modelscope
/
ModelScope

 
			
							# Copyright 2021-2022 The Alibaba DAMO NLP Team Authors.
# Copyright 2020 Microsoft 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.
"""Fast Tokenization class for model DeBERTa."""

import os
from shutil import copyfile
from typing import Optional, Tuple

from transformers.file_utils import is_sentencepiece_available
from transformers.tokenization_utils_fast import PreTrainedTokenizerFast

from modelscope.utils import logger as logging

if is_sentencepiece_available():
    from .tokenization import DebertaV2Tokenizer
else:
    DebertaV2Tokenizer = None

logger = logging.get_logger()

VOCAB_FILES_NAMES = {
    'vocab_file': 'spm.model',
    'tokenizer_file': 'tokenizer.json'
}

PRETRAINED_VOCAB_FILES_MAP = {'vocab_file': {}}

PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {}

PRETRAINED_INIT_CONFIGURATION = {}


class DebertaV2TokenizerFast(PreTrainedTokenizerFast):
    r"""
    Constructs a DeBERTa-v2 fast tokenizer. Based on [SentencePiece](https://github.com/google/sentencepiece)
    and [rjieba-py](https://github.com/messense/rjieba-py).

    Args:
        vocab_file (`str`):
            [SentencePiece](https://github.com/google/sentencepiece) file (generally has a *.spm* extension) that
            contains the vocabulary necessary to instantiate a tokenizer.
        do_lower_case (`bool`, *optional*, defaults to `False`):
            Whether or not to lowercase the input when tokenizing.
        bos_token (`string`, *optional*, defaults to `"[CLS]"`):
            The beginning of sequence token that was used during pre-training. Can be used a sequence classifier token.
            When building a sequence using special tokens, this is not the token that is used for the beginning of
            sequence. The token used is the `cls_token`.
        eos_token (`string`, *optional*, defaults to `"[SEP]"`):
            The end of sequence token. When building a sequence using special tokens, this is not the token that is
            used for the end of sequence. The token used is the `sep_token`.
        unk_token (`str`, *optional*, defaults to `"[UNK]"`):
            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.
        sep_token (`str`, *optional*, defaults to `"[SEP]"`):
            The separator token, which is used when building a sequence from multiple sequences, e.g. two sequences for
            sequence classification or for a text and a question for question answering. It is also used as the last
            token of a sequence built with special tokens.
        pad_token (`str`, *optional*, defaults to `"[PAD]"`):
            The token used for padding, for example when batching sequences of different lengths.
        cls_token (`str`, *optional*, defaults to `"[CLS]"`):
            The classifier token which is used when doing sequence classification (classification of the whole sequence
            instead of per-token classification). It is the first token of the sequence when built with special tokens.
        mask_token (`str`, *optional*, defaults to `"[MASK]"`):
            The token used for masking values. This is the token used when training this model with masked language
            modeling. This is the token which the model will try to predict.
        sp_model_kwargs (`dict`, *optional*):
            Will be passed to the `SentencePieceProcessor.__init__()` method. The [Python wrapper for
            SentencePiece](https://github.com/google/sentencepiece/tree/master/python) can be used, among other things,
            to set:

            - `enable_sampling`: Enable subword regularization.
            - `nbest_size`: Sampling parameters for unigram. Invalid for BPE-Dropout.

              - `nbest_size = {0,1}`: No sampling is performed.
              - `nbest_size > 1`: samples from the nbest_size results.
              - `nbest_size < 0`: assuming that nbest_size is infinite and samples from the all hypothesis (lattice)
                using forward-filtering-and-backward-sampling algorithm.

            - `alpha`: Smoothing parameter for unigram sampling, and dropout probability of merge operations for
              BPE-dropout.
    """

    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 = DebertaV2Tokenizer

    def __init__(self,
                 vocab_file=None,
                 tokenizer_file=None,
                 do_lower_case=False,
                 split_by_punct=False,
                 split_chinese=True,
                 bos_token='[CLS]',
                 eos_token='[SEP]',
                 unk_token='[UNK]',
                 sep_token='[SEP]',
                 pad_token='[PAD]',
                 cls_token='[CLS]',
                 mask_token='[MASK]',
                 **kwargs) -> None:
        super().__init__(
            vocab_file,
            tokenizer_file=tokenizer_file,
            do_lower_case=do_lower_case,
            bos_token=bos_token,
            eos_token=eos_token,
            unk_token=unk_token,
            sep_token=sep_token,
            pad_token=pad_token,
            cls_token=cls_token,
            mask_token=mask_token,
            split_by_punct=split_by_punct,
            split_chinese=split_chinese,
            **kwargs,
        )

        self.do_lower_case = do_lower_case
        self.split_by_punct = split_by_punct
        self.split_chinese = split_chinese
        self.vocab_file = vocab_file
        self.can_save_slow_tokenizer = False if not self.vocab_file else True

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

        - single sequence: [CLS] X [SEP]
        - pair of sequences: [CLS] A [SEP] B [SEP]

        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.
        """

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

    def get_special_tokens_mask(self,
                                token_ids_0,
                                token_ids_1=None,
                                already_has_special_tokens=False):
        """
        Retrieves 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` or `encode_plus` methods.

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

        Returns:
            `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 not None:
            return [1] + ([0] * len(token_ids_0)) + [1] + (
                [0] * len(token_ids_1)) + [1]
        return [1] + ([0] * len(token_ids_0)) + [1]

    def create_token_type_ids_from_sequences(self,
                                             token_ids_0,
                                             token_ids_1=None):
        """
        Create a mask from the two sequences passed to be used in a sequence-pair classification task. A DeBERTa
        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 |
        ```

        If `token_ids_1` is `None`, this method only returns the first portion of the mask (0s).

        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 [token type IDs](../glossary#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]:
        if not self.can_save_slow_tokenizer:
            raise ValueError(
                'Your fast tokenizer does not have the necessary information to save the vocabulary for a slow '
                'tokenizer.')

        if not os.path.isdir(save_directory):
            logger.error(
                f'Vocabulary path ({save_directory}) should be a directory')
            return
        out_vocab_file = os.path.join(
            save_directory, (filename_prefix + '-' if filename_prefix else '')
            + VOCAB_FILES_NAMES['vocab_file'])

        if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file):
            copyfile(self.vocab_file, out_vocab_file)

        return (out_vocab_file, )