+ j^RIHt^RIHt^RIHt]!RR7]!RR]444t]!RR7]!RR ]444tR .tR #) )strict)PreTrainedConfig)auto_docstringz&PaddlePaddle/SLANeXt_wired_safetensors) checkpointcxa]tRt^toRtRtRtRt^ t^ t ^t Rt ^t Rt RtRtR tR tR tR t^tRtR tV3R ltR tVtR#)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_configigelugư>gg|=Ti cp<V^8dQh/S[;R&S[;R&S[;R&S[;R&S[;R&S[;R&S[S[S[,,S[S[S[3,,;R&S[;R&S[;R &S[S[,;R &S[;R &S[;R &S[;R &S[;R&S[;R&S[S[,S[S[R3,,;R&S[;R&#) hidden_sizeoutput_channelsnum_hidden_layersnum_attention_heads num_channels image_size patch_size hidden_actlayer_norm_epsattention_dropoutinitializer_rangeqkv_bias use_abs_pos use_rel_pos window_size.global_attn_indexesmlp_dim)intlisttuplestrfloatbool)format __classdict__s"r/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/slanext/configuration_slanext.py __annotate__ SLANeXtVisionConfig.__annotate__s&'()*+,!-./012d3i%S/163456!78s{(9:$;<=>?@ABCDcU38_4DEFGN)r )__name__ __module__ __qualname____firstlineno____doc__base_config_keyrrrrrrrrrrrrrrrrr__annotate_func____static_attributes____classdictcell__)r's@r(rrss &OKO!LJ46JJ!N%($HKKK7DGGr+rcfaa]tRt^BtoRtRtR]/tRtRt Rt ^2t Rt Rt V3RltV3R ltR tVtV;t#) SLANeXtConfiga 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 r ic <VPf\4VnM:\VP\4'd\R/VPBVn\SV`!R/VBR#)Nr,)r r isinstancedictsuper __post_init__)selfkwargs __class__s&,r(r@SLANeXtConfig.__post_init___sS    %!4!6D  **D 1 1!4!Jt7I7I!JD  ''r+c<V^8dQh/S[S[,R,;R&S[;R&S[;R&S[;R&S[;R&S[;R&#)rNr post_conv_in_channelspost_conv_out_channels out_channelsrmax_text_length)r>rr )r&r's"r(r)SLANeXtConfig.__annotate__Bs^,--4;-.$/0 %1234567r+)r )r0r1r2r3r4 model_typer sub_configsr rFrGrHrrIr@r6r7r8 __classcell__)rCr's@@r(r:r:BsH J"$78K7;M!$"%LKO(;r+r:N) huggingface_hub.dataclassesrconfiguration_utilsrutilsrrr:__all__r,r+r(rRsr,/3#CD!*!E!HCD ($ (E (F  r+