Update README.md

README.md

@@ -67,11 +67,15 @@ sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)
 
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 
-prompt = "Give me a short introduction to large language model."
+messages = [
+    {"role": "user", "content": "Give me a short introduction to large language model."},
+]
+
+prompts = tokenizer.apply_chat_template(messages, tokenize=False)
 
 llm = LLM(model=model_id, tensor_parallel_size=number_gpus)
 
-outputs = llm.generate(prompt, sampling_params)
+outputs = llm.generate(prompts, sampling_params)
 
 generated_text = outputs[0].outputs[0].text
 print(generated_text)