
    gf                     ^    d Z ddlmZ ddlmZ  ej        e          Z G d de          ZdS )zPixtral model configuration   )PretrainedConfig)loggingc                   <     e Zd ZdZdZ	 	 	 	 	 	 	 	 	 	 d fd	Z xZS )PixtralVisionConfiga  
    This is the configuration class to store the configuration of a [`PixtralVisionModel`]. It is used to instantiate an
    Pixtral vision encoder according to the specified arguments, defining the model architecture. Instantiating a configuration
    with the defaults will yield a similar configuration to the vision encoder used by Pixtral-12B.

    e.g. [pixtral-hf/pixtral-9b](https://huggingface.co/pixtral-hf/pixtral-9b)

    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 1024):
            Dimension of the hidden representations.
        intermediate_size (`int`, *optional*, defaults to 4096):
            Dimension of the MLP representations.
        num_hidden_layers (`int`, *optional*, defaults to 24):
            Number of hidden layers in the Transformer encoder.
        num_attention_heads (`int`, *optional*, defaults to 16):
            Number of attention heads in the Transformer encoder.
        num_channels (`int`, *optional*, defaults to 3):
            Number of input channels in the input images.
        image_size (`int`, *optional*, defaults to 1024):
            Max dimension of the input images.
        patch_size (`int`, *optional*, defaults to 16):
            Size of the image patches.
        hidden_act (`str`, *optional*, defaults to `"gelu"`):
            Activation function used in the hidden layers.
        attention_dropout (`float`, *optional*, defaults to 0.0):
            Dropout probability for the attention layers.
        rope_theta (`float`, *optional*, defaults to 10000.0):
            The base period of the RoPE embeddings.

    Example:

    ```python
    >>> from transformers import PixtralVisionModel, PixtralVisionConfig

    >>> # Initializing a Pixtral-12B style configuration
    >>> config = PixtralVisionConfig()

    >>> # Initializing a model (with randomly initialized weights) from the configuration
    >>> model = PixtralVisionModel(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```pixtral            r   gelu             @c                      t                      j        di | || _        || _        || _        || _        || _        || _        || _        |	| _	        || _
        |
| _        ||z  | _        d S )N )super__init__hidden_sizeintermediate_sizenum_hidden_layersnum_attention_headsnum_channels
patch_size
image_sizeattention_dropout
hidden_act
rope_thetahead_dim)selfr   r   r   r   r   r   r   r   r   r   kwargs	__class__s               m/var/www/html/ai-engine/env/lib/python3.11/site-packages/transformers/models/pixtral/configuration_pixtral.pyr   zPixtralVisionConfig.__init__I   s     	""6"""&!2!2#6 ($$!2$$#'::    )
r   r	   r
   r   r   r   r   r   r   r   )__name__
__module____qualname____doc__
model_typer   __classcell__)r    s   @r!   r   r      so        - -^ J ; ; ; ; ; ; ; ; ; ;r"   r   N)	r&   configuration_utilsr   utilsr   
get_loggerr#   loggerr   r   r"   r!   <module>r-      s    " ! 3 3 3 3 3 3       
	H	%	%L; L; L; L; L;* L; L; L; L; L;r"   