
    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
 ddlmZ  ej                  e      Z G d	 d
e      Z G d de
      Zy)zViT model configuration    OrderedDict)Mapping)version   )PretrainedConfig)
OnnxConfig)loggingc                   D     e Zd ZdZdZ	 	 	 	 	 	 	 	 	 	 	 	 	 	 d fd	Z xZS )	ViTConfiga  
    This is the configuration class to store the configuration of a [`ViTModel`]. It is used to instantiate an ViT
    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 ViT
    [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) architecture.

    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
    documentation from [`PretrainedConfig`] for more information.


    Args:
        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 0.0):
            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
        attention_probs_dropout_prob (`float`, *optional*, defaults to 0.0):
            The dropout ratio for the attention probabilities.
        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.
        image_size (`int`, *optional*, defaults to 224):
            The size (resolution) of each image.
        patch_size (`int`, *optional*, defaults to 16):
            The size (resolution) of each patch.
        num_channels (`int`, *optional*, defaults to 3):
            The number of input channels.
        qkv_bias (`bool`, *optional*, defaults to `True`):
            Whether to add a bias to the queries, keys and values.
        encoder_stride (`int`, *optional*, defaults to 16):
           Factor to increase the spatial resolution by in the decoder head for masked image modeling.

    Example:

    ```python
    >>> from transformers import ViTConfig, ViTModel

    >>> # Initializing a ViT vit-base-patch16-224 style configuration
    >>> configuration = ViTConfig()

    >>> # Initializing a model (with random weights) from the vit-base-patch16-224 style configuration
    >>> model = ViTModel(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```vitc                     t        |   di | || _        || _        || _        || _        || _        || _        || _        || _	        |	| _
        |
| _        || _        || _        || _        || _        y )N )super__init__hidden_sizenum_hidden_layersnum_attention_headsintermediate_size
hidden_acthidden_dropout_probattention_probs_dropout_probinitializer_rangelayer_norm_eps
image_size
patch_sizenum_channelsqkv_biasencoder_stride)selfr   r   r   r   r   r   r   r   r   r   r   r   r   r   kwargs	__class__s                   \/var/www/html/venv/lib/python3.12/site-packages/transformers/models/vit/configuration_vit.pyr   zViTConfig.__init__Y   s    $ 	"6"&!2#6 !2$#6 ,H)!2,$$( ,    )i      r%   i   gelu        r'   g{Gz?g-q=      r   Tr)   )__name__
__module____qualname____doc__
model_typer   __classcell__)r"   s   @r#   r   r      sF    6p J %(!- !-r$   r   c                   p    e Zd Z ej                  d      Zedeeee	ef   f   fd       Z
edefd       Zy)ViTOnnxConfigz1.11returnc                 (    t        ddddddfg      S )Npixel_valuesbatchr   heightwidth)r         r   r   r    s    r#   inputszViTOnnxConfig.inputs   s&    WHQX!YZ
 	
r$   c                      y)Ng-C6?r   r:   s    r#   atol_for_validationz!ViTOnnxConfig.atol_for_validation   s    r$   N)r*   r+   r,   r   parsetorch_onnx_minimum_versionpropertyr   strintr;   floatr=   r   r$   r#   r1   r1   }   sZ    !.v!6
WS#X%6 67 
 
 U  r$   r1   N)r-   collectionsr   typingr   	packagingr   configuration_utilsr   onnxr	   utilsr
   
get_loggerr*   loggerr   r1   r   r$   r#   <module>rL      sL     #   3   
		H	%\-  \-~J r$   