๐ Model Description
license: llama3.1 language:
- en
- ja
- TFMC/imatrix-dataset-for-japanese-llm
- tokyotech-llm/Llama-3.1-Swallow-70B-Instruct-v0.3
tokyotech-llm-Llama-3.1-Swallow-70B-Instruct-v0.3-gguf
tokyotech-llmใใใๅ ฌ้ใใฆใใLlama-3.1-Swallow-70B-Instruct-v0.3ใฎggufใใฉใผใใใๅคๆ็ใงใใimatrixใฎใใผใฟใฏTFMC/imatrix-dataset-for-japanese-llmใไฝฟ็จใใฆไฝๆใใพใใใ
Usage
git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build -DGGML_CUDA=ON
cmake --build build --config Release
build/bin/llama-cli -m 'tokyotech-llm-Llama-3.1-Swallow-70B-Instruct-v0.3-Q4_0.gguf' -n 128 -c 128 -p 'ใใชใใฏใใญใฎๆ็ไบบใงใใใฌใทใใๆใใฆ' -cnv๐ GGUF File List
| ๐ Filename | ๐ฆ Size | โก Download |
|---|---|---|
|
tokyotech-llm-Llama-3.1-Swallow-70B-Instruct-v0.3-IQ1_M.gguf
LFS
|
15.6 GB | Download |
|
tokyotech-llm-Llama-3.1-Swallow-70B-Instruct-v0.3-IQ1_S.gguf
LFS
|
14.29 GB | Download |
|
tokyotech-llm-Llama-3.1-Swallow-70B-Instruct-v0.3-IQ2_M.gguf
LFS
Q2
|
22.46 GB | Download |
|
tokyotech-llm-Llama-3.1-Swallow-70B-Instruct-v0.3-IQ2_S.gguf
LFS
Q2
|
20.71 GB | Download |
|
tokyotech-llm-Llama-3.1-Swallow-70B-Instruct-v0.3-IQ2_XS.gguf
LFS
Q2
|
19.69 GB | Download |
|
tokyotech-llm-Llama-3.1-Swallow-70B-Instruct-v0.3-IQ2_XXS.gguf
LFS
Q2
|
17.79 GB | Download |
|
tokyotech-llm-Llama-3.1-Swallow-70B-Instruct-v0.3-IQ3_M.gguf
LFS
Q3
|
29.74 GB | Download |
|
tokyotech-llm-Llama-3.1-Swallow-70B-Instruct-v0.3-IQ3_S.gguf
LFS
Q3
|
28.79 GB | Download |
|
tokyotech-llm-Llama-3.1-Swallow-70B-Instruct-v0.3-IQ3_XS.gguf
LFS
Q3
|
27.29 GB | Download |
|
tokyotech-llm-Llama-3.1-Swallow-70B-Instruct-v0.3-IQ3_XXS.gguf
LFS
Q3
|
25.58 GB | Download |
|
tokyotech-llm-Llama-3.1-Swallow-70B-Instruct-v0.3-IQ4_NL.gguf
LFS
Q4
|
37.3 GB | Download |
|
tokyotech-llm-Llama-3.1-Swallow-70B-Instruct-v0.3-IQ4_XS.gguf
LFS
Q4
|
35.3 GB | Download |
|
tokyotech-llm-Llama-3.1-Swallow-70B-Instruct-v0.3-Q2_K.gguf
LFS
Q2
|
24.56 GB | Download |
|
tokyotech-llm-Llama-3.1-Swallow-70B-Instruct-v0.3-Q3_K_L.gguf
LFS
Q3
|
34.59 GB | Download |
|
tokyotech-llm-Llama-3.1-Swallow-70B-Instruct-v0.3-Q3_K_M.gguf
LFS
Q3
|
31.91 GB | Download |
|
tokyotech-llm-Llama-3.1-Swallow-70B-Instruct-v0.3-Q3_K_S.gguf
LFS
Q3
|
28.79 GB | Download |
|
tokyotech-llm-Llama-3.1-Swallow-70B-Instruct-v0.3-Q4_0.gguf
Recommended
LFS
Q4
|
37.22 GB | Download |
|
tokyotech-llm-Llama-3.1-Swallow-70B-Instruct-v0.3-Q4_K_M.gguf
LFS
Q4
|
39.6 GB | Download |
|
tokyotech-llm-Llama-3.1-Swallow-70B-Instruct-v0.3-Q4_K_S.gguf
LFS
Q4
|
37.58 GB | Download |
|
tokyotech-llm-Llama-3.1-Swallow-70B-Instruct-v0.3-Q5_0.gguf
LFS
Q5
|
45.32 GB | Download |
|
tokyotech-llm-Llama-3.1-Swallow-70B-Instruct-v0.3-Q5_K_S.gguf
LFS
Q5
|
45.32 GB | Download |