Got it, I think

app.py

@@ -80,9 +80,9 @@ def process_image(image):
 
 
 title = "Extracting Receipts: LayoutLMv3"
-description = """<p Demo for Microsoft's LayoutLMv3, a Transformer for state-of-the-art document image understanding tasks. </p>  <p This particular model is fine-tuned from 
+description = """<p> Demo for Microsoft's LayoutLMv3, a Transformer for state-of-the-art document image understanding tasks. </p>  <p> This particular model is fine-tuned from 
 <a href="https://github.com/clovaai/cord">CORD</a> on the Consolidated Receipt Dataset, a dataset of receipts. If you search the 🤗 Hugging Face hub you will see other related models fine-tuned for other documents. This model is trained using fine-tuning to look for entities around menu items, subtotal, and total prices. To perform your own fine-tuning, take a look at the 
-<a href="https://github.com/NielsRogge/Transformers-Tutorials/tree/master/LayoutLMv3">notebook by Niels</a>. </p>  <p To try it out, simply upload an image or use the example image below and click 'Submit'. Results will show up in a few seconds. To see the output bigger, right-click on it, select 'Open image in new tab', and use your browser's zoom feature. </p>"""
+<a href="https://github.com/NielsRogge/Transformers-Tutorials/tree/master/LayoutLMv3">notebook by Niels</a>. </p>  <p> To try it out, simply upload an image or use the example image below and click 'Submit'. Results will show up in a few seconds. To see the output bigger, right-click on it, select 'Open image in new tab', and use your browser's zoom feature. </p>"""
 
 article = "<p style='text-align: center'><a href='https://arxiv.org/abs/2204.08387' target='_blank'>LayoutLMv3: Multi-modal Pre-training for Visually-Rich Document Understanding</a> | <a href='https://github.com/microsoft/unilm' target='_blank'>Github Repo</a></p>"
 examples =[['test0.jpeg'],['test1.jpeg'],['test2.jpeg']]