| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566 |
- # 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
- # 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.
- # 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
- # 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 huggingface_hub.dataclasses import strict
- from ...configuration_utils import PreTrainedConfig
- from ...utils import auto_docstring
- @auto_docstring(checkpoint="DeepGlint-AI/mlcd-vit-bigG-patch14-336")
- @strict
- class MLCDVisionConfig(PreTrainedConfig):
- r"""
- num_key_value_groups (`int`, *optional*, defaults to 1):
- Number of key-value groups used in Attention.
- 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"
- hidden_size: int = 1664
- intermediate_size: int = 8192
- num_hidden_layers: int = 48
- num_attention_heads: int = 16
- num_key_value_groups: int = 1
- num_channels: int = 3
- image_size: int | list[int] | tuple[int, int] = 336
- patch_size: int | list[int] | tuple[int, int] = 14
- hidden_act: str = "gelu"
- layer_norm_eps: float = 1e-5
- attention_dropout: float | int = 0.0
- initializer_range: float = 0.02
- initializer_factor: float = 1.0
- __all__ = ["MLCDVisionConfig"]
|