+
    œ°³j9  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!swiss-ai/Apertus-8B-Instruct-2509)Ú
checkpointc                   óæ   a a€ ] tR t^t oRtRtR.tRt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RtRtRtRtRtRt^t^t^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ApertusConfigaV  
```python
>>> from transformers import ApertusModel, ApertusConfig

>>> # Initializing a Apertus-8B style configuration
>>> configuration = ApertusConfig()

>>> # Initializing a model from the Apertus-8B style configuration
>>> model = ApertusModel(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config
```ÚapertusÚpast_key_valuesç    `ãfAz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.up_projzlayers.*.mlp.down_projÚembed_tokensÚ	input_idsÚinputs_embedsÚlayersÚhidden_statesÚattention_maskÚnormi   i   i 8  NÚxielui   g{®Gáz”?gñhãˆµøä>TFg        c                ó¨   <€ V P                   f   V P                  V n         V P                  f   RRRRRRRRR	R
RR/V n        \        SV `  ! R/ VB  R # )NÚ	rope_typeÚllama3Ú
rope_thetar   Úfactorg       @Ú original_max_position_embeddingsi    Úlow_freq_factorg      ð?Úhigh_freq_factorg      @© )Únum_key_value_headsÚnum_attention_headsÚrope_parametersÚsuperÚ__post_init__)ÚselfÚkwargsÚ	__class__s   &,€Úr/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/apertus/configuration_apertus.pyr%   ÚApertusConfig.__post_init__S   sc   ø€ Ø×#Ñ#Ò+Ø'+×'?Ñ'?ˆDÔ$à×ÑÒ'à˜XØ˜jØ˜#Ø2°DØ! 3Ø" Cð$ˆDÔ ô 	‰ÒÑ' Ô'ó    c                óx  <€ V ^8„  d   Qh/ S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ R,          ;R&   S[;R&   S[ ;R	&   S[;R
&   S[;R&   S[;R&   S[ R,          ;R&   S[ R,          ;R&   S[ S[S[ ,          ,          R,          ;R&   S[;R&   S[S[,          R,          ;R&   S[;R&   S[S[ ,          ;R&   # )é   Ú
vocab_sizeÚhidden_sizeÚintermediate_sizeÚnum_hidden_layersr"   Nr!   Ú
hidden_actÚmax_position_embeddingsÚinitializer_rangeÚrms_norm_epsÚ	use_cacheÚpad_token_idÚbos_token_idÚeos_token_idÚtie_word_embeddingsr#   Úattention_biasÚattention_dropout)ÚintÚstrÚfloatÚboolÚlistr   Údict)ÚformatÚ__classdict__s   "€r)   Ú__annotate__ÚApertusConfig.__annotate__   s:  ø‡ ‚ ñH ÑñI ñJ ÑñK ñL Ñ"ñM ñN ÑñO ñP Ñ!ñQ ñR ˜t�Ñ*ñS ñT ÑñU ñV !Ñ(ñW ñX Ñ#ñY ñZ Ññ[ ñ\ Ññ] ñ^ ˜•*Ñ ñ_ ñ` ˜•*Ñ ña ñb ™™S�	•/ DÕ(Ñ,ñc ñd Ñ%ñe ñf $¡dÕ*¨TÕ1Ñ8ñg ñh Ñ ñi ñj ™s•{Ñ(òk r+   )r!   r#   )!Ú__name__Ú
__module__Ú__qualname__Ú__firstlineno__Ú__doc__Ú
model_typeÚkeys_to_ignore_at_inferenceÚdefault_thetaÚbase_model_tp_planÚbase_model_pp_planr.   r/   r0   r1   r"   r!   r2   r3   r4   r5   r6   r7   r8   r9   r:   r#   r;   r<   r%   Ú__annotate_func__Ú__static_attributes__Ú__classdictcell__Ú__classcell__)r(   rD   s   @@r)   r	   r	      sþ   ù‡ € ñð €JØ#4Ð"5ÐØ€Mà# YØ# YØ# YØ#Ð%EØ#Ð%EØ# YØ 	Ø  )ð	Ðð 	˜+˜¨Ð(9Ð:Ø�OÐ%5Ð6¸Ð8IÐJØ�/Ð" _Ð$5Ð6ðÐð €JØ€KØ"ÐØÐØ!ÐØ&*ÐØ€JØ#(ÐØ#ÐØ€LØ€IØ €LØ €LØ+,€LØ %ÐØ48€OØ €NØ%(Ðõ(÷o … r+   r	   N)
Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úmodeling_rope_utilsr   Úutilsr   r	   Ú__all__r    r+   r)   Ú<module>rZ      sL   ðõ* /å 3Ý 1Ý #ñ Ð>Ô?ØôB(Ð$ó B(ó ó @ðB(ðJ Ð
‚r+   