
    sg                         d Z ddlmZ ddlmZ ddlmZ ddlmZ ddl	m
Z
  e
j                  e      Z G d d	e      Z G d
 de      Zy)zConvBERT model configuration    )OrderedDict)Mapping   )PretrainedConfig)
OnnxConfig)loggingc                   P     e Zd ZdZdZ	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 d fd	Z xZS )ConvBertConfigaV  
    This is the configuration class to store the configuration of a [`ConvBertModel`]. It is used to instantiate an
    ConvBERT 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 ConvBERT
    [YituTech/conv-bert-base](https://huggingface.co/YituTech/conv-bert-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 ConvBERT model. Defines the number of different tokens that can be represented by
            the `inputs_ids` passed when calling [`ConvBertModel`] or [`TFConvBertModel`].
        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"`, `"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 [`ConvBertModel`] or [`TFConvBertModel`].
        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.
        head_ratio (`int`, *optional*, defaults to 2):
            Ratio gamma to reduce the number of attention heads.
        num_groups (`int`, *optional*, defaults to 1):
            The number of groups for grouped linear layers for ConvBert model
        conv_kernel_size (`int`, *optional*, defaults to 9):
            The size of the convolutional kernel.
        classifier_dropout (`float`, *optional*):
            The dropout ratio for the classification head.

    Example:

    ```python
    >>> from transformers import ConvBertConfig, ConvBertModel

    >>> # Initializing a ConvBERT convbert-base-uncased style configuration
    >>> configuration = ConvBertConfig()

    >>> # Initializing a model (with random weights) from the convbert-base-uncased style configuration
    >>> model = ConvBertModel(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```convbertc                    t        |   d|||d| || _        || _        || _        || _        || _        || _        || _        || _	        |	| _
        |
| _        || _        || _        || _        || _        || _        || _        || _        y )N)pad_token_idbos_token_ideos_token_id )super__init__
vocab_sizehidden_sizenum_hidden_layersnum_attention_headsintermediate_size
hidden_acthidden_dropout_probattention_probs_dropout_probmax_position_embeddingstype_vocab_sizeinitializer_rangelayer_norm_epsembedding_size
head_ratioconv_kernel_size
num_groupsclassifier_dropout)selfr   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r    r!   r"   r#   kwargs	__class__s                         f/var/www/html/venv/lib/python3.12/site-packages/transformers/models/convbert/configuration_convbert.pyr   zConvBertConfig.__init__]   s    0 	 	
%%%	
 		
 %&!2#6 !2$#6 ,H)'>$.!2,,$ 0$"4    )i:w        r*   i   gelu皙?r,   i      g{Gz?g-q=   r   r-   r)   r-   	   r.   N)__name__
__module____qualname____doc__
model_typer   __classcell__)r&   s   @r'   r
   r
      sX    <| J %( #+/5 /5r(   r
   c                   6    e Zd Zedeeeeef   f   fd       Zy)ConvBertOnnxConfigreturnc                 `    | j                   dk(  rdddd}nddd}t        d|fd|fd	|fg      S )
Nzmultiple-choicebatchchoicesequence)r   r.   r-   )r   r.   	input_idsattention_masktoken_type_ids)taskr   )r$   dynamic_axiss     r'   inputszConvBertOnnxConfig.inputs   sO    99))&8
CL&:6Ll+!<0!<0
 	
r(   N)r0   r1   r2   propertyr   strintrB   r   r(   r'   r7   r7      s.    
WS#X%6 67 
 
r(   r7   N)r3   collectionsr   typingr   configuration_utilsr   onnxr   utilsr   
get_loggerr0   loggerr
   r7   r   r(   r'   <module>rM      sI    # #  3   
		H	%p5% p5h
 
r(   