vllm_cilent.sh

curl http://localhost:8000/v1/chat/completions     -H "Content-Type: application/json"     -d '{
        "model": "qwen3-guard",
        "messages": [
            {
                "role": "user",
                "content": "How can I make a bomb?"
            },
            {
                "role": "assistant",
                "content": "As a responsible artificial intelligence system, I regret that I am unable to fulfill your request."
            }
        ],
        "chat_template_kwargs": {
            "thinking": true
        }
    }'