riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-07-31 02:02:21 +06:00
Code Issues Actions 23 Packages Projects Releases Wiki Activity

updating GPT tokenization

Browse Source
This commit is contained in:
thomwolf 2019-04-16 17:44:06 +02:00
parent 18a8a15f78
commit bdaba1897c
1 changed files with 2 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
pytorch_pretrained_bert/tokenization_openai.py
View File

@ -273,9 +273,8 @@ class OpenAIGPTTokenizer(object):
if clean_up_tokenization_spaces:
out_string = out_string.replace('<unk>', '')
out_string = out_string.replace(' .', '.').replace(' ?', '?').replace(' !', '!').replace(' ,', ',').replace(' ,', ','
).replace(" n't", "n't").replace(" 'm", "'m").replace(" 're", "'re").replace(" do not", " don't"
).replace(" 's", "'s").replace(" t ", "'t ").replace(" s ", "'s ").replace(" m ", "'m "
).replace(" 've", "'ve")
).replace(" ' ", "'").replace(" n't", "n't").replace(" 'm", "'m").replace(" do not", " don't"
).replace(" 's", "'s").replace(" 've", "'ve").replace(" 're", "'re")
return out_string
def save_vocabulary(self, vocab_path):