update encode_plus - add truncation strategies

This commit is contained in:
thomwolf
2019-10-04 17:38:38 -04:00
parent 92c0f2fb90
commit 6c1d0bc066
12 changed files with 222 additions and 193 deletions

View File

@@ -131,8 +131,8 @@ class BertTokenizationTest(CommonTestCases.CommonTokenizerTester):
text = tokenizer.encode("sequence builders")
text_2 = tokenizer.encode("multi-sequence build")
encoded_sentence = tokenizer.add_special_tokens_single_sequence(text)
encoded_pair = tokenizer.add_special_tokens_sequence_pair(text, text_2)
encoded_sentence = tokenizer.build_inputs_with_special_tokens(text)
encoded_pair = tokenizer.build_inputs_with_special_tokens(text, text_2)
assert encoded_sentence == [101] + text + [102]
assert encoded_pair == [101] + text + [102] + text_2 + [102]