transformers/pytorch_transformers/tokenization_distilbert.py
2019-09-19 10:55:06 +02:00

82 lines
3.1 KiB
Python

# coding=utf-8
# Copyright 2018 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.
"""Tokenization classes for DistilBERT."""
from __future__ import absolute_import, division, print_function, unicode_literals
import collections
import logging
import os
import unicodedata
from io import open
from .tokenization_bert import BertTokenizer
logger = logging.getLogger(__name__)
VOCAB_FILES_NAMES = {'vocab_file': 'vocab.txt'}
PRETRAINED_VOCAB_FILES_MAP = {
'vocab_file':
{
'distilbert-base-uncased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-uncased-vocab.txt",
'distilbert-base-uncased-distilled-squad': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-uncased-vocab.txt",
}
}
PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
'distilbert-base-uncased': 512,
'distilbert-base-uncased-distilled-squad': 512,
}
class DistilBertTokenizer(BertTokenizer):
r"""
Constructs a DistilBertTokenizer.
:class:`~pytorch_transformers.DistilBertTokenizer` is identical to BertTokenizer and runs end-to-end tokenization: punctuation splitting + wordpiece
Args:
vocab_file: Path to a one-wordpiece-per-line vocabulary file
do_lower_case: Whether to lower case the input. Only has an effect when do_wordpiece_only=False
do_basic_tokenize: Whether to do basic tokenization before wordpiece.
max_len: An artificial maximum length to truncate tokenized sequences to; Effective maximum length is always the
minimum of this value (if specified) and the underlying BERT model's sequence length.
never_split: List of tokens which will never be split during tokenization. Only has an effect when
do_wordpiece_only=False
"""
vocab_files_names = VOCAB_FILES_NAMES
pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES
def add_special_tokens_single_sequence(self, token_ids):
return token_ids
def add_special_tokens_sequence_pair(self, token_ids_0, token_ids_1):
sep = [self.sep_token_id]
return token_ids_0 + sep + token_ids_1
def create_mask_from_sequences(self, sequence_0, sequence_1):
"""
Creates a mask from the two sequences passed to be used in a sequence-pair classification task.
A BERT sequence pair mask has the following format:
0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1 1 1
| first sequence | second sequence
"""
sep = [self.sep_token_id]
cls = [self.cls_token_id]
return len(self.encode(sequence_0) + sep) * [0] + len(self.encode(sequence_1)) * [1]