"vscode:/vscode.git/clone" did not exist on "a80778f40e4738071b5d01420a0328bb00cdb356"
tokenization_distilbert.py 3.31 KB
Newer Older
thomwolf's avatar
thomwolf committed
1
# coding=utf-8
thomwolf's avatar
thomwolf committed
2
# Copyright 2018 The HuggingFace Inc. team.
thomwolf's avatar
thomwolf committed
3
4
5
6
7
8
9
10
11
12
13
14
#
# 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.
thomwolf's avatar
thomwolf committed
15
"""Tokenization classes for DistilBERT."""
thomwolf's avatar
thomwolf committed
16
17
18
19


import logging

20
from .tokenization_bert import BertTokenizer, BertTokenizerFast
thomwolf's avatar
thomwolf committed
21

Aymeric Augustin's avatar
Aymeric Augustin committed
22

thomwolf's avatar
thomwolf committed
23
24
logger = logging.getLogger(__name__)

25
VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt"}
thomwolf's avatar
thomwolf committed
26
27

PRETRAINED_VOCAB_FILES_MAP = {
28
29
30
    "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",
31
32
        "distilbert-base-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-cased-vocab.txt",
        "distilbert-base-cased-distilled-squad": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-cased-vocab.txt",
33
34
        "distilbert-base-german-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/distilbert-base-german-cased-vocab.txt",
        "distilbert-base-multilingual-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-multilingual-cased-vocab.txt",
thomwolf's avatar
thomwolf committed
35
36
37
38
    }
}

PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
39
40
    "distilbert-base-uncased": 512,
    "distilbert-base-uncased-distilled-squad": 512,
41
42
    "distilbert-base-cased": 512,
    "distilbert-base-cased-distilled-squad": 512,
43
44
    "distilbert-base-german-cased": 512,
    "distilbert-base-multilingual-cased": 512,
thomwolf's avatar
thomwolf committed
45
46
47
}


48
49
50
PRETRAINED_INIT_CONFIGURATION = {
    "distilbert-base-uncased": {"do_lower_case": True},
    "distilbert-base-uncased-distilled-squad": {"do_lower_case": True},
51
52
    "distilbert-base-cased": {"do_lower_case": False},
    "distilbert-base-cased-distilled-squad": {"do_lower_case": False},
53
54
55
56
57
    "distilbert-base-german-cased": {"do_lower_case": False},
    "distilbert-base-multilingual-cased": {"do_lower_case": False},
}


thomwolf's avatar
thomwolf committed
58
class DistilBertTokenizer(BertTokenizer):
thomwolf's avatar
thomwolf committed
59
    r"""
thomwolf's avatar
thomwolf committed
60
    Constructs a DistilBertTokenizer.
Lysandre Debut's avatar
Lysandre Debut committed
61
62
63
64
65
    :class:`~transformers.DistilBertTokenizer` is identical to :class:`~transformers.BertTokenizer` and runs end-to-end
    tokenization: punctuation splitting + wordpiece.

    Refer to superclass :class:`~transformers.BertTokenizer` for usage examples and documentation concerning
    parameters.
thomwolf's avatar
thomwolf committed
66
67
68
69
70
    """

    vocab_files_names = VOCAB_FILES_NAMES
    pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
    max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES
71
    pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION
Lysandre Debut's avatar
Lysandre Debut committed
72
    model_input_names = ["attention_mask"]
73
74
75
76
77
78
79


class DistilBertTokenizerFast(BertTokenizerFast):
    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
Lysandre Debut's avatar
Lysandre Debut committed
80
    model_input_names = ["attention_mask"]