ZjrSrSSKJr SSKJr SSKJr SSKJr \"SS9\"S S \\555r S /r g ) zFocalNet model configuration)strict)BackboneConfigMixin)PreTrainedConfig)auto_docstringzmicrosoft/focalnet-tiny) checkpointc(^\rSrSr%SrSrSr\\\-\ \\4-\ S'Sr \\\-\ \\4-\ S'Sr \\ S 'S r \\ S 'S r\\ S 'Sr\\\ \S4-\ S'Sr\\\ \S4-\ S'Sr\\\ \S4-\ S'Sr\\\ \S4-\ S'Sr\\ S'Sr\\ S'Sr\\-\ S'Sr\\-\ S'S r\\ S'S r\\ S!'S r\\ S"'S r\\ S#'S r\\ S$'S%r\\ S&'S'r \\ S('S)r!\\ S*'S+r"\\S+-\ S,'S+r#\\S+-\ S-'U4S.jr$S/r%U=r&$)0FocalNetConfiga use_conv_embed (`bool`, *optional*, defaults to `False`): Whether to use convolutional embedding. The authors noted that using convolutional embedding usually improve the performance, but it's not used by default. focal_levels (`list(int)`, *optional*, defaults to `[2, 2, 2, 2]`): Number of focal levels in each layer of the respective stages in the encoder. focal_windows (`list(int)`, *optional*, defaults to `[3, 3, 3, 3]`): Focal window size in each layer of the respective stages in the encoder. hidden_dropout_prob (`float`, *optional*, defaults to 0.0): The dropout probability for all fully connected layers in the embeddings and encoder. use_layerscale (`bool`, *optional*, defaults to `False`): Whether to use layer scale in the encoder. layerscale_value (`float`, *optional*, defaults to 0.0001): The initial value of the layer scale. use_post_layernorm (`bool`, *optional*, defaults to `False`): Whether to use post layer normalization in the encoder. use_post_layernorm_in_modulation (`bool`, *optional*, defaults to `False`): Whether to use post layer normalization in the modulation layer. normalize_modulator (`bool`, *optional*, defaults to `False`): Whether to normalize the modulator. encoder_stride (`int`, *optional*, defaults to 32): Factor to increase the spatial resolution by in the decoder head for masked image modeling. Example: ```python >>> from transformers import FocalNetConfig, FocalNetModel >>> # Initializing a FocalNet microsoft/focalnet-tiny style configuration >>> configuration = FocalNetConfig() >>> # Initializing a model (with random weights) from the microsoft/focalnet-tiny style configuration >>> model = FocalNetModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```focalnet image_size patch_sizer num_channels` embed_dimFuse_conv_embed)ir. hidden_sizes)rrdepths)rrrr focal_levels)rrrr focal_windowsgelu hidden_actg@ mlp_ratioghidden_dropout_probg?drop_path_rateuse_layerscaleg-C6?layerscale_valueuse_post_layernorm use_post_layernorm_in_modulationnormalize_modulatorg{Gz?initializer_rangegh㈵>layer_norm_eps encoder_strideN _out_features _out_indicesc >S/[S[UR5S-5Vs/sHnSU3PM sn-UlUR UR SS5UR SS5S9 [ TU]"S0UD6 gs snf)Nstemstage out_indices out_features)r1r2)rangelenr stage_names"set_output_features_output_indicespopsuper __post_init__)selfkwargsidx __class__s ڄ/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/focalnet/configuration_focalnet.pyr:FocalNetConfig.__post_init__Zs"8aT[[IY\]I]@^&_@^se}@^&__ // =$7fjjQ_aeFf 0  '' '`sB)r6)'__name__ __module__ __qualname____firstlineno____doc__ model_typerintlisttuple__annotations__rrrrboolrrrrrstrrfloatr r!r"r#r$r%r&r'r(r*r+r,r:__static_attributes__ __classcell__)r>s@r?r r s$ LJ47Jd3i%S/1745Jd3i%S/15L#Is ND 0DL$s)eCHo-D*6FDIc3h '60rVsQ#.13#45F((*:F(6F(R  rP