master
/ transformers / models / deberta / configuration_deberta.py

configuration_deberta.py @3c11360 — raw · history · blame 

  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
# coding=utf-8
# Copyright 2020, Microsoft 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.
""" DeBERTa model configuration """

from ...configuration_utils import PretrainedConfig
from ...utils import logging


logger = logging.get_logger(__name__)

DEBERTA_PRETRAINED_CONFIG_ARCHIVE_MAP = {
    "microsoft/deberta-base": "https://huggingface.co/microsoft/deberta-base/resolve/main/config.json",
    "microsoft/deberta-large": "https://huggingface.co/microsoft/deberta-large/resolve/main/config.json",
    "microsoft/deberta-xlarge": "https://huggingface.co/microsoft/deberta-xlarge/resolve/main/config.json",
    "microsoft/deberta-base-mnli": "https://huggingface.co/microsoft/deberta-base-mnli/resolve/main/config.json",
    "microsoft/deberta-large-mnli": "https://huggingface.co/microsoft/deberta-large-mnli/resolve/main/config.json",
    "microsoft/deberta-xlarge-mnli": "https://huggingface.co/microsoft/deberta-xlarge-mnli/resolve/main/config.json",
}


class DebertaConfig(PretrainedConfig):
    r"""
    This is the configuration class to store the configuration of a [`DebertaModel`] or a
    [`TFDebertaModel`]. It is used to instantiate a DeBERTa 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 DeBERTa [microsoft/deberta-base](https://huggingface.co/microsoft/deberta-base)
    architecture.

    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model
    outputs. Read the documentation from [`PretrainedConfig`] for more information.

    Arguments:
        vocab_size (`int`, *optional*, defaults to 30522):
            Vocabulary size of the DeBERTa model. Defines the number of different tokens that can be represented by the
            `inputs_ids` passed when calling [`DebertaModel`] or
            [`TFDebertaModel`].
        hidden_size (`int`, *optional*, defaults to 768):
            Dimensionality of the encoder layers and the pooler layer.
        num_hidden_layers (`int`, *optional*, defaults to 12):
            Number of hidden layers in the Transformer encoder.
        num_attention_heads (`int`, *optional*, defaults to 12):
            Number of attention heads for each attention layer in the Transformer encoder.
        intermediate_size (`int`, *optional*, defaults to 3072):
            Dimensionality of the "intermediate" (often named feed-forward) layer in the Transformer encoder.
        hidden_act (`str` or `Callable`, *optional*, defaults to `"gelu"`):
            The non-linear activation function (function or string) in the encoder and pooler. If string,
            `"gelu"`, `"relu"`, `"silu"`, `"gelu"`, `"tanh"`, `"gelu_fast"`,
            `"mish"`, `"linear"`, `"sigmoid"` and `"gelu_new"` are supported.
        hidden_dropout_prob (`float`, *optional*, defaults to 0.1):
            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
        attention_probs_dropout_prob (`float`, *optional*, defaults to 0.1):
            The dropout ratio for the attention probabilities.
        max_position_embeddings (`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 (`int`, *optional*, defaults to 2):
            The vocabulary size of the `token_type_ids` passed when calling [`DebertaModel`] or
            [`TFDebertaModel`].
        initializer_range (`float`, *optional*, defaults to 0.02):
            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
        layer_norm_eps (`float`, *optional*, defaults to 1e-12):
            The epsilon used by the layer normalization layers.
        relative_attention (`bool`, *optional*, defaults to `False`):
            Whether use relative position encoding.
        max_relative_positions (`int`, *optional*, defaults to 1):
            The range of relative positions `[-max_position_embeddings, max_position_embeddings]`. Use the same
            value as `max_position_embeddings`.
        pad_token_id (`int`, *optional*, defaults to 0):
            The value used to pad input_ids.
        position_biased_input (`bool`, *optional*, defaults to `True`):
            Whether add absolute position embedding to content embedding.
        pos_att_type (`List[str]`, *optional*):
            The type of relative position attention, it can be a combination of `["p2c", "c2p"]`, e.g.
            `["p2c"]`, `["p2c", "c2p"]`.
        layer_norm_eps (`float`, optional, defaults to 1e-12):
            The epsilon used by the layer normalization layers.
    """
    model_type = "deberta"

    def __init__(
        self,
        vocab_size=50265,
        hidden_size=768,
        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=0,
        initializer_range=0.02,
        layer_norm_eps=1e-7,
        relative_attention=False,
        max_relative_positions=-1,
        pad_token_id=0,
        position_biased_input=True,
        pos_att_type=None,
        pooler_dropout=0,
        pooler_hidden_act="gelu",
        **kwargs
    ):
        super().__init__(**kwargs)

        self.hidden_size = hidden_size
        self.num_hidden_layers = num_hidden_layers
        self.num_attention_heads = num_attention_heads
        self.intermediate_size = intermediate_size
        self.hidden_act = hidden_act
        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.relative_attention = relative_attention
        self.max_relative_positions = max_relative_positions
        self.pad_token_id = pad_token_id
        self.position_biased_input = position_biased_input

        # Backwards compatibility
        if type(pos_att_type) == str:
            pos_att_type = [x.strip() for x in pos_att_type.lower().split("|")]

        self.pos_att_type = pos_att_type
        self.vocab_size = vocab_size
        self.layer_norm_eps = layer_norm_eps

        self.pooler_hidden_size = kwargs.get("pooler_hidden_size", hidden_size)
        self.pooler_dropout = pooler_dropout
        self.pooler_hidden_act = pooler_hidden_act