o ¾e¦i !ã@s@dZddlmZddlmZe e¡ZGdd„deƒZdgZ dS)zLayoutLMv3 model configurationé)ÚPreTrainedConfig)ÚloggingcsbeZdZdZdZ                        d‡fdd„ Z‡ZS)ÚLayoutLMv3Configa  This is the configuration class to store the configuration of a [`LayoutLMv3Model`]. It is used to instantiate an LayoutLMv3 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 LayoutLMv3 [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-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 50265): Vocabulary size of the LayoutLMv3 model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`LayoutLMv3Model`]. 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 [`LayoutLMv3Model`]. 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-5): The epsilon used by the layer normalization layers. 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). 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. rel_pos_bins (`int`, *optional*, defaults to 32): The number of relative position bins to be used in the self-attention mechanism. max_rel_pos (`int`, *optional*, defaults to 128): The maximum number of relative positions to be used in the self-attention mechanism. 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. has_spatial_attention_bias (`bool`, *optional*, defaults to `True`): Whether or not to use a spatial attention bias in the self-attention mechanism. visual_embed (`bool`, *optional*, defaults to `True`): Whether or not to add patch embeddings. input_size (`int`, *optional*, defaults to `224`): The size (resolution) of the images. num_channels (`int`, *optional*, defaults to `3`): The number of channels of the images. patch_size (`int`, *optional*, defaults to `16`) The size (resolution) of the patches. classifier_dropout (`float`, *optional*): The dropout ratio for the classification head. Example: ```python >>> from transformers import LayoutLMv3Config, LayoutLMv3Model >>> # Initializing a LayoutLMv3 microsoft/layoutlmv3-base style configuration >>> configuration = LayoutLMv3Config() >>> # Initializing a model (with random weights) from the microsoft/layoutlmv3-base style configuration >>> model = LayoutLMv3Model(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```Ú layoutlmv3éYÄéé é Úgeluçš™™™™™¹?ééç{®Gáz”?çñh㈵øä>éééé€Té é@ééàréNc  sÊtƒjdi|¤Ž||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ | |_||_||_||_||_||_||_||_||_||_||_||_||_||_||_||_||_||_dS)N©) ÚsuperÚ__init__Ú vocab_sizeÚ hidden_sizeÚnum_hidden_layersÚnum_attention_headsÚintermediate_sizeÚ hidden_actÚhidden_dropout_probÚattention_probs_dropout_probÚmax_position_embeddingsÚtype_vocab_sizeÚinitializer_rangeÚlayer_norm_epsÚ pad_token_idÚ bos_token_idÚ eos_token_idÚmax_2d_position_embeddingsÚcoordinate_sizeÚ shape_sizeÚhas_relative_attention_biasÚ rel_pos_binsÚ max_rel_posÚhas_spatial_attention_biasÚrel_2d_pos_binsÚmax_rel_2d_posÚ text_embedÚ visual_embedÚ input_sizeÚ num_channelsÚ patch_sizeÚclassifier_dropout) Úselfrrrrr r!r"r#r$r%r&r'r(r)r*r+r,r-r.r/r0r2r3r1r4r5r6r7r8r9Úkwargs©Ú __class__rúu/home/ubuntu/transcripts/venv/lib/python3.10/site-packages/transformers/models/layoutlmv3/configuration_layoutlmv3.pyrls>" zLayoutLMv3Config.__init__)rrrrr r r r r r rrrrr rrrTrrrrTTTrrrN)Ú__name__Ú __module__Ú __qualname__Ú__doc__Ú model_typerÚ __classcell__rrr<r>rsDRárN) rBÚconfiguration_utilsrÚutilsrÚ get_loggerr?ÚloggerrÚ__all__rrrr>Ús