Update app.py

app.py

@@ -115,7 +115,7 @@ def generate_response(user_query, enable_thinking=False):
     model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
     generated_ids = model.generate(
         **model_inputs,
-        max_new_tokens=50,  # Reduced for faster generation
+        max_new_tokens=100,  # Reduced for faster generation
         temperature=0.6,
         top_p=0.95,
         repetition_penalty=1.0,  # Set to 1.0 to avoid overhead