๐ Model Description
library_name: transformers license: other license_name: nvidia-open-model-license license_link: >- https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/ pipeline_tag: text-generation language: - en - ja tags:
- nvidia
- nvidia/NVIDIA-Nemotron-Nano-9B-v2-Japanese
- TFMC/imatrix-dataset-for-japanese-llm
NVIDIA-Nemotron-Nano-9B-v2-Japanese-gguf
nvidiaใใใๅ ฌ้ใใฆใใNVIDIA-Nemotron-Nano-9B-v2-Japaneseใฎggufใใฉใผใใใๅคๆ็ใงใใimatrixใฎใใผใฟใฏTFMC/imatrix-dataset-for-japanese-llmใไฝฟ็จใใฆไฝๆใใพใใใ
Usage
git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build -DGGML_CUDA=ON
cmake --build build --config Release
build/bin/llama-cli -m 'NVIDIA-Nemotron-Nano-9B-v2-Japanese-gguf' -n 128 -c 128 -p 'ใใชใใฏใใญใฎๆ็ไบบใงใใใฌใทใใๆใใฆ'
๐ GGUF File List
| ๐ Filename | ๐ฆ Size | โก Download |
|---|---|---|
|
NVIDIA-Nemotron-Nano-9B-v2-Japanese-IQ3_M.gguf
LFS
Q3
|
4.85 GB | Download |
|
NVIDIA-Nemotron-Nano-9B-v2-Japanese-IQ4_NL.gguf
LFS
Q4
|
4.94 GB | Download |
|
NVIDIA-Nemotron-Nano-9B-v2-Japanese-IQ4_XS.gguf
LFS
Q4
|
4.91 GB | Download |
|
NVIDIA-Nemotron-Nano-9B-v2-Japanese-Q3_K_L.gguf
LFS
Q3
|
5.11 GB | Download |
|
NVIDIA-Nemotron-Nano-9B-v2-Japanese-Q3_K_M.gguf
LFS
Q3
|
5.01 GB | Download |
|
NVIDIA-Nemotron-Nano-9B-v2-Japanese-Q4_0.gguf
Recommended
LFS
Q4
|
4.94 GB | Download |
|
NVIDIA-Nemotron-Nano-9B-v2-Japanese-Q4_K_M.gguf
LFS
Q4
|
6.08 GB | Download |
|
NVIDIA-Nemotron-Nano-9B-v2-Japanese-Q4_K_S.gguf
LFS
Q4
|
5.79 GB | Download |
|
NVIDIA-Nemotron-Nano-9B-v2-Japanese-Q5_0.gguf
LFS
Q5
|
5.91 GB | Download |
|
NVIDIA-Nemotron-Nano-9B-v2-Japanese-Q5_K_M.gguf
LFS
Q5
|
6.58 GB | Download |
|
NVIDIA-Nemotron-Nano-9B-v2-Japanese-Q5_K_S.gguf
LFS
Q5
|
6.32 GB | Download |
|
NVIDIA-Nemotron-Nano-9B-v2-Japanese-Q6_K.gguf
LFS
Q6
|
8.51 GB | Download |
|
NVIDIA-Nemotron-Nano-9B-v2-Japanese-Q8_0.gguf
LFS
Q8
|
8.81 GB | Download |