apologies for the tiny PRs, just sending those as I find them.
This commit is contained in:
Stas Bekman
2020-09-07 22:22:20 -07:00
committed by GitHub
parent 60fc03290b
commit c18f5916a0

View File

@@ -1609,7 +1609,7 @@ class PreTrainedTokenizerBase(SpecialTokensMixin):
)
tokenizer.add_tokens(token, special_tokens=bool(token in special_tokens))
# Check all our special tokens are registrered as "no split" token (we don't cut them) and are in the vocab
# Check all our special tokens are registered as "no split" token (we don't cut them) and are in the vocab
added_tokens = tokenizer.sanitize_special_tokens()
if added_tokens:
logger.warning(