public/gpt-2/transformers/models/herbert/tokenization_herbert_fast.py

# coding=utf-8
# Copyright 2020 The Google AI Language Team Authors, Allegro.pl, Facebook Inc. 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.

from typing import List, Optional, Tuple

from ...tokenization_utils_fast import PreTrainedTokenizerFast
from ...utils import logging
from .tokenization_herbert import HerbertTokenizer


logger = logging.get_logger(__name__)

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

PRETRAINED_VOCAB_FILES_MAP = {
    "vocab_file": {
        "allegro/herbert-base-cased": "https://huggingface.co/allegro/herbert-base-cased/resolve/main/vocab.json"
    },
    "merges_file": {
        "allegro/herbert-base-cased": "https://huggingface.co/allegro/herbert-base-cased/resolve/main/merges.txt"
    },
}

PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {"allegro/herbert-base-cased": 514}
PRETRAINED_INIT_CONFIGURATION = {}


class HerbertTokenizerFast(PreTrainedTokenizerFast):
    """
    Construct a "Fast" BPE tokenizer for HerBERT (backed by HuggingFace's `tokenizers` library).

    Peculiarities:

    - uses BERT's pre-tokenizer: BertPreTokenizer splits tokens on spaces, and also on punctuation. Each occurrence of
      a punctuation character will be treated separately.

    This tokenizer inherits from :class:`~transformers.PreTrainedTokenizer` which contains most of the methods. Users
    should refer to the superclass for more information regarding methods.

    Args:
        vocab_file (:obj:`str`):
            Path to the vocabulary file.
        merges_file (:obj:`str`):
            Path to the merges file.
    """

    vocab_files_names = VOCAB_FILES_NAMES
    pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
    pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION
    max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES
    slow_tokenizer_class = HerbertTokenizer

    def __init__(
        self,
        vocab_file=None,
        merges_file=None,
        tokenizer_file=None,
        cls_token="<s>",
        unk_token="<unk>",
        pad_token="<pad>",
        mask_token="<mask>",
        sep_token="</s>",
        **kwargs
    ):

        super().__init__(
            vocab_file,
            merges_file,
            tokenizer_file=tokenizer_file,
            cls_token=cls_token,
            unk_token=unk_token,
            pad_token=pad_token,
            mask_token=mask_token,
            sep_token=sep_token,
            **kwargs,
        )

    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. An HerBERT, like BERT sequence has the following format:

        - single sequence: ``<s> X </s>``
        - pair of sequences: ``<s> A </s> B </s>``

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

        Returns:
            :obj:`List[int]`: List of `input IDs <../glossary.html#input-ids>`__ with the appropriate special tokens.
        """

        cls = [self.cls_token_id]
        sep = [self.sep_token_id]
        if token_ids_1 is None:
            return cls + token_ids_0 + sep

        return cls + token_ids_0 + sep + token_ids_1 + sep

    def get_special_tokens_mask(
        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None, already_has_special_tokens: bool = False
    ) -> List[int]:
        """
        Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
        special tokens using the tokenizer ``prepare_for_model`` method.

        Args:
            token_ids_0 (:obj:`List[int]`):
                List of IDs.
            token_ids_1 (:obj:`List[int]`, `optional`):
                Optional second list of IDs for sequence pairs.
            already_has_special_tokens (:obj:`bool`, `optional`, defaults to :obj:`False`):
                Whether or not the token list is already formatted with special tokens for the model.

        Returns:
            :obj:`List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
        """
        if already_has_special_tokens:
            return super().get_special_tokens_mask(
                token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=True
            )

        if token_ids_1 is None:
            return [1] + ([0] * len(token_ids_0)) + [1]
        return [1] + ([0] * len(token_ids_0)) + [1] + ([0] * len(token_ids_1)) + [1]

    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 to be used in a sequence-pair classification task. HerBERT, like
        BERT sequence pair mask has the following format:

        ::

            0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1
            | first sequence    | second sequence |

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

        Returns:
            :obj:`List[int]`: List of `token type IDs <../glossary.html#token-type-ids>`_ according to the given
            sequence(s).
        """
        sep = [self.sep_token_id]
        cls = [self.cls_token_id]

        if token_ids_1 is None:
            return len(cls + token_ids_0 + sep) * [0]
        return len(cls + token_ids_0 + sep) * [0] + len(token_ids_1 + sep) * [1]

    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)