ByT5

Reported on 2 benchmarks across 2 tasks · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing2 results

Question AnsweringonTweetQA
ROUGE-L· 2021-05-28
75.7
SOTA
ByT5: Towards a token-free future with pre-trained byte-to-byte models arXiv:2105.13626
Extreme SummarizationonGEM-XSum
BLEU score· 2021-05-28
15.3
SOTA
ByT5: Towards a token-free future with pre-trained byte-to-byte models arXiv:2105.13626