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

tokenizer.save_pretrained: only save file if non-empty

Browse Source
This commit is contained in:
Julien Chaumond
2020-01-15 17:36:52 +00:00
parent 6e2c28a14a
commit 9d8fd2d40e
3 changed files with 6 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tests/test_tokenization_auto.py
View File

@@ -33,13 +33,13 @@ class AutoTokenizerTest(unittest.TestCase):
# @slow
def test_tokenizer_from_pretrained(self):
logging.basicConfig(level=logging.INFO)
for model_name in [x for x in BERT_PRETRAINED_CONFIG_ARCHIVE_MAP.keys() if "japanese" not in x]:
for model_name in (x for x in BERT_PRETRAINED_CONFIG_ARCHIVE_MAP.keys() if "japanese" not in x):
tokenizer = AutoTokenizer.from_pretrained(model_name)
self.assertIsNotNone(tokenizer)
self.assertIsInstance(tokenizer, BertTokenizer)
self.assertGreater(len(tokenizer), 0)
for model_name in list(GPT2_PRETRAINED_CONFIG_ARCHIVE_MAP.keys())[:1]:
for model_name in GPT2_PRETRAINED_CONFIG_ARCHIVE_MAP.keys():
tokenizer = AutoTokenizer.from_pretrained(model_name)
self.assertIsNotNone(tokenizer)
self.assertIsInstance(tokenizer, GPT2Tokenizer)