Skip to content

GitLab

"git@developer.sourcefind.cn:modelzoo/resnet50_tensorflow.git" did not exist on "80f1d815f3f29836ef329b465d5e745a1f9cbf22"
Commit 699bc7e8 authored by thomwolf's avatar thomwolf
Browse files

fix gpt-2 unk token test

parent 762ded9b
Show whitespace changes
Inline Side-by-side
Showing with 4 additions and 2 deletions
pytorch_transformers/tokenization_gpt2.py
View file @ 699bc7e8
...@@ -177,7 +177,9 @@ class GPT2Tokenizer(PreTrainedTokenizer): ...@@ -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. """
if token in self.encoder:
return self.encoder.get(token) 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."""
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment