mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-04 13:20:12 +06:00
523ca4e016
* resolve conflicts * rebase and make style * test * test * test * rebase and make style * rebase and make style * tests * tests * rewrite some functions * rebase and make style * fix load_tf_weights_in_cpmant * reformat some unrelated files * upgrade quality * fix some bugs & docstring * add models and tests * solve conflicts * resolve conflicts * resolve conflicts * resolve conflicts * resolve conflicts * tests * resolve conflicts * resolve conflicts * fix load_tf_weights_in_cpmant * reformat some unrelated files * upgrade quality * fix some bugs & docstring * save resolution * make style * delete redefinition code * reformat function * reformat * resolve conflicts * resolve conflicts * resolve conflicts * resolve conflicts * resolve conflicts * tests * resolve conflicts * resolve conflicts * fix load_tf_weights_in_cpmant * reformat some unrelated files * upgrade quality * resolve conflicts * resolve conflicts * resolve conflicts * resolve conflicts * resolve conflicts * fix load_tf_weights_in_cpmant * reformat some unrelated files * upgrade quality * resolve conflicts * make style * fix bugs and refactor * modify docstrings and make style * unify import format in __init__.py * fix import-altclp bug * fix copies to update index.md * fix unused config parameters * fix unused config parameters * fix unused config parameters * update README_ja.md * dummy commit for unit test * fix attention mask * add CPMAntTokenizer&-Fast to auto-mapping * drop redundant changes in README_ko * fix defaults in docstring * fix use_cache and some docstring * add missing args in tokenizer * modify tester inheritance * add is_jieba_available * fix some bugs * make style and fix-copies * add doctests * skip integration tests * add is_jieba_available * fix bugs in common tests * adjust docstrings and make style * add argument docstring * adjust code to some specifications * make style and fix-copies * add fast tokenization test * dummy commit for unit test * dummy commit for unit test * dummy commit for unit test * normalize some comments and names * Bert->CPMAnt * camel names and drop redundant codes * make style and fix-coies * add CpmTokenizerFast _import_structure * drop cpmanttokenizerfast in model_doc * fix some problems * fix CPMAnt tokenization for common test * make style and fixup * fix copies and fixup * fix bugs in tokenization test * dummy commit for connection failure in unittest * fix copies * drop trailing comma * fix decorator in tests * dummy commit for connection failure in unittest --------- Co-authored-by: Gong Baitao <gongbaitao11@gmail.com>
70 lines
2.3 KiB
Python
70 lines
2.3 KiB
Python
# coding=utf-8
|
||
# Copyright 2022 The OpenBMB Team and The 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 os
|
||
import unittest
|
||
|
||
from transformers.models.cpmant.tokenization_cpmant import VOCAB_FILES_NAMES, CpmAntTokenizer
|
||
from transformers.testing_utils import require_jieba, tooslow
|
||
|
||
from ...test_tokenization_common import TokenizerTesterMixin
|
||
|
||
|
||
@require_jieba
|
||
class CPMAntTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
|
||
tokenizer_class = CpmAntTokenizer
|
||
test_rust_tokenizer = False
|
||
|
||
def setUp(self):
|
||
super().setUp()
|
||
|
||
vocab_tokens = [
|
||
"<d>",
|
||
"</d>",
|
||
"<s>",
|
||
"</s>",
|
||
"</_>",
|
||
"<unk>",
|
||
"<pad>",
|
||
"</n>",
|
||
"我",
|
||
"是",
|
||
"C",
|
||
"P",
|
||
"M",
|
||
"A",
|
||
"n",
|
||
"t",
|
||
]
|
||
self.vocab_file = os.path.join(self.tmpdirname, VOCAB_FILES_NAMES["vocab_file"])
|
||
with open(self.vocab_file, "w", encoding="utf-8") as vocab_writer:
|
||
vocab_writer.write("".join([x + "\n" for x in vocab_tokens]))
|
||
|
||
@tooslow
|
||
def test_pre_tokenization(self):
|
||
tokenizer = CpmAntTokenizer.from_pretrained("openbmb/cpm-ant-10b")
|
||
texts = "今天天气真好！"
|
||
jieba_tokens = ["今天", "天气", "真", "好", "！"]
|
||
tokens = tokenizer.tokenize(texts)
|
||
self.assertListEqual(tokens, jieba_tokens)
|
||
normalized_text = "今天天气真好！"
|
||
input_tokens = [tokenizer.bos_token] + tokens
|
||
|
||
input_jieba_tokens = [6, 9802, 14962, 2082, 831, 244]
|
||
self.assertListEqual(tokenizer.convert_tokens_to_ids(input_tokens), input_jieba_tokens)
|
||
|
||
reconstructed_text = tokenizer.decode(input_jieba_tokens)
|
||
self.assertEqual(reconstructed_text, normalized_text)
|