File size: 6,956 Bytes
9231ab9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
# coding=utf-8
# Copyright 2021 The Open AI Team Authors and 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 OpenAI GPT."""


from typing import List, Optional, Tuple

from tokenizers import pre_tokenizers

from ...tokenization_utils_fast import PreTrainedTokenizerFast
from ...utils import logging
from .tokenization_clip import CLIPTokenizer


logger = logging.get_logger(__name__)

VOCAB_FILES_NAMES = {"vocab_file": "vocab.json", "merges_file": "merges.txt", "tokenizer_file": "tokenizer.json"}

PRETRAINED_VOCAB_FILES_MAP = {
    "vocab_file": {
        "openai/clip-vit-base-patch32": "https://huggingface.co/openai/clip-vit-base-patch32/resolve/main/vocab.json",
    },
    "merges_file": {
        "openai/clip-vit-base-patch32": "https://huggingface.co/openai/clip-vit-base-patch32/resolve/main/merges.txt",
    },
    "tokenizer_file": {
        "openai/clip-vit-base-patch32": (
            "https://huggingface.co/openai/clip-vit-base-patch32/resolve/main/tokenizer.json"
        ),
    },
}

PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
    "openai/clip-vit-base-patch32": 77,
}


class CLIPTokenizerFast(PreTrainedTokenizerFast):
    """
    Construct a "fast" CLIP tokenizer (backed by HuggingFace's *tokenizers* library). Based on byte-level
    Byte-Pair-Encoding.

    This tokenizer inherits from [`PreTrainedTokenizerFast`] which contains most of the main methods. Users should
    refer to this superclass for more information regarding those methods.

    Args:
        vocab_file (`str`):
            Path to the vocabulary file.
        merges_file (`str`):
            Path to the merges file.
        unk_token (`str`, *optional*, defaults to `<|endoftext|>`):
            The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this
            token instead.
        bos_token (`str`, *optional*, defaults to `<|startoftext|>`):
            The beginning of sequence token.
        eos_token (`str`, *optional*, defaults to `<|endoftext|>`):
            The end of sequence token.
    """

    vocab_files_names = VOCAB_FILES_NAMES
    pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
    max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES
    model_input_names = ["input_ids", "attention_mask"]
    slow_tokenizer_class = CLIPTokenizer

    def __init__(
        self,
        vocab_file=None,
        merges_file=None,
        tokenizer_file=None,
        unk_token="<|endoftext|>",
        bos_token="<|startoftext|>",
        eos_token="<|endoftext|>",
        pad_token="<|endoftext|>",  # hack to enable padding
        **kwargs,
    ):
        super().__init__(
            vocab_file,
            merges_file,
            tokenizer_file=tokenizer_file,
            unk_token=unk_token,
            bos_token=bos_token,
            eos_token=eos_token,
            pad_token=pad_token,
            **kwargs,
        )

        if not isinstance(self.backend_tokenizer.pre_tokenizer, pre_tokenizers.Sequence):
            raise ValueError(
                "The `backend_tokenizer` provided does not match the expected format. The CLIP tokenizer has been"
                " heavily modified from transformers version 4.17.0. You need to convert the tokenizer you are using"
                " to be compatible with this version.The easiest way to do so is"
                ' `CLIPTokenizerFast.from_pretrained("path_to_local_folder_or_hub_repo, from_slow=True)`. If you want'
                " to use your existing tokenizer, you will have to revert to a version prior to 4.17.0 of"
                " transformers."
            )

        self._wrap_decode_method_backend_tokenizer()

    # Very ugly hack to enable padding to have a correct decoding see https://github.com/huggingface/tokenizers/issues/872
    def _wrap_decode_method_backend_tokenizer(self):
        orig_decode_method = self.backend_tokenizer.decode

        def new_decode_method(*args, **kwargs):
            text = orig_decode_method(*args, **kwargs)
            text = text.replace(self.backend_tokenizer.model.end_of_word_suffix, " ").strip()
            return text

        self.backend_tokenizer.decode = new_decode_method

    def build_inputs_with_special_tokens(
        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
    ) -> List[int]:
        """
        Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and
        adding special tokens. A CLIP sequence has the following format:

        - single sequence: `<|startoftext|> X <|endoftext|>`

        Pairs of sequences are not the expected use case, but they will be handled without a separator.

        Args:
            token_ids_0 (`List[int]`):
                List of IDs to which the special tokens will be added.
            token_ids_1 (`List[int]`, *optional*):
                Optional second list of IDs for sequence pairs.

        Returns:
            `List[int]`: List of [input IDs](../glossary#input-ids) with the appropriate special tokens.
        """
        bos_token = [self.bos_token_id]
        eos_token = [self.eos_token_id]

        if token_ids_1 is None:
            return bos_token + token_ids_0 + eos_token
        return bos_token + token_ids_0 + eos_token + eos_token + token_ids_1 + eos_token

    def create_token_type_ids_from_sequences(
        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
    ) -> List[int]:
        """
        Create a mask from the two sequences passed. CLIP does not make use of token type ids, therefore a list of
        zeros is returned.

        Args:
            token_ids_0 (`List[int]`):
                List of IDs.
            token_ids_1 (`List[int]`, *optional*):
                Optional second list of IDs for sequence pairs.

        Returns:
            `List[int]`: List of zeros.
        """
        bos_token = [self.bos_token_id]
        eos_token = [self.eos_token_id]

        if token_ids_1 is None:
            return len(bos_token + token_ids_0 + eos_token) * [0]
        return len(bos_token + token_ids_0 + eos_token + eos_token + token_ids_1 + eos_token) * [0]

    def save_vocabulary(self, save_directory: str, filename_prefix: Optional[str] = None) -> Tuple[str]:
        files = self._tokenizer.model.save(save_directory, name=filename_prefix)
        return tuple(files)