# 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨 # This file was automatically generated from src/transformers/models/dinov2_with_registers/modular_dinov2_with_registers.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_dinov2_with_registers.py file directly. One of our CI enforces this. # 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨 # coding=utf-8 # Copyright 2024 Meta Inc. and the HuggingFace Inc. team. 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. from ...configuration_utils import PretrainedConfig from ...utils.backbone_utils import BackboneConfigMixin, get_aligned_output_features_output_indices class Dinov2WithRegistersConfig(BackboneConfigMixin, PretrainedConfig): r""" This is the configuration class to store the configuration of a [`Dinov2WithRegistersModel`]. It is used to instantiate an Dinov2WithRegisters 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 DINOv2 with Registers [facebook/dinov2-with-registers-base](https://huggingface.co/facebook/dinov2-with-registers-base) 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 768): Dimensionality of the encoder layers and the pooler layer. num_hidden_layers (`int`, *optional*, defaults to 12): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 12): Number of attention heads for each attention layer in the Transformer encoder. mlp_ratio (`int`, *optional*, defaults to 4): Ratio of the hidden size of the MLPs relative to the `hidden_size`. 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"` are supported. hidden_dropout_prob (`float`, *optional*, defaults to 0.0): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. attention_probs_dropout_prob (`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. layer_norm_eps (`float`, *optional*, defaults to 1e-06): The epsilon used by the layer normalization layers. image_size (`int`, *optional*, defaults to 224): The size (resolution) of each image. patch_size (`int`, *optional*, defaults to 16): The size (resolution) of each patch. num_channels (`int`, *optional*, defaults to 3): The number of input channels. qkv_bias (`bool`, *optional*, defaults to `True`): Whether to add a bias to the queries, keys and values. layerscale_value (`float`, *optional*, defaults to 1.0): Initial value to use for layer scale. drop_path_rate (`float`, *optional*, defaults to 0.0): Stochastic depth rate per sample (when applied in the main path of residual layers). use_swiglu_ffn (`bool`, *optional*, defaults to `False`): Whether to use the SwiGLU feedforward neural network. num_register_tokens (`int`, *optional*, defaults to 4): Number of register tokens to use. out_features (`List[str]`, *optional*): If used as backbone, list of features to output. Can be any of `"stem"`, `"stage1"`, `"stage2"`, etc. (depending on how many stages the model has). If unset and `out_indices` is set, will default to the corresponding stages. If unset and `out_indices` is unset, will default to the last stage. Must be in the same order as defined in the `stage_names` attribute. out_indices (`List[int]`, *optional*): If used as backbone, list of indices of features to output. Can be any of 0, 1, 2, etc. (depending on how many stages the model has). If unset and `out_features` is set, will default to the corresponding stages. If unset and `out_features` is unset, will default to the last stage. Must be in the same order as defined in the `stage_names` attribute. apply_layernorm (`bool`, *optional*, defaults to `True`): Whether to apply layer normalization to the feature maps in case the model is used as backbone. reshape_hidden_states (`bool`, *optional*, defaults to `True`): Whether to reshape the feature maps to 4D tensors of shape `(batch_size, hidden_size, height, width)` in case the model is used as backbone. If `False`, the feature maps will be 3D tensors of shape `(batch_size, seq_len, hidden_size)`. Example: ```python >>> from transformers import Dinov2WithRegistersConfig, Dinov2WithRegistersModel >>> # Initializing a Dinov2WithRegisters base style configuration >>> configuration = Dinov2WithRegistersConfig() >>> # Initializing a model (with random weights) from the base style configuration >>> model = Dinov2WithRegistersModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```""" model_type = "dinov2_with_registers" def __init__( self, hidden_size=768, num_hidden_layers=12, num_attention_heads=12, mlp_ratio=4, hidden_act="gelu", hidden_dropout_prob=0.0, attention_probs_dropout_prob=0.0, initializer_range=0.02, layer_norm_eps=1e-6, image_size=224, patch_size=16, num_channels=3, qkv_bias=True, layerscale_value=1.0, drop_path_rate=0.0, use_swiglu_ffn=False, num_register_tokens=4, out_features=None, out_indices=None, apply_layernorm=True, reshape_hidden_states=True, **kwargs, ): super().__init__(**kwargs) self.hidden_size = hidden_size self.num_hidden_layers = num_hidden_layers self.num_attention_heads = num_attention_heads self.mlp_ratio = mlp_ratio self.hidden_act = hidden_act self.hidden_dropout_prob = hidden_dropout_prob self.attention_probs_dropout_prob = attention_probs_dropout_prob self.initializer_range = initializer_range self.layer_norm_eps = layer_norm_eps self.image_size = image_size self.patch_size = patch_size self.num_channels = num_channels self.qkv_bias = qkv_bias self.layerscale_value = layerscale_value self.drop_path_rate = drop_path_rate self.use_swiglu_ffn = use_swiglu_ffn self.num_register_tokens = num_register_tokens self.stage_names = ["stem"] + [f"stage{idx}" for idx in range(1, num_hidden_layers + 1)] self._out_features, self._out_indices = get_aligned_output_features_output_indices( out_features=out_features, out_indices=out_indices, stage_names=self.stage_names ) self.apply_layernorm = apply_layernorm self.reshape_hidden_states = reshape_hidden_states __all__ = ["Dinov2WithRegistersConfig"]