File size: 7,868 Bytes
0e5d19e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
65d5357
0e5d19e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0d45d88
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
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
# coding=utf-8
# 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.
""" HAT configuration"""
from collections import OrderedDict
from typing import Mapping

from transformers.onnx import OnnxConfig
from transformers.utils import logging
from transformers import PretrainedConfig


logger = logging.get_logger(__name__)

HAT_PRETRAINED_CONFIG_ARCHIVE_MAP = {
    "kiddothe2b/hierarchical-transformer-base-4096": "https://huggingface.co/kiddothe2b/hierarchical-transformer-base-4096/resolve/main/config.json",
    "kiddothe2b/adhoc-hierarchical-transformer-base-4096": "https://huggingface.co/kiddothe2b/adhoc-hierarchical-transformer-base-4096/resolve/main/config.json",
}


class HATConfig(PretrainedConfig):
    r"""
    This is the configuration class to store the configuration of a :class:`~transformers.HAT`.
    It is used to instantiate a HAT model according to the specified arguments,
    defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration
    to that of the HAT `kiddothe2b/hierarchical-transformer-base-4096
    <https://huggingface.co/kiddothe2b/hierarchical-transformer-base-4096>`__ architecture.

    Configuration objects inherit from :class:`~transformers.PretrainedConfig` and can be used to control the model
    outputs. Read the documentation from :class:`~transformers.PretrainedConfig` for more information.


    Args:
        vocab_size (:obj:`int`, `optional`, defaults to 30522):
            Vocabulary size of the BERT model. Defines the number of different tokens that can be represented by the
            :obj:`inputs_ids` passed when calling :class:`~transformers.BertModel` or
            :class:`~transformers.TFBertModel`.
        max_sentences (:obj:`int`, `optional`, defaults to 64):
            The maximum number of sentences that this model might ever be used with.
        max_sentence_size (:obj:`int`, `optional`, defaults to 128):
            The maximum sentence length that this model might ever be used with.
        model_max_length (:obj:`int`, `optional`, defaults to 8192):
            The maximum  sequence length (max_sentences * max_sentence_size) that this model might ever be used with
        encoder_layout (:obj:`Dict`):
            The sentence/document encoder layout.
        hidden_size (:obj:`int`, `optional`, defaults to 768):
            Dimensionality of the encoder layers and the pooler layer.
        num_hidden_layers (:obj:`int`, `optional`, defaults to 12):
            Number of hidden layers in the Transformer encoder.
        num_attention_heads (:obj:`int`, `optional`, defaults to 12):
            Number of attention heads for each attention layer in the Transformer encoder.
        intermediate_size (:obj:`int`, `optional`, defaults to 3072):
            Dimensionality of the "intermediate" (often named feed-forward) layer in the Transformer encoder.
        hidden_act (:obj:`str` or :obj:`Callable`, `optional`, defaults to :obj:`"gelu"`):
            The non-linear activation function (function or string) in the encoder and pooler. If string,
            :obj:`"gelu"`, :obj:`"relu"`, :obj:`"silu"` and :obj:`"gelu_new"` are supported.
        hidden_dropout_prob (:obj:`float`, `optional`, defaults to 0.1):
            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
        attention_probs_dropout_prob (:obj:`float`, `optional`, defaults to 0.1):
            The dropout ratio for the attention probabilities.
        max_position_embeddings (:obj:`int`, `optional`, defaults to 512):
            The maximum sequence length that this model might ever be used with. Typically set this to something large
            just in case (e.g., 512 or 1024 or 2048).
        type_vocab_size (:obj:`int`, `optional`, defaults to 2):
            The vocabulary size of the :obj:`token_type_ids` passed when calling :class:`~transformers.BertModel` or
            :class:`~transformers.TFBertModel`.
        initializer_range (:obj:`float`, `optional`, defaults to 0.02):
            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
        layer_norm_eps (:obj:`float`, `optional`, defaults to 1e-12):
            The epsilon used by the layer normalization layers.
        position_embedding_type (:obj:`str`, `optional`, defaults to :obj:`"absolute"`):
            Type of position embedding. Choose one of :obj:`"absolute"`, :obj:`"relative_key"`,
            :obj:`"relative_key_query"`. For positional embeddings use :obj:`"absolute"`. For more information on
            :obj:`"relative_key"`, please refer to `Self-Attention with Relative Position Representations (Shaw et al.)
            <https://arxiv.org/abs/1803.02155>`__. For more information on :obj:`"relative_key_query"`, please refer to
            `Method 4` in `Improve Transformer Models with Better Relative Position Embeddings (Huang et al.)
            <https://arxiv.org/abs/2009.13658>`__.
        use_cache (:obj:`bool`, `optional`, defaults to :obj:`True`):
            Whether or not the model should return the last key/values attentions (not used by all models). Only
            relevant if ``config.is_decoder=True``.
        classifier_dropout (:obj:`float`, `optional`):
            The dropout ratio for the classification head.
    """
    model_type = "hi-transformer"

    def __init__(
        self,
        vocab_size=30522,
        hidden_size=768,
        max_sentences=64,
        max_sentence_size=128,
        model_max_length=8192,
        num_hidden_layers=12,
        num_attention_heads=12,
        intermediate_size=3072,
        hidden_act="gelu",
        hidden_dropout_prob=0.1,
        attention_probs_dropout_prob=0.1,
        max_position_embeddings=512,
        type_vocab_size=2,
        initializer_range=0.02,
        layer_norm_eps=1e-12,
        pad_token_id=0,
        position_embedding_type="absolute",
        encoder_layout=None,
        use_cache=True,
        classifier_dropout=None,
        **kwargs
    ):
        super().__init__(pad_token_id=pad_token_id, **kwargs)

        self.vocab_size = vocab_size
        self.hidden_size = hidden_size
        self.max_sentences = max_sentences
        self.max_sentence_size = max_sentence_size
        self.model_max_length = model_max_length
        self.encoder_layout = encoder_layout
        self.num_hidden_layers = num_hidden_layers
        self.num_attention_heads = num_attention_heads
        self.hidden_act = hidden_act
        self.intermediate_size = intermediate_size
        self.hidden_dropout_prob = hidden_dropout_prob
        self.attention_probs_dropout_prob = attention_probs_dropout_prob
        self.max_position_embeddings = max_position_embeddings
        self.type_vocab_size = type_vocab_size
        self.initializer_range = initializer_range
        self.layer_norm_eps = layer_norm_eps
        self.position_embedding_type = position_embedding_type
        self.use_cache = use_cache
        self.classifier_dropout = classifier_dropout


class HATOnnxConfig(OnnxConfig):
    @property
    def inputs(self) -> Mapping[str, Mapping[int, str]]:
        return OrderedDict(
            [
                ("input_ids", {0: "batch", 1: "sequence"}),
                ("attention_mask", {0: "batch", 1: "sequence"}),
            ]
        )