Source code for transformers.models.reformer.tokenization_reformer_fast
# coding=utf-8
# Copyright 2020 The Trax Authors 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 class for model Reformer."""
import os
from shutil import copyfile
from typing import Optional, Tuple
from ...file_utils import is_sentencepiece_available
from ...tokenization_utils_fast import PreTrainedTokenizerFast
from ...utils import logging
if is_sentencepiece_available():
from .tokenization_reformer import ReformerTokenizer
else:
ReformerTokenizer = None
logger = logging.get_logger(__name__)
SPIECE_UNDERLINE = "▁"
VOCAB_FILES_NAMES = {"vocab_file": "spiece.model", "tokenizer_file": "tokenizer.json"}
PRETRAINED_VOCAB_FILES_MAP = {
"vocab_file": {
"google/reformer-crime-and-punishment": "https://huggingface.co/google/reformer-crime-and-punishment/resolve/main/spiece.model"
},
"tokenizer_file": {
"google/reformer-crime-and-punishment": "https://huggingface.co/google/reformer-crime-and-punishment/resolve/main/tokenizer.json"
},
}
PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
"google/reformer-crime-and-punishment": 524288,
}
[docs]class ReformerTokenizerFast(PreTrainedTokenizerFast):
"""
Construct a "fast" Reformer tokenizer (backed by HuggingFace's `tokenizers` library). Based on `Unigram
<https://huggingface.co/docs/tokenizers/python/latest/components.html?highlight=unigram#models>`__.
This tokenizer inherits from :class:`~transformers.PreTrainedTokenizerFast` which contains most of the main
methods. Users should refer to this superclass for more information regarding those methods.
Args:
vocab_file (:obj:`str`):
`SentencePiece <https://github.com/google/sentencepiece>`__ file (generally has a `.spm` extension) that
contains the vocabulary necessary to instantiate a tokenizer.
eos_token (:obj:`str`, `optional`, defaults to :obj:`"</s>"`):
The end of sequence token.
.. note::
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 :obj:`sep_token`.
unk_token (:obj:`str`, `optional`, defaults to :obj:`"<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 (:obj:`str`, `optional`, defaults to :obj:`"<pad>"`):
The token used for padding, for example when batching sequences of different lengths.
additional_special_tokens (:obj:`List[str]`, `optional`):
Additional special tokens used by the tokenizer.
"""
vocab_files_names = VOCAB_FILES_NAMES
pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES
model_input_names = ["input_ids", "attention_mask"]
slow_tokenizer_class = ReformerTokenizer
def __init__(
self,
vocab_file,
tokenizer_file=None,
eos_token="</s>",
unk_token="<unk>",
additional_special_tokens=[],
**kwargs
):
super().__init__(
vocab_file,
tokenizer_file=tokenizer_file,
eos_token=eos_token,
unk_token=unk_token,
additional_special_tokens=additional_special_tokens,
**kwargs,
)
self.vocab_file = vocab_file
[docs] def save_vocabulary(self, save_directory: str, filename_prefix: Optional[str] = None) -> Tuple[str]:
if not os.path.isdir(save_directory):
logger.error("Vocabulary path ({}) should be a directory".format(save_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,)