Update app.py

app.py

@@ -91,7 +91,7 @@ def remove_duplicates(text):
 @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
+        response = model(inputs)
         return remove_duplicates(response['choices'][0]['text'])
     except Exception as e:
         print(f"Error generating model response: {e}")
@@ -135,4 +135,4 @@ iface = gr.Interface(
 
 if __name__ == "__main__":
     port = int(os.environ.get("PORT", 7860))
-    iface.launch(server_port=port)
+    iface.launch(server_port=port)