§
    ‚Štj÷  ã                   ó„   — 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d
S )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                 ót   •— |                      dd ¦  «         d| _         t          ¦   «         j        di |¤Ž d S )Nr#   T© )Úpopr#   ÚsuperÚ__post_init__)ÚselfÚkwargsÚ	__class__s     €úi/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/transformers/models/vilt/configuration_vilt.pyr*   zViltConfig.__post_init__L   sC   ø€ Ø�
Š
Ð(¨$Ñ/Ô/Ð/Ø#'ˆÔ Ø�‰ŒÔÐ'Ð' Ð'Ð'Ð'Ð'Ð'ó    )#Ú__name__Ú
__module__Ú__qualname__Ú__doc__Ú
model_typer   ÚintÚ__annotations__r   r   r   r   r   r   r   r   Ústrr   Úfloatr   r   r   r   ÚlistÚtupler   r   r    Úboolr"   r#   r$   r%   r*   Ú__classcell__)r-   s   @r.   r	   r	      sÛ  ø€ € € € € € ðð ð6 €Jà€J�ÐÐÑØ€O�SÐÐÑØ$%Ð˜cÐ%Ð%Ñ%Ø#%Ð˜SÐ%Ð%Ñ%Ø€K�ÐÐÑØÐ�sÐÐÑØ!Ð˜Ð!Ð!Ñ!Ø!Ð�sÐ!Ð!Ñ!Ø€J�ÐÐÑØ'*Ð˜ ™Ð*Ð*Ñ*Ø03Ð  %¨#¡+Ð3Ð3Ñ3Ø#Ð�uÐ#Ð#Ñ#Ø!€N�EÐ!Ð!Ñ!Ø47€J��d˜3”i‘ %¨¨S¨¤/Ñ1Ð7Ð7Ñ7Ø46€J��d˜3”i‘ %¨¨S¨¤/Ñ1Ð6Ð6Ñ6Ø€L�#ÐÐÑØ€HˆdÐÐÑØÐ�cÐÐÑØ $Ð˜Ð$Ð$Ñ$Ø€J�ÐÐÑØ#€L�#˜‘*Ð#Ð#Ñ#ð(ð (ð (ð (ð (ð (ð (ð (ð (r/   r	   N)	r3   Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úutilsr   r	   Ú__all__r'   r/   r.   ú<module>rA      s¡   ðð Ð à .Ð .Ð .Ð .Ð .Ð .à 3Ð 3Ð 3Ð 3Ð 3Ð 3Ø #Ð #Ð #Ð #Ð #Ð #ð €Ð2Ð3Ñ3Ô3Øð7(ð 7(ð 7(ð 7(ð 7(Ð!ñ 7(ô 7(ñ „ñ 4Ô3ð7(ðt ˆ.€€€r/   