You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
63 lines
3.2 KiB
63 lines
3.2 KiB
# Copyright 2024 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 FNet model."""
|
|
|
|
from ...utils import logging
|
|
from ..albert.tokenization_albert import AlbertTokenizer
|
|
|
|
|
|
logger = logging.get_logger(__name__)
|
|
|
|
|
|
class FNetTokenizer(AlbertTokenizer):
|
|
"""
|
|
Construct an FNet tokenizer. Based on [Unigram](https://huggingface.co/docs/tokenizers/python/latest/components.html?highlight=unigram#models).
|
|
|
|
This tokenizer inherits from [`AlbertTokenizer`] which contains most of the main methods. Users should refer to
|
|
this superclass for more information regarding those methods.
|
|
|
|
Args:
|
|
do_lower_case (`bool`, *optional*, defaults to `True`):
|
|
Whether or not to lowercase the input when tokenizing.
|
|
keep_accents (`bool`, *optional*, defaults to `False`):
|
|
Whether or not to keep accents when tokenizing.
|
|
bos_token (`str`, *optional*, defaults to `"[CLS]"`):
|
|
The beginning of sequence token that was used during pretraining. Can be used a sequence classifier token.
|
|
eos_token (`str`, *optional*, defaults to `"[SEP]"`):
|
|
The end of sequence 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.
|
|
"""
|
|
|
|
model_input_names = ["input_ids", "token_type_ids"]
|
|
|
|
|
|
# FNetTokenizerFast is an alias for FNetTokenizer (since AlbertTokenizer is already a fast tokenizer)
|
|
FNetTokenizerFast = FNetTokenizer
|
|
|
|
__all__ = ["FNetTokenizer", "FNetTokenizerFast"]
|