Update app.py

app.py

@@ -13,9 +13,9 @@ tokenizer = AutoTokenizer.from_pretrained(model_id)
 def respond(prompt, history):
     # 構建聊天模板
     messages = [
-        {"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."},
+        {"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant. Think internally, but do not generate thoughts explicitly in the output."},
         {"role": "user", "content": prompt}
-    ]
+    ]    
     text = tokenizer.apply_chat_template(
         messages,
         tokenize=False,
@@ -39,10 +39,9 @@ def respond(prompt, history):
         output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
     ]
     response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+    print("Decoded response:", response)
     # **去除 `<think>` 及其他無用內容**
     response = response.replace("<think>", "").replace("</think>", "").strip()
-    print("Decoded response:", response)
-
     # 返回回應
     return response