File size: 8,727 Bytes
b49751a |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 |
from transformers.configuration_utils import PretrainedConfig
class BertConfig(PretrainedConfig):
r"""
This is the configuration class to store the configuration of a :class:`~transformers.ElectraModel` or a
:class:`~transformers.TFElectraModel`. It is used to instantiate a ELECTRA 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 ELECTRA `google/electra-small-discriminator
<https://huggingface.co/google/electra-small-discriminator>`__ 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 ELECTRA model. Defines the number of different tokens that can be represented by the
:obj:`inputs_ids` passed when calling :class:`~transformers.ElectraModel` or
:class:`~transformers.TFElectraModel`.
embedding_size (:obj:`int`, `optional`, defaults to 128):
Dimensionality of the encoder layers and the pooler layer.
hidden_size (:obj:`int`, `optional`, defaults to 256):
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 4):
Number of attention heads for each attention layer in the Transformer encoder.
intermediate_size (:obj:`int`, `optional`, defaults to 1024):
Dimensionality of the "intermediate" (i.e., 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.ElectraModel` or
:class:`~transformers.TFElectraModel`.
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.
summary_type (:obj:`str`, `optional`, defaults to :obj:`"first"`):
Argument used when doing sequence summary. Used in the sequence classification and multiple choice models.
Has to be one of the following options:
- :obj:`"last"`: Take the last token hidden state (like XLNet).
- :obj:`"first"`: Take the first token hidden state (like BERT).
- :obj:`"mean"`: Take the mean of all tokens hidden states.
- :obj:`"cls_index"`: Supply a Tensor of classification token position (like GPT/GPT-2).
- :obj:`"attn"`: Not implemented now, use multi-head attention.
summary_use_proj (:obj:`bool`, `optional`, defaults to :obj:`True`):
Argument used when doing sequence summary. Used in the sequence classification and multiple choice models.
Whether or not to add a projection after the vector extraction.
summary_activation (:obj:`str`, `optional`):
Argument used when doing sequence summary. Used in the sequence classification and multiple choice models.
Pass :obj:`"gelu"` for a gelu activation to the output, any other value will result in no activation.
summary_last_dropout (:obj:`float`, `optional`, defaults to 0.0):
Argument used when doing sequence summary. Used in the sequence classification and multiple choice models.
The dropout ratio to be used after the projection and activation.
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>`__.
classifier_dropout (:obj:`float`, `optional`):
The dropout ratio for the classification head.
Examples::
>>> from transformers import ElectraModel, ElectraConfig
>>> # Initializing a ELECTRA electra-base-uncased style configuration
>>> configuration = ElectraConfig()
>>> # Initializing a model from the electra-base-uncased style configuration
>>> model = ElectraModel(configuration)
>>> # Accessing the model configuration
>>> configuration = model.config
"""
model_type = "bert"
def __init__(
self,
vocab_size=30522,
embedding_size=128,
hidden_size=256,
num_hidden_layers=12,
num_attention_heads=4,
intermediate_size=1024,
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,
summary_type="first",
summary_use_proj=True,
summary_activation="gelu",
summary_last_dropout=0.1,
pad_token_id=0,
position_embedding_type="absolute",
classifier_dropout=None,
prenorm=False,
mup=False,
embedding_norm_layer_type="layer_norm",
embedding_num_groups=1,
attn_norm_layer_type="layer_norm",
attn_num_groups=1,
output_mult=1,
readout_zero_init=False,
query_zero_init=False,
**kwargs,
):
super().__init__(pad_token_id=pad_token_id, **kwargs)
self.vocab_size = vocab_size
self.embedding_size = embedding_size
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.layer_norm_eps = layer_norm_eps
# passing in 1e-x in config turns to string
if isinstance(self.layer_norm_eps, str):
self.layer_norm_eps = float(self.layer_norm_eps)
self.summary_type = summary_type
self.summary_use_proj = summary_use_proj
self.summary_activation = summary_activation
self.summary_last_dropout = summary_last_dropout
self.position_embedding_type = position_embedding_type
self.classifier_dropout = classifier_dropout
# transformers without tears suggests using prenorm
self.prenorm = prenorm
self.mup = mup
self.embedding_norm_layer_type = embedding_norm_layer_type
self.embedding_num_groups = embedding_num_groups
self.attn_norm_layer_type = attn_norm_layer_type
self.attn_num_groups = attn_num_groups
self.output_mult = output_mult
self.readout_zero_init = readout_zero_init
self.query_zero_init = query_zero_init
|