Update app.py

app.py

@@ -26,5 +26,9 @@ question = gr.inputs.Textbox(label="Question")
 answer = gr.outputs.Textbox(label="Predicted answer")
 examples = [["cats.jpg", "How many cats are there?"], ["banana.png", "What is the mustache made of?"]]
 
+title = "Interactive demo: ViLT"
+description = "Gradio Demo for Vision and Language Transformer (ViLT) model fine-tuned on VQAv2 To use it, simply upload your image and type a question and click 'submit', or click one of the examples to load them. Read more at the links below."
+article = "<p style='text-align: center'><a href='https://arxiv.org/abs/2102.03334' target='_blank'>ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision</a> | <a href='https://github.com/dandelin/ViLT' target='_blank'>Github Repo</a></p>"
+
 interface = gr.Interface(fn=answer_question, inputs=[image, question], outputs=answer, examples=examples, enable_queue=True)
 interface.launch(debug=True)