Zj- dSrSSKJr SSKJr SSKJr \"SS9\"SS \555rS /rg ) zRegNet model configuration)strict)PreTrainedConfig)auto_docstringzfacebook/regnet-y-040) checkpointc\rSrSr%SrSrSS/rSr\\ S'Sr \\ S 'S r \ \\ \S 4-\ S 'S r\ \\ \S 4-\ S'Sr\\ S'Sr\\ S'Sr\\ S'Sr\\ S'SrSrg) RegNetConfiga groups_width (`int`, *optional*, defaults to 64): Width of group for each stage. layer_type (`str`, *optional*, defaults to `"y"`): The layer to use, it can be either `"x" or `"y"`. An `x` layer is a ResNet's BottleNeck layer with `reduction` fixed to `1`. While a `y` layer is a `x` but with squeeze and excitation. Please refer to the paper for a detailed explanation of how these layers were constructed. downsample_in_first_stage (`bool`, *optional*, defaults to `False`): If `True`, the first stage will downsample the inputs using a `stride` of 2. Example: ```python >>> from transformers import RegNetConfig, RegNetModel >>> # Initializing a RegNet regnet-y-40 style configuration >>> configuration = RegNetConfig() >>> # Initializing a model from the regnet-y-40 style configuration >>> model = RegNetModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` regnetxyr num_channels embedding_size)ii@. hidden_sizes) rdepths@ groups_width layer_typerelu hidden_actTdownsample_in_first_stagecURUR;a4[SURSSRUR535eg)zOPart of `@strict`-powered validation. Validates the architecture of the config.z layer_type=z is not one of ,N)r layer_types ValueErrorjoin)selfs ڀ/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/regnet/configuration_regnet.pyvalidate_architecture"RegNetConfig.validate_architecture<sG ??$"2"2 2{4??*;?388TXTdTdKeJfgh h 3N)__name__ __module__ __qualname____firstlineno____doc__ model_typer rint__annotations__rrlisttuplerrrstrrrboolr%__static_attributes__r(r'r$r r s.J*KL#NC0EL$s)eCHo-E*7FDIc3h '7L#JJ&*t*ir'r N) r-huggingface_hub.dataclassesrconfiguration_utilsrutilsrr __all__r(r'r$r:sK!.3#23'i#'i4'iT  r'