Page MenuHomec4science
Files F64757118

tokenization_convbert_fast.py
No OneTemporary
Actions

File Metadata

Created
Wed, May 29, 05:44

tokenization_convbert_fast.py
View Options

# coding=utf-8
# Copyright The HuggingFace Inc. 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.
"""Tokenization classes for ConvBERT."""
from ...utils import logging
from ..bert.tokenization_bert_fast import BertTokenizerFast
from .tokenization_convbert import ConvBertTokenizer
logger = logging.get_logger(__name__)
VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt"}
PRETRAINED_VOCAB_FILES_MAP = {
"vocab_file": {
"YituTech/conv-bert-base": "https://huggingface.co/YituTech/conv-bert-base/resolve/main/vocab.txt",
"YituTech/conv-bert-medium-small": "https://huggingface.co/YituTech/conv-bert-medium-small/resolve/main/vocab.txt",
"YituTech/conv-bert-small": "https://huggingface.co/YituTech/conv-bert-small/resolve/main/vocab.txt",
}
}
PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
"YituTech/conv-bert-base": 512,
"YituTech/conv-bert-medium-small": 512,
"YituTech/conv-bert-small": 512,
}
PRETRAINED_INIT_CONFIGURATION = {
"YituTech/conv-bert-base": {"do_lower_case": True},
"YituTech/conv-bert-medium-small": {"do_lower_case": True},
"YituTech/conv-bert-small": {"do_lower_case": True},
}
class ConvBertTokenizerFast(BertTokenizerFast):
r"""
Construct a "fast" ConvBERT tokenizer (backed by HuggingFace's `tokenizers` library).
:class:`~transformers.ConvBertTokenizerFast` is identical to :class:`~transformers.BertTokenizerFast` and runs
end-to-end tokenization: punctuation splitting and wordpiece.
Refer to superclass :class:`~transformers.BertTokenizerFast` for usage examples and documentation concerning
parameters.
"""
vocab_files_names = VOCAB_FILES_NAMES
pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES
pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION
slow_tokenizer_class = ConvBertTokenizer

Event Timeline

c4science · Help