Update app.py

app.py

@@ -42,24 +42,18 @@ def respond(message, history, system_message, max_tokens, temperature, top_p):
 
         output = ""
         for chunk in stream:
-            print("[DEBUG] chunk:", chunk)
+            #print("[DEBUG] chunk:", chunk)
             delta = chunk.choices[0].delta
             if delta:
                 # 安全取得 content
                 if delta.content:
                     output += delta.content
-                # 安全取得 reasoning_content，如果不存在就跳過
+                # 安全取得 reasoning_content，如果不存在就跳過 印出思維練
                 #reasoning = getattr(delta, "reasoning_content", None)
                 #if reasoning:
                 #    output += reasoning
                 # 每個 chunk 都 yield 最新內容
                 yield {"role": "assistant", "content": output}
-            
-            #if chunk.choices:
-            #    delta = chunk.choices[0].delta
-            #    if delta and delta.reasoning_content:
-            #        output += delta.reasoning_content
-            #        yield {"role": "assistant", "content": output}
 
     except Exception as e:
         print(f"[Error] {e}")
@@ -71,7 +65,7 @@ demo = gr.ChatInterface(
     type="messages",  # 🔑 使用 OpenAI 風格訊息格式
     additional_inputs=[
         gr.Textbox(value="You are a friendly assistant.", label="System message"),
-        gr.Slider(minimum=1, maximum=4096, value=1024, step=1, label="Max new tokens"),
+        gr.Slider(minimum=1, maximum=4096, value=4096, step=1, label="Max new tokens"),
         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
         gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
     ],