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

Fixed error with encoding

Browse Source
This commit is contained in:
LysandreJik
2019-08-13 12:00:24 -04:00
parent 634a3172d8
commit 3d87991f60
2 changed files with 8 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
pytorch_transformers/tests/tokenization_roberta_test.py
View File

@@ -81,11 +81,14 @@ class RobertaTokenizationTest(CommonTestCases.CommonTokenizerTester):
text = tokenizer.encode("sequence builders")
text_2 = tokenizer.encode("multi-sequence build")
encoded_text_from_decode = tokenizer.encode("sequence builders", add_special_tokens=True)
encoded_pair_from_decode = tokenizer.encode("sequence builders", "multi-sequence build", add_special_tokens=True)
encoded_sentence = tokenizer.add_special_tokens_single_sentence(text)
encoded_pair = tokenizer.add_special_tokens_sentences_pair(text, text_2)
assert encoded_sentence == [0] + text + [2]
assert encoded_pair == [0] + text + [2, 2] + text_2 + [2]
assert encoded_sentence == encoded_text_from_decode
assert encoded_pair == encoded_pair_from_decode
if __name__ == '__main__':