124 lines
5.7 KiB
Python
124 lines
5.7 KiB
Python
# coding=utf-8
|
|
# Copyright 2021 NVIDIA Corporation and The HuggingFace 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.
|
|
""" QDQBERT model configuration"""
|
|
|
|
from ...configuration_utils import PretrainedConfig
|
|
from ...utils import logging
|
|
|
|
|
|
logger = logging.get_logger(__name__)
|
|
|
|
|
|
from ..deprecated._archive_maps import QDQBERT_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402
|
|
|
|
|
|
class QDQBertConfig(PretrainedConfig):
|
|
r"""
|
|
This is the configuration class to store the configuration of a [`QDQBertModel`]. It is used to instantiate an
|
|
QDQBERT 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 BERT
|
|
[google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) 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 30522):
|
|
Vocabulary size of the QDQBERT model. Defines the number of different tokens that can be represented by the
|
|
`inputs_ids` passed when calling [`QDQBertModel`].
|
|
hidden_size (`int`, *optional*, defaults to 768):
|
|
Dimension 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):
|
|
Dimension 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 0.1):
|
|
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 [`QDQBertModel`].
|
|
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`.
|
|
|
|
Examples:
|
|
|
|
```python
|
|
>>> from transformers import QDQBertModel, QDQBertConfig
|
|
|
|
>>> # Initializing a QDQBERT google-bert/bert-base-uncased style configuration
|
|
>>> configuration = QDQBertConfig()
|
|
|
|
>>> # Initializing a model from the google-bert/bert-base-uncased style configuration
|
|
>>> model = QDQBertModel(configuration)
|
|
|
|
>>> # Accessing the model configuration
|
|
>>> configuration = model.config
|
|
```"""
|
|
|
|
model_type = "qdqbert"
|
|
|
|
def __init__(
|
|
self,
|
|
vocab_size=30522,
|
|
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=2,
|
|
initializer_range=0.02,
|
|
layer_norm_eps=1e-12,
|
|
use_cache=True,
|
|
pad_token_id=1,
|
|
bos_token_id=0,
|
|
eos_token_id=2,
|
|
**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.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.initializer_range = initializer_range
|
|
self.type_vocab_size = type_vocab_size
|
|
self.layer_norm_eps = layer_norm_eps
|
|
self.use_cache = use_cache
|