代码初始化

inference/inference.py

@@ -41,7 +41,7 @@ async def chat_completion(token: str = Body(...), messages: list = Body(...)):
 
         # 使用 chat API 请求生成模型的回答
         completion = client.chat.completions.create(
-            model="meta-llama/Llama-3.1-8B-Instruct",
+            model="meta-llama/Llama-3.3-70B-Instruct",
             messages=messages,
             max_tokens=500
         )