
    Z j                     r    S r SSKJ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VitDet model configuration    )strict   )BackboneConfigMixin)PreTrainedConfig)auto_docstringzgoogle/vitdet-base-patch16-224)
checkpointc                     ^  \ rS rSr% SrSr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\\\   -  \\\4   -  \S'   Sr\\\   -  \\\4   -  \S'   Sr\\\   -  \\\4   -  \S'   Sr\\S'   Sr\\S'   Sr\\-  \S'   Sr\\   \\S4   -  \S'   Sr\\   \\S4   -  \S '   Sr\\S!'   S"r\\S#'   S$r\\S%'   S&r \\   S&-  \S''   S&r!\\   S&-  \S('   U 4S) jr"S*r#U =r$$ )+VitDetConfig   a  
pretrain_image_size (`int`, *optional*, defaults to 224):
    The size (resolution) of each image during pretraining.
window_block_indices (`list[int]`, *optional*, defaults to `[]`):
    List of indices of blocks that should have window attention instead of regular global self-attention.
residual_block_indices (`list[int]`, *optional*, defaults to `[]`):
    List of indices of blocks that should have an extra residual block after the MLP.
use_relative_position_embeddings (`bool`, *optional*, defaults to `False`):
    Whether to add relative position embeddings to the attention maps.
window_size (`int`, *optional*, defaults to 0):
    The size of the attention window.

Example:

```python
>>> from transformers import VitDetConfig, VitDetModel

>>> # Initializing a VitDet configuration
>>> configuration = VitDetConfig()

>>> # Initializing a model (with random weights) from the configuration
>>> model = VitDetModel(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config
```vitdeti   hidden_size   num_hidden_layersnum_attention_heads   	mlp_ratiogelu
hidden_actg        dropout_probg{Gz?initializer_rangegư>layer_norm_eps   
image_sizepretrain_image_size   
patch_sizer   num_channelsTqkv_biasdrop_path_rate .window_block_indicesresidual_block_indices use_absolute_position_embeddingsF use_relative_position_embeddingsr   window_sizeN_out_features_out_indicesc                    > S/[        SU R                  S-   5       Vs/ s H  nSU 3PM
     sn-   U l        U R                  UR	                  SS 5      UR	                  SS 5      S9  [
        TU ]  " S0 UD6  g s  snf )Nstem   stageout_indicesout_features)r,   r-   r    )ranger   stage_names"set_output_features_output_indicespopsuper__post_init__)selfkwargsidx	__class__s      ڀ/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/vitdet/configuration_vitdet.pyr3   VitDetConfig.__post_init__M   s    "8aI_I_bcIc@d&e@dse}@d&ee//

=$7fjjQ_aeFf 	0 	
 	''	 'fs   A9)r/   )%__name__
__module____qualname____firstlineno____doc__
model_typer   int__annotations__r   r   r   r   strr   floatr   r   r   listtupler   r   r   r   boolr   r!   r"   r#   r$   r%   r&   r'   r3   __static_attributes____classcell__)r7   s   @r8   r
   r
      sn   6 JKs!!IsJ #L%#+##u# NE 47Jd3i%S/17=@tCy5c?:@46Jd3i%S/16L#Hd"%NECK%8:$s)eCHo5::<DIc3h7<-1$d1-2$d2K&*M49t#*%)L$s)d")( (    r
   N)r>   huggingface_hub.dataclassesr   backbone_utilsr   configuration_utilsr   utilsr   r
   __all__r    rI   r8   <module>rO      sN    ! . 1 3 # ;<9(&(8 9(  =9(x 
rI   