Update app.py

app.py

@@ -44,7 +44,7 @@ def generate_response(message, max_tokens, temperature, top_p):
     global stop_signal
     stop_signal = False
 
-    prompt = f"Question: {message}\nThinking:"
+    prompt = f"Question: {message}\nThinking: \nAnswer:"
     inputs = tokenizer(prompt, return_tensors="pt").to(device)
 
     streamer = TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)