Add example

app.py

@@ -2,6 +2,8 @@ import gradio as gr
 from transformers import ViltProcessor, ViltForVisualQuestionAnswering
 import torch
 
+torch.hub.download_url_to_file('http://images.cocodataset.org/val2017/000000039769.jpg', 'cats.jpg')
+
 processor = ViltProcessor.from_pretrained("dandelin/vilt-b32-finetuned-vqa")
 model = ViltForVisualQuestionAnswering.from_pretrained("dandelin/vilt-b32-finetuned-vqa")
 
@@ -21,4 +23,5 @@ def answer_question(image, text):
 image = gr.inputs.Image(type="pil")
 question = gr.inputs.Textbox(label="Question")
 answer = gr.outputs.Textbox(label="Predicted answer")
-gr.Interface(fn=answer_question, inputs=[image, question], outputs=answer, enable_queue=True).launch(debug=True)
+examples = [["cats.jpg"], ["How many cats are there?"]]
+gr.Interface(fn=answer_question, inputs=[image, question], outputs=answer, examples=examples, enable_queue=True).launch(debug=True)