wehub-resource-sync
109 lines
3.7 KiB
Python
109 lines
3.7 KiB
Python
# Copyright (c) 2023 PaddlePaddle Authors. 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 json
|
|
import os
|
|
import unittest
|
|
|
|
from paddlenlp.transformers import DebertaTokenizer
|
|
|
|
from ..test_tokenizer_common import TokenizerTesterMixin
|
|
|
|
VOCAB_FILES_NAMES = {
|
|
"vocab_file": "vocab.json",
|
|
"merges_file": "merges.txt",
|
|
}
|
|
|
|
|
|
class DebertaTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
|
|
|
|
tokenizer_class = DebertaTokenizer
|
|
from_pretrained_kwargs = {"add_prefix_space": True}
|
|
test_seq2seq = False
|
|
|
|
def setUp(self):
|
|
super().setUp()
|
|
|
|
# Adapted from Sennrich et al. 2015 and https://github.com/rsennrich/subword-nmt
|
|
vocab = [
|
|
"l",
|
|
"o",
|
|
"w",
|
|
"e",
|
|
"r",
|
|
"s",
|
|
"t",
|
|
"i",
|
|
"d",
|
|
"n",
|
|
"\u0120",
|
|
"\u0120l",
|
|
"\u0120n",
|
|
"\u0120lo",
|
|
"\u0120low",
|
|
"er",
|
|
"\u0120lowest",
|
|
"\u0120newer",
|
|
"\u0120wider",
|
|
"[UNK]",
|
|
]
|
|
vocab_tokens = dict(zip(vocab, range(len(vocab))))
|
|
merges = ["#version: 0.2", "\u0120 l", "\u0120l o", "\u0120lo w", "e r", ""]
|
|
self.special_tokens_map = {"unk_token": "[UNK]"}
|
|
|
|
self.vocab_file = os.path.join(self.tmpdirname, VOCAB_FILES_NAMES["vocab_file"])
|
|
self.merges_file = os.path.join(self.tmpdirname, VOCAB_FILES_NAMES["merges_file"])
|
|
with open(self.vocab_file, "w", encoding="utf-8") as fp:
|
|
fp.write(json.dumps(vocab_tokens) + "\n")
|
|
with open(self.merges_file, "w", encoding="utf-8") as fp:
|
|
fp.write("\n".join(merges))
|
|
|
|
def get_tokenizer(self, **kwargs):
|
|
kwargs.update(self.special_tokens_map)
|
|
return DebertaTokenizer.from_pretrained(self.tmpdirname, **kwargs)
|
|
|
|
def get_input_output_texts(self, tokenizer):
|
|
input_text = "lower newer"
|
|
output_text = "lower newer"
|
|
return input_text, output_text
|
|
|
|
def test_full_tokenizer(self):
|
|
tokenizer = self.get_tokenizer()
|
|
text = "lower newer"
|
|
bpe_tokens = ["l", "o", "w", "er", "\u0120", "n", "e", "w", "er"]
|
|
tokens = tokenizer.tokenize(text)
|
|
self.assertListEqual(tokens, bpe_tokens)
|
|
|
|
input_tokens = tokens + [tokenizer.unk_token]
|
|
input_bpe_tokens = [0, 1, 2, 15, 10, 9, 3, 2, 15, 19]
|
|
self.assertListEqual(tokenizer.convert_tokens_to_ids(input_tokens), input_bpe_tokens)
|
|
|
|
def test_token_type_ids(self):
|
|
tokenizer = self.get_tokenizer()
|
|
tokd = tokenizer("Hello", "World")
|
|
expected_token_type_ids = [0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1]
|
|
self.assertListEqual(tokd["token_type_ids"], expected_token_type_ids)
|
|
|
|
def test_pretokenized_inputs(self, *args, **kwargs):
|
|
pass
|
|
|
|
# tokenizer has no padding token
|
|
def test_padding_different_model_input_name(self):
|
|
pass
|
|
|
|
def test_pretrained_model_lists(self):
|
|
# No max_model_input_sizes
|
|
self.assertGreaterEqual(len(self.tokenizer_class.pretrained_resource_files_map), 1)
|
|
self.assertGreaterEqual(len(list(self.tokenizer_class.pretrained_resource_files_map.values())[0]), 1)
|