From 7eee875f6c68b3841d0630dc3cda69acc39679a0 Mon Sep 17 00:00:00 2001 From: Lysandre Debut Date: Wed, 27 Jul 2022 14:57:01 +0200 Subject: [PATCH] sentencepiece shouldn't be required for the fast LayoutXLM tokenizer --- .../layoutxlm/tokenization_layoutxlm_fast.py | 105 +++++++++++++++++- 1 file changed, 103 insertions(+), 2 deletions(-) diff --git a/src/transformers/models/layoutxlm/tokenization_layoutxlm_fast.py b/src/transformers/models/layoutxlm/tokenization_layoutxlm_fast.py index 26d42d4d7e4ba1..71a76614376a03 100644 --- a/src/transformers/models/layoutxlm/tokenization_layoutxlm_fast.py +++ b/src/transformers/models/layoutxlm/tokenization_layoutxlm_fast.py @@ -19,8 +19,6 @@ from shutil import copyfile from typing import Dict, List, Optional, Tuple, Union -from transformers.models.layoutxlm.tokenization_layoutxlm import LAYOUTXLM_ENCODE_KWARGS_DOCSTRING - from ...tokenization_utils import AddedToken from ...tokenization_utils_base import ( BatchEncoding, @@ -47,6 +45,109 @@ logger = logging.get_logger(__name__) +LAYOUTXLM_ENCODE_KWARGS_DOCSTRING = r""" + add_special_tokens (`bool`, *optional*, defaults to `True`): + Whether or not to encode the sequences with the special tokens relative to their model. + padding (`bool`, `str` or [`~file_utils.PaddingStrategy`], *optional*, defaults to `False`): + Activates and controls padding. Accepts the following values: + + - `True` or `'longest'`: Pad to the longest sequence in the batch (or no padding if only a single + sequence if provided). + - `'max_length'`: Pad to a maximum length specified with the argument `max_length` or to the maximum + acceptable input length for the model if that argument is not provided. + - `False` or `'do_not_pad'` (default): No padding (i.e., can output a batch with sequences of different + lengths). + truncation (`bool`, `str` or [`~tokenization_utils_base.TruncationStrategy`], *optional*, defaults to `False`): + Activates and controls truncation. Accepts the following values: + + - `True` or `'longest_first'`: Truncate to a maximum length specified with the argument `max_length` or + to the maximum acceptable input length for the model if that argument is not provided. This will + truncate token by token, removing a token from the longest sequence in the pair if a pair of + sequences (or a batch of pairs) is provided. + - `'only_first'`: Truncate to a maximum length specified with the argument `max_length` or to the + maximum acceptable input length for the model if that argument is not provided. This will only + truncate the first sequence of a pair if a pair of sequences (or a batch of pairs) is provided. + - `'only_second'`: Truncate to a maximum length specified with the argument `max_length` or to the + maximum acceptable input length for the model if that argument is not provided. This will only + truncate the second sequence of a pair if a pair of sequences (or a batch of pairs) is provided. + - `False` or `'do_not_truncate'` (default): No truncation (i.e., can output batch with sequence lengths + greater than the model maximum admissible input size). + max_length (`int`, *optional*): + Controls the maximum length to use by one of the truncation/padding parameters. + + If left unset or set to `None`, this will use the predefined model maximum length if a maximum length + is required by one of the truncation/padding parameters. If the model has no specific maximum input + length (like XLNet) truncation/padding to a maximum length will be deactivated. + stride (`int`, *optional*, defaults to 0): + If set to a number along with `max_length`, the overflowing tokens returned when + `return_overflowing_tokens=True` will contain some tokens from the end of the truncated sequence + returned to provide some overlap between truncated and overflowing sequences. The value of this + argument defines the number of overlapping tokens. + pad_to_multiple_of (`int`, *optional*): + If set will pad the sequence to a multiple of the provided value. This is especially useful to enable + the use of Tensor Cores on NVIDIA hardware with compute capability >= 7.5 (Volta). + return_tensors (`str` or [`~file_utils.TensorType`], *optional*): + If set, will return tensors instead of list of python integers. Acceptable values are: + + - `'tf'`: Return TensorFlow `tf.constant` objects. + - `'pt'`: Return PyTorch `torch.Tensor` objects. + - `'np'`: Return Numpy `np.ndarray` objects. + return_token_type_ids (`bool`, *optional*): + Whether to return token type IDs. If left to the default, will return the token type IDs according to + the specific tokenizer's default, defined by the `return_outputs` attribute. + + [What are token type IDs?](../glossary#token-type-ids) + return_attention_mask (`bool`, *optional*): + Whether to return the attention mask. If left to the default, will return the attention mask according + to the specific tokenizer's default, defined by the `return_outputs` attribute. + + [What are attention masks?](../glossary#attention-mask) + return_overflowing_tokens (`bool`, *optional*, defaults to `False`): + Whether or not to return overflowing token sequences. If a pair of sequences of input ids (or a batch + of pairs) is provided with `truncation_strategy = longest_first` or `True`, an error is raised instead + of returning overflowing tokens. + return_special_tokens_mask (`bool`, *optional*, defaults to `False`): + Whether or not to return special tokens mask information. + return_offsets_mapping (`bool`, *optional*, defaults to `False`): + Whether or not to return `(char_start, char_end)` for each token. + + This is only available on fast tokenizers inheriting from [`PreTrainedTokenizerFast`], if using + Python's tokenizer, this method will raise `NotImplementedError`. + return_length (`bool`, *optional*, defaults to `False`): + Whether or not to return the lengths of the encoded inputs. + verbose (`bool`, *optional*, defaults to `True`): + Whether or not to print more information and warnings. + **kwargs: passed to the `self.tokenize()` method + + Return: + [`BatchEncoding`]: A [`BatchEncoding`] with the following fields: + + - **input_ids** -- List of token ids to be fed to a model. + + [What are input IDs?](../glossary#input-ids) + + - **bbox** -- List of bounding boxes to be fed to a model. + + - **token_type_ids** -- List of token type ids to be fed to a model (when `return_token_type_ids=True` or + if *"token_type_ids"* is in `self.model_input_names`). + + [What are token type IDs?](../glossary#token-type-ids) + + - **attention_mask** -- List of indices specifying which tokens should be attended to by the model (when + `return_attention_mask=True` or if *"attention_mask"* is in `self.model_input_names`). + + [What are attention masks?](../glossary#attention-mask) + + - **labels** -- List of labels to be fed to a model. (when `word_labels` is specified). + - **overflowing_tokens** -- List of overflowing tokens sequences (when a `max_length` is specified and + `return_overflowing_tokens=True`). + - **num_truncated_tokens** -- Number of tokens truncated (when a `max_length` is specified and + `return_overflowing_tokens=True`). + - **special_tokens_mask** -- List of 0s and 1s, with 1 specifying added special tokens and 0 specifying + regular sequence tokens (when `add_special_tokens=True` and `return_special_tokens_mask=True`). + - **length** -- The length of the inputs (when `return_length=True`). +""" + class LayoutXLMTokenizerFast(PreTrainedTokenizerFast): """