Spaces:
Sleeping
Sleeping
File size: 3,052 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 53 54 55 56 57 58 59 60 61 62 63 64 65 66 |
# coding=utf-8
# Copyright 2020 The Facebook AI Research Team 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.
from ...utils import logging
from ..roberta.tokenization_roberta import RobertaTokenizer
logger = logging.get_logger(__name__)
VOCAB_FILES_NAMES = {"vocab_file": "vocab.json", "merges_file": "merges.txt"}
# See all BART models at https://huggingface.co/models?filter=bart
PRETRAINED_VOCAB_FILES_MAP = {
"vocab_file": {
"facebook/bart-base": "https://huggingface.co/facebook/bart-base/resolve/main/vocab.json",
"facebook/bart-large": "https://huggingface.co/facebook/bart-large/resolve/main/vocab.json",
"facebook/bart-large-mnli": "https://huggingface.co/facebook/bart-large-mnli/resolve/main/vocab.json",
"facebook/bart-large-cnn": "https://huggingface.co/facebook/bart-large-cnn/resolve/main/vocab.json",
"facebook/bart-large-xsum": "https://huggingface.co/facebook/bart-large-xsum/resolve/main/vocab.json",
"yjernite/bart_eli5": "https://huggingface.co/yjernite/bart_eli5/resolve/main/vocab.json",
},
"merges_file": {
"facebook/bart-base": "https://huggingface.co/facebook/bart-base/resolve/main/merges.txt",
"facebook/bart-large": "https://huggingface.co/facebook/bart-large/resolve/main/merges.txt",
"facebook/bart-large-mnli": "https://huggingface.co/facebook/bart-large-mnli/resolve/main/merges.txt",
"facebook/bart-large-cnn": "https://huggingface.co/facebook/bart-large-cnn/resolve/main/merges.txt",
"facebook/bart-large-xsum": "https://huggingface.co/facebook/bart-large-xsum/resolve/main/merges.txt",
"yjernite/bart_eli5": "https://huggingface.co/yjernite/bart_eli5/resolve/main/merges.txt",
},
}
PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
"facebook/bart-base": 1024,
"facebook/bart-large": 1024,
"facebook/bart-large-mnli": 1024,
"facebook/bart-large-cnn": 1024,
"facebook/bart-large-xsum": 1024,
"yjernite/bart_eli5": 1024,
}
class BartTokenizer(RobertaTokenizer):
r"""
Construct a BART tokenizer.
:class:`~transformers.BartTokenizer` is identical to :class:`~transformers.RobertaTokenizer`. Refer to superclass
:class:`~transformers.RobertaTokenizer` for usage examples and documentation concerning the initialization
parameters and other methods.
"""
vocab_files_names = VOCAB_FILES_NAMES
pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES
|