+
    œ°³jÂ
  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TrOCR model configuration)Ústrict)ÚPreTrainedConfig)Úauto_docstringz microsoft/trocr-base-handwritten)Ú
checkpointc                   ó¦   a € ] tR t^t o RtRtR.tRRRRRR	/tR
tRt	^t
^tRtRtRtRtRtRt^tRtRtRtRtRtRt^t^ t^tRtRtRtV 3R ltRt V t!R# )ÚTrOCRConfiga»  
use_learned_position_embeddings (`bool`, *optional*, defaults to `True`):
    Whether or not to use learned position embeddings. If not, sinusoidal position embeddings will be used.
layernorm_embedding (`bool`, *optional*, defaults to `True`):
    Whether or not to use a layernorm after the word + position embeddings.

Example:

```python
>>> from transformers import TrOCRConfig, TrOCRForCausalLM

>>> # Initializing a TrOCR-base style configuration
>>> configuration = TrOCRConfig()

>>> # Initializing a model (with random weights) from the TrOCR-base style configuration
>>> model = TrOCRForCausalLM(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config
```ÚtrocrÚpast_key_valuesÚnum_attention_headsÚdecoder_attention_headsÚhidden_sizeÚd_modelÚnum_hidden_layersÚdecoder_layersiYÄ  i   i   Úgelui   gš™™™™™¹?g        g{®Gáz”?TFNc                óÆ  <€ V ^8„  d   Qh/ S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[;R&   S[ ;R&   S[S[ ,          ;R&   S[S[ ,          ;R	&   S[S[ ,          ;R
&   S[ ;R&   S[;R&   S[S[ ,          ;R&   S[;R&   S[;R&   S[;R&   S[;R&   S[ R,          ;R&   S[ R,          ;R&   S[ S[S[ ,          ,          R,          ;R&   S[ R,          ;R&   S[;R&   S[;R&   # )é   Ú
vocab_sizer   r   r   Údecoder_ffn_dimÚactivation_functionÚmax_position_embeddingsÚdropoutÚattention_dropoutÚactivation_dropoutÚdecoder_start_token_idÚinit_stdÚdecoder_layerdropÚ	use_cacheÚscale_embeddingÚuse_learned_position_embeddingsÚlayernorm_embeddingNÚpad_token_idÚbos_token_idÚeos_token_idÚcross_attention_hidden_sizeÚ
is_decoderÚtie_word_embeddings)ÚintÚstrÚfloatÚboolÚlist)ÚformatÚ__classdict__s   "€Ún/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/trocr/configuration_trocr.pyÚ__annotate__ÚTrOCRConfig.__annotate__   s‡  ø‡ ‚ ñ@ ÑñA ñB ÑñC ñD ÑñE ñF !Ñ%ñG ñH ÑñI ñJ Ñ%ñK ñL !Ñ&ñM ñN ‘S�[ÑñO ñP ™s•{Ñ(ñQ ñR ¡�Ñ)ñS ñT  Ñ#ñU ñV ÑñW ñX ™s•{Ñ(ñY ñZ Ññ[ ñ\ Ñ!ñ] ñ^ &*Ñ0ñ_ ñ` Ñ$ña ñb ˜•*Ñ ñc ñd ˜•*Ñ ñe ñf ™™S�	•/ DÕ(Ñ,ñg ñh "% t¥Ñ2ñi ñj Ññk ñl Ñ$òm ó    © )"Ú__name__Ú
__module__Ú__qualname__Ú__firstlineno__Ú__doc__Ú
model_typeÚkeys_to_ignore_at_inferenceÚattribute_mapr   r   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__)r-   s   @r.   r   r      sº   ø‡ € ñð* €JØ#4Ð"5ÐàÐ8Ø�yØÐ-ð€Mð €JØ€GØ€NØ#%ÐØ€OØ%ÐØ#&ÐØ€GØ%(ÐØ&)ÐØ"#ÐØ€HØ%(ÐØ€IØ!€OØ,0Ð#Ø $ÐØ €LØ €LØ+,€LØ.2ÐØ€JØ $Ð÷m ƒ r1   r   N)	r7   Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úutilsr   r   Ú__all__r2   r1   r.   Ú<module>rB      sG   ðñ  å .å 3Ý #ñ Ð=Ô>Øô4%Ð"ó 4%ó ó ?ð4%ðn ˆ/‚r1   