
    sge                         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DistilBERT model configuration    )OrderedDict)Mapping   )PretrainedConfig)
OnnxConfig)loggingc                   P     e Zd ZdZdZddddZ	 	 	 	 	 	 	 	 	 	 	 	 	 	 d fd	Z xZS )	DistilBertConfiga  
    This is the configuration class to store the configuration of a [`DistilBertModel`] or a [`TFDistilBertModel`]. It
    is used to instantiate a DistilBERT 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 DistilBERT
    [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) 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 DistilBERT model. Defines the number of different tokens that can be represented by
            the `inputs_ids` passed when calling [`DistilBertModel`] or [`TFDistilBertModel`].
        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).
        sinusoidal_pos_embds (`boolean`, *optional*, defaults to `False`):
            Whether to use sinusoidal positional embeddings.
        n_layers (`int`, *optional*, defaults to 6):
            Number of hidden layers in the Transformer encoder.
        n_heads (`int`, *optional*, defaults to 12):
            Number of attention heads for each attention layer in the Transformer encoder.
        dim (`int`, *optional*, defaults to 768):
            Dimensionality of the encoder layers and the pooler layer.
        hidden_dim (`int`, *optional*, defaults to 3072):
            The size of the "intermediate" (often named feed-forward) layer in the Transformer encoder.
        dropout (`float`, *optional*, defaults to 0.1):
            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
        attention_dropout (`float`, *optional*, defaults to 0.1):
            The dropout ratio for the attention probabilities.
        activation (`str` or `Callable`, *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.
        initializer_range (`float`, *optional*, defaults to 0.02):
            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
        qa_dropout (`float`, *optional*, defaults to 0.1):
            The dropout probabilities used in the question answering model [`DistilBertForQuestionAnswering`].
        seq_classif_dropout (`float`, *optional*, defaults to 0.2):
            The dropout probabilities used in the sequence classification and the multiple choice model
            [`DistilBertForSequenceClassification`].

    Examples:

    ```python
    >>> from transformers import DistilBertConfig, DistilBertModel

    >>> # Initializing a DistilBERT configuration
    >>> configuration = DistilBertConfig()

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

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```
distilbertdimn_headsn_layers)hidden_sizenum_attention_headsnum_hidden_layersc                     || _         || _        || _        || _        || _        || _        || _        || _        |	| _        |
| _	        || _
        || _        || _        t        | 8  di |d|i y )Npad_token_id )
vocab_sizemax_position_embeddingssinusoidal_pos_embdsr   r   r   
hidden_dimdropoutattention_dropout
activationinitializer_range
qa_dropoutseq_classif_dropoutsuper__init__)selfr   r   r   r   r   r   r   r   r   r   r   r   r   r   kwargs	__class__s                   j/var/www/html/venv/lib/python3.12/site-packages/transformers/models/distilbert/configuration_distilbert.pyr    zDistilBertConfig.__init__\   sz    $ %'>$$8! $!2$!2$#6 =6==    )i:w  i   F      i   i   皙?r(   gelug{Gz?r(   g?r   )__name__
__module____qualname____doc__
model_typeattribute_mapr    __classcell__)r#   s   @r$   r
   r
      sV    6p J('M  #"> >r%   r
   c                   6    e Zd Zedeeeeef   f   fd       Zy)DistilBertOnnxConfigreturnc                 Z    | j                   dk(  rdddd}nddd}t        d|fd|fg      S )	Nzmultiple-choicebatchchoicesequence)r         )r   r8   	input_idsattention_mask)taskr   )r!   dynamic_axiss     r$   inputszDistilBertOnnxConfig.inputs   sG    99))&8
CL&:6Ll+!<0
 	
r%   N)r*   r+   r,   propertyr   strintr>   r   r%   r$   r2   r2   ~   s.    

WS#X%6 67 

 

r%   r2   N)r-   collectionsr   typingr   configuration_utilsr   onnxr   utilsr   
get_loggerr*   loggerr
   r2   r   r%   r$   <module>rI      sI    % #  3   
		H	%_>' _>D
: 
r%   