+
    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rednote-hilab/dots.llm1.base)Ú
checkpointc                   óJ  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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$tR%tR&tR't^>t^ t^ tR(tR(t^t^tR(t^ tR)tR*tR+tR,tR-tR.tR)tR(tR)t R/t!R0t"R1t#^>t$R(t%R(t&R(t'R(t(V 3R2 lt)V3R3 lt*R4t+Vt,V ;t-# )5ÚDots1ConfigaÎ  
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 at the beginning of the model before the first MoE layer.

Examples:

```python
>>> from transformers import Dots1Model, Dots1Config
>>> # Initializing a Dots1 style configuration
>>> configuration = Dots1Config()
>>> # Accessing the model configuration
>>> configuration = model.config
```
Údots1Úpast_key_valueszlayers.*.self_attn.q_projÚcolwisezlayers.*.self_attn.k_projzlayers.*.self_attn.v_projzlayers.*.self_attn.o_projÚrowwisezlayers.*.self_attn.q_normÚreplicated_with_grad_allreducezlayers.*.self_attn.k_normz!layers.*.mlp.experts.gate_up_projÚpacked_colwisezlayers.*.mlp.experts.down_projzlayers.*.mlp.expertsÚmoe_tp_expertsz%layers.*.mlp.shared_experts.gate_projz#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 R i   iÀ*  i€  NFÚsilui   g{®Gáz”?g�íµ ÷Æ°>Tg        g      ð?i   c                ó   <€ V P                   f   V P                  V n         V P                  fK   \        V P                  4       Uu. uF%  pV P
                  e   W P                  8¼  d   RMRNK'  	  upV n        \        SV `   ! R/ VB  R # u upi )NÚsliding_attentionÚfull_attention© )	Únum_key_value_headsÚnum_attention_headsÚlayer_typesÚrangeÚnum_hidden_layersÚsliding_windowÚmax_window_layersÚsuperÚ__post_init__)ÚselfÚkwargsÚiÚ	__class__s   &, €Ún/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/dots1/configuration_dots1.pyr)   ÚDots1Config.__post_init__s   s’   ø€ Ø×#Ñ#Ò+Ø'+×'?Ñ'?ˆDÔ$à×ÑÒ#ô
 ˜t×5Ñ5Ô6ó	 ñ 7�Að ×&Ñ&Ò2°q×<RÑ<RÔ7Rñ $à%ò&ñ 7ñ	 ˆDÔô 	‰ÒÑ' Ô'ùò s   Á+Bc                ó²  <€ V ^8„  d   Qh/ S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ R,          ;R&   S[ R,          ;R	&   S[ R,          ;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&   S[S[,          R,          ;R&   S[;R&   S[S[ ,          R,          ;R&   S[;R&   S[ R,          ;R&   S[ R,          ;R&   S[S[,          R,          ;R&   S[ R,          ;R&   S[ R,          ;R&   S[ S[S[ ,          ,          R,          ;R&   # ) é   Ú
vocab_sizeÚhidden_sizeÚintermediate_sizeÚmoe_intermediate_sizer%   r"   Nr!   Ún_shared_expertsr   Ún_groupÚ
topk_groupÚnum_experts_per_tokÚfirst_k_dense_replaceÚnorm_topk_probÚ
hidden_actÚmax_position_embeddingsÚinitializer_rangeÚrms_norm_epsÚ	use_cacheÚtie_word_embeddingsÚrope_parametersÚattention_biasÚattention_dropoutÚrouted_scaling_factorr&   r'   r#   Úpad_token_idÚbos_token_idÚeos_token_id)ÚintÚboolÚstrÚfloatr   ÚdictÚlist)ÚformatÚ__classdict__s   "€r.   Ú__annotate__ÚDots1Config.__annotate__   s   ø‡ ‚ ñr Ññs ñt Ññu ñv Ñ"ñw ñx Ñ%ñy ñz Ññ{ ñ| Ñ!ñ} ñ~ ˜t�Ñ(ñ ñ@ ˜D•jÑ'ñA ñB ˜D•jÑ'ñC ñD �4�ZÑñE ñF �d•
ÑñG ñH ˜t�Ñ*ñI ñJ  �:Ñ)ñK ñL ˜4•KÑ'ñM ñN ÑñO ñP !Ñ'ñQ ñR Ñ#ñS ñT ÑñU ñV ÑñW ñX Ñ%ñY ñZ $¡dÕ*¨TÕ1Ñ8ñ[ ñ\ Ñ ñ] ñ^ ™s•{ TÕ)Ñ/ñ_ ñ` !Ñ&ña ñb ˜$•JÑ%ñc ñd ˜T•zÑ&ñe ñf ‘c•˜TÕ!Ñ(ñg ñh ˜•*Ñ#ñi ñj ˜•*Ñ#ñk ñl ™™S�	•/ DÕ(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_planÚbase_model_ep_planÚattribute_mapr2   r3   r4   r5   r%   r"   r!   r6   r   r7   r8   r9   r:   r;   r<   r=   r>   r?   r@   rA   rB   rC   rD   rE   r&   r'   r#   rF   rG   rH   r)   Ú__annotate_func__Ú__static_attributes__Ú__classdictcell__Ú__classcell__)r-   rP   s   @@r.   r	   r	      s‘  ù‡ € ñð" €JØ#4Ð"5Ðð 	$ YØ# YØ# YØ# YØ#Ð%EØ#Ð%EØ+Ð-=Ø(¨)ØÐ 0Ø/°Ø-¨yØ/°Ø  )Ø 	Ø  )ðÐð& 	˜+˜¨Ð(9Ð:Ø�OÐ%5Ð6¸Ð8IÐJØ�/Ð" _Ð$5Ð6ðÐð 	˜[Ø+¨^Ø(¨.ØÐ 0ð	Ðð 	Ð/ð€Mð €JØ€KØ"ÐØ!%ÐØÐØ!ÐØ&(ÐØ#'ÐØ#'ÐØ€GØ€JØ&*ÐØ()ÐØ"'€NØ€JØ#'ÐØ#ÐØ€LØ€IØ %ÐØ48€OØ €NØ,/ÐØ#&ÐØ!%€NØ$&ÐØ$(€KØ#€LØ#€LØ+/€Lõ(÷q … rS   r	   N)
Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úmodeling_rope_utilsr   Úutilsr   r	   Ú__all__r    rS   r.   Ú<module>rh      sJ   ðõ( /å 3Ý 1Ý #ñ Ð9Ô:Øôb(Ð"ó b(ó ó ;ðb(ðJ ˆ/‚rS   