a
    ½Àh§  ã                   @   sv   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
 e¡ZG dd	„ d	eƒZG d
d„ deƒZd	dgZdS )zDistilBERT model configurationé    )ÚOrderedDict)ÚMappingé   )ÚPretrainedConfig)Ú
OnnxConfig)Úloggingc                       s2   e Zd ZdZdZddddœZd‡ fdd„	Z‡  ZS )Ú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
    ```Z
distilbertÚdimÚn_headsÚn_layers)Zhidden_sizeZnum_attention_headsZnum_hidden_layersé:w  é   Fé   é   é   é   çš™™™™™¹?Úgeluç{®Gáz”?çš™™™™™É?r   c                    sl   || _ || _|| _|| _|| _|| _|| _|| _|	| _|
| _	|| _
|| _|| _tƒ jf i |¤d|i¤Ž d S )NÚpad_token_id)Ú
vocab_sizeÚmax_position_embeddingsÚsinusoidal_pos_embdsr   r
   r	   Ú
hidden_dimÚdropoutÚattention_dropoutÚ
activationÚinitializer_rangeÚ
qa_dropoutÚseq_classif_dropoutÚsuperÚ__init__)Úselfr   r   r   r   r
   r	   r   r   r   r   r   r   r    r   Úkwargs©Ú	__class__© ús/var/www/html/assistant/venv/lib/python3.9/site-packages/transformers/models/distilbert/configuration_distilbert.pyr"   \   s    zDistilBertConfig.__init__)r   r   Fr   r   r   r   r   r   r   r   r   r   r   )Ú__name__Ú
__module__Ú__qualname__Ú__doc__Z
model_typeZattribute_mapr"   Ú__classcell__r'   r'   r%   r(   r      s*   8ý              ñr   c                   @   s.   e Zd Zeeeeeef f dœdd„ƒZdS )ÚDistilBertOnnxConfig)Úreturnc                 C   s6   | j dkrddddœ}n
dddœ}td|fd|fgƒS )	Nzmultiple-choiceÚbatchÚchoiceÚsequence)r   é   é   )r   r3   Z	input_idsZattention_mask)Útaskr   )r#   Zdynamic_axisr'   r'   r(   Úinputs   s    

þÿzDistilBertOnnxConfig.inputsN)r)   r*   r+   Úpropertyr   ÚstrÚintr6   r'   r'   r'   r(   r.   ~   s   r.   N)r,   Úcollectionsr   Úcollections.abcr   Zconfiguration_utilsr   Zonnxr   Úutilsr   Z
get_loggerr)   Úloggerr   r.   Ú__all__r'   r'   r'   r(   Ú<module>   s   
b