Update README.md

README.md

@@ -46,6 +46,10 @@ print(tokenized_text["attention_mask"].size())  # torch.Size([3, 16, 32])
 
 out = model(**tokenized_text)
 print(out.size())   # torch.Size([3, 512])
+
+# to get the Transformer attentions:
+out, attentions = model(**tokenized_text, output_attentions=True)
+print(attentions[0].size())     # torch.Size([48, 12, 32, 32])
 ```
 
 ## Citing & Authors