个人发展] llama2 部署实践（四）- llama 服务接口调用模式 - 3.langchain 调用

from langchain.llms.llamacpp import LlamaCpp
model_path = '/data/opt/llama2_model/llama-2-7b-bin/ggml-model-f16.bin'
llm = LlamaCpp(model_path=model_path,verbose=False)
for s in llm.stream("write me a poem!"):
    print(s,end="",flush=True)