Ë
    ÜÓ^j÷  ã                   ój   — d Z ddlmZ ddlmZ ddlmZ  ed¬«      e G d„ d	e«      «       «       Zd	gZy
)zVilT model configurationé    )Ústricté   )ÚPreTrainedConfig)Úauto_docstringzdandelin/vilt-b32-mlm)Ú
checkpointc                   ó˜  ‡ — e Zd ZU dZdZdZeed<   dZeed<   dZ	eed<   dZ
eed	<   d
Zeed<   dZeed<   dZeed<   dZeed<   dZeed<   dZeez  ed<   dZeez  ed<   dZeed<   dZeed<   dZeee   z  eeef   z  ed<   dZeee   z  eeef   z  ed<   dZeed<   d Zeed!<   d"Zeed#<   d Zeed$<   d"Zeed%<   d&Z ed&z  ed'<   ˆ fd(„Z!ˆ xZ"S ))Ú
ViltConfiga«  
    modality_type_vocab_size (`int`, *optional*, defaults to 2):
        The vocabulary size of the modalities passed when calling [`ViltModel`]. This is used after concatenating the
        embeddings of the text and image modalities.
    max_image_length (`int`, *optional*, defaults to -1):
        The maximum number of patches to take as input for the Transformer encoder. If set to a positive integer,
        the encoder will sample `max_image_length` patches at maximum. If set to -1, will not be taken into
        account.
    num_images (`int`, *optional*, defaults to -1):
        The number of images to use for natural language visual reasoning. If set to a positive integer, will be
        used by [`ViltForImagesAndTextClassification`] for defining the classifier head.

    Example:

    ```python
    >>> from transformers import ViLTModel, ViLTConfig

    >>> # Initializing a ViLT dandelin/vilt-b32-mlm style configuration
    >>> configuration = ViLTConfig()

    >>> # Initializing a model from the dandelin/vilt-b32-mlm style configuration
    >>> model = ViLTModel(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```Úvilti:w  Ú
vocab_sizeé   Útype_vocab_sizeÚmodality_type_vocab_sizeé(   Úmax_position_embeddingsi   Úhidden_sizeé   Únum_hidden_layersÚnum_attention_headsi   Úintermediate_sizeÚgeluÚ
hidden_actg        Úhidden_dropout_probÚattention_probs_dropout_probg{®Gáz”?Úinitializer_rangegê-�™—q=Úlayer_norm_epsi€  Ú
image_sizeé    Ú
patch_sizer   Únum_channelsTÚqkv_biaséÿÿÿÿÚmax_image_lengthÚtie_word_embeddingsÚ
num_imagesNÚpad_token_idc                 óV   •— |j                  dd «       d| _        t        ‰| �  di |¤Ž y )Nr#   T© )Úpopr#   ÚsuperÚ__post_init__)ÚselfÚkwargsÚ	__class__s     €úv/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/vilt/configuration_vilt.pyr*   zViltConfig.__post_init__L   s*   ø€ Ø�
‰
Ð(¨$Ô/Ø#'ˆÔ Ü‰ÑÑ' Ó'ó    )#Ú__name__Ú
__module__Ú__qualname__Ú__doc__Ú
model_typer   ÚintÚ__annotations__r   r   r   r   r   r   r   r   Ústrr   Úfloatr   r   r   r   ÚlistÚtupler   r   r    Úboolr"   r#   r$   r%   r*   Ú__classcell__)r-   s   @r.   r	   r	      s+  ø… ñð6 €Jà€J�ÓØ€O�SÓØ$%Ð˜cÓ%Ø#%Ð˜SÓ%Ø€K�ÓØÐ�sÓØ!Ð˜Ó!Ø!Ð�sÓ!Ø€J�ÓØ'*Ð˜ ™Ó*Ø03Ð  %¨#¡+Ó3Ø#Ð�uÓ#Ø!€N�EÓ!Ø47€J��d˜3‘i‘ %¨¨S¨¡/Ñ1Ó7Ø46€J��d˜3‘i‘ %¨¨S¨¡/Ñ1Ó6Ø€L�#ÓØ€HˆdÓØÐ�cÓØ $Ð˜Ó$Ø€J�ÓØ#€L�#˜‘*Ó#÷(ð (r/   r	   N)	r3   Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úutilsr   r	   Ú__all__r'   r/   r.   ú<module>rA      sG   ðñ å .å 3Ý #ñ Ð2Ô3Øô7(Ð!ó 7(ó ó 4ð7(ðt ˆ.�r/   