Spaces:
Sleeping
Sleeping
File size: 6,228 Bytes
1ce5e18 |
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 |
# coding=utf-8
# Copyright 2020 The Google AI Language Team Authors 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.
""" BertGeneration model configuration"""
from ...configuration_utils import PretrainedConfig
class BertGenerationConfig(PretrainedConfig):
r"""
This is the configuration class to store the configuration of a [`BertGenerationPreTrainedModel`]. It is used to
instantiate a BertGeneration 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 BertGeneration
[google/bert_for_seq_generation_L-24_bbc_encoder](https://huggingface.co/google/bert_for_seq_generation_L-24_bbc_encoder)
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 50358):
Vocabulary size of the BERT model. Defines the number of different tokens that can be represented by the
`inputs_ids` passed when calling [`BertGeneration`].
hidden_size (`int`, *optional*, defaults to 1024):
Dimensionality of the encoder layers and the pooler layer.
num_hidden_layers (`int`, *optional*, defaults to 24):
Number of hidden layers in the Transformer encoder.
num_attention_heads (`int`, *optional*, defaults to 16):
Number of attention heads for each attention layer in the Transformer encoder.
intermediate_size (`int`, *optional*, defaults to 3072):
Dimensionality of the "intermediate" (often called 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"`, `"silu"` 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).
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.
position_embedding_type (`str`, *optional*, defaults to `"absolute"`):
Type of position embedding. Choose one of `"absolute"`, `"relative_key"`, `"relative_key_query"`. For
positional embeddings use `"absolute"`. For more information on `"relative_key"`, please refer to
[Self-Attention with Relative Position Representations (Shaw et al.)](https://arxiv.org/abs/1803.02155).
For more information on `"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).
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 BertGenerationConfig, BertGenerationEncoder
>>> # Initializing a BertGeneration config
>>> configuration = BertGenerationConfig()
>>> # Initializing a model (with random weights) from the config
>>> model = BertGenerationEncoder(configuration)
>>> # Accessing the model configuration
>>> configuration = model.config
```"""
model_type = "bert-generation"
def __init__(
self,
vocab_size=50358,
hidden_size=1024,
num_hidden_layers=24,
num_attention_heads=16,
intermediate_size=4096,
hidden_act="gelu",
hidden_dropout_prob=0.1,
attention_probs_dropout_prob=0.1,
max_position_embeddings=512,
initializer_range=0.02,
layer_norm_eps=1e-12,
pad_token_id=0,
bos_token_id=2,
eos_token_id=1,
position_embedding_type="absolute",
use_cache=True,
**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.initializer_range = initializer_range
self.layer_norm_eps = layer_norm_eps
self.position_embedding_type = position_embedding_type
self.use_cache = use_cache
|