117 lines
5.7 KiB
Python
117 lines
5.7 KiB
Python
# 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
|
|
# This file was automatically generated from src/transformers/models/mlcd/modular_mlcd.py.
|
|
# Do NOT edit this file manually as any edits will be overwritten by the generation of
|
|
# the file from the modular. If any change should be done, please apply the change to the
|
|
# modular_mlcd.py file directly. One of our CI enforces this.
|
|
# 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
|
|
# coding=utf-8
|
|
# Copyright 2025 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.
|
|
|
|
from ...configuration_utils import PretrainedConfig
|
|
|
|
|
|
class MLCDVisionConfig(PretrainedConfig):
|
|
r"""
|
|
This is the configuration class to store the configuration of a [`MLCDVisionModel`]. It is used to instantiate a MLCD
|
|
vision encoder according to the specified arguments, defining the model architecture. Instantiating a configuration
|
|
with the defaults will yield a similar configuration to that of the vision encoder of the MLCD
|
|
[DeepGlint-AI/mlcd-vit-bigG-patch14-336](https://huggingface.co/DeepGlint-AI/mlcd-vit-bigG-patch14-336) architecture.
|
|
|
|
Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
|
|
documentation from [`PretrainedConfig`] for more information.
|
|
|
|
Args:
|
|
hidden_size (`int`, *optional*, defaults to 1664):
|
|
Dimensionality of the encoder layers and the pooler layer.
|
|
intermediate_size (`int`, *optional*, defaults to 8192):
|
|
Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder.
|
|
projection_dim (`int`, *optional*, defaults to 1024):
|
|
Dimensionality of text and vision projection layers.
|
|
num_hidden_layers (`int`, *optional*, defaults to 48):
|
|
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.
|
|
num_channels (`int`, *optional*, defaults to 3):
|
|
The number of input channels.
|
|
image_size (`int`, *optional*, defaults to 336):
|
|
The size (resolution) of each image.
|
|
patch_size (`int`, *optional*, defaults to 14):
|
|
The size (resolution) of each patch.
|
|
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"` `"quick_gelu"` are supported.
|
|
layer_norm_eps (`float`, *optional*, defaults to 1e-05):
|
|
The epsilon used by the layer normalization layers.
|
|
attention_dropout (`float`, *optional*, defaults to 0.0):
|
|
The dropout ratio for the attention probabilities.
|
|
initializer_range (`float`, *optional*, defaults to 0.02):
|
|
The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
|
|
initializer_factor (`float`, *optional*, defaults to 1.0):
|
|
A factor for initializing all weight matrices (should be kept to 1, used internally for initialization
|
|
testing).
|
|
|
|
Example:
|
|
|
|
```python
|
|
>>> from transformers import MLCDVisionConfig, MLCDVisionModel
|
|
|
|
>>> # Initializing a MLCDVisionConfig with DeepGlint-AI/mlcd-vit-bigG-patch14-336 style configuration
|
|
>>> configuration = MLCDVisionConfig()
|
|
|
|
>>> # Initializing a MLCDVisionModel (with random weights) from the DeepGlint-AI/mlcd-vit-bigG-patch14-336 style configuration
|
|
>>> model = MLCDVisionModel(configuration)
|
|
|
|
>>> # Accessing the model configuration
|
|
>>> configuration = model.config
|
|
```"""
|
|
|
|
model_type = "mlcd_vision_model"
|
|
base_config_key = "vision_config"
|
|
|
|
def __init__(
|
|
self,
|
|
hidden_size=1664,
|
|
intermediate_size=8192,
|
|
num_hidden_layers=48,
|
|
num_attention_heads=16,
|
|
num_key_value_groups=1,
|
|
num_channels=3,
|
|
image_size=336,
|
|
patch_size=14,
|
|
hidden_act="gelu",
|
|
layer_norm_eps=1e-5,
|
|
attention_dropout=0.0,
|
|
initializer_range=0.02,
|
|
initializer_factor=1.0,
|
|
**kwargs,
|
|
):
|
|
super().__init__(**kwargs)
|
|
|
|
self.hidden_size = hidden_size
|
|
self.intermediate_size = intermediate_size
|
|
self.num_hidden_layers = num_hidden_layers
|
|
self.num_attention_heads = num_attention_heads
|
|
self.num_key_value_groups = num_key_value_groups
|
|
self.num_channels = num_channels
|
|
self.patch_size = patch_size
|
|
self.image_size = image_size
|
|
self.initializer_range = initializer_range
|
|
self.initializer_factor = initializer_factor
|
|
self.attention_dropout = attention_dropout
|
|
self.layer_norm_eps = layer_norm_eps
|
|
self.hidden_act = hidden_act
|
|
|
|
|
|
__all__ = ["MLCDVisionConfig"]
|