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.
145 lines
6.0 KiB
145 lines
6.0 KiB
# Copyright 2020 Ecole Polytechnique 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 the BARThez model."""
|
|
|
|
from tokenizers import Regex, Tokenizer, decoders, normalizers, pre_tokenizers
|
|
from tokenizers.models import Unigram
|
|
|
|
from ...tokenization_python import AddedToken
|
|
from ...tokenization_utils_tokenizers import TokenizersBackend
|
|
from ...utils import logging
|
|
|
|
|
|
logger = logging.get_logger(__name__)
|
|
|
|
VOCAB_FILES_NAMES = {"vocab_file": "sentencepiece.bpe.model", "tokenizer_file": "tokenizer.json"}
|
|
|
|
|
|
SPIECE_UNDERLINE = "▁"
|
|
|
|
|
|
class BarthezTokenizer(TokenizersBackend):
|
|
"""
|
|
Adapted from [`CamembertTokenizer`] and [`BartTokenizer`]. Construct a "fast" BARThez tokenizer. Based on
|
|
[SentencePiece](https://github.com/google/sentencepiece).
|
|
|
|
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:
|
|
bos_token (`str`, *optional*, defaults to `"<s>"`):
|
|
The beginning of sequence token that was used during pretraining. Can be used a sequence classifier token.
|
|
|
|
<Tip>
|
|
|
|
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`.
|
|
|
|
</Tip>
|
|
|
|
eos_token (`str`, *optional*, defaults to `"</s>"`):
|
|
The end of sequence token.
|
|
|
|
<Tip>
|
|
|
|
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`.
|
|
|
|
</Tip>
|
|
|
|
sep_token (`str`, *optional*, defaults to `"</s>"`):
|
|
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.
|
|
cls_token (`str`, *optional*, defaults to `"<s>"`):
|
|
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.
|
|
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.
|
|
pad_token (`str`, *optional*, defaults to `"<pad>"`):
|
|
The token used for padding, for example when batching sequences of different lengths.
|
|
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.
|
|
vocab_file (`str`, *optional*):
|
|
[SentencePiece](https://github.com/google/sentencepiece) file (generally has a *.spm* extension) that
|
|
contains the vocabulary necessary to instantiate a tokenizer.
|
|
vocab (`str`, `dict` or `list`, *optional*):
|
|
Custom vocabulary dictionary. If not provided, vocabulary is loaded from vocab_file.
|
|
add_prefix_space (`bool`, *optional*, defaults to `True`):
|
|
Whether or not to add an initial space to the input. This allows to treat the leading word just as any
|
|
other word.
|
|
"""
|
|
|
|
vocab_files_names = VOCAB_FILES_NAMES
|
|
model_input_names = ["input_ids", "attention_mask"]
|
|
slow_tokenizer_class = None
|
|
|
|
def __init__(
|
|
self,
|
|
vocab: str | dict | list | None = None,
|
|
bos_token="<s>",
|
|
eos_token="</s>",
|
|
sep_token="</s>",
|
|
cls_token="<s>",
|
|
unk_token="<unk>",
|
|
pad_token="<pad>",
|
|
mask_token="<mask>",
|
|
add_prefix_space=True,
|
|
**kwargs,
|
|
):
|
|
# Mask token behave like a normal word, i.e. include the space before it
|
|
mask_token = AddedToken(mask_token, lstrip=True, rstrip=False) if isinstance(mask_token, str) else mask_token
|
|
self.add_prefix_space = add_prefix_space
|
|
|
|
if vocab is not None:
|
|
self._vocab = vocab
|
|
else:
|
|
self._vocab = [
|
|
(str(pad_token), 0.0),
|
|
(str(unk_token), 0.0),
|
|
(str(cls_token), 0.0),
|
|
(str(sep_token), 0.0),
|
|
(str(mask_token), 0.0),
|
|
]
|
|
|
|
self._tokenizer = Tokenizer(Unigram(self._vocab, unk_id=3, byte_fallback=False))
|
|
|
|
self._tokenizer.normalizer = normalizers.Sequence(
|
|
[
|
|
normalizers.Replace(Regex(r"\s{2,}|[\n\r\t]"), " "),
|
|
normalizers.NFC(),
|
|
normalizers.Strip(left=False, right=True),
|
|
]
|
|
)
|
|
prepend_scheme = "always" if add_prefix_space else "never"
|
|
self._tokenizer.pre_tokenizer = pre_tokenizers.Metaspace(replacement="▁", prepend_scheme=prepend_scheme)
|
|
self._tokenizer.decoder = decoders.Metaspace(replacement="▁", prepend_scheme=prepend_scheme)
|
|
|
|
super().__init__(
|
|
bos_token=bos_token,
|
|
eos_token=eos_token,
|
|
unk_token=unk_token,
|
|
sep_token=sep_token,
|
|
cls_token=cls_token,
|
|
pad_token=pad_token,
|
|
mask_token=mask_token,
|
|
add_prefix_space=add_prefix_space,
|
|
**kwargs,
|
|
)
|
|
|
|
|
|
__all__ = ["BarthezTokenizer"]
|