wehub-resource-sync
e06fe8e8c6
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
Self-hosted runner (benchmark) / Benchmark (aws-g5-4xlarge-cache) (push) Has been cancelled
New model PR merged notification / Notify new model (push) Has been cancelled
Update Transformers metadata / build_and_package (push) Has been cancelled
51 lines
1.9 KiB
Python
51 lines
1.9 KiB
Python
# Copyright 2018 HuggingFace Inc. team.
|
|
# 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 unittest
|
|
|
|
from transformers.models.cpm.tokenization_cpm import CpmTokenizer
|
|
from transformers.testing_utils import custom_tokenizers
|
|
|
|
|
|
@custom_tokenizers
|
|
class CpmTokenizationTest(unittest.TestCase):
|
|
# There is no `CpmModel`
|
|
def is_pipeline_test_to_skip(
|
|
self,
|
|
pipeline_test_case_name,
|
|
config_class,
|
|
model_architecture,
|
|
tokenizer_name,
|
|
image_processor_name,
|
|
feature_extractor_name,
|
|
processor_name,
|
|
):
|
|
return True
|
|
|
|
def test_pre_tokenization(self):
|
|
tokenizer = CpmTokenizer.from_pretrained("TsinghuaAI/CPM-Generate")
|
|
text = "Hugging Face大法好，谁用谁知道。"
|
|
normalized_text = "Hugging Face大法好,谁用谁知道。<unk>"
|
|
bpe_tokens = "▁Hu gg ing ▁ ▂ ▁F ace ▁大法 ▁好 ▁ , ▁谁 ▁用 ▁谁 ▁知 道 ▁ 。".split()
|
|
|
|
tokens = tokenizer.tokenize(text)
|
|
self.assertListEqual(tokens, bpe_tokens)
|
|
|
|
input_tokens = tokens + [tokenizer.unk_token]
|
|
|
|
input_bpe_tokens = [13789, 13283, 1421, 8, 10, 1164, 13608, 16528, 63, 8, 9, 440, 108, 440, 121, 90, 8, 12, 0]
|
|
self.assertListEqual(tokenizer.convert_tokens_to_ids(input_tokens), input_bpe_tokens)
|
|
|
|
reconstructed_text = tokenizer.decode(input_bpe_tokens)
|
|
self.assertEqual(reconstructed_text, normalized_text)
|