SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

fix gpt-2 unk token test

Browse Source
This commit is contained in:
thomwolf
2019-07-12 11:46:57 +02:00
parent 762ded9b1c
commit 699bc7e86e
2 changed files with 4 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
pytorch_transformers/tokenization_gpt2.py
View File

@@ -177,7 +177,9 @@ class GPT2Tokenizer(PreTrainedTokenizer):
def _convert_token_to_id(self, token): def _convert_token_to_id(self, token):
""" Converts a token (str/unicode) in an id using the vocab. """ """ Converts a token (str/unicode) in an id using the vocab. """
return self.encoder.get(token) if token in self.encoder:
return self.encoder.get(token)
return self.encoder.get(self.unk_token)
def _convert_id_to_token(self, index): def _convert_id_to_token(self, index):
"""Converts an index (integer) in a token (string/unicode) using the vocab.""" """Converts an index (integer) in a token (string/unicode) using the vocab."""