woshikid/llama2-7b repository overview

docker run -it woshikid/llama2-7b ./chat.sh /chinese-alpaca-2-7b/ggml-model-q4_k.gguf [你好] [4]
docker run -d -p 8080:8080 woshikid/llama2-7b ./server -m /chinese-alpaca-2-7b/ggml-model-q4_k.gguf -c 4096 [-t 8] --host 0.0.0.0 [--port 8080]

docker run -d -p 8081:8081 woshikid/llama2-7b:openai ./openai.sh [4]