+
    œ°³jO  ã                   óz   € R t ^ RIH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BEiT model configuration)Ústrict)ÚBackboneConfigMixin)ÚPreTrainedConfig)Úauto_docstringz%microsoft/beit-base-patch16-224-pt22k)Ú
checkpointc                   óÂ   a a€ ] tR t^t oRtRtRtRt^t^t	Rt
RtRtRtRtR	t^àt^t^tR
tR
tR
tR
tRtRtRtRtRtRtRt^tR
t^ÿt Rt!Rt"R
t#Rt$V 3R lt%V3R lt&Rt'Vt(V ;t)# )Ú
BeitConfigaC	  
use_mask_token (`bool`, *optional*, defaults to `False`):
    Whether to use a mask token for masked image modeling.
use_relative_position_bias (`bool`, *optional*, defaults to `False`):
    Whether to use T5-style relative position embeddings in the self-attention layers.
use_shared_relative_position_bias (`bool`, *optional*, defaults to `False`):
    Whether to use the same relative position embeddings across all self-attention layers of the Transformer.
use_mean_pooling (`bool`, *optional*, defaults to `True`):
    Whether to mean pool the final hidden states of the patches instead of using the final hidden state of the
    CLS token, before applying the classification head.
pool_scales (`tuple[int]`, *optional*, defaults to `[1, 2, 3, 6]`):
    Pooling scales used in Pooling Pyramid Module applied on the last feature map.
use_auxiliary_head (`bool`, *optional*, defaults to `True`):
    Whether to use an auxiliary head during training.
auxiliary_loss_weight (`float`, *optional*, defaults to 0.4):
    Weight of the cross-entropy loss of the auxiliary head.
auxiliary_channels (`int`, *optional*, defaults to 256):
    Number of channels to use in the auxiliary head.
auxiliary_num_convs (`int`, *optional*, defaults to 1):
    Number of convolutional layers to use in the auxiliary head.
auxiliary_concat_input (`bool`, *optional*, defaults to `False`):
    Whether to concatenate the output of the auxiliary head with the input before the classification layer.
add_fpn (`bool`, *optional*, defaults to `False`):
    Whether to add a FPN as part of the backbone. Only relevant for [`BeitBackbone`].
reshape_hidden_states (`bool`, *optional*, defaults to `True`):
    Whether to reshape the feature maps to 4D tensors of shape `(batch_size, hidden_size, height, width)` in
    case the model is used as backbone. If `False`, the feature maps will be 3D tensors of shape `(batch_size,
        seq_len, hidden_size)`. Only relevant for [`BeitBackbone`].

Example:

```python
>>> from transformers import BeitConfig, BeitModel

>>> # Initializing a BEiT beit-base-patch16-224-pt22k style configuration
>>> configuration = BeitConfig()

>>> # Initializing a model (with random weights) from the beit-base-patch16-224-pt22k style configuration
>>> model = BeitModel(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config
```Úbeiti    i   i   Úgelug        g{®Gáz”?gê-�™—q=Fgš™™™™™¹?Tgš™™™™™Ù?é   Nc                óø  <€ R V9   d(   VP                  R4      f   VP                  R 4      VR&   R.\        ^V P                  ^,           4       Uu. uF  pRV 2NK
  	  up,           V n        V P                  VP                  RR4      VP                  RR4      R7       V P                  '       d4   V P                  e   \        V P                  4      ^8w  d   \        R4      h\        SV `,  ! R/ VB  R# u upi )	Úsegmentation_indicesÚout_indicesNÚstemÚstageÚout_features)r   r   zÔBeitConfig requires `out_indices` to be a list of exactly 4 integers when `add_fpn=True`, specifying which features to use from the backbone. One can use `out_indices=[3, 5, 7, 11]` for a base-sized architecture.© )ÚgetÚpopÚrangeÚnum_hidden_layersÚstage_namesÚ"set_output_features_output_indicesÚadd_fpnÚ_out_indicesÚlenÚ
ValueErrorÚsuperÚ__post_init__)ÚselfÚkwargsÚidxÚ	__class__s   &, €Úl/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/beit/configuration_beit.pyr   ÚBeitConfig.__post_init__h   së   ø€ Ø! VÔ+°·
±
¸=Ó0IÒ0QØ$*§J¡JÐ/EÓ$FˆF�=Ñ!ð #˜8ÄÀaÈ×I_ÑI_ÐbcÕIcÔ@dÓ&eÑ@d¸¨¨s¨e£}Ñ@dÑ&eÕeˆÔØ×/Ñ/ØŸ
™
 =°$Ó7ÀfÇjÁjÐQ_ÐaeÓFfð 	0ô 	
ð �<�<ˆ<˜T×.Ñ.Ò6¼#¸d×>OÑ>OÓ:PÐTUÔ:UÜð1óð ô 	‰ÒÑ' Ô'ùò 'fs   ÁC7c                óº  <€ V ^8„  d   Qh/ S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[;R&   S[S[ ,          ;R&   S[S[ ,          ;R&   S[;R	&   S[;R
&   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[S[ ,          ;R&   S[;R&   S[S[ ,          S[S[ R3,          ,          ;R&   S[;R&   S[;R&   S[ ;R&   S[ ;R&   S[;R&   S[ ;R&   S[S[,          R,          ;R&   S[S[ ,          R,          ;R&   S[;R &   S[;R!&   # )"é   Ú
vocab_sizeÚhidden_sizer   Únum_attention_headsÚintermediate_sizeÚ
hidden_actÚhidden_dropout_probÚattention_probs_dropout_probÚinitializer_rangeÚlayer_norm_epsÚ
image_sizeÚ
patch_sizeÚnum_channelsÚuse_mask_tokenÚ use_absolute_position_embeddingsÚuse_relative_position_biasÚ!use_shared_relative_position_biasÚlayer_scale_init_valueÚdrop_path_rateÚuse_mean_pooling.Úpool_scalesÚuse_auxiliary_headÚauxiliary_loss_weightÚauxiliary_channelsÚauxiliary_num_convsÚauxiliary_concat_inputÚsemantic_loss_ignore_indexNÚ_out_featuresr   r   Úreshape_hidden_states)ÚintÚstrÚfloatÚlistÚtupleÚbool)ÚformatÚ__classdict__s   "€r#   Ú__annotate__ÚBeitConfig.__annotate__   s/  ø‡ ‚ ñb Ññc ñd Ññe ñf Ññg ñh Ñ!ñi ñj Ñ!ñk ñl Ññm ñn ¡�Ñ*ño ñp #(©#¥+Ñ3ñq ñr Ñ#ñs ñt Ñ!ñu ñv ‘d™3•i•¡%©©S¨¥/Õ1Ñ7ñw ñx ‘d™3•i•¡%©©S¨¥/Õ1Ñ6ñy ñz Ññ{ ñ| Ñ ñ} ñ~ '+Ñ2ñ ñ@ !%Ñ,ñA ñB (,Ñ3ñC ñD "Ñ'ñE ñF ™C•KÑ%ñG ñH Ñ!ñI ñJ ‘c•™U¡3¨ 8�_Õ,Ñ;ñK ñL Ñ#ñM ñN !Ñ&ñO ñP Ñ!ñQ ñR Ñ ñS ñT !Ñ(ñU ñV !$Ñ)ñW ñX ™•9˜tÕ#Ñ*ñY ñZ ‘s•)˜dÕ"Ñ)ñ[ ñ\ Ññ] ñ^  Ñ&ò_ ó    )r   )é   r&   é   é   )*Ú__name__Ú
__module__Ú__qualname__Ú__firstlineno__Ú__doc__Ú
model_typer'   r(   r   r)   r*   r+   r,   r-   r.   r/   r0   r1   r2   r3   r4   r5   r6   r7   r8   r9   r:   r;   r<   r=   r>   r?   r@   rA   r   r   rB   r   Ú__annotate_func__Ú__static_attributes__Ú__classdictcell__Ú__classcell__)r"   rJ   s   @@r#   r   r      sÌ   ù‡ € ñ*ðX €Jà€JØ€KØÐØ!ÐØ!ÐØ€JØ'*ÐØ03Ð Ø#ÐØ!€NØ47€JØ46€JØ€LØ €NØ-2Ð$Ø',ÐØ.3Ð%Ø$'ÐØ"%€NØ!ÐØ/;€KØ#ÐØ#&ÐØ!ÐØ ÐØ#(ÐØ&)ÐØ&*€MØ%)€LØ€GØ"&Ðõ(÷c … rM   r   N)rU   Úhuggingface_hub.dataclassesr   Úbackbone_utilsr   Úconfiguration_utilsr   Úutilsr   r   Ú__all__r   rM   r#   Ú<module>r`      sQ   ðñ å .å 1Ý 3Ý #ñ ÐBÔCØô`(Ð$Ð&6ó `(ó ó Dð`(ðF ˆ.‚rM   