Files
wehub-resource-sync e06fe8e8c6
Self-hosted runner (benchmark) / Benchmark (aws-g5-4xlarge-cache) (push) Waiting to run
New model PR merged notification / Notify new model (push) Waiting to run
Update Transformers metadata / build_and_package (push) Waiting to run
Secret Leaks / trufflehog (push) Failing after 1s
Build documentation / build (push) Failing after 1s
Build documentation / build_other_lang (push) Failing after 0s
CodeQL Security Analysis / CodeQL Analysis (push) Failing after 0s
PR CI / pr-ci (push) Failing after 1s
Slow tests on important models (on Push - A10) / Get all modified files (push) Failing after 1s
Slow tests on important models (on Push - A10) / Model CI (push) Has been skipped
chore: import upstream snapshot with attribution
2026-07-13 11:57:37 +08:00

41 lines
1.4 KiB
Python

# Copyright 2020 The HuggingFace Team. All rights reserved.
#
# 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.
from transformers import AutoTokenizer
from transformers.models.distilbert.tokenization_distilbert import DistilBertTokenizer
from transformers.testing_utils import require_tokenizers
from ..bert import test_tokenization_bert
# TODO: Ita remove this test file?
@require_tokenizers
class DistilBertTokenizationTest(test_tokenization_bert.BertTokenizationTest):
tokenizer_class = DistilBertTokenizer
rust_tokenizer_class = DistilBertTokenizer
test_rust_tokenizer = False
from_pretrained_id = "distilbert/distilbert-base-uncased"
@classmethod
def setUpClass(cls):
super().setUpClass()
from_pretrained_id = "distilbert/distilbert-base-uncased"
tok_auto = AutoTokenizer.from_pretrained(from_pretrained_id)
tok_auto.save_pretrained(cls.tmpdirname)
cls.tokenizers = [tok_auto]