File size: 7,240 Bytes
d1ceb73 |
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 |
# coding=utf-8
# Copyright The HuggingFace Team 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.
"""RemBERT model configuration"""
from collections import OrderedDict
from typing import Mapping
from ...configuration_utils import PretrainedConfig
from ...onnx import OnnxConfig
from ...utils import logging
logger = logging.get_logger(__name__)
class RemBertConfig(PretrainedConfig):
r"""
This is the configuration class to store the configuration of a [`RemBertModel`]. It is used to instantiate an
RemBERT 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 RemBERT
[google/rembert](https://huggingface.co/google/rembert) architecture.
Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
documentation from [`PretrainedConfig`] for more information.
Args:
vocab_size (`int`, *optional*, defaults to 250300):
Vocabulary size of the RemBERT model. Defines the number of different tokens that can be represented by the
`inputs_ids` passed when calling [`RemBertModel`] or [`TFRemBertModel`]. Vocabulary size of the model.
Defines the different tokens that can be represented by the *inputs_ids* passed to the forward method of
[`RemBertModel`].
hidden_size (`int`, *optional*, defaults to 1152):
Dimensionality of the encoder layers and the pooler layer.
num_hidden_layers (`int`, *optional*, defaults to 32):
Number of hidden layers in the Transformer encoder.
num_attention_heads (`int`, *optional*, defaults to 18):
Number of attention heads for each attention layer in the Transformer encoder.
input_embedding_size (`int`, *optional*, defaults to 256):
Dimensionality of the input embeddings.
output_embedding_size (`int`, *optional*, defaults to 1664):
Dimensionality of the output embeddings.
intermediate_size (`int`, *optional*, defaults to 4608):
Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder.
hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`):
The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
`"relu"`, `"selu"` and `"gelu_new"` are supported.
hidden_dropout_prob (`float`, *optional*, defaults to 0):
The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
attention_probs_dropout_prob (`float`, *optional*, defaults to 0):
The dropout ratio for the attention probabilities.
classifier_dropout_prob (`float`, *optional*, defaults to 0.1):
The dropout ratio for the classifier layer when fine-tuning.
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 [`RemBertModel`] or [`TFRemBertModel`].
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.
is_decoder (`bool`, *optional*, defaults to `False`):
Whether the model is used as a decoder or not. If `False`, the model is used as an encoder.
use_cache (`bool`, *optional*, defaults to `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`.
Example:
```python
>>> from transformers import RemBertModel, RemBertConfig
>>> # Initializing a RemBERT rembert style configuration
>>> configuration = RemBertConfig()
>>> # Initializing a model from the rembert style configuration
>>> model = RemBertModel(configuration)
>>> # Accessing the model configuration
>>> configuration = model.config
```"""
model_type = "rembert"
def __init__(
self,
vocab_size=250300,
hidden_size=1152,
num_hidden_layers=32,
num_attention_heads=18,
input_embedding_size=256,
output_embedding_size=1664,
intermediate_size=4608,
hidden_act="gelu",
hidden_dropout_prob=0.0,
attention_probs_dropout_prob=0.0,
classifier_dropout_prob=0.1,
max_position_embeddings=512,
type_vocab_size=2,
initializer_range=0.02,
layer_norm_eps=1e-12,
use_cache=True,
pad_token_id=0,
bos_token_id=312,
eos_token_id=313,
**kwargs,
):
super().__init__(pad_token_id=pad_token_id, bos_token_id=bos_token_id, eos_token_id=eos_token_id, **kwargs)
self.vocab_size = vocab_size
self.input_embedding_size = input_embedding_size
self.output_embedding_size = output_embedding_size
self.max_position_embeddings = max_position_embeddings
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.classifier_dropout_prob = classifier_dropout_prob
self.initializer_range = initializer_range
self.type_vocab_size = type_vocab_size
self.layer_norm_eps = layer_norm_eps
self.use_cache = use_cache
self.tie_word_embeddings = False
class RemBertOnnxConfig(OnnxConfig):
@property
def inputs(self) -> Mapping[str, Mapping[int, str]]:
if self.task == "multiple-choice":
dynamic_axis = {0: "batch", 1: "choice", 2: "sequence"}
else:
dynamic_axis = {0: "batch", 1: "sequence"}
return OrderedDict(
[
("input_ids", dynamic_axis),
("attention_mask", dynamic_axis),
("token_type_ids", dynamic_axis),
]
)
@property
def atol_for_validation(self) -> float:
return 1e-4
|