
    <hC                     h    S r SSKrSSKJr  SSKJr  \R                  " \5      r " S S\5      r	S/r
g)zMarkupLM model configuration    N   )PretrainedConfig)loggingc                      ^  \ rS rSrSrSr                        SU 4S jjr\S 5       r\R                  S 5       rSr
U =r$ )	MarkupLMConfig   a  
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                 <  > [         TU ]  " SUUUS.UD6  Xl        X l        X0l        X@l        X`l        XPl        Xpl        Xl	        Xl
        Xl        Xl        Xl        UU l        UU l        UU l        UU l        UU l        UU l        UU l        UU l        UU l        g )N)pad_token_idbos_token_ideos_token_id )super__init__
vocab_sizehidden_sizenum_hidden_layersnum_attention_heads
hidden_actintermediate_sizehidden_dropout_probattention_probs_dropout_probmax_position_embeddingstype_vocab_sizeinitializer_rangelayer_norm_eps_position_embedding_type	use_cacheclassifier_dropout	max_depthmax_xpath_tag_unit_embeddingsmax_xpath_subs_unit_embeddings
tag_pad_idsubs_pad_idxpath_unit_hidden_size)selfr   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r!   r"   r#   r$   r%   r    position_embedding_typer   r   kwargs	__class__s                             k/var/www/html/shao/venv/lib/python3.13/site-packages/transformers/models/markuplm/configuration_markuplm.pyr   MarkupLMConfig.__init__d   s    8 	 	
%%%	
 		
 %&!2#6 $!2#6 ,H)'>$.!2,(?%""4"-J*.L+$&&<#    c                 P    [         R                  " S[        5        U R                  $ )NzSThe `position_embedding_type` attribute is deprecated and will be removed in v4.55.)warningswarnFutureWarningr   )r&   s    r*   r'   &MarkupLMConfig.position_embedding_type   s"    a	
 ,,,r,   c                     Xl         g )N)r   )r&   values     r*   r'   r1      s    (-%r,   )r   r   r   r   r   r   r   r   r   r    r   r"   r!   r   r   r$   r#   r   r   r   r%   )i:w  i      r4   i   gelu皙?r6   i      g{Gz?g-q=r   r   r7      i      i      2   absoluteTN)__name__
__module____qualname____firstlineno____doc__
model_typer   propertyr'   setter__static_attributes____classcell__)r)   s   @r*   r   r      s    EN J %( #&)'+! *37=r - - ##. $.r,   r   )rA   r.   configuration_utilsr   utilsr   
get_loggerr=   loggerr   __all__r   r,   r*   <module>rL      s?    #  3  
		H	%M.% M.` 
r,   