Update README.md

README.md

@@ -29,13 +29,15 @@ I'm interested in using encoder-based extraction of named legal document section
 - ROBERTa base output shape (batch size, seq length, hidden size)
 - ROBERTa base hidden size = 768
 - ROBERTa base max input seq length = 512
-- ** Using ROBERTA for segmentation involves combining sentences A and B into single input to ROBERTA. See below:
+
+
+### Using ROBERTA for segmentation involves combining sentences A and B into single input to ROBERTA. See below:
 
 [cls] A [sep] B
 
 and the embedding for [cls] can be used in a binary classifier.
 
-Specifically, the architecture used here (implemented via ) is:
+### But, the architecture used here (implemented via ) is:
 
 1. standard ROBERTA model
 2. classification of [CLS] token embedding: