CSS-LM

1
# coding=utf-8
2
# Copyright 2020 The Allen Institute for AI team and The HuggingFace Inc. team.
3
#
4
# Licensed under the Apache License, Version 2.0 (the "License");
5
# you may not use this file except in compliance with the License.
6
# You may obtain a copy of the License at
7
#
8
#     http://www.apache.org/licenses/LICENSE-2.0
9
#
10
# Unless required by applicable law or agreed to in writing, software
11
# distributed under the License is distributed on an "AS IS" BASIS,
12
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13
# See the License for the specific language governing permissions and
14
# limitations under the License.
15
""" Longformer configuration """
16

17
import logging
18
from typing import List, Union
19

20
from .configuration_roberta import RobertaConfig
21

22

23
logger = logging.getLogger(__name__)
24

25
LONGFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = {
26
    "allenai/longformer-base-4096": "https://s3.amazonaws.com/models.huggingface.co/bert/allenai/longformer-base-4096/config.json",
27
    "allenai/longformer-large-4096": "https://s3.amazonaws.com/models.huggingface.co/bert/allenai/longformer-large-4096/config.json",
28
    "allenai/longformer-large-4096-finetuned-triviaqa": "https://s3.amazonaws.com/models.huggingface.co/bert/allenai/longformer-large-4096-finetuned-triviaqa/config.json",
29
    "allenai/longformer-base-4096-extra.pos.embd.only": "https://s3.amazonaws.com/models.huggingface.co/bert/allenai/longformer-base-4096-extra.pos.embd.only/config.json",
30
    "allenai/longformer-large-4096-extra.pos.embd.only": "https://s3.amazonaws.com/models.huggingface.co/bert/allenai/longformer-large-4096-extra.pos.embd.only/config.json",
31
}
32

33

34
class LongformerConfig(RobertaConfig):
35
    r"""
36
        This is the configuration class to store the configuration of a :class:`~transformers.LongformerModel`.
37
        It is used to instantiate an Longformer model according to the specified arguments, defining the model
38
        architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of
39
        the RoBERTa `roberta-base <https://huggingface.co/roberta-base>`__ architecture with a sequence length 4,096.
40

41
        The :class:`~transformers.LongformerConfig` class directly inherits :class:`~transformers.RobertaConfig`.
42
        It reuses the same defaults. Please check the parent class for more information.
43

44
        Args:
45
            attention_window (:obj:`int` or :obj:`List[int]`, optional, defaults to 512):
46
                Size of an attention window around each token. If :obj:`int`, use the same size for all layers.
47
                To specify a different window size for each layer, use a :obj:`List[int]` where
48
                ``len(attention_window) == num_hidden_layers``.
49

50
        Example::
51

52
            >>> from transformers import LongformerConfig, LongformerModel
53

54
            >>> # Initializing a Longformer configuration
55
            >>> configuration = LongformerConfig()
56

57
            >>> # Initializing a model from the configuration
58
            >>> model = LongformerModel(configuration)
59

60
            >>> # Accessing the model configuration
61
            >>> configuration = model.config
62
    """
63
    model_type = "longformer"
64

65
    def __init__(self, attention_window: Union[List[int], int] = 512, sep_token_id: int = 2, **kwargs):
66
        super().__init__(**kwargs)
67
        self.attention_window = attention_window
68
        self.sep_token_id = sep_token_id
69