GraySoft
Projects Models About FAQ Contact Download guIDE →

mmnga/haqishen-llama-3-8b-japanese-instruct-gguf IQ2_XXS 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/haqishen-llama-3-8b-japanese-instruct-gguf overview

haqishen-Llama-3-8B-Japanese-Instruct-gguf haqishenさんが公開しているLlama-3-8B-Japanese-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。

ggufllama3enjadataset:TFMC/imatrix-dataset-for-japanese-llmlicense:llama3endpoints_compatibleregion:usconversational
mmnga/haqishen-llama-3-8b-japanese-instruct-gguf visual
Downloads
255
Likes
4
Pipeline
Library
Visibility
Public
Access
Open

Repository Files & Downloads

24 files detected
Direct downloads for all repository files
FileTypeQuantizationSizeLink
haqishen-Llama-3-8B-Japanese-Instruct-IQ1_M.gguf GGUF IQ1_M 2.01 GB Download
haqishen-Llama-3-8B-Japanese-Instruct-IQ1_S.gguf GGUF IQ1_S 1.88 GB Download
haqishen-Llama-3-8B-Japanese-Instruct-IQ2_M.gguf GGUF IQ2_M 2.75 GB Download
haqishen-Llama-3-8B-Japanese-Instruct-IQ2_S.gguf GGUF IQ2_S 2.57 GB Download
haqishen-Llama-3-8B-Japanese-Instruct-IQ2_XS.gguf GGUF IQ2_XS 2.43 GB Download
haqishen-Llama-3-8B-Japanese-Instruct-IQ2_XXS.gguf GGUF IQ2_XXS 2.23 GB Download
haqishen-Llama-3-8B-Japanese-Instruct-IQ3_M.gguf GGUF IQ3_M 3.53 GB Download
haqishen-Llama-3-8B-Japanese-Instruct-IQ3_S.gguf GGUF IQ3_S 3.43 GB Download
haqishen-Llama-3-8B-Japanese-Instruct-IQ3_XS.gguf GGUF IQ3_XS 3.28 GB Download
haqishen-Llama-3-8B-Japanese-Instruct-IQ3_XXS.gguf GGUF IQ3_XXS 3.05 GB Download
haqishen-Llama-3-8B-Japanese-Instruct-IQ4_NL.gguf GGUF IQ4_NL 4.36 GB Download
haqishen-Llama-3-8B-Japanese-Instruct-IQ4_XS.gguf GGUF IQ4_XS 4.14 GB Download
haqishen-Llama-3-8B-Japanese-Instruct-Q2_K.gguf GGUF Q2_K 2.96 GB Download
haqishen-Llama-3-8B-Japanese-Instruct-Q3_K_L.gguf GGUF Q3_K_L 4.03 GB Download
haqishen-Llama-3-8B-Japanese-Instruct-Q3_K_M.gguf GGUF Q3_K_M 3.74 GB Download
haqishen-Llama-3-8B-Japanese-Instruct-Q3_K_S.gguf GGUF Q3_K_S 3.41 GB Download
haqishen-Llama-3-8B-Japanese-Instruct-Q4_0.gguf GGUF 4.34 GB Download
haqishen-Llama-3-8B-Japanese-Instruct-Q4_K_M.gguf GGUF Q4_K_M 4.58 GB Download
haqishen-Llama-3-8B-Japanese-Instruct-Q4_K_S.gguf GGUF Q4_K_S 4.37 GB Download
haqishen-Llama-3-8B-Japanese-Instruct-Q5_0.gguf GGUF 5.22 GB Download
haqishen-Llama-3-8B-Japanese-Instruct-Q5_K_M.gguf GGUF Q5_K_M 5.34 GB Download
haqishen-Llama-3-8B-Japanese-Instruct-Q5_K_S.gguf GGUF Q5_K_S 5.22 GB Download
haqishen-Llama-3-8B-Japanese-Instruct-Q6_K.gguf GGUF Q6_K 6.14 GB Download
haqishen-Llama-3-8B-Japanese-Instruct-Q8_0.gguf GGUF 7.95 GB Download

Model Details Live

Model Slug
mmnga/haqishen-llama-3-8b-japanese-instruct-gguf
Author
mmnga
Pipeline Task
Library
Created
2024-04-23
Last Modified
2024-04-23
Gated
No
Private
No
HF SHA
923a0c1a543f96d8c9dae0efecafdca19965ea83
License
llama3
Language
en, ja
Base Model
Unknown

Metadata Inspector

Normalized metadata (stored in metadata_json)
{
  "metadata": {},
  "card_data": {
    "license": "llama3",
    "language": [
      "en",
      "ja"
    ],
    "tags": [
      "llama3"
    ],
    "datasets": [
      "TFMC/imatrix-dataset-for-japanese-llm"
    ],
    "frontmatter": {
      "license": "llama3",
      "language": [
        "en",
        "ja"
      ],
      "tags": [
        "llama3"
      ],
      "datasets": [
        "TFMC/imatrix-dataset-for-japanese-llm"
      ]
    },
    "hero_image_url": "",
    "summary": "# haqishen-Llama-3-8B-Japanese-Instruct-gguf haqishenさんが公開しているLlama-3-8B-Japanese-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: llama3\nlanguage:\n- en\n- ja\ntags:\n- llama3\ndatasets:\n- TFMC/imatrix-dataset-for-japanese-llm\n---\n# haqishen-Llama-3-8B-Japanese-Instruct-gguf \n[haqishenさんが公開しているLlama-3-8B-Japanese-Instruct](https://huggingface.co/haqishen/Llama-3-8B-Japanese-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## 他のモデル\n[mmnga/haqishen-Llama-3-8B-Japanese-Instruct-gguf](https://huggingface.co/mmnga/haqishen-Llama-3-8B-Japanese-Instruct-gguf)  \n\n## Usage\n\n```\ngit clone https://github.com/ggerganov/llama.cpp.git\ncd llama.cpp\nmake -j\n./main -m 'haqishen-Llama-3-8B-Japanese-Instruct-Q4_0.gguf' -p \"<|begin_of_text|><|start_header_id|>user <|end_header_id|>\\n\\nこんにちわ<|eot_id|><|start_header_id|>assistant <|end_header_id|>\\n\\n\" -n 128\n```",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "llama3",
    "en",
    "ja",
    "dataset:TFMC/imatrix-dataset-for-japanese-llm",
    "license:llama3",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 4,
  "downloads": 255,
  "gated": false,
  "private": false,
  "last_modified": "2024-04-23T14:54:23.000Z",
  "created_at": "2024-04-23T13:55:17.000Z",
  "pipeline_tag": "",
  "library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
  "_id": "6627bdc53cf58c2c8d68ed67",
  "id": "mmnga/haqishen-Llama-3-8B-Japanese-Instruct-gguf",
  "modelId": "mmnga/haqishen-Llama-3-8B-Japanese-Instruct-gguf",
  "sha": "923a0c1a543f96d8c9dae0efecafdca19965ea83",
  "createdAt": "2024-04-23T13:55:17.000Z",
  "lastModified": "2024-04-23T14:54:23.000Z",
  "author": "mmnga",
  "downloads": 255,
  "likes": 4,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 26
}