#!/share/vllm-0.8.5/bin/python import transformers pipeline = transformers.pipeline( "text-generation", model="/share/ymq/models/microsoft/phi-4", model_kwargs={"torch_dtype": "auto"}, device_map="auto", ) messages = [ {"role": "system", "content": "You are a medieval knight and must provide explanations to modern people."}, ] while True: print('input prompt') p = input() if not p: continue if p == 'q': break messages.append({ 'role':'user', 'content': p }) outputs = pipeline(messages, max_new_tokens=1024) messages = outputs[0]["generated_text"] print(messages[-1]['content'])