nielsr HF staff commited on
Commit
b65a1a5
1 Parent(s): 9c84a3b

Fix paper link

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -14,7 +14,7 @@ ByT5 was only pre-trained on [mC4](https://www.tensorflow.org/datasets/catalog/c
14
 
15
  ByT5 works especially well on noisy text data,*e.g.*, `google/byt5-base` significantly outperforms [mt5-base](https://huggingface.co/google/mt5-base) on [TweetQA](https://arxiv.org/abs/1907.06292).
16
 
17
- Paper: [ByT5: Towards a token-free future with pre-trained byte-to-byte models](https://arxiv.org/pdf/1910.10683.pdf)
18
 
19
  Authors: *Linting Xue, Aditya Barua, Noah Constant, Rami Al-Rfou, Sharan Narang, Mihir Kale, Adam Roberts, Colin Raffel*
20
 
14
 
15
  ByT5 works especially well on noisy text data,*e.g.*, `google/byt5-base` significantly outperforms [mt5-base](https://huggingface.co/google/mt5-base) on [TweetQA](https://arxiv.org/abs/1907.06292).
16
 
17
+ Paper: [ByT5: Towards a token-free future with pre-trained byte-to-byte models](https://arxiv.org/abs/2105.13626)
18
 
19
  Authors: *Linting Xue, Aditya Barua, Noah Constant, Rami Al-Rfou, Sharan Narang, Mihir Kale, Adam Roberts, Colin Raffel*
20