Update app.py

app.py

@@ -78,7 +78,7 @@ def generate_response(message, history):
     # Generate response
     outputs = model.generate(
         input_ids, 
-        max_new_tokens=2048,  # Reduced from 1024 to improve speed
+        max_new_tokens=4096,
         temperature=0.7,
         do_sample=True,
     )