This commit is contained in:
thomwolf 2019-08-20 11:05:51 +02:00
parent e239a4a20f
commit 901dde0e45

View File

@ -187,6 +187,8 @@ class BertTokenizer(PreTrainedTokenizer):
index = 0
if os.path.isdir(vocab_path):
vocab_file = os.path.join(vocab_path, VOCAB_FILES_NAMES['vocab_file'])
else:
vocab_file = vocab_path
with open(vocab_file, "w", encoding="utf-8") as writer:
for token, token_index in sorted(self.vocab.items(), key=lambda kv: kv[1]):
if index != token_index: