Update app.py

app.py

@@ -87,7 +87,7 @@ def remove_duplicates(text):
             seen_lines.add(line)
     return '\n'.join(unique_lines)
 
-@spaces.GPU(queue=False, allow_gpu_memory=True, timeout=0)
+@spaces.GPU(queue=False, allow_gpu_memory=True, timeout=0, duration=0)
 def generate_model_response(model, inputs):
     try:
         response = model(inputs, n_threads=8) # Use multiple threads for faster generation