+
    œ°³j  ã                   ól   € R t ^ RIHt ^RIHt ^RIHt ]! RR7      ] ! R R]4      4       4       tR.tR# )	zVideoMAE model configuration)Ústrict)ÚPreTrainedConfig)Úauto_docstringzMCG-NJU/videomae-base)Ú
checkpointc                   óˆ   a € ] tR t^t o RtRt^àt^t^t^t	^t
Rt^t^tRtRtRtRtRtRtR	tR	t^tR
t^tRtR	tV 3R ltRtV tR# )ÚVideoMAEConfiga  
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videomaei   i   Úgelug        g{®Gáz”?gê-�™—q=Ti€  i   c                óÂ  <€ V ^8„  d   Qh/ S[ S[S[ ,          ,          S[S[ S[ 3,          ,          ;R&   S[ S[S[ ,          ,          S[S[ S[ 3,          ,          ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R	&   S[;R
&   S[S[ ,          ;R&   S[S[ ,          ;R&   S[;R&   S[;R&   S[;R&   S[;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[;R&   # )é   Ú
image_sizeÚ
patch_sizeÚnum_channelsÚ
num_framesÚtubelet_sizeÚhidden_sizeÚnum_hidden_layersÚnum_attention_headsÚintermediate_sizeÚ
hidden_actÚhidden_dropout_probÚattention_probs_dropout_probÚinitializer_rangeÚlayer_norm_epsÚqkv_biasÚuse_mean_poolingÚdecoder_num_attention_headsÚdecoder_hidden_sizeÚdecoder_num_hidden_layersÚdecoder_intermediate_sizeÚnorm_pix_loss)ÚintÚlistÚtupleÚstrÚfloatÚbool)ÚformatÚ__classdict__s   "€Út/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/videomae/configuration_videomae.pyÚ__annotate__ÚVideoMAEConfig.__annotate__   sr  ø‡ ‚ ñL ‘d™3•i•¡%©©S¨¥/Õ1Ñ7ñM ñN ‘d™3•i•¡%©©S¨¥/Õ1Ñ6ñO ñP ÑñQ ñR ÑñS ñT ÑñU ñV ÑñW ñX ÑñY ñZ Ñ!ñ[ ñ\ Ñ!ñ] ñ^ Ññ_ ñ` ¡�Ñ*ña ñb #(©#¥+Ñ3ñc ñd Ñ#ñe ñf Ñ!ñg ñh Ññi ñj Ñ!ñk ñl "%Ñ(ñm ñn Ñ"ño ñp  #Ñ&ñq ñr  #Ñ)ñs ñt Ñòu ó    © N)Ú__name__Ú
__module__Ú__qualname__Ú__firstlineno__Ú__doc__Ú
model_typer   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r    Ú__annotate_func__Ú__static_attributes__Ú__classdictcell__)r(   s   @r)   r   r      sŽ   ø‡ € ñðB €Jà47€JØ46€JØ€LØ€JØ€LØ€KØÐØ!ÐØ!ÐØ€JØ'*ÐØ03Ð Ø#ÐØ!€NØ€HØ!ÐØ'(ÐØ"ÐØ%&ÐØ%)ÐØ€M÷u ƒ r,   r   N)	r2   Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úutilsr   r   Ú__all__r-   r,   r)   Ú<module>r;      sH   ðñ #å .å 3Ý #ñ Ð2Ô3Øô8Ð%ó 8ó ó 4ð8ðv Ð
‚r,   