mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-05 22:00:09 +06:00
19420fd99e
* move test model folders (TODO: fix imports and others) * fix (potentially partially) imports (in model test modules) * fix (potentially partially) imports (in tokenization test modules) * fix (potentially partially) imports (in feature extraction test modules) * fix import utils.test_modeling_tf_core * fix path ../fixtures/ * fix imports about generation.test_generation_flax_utils * fix more imports * fix fixture path * fix get_test_dir * update module_to_test_file * fix get_tests_dir from wrong transformers.utils * update config.yml (CircleCI) * fix style * remove missing imports * update new model script * update check_repo * update SPECIAL_MODULE_TO_TEST_MAP * fix style * add __init__ * update self-scheduled * fix add_new_model scripts * check one way to get location back * python setup.py build install * fix import in test auto * update self-scheduled.yml * update slack notification script * Add comments about artifact names * fix for yolos Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>
40 lines
1.7 KiB
Python
40 lines
1.7 KiB
Python
# coding=utf-8
|
||
# 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.
|
||
|
||
|
||
from transformers.models.cpm.tokenization_cpm import CpmTokenizer
|
||
from transformers.testing_utils import custom_tokenizers
|
||
|
||
from ..xlnet.test_modeling_xlnet import XLNetModelTest
|
||
|
||
|
||
@custom_tokenizers
|
||
class CpmTokenizationTest(XLNetModelTest):
|
||
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)
|