+
    œ°³j—  ã                   ót   € ^ 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	# )
é    )Ústrict)ÚPreTrainedConfig)ÚRopeParameters)Úauto_docstringzLGAI-EXAONE/EXAONE-4.0-32B)Ú
checkpointc                   óî   a a€ ] tR t^t oRtRtR.tRRRRRRRR	R
R	RRRRRRRR/	tRR.R.3RRR.R.3RR.R.3/tRt	Rt
Rt^ t^ t^ tRtRtRtRtRt^ t^tRtR tRtR!tRt^tRtV 3R" ltV3R# ltR$tVt V ;t!# )%ÚExaone4Configa*  
sliding_window_pattern (`str`, *optional*):
    The pattern to use for sliding window attention. Can be one of:
        - `None`: No sliding window attention is used
        - `int`: Every `sliding_window` layers, use global attention, else use local attention.
        - `str`: A sequence of "L" (local attention) and "G" (global attention) characters that defines the
          attention pattern. The pattern starts from layer 0 and repeats every `sliding_window` layers. The
          final layer always uses global attention regardless of the pattern.
    For instance, sliding_window_pattern="LLLG" same as sliding_window=4, which means:
        - Layer 0, 1, 2: local attention,
        - Layer 3: global attention,
        ...(repeated)

Example:

```python
>>> from transformers import Exaone4Model, Exaone4Config

>>> # Initializing a EXAONE configuration
>>> configuration = Exaone4Config()

>>> # Initializing a model from configuration
>>> model = Exaone4Model(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config
```Úexaone4Úpast_key_valueszlayers.*.self_attn.q_projÚcolwisezlayers.*.self_attn.k_projzlayers.*.self_attn.v_projzlayers.*.self_attn.q_normÚreplicated_with_grad_allreducezlayers.*.self_attn.k_normzlayers.*.self_attn.o_projÚrowwisezlayers.*.mlp.gate_projzlayers.*.mlp.up_projzlayers.*.mlp.down_projÚembed_tokensÚ	input_idsÚinputs_embedsÚlayersÚhidden_statesÚattention_maskÚnormi � i   i @  Úsilui   g{®Gáz”?gñhãˆµøä>TNFg        c                ó.  <€ V P                   f   ^ V n        V P                  f\   \        V P                  4       Uu. uF6  pV^,           V P                  ,          ^ 8w  d   W P                  8  d   RMRNK8  	  upV n        \
        SV `  ! R/ VB  R # u upi )NÚsliding_attentionÚfull_attention© )Úsliding_windowÚsliding_window_patternÚlayer_typesÚrangeÚnum_hidden_layersÚsuperÚ__post_init__)ÚselfÚkwargsÚiÚ	__class__s   &, €Úr/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/exaone4/configuration_exaone4.pyr!   ÚExaone4Config.__post_init__d   s—   ø€ Ø×ÑÒ&Ø*+ˆDÔ'Ø×ÑÒ#ô
 ˜t×5Ñ5Ô6ó	 ñ 7�Að ˜•U˜t×:Ñ:Õ;¸qÔ@ÀQ×I_ÑI_ÔE_ñ $à%ò&ñ 7ñ	 ˆDÔô 	‰ÒÑ' Ô'ùò s   ¼<Bc                óÌ  <€ V ^8„  d   Qh/ S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[;R&   S[ ;R&   S[;R	&   S[;R
&   S[;R&   S[ R,          ;R&   S[ S[S[ ,          ,          R,          ;R&   S[ R,          ;R&   S[;R&   S[S[,          R,          ;R&   S[S[ ,          ;R&   S[ R,          ;R&   S[S[ ,          R,          ;R&   S[S[,          R,          ;R&   # )é   Ú
vocab_sizeÚhidden_sizeÚintermediate_sizer   Únum_attention_headsÚnum_key_value_headsÚ
hidden_actÚmax_position_embeddingsÚinitializer_rangeÚrms_norm_epsÚ	use_cacheNÚbos_token_idÚeos_token_idÚpad_token_idÚtie_word_embeddingsÚrope_parametersÚattention_dropoutr   r   r   )ÚintÚstrÚfloatÚboolÚlistr   Údict)ÚformatÚ__classdict__s   "€r&   Ú__annotate__ÚExaone4Config.__annotate__   sj  ø‡ ‚ ñf Ññg ñh Ññi ñj Ñ"ñk ñl Ññm ñn Ñ!ño ñp Ñ!ñq ñr Ññs ñt !Ñ'ñu ñv Ñ#ñw ñx Ññy ñz Ññ{ ñ| ˜•*Ñ ñ} ñ~ ™™S�	•/ DÕ(Ñ,ñ ñ@ ˜•*Ñ#ñA ñB Ñ%ñC ñD $¡dÕ*¨TÕ1Ñ8ñE ñF ™s•{Ñ(ñG ñH ˜$•JÑ%ñI ñJ  ¡#�I¨Õ,Ñ0ñK ñL ‘c•˜TÕ!Ñ(òM ó    )r   r   )"Ú__name__Ú
__module__Ú__qualname__Ú__firstlineno__Ú__doc__Ú
model_typeÚkeys_to_ignore_at_inferenceÚbase_model_tp_planÚbase_model_pp_planr*   r+   r,   r   r-   r.   r/   r0   r1   r2   r3   r4   r5   r6   r7   r8   r9   r   r   r   r!   Ú__annotate_func__Ú__static_attributes__Ú__classdictcell__Ú__classcell__)r%   rA   s   @@r&   r	   r	      s  ù‡ € ñð8 €JØ#4Ð"5Ðð 	$ YØ# YØ# YØ#Ð%EØ#Ð%EØ# YØ  )Ø 	Ø  )ð
Ðð 	˜+˜¨Ð(9Ð:Ø�OÐ%5Ð6¸Ð8IÐJØ�/Ð" _Ð$5Ð6ðÐð €JØ€KØ"ÐØÐØ!ÐØ!ÐØ€JØ#'ÐØ#ÐØ€LØ€IØ €LØ+,€LØ#€LØ %ÐØ48€OØ%(ÐØ!%€NØ/0ÐØ$(€Kõ(÷Q … rD   r	   N)
Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úmodeling_rope_utilsr   Úutilsr   r	   Ú__all__r   rD   r&   Ú<module>rW      sK   ðõ* /å 3Ý 1Ý #ñ Ð7Ô8ØôQ(Ð$ó Q(ó ó 9ðQ(ðh Ð
‚rD   