woshikid/llama3-8b repository overview

docker run -it woshikid/llama3-8b ./chat.sh [你好] [4]
# OpenAI API compatible
docker run -d -p 8080:8080 woshikid/llama3-8b ./llama-server -m /ggml-model-q4_k.gguf --temp 0.2 [-t 4] --host 0.0.0.0 [--port 8080]