Update README.md

README.md

@@ -17,6 +17,7 @@ We use token-level cross-entropy loss calculated using the gold paraphrase sente
 
  # How to use
  Using `top_p=0.9` and `temperature` between `0` and `1` usually results in good generated paraphrases. Higher temperatures make paraphrases more diverse and more different from the input, but might slightly change the meaning of the original sentence.
+ Note that this is a sentence-level paraphraser. If you want to paraphrase longer inputs (like paragraphs) with this model, make sure to first break the input into individual sentences.
  
  
 # Citation