T^(h`dZddlmZddlmZej eZGddeZdgZ y)zMarkupLM model configuration)PretrainedConfig)loggingcXeZdZdZdZ dfd ZxZS)MarkupLMConfiga This is the configuration class to store the configuration of a [`MarkupLMModel`]. It is used to instantiate a MarkupLM 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 MarkupLM [microsoft/markuplm-base](https://huggingface.co/microsoft/markuplm-base) architecture. Configuration objects inherit from [`BertConfig`] and can be used to control the model outputs. Read the documentation from [`BertConfig`] for more information. Args: vocab_size (`int`, *optional*, defaults to 30522): Vocabulary size of the MarkupLM model. Defines the different tokens that can be represented by the *inputs_ids* passed to the forward method of [`MarkupLMModel`]. hidden_size (`int`, *optional*, defaults to 768): Dimensionality 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): Dimensionality 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"`, `"silu"` 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 into [`MarkupLMModel`]. 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. max_tree_id_unit_embeddings (`int`, *optional*, defaults to 1024): The maximum value that the tree id unit embedding might ever use. Typically set this to something large just in case (e.g., 1024). max_xpath_tag_unit_embeddings (`int`, *optional*, defaults to 256): The maximum value that the xpath tag unit embedding might ever use. Typically set this to something large just in case (e.g., 256). max_xpath_subs_unit_embeddings (`int`, *optional*, defaults to 1024): The maximum value that the xpath subscript unit embedding might ever use. Typically set this to something large just in case (e.g., 1024). tag_pad_id (`int`, *optional*, defaults to 216): The id of the padding token in the xpath tags. subs_pad_id (`int`, *optional*, defaults to 1001): The id of the padding token in the xpath subscripts. xpath_tag_unit_hidden_size (`int`, *optional*, defaults to 32): The hidden size of each tree id unit. One complete tree index will have (50*xpath_tag_unit_hidden_size)-dim. max_depth (`int`, *optional*, defaults to 50): The maximum depth in xpath. Examples: ```python >>> from transformers import MarkupLMModel, MarkupLMConfig >>> # Initializing a MarkupLM microsoft/markuplm-base style configuration >>> configuration = MarkupLMConfig() >>> # Initializing a model from the microsoft/markuplm-base style configuration >>> model = MarkupLMModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```markuplmc Rt|d| ||d|||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ ||_||_||_||_||_||_||_||_||_y)N) pad_token_id bos_token_id eos_token_id)super__init__ vocab_size hidden_sizenum_hidden_layersnum_attention_heads hidden_actintermediate_sizehidden_dropout_probattention_probs_dropout_probmax_position_embeddingstype_vocab_sizeinitializer_rangelayer_norm_epsposition_embedding_type use_cacheclassifier_dropout max_depthmax_xpath_tag_unit_embeddingsmax_xpath_subs_unit_embeddings tag_pad_id subs_pad_idxpath_unit_hidden_size)selfrrrrrrrrrrrrr r r rr r!r"r#rrrrkwargs __class__s q/var/www/skyplay_api_hub/venv/lib/python3.12/site-packages/transformers/models/markuplm/configuration_markuplm.pyrzMarkupLMConfig.__init__bs8  %%%   %&!2#6 $!2#6 ,H)'>$.!2,'>$""4"-J*.L+$&&<#)i:wi r)i gelu皙?r+ig{Gz?g-q=r-r,ii 2absoluteTN)__name__ __module__ __qualname____doc__ model_typer __classcell__)r&s@r'rrseE NJ%( #&)'+! *37=7=r(rN) r6configuration_utilsrutilsr get_loggerr3loggerr__all__r r(r'r>s>#3   H %A=%A=H  r(