+
    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CvT model configuration)Ústrict)ÚPreTrainedConfig)Úauto_docstringzmicrosoft/cvt-13)Ú
checkpointc                   óˆ   a € ] tR t^t o RtRt^tRtR	tR
t	Rt
RtRtRtRtRtRtRtRtRtRtRtRtRtRtRtRtV 3R ltRtV tR# )Ú	CvtConfiga­  
patch_stride (`list[int]`, *optional*, defaults to `[4, 2, 2]`):
    The stride size of each encoder's patch embedding.
patch_padding (`list[int]`, *optional*, defaults to `[2, 1, 1]`):
    The padding size of each encoder's patch embedding.
depth (`list[int]`, *optional*, defaults to `[1, 2, 10]`):
    The number of layers in each encoder block.
attention_drop_rate (`list[float]`, *optional*, defaults to `[0.0, 0.0, 0.0]`):
    The dropout ratio for the attention probabilities.
drop_rate (`list[float]`, *optional*, defaults to `[0.0, 0.0, 0.0]`):
    The dropout ratio for the patch embeddings probabilities.
cls_token (`list[bool]`, *optional*, defaults to `[False, False, True]`):
    Whether or not to add a classification token to the output of each of the last 3 stages.
qkv_projection_method (`list[string]`, *optional*, defaults to ["dw_bn", "dw_bn", "dw_bn"]`):
    The projection method for query, key and value Default is depth-wise convolutions with batch norm. For
    Linear projection use "avg".
kernel_qkv (`list[int]`, *optional*, defaults to `[3, 3, 3]`):
    The kernel size for query, key and value in attention layer
padding_kv (`list[int]`, *optional*, defaults to `[1, 1, 1]`):
    The padding size for key and value in attention layer
stride_kv (`list[int]`, *optional*, defaults to `[2, 2, 2]`):
    The stride size for key and value in attention layer
padding_q (`list[int]`, *optional*, defaults to `[1, 1, 1]`):
    The padding size for query in attention layer
stride_q (`list[int]`, *optional*, defaults to `[1, 1, 1]`):
    The stride size for query in attention layer

Example:

```python
>>> from transformers import CvtConfig, CvtModel

>>> # Initializing a Cvt msft/cvt style configuration
>>> configuration = CvtConfig()

>>> # Initializing a model (with random weights) from the msft/cvt style configuration
>>> model = CvtModel(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config
```Úcvtg{®Gáz”?gê-�™—q=c                ó¾  <€ V ^8„  d   Qh/ S[ ;R&   S[S[ ,          S[S[ R3,          ,          ;R&   S[S[ ,          S[S[ R3,          ,          ;R&   S[S[ ,          S[S[ R3,          ,          ;R&   S[S[ ,          S[S[ R3,          ,          ;R&   S[S[ ,          S[S[ R3,          ,          ;R&   S[S[ ,          S[S[ R3,          ,          ;R&   S[S[,          S[S[R3,          ,          ;R	&   S[S[,          S[S[R3,          ,          ;R
&   S[S[,          S[S[R3,          ,          ;R&   S[S[,          S[S[R3,          ,          ;R&   S[S[,          S[S[R3,          ,          ;R&   S[S[,          S[S[R3,          ,          ;R&   S[S[,          S[S[R3,          ,          ;R&   S[S[ ,          S[S[ R3,          ,          ;R&   S[S[ ,          S[S[ R3,          ,          ;R&   S[S[ ,          S[S[ R3,          ,          ;R&   S[S[ ,          S[S[ R3,          ,          ;R&   S[S[ ,          S[S[ R3,          ,          ;R&   S[;R&   S[;R&   # )é   Únum_channels.Úpatch_sizesÚpatch_strideÚpatch_paddingÚ	embed_dimÚ	num_headsÚdepthÚ	mlp_ratioÚattention_drop_rateÚ	drop_rateÚdrop_path_rateÚqkv_biasÚ	cls_tokenÚqkv_projection_methodÚ
kernel_qkvÚ
padding_kvÚ	stride_kvÚ	padding_qÚstride_qÚinitializer_rangeÚlayer_norm_eps)ÚintÚlistÚtupleÚfloatÚboolÚstr)ÚformatÚ__classdict__s   "€Új/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/cvt/configuration_cvt.pyÚ__annotate__ÚCvtConfig.__annotate__   sx  ø‡ ‚ ñ^ Ññ_ ñ` ‘c•™U¡3¨ 8�_Õ,Ñ8ña ñb ‘s•)™e¡C¨ H�oÕ-Ñ9ñc ñd ™•9™u¡S¨# X�Õ.Ñ:ñe ñf ‘C�y™5¡ c �?Õ*Ñ;ñg ñh ‘C�y™5¡ c �?Õ*Ñ6ñi ñj ‘�9‘u™S #˜X•Õ&Ñ3ñk ñl ‘E�{™U¡5¨# :Õ.Õ.Ñ@ñm ñn ™e�¡u©U°C¨ZÕ'8Õ8ÑJño ñp ‘E�{™U¡5¨# :Õ.Õ.Ñ@ñq ñr ™•K¡%©¨s¨
Õ"3Õ3ÑEñs ñt ‘4�j™5¡ s Õ+Õ+Ñ@ñu ñv ‘D�z™E¡$¨ )Õ,Õ,ÑCñw ñx  ¡�9¡u©S°#¨X¥Õ6ÑTñy ñz ‘S•	™E¡# s (�OÕ+Ñ7ñ{ ñ| ‘S•	™E¡# s (�OÕ+Ñ7ñ} ñ~ ‘C�y™5¡ c �?Õ*Ñ6ñ ñ@ ‘C�y™5¡ c �?Õ*Ñ6ñA ñB ‘3�i™%¡ S �/Õ)Ñ5ñC ñD Ñ#ñE ñF Ñ!òG ó    © N)é   é   r.   )é   r
   r
   )r
   é   r0   )é@   éÀ   i€  )r0   r.   é   )r0   r
   é
   )ç      @r5   r5   )ç        r6   r6   )r6   r6   gš™™™™™¹?)TTT)FFT)Údw_bnr7   r7   )r.   r.   r.   )r0   r0   r0   )r
   r
   r
   )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      s†   ø‡ € ñ(ðT €Jà€LØ/8€KØ09€LØ1:€MØ-;€IØ-6€IØ)3€EØ1@€IØ;JÐØ1@€IØ6E€NØ.@€HØ/C€IØ9TÐØ.7€JØ.7€JØ-6€IØ-6€IØ,5€HØ#ÐØ!€N÷G ƒ r+   r   N)	r<   Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úutilsr   r   Ú__all__r,   r+   r(   Ú<module>rE      sJ   ðñ å .å 3Ý #ñ Ð-Ô.ØôA"Ð ó A"ó ó /ðA"ðH ˆ-‚r+   