+ j& lRt^RIHt^RIHt^RIHt]!RR7]!RR]444tR.tR#) zLeViT model configuration)strict)PreTrainedConfig)auto_docstringzfacebook/levit-128S) checkpointc~aa]tRt^toRtRt^t^t^t^t ^t ^t Rt Rt R tR t^tR tR tRtV3RltV3RltRtVtV;t#) LevitConfigax stride (`int`, *optional*, defaults to 2): The stride size for the initial convolution layers of patch embedding. padding (`int`, *optional*, defaults to 1): The padding size for the initial convolution layers of patch embedding. key_dim (`list[int]`, *optional*, defaults to `[16, 16, 16]`): The size of key in each of the encoder blocks. attention_ratio (`list[int]`, *optional*, defaults to `[2, 2, 2]`): Ratio of the size of the output dimension compared to input dimension of attention layers. Example: ```python >>> from transformers import LevitConfig, LevitModel >>> # Initializing a LeViT levit-128S style configuration >>> configuration = LevitConfig() >>> # Initializing a model (with random weights) from the levit-128S style configuration >>> model = LevitModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```levitg{Gz?c :<RVP^,VP^,VP^,,^^^.RVP^,VP^,VP^,,^^^..Vn\SV`!R/VBR#) SubsampleN)key_dim hidden_sizesdown_opssuper __post_init__)selfkwargs __class__s&,n/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/levit/configuration_levit.pyrLevitConfig.__post_init__Cs $,,q/4+<+?@AB OCDEFd3i%S/16GHs)eCHo-?IJcU38_4AKL Ic3h '3MN#YsCx (7OPQRCy5c?*6ST#YsCx0rAsG .3#010("0(20(f /r