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

Merge branch 'xlnet' into embeddings

Browse Source
This commit is contained in:
Thomas Wolf
2019-07-12 11:10:14 +02:00
committed by GitHub
parent 2918b7d2a0 3821ecbf4a
commit c57e9d946f
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
pytorch_transformers/tokenization_gpt2.py
View File

@@ -177,11 +177,11 @@ 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, self.encoder.get(self.unk_token)) return self.encoder.get(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."""
return self.decoder.get(index, self.unk_token) return self.decoder.get(index)
def _convert_ids_to_string(self, tokens_ids): def _convert_ids_to_string(self, tokens_ids):
"""Converts a sequence of ids in a string.""" """Converts a sequence of ids in a string."""