⚠️⚠️[`T5Tokenize`] Fix T5 family tokenizers⚠️⚠️ #24565
don't add space before single letter chars that don't have a merge
e03a7685
fix the fix
76d6ab39
fixup
5a7184bb
add a test
baac7be9
more testing
6e37601e
fixup
b9333287
hack to make sure fast is also fixed
d0cbc495
ArthurZucker
marked this pull request as ready for review 2 years ago
update switch transformers test
50008ed2
revert convert slow
5edf8633
sgugger
approved these changes
on 2023-06-29
Update src/transformers/models/t5/tokenization_t5.py
17bda2cd
add typechecking
059999e1
quality
8d3f2a2f
ArthurZucker
deleted the fix-t5-tokenizer branch 2 years ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub