Spaces:
Sleeping
Sleeping
File size: 6,985 Bytes
2260825 |
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 |
# coding=utf-8
# Copyright 2021 The I-BERT Authors (Sehoon Kim, Amir Gholami, Zhewei Yao,
# Michael Mahoney, Kurt Keutzer - UC Berkeley) and The HuggingFace Inc. team.
# Copyright (c) 20121, NVIDIA CORPORATION. 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.
""" I-BERT configuration """
from ...configuration_utils import PretrainedConfig
from ...utils import logging
logger = logging.get_logger(__name__)
IBERT_PRETRAINED_CONFIG_ARCHIVE_MAP = {
"kssteven/ibert-roberta-base": "https://huggingface.co/kssteven/ibert-roberta-base/resolve/main/config.json",
"kssteven/ibert-roberta-large": "https://huggingface.co/kssteven/ibert-roberta-large/resolve/main/config.json",
"kssteven/ibert-roberta-large-mnli": "https://huggingface.co/kssteven/ibert-roberta-large-mnli/resolve/main/config.json",
}
class IBertConfig(PretrainedConfig):
"""
This is the configuration class to store the configuration of a :class:`~transformers.IBertModel`. It is used to
instantiate a I-BERT model according to the specified arguments,
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 I-BERT model. Defines the number of different tokens that can be represented by the
:obj:`inputs_ids` passed when calling :class:`~transformers.IBertModel`
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.IBertModel`
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>`__.
quant_mode (:obj:`bool`, `optional`, defaults to :obj:`False`):
Whether to quantize the model or not.
force_dequant (:obj:`str`, `optional`, defaults to :obj:`"none"`):
Force dequantize specific nonlinear layer. Dequatized layers are then executed with full precision.
:obj:`"none"`, :obj:`"gelu"`, :obj:`"softmax"`, :obj:`"layernorm"` and :obj:`"nonlinear"` are supported. As
deafult, it is set as :obj:`"none"`, which does not dequantize any layers. Please specify :obj:`"gelu"`,
:obj:`"softmax"`, or :obj:`"layernorm"` to dequantize GELU, Softmax, or LayerNorm, respectively.
:obj:`"nonlinear"` will dequantize all nonlinear layers, i.e., GELU, Softmax, and LayerNorm.
"""
model_type = "ibert"
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,
pad_token_id=1,
bos_token_id=0,
eos_token_id=2,
position_embedding_type="absolute",
quant_mode=False,
force_dequant="none",
**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.hidden_size = hidden_size
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.quant_mode = quant_mode
self.force_dequant = force_dequant
|