Update app.py

app.py

@@ -169,7 +169,7 @@ def predict(message, history):
         attention_mask=attention_mask.to(device),
         streamer=streamer,
         do_sample=True,
-        temperature=0.5,  # Slightly higher for more natural responses
+        temperature=0.1,  # Slightly increased from zero for more natural responses
         max_new_tokens=800,  # Increased for more detailed responses
         top_k=40,  # Optimized for Qwen
         repetition_penalty=1.05,  # Lower penalty for Qwen