ó
    qyüi  ã                   ód   • S r SSKJr  SSKJr  SSKJr  \" SS9\ " S S	\5      5       5       rS	/rg
)zVideoMAE model configurationé    )Ústricté   )ÚPreTrainedConfig)Úauto_docstringzMCG-NJU/videomae-base)Ú
checkpointc                   óˆ  • \ rS rSr% SrSrSr\\\   -  \	\\4   -  \
S'   Sr\\\   -  \	\\4   -  \
S'   Sr\\
S	'   Sr\\
S
'   Sr\\
S'   Sr\\
S'   Sr\\
S'   Sr\\
S'   Sr\\
S'   Sr\\
S'   Sr\\-  \
S'   Sr\\-  \
S'   Sr\\
S'   Sr\\
S'   Sr\\
S'   Sr\\
S'   S r\\
S!'   S"r\\
S#'   S$r\\
S%'   S&r \\
S''   Sr!\\
S('   S)r"g*)+ÚVideoMAEConfigé   a  
num_frames (`int`, *optional*, defaults to 16):
    The number of frames in each video.
tubelet_size (`int`, *optional*, defaults to 2):
    The number of tubelets.
use_mean_pooling (`bool`, *optional*, defaults to `True`):
    Whether to mean pool the final hidden states instead of using the final hidden state of the [CLS] token.
decoder_num_attention_heads (`int`, *optional*, defaults to 6):
    Number of attention heads for each attention layer in the decoder.
decoder_hidden_size (`int`, *optional*, defaults to 384):
    Dimensionality of the decoder.
decoder_num_hidden_layers (`int`, *optional*, defaults to 4):
    Number of hidden layers in the decoder.
decoder_intermediate_size (`int`, *optional*, defaults to 1536):
    Dimensionality of the "intermediate" (i.e., feed-forward) layer in the decoder.
norm_pix_loss (`bool`, *optional*, defaults to `True`):
    Whether to normalize the target patch pixels.

Example:

```python
>>> from transformers import VideoMAEConfig, VideoMAEModel

>>> # Initializing a VideoMAE videomae-base style configuration
>>> configuration = VideoMAEConfig()

>>> # Randomly initializing a model from the configuration
>>> model = VideoMAEModel(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config
```Úvideomaeéà   Ú
image_sizeé   Ú
patch_sizer   Únum_channelsÚ
num_framesé   Útubelet_sizei   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_epsTÚqkv_biasÚuse_mean_poolingé   Údecoder_num_attention_headsi€  Údecoder_hidden_sizeé   Údecoder_num_hidden_layersi   Údecoder_intermediate_sizeÚnorm_pix_loss© N)#Ú__name__Ú
__module__Ú__qualname__Ú__firstlineno__Ú__doc__Ú
model_typer   ÚintÚlistÚtupleÚ__annotations__r   r   r   r   r   r   r   r   r   Ústrr   Úfloatr   r   r   r   Úboolr    r"   r#   r%   r&   r'   Ú__static_attributes__r(   ó    Úp/home/mande/repo/quber/.venv/lib/python3.13/site-packages/transformers/models/videomae/configuration_videomae.pyr	   r	      s  ‡ ñðB €Jà47€J��d˜3‘i‘ %¨¨S¨¡/Ñ1Ó7Ø46€J��d˜3‘i‘ %¨¨S¨¡/Ñ1Ó6Ø€L�#ÓØ€J�ÓØ€L�#Ó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!Ø€HˆdÓØ!Ð�dÓ!Ø'(Ð Ó(Ø"Ð˜Ó"Ø%&Ð˜sÓ&Ø%)Ð˜sÓ)Ø€M�4Ör7   r	   N)	r-   Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úutilsr   r	   Ú__all__r(   r7   r8   Ú<module>r=      sH   ðñ #å .å 3Ý #ñ Ð2Ñ3Øô8Ð%ó 8ó ó 4ð8ðv Ð
�r7   