Spaces:
Running
on
CPU Upgrade
Running
on
CPU Upgrade
File size: 3,006 Bytes
63858e7 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 |
# coding=utf-8
# Copyright 2018 The Google AI Language Team Authors.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import logging
import unittest
from transformers import (
BERT_PRETRAINED_CONFIG_ARCHIVE_MAP,
GPT2_PRETRAINED_CONFIG_ARCHIVE_MAP,
AutoTokenizer,
BertTokenizer,
GPT2Tokenizer,
RobertaTokenizer,
)
from .utils import DUMMY_UNKWOWN_IDENTIFIER, SMALL_MODEL_IDENTIFIER, slow # noqa: F401
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):
tokenizer = AutoTokenizer.from_pretrained(model_name)
self.assertIsNotNone(tokenizer)
self.assertIsInstance(tokenizer, BertTokenizer)
self.assertGreater(len(tokenizer), 0)
for model_name in GPT2_PRETRAINED_CONFIG_ARCHIVE_MAP.keys():
tokenizer = AutoTokenizer.from_pretrained(model_name)
self.assertIsNotNone(tokenizer)
self.assertIsInstance(tokenizer, GPT2Tokenizer)
self.assertGreater(len(tokenizer), 0)
def test_tokenizer_from_pretrained_identifier(self):
logging.basicConfig(level=logging.INFO)
tokenizer = AutoTokenizer.from_pretrained(SMALL_MODEL_IDENTIFIER)
self.assertIsInstance(tokenizer, BertTokenizer)
self.assertEqual(len(tokenizer), 12)
def test_tokenizer_from_model_type(self):
logging.basicConfig(level=logging.INFO)
tokenizer = AutoTokenizer.from_pretrained(DUMMY_UNKWOWN_IDENTIFIER)
self.assertIsInstance(tokenizer, RobertaTokenizer)
self.assertEqual(len(tokenizer), 20)
def test_tokenizer_identifier_with_correct_config(self):
logging.basicConfig(level=logging.INFO)
for tokenizer_class in [BertTokenizer, AutoTokenizer]:
tokenizer = tokenizer_class.from_pretrained("wietsedv/bert-base-dutch-cased")
self.assertIsInstance(tokenizer, BertTokenizer)
self.assertEqual(tokenizer.basic_tokenizer.do_lower_case, False)
self.assertEqual(tokenizer.max_len, 512)
def test_tokenizer_identifier_non_existent(self):
logging.basicConfig(level=logging.INFO)
for tokenizer_class in [BertTokenizer, AutoTokenizer]:
with self.assertRaises(EnvironmentError):
_ = tokenizer_class.from_pretrained("julien-c/herlolip-not-exists")
|