Update app.py

app.py

@@ -12,7 +12,7 @@ model = Llama.from_pretrained(
 )
 
 def chat(message, history):
-    messages = []
+    messages = [{"role": "system", "content": "/nothink"}]
     for user, assistant in history:
         messages.append({"role": "user", "content": user})
         messages.append({"role": "assistant", "content": assistant})
@@ -22,8 +22,7 @@ def chat(message, history):
     for chunk in model.create_chat_completion(
         messages=messages,
         max_tokens=2048,
-        stream=True,
-        chat_template_kwargs={"enable_thinking": False}
+        stream=True
     ):
         delta = chunk["choices"][0]["delta"].get("content", "")
         output += delta