Update app.py

app.py

@@ -221,11 +221,14 @@ with demo:
     # gr.Markdown("If a model can reliably report the underspecification of an inference-time task, an AI systems can replace only those task predictions with\
     #     an appropriate heuristic or information retrieval process.")
     gr.Markdown("*Follow the numbered steps below to test one of the pre-loaded options.* Once you get the hang of it, you can load a new model and/or provide your own input texts.")
-    
-    gr.Markdown("1) Pick a preloaded BERT-like model (note: RoBERTa-large performance is best).")
-    gr.Markdown(f"2) Pick an Occupation type from the Winogender Schemas evaluation set, or select '{PICK_YOUR_OWN_LABEL}' (it need not be about an occupation).")
-    gr.Markdown("3) Click button to load input texts.\n(Read the sentences to determine which two are well-specified for gendered pronoun coreference resolution. The rest are gender-unspecified.)")
-    gr.Markdown("4) Click button to get Task Specification Metric results!")
+    gr.Markdown(f"""1) Pick a preloaded BERT-like model. 
+        Note: RoBERTa-large performance is best.
+    2) Pick an Occupation type from the Winogender Schemas evaluation set.
+        Or select '{PICK_YOUR_OWN_LABEL}' (it need not be about an occupation).
+    3) Click button to load input texts.
+        Read the sentences to determine which two are well-specified for gendered pronoun coreference resolution. The rest are gender-unspecified.
+    4) Click button to get Task Specification Metric results!
+    """