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。
Downloads
249
Likes
6
Pipeline
—
Library
—
Visibility
Public
Access
Open
Repository Files & Downloads
24 files detected
Direct downloads for all repository files
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| 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
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
}