+
    œ°³j�  ã                   óx   € R t ^ 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	# )
zMistral4 model configuration)Ústrict)ÚPreTrainedConfig)ÚRopeParameters)Úauto_docstringz#mistralai/Mistral-Small-4-119B-2603)Ú
checkpointc                   óB  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RRRRRRR	/t	RR/t
RtRtRtR t^$t^ t^ t^t^€tR!tR"tR#t^@t^€t^@t^t^t^t^ tR$tR%tR&t R't!R(t"R$t#^t$^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t0V ;t1# )/ÚMistral4Configa§  
n_group (`int`, *optional*, defaults to 1):
    Number of groups for routed experts.
first_k_dense_replace (`int`, *optional*, defaults to 0):
    Number of dense layers in shallow layers(embed->dense->dense->...->dense->moe->moe...->lm_head).
                                                    \--k dense layers--/
rope_interleave (`bool`, *optional*, defaults to `True`):
    Whether to interleave the rotary position embeddings.

Example:

```python
>>> from transformers import Mistral4Model, Mistral4Config

>>> # Initializing a Mistral4 style configuration
>>> configuration = Mistral4Config()

>>> # Accessing the model configuration
>>> configuration = model.config
```Úmistral4Úpast_key_valuesz!layers.*.mlp.experts.gate_up_projÚpacked_colwisezlayers.*.mlp.experts.down_projÚrowwisezlayers.*.mlp.expertsÚmoe_tp_expertsz%layers.*.mlp.shared_experts.gate_projÚcolwisez#layers.*.mlp.shared_experts.up_projz%layers.*.mlp.shared_experts.down_projzlayers.*.mlp.gate_projzlayers.*.mlp.up_projzlayers.*.mlp.down_projÚembed_tokensÚ	input_idsÚinputs_embedsÚlayersÚhidden_statesÚattention_maskÚnormzlayers.*.mlp.gateÚ	ep_routerÚgrouped_gemmÚnum_local_expertsÚn_routed_expertsi   i   i 0  i   ç      ð?é   i   TÚsilui   g{®Gáz”?g�íµ ÷Æ°>FNg        c                ó&  <€ V P                   fT   RRRRRRRRR	V P                  R
RRRRRRRRRRV P                  V P                  V P                  ,           ,          /V n         V P                  f   V P
                  V n        V P                  V P                  ,           V n        V P                  V P                  ,           V n        V P                   P                  RV P                  V P                  ,          4       \        SV `(  ! RRRR	0/VB  R # )NÚtypeÚyarnÚ
rope_thetag     ˆÃ@Úfactorg      `@Ú original_max_position_embeddingsi    Úmax_position_embeddingsÚ	beta_fastg      @@Ú	beta_slowr   Úmscale_all_dimÚmscaleÚllama_4_scaling_betagš™™™™™¹?Úpartial_rotary_factorÚignore_keys_at_rope_validation© )Úrope_parametersr#   Úqk_rope_head_dimÚqk_nope_head_dimÚnum_key_value_headsÚnum_attention_headsÚqk_head_dimÚhead_dimÚ
setdefaultÚsuperÚ__post_init__)ÚselfÚkwargsÚ	__class__s   &,€Út/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/mistral4/configuration_mistral4.pyr5   ÚMistral4Config.__post_init__o   s  ø€ Ø×ÑÒ'à˜Ø˜gØ˜%Ø2°DØ)¨4×+GÑ+GØ˜TØ˜SØ  #Ø˜#Ø&¨Ø'¨×)>Ñ)>À$×BWÑBWÐZ^×ZoÑZoÕBoÕ)pð$ˆDÔ ð ×#Ñ#Ò+Ø'+×'?Ñ'?ˆDÔ$à×0Ñ0°4×3HÑ3HÕHˆÔØ×-Ñ-°×0EÑ0EÕEˆŒØ×Ñ×'Ñ'Ð(?À×AVÑAVÐY]×YfÑYfÕAfÔgÜ‰Òñ 	
Ø,BÐD]Ð+^ð	
Øbhô	
ó    c                óÄ  <€ V ^8„  d   Qh/ S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ R,          ;R&   S[ ;R	&   S[ ;R
&   S[;R&   S[ ;R&   S[ R,          ;R&   S[ ;R&   S[ R,          ;R&   S[ ;R&   S[ R,          ;R&   S[ R,          ;R&   S[ R,          ;R&   S[ R,          ;R&   S[R,          ;R&   S[;R&   S[ ;R&   S[;R&   S[;R&   S[;R&   S[ R,          ;R&   S[ R,          ;R&   S[ S[S[ ,          ,          R,          ;R&   S[ R,          ;R&   S[;R&   S[S[,          R,          ;R &   S[R,          ;R!&   S[;R"&   S[S[ ,          R,          ;R#&   # )$é   Ú
vocab_sizeÚhidden_sizeÚintermediate_sizeÚmoe_intermediate_sizeÚnum_hidden_layersr0   Nr/   Ún_shared_expertsr   Úrouted_scaling_factorÚkv_lora_rankÚq_lora_rankr-   Ú
v_head_dimr.   Ún_groupÚ
topk_groupÚnum_experts_per_tokÚfirst_k_dense_replaceÚnorm_topk_probÚ
hidden_actr#   Úinitializer_rangeÚrms_norm_epsÚ	use_cacheÚpad_token_idÚbos_token_idÚeos_token_idÚpretraining_tpÚtie_word_embeddingsr,   Úrope_interleaveÚattention_biasÚattention_dropout)ÚintÚfloatÚboolÚstrÚlistr   Údict)ÚformatÚ__classdict__s   "€r9   Ú__annotate__ÚMistral4Config.__annotate__   sS  ø‡ ‚ ñj Ññk ñl Ññm ñn Ñ"ño ñp Ñ%ñq ñr Ññs ñt Ñ!ñu ñv ˜t�Ñ(ñw ñx Ññy ñz Ññ{ ñ| !Ñ&ñ} ñ~ Ññ ñ@ �t•Ñ"ñA ñB ÑñC ñD �d•
Ñ ñE ñF ÑñG ñH �4�ZÑñI ñJ �d•
ÑñK ñL ˜t�Ñ'ñM ñN  �:Ñ)ñO ñP ˜4•KÑ&ñQ ñR ÑñS ñT !Ñ*ñU ñV Ñ#ñW ñX ÑñY ñZ Ññ[ ñ\ ˜•*Ñ!ñ] ñ^ ˜•*Ñ ñ_ ñ` ™™S�	•/ DÕ(Ñ,ña ñb ˜$•JÑ"ñc ñd Ñ%ñe ñf $¡dÕ*¨TÕ1Ñ8ñg ñh ˜D•[Ñ'ñi ñj Ñ ñk ñl ™s•{ TÕ)Ñ/òm r;   )r2   r/   r1   r,   )2Ú__name__Ú
__module__Ú__qualname__Ú__firstlineno__Ú__doc__Ú
model_typeÚkeys_to_ignore_at_inferenceÚbase_model_tp_planÚbase_model_pp_planÚbase_model_ep_planÚattribute_mapr>   r?   r@   rA   rB   r0   r/   rC   r   rD   rE   rF   r-   rG   r.   rH   rI   rJ   rK   rL   rM   r#   rN   rO   rP   rQ   rR   rS   rT   rU   r,   rV   rW   rX   r5   Ú__annotate_func__Ú__static_attributes__Ú__classdictcell__Ú__classcell__)r8   r`   s   @@r9   r   r      s„  ù‡ € ñð* €JØ#4Ð"5Ðà+Ð-=Ø(¨)ØÐ 0Ø/°Ø-¨yØ/°Ø  )Ø 	Ø  )ð
Ðð 	˜+˜¨Ð(9Ð:Ø�OÐ%5Ð6¸Ð8IÐJØ�/Ð" _Ð$5Ð6ðÐð 	˜[Ø+¨^Ø(¨.ØÐ 0ð	Ðð 	Ð/ð€Mð €JØ€KØ"ÐØ!%ÐØÐØ!ÐØ&(ÐØÐØÐØ#&ÐØ€LØ"€KØÐØ €JØÐØ€GØ€JØ&'ÐØ()ÐØ"&€NØ€JØ#*ÐØ#ÐØ€LØ€IØ!€LØ €LØ+,€LØ!"€NØ %ÐØ48€OØ#'€OØ €NØ,/Ðõ
÷q … r;   r   N)rg   Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úmodeling_rope_utilsr   Úutilsr   r   Ú__all__r+   r;   r9   Ú<module>rw      sO   ðñ #å .å 3Ý 1Ý #ñ Ð@ÔAØôn
Ð%ó n
ó ó Bðn
ðb Ð
‚r;   