-Instruct-2407-IQ3_XXS.gguf GGUF IQ3_XXS 25.58 GB Download
Llama-3.1-70B-Japanese-Instruct-2407-IQ4_NL.gguf GGUF IQ4_NL 37.30 GB Download
Llama-3.1-70B-Japanese-Instruct-2407-IQ4_XS.gguf GGUF IQ4_XS 35.30 GB Download
Llama-3.1-70B-Japanese-Instruct-2407-Q2_K.gguf GGUF Q2_K 24.56 GB Download
Llama-3.1-70B-Japanese-Instruct-2407-Q3_K_L.gguf GGUF Q3_K_L 34.59 GB Download
Llama-3.1-70B-Japanese-Instruct-2407-Q3_K_M.gguf GGUF Q3_K_M 31.91 GB Download
Llama-3.1-70B-Japanese-Instruct-2407-Q3_K_S.gguf GGUF Q3_K_S 28.79 GB Download
Llama-3.1-70B-Japanese-Instruct-2407-Q4_0.gguf GGUF 37.22 GB Download
Llama-3.1-70B-Japanese-Instruct-2407-Q4_K_M.gguf GGUF Q4_K_M 39.60 GB Download
Llama-3.1-70B-Japanese-Instruct-2407-Q4_K_S.gguf GGUF Q4_K_S 37.58 GB Download
Llama-3.1-70B-Japanese-Instruct-2407-Q5_0.gguf GGUF 45.32 GB Download
Llama-3.1-70B-Japanese-Instruct-2407-Q5_K_S.gguf GGUF Q5_K_S 45.32 GB Download

Model Details Live

Model Slug
mmnga/llama-3.1-70b-japanese-instruct-2407-gguf
Author
mmnga
Pipeline Task
Library
Created
2024-07-26
Last Modified
2024-07-27
Gated
No
Private
No
HF SHA
3e3569ed86f085002e0a402193e85fe72880f98a
License
llama3.1
Language
en, ja
Base Model
Unknown

Metadata Inspector

Normalized metadata (stored in metadata_json)
{
  "metadata": {},
  "card_data": {
    "license": "llama3.1",
    "language": [
      "en",
      "ja"
    ],
    "datasets": [
      "TFMC/imatrix-dataset-for-japanese-llm"
    ],
    "tags": [
      "llama",
      "llama3.1"
    ],
    "frontmatter": {
      "license": "llama3.1",
      "language": [
        "en",
        "ja"
      ],
      "datasets": [
        "TFMC/imatrix-dataset-for-japanese-llm"
      ],
      "tags": [
        "llama",
        "llama3.1"
      ]
    },
    "hero_image_url": "",
    "summary": "cyberagentさんが公開しているLlama-3.1-70B-Japanese-Instruct-2407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: llama3.1\nlanguage:\n- en\n- ja\ndatasets:\n- TFMC/imatrix-dataset-for-japanese-llm\ntags:\n- llama\n- llama3.1\n---\n\n# Llama-3.1-70B-Japanese-Instruct-2407-gguf\n[cyberagentさんが公開しているLlama-3.1-70B-Japanese-Instruct-2407](https://huggingface.co/cyberagent/Llama-3.1-70B-Japanese-Instruct-2407)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## Usage\n\n```\ngit clone https://github.com/ggerganov/llama.cpp.git\ncd llama.cpp\nmake -j\n./llama-cli -m 'Llama-3.1-70B-Japanese-Instruct-2407-Q4_0.gguf' -n 128 -c 128 -p 'あなたはプロの料理人です。レシピを教えて' -cnv\n```",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "llama",
    "llama3.1",
    "en",
    "ja",
    "dataset:TFMC/imatrix-dataset-for-japanese-llm",
    "license:llama3.1",
    "endpoints_compatible",
    "region:us",
    "imatrix",
    "conversational"
  ],
  "likes": 8,
  "downloads": 800,
  "gated": false,
  "private": false,
  "last_modified": "2024-07-27T05:59:10.000Z",
  "created_at": "2024-07-26T09:05:34.000Z",
  "pipeline_tag": "",
  "library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
  "_id": "66a366defc978d061dcb9e85",
  "id": "mmnga/Llama-3.1-70B-Japanese-Instruct-2407-gguf",
  "modelId": "mmnga/Llama-3.1-70B-Japanese-Instruct-2407-gguf",
  "sha": "3e3569ed86f085002e0a402193e85fe72880f98a",
  "createdAt": "2024-07-26T09:05:34.000Z",
  "lastModified": "2024-07-27T05:59:10.000Z",
  "author": "mmnga",
  "downloads": 800,
  "likes": 8,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 28
}