llamafactory调用model

from openai import OpenAI

# autodl 中指令
#  # Set OpenAI's API key and API base to use vLLM's API server.
openai_api_key = "EMPTY"
openai_api_base = "http://localhost:8000/v1"

client = OpenAI(
    api_key=openai_api_key,
    base_url=openai_api_base,
)
chat_response = client.chat.completions.create(
    model="Meta-Llama-3-8B-Instruct",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": 'how are you?'},
    ]
)
print("Chat response:", chat_response.choices)

#环境lora
#微调代码，启动服务器
#CUDA_VISIBLE_DEVICES=0 API_PORT=8000 llamafactory-cli api --model_name_or_path /media/ldx/陈启的机械硬盘/models/Llama3-8B-Chinese-Chat-cq --template llama3 --infer_backend vllm --vllm_enforce_eager