master
/ transformers / models / distilbert / tokenization_distilbert.py

tokenization_distilbert.py @3c11360 — raw · history · blame 

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
# 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 ...utils import logging
from ..bert.tokenization_bert import BertTokenizer


logger = logging.get_logger(__name__)

VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt"}

PRETRAINED_VOCAB_FILES_MAP = {
    "vocab_file": {
        "distilbert-base-uncased": "https://huggingface.co/distilbert-base-uncased/resolve/main/vocab.txt",
        "distilbert-base-uncased-distilled-squad": "https://huggingface.co/distilbert-base-uncased-distilled-squad/resolve/main/vocab.txt",
        "distilbert-base-cased": "https://huggingface.co/distilbert-base-cased/resolve/main/vocab.txt",
        "distilbert-base-cased-distilled-squad": "https://huggingface.co/distilbert-base-cased-distilled-squad/resolve/main/vocab.txt",
        "distilbert-base-german-cased": "https://huggingface.co/distilbert-base-german-cased/resolve/main/vocab.txt",
        "distilbert-base-multilingual-cased": "https://huggingface.co/distilbert-base-multilingual-cased/resolve/main/vocab.txt",
    }
}

PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
    "distilbert-base-uncased": 512,
    "distilbert-base-uncased-distilled-squad": 512,
    "distilbert-base-cased": 512,
    "distilbert-base-cased-distilled-squad": 512,
    "distilbert-base-german-cased": 512,
    "distilbert-base-multilingual-cased": 512,
}


PRETRAINED_INIT_CONFIGURATION = {
    "distilbert-base-uncased": {"do_lower_case": True},
    "distilbert-base-uncased-distilled-squad": {"do_lower_case": True},
    "distilbert-base-cased": {"do_lower_case": False},
    "distilbert-base-cased-distilled-squad": {"do_lower_case": False},
    "distilbert-base-german-cased": {"do_lower_case": False},
    "distilbert-base-multilingual-cased": {"do_lower_case": False},
}


class DistilBertTokenizer(BertTokenizer):
    r"""
    Construct a DistilBERT tokenizer.

    [`DistilBertTokenizer`] is identical to [`BertTokenizer`] and runs end-to-end
    tokenization: punctuation splitting and wordpiece.

    Refer to superclass [`BertTokenizer`] 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
    model_input_names = ["input_ids", "attention_mask"]