s-jse commited on
Commit
ad5e361
1 Parent(s): 9115f57

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -0
README.md CHANGED
@@ -17,6 +17,7 @@ We use token-level cross-entropy loss calculated using the gold paraphrase sente
17
 
18
  # How to use
19
  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.
 
20
 
21
 
22
  # Citation
 
17
 
18
  # How to use
19
  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.
20
+ 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.
21
 
22
 
23
  # Citation