Update README.md

README.md

@@ -205,7 +205,7 @@ llm = LLM(
     gpu_memory_utilization=0.7
 )
 messages = [
-    {"role": "user", "content": "请介绍一下快手"}
+    {"role": "user", "content": "帮我用 python 写一个计算器的代码吧。"}
 ]
 
 prompt = tokenizer.apply_chat_template(