Fix detokenizer space match for quote (#1072)

* fix + test

* remove transformer flax/torch warning

* format
This commit is contained in:
Awni Hannun
2024-10-27 15:06:07 -07:00
committed by GitHub
parent ab4bf05c6e
commit 8fe9539af7
3 changed files with 9 additions and 1 deletions

View File

@@ -169,7 +169,7 @@ class BPEStreamingDetokenizer(StreamingDetokenizer):
"""
_byte_decoder = None
_space_matches = (".", "?", "!", ",", "'", "n't", "'m", "'s", "'ve", "'re")
_space_matches = (".", "?", "!", ",", "n't", "'m", "'s", "'ve", "'re")
def __init__(self, tokenizer):