wehub-resource-sync
75 lines
2.6 KiB
Python
75 lines
2.6 KiB
Python
# Copyright (c) 2023 PaddlePaddle Authors. All Rights Reserved.
|
|
# 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.
|
|
|
|
import os
|
|
import unittest
|
|
|
|
from paddlenlp.transformers import MPNetTokenizer
|
|
|
|
from ...transformers.test_tokenizer_common import TokenizerTesterMixin
|
|
|
|
|
|
class MPNetTokenizerTest(TokenizerTesterMixin, unittest.TestCase):
|
|
tokenizer_class = MPNetTokenizer
|
|
space_between_special_tokens = True
|
|
|
|
def setUp(self):
|
|
super().setUp()
|
|
|
|
vocab_tokens = [
|
|
"[UNK]",
|
|
"[CLS]",
|
|
"[SEP]",
|
|
"[PAD]",
|
|
"[MASK]",
|
|
"want",
|
|
"##want",
|
|
"##ed",
|
|
"wa",
|
|
"un",
|
|
"runn",
|
|
"##ing",
|
|
",",
|
|
"low",
|
|
"lowest",
|
|
]
|
|
self.vocab_file = os.path.join(self.tmpdirname, MPNetTokenizer.resource_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]))
|
|
|
|
def get_input_output_texts(self, tokenizer):
|
|
input_text = "UNwant\u00E9d,running"
|
|
output_text = "unwanted, running"
|
|
return input_text, output_text
|
|
|
|
def test_full_tokenizer(self):
|
|
tokenizer = self.tokenizer_class(self.vocab_file)
|
|
|
|
tokens = tokenizer.tokenize("UNwant\u00E9d,running")
|
|
self.assertListEqual(tokens, ["un", "##want", "##ed", ",", "runn", "##ing"])
|
|
self.assertListEqual(tokenizer.convert_tokens_to_ids(tokens), [9, 6, 7, 12, 10, 11])
|
|
|
|
def test_sequence_builders(self):
|
|
tokenizer = self.tokenizer_class.from_pretrained("mpnet-base")
|
|
|
|
text = tokenizer.encode("sequence builders", add_special_tokens=False)["input_ids"]
|
|
text_2 = tokenizer.encode("multi-sequence build", add_special_tokens=False)["input_ids"]
|
|
|
|
encoded_sentence = tokenizer.build_inputs_with_special_tokens(text)
|
|
encoded_pair = tokenizer.build_inputs_with_special_tokens(text, text_2)
|
|
|
|
assert encoded_sentence == [0] + text + [2]
|
|
assert encoded_pair == [0] + text + [2] + [2] + text_2 + [2]
|