+
    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VilT model configuration)Ústrict)ÚPreTrainedConfig)Úauto_docstringzdandelin/vilt-b32-mlm)Ú
checkpointc                   óš   a a€ ] tR t^t oRtRtRt^t^t^(t	Rt
^t^tRtRtRtRtRtR	tR
t^ t^tRt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
ViltConfiga[  
modality_type_vocab_size (`int`, *optional*, defaults to 2):
    The vocabulary size of the modalities passed when calling [`ViltModel`]. This is used after concatenating the
    embeddings of the text and image modalities.
max_image_length (`int`, *optional*, defaults to -1):
    The maximum number of patches to take as input for the Transformer encoder. If set to a positive integer,
    the encoder will sample `max_image_length` patches at maximum. If set to -1, will not be taken into
    account.
num_images (`int`, *optional*, defaults to -1):
    The number of images to use for natural language visual reasoning. If set to a positive integer, will be
    used by [`ViltForImagesAndTextClassification`] for defining the classifier head.

Example:

```python
>>> from transformers import ViLTModel, ViLTConfig

>>> # Initializing a ViLT dandelin/vilt-b32-mlm style configuration
>>> configuration = ViLTConfig()

>>> # Initializing a model from the dandelin/vilt-b32-mlm style configuration
>>> model = ViLTModel(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config
```Úvilti:w  i   i   Úgelug        g{®Gáz”?gê-�™—q=i€  TNc                óZ   <€ VP                  R R4       RV n        \        SV `  ! R/ VB  R# )Útie_word_embeddingsNT© )Úpopr   ÚsuperÚ__post_init__)ÚselfÚkwargsÚ	__class__s   &,€Úl/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/vilt/configuration_vilt.pyr   ÚViltConfig.__post_init__L   s*   ø€ Ø�
‰
Ð(¨$Ô/Ø#'ˆÔ Ü‰ÒÑ' Ô'ó    c                óÐ  <€ V ^8„  d   Qh/ S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[;R	&   S[S[ ,          ;R
&   S[S[ ,          ;R&   S[;R&   S[;R&   S[ S[S[ ,          ,          S[S[ S[ 3,          ,          ;R&   S[ S[S[ ,          ,          S[S[ S[ 3,          ,          ;R&   S[ ;R&   S[;R&   S[ ;R&   S[;R&   S[ ;R&   S[ R,          ;R&   # )é   Ú
vocab_sizeÚtype_vocab_sizeÚmodality_type_vocab_sizeÚmax_position_embeddingsÚhidden_sizeÚnum_hidden_layersÚnum_attention_headsÚintermediate_sizeÚ
hidden_actÚhidden_dropout_probÚattention_probs_dropout_probÚinitializer_rangeÚlayer_norm_epsÚ
image_sizeÚ
patch_sizeÚnum_channelsÚqkv_biasÚmax_image_lengthr   Ú
num_imagesNÚpad_token_id)ÚintÚstrÚfloatÚlistÚtupleÚbool)ÚformatÚ__classdict__s   "€r   Ú__annotate__ÚViltConfig.__annotate__   sv  ø‡ ‚ ñ@ ÑñA ñB ÑñC ñD "Ñ%ñE ñF !Ñ%ñG ñH ÑñI ñJ ÑñK ñL Ñ!ñM ñN Ñ!ñO ñP ÑñQ ñR ¡�Ñ*ñS ñT #(©#¥+Ñ3ñU ñV Ñ#ñW ñX Ñ!ñY ñZ ‘d™3•i•¡%©©S¨¥/Õ1Ñ7ñ[ ñ\ ‘d™3•i•¡%©©S¨¥/Õ1Ñ6ñ] ñ^ Ññ_ ñ` Ñña ñb Ññc ñd Ñ$ñe ñf Ññg ñh ˜•*Ñ#òi r   )r   éÿÿÿÿ) 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$   r%   r&   r'   r(   r)   r   r*   r+   r   Ú__annotate_func__Ú__static_attributes__Ú__classdictcell__Ú__classcell__)r   r3   s   @@r   r   r      s‘   ù‡ € ñð6 €Jà€JØ€OØ$%ÐØ#%ÐØ€KØÐØ!ÐØ!ÐØ€JØ'*ÐØ03Ð Ø#ÐØ!€NØ47€JØ46€JØ€LØ€HØÐØ $ÐØ€JØ#€Lõ(÷m … r   r   N)	r;   Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úutilsr   r   Ú__all__r   r   r   Ú<module>rE      sG   ðñ å .å 3Ý #ñ Ð2Ô3Øô7(Ð!ó 7(ó ó 4ð7(ðt ˆ.‚r   