ZjSSKJr SSKJr SSKJr \"SS9\"SS\555r\"SS9\"S S \555rS /rg ) )strict)PreTrainedConfig)auto_docstringz&PaddlePaddle/SLANeXt_wired_safetensors) checkpointcD\rSrSr%SrSrSr\\S'Sr \\S'Sr \\S 'Sr \\S 'S r \\S 'S r \\S'Sr\\\-\\\4-\S'Sr\\S'Sr\\S'Sr\\-\S'Sr\\S'Sr\\S'Sr\\S'Sr\\S'Sr\\S'Sr\\\\S 4-\S!'S"r\\S#'S$rg%)&SLANeXtVisionConfiga output_channels (`int`, *optional*, defaults to 256): Dimensionality of the output channels in the Patch Encoder. use_abs_pos (`bool`, *optional*, defaults to `True`): Whether to use absolute position embedding. use_rel_pos (`bool`, *optional*, defaults to `True`): Whether to use relative position embedding. window_size (`int`, *optional*, defaults to 14): Window size for relative position. global_attn_indexes (`list[int]`, *optional*, defaults to `[2, 5, 8, 11]`): The indexes of the global attention layers. mlp_dim (`int`, *optional*, defaults to 3072): The dimensionality of the MLP layer in the Transformer encoder. vision_configi hidden_sizeoutput_channels num_hidden_layersnum_attention_headsr num_channels image_size patch_sizegelu hidden_actgư>layer_norm_epsgattention_dropoutg|=initializer_rangeTqkv_bias use_abs_pos use_rel_pos window_size) .global_attn_indexesi mlp_dimN)__name__ __module__ __qualname____firstlineno____doc__base_config_keyr int__annotations__rrrrrrlisttuplerstrrfloatrrrboolrrr r%r&__static_attributes__r'ڂ/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/slanext/configuration_slanext.pyr r s &OKOSs!!L#J46Jd3i%S/16J!NE!%(us{($u$HdKKK7DcU38_4DGSr6r c^\rSrSr%SrSrS\0rSr\ \-S-\ S'Sr \ \ S'Sr \ \ S 'S r\ \ S 'Sr\ \ S 'S r\ \ S'U4SjrSrU=r$) SLANeXtConfigBa vision_config (`dict` or [`SLANeXtVisionConfig`], *optional*): Configuration for the vision encoder. If `None`, a default [`SLANeXtVisionConfig`] is used. post_conv_in_channels (`int`, *optional*, defaults to 256): Number of input channels for the post-encoder convolution layer. post_conv_out_channels (`int`, *optional*, defaults to 512): Number of output channels for the post-encoder convolution layer. out_channels (`int`, *optional*, defaults to 50): Vocabulary size for the table structure token prediction head, i.e., the number of distinct structure tokens the model can predict. hidden_size (`int`, *optional*, defaults to 512): Dimensionality of the hidden states in the attention GRU cell and the structure/location prediction heads. max_text_length (`int`, *optional*, defaults to 500): Maximum number of autoregressive decoding steps (tokens) for the structure and location decoder. slanextr Nr post_conv_in_channelsrpost_conv_out_channels2 out_channelsr imax_text_lengthc >URc[5UlO9[UR[5(a[S0URD6Ul[TU]"S0UD6 g)Nr')r r isinstancedictsuper __post_init__)selfkwargs __class__s r7rESLANeXtConfig.__post_init___sS    %!4!6D  **D 1 1!4!Jt7I7I!JD  ''r6)r )r(r)r*r+r, model_typer sub_configsr rCr/r<r.r=r?r r@rEr5 __classcell__)rHs@r7r9r9Bsm J"$78K7;M4--4;!$3$"%C%L#KOS((r6r9N) huggingface_hub.dataclassesrconfiguration_utilsrutilsrr r9__all__r'r6r7rQsr,/3#CD!*!E!HCD ($ (E (F  r6