Spaces:
Sleeping
Sleeping
File size: 1,864 Bytes
2260825 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 |
# coding=utf-8
# Copyright 2021 Iz Beltagy, Matthew E. Peters, Arman Cohan and The HuggingFace Inc. team. All rights reserved.
#
# 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 LED."""
from ...utils import logging
from ..bart.tokenization_bart import BartTokenizer
logger = logging.get_logger(__name__)
PRETRAINED_VOCAB_FILES_MAP = {
"vocab_file": {
"allenai/led-base-16384": "https://huggingface.co/allenai/led-base-16384/resolve/main/vocab.json",
},
"merges_file": {
"allenai/led-base-16384": "https://huggingface.co/allenai/led-base-16384/resolve/main/merges.txt",
},
"tokenizer_file": {
"allenai/led-base-16384": "https://huggingface.co/allenai/led-base-16384/resolve/main/tokenizer.json",
},
}
PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
"allenai/led-base-16384": 16384,
}
class LEDTokenizer(BartTokenizer):
"""
Construct a LED tokenizer.
:class:`~transformers.LEDTokenizer` is identical to :class:`~transformers.BartTokenizer` and runs end-to-end
tokenization: punctuation splitting and wordpiece.
Refer to superclass :class:`~transformers.BartTokenizer` for usage examples and documentation concerning
parameters.
"""
pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES
|