
    <hq%                         S r SSKrSSKJr  SSKJr  SSKJrJr  SSK	J
r
Jr  SSKJrJr  SS	KJrJrJr  \R&                  " \5      r " S
 S\
5      r " S S\5      rSS/rg)zLayoutLM model configuration    NOrderedDict)Mapping)AnyOptional   )PretrainedConfigPreTrainedTokenizer)
OnnxConfigPatchingSpec)
TensorTypeis_torch_available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$ )	LayoutLMConfig   a  
This is the configuration class to store the configuration of a [`LayoutLMModel`]. It is used to instantiate a
LayoutLM 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 LayoutLM
[microsoft/layoutlm-base-uncased](https://huggingface.co/microsoft/layoutlm-base-uncased) 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 LayoutLM model. Defines the different tokens that can be represented by the
        *inputs_ids* passed to the forward method of [`LayoutLMModel`].
    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 [`LayoutLMModel`].
    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):
        The value used to pad input_ids.
    position_embedding_type (`str`, *optional*, defaults to `"absolute"`):
        Type of position embedding. Choose one of `"absolute"`, `"relative_key"`, `"relative_key_query"`. For
        positional embeddings use `"absolute"`. For more information on `"relative_key"`, please refer to
        [Self-Attention with Relative Position Representations (Shaw et al.)](https://huggingface.co/papers/1803.02155).
        For more information on `"relative_key_query"`, please refer to *Method 4* in [Improve Transformer Models
        with Better Relative Position Embeddings (Huang et al.)](https://huggingface.co/papers/2009.13658).
    use_cache (`bool`, *optional*, defaults to `True`):
        Whether or not the model should return the last key/values attentions (not used by all models). Only
        relevant if `config.is_decoder=True`.
    max_2d_position_embeddings (`int`, *optional*, defaults to 1024):
        The maximum value that the 2D position embedding might ever used. Typically set this to something large
        just in case (e.g., 1024).

Examples:

```python
>>> from transformers import LayoutLMConfig, LayoutLMModel

>>> # Initializing a LayoutLM configuration
>>> configuration = LayoutLMConfig()

>>> # Initializing a model (with random weights) from the configuration
>>> model = LayoutLMModel(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config
```layoutlmc                    > [         TU ]  " SSU0UD6  Xl        X l        X0l        X@l        X`l        XPl        Xpl        Xl	        Xl
        Xl        Xl        Xl        Xl        Xl        UU l        g )Npad_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max_2d_position_embeddings)selfr   r   r   r   r   r   r   r    r!   r"   r#   r$   r   position_embedding_typer&   r'   kwargs	__class__s                     k/var/www/html/shao/venv/lib/python3.13/site-packages/transformers/models/layoutlm/configuration_layoutlm.pyr   LayoutLMConfig.__init__e   ss    ( 	=l=f=$&!2#6 $!2#6 ,H)'>$.!2,(?%"*D'    c                 P    [         R                  " S[        5        U R                  $ )NzSThe `position_embedding_type` attribute is deprecated and will be removed in v4.55.)warningswarnFutureWarningr%   r(   s    r,   r)   &LayoutLMConfig.position_embedding_type   s"    a	
 ,,,r.   c                     Xl         g )N)r%   )r(   values     r,   r)   r4      s    (-%r.   )r%   r    r   r   r   r#   r   r$   r'   r!   r   r   r"   r&   r   )i:w  i      r7   i   gelu皙?r9   i      g{Gz?g-q=r   absoluteTi   )__name__
__module____qualname____firstlineno____doc__
model_typer   propertyr)   setter__static_attributes____classcell__r+   s   @r,   r   r      sx    BH J %( # *#'##EJ - - ##. $.r.   r   c                      ^  \ rS rSr  SS\S\S\\\      4U 4S jjjr	\
S\\\\\4   4   4S j5       r    SS\S	\S
\S\S\\   S\\\4   4U 4S jjjrSrU =r$ )LayoutLMOnnxConfig   configtaskpatching_specsc                 J   > [         TU ]  XUS9  UR                  S-
  U l        g )N)rK   rL      )r   r   r'   max_2d_positions)r(   rJ   rK   rL   r+   s       r,   r   LayoutLMOnnxConfig.__init__   s*     	>J & A AA Er.   returnc           	      H    [        SSSS.4SSSS.4SSSS.4SSSS.4/5      $ )N	input_idsbatchsequence)r   rN   bboxattention_masktoken_type_idsr   r3   s    r,   inputsLayoutLMOnnxConfig.inputs   sH    'j9:W45!w:#>?!w:#>?	
 	
r.   	tokenizer
batch_size
seq_lengthis_pair	frameworkc                    > [         T	U ]  XX4US9n/ SQnU[        R                  :X  d  [	        S5      e[        5       (       d  [        S5      eSSKnUS   R                  u  p#UR                  / U/U-  Q5      R                  USS5      US	'   U$ )
a>  
Generate inputs to provide to the ONNX exporter for the specific framework

Args:
    tokenizer: The tokenizer associated with this model configuration
    batch_size: The batch size (int) to export the model for (-1 means dynamic axis)
    seq_length: The sequence length (int) to export the model for (-1 means dynamic axis)
    is_pair: Indicate if the input is a pair (sentence 1, sentence 2)
    framework: The framework (optional) the tokenizer will generate tensor for

Returns:
    Mapping[str, Tensor] holding the kwargs to provide to the model's forward function
)r\   r]   r^   r_   )0   T   I      zCExporting LayoutLM to ONNX is currently only supported for PyTorch.z7Cannot generate dummy inputs without PyTorch installed.r   NrS   rN   rV   )r   generate_dummy_inputsr   PYTORCHNotImplementedErrorr   
ValueErrortorchshapetensortile)
r(   r[   r\   r]   r^   r_   
input_dictboxri   r+   s
            r,   re   (LayoutLMOnnxConfig.generate_dummy_inputs   s    , W2`i 3 


  J...%&kll!##VWW!+K!8!>!>
"\\*?SEJ,>*?@EEjRSUVW
6r.   )rO   )defaultN)rq   FN)r<   r=   r>   r?   r	   strr   listr   r   rB   r   intrY   r
   boolr   r   re   rD   rE   rF   s   @r,   rH   rH      s     7;	F F F !l!34	F F 
WS#X%6 67 
 
 *.&&& & 	&
 & J'& 
c	& &r.   rH   )r@   r0   collectionsr   collections.abcr   typingr   r    r	   r
   onnxr   r   utilsr   r   r   
get_loggerr<   loggerr   rH   __all__r   r.   r,   <module>r      s^    #  # #   5 , < < 
		H	%v.% v.r; ;| 1
2r.   