§
    ‚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VJEPA 2 model configurationé    )Ústricté   )ÚPreTrainedConfig)Úauto_docstringzfacebook/vjepa2-vitl-fpc64-256)Ú
checkpointc                   ó   — e Zd ZU dZdZ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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z  e	d<   dZee	d<   dZee	d<   dZee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e	d(<   dZ"eez  e	d)<   d*S )+ÚVJEPA2Configa¿  
    crop_size (`int`, *optional*, defaults to 256):
        Input resolution of the model
    frames_per_clip (`int`, *optional*, defaults to 64):
        The number of frames the model has been pretrained with. Does not impact inference.
    tubelet_size (`int`, *optional*, defaults to 2):
        The number of temporal frames used for a single rastor, check paper for more information.
    num_pooler_layers (`int`, *optional*, defaults to 3):
        The number of self-attention layers in the pooler.
    pred_hidden_size (`int`, *optional*, defaults to 384):
        Dimensionality of the predictor layers
    pred_num_attention_heads (`int`, *optional*, defaults to 12):
        Number of attention heads for each attention layer in the Predictor
    pred_num_hidden_layers (`int`, *optional*, defaults to 12):
        Number of hidden layers in the Predictor
    pred_num_mask_tokens (`int`, *optional*, defaults to 10):
        Define the number of mask tokens to use in the Predictor
    pred_zero_init_mask_tokens (`bool`, *optional*, defaults to `True`):
        Initialize the mask tokens in the predictor with 0.
    pred_mlp_ratio (`float`, *optional*, defaults to 4.0):
        Ratio of the hidden size of the MLPs used in Predictor relative to the `pred_hidden_size`.

    Example:

    ```python
    >>> from transformers import VJEPA2Config, VJEPA2Model

    >>> # Initializing a VJEPA2 vjepa2-vitl-fpc64-256 style configuration
    >>> configuration = VJEPA2Config()

    >>> # Initializing a model (with random weights) from the vjepa2-vitl-fpc64-256  style configuration
    >>> model = VJEPA2Model(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```Úvjepa2é   Ú
patch_sizeé   Ú	crop_sizeé@   Úframes_per_clipé   Útubelet_sizei   Úhidden_sizer   Úin_chansÚnum_attention_headsé   Únum_hidden_layersg        Údrop_path_rateg      @Ú	mlp_ratiog�íµ ÷Æ°>Úlayer_norm_epsTÚqkv_biasÚattention_probs_dropout_probÚgeluÚ
hidden_actg{®Gáz”?Úinitializer_rangeÚattention_dropoutÚnum_pooler_layersi€  Úpred_hidden_sizeé   Úpred_num_attention_headsÚpred_num_hidden_layersé
   Úpred_num_mask_tokensÚpred_zero_init_mask_tokensÚpred_mlp_ratioN)#Ú__name__Ú
__module__Ú__qualname__Ú__doc__Ú
model_typer   ÚintÚlistÚtupleÚ__annotations__r   r   r   r   r   r   r   r   Úfloatr   r   r   Úboolr   r   Ústrr   r    r!   r"   r$   r%   r'   r(   r)   © ó    úm/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/transformers/models/vjepa2/configuration_vjepa2.pyr	   r	      sÈ  € € € € € € ð#ð #ðJ €Jà46€J��d˜3”i‘ %¨¨S¨¤/Ñ1Ð6Ð6Ñ6Ø€IˆsÐÐÑØ€O�SÐÐÑØ€L�#ÐÐÑØ€K�ÐÐÑØ€HˆcÐÐÑØ!Ð˜Ð!Ð!Ñ!ØÐ�sÐÐÑØ"%€N�E˜C‘KÐ%Ð%Ñ%Ø €Iˆs�U‰{Ð Ð Ñ Ø €N�EÐ Ð Ñ Ø€HˆdÐÐÑØ03Ð  %¨#¡+Ð3Ð3Ñ3Ø€J�ÐÐÑØ#Ð�uÐ#Ð#Ñ#Ø%(Ð�u˜s‘{Ð(Ð(Ñ(ØÐ�sÐÐÑØÐ�cÐÐÑØ$&Ð˜cÐ&Ð&Ñ&Ø"$Ð˜CÐ$Ð$Ñ$Ø "Ð˜#Ð"Ð"Ñ"Ø'+Ð Ð+Ð+Ñ+Ø"%€N�C˜%‘KÐ%Ð%Ñ%Ð%Ð%r7   r	   N)	r-   Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úutilsr   r	   Ú__all__r6   r7   r8   ú<module>r=      s¢   ðð "Ð !à .Ð .Ð .Ð .Ð .Ð .à 3Ð 3Ð 3Ð 3Ð 3Ð 3Ø #Ð #Ð #Ð #Ð #Ð #ð €Ð;Ð<Ñ<Ô<Øð>&ð >&ð >&ð >&ð >&Ð#ñ >&ô >&ñ „ñ =Ô<ð>&ðB Ð
€€€r7   