i.NddlmZddlmZerddlZGddeZdgZy))PreTrainedConfig)is_detectron2_availableNcxeZdZdZdZddddddddd d d d d dddddddgdddddddffd ZedZdZxZ S)LayoutXLMConfiga This is the configuration class to store the configuration of a [`LayoutXLMModel`]. It is used to instantiate an LayoutXLM model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the LayoutXLM [microsoft/layoutxlm-base](https://huggingface.co/microsoft/layoutxlm-base) architecture. Configuration objects inherit from [`PreTrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PreTrainedConfig`] for more information. Args: vocab_size (`int`, *optional*, defaults to 30522): Vocabulary size of the LayoutXLM model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`LayoutXLMModel`]. hidden_size (`int`, *optional*, defaults to 768): Dimension of the encoder layers and the pooler layer. num_hidden_layers (`int`, *optional*, defaults to 12): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 12): Number of attention heads for each attention layer in the Transformer encoder. intermediate_size (`int`, *optional*, defaults to 3072): Dimension of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` are supported. hidden_dropout_prob (`float`, *optional*, defaults to 0.1): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. attention_probs_dropout_prob (`float`, *optional*, defaults to 0.1): The dropout ratio for the attention probabilities. max_position_embeddings (`int`, *optional*, defaults to 512): The maximum sequence length that this model might ever be used with. Typically set this to something large just in case (e.g., 512 or 1024 or 2048). type_vocab_size (`int`, *optional*, defaults to 2): The vocabulary size of the `token_type_ids` passed when calling [`LayoutXLMModel`]. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. layer_norm_eps (`float`, *optional*, defaults to 1e-12): The epsilon used by the layer normalization layers. pad_token_id (`int`, *optional*, defaults to 0): Padding token id. max_2d_position_embeddings (`int`, *optional*, defaults to 1024): The maximum value that the 2D position embedding might ever be used with. Typically set this to something large just in case (e.g., 1024). max_rel_pos (`int`, *optional*, defaults to 128): The maximum number of relative positions to be used in the self-attention mechanism. rel_pos_bins (`int`, *optional*, defaults to 32): The number of relative position bins to be used in the self-attention mechanism. fast_qkv (`bool`, *optional*, defaults to `True`): Whether or not to use a single matrix for the queries, keys, values in the self-attention layers. max_rel_2d_pos (`int`, *optional*, defaults to 256): The maximum number of relative 2D positions in the self-attention mechanism. rel_2d_pos_bins (`int`, *optional*, defaults to 64): The number of 2D relative position bins in the self-attention mechanism. convert_sync_batchnorm (`bool`, *optional*, defaults to `True`): Whether or not to convert batch normalization layers to synchronized batch normalization layers. image_feature_pool_shape (`list[int]`, *optional*, defaults to `[7, 7, 256]`): The shape of the average-pooled feature map. coordinate_size (`int`, *optional*, defaults to 128): Dimension of the coordinate embeddings. shape_size (`int`, *optional*, defaults to 128): Dimension of the width and height embeddings. has_relative_attention_bias (`bool`, *optional*, defaults to `True`): Whether or not to use a relative attention bias in the self-attention mechanism. has_spatial_attention_bias (`bool`, *optional*, defaults to `True`): Whether or not to use a spatial attention bias in the self-attention mechanism. has_visual_segment_embedding (`bool`, *optional*, defaults to `False`): Whether or not to add visual segment embeddings. detectron2_config_args (`dict`, *optional*): Dictionary containing the configuration arguments of the Detectron2 visual backbone. Refer to [this file](https://github.com/microsoft/unilm/blob/master/layoutlmft/layoutlmft/models/layoutxlm/detectron2_config.py) for details regarding default values. Example: ```python >>> from transformers import LayoutXLMConfig, LayoutXLMModel >>> # Initializing a LayoutXLM microsoft/layoutxlm-base style configuration >>> configuration = LayoutXLMConfig() >>> # Initializing a model (with random weights) from the microsoft/layoutxlm-base style configuration >>> model = LayoutXLMModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` layoutxlmi:wi i gelug?g{Gz?g-q=ri T@)rrFNc t|di|||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ | |_||_||_||_||_||_||_||_||_||_||_||_||_||_|||_y|j9|_y)N)super__init__ vocab_size hidden_sizenum_hidden_layersnum_attention_headsintermediate_size hidden_acthidden_dropout_probattention_probs_dropout_probmax_position_embeddingstype_vocab_sizeinitializer_rangelayer_norm_eps pad_token_idmax_2d_position_embeddings max_rel_pos rel_pos_binsfast_qkvmax_rel_2d_posrel_2d_pos_binsconvert_sync_batchnormimage_feature_pool_shapecoordinate_size shape_sizehas_relative_attention_biashas_spatial_attention_biashas_visual_segment_embeddingget_default_detectron2_configdetectron2_config_args)selfrrrrrrrrrrr r!r"r#r$r%r&r'r(r)r*r+r,r-r.r/r1kwargs __class__s q/mnt/e/genesis-system/.venv/lib/python3.12/site-packages/transformers/models/layoutxlm/configuration_layoutxlm.pyrzLayoutXLMConfig.__init__xs> "6"$&!2#6 !2$#6 ,H)'>$.!2,(*D'&(  ,.&<#(@%.$+F(*D',H)&<&H " #NRNpNpNr #c idddgddddgdd d gd gd gd gdggdgddddddddddddddgddddd d!d"d#d$d%d&d'd gd gd gd gdgggd(ggdd d)d*d+ S),Nz MODEL.MASK_ONTzMODEL.PIXEL_STD)gL@g(\L@g(\2M@zMODEL.BACKBONE.NAMEbuild_resnet_fpn_backbonezMODEL.FPN.IN_FEATURES)res2res3res4res5zMODEL.ANCHOR_GENERATOR.SIZESrrr rr zMODEL.RPN.IN_FEATURES)p2p3p4p5p6zMODEL.RPN.PRE_NMS_TOPK_TRAINizMODEL.RPN.PRE_NMS_TOPK_TESTizMODEL.RPN.POST_NMS_TOPK_TRAINzMODEL.POST_NMS_TOPK_TESTzMODEL.ROI_HEADS.NAMEStandardROIHeadszMODEL.ROI_HEADS.NUM_CLASSESzMODEL.ROI_HEADS.IN_FEATURES)r=r>r?r@zMODEL.ROI_BOX_HEAD.NAMEFastRCNNConvFCHeadzMODEL.ROI_BOX_HEAD.NUM_FCr z$MODEL.ROI_BOX_HEAD.POOLER_RESOLUTIONzMODEL.ROI_MASK_HEAD.NAMEMaskRCNNConvUpsampleHeadre)g?g?g@F) zMODEL.ROI_MASK_HEAD.NUM_CONVz%MODEL.ROI_MASK_HEAD.POOLER_RESOLUTIONzMODEL.RESNETS.DEPTHzMODEL.RESNETS.SIZESzMODEL.RESNETS.ASPECT_RATIOSzMODEL.RESNETS.OUT_FEATURESzMODEL.RESNETS.NUM_GROUPSzMODEL.RESNETS.WIDTH_PER_GROUPzMODEL.RESNETS.STRIDE_IN_1X1r)clss r5r0z-LayoutXLMConfig.get_default_detectron2_configs+ T 7  "#>  $%E  +bTB4#u,M  $%C   +D  *4  ,T  '  #$6  *1  *+C  &';  ( 3B! " '(B# $-.56#&%'D2$use#D,;+<*J(*-.+05  r6ctjj}|jj D]>\}}|j d}|}|ddD]}t ||}t||d|@|S)N.) detectron2configget_cfgr1itemssplitgetattrsetattr)r2detectron2_configkv attributesto_set attributes r5get_detectron2_configz%LayoutXLMConfig.get_detectron2_configs&--557//557 /DAqJ&F'_ 4  3 4 FJrNA .  /! r6) __name__ __module__ __qualname____doc__ model_typer classmethodr0r[ __classcell__)r4s@r5rrsT lJ%( ##'#!,$(#'%*#9< |  < !r6r)configuration_utilsrutilsrrNr__all__rr6r5rfs2,4,!&!D  r6