Update app.py

app.py

@@ -40,6 +40,8 @@ if menu == "Demo":
         In this Space, we will see how to transform an example
         NLU dataset (e.g. utterances and intent / slot annotations) into [SQuAD 2.0 format](https://rajpurkar.github.io/SQuAD-explorer/explore/v2.0/dev/)
         question-answering data that can be used by QANLU.
+        
+        ### Demo
 
         Feel free to query the pre-trained QA-NLU model using the buttons below.