Skip to content

int4推理

Li Yudong (李煜东) edited this page May 17, 2023 · 4 revisions
git lfs install
git clone https://github.com/ggerganov/llama.cpp.git
git clone https://huggingface.co/P01son/Linly-ChatFlow-7B-int4

cd llama.cpp
make
./main -m ../Linly-ChatFlow-7B-int4/chatflow-ggml-q4_0.bin -p "北京有什么好玩的地方?\n" -n 256