Update README.md

README.md

@@ -63,7 +63,12 @@ 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": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
+    {"role": "user", "content": "Who are you?"},
+]
+
+prompts = tokenizer.apply_chat_template(messages, tokenize=False)
 
 llm = LLM(model=model_id, tensor_parallel_size=number_gpus)