mmnga/tokyotech-llm-swallow-ms-7b-instruct-v0.1-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/tokyotech-llm-swallow-ms-7b-instruct-v0.1-gguf overview
tokyotech-llmさんが公開しているSwallow-MS-7b-instruct-v0.1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
205
Likes
0
Pipeline
—
Library
—
Visibility
Public
Access
Open
Repository Files & Downloads
24 files detected
Direct downloads for all repository files
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| tokyotech-llm-Swallow-MS-7b-instruct-v0.1-IQ1_M.gguf | GGUF | IQ1_M | 1.68 GB | Download |
| tokyotech-llm-Swallow-MS-7b-instruct-v0.1-IQ1_S.gguf | GGUF | IQ1_S | 1.54 GB | Download |
| tokyotech-llm-Swallow-MS-7b-instruct-v0.1-IQ2_M.gguf | GGUF | IQ2_M | 2.38 GB | Download |
| tokyotech-llm-Swallow-MS-7b-instruct-v0.1-IQ2_S.gguf | GGUF | IQ2_S | 2.20 GB | Download |
| tokyotech-llm-Swallow-MS-7b-instruct-v0.1-IQ2_XS.gguf | GGUF | IQ2_XS | 2.09 GB | Download |
| tokyotech-llm-Swallow-MS-7b-instruct-v0.1-IQ2_XXS.gguf | GGUF | IQ2_XXS | 1.90 GB | Download |
| tokyotech-llm-Swallow-MS-7b-instruct-v0.1-IQ3_M.gguf | GGUF | IQ3_M | 3.11 GB | Download |
| tokyotech-llm-Swallow-MS-7b-instruct-v0.1-IQ3_S.gguf | GGUF | IQ3_S | 3.02 GB | Download |
| tokyotech-llm-Swallow-MS-7b-instruct-v0.1-IQ3_XS.gguf | GGUF | IQ3_XS | 2.86 GB | Download |
| tokyotech-llm-Swallow-MS-7b-instruct-v0.1-IQ3_XXS.gguf | GGUF | IQ3_XXS | 2.68 GB | Download |
| tokyotech-llm-Swallow-MS-7b-instruct-v0.1-IQ4_NL.gguf | GGUF | IQ4_NL | 3.90 GB | Download |
| tokyotech-llm-Swallow-MS-7b-instruct-v0.1-IQ4_XS.gguf | GGUF | IQ4_XS | 3.70 GB | Download |
| tokyotech-llm-Swallow-MS-7b-instruct-v0.1-Q2_K.gguf | GGUF | Q2_K | 2.58 GB | Download |
| tokyotech-llm-Swallow-MS-7b-instruct-v0.1-Q3_K_L.gguf | GGUF | Q3_K_L | 3.61 GB | Download |
| tokyotech-llm-Swallow-MS-7b-instruct-v0.1-Q3_K_M.gguf | GGUF | Q3_K_M | 3.33 GB | Download |
| tokyotech-llm-Swallow-MS-7b-instruct-v0.1-Q3_K_S.gguf | GGUF | Q3_K_S | 3.00 GB | Download |
| tokyotech-llm-Swallow-MS-7b-instruct-v0.1-Q4_0.gguf | GGUF | — | 3.88 GB | Download |
| tokyotech-llm-Swallow-MS-7b-instruct-v0.1-Q4_K_M.gguf | GGUF | Q4_K_M | 4.13 GB | Download |
| tokyotech-llm-Swallow-MS-7b-instruct-v0.1-Q4_K_S.gguf | GGUF | Q4_K_S | 3.91 GB | Download |
| tokyotech-llm-Swallow-MS-7b-instruct-v0.1-Q5_0.gguf | GGUF | — | 4.72 GB | Download |
| tokyotech-llm-Swallow-MS-7b-instruct-v0.1-Q5_K_M.gguf | GGUF | Q5_K_M | 4.84 GB | Download |
| tokyotech-llm-Swallow-MS-7b-instruct-v0.1-Q5_K_S.gguf | GGUF | Q5_K_S | 4.72 GB | Download |
| tokyotech-llm-Swallow-MS-7b-instruct-v0.1-Q6_K.gguf | GGUF | Q6_K | 5.60 GB | Download |
| tokyotech-llm-Swallow-MS-7b-instruct-v0.1-Q8_0.gguf | GGUF | — | 7.26 GB | Download |
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"license": "apache-2.0",
"language": [
"en",
"ja"
],
"datasets": [
"TFMC/imatrix-dataset-for-japanese-llm"
],
"tags": [
"mistral"
],
"frontmatter": {
"license": "apache-2.0",
"language": [
"en",
"ja"
],
"datasets": [
"TFMC/imatrix-dataset-for-japanese-llm"
],
"tags": [
"mistral"
]
},
"hero_image_url": "",
"summary": "tokyotech-llmさんが公開しているSwallow-MS-7b-instruct-v0.1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: apache-2.0\nlanguage:\n- en\n- ja\ndatasets:\n- TFMC/imatrix-dataset-for-japanese-llm\ntags:\n- mistral\n---\n\n# tokyotech-llm-Swallow-MS-7b-instruct-v0.1-gguf\n[tokyotech-llmさんが公開しているSwallow-MS-7b-instruct-v0.1](https://huggingface.co/tokyotech-llm/Swallow-MS-7b-instruct-v0.1)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\nmistral \n[mmnga/tokyotech-llm-Swallow-MS-7b-instruct-v0.1-gguf](https://huggingface.co/mmnga/tokyotech-llm-Swallow-MS-7b-instruct-v0.1-gguf) \n[mmnga/tokyotech-llm-Swallow-7b-plus-hf-gguf](https://huggingface.co/mmnga/tokyotech-llm-Swallow-7b-plus-hf-gguf) \n[mmnga/tokyotech-llm-Swallow-MS-7b-v0.1-gguf](https://huggingface.co/mmnga/tokyotech-llm-Swallow-MS-7b-v0.1-gguf) \n[mmnga/tokyotech-llm-Swallow-MX-8x7b-NVE-v0.1-gguf](https://huggingface.co/mmnga/tokyotech-llm-Swallow-MX-8x7b-NVE-v0.1-gguf) \n\nllama2 \n[mmnga/tokyotech-llm-Swallow-7b-instruct-v0.1-gguf](https://huggingface.co/mmnga/tokyotech-llm-Swallow-7b-instruct-v0.1-gguf) \n[mmnga/tokyotech-llm-Swallow-13b-instruct-v0.1-gguf](https://huggingface.co/mmnga/tokyotech-llm-Swallow-13b-instruct-v0.1-gguf) \n[mmnga/tokyotech-llm-Swallow-70b-instruct-v0.1-gguf](https://huggingface.co/mmnga/tokyotech-llm-Swallow-70b-instruct-v0.1-gguf) \n\n\n## Usage\n\n```\ngit clone https://github.com/ggerganov/llama.cpp.git\ncd llama.cpp\nmake -j\n./main -m 'tokyotech-llm-Swallow-MS-7b-instruct-v0.1-Q4_0.gguf' -n 128 -p '[INST] 今晩の夕食の レシピを教えて [/INST] '\n```",
"related_quantizations": []
},
"tags": [
"gguf",
"mistral",
"en",
"ja",
"dataset:TFMC/imatrix-dataset-for-japanese-llm",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
],
"likes": 0,
"downloads": 205,
"gated": false,
"private": false,
"last_modified": "2024-05-03T04:35:34.000Z",
"created_at": "2024-05-02T13:37:22.000Z",
"pipeline_tag": "",
"library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
"_id": "6633971200c6f2c1e25bd369",
"id": "mmnga/tokyotech-llm-Swallow-MS-7b-instruct-v0.1-gguf",
"modelId": "mmnga/tokyotech-llm-Swallow-MS-7b-instruct-v0.1-gguf",
"sha": "cb9ab1c831cfdb8f56371f0ba94806df0fabd518",
"createdAt": "2024-05-02T13:37:22.000Z",
"lastModified": "2024-05-03T04:35:34.000Z",
"author": "mmnga",
"downloads": 205,
"likes": 0,
"gated": false,
"private": false,
"pipeline_tag": "",
"library_name": "",
"siblings_count": 26
}