use a shorter description

app.py

@@ -70,9 +70,9 @@ if __name__ == "__main__":
     with demo:
         gr.Markdown(
             """
-            # Grammar-Constrained Decoding with GPT-2 
-            This is a demo of how you can constrain the output of a GPT-2 model using a formal grammar.
-            Here we use a simple JSON grammar to constrain the output of the model to be valid JSON strings.
+            # 👻 Transformers-CFG JSON Demo
+            This is a demo of how you can constrain the output of a GPT-2 model to be a valid JSON string.
+            Here we use a simple JSON grammar to constrain the output of the model.
             The grammar is defined in `json_minimal.ebnf` and is written in the Extended Backus-Naur Form (EBNF).
             Internally, it relies on the library [`transformers-cfg`](https://github.com/epfl-dlab/transformers-CFG).
             For demo purpose, gpt2 is used, but you can use much larger models for better performance.