/usr/local/lib/python3.6/site-packages/transformers/models/led
Edit: /usr/local/lib/python3.6/site-packages/transformers/models/led/tokenization_led.py (3885B)
# 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 typing import Dict, Optional, Union
from ...tokenization_utils_base import BatchEncoding, EncodedInput
from ...utils import PaddingStrategy, 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.
[`LEDTokenizer`] is identical to [`BartTokenizer`] and runs end-to-end tokenization: punctuation splitting and
wordpiece.
Refer to superclass [`BartTokenizer`] for usage examples and documentation concerning parameters.
"""
pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES
def _pad(
self,
encoded_inputs: Union[Dict[str, EncodedInput], BatchEncoding],
max_length: Optional[int] = None,
padding_strategy: PaddingStrategy = PaddingStrategy.DO_NOT_PAD,
pad_to_multiple_of: Optional[int] = None,
return_attention_mask: Optional[bool] = None,
) -> dict:
encoded_inputs = super()._pad(
encoded_inputs=encoded_inputs,
max_length=max_length,
padding_strategy=padding_strategy,
pad_to_multiple_of=pad_to_multiple_of,
return_attention_mask=return_attention_mask,
)
# Load from model defaults
if return_attention_mask is None:
return_attention_mask = "attention_mask" in self.model_input_names
if return_attention_mask and "global_attention_mask" in encoded_inputs:
required_input = encoded_inputs[self.model_input_names[0]]
# `global_attention_mask` need to have the same length as other (sequential) inputs.
needs_to_be_padded = len(encoded_inputs["global_attention_mask"]) != len(required_input)
if needs_to_be_padded:
difference = len(required_input) - len(encoded_inputs["global_attention_mask"])
if self.padding_side == "right":
# Use `-1` since `0` in `global_attention_mask` means `local attention` instead of `not to attend`
encoded_inputs["global_attention_mask"] = (
encoded_inputs["global_attention_mask"] + [-1] * difference
)
elif self.padding_side == "left":
encoded_inputs["global_attention_mask"] = [-1] * difference + encoded_inputs[
"global_attention_mask"
]
else:
raise ValueError("Invalid padding strategy:" + str(self.padding_side))
return encoded_inputs