o
    ZŽh  ã                   @   s@   d Z ddlmZ ddlmZ e e¡ZG dd„ deƒZdgZ	dS )zPixtral model configurationé   )ÚPretrainedConfig)Úloggingc                       s<   e Zd ZdZdZ											
	d‡ fdd„	Z‡  ZS )ÚPixtralVisionConfigaT	  
    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.
        initializer_range (`float`, *optional*, defaults to 0.02):
            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.

    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
    ```Zpixtralé   é   é   é   r   Úgeluç        ç     ˆÃ@ç{®Gáz”?c                    sb   t ƒ jdi |¤Ž || _|| _|| _|| _|| _|| _|| _|	| _	|| _
|
| _|| | _|| _d S )N© )ÚsuperÚ__init__Úhidden_sizeÚintermediate_sizeÚnum_hidden_layersÚnum_attention_headsÚnum_channelsÚ
patch_sizeÚ
image_sizeÚattention_dropoutÚ
hidden_actÚ
rope_thetaZhead_dimÚinitializer_range)Úselfr   r   r   r   r   r   r   r   r   r   r   Úkwargs©Ú	__class__r   ú`/var/www/auris/lib/python3.10/site-packages/transformers/models/pixtral/configuration_pixtral.pyr   K   s   

zPixtralVisionConfig.__init__)r   r   r   r   r   r   r   r	   r
   r   r   )Ú__name__Ú
__module__Ú__qualname__Ú__doc__Z
model_typer   Ú__classcell__r   r   r   r   r      s    1ôr   N)
r#   Zconfiguration_utilsr   Úutilsr   Z
get_loggerr    Úloggerr   Ú__all__r   r   r   r   Ú<module>   s   

S