File size: 8,719 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 |
# coding=utf-8
# Copyright 2021 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.
"""OpenAI ImageGPT configuration"""
from collections import OrderedDict
from typing import TYPE_CHECKING, Any, Mapping, Optional
from ...configuration_utils import PretrainedConfig
from ...onnx import OnnxConfig
from ...utils import logging
if TYPE_CHECKING:
from ... import FeatureExtractionMixin, TensorType
logger = logging.get_logger(__name__)
class ImageGPTConfig(PretrainedConfig):
"""
This is the configuration class to store the configuration of a [`ImageGPTModel`] or a [`TFImageGPTModel`]. It is
used to instantiate a GPT-2 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 ImageGPT
[openai/imagegpt-small](https://huggingface.co/openai/imagegpt-small) 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 512):
Vocabulary size of the GPT-2 model. Defines the number of different tokens that can be represented by the
`inputs_ids` passed when calling [`ImageGPTModel`] or [`TFImageGPTModel`].
n_positions (`int`, *optional*, defaults to 32*32):
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).
n_embd (`int`, *optional*, defaults to 512):
Dimensionality of the embeddings and hidden states.
n_layer (`int`, *optional*, defaults to 24):
Number of hidden layers in the Transformer encoder.
n_head (`int`, *optional*, defaults to 8):
Number of attention heads for each attention layer in the Transformer encoder.
n_inner (`int`, *optional*, defaults to None):
Dimensionality of the inner feed-forward layers. `None` will set it to 4 times n_embd
activation_function (`str`, *optional*, defaults to `"quick_gelu"`):
Activation function (can be one of the activation functions defined in src/transformers/activations.py).
Defaults to "quick_gelu".
resid_pdrop (`float`, *optional*, defaults to 0.1):
The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
embd_pdrop (`int`, *optional*, defaults to 0.1):
The dropout ratio for the embeddings.
attn_pdrop (`float`, *optional*, defaults to 0.1):
The dropout ratio for the attention.
layer_norm_epsilon (`float`, *optional*, defaults to 1e-5):
The epsilon to use in the layer normalization layers.
initializer_range (`float`, *optional*, defaults to 0.02):
The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
scale_attn_weights (`bool`, *optional*, defaults to `True`):
Scale attention weights by dividing by sqrt(hidden_size)..
use_cache (`bool`, *optional*, defaults to `True`):
Whether or not the model should return the last key/values attentions (not used by all models).
scale_attn_by_inverse_layer_idx (`bool`, *optional*, defaults to `False`):
Whether to additionally scale attention weights by `1 / layer_idx + 1`.
reorder_and_upcast_attn (`bool`, *optional*, defaults to `False`):
Whether to scale keys (K) prior to computing attention (dot-product) and upcast attention
dot-product/softmax to float() when training with mixed precision.
Example:
```python
>>> from transformers import ImageGPTConfig, ImageGPTModel
>>> # Initializing a ImageGPT configuration
>>> configuration = ImageGPTConfig()
>>> # Initializing a model (with random weights) from the configuration
>>> model = ImageGPTModel(configuration)
>>> # Accessing the model configuration
>>> configuration = model.config
```"""
model_type = "imagegpt"
keys_to_ignore_at_inference = ["past_key_values"]
attribute_map = {
"hidden_size": "n_embd",
"max_position_embeddings": "n_positions",
"num_attention_heads": "n_head",
"num_hidden_layers": "n_layer",
}
def __init__(
self,
vocab_size=512 + 1, # add one for start of sentence (sos) token
n_positions=32 * 32,
n_embd=512,
n_layer=24,
n_head=8,
n_inner=None,
activation_function="quick_gelu",
resid_pdrop=0.1,
embd_pdrop=0.1,
attn_pdrop=0.1,
layer_norm_epsilon=1e-5,
initializer_range=0.02,
scale_attn_weights=True,
use_cache=True,
tie_word_embeddings=False,
scale_attn_by_inverse_layer_idx=False,
reorder_and_upcast_attn=False,
**kwargs,
):
self.vocab_size = vocab_size
self.n_positions = n_positions
self.n_embd = n_embd
self.n_layer = n_layer
self.n_head = n_head
self.n_inner = n_inner
self.activation_function = activation_function
self.resid_pdrop = resid_pdrop
self.embd_pdrop = embd_pdrop
self.attn_pdrop = attn_pdrop
self.layer_norm_epsilon = layer_norm_epsilon
self.initializer_range = initializer_range
self.scale_attn_weights = scale_attn_weights
self.use_cache = use_cache
self.scale_attn_by_inverse_layer_idx = scale_attn_by_inverse_layer_idx
self.reorder_and_upcast_attn = reorder_and_upcast_attn
self.tie_word_embeddings = tie_word_embeddings
super().__init__(tie_word_embeddings=tie_word_embeddings, **kwargs)
class ImageGPTOnnxConfig(OnnxConfig):
@property
def inputs(self) -> Mapping[str, Mapping[int, str]]:
return OrderedDict(
[
("input_ids", {0: "batch", 1: "sequence"}),
]
)
def generate_dummy_inputs(
self,
preprocessor: "FeatureExtractionMixin",
batch_size: int = 1,
seq_length: int = -1,
is_pair: bool = False,
framework: Optional["TensorType"] = None,
num_channels: int = 3,
image_width: int = 32,
image_height: int = 32,
) -> Mapping[str, Any]:
"""
Generate inputs to provide to the ONNX exporter for the specific framework
Args:
preprocessor ([`PreTrainedTokenizerBase`] or [`FeatureExtractionMixin`]):
The preprocessor associated with this model configuration.
batch_size (`int`, *optional*, defaults to -1):
The batch size to export the model for (-1 means dynamic axis).
num_choices (`int`, *optional*, defaults to -1):
The number of candidate answers provided for multiple choice task (-1 means dynamic axis).
seq_length (`int`, *optional*, defaults to -1):
The sequence length to export the model for (-1 means dynamic axis).
is_pair (`bool`, *optional*, defaults to `False`):
Indicate if the input is a pair (sentence 1, sentence 2)
framework (`TensorType`, *optional*, defaults to `None`):
The framework (PyTorch or TensorFlow) that the tokenizer will generate tensors for.
num_channels (`int`, *optional*, defaults to 3):
The number of channels of the generated images.
image_width (`int`, *optional*, defaults to 40):
The width of the generated images.
image_height (`int`, *optional*, defaults to 40):
The height of the generated images.
Returns:
Mapping[str, Tensor] holding the kwargs to provide to the model's forward function
"""
input_image = self._generate_dummy_images(batch_size, num_channels, image_height, image_width)
inputs = dict(preprocessor(images=input_image, return_tensors=framework))
return inputs
|