§
    ‚Štjˆ  ã                   ó*  — d dl mZ d dlmZ d dlZd dlmc mZ d dlmZ ddl	m
Z ddlmZ ddlmZmZ dd	lmZ dd
lmZmZ ddlmZmZ ddlmZ ddlmZ ddlmZmZ ddl m!Z!m"Z" ddl#m$Z$m%Z% ddl&m'Z' ddl(m)Z)m*Z* ddl+m,Z,m-Z-m.Z. ddl/m0Z0m1Z1 ddl2m3Z3  ed¦  «         G d„ dej4        ¦  «        ¦   «         Z5 G d„ dej4        ¦  «        Z6 G d„ dej4        ¦  «        Z7 G d„ dej4        ¦  «        Z8e G d „ d!ej4        ¦  «        ¦   «         Z9 G d"„ d#ej4        ¦  «        Z:d$„ Z;dCd%„Z<d&ej=        d'e>d(ej=        fd)„Z?	 dDd+ej4        d,ej=        d-ej=        d.ej=        d/ej=        dz  d0e@d1e@d2e'e,         fd3„ZA G d4„ d5ej4        ¦  «        ZB G d6„ d7e¦  «        ZCe) G d8„ d9e%¦  «        ¦   «         ZDe) G d:„ d;eD¦  «        ¦   «         ZE	 	 	 dEd=ej=        eFej=                 z  dz  d>e>dz  d/ej=        dz  d(ej=        e>z  fd?„ZGe) G d@„ dAeDe¦  «        ¦   «         ZHg dB¢ZIdS )Fé    )ÚCallable)ÚOptionalN)Únné   )Úinitialization)ÚACT2FN)ÚCacheÚDynamicCache)ÚGenerationMixin)Úuse_experts_implementationÚuse_kernel_forward_from_hub)Úcreate_causal_maskÚ!create_sliding_window_causal_mask)ÚFlashAttentionKwargs)ÚGradientCheckpointingLayer)ÚMoeCausalLMOutputWithPastÚMoeModelOutputWithPast)ÚROPE_INIT_FUNCTIONSÚdynamic_rope_update)ÚALL_ATTENTION_FUNCTIONSÚPreTrainedModel)ÚUnpack)Úauto_docstringÚcan_return_tuple)ÚTransformersKwargsÚmaybe_autocastÚmerge_with_config_defaults)ÚOutputRecorderÚcapture_outputsé   )ÚLagunaConfigÚRMSNormc                   óT   ‡ — e Zd Zd	deddfˆ fd„Zdej        dej        fd„Zd„ Zˆ xZ	S )
ÚLagunaRMSNormç�íµ ÷Æ°>ÚepsÚreturnNc                 ó¬   •— t          ¦   «                              ¦   «          t          j        t	          j        |¦  «        ¦  «        | _        || _        dS )z<
        LagunaRMSNorm is equivalent to T5LayerNorm
        N)ÚsuperÚ__init__r   Ú	ParameterÚtorchÚonesÚweightÚvariance_epsilon)ÚselfÚhidden_sizer&   Ú	__class__s      €úh/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/transformers/models/laguna/modeling_laguna.pyr*   zLagunaRMSNorm.__init__0   sD   ø€ õ 	‰Œ×ÒÑÔÐÝ”l¥5¤:¨kÑ#:Ô#:Ñ;Ô;ˆŒØ #ˆÔÐÐó    Úhidden_statesc                 ó  — |j         }|                     t          j        ¦  «        }|                     d¦  «                             dd¬¦  «        }|t          j        || j        z   ¦  «        z  }| j        |                     |¦  «        z  S )Né   éÿÿÿÿT)Úkeepdim)	ÚdtypeÚtor,   Úfloat32ÚpowÚmeanÚrsqrtr/   r.   )r0   r5   Úinput_dtypeÚvariances       r3   ÚforwardzLagunaRMSNorm.forward8   s|   € Ø#Ô)ˆØ%×(Ò(­¬Ñ7Ô7ˆØ ×$Ò$ QÑ'Ô'×,Ò,¨R¸Ð,Ñ>Ô>ˆØ%­¬°H¸tÔ?TÑ4TÑ(UÔ(UÑUˆØŒ{˜]×-Ò-¨kÑ:Ô:Ñ:Ð:r4   c                 óH   — t          | j        j        ¦  «        › d| j        › �S )Nz, eps=)Útupler.   Úshaper/   )r0   s    r3   Ú
extra_reprzLagunaRMSNorm.extra_repr?   s&   € Ý˜œÔ)Ñ*Ô*ÐIÐI°$Ô2GÐIÐIÐIr4   )r%   )
Ú__name__Ú
__module__Ú__qualname__Úfloatr*   r,   ÚTensorrB   rF   Ú__classcell__©r2   s   @r3   r$   r$   .   sŒ   ø€ € € € € ð$ð $¨ð $¸$ð $ð $ð $ð $ð $ð $ð; U¤\ð ;°e´lð ;ð ;ð ;ð ;ðJð Jð Jð Jð Jð Jð Jr4   r$   c                   óà   ‡ — e Zd ZU ej        ed<   defˆ fd„Ze	 	 	 	 ddedz  de	d         de
dz  dedz  d	ed
ef         f
d„¦   «         Z ej        ¦   «         edd„¦   «         ¦   «         Zˆ xZS )ÚLagunaRotaryEmbeddingÚinv_freqÚconfigc                 ó€  •— t          ¦   «                              ¦   «          |j        | _        |j        | _        || _        t          t          |j        ¦  «        ¦  «        | _        i | _	        | j        D ]È}| j        j
        |         }|€Œ|d         | j	        |<   | j        }| j	        |         dk    rt          | j	        |                  } || j        |¬¦  «        \  }}|                      |› d�|d¬¦  «         |                      |› d�|                     ¦   «         d¬¦  «         t          | |› d�|¦  «         ŒÉd S )	NÚ	rope_typeÚdefault©Ú
layer_typeÚ	_inv_freqF)Ú
persistentÚ_original_inv_freqÚ_attention_scaling)r)   r*   Úmax_position_embeddingsÚmax_seq_len_cachedÚoriginal_max_seq_lenrQ   ÚlistÚsetÚlayer_typesrS   Úrope_parametersÚcompute_default_rope_parametersr   Úregister_bufferÚcloneÚsetattr)r0   rQ   rV   Úrope_paramsÚrope_init_fnÚcurr_inv_freqÚcurr_attention_scalingr2   s          €r3   r*   zLagunaRotaryEmbedding.__init__F   s^  ø€ Ý‰Œ×ÒÑÔÐØ"(Ô"@ˆÔØ$*Ô$BˆÔ!ØˆŒÝ¥ FÔ$6Ñ 7Ô 7Ñ8Ô8ˆÔØˆŒØÔ*ð 	Uð 	UˆJØœ+Ô5°jÔAˆKØÐ"Øà)4°[Ô)AˆDŒN˜:Ñ&Ø%)Ô%IˆLØŒ~˜jÔ)¨YÒ6Ð6Ý2°4´>À*Ô3MÔN�Ø4@°LÀÄÐYcÐ4dÑ4dÔ4dÑ1ˆMÐ1Ø× Ò  JÐ!9Ð!9Ð!9¸=ÐUZÐ Ñ[Ô[Ð[Ø× Ò  JÐ!BÐ!BÐ!BÀM×DWÒDWÑDYÔDYÐfkÐ ÑlÔlÐlÝ�D˜ZÐ;Ð;Ð;Ð=SÑTÔTÐTÐTð	Uð 	Ur4   NÚdeviceztorch.deviceÚseq_lenrV   r'   ztorch.Tensorc                 ón  — | j         |         d         }| j         |                              dd¦  «        }t          | dd¦  «        p| j        | j        z  }t          ||z  ¦  «        }d}d|t          j        d|dt          j        ¬¦  «         	                    |t          j
        ¬	¦  «        |z  z  z  }	|	|fS )
a{  
        Computes the inverse frequencies according to the original RoPE implementation
        Args:
            config ([`~transformers.PreTrainedConfig`]):
                The model configuration.
            device (`torch.device`):
                The device to use for initialization of the inverse frequencies.
            seq_len (`int`, *optional*):
                The current sequence length. Unused for this type of RoPE.
            layer_type (`str`, *optional*):
                The current layer type if the model has different RoPE parameters per type.
                Should not be used unless `config.layer_types is not None`
        Returns:
            Tuple of (`torch.Tensor`, `float`), containing the inverse frequencies for the RoPE embeddings and the
            post-processing scaling factor applied to the computed cos/sin (unused in this type of RoPE).
        Ú
rope_thetaÚpartial_rotary_factorg      ð?Úhead_dimNr   r7   ©r:   )rj   r:   )ra   ÚgetÚgetattrr1   Únum_attention_headsÚintr,   ÚarangeÚint64r;   rJ   )
rQ   rj   rk   rV   Úbasern   ro   ÚdimÚattention_factorrP   s
             r3   rb   z5LagunaRotaryEmbedding.compute_default_rope_parameters[   sÄ   € ð. Ô% jÔ1°,Ô?ˆà &Ô 6°zÔ B× FÒ FÐG^Ð`cÑ dÔ dÐÝ˜6 :¨tÑ4Ô4Ðh¸Ô8JÈfÔNhÑ8hˆÝ�(Ð2Ñ2Ñ3Ô3ˆàÐð Ø•U”\ ! S¨!µ5´;Ð?Ñ?Ô?×BÒBÈ&ÕX]ÔXcÐBÑdÔdÐgjÑjÑkñ
ˆð Ð)Ð)Ð)r4   c                 ó|  — t          | |› d�¦  «        }t          | |› d�¦  «        }|d d d …d f                              ¦   «                              |j        d         dd¦  «                             |j        ¦  «        }|d d …d d d …f                              ¦   «         }t          |j        j        t          ¦  «        r|j        j        dk    r|j        j        nd}t          |d¬	¦  «        5  |                     ¦   «         |                     ¦   «         z   
                    dd
¦  «        }	t          j        |	|	fd¬¦  «        }
|
                     ¦   «         |z  }|
                     ¦   «         |z  }d d d ¦  «         n# 1 swxY w Y   |                     |j        ¬¦  «        |                     |j        ¬¦  «        fS )NrW   rZ   r   r8   r    ÚmpsÚcpuF)Údevice_typeÚenabledr7   ©rx   rp   )rr   rJ   ÚexpandrE   r;   rj   Ú
isinstanceÚtypeÚstrr   Ú	transposer,   ÚcatÚcosÚsinr:   )r0   ÚxÚposition_idsrV   rP   Úattention_scalingÚinv_freq_expandedÚposition_ids_expandedr}   ÚfreqsÚembr†   r‡   s                r3   rB   zLagunaRotaryEmbedding.forward€   sâ  € õ ˜4 JÐ!9Ð!9Ð!9Ñ:Ô:ˆÝ# D¨ZÐ*KÐ*KÐ*KÑLÔLÐà$ T¨1¨1¨1¨d ]Ô3×9Ò9Ñ;Ô;×BÒBÀ<ÔCUÐVWÔCXÐZ\Ð^_Ñ`Ô`×cÒcÐdeÔdlÑmÔmÐØ ,¨Q¨Q¨Q°°a°a°a¨ZÔ 8× >Ò >Ñ @Ô @Ðå'1°!´(´-ÅÑ'EÔ'EÐkÈ!Ì(Ì-Ð[`ÒJ`ÐJ`�a”h”m�mÐfkˆÝ¨¸UÐCÑCÔCð 	0ð 	0Ø&×,Ò,Ñ.Ô.Ð1F×1LÒ1LÑ1NÔ1NÑN×YÒYÐZ[Ð]^Ñ_Ô_ˆEÝ”)˜U E˜N°Ð3Ñ3Ô3ˆCØ—'’'‘)”)Ð/Ñ/ˆCØ—'’'‘)”)Ð/Ñ/ˆCð		0ð 	0ð 	0ñ 	0ô 	0ð 	0ð 	0ð 	0ð 	0ð 	0ð 	0øøøð 	0ð 	0ð 	0ð 	0ð �vŠv˜AœGˆvÑ$Ô$ c§f¢f°1´7 fÑ&;Ô&;Ð;Ð;s   Ã-BE=Å=FÆF)NNNN©N)rG   rH   rI   r,   rK   Ú__annotations__r!   r*   Ústaticmethodr   rt   rƒ   rD   rJ   rb   Úno_gradr   rB   rL   rM   s   @r3   rO   rO   C   s
  ø€ € € € € € ØŒlÐÐÑðU˜|ð Uð Uð Uð Uð Uð Uð* à&*Ø+/Ø"Ø!%ð	"*ð "*Ø˜tÑ#ð"*à˜Ô(ð"*ð �t‘ð"*ð ˜$‘Jð	"*ð
 
ˆ~˜uÐ$Ô	%ð"*ð "*ð "*ñ „\ð"*ðH €U„]�_„_Øð<ð <ð <ñ Ôñ „_ð<ð <ð <ð <ð <r4   rO   c                   ó&   ‡ — e Zd Zdˆ fd„	Zd„ Zˆ xZS )Ú	LagunaMLPNc                 ó   •— t          ¦   «                              ¦   «          || _        |j        | _        |€|j        n|| _        t          j        | j        | j        d¬¦  «        | _        t          j        | j        | j        d¬¦  «        | _        t          j        | j        | j        d¬¦  «        | _	        t          |j                 | _        d S ©NF©Úbias)r)   r*   rQ   r1   Úintermediate_sizer   ÚLinearÚ	gate_projÚup_projÚ	down_projr   Ú
hidden_actÚact_fn)r0   rQ   r™   r2   s      €r3   r*   zLagunaMLP.__init__”   s±   ø€ Ý‰Œ×ÒÑÔÐØˆŒØ!Ô-ˆÔØ=NÐ=V Ô!9Ð!9Ð\mˆÔÝœ 4Ô#3°TÔ5KÐRWÐXÑXÔXˆŒÝ”y Ô!1°4Ô3IÐPUÐVÑVÔVˆŒÝœ 4Ô#9¸4Ô;KÐRWÐXÑXÔXˆŒÝ˜VÔ.Ô/ˆŒˆˆr4   c                 ó¨   — |                       |                      |                      |¦  «        ¦  «        |                      |¦  «        z  ¦  «        }|S r�   )r�   rŸ   r›   rœ   )r0   rˆ   r�   s      r3   rB   zLagunaMLP.forwardž   sA   € Ø—N’N 4§;¢;¨t¯~ª~¸aÑ/@Ô/@Ñ#AÔ#AÀDÇLÂLÐQRÁOÄOÑ#SÑTÔTˆ	ØÐr4   r�   )rG   rH   rI   r*   rB   rL   rM   s   @r3   r”   r”   “   sL   ø€ € € € € ð0ð 0ð 0ð 0ð 0ð 0ðð ð ð ð ð ð r4   r”   c                   óh   ‡ — e Zd Zˆ fd„Zdej        deej        ej        ej        f         fd„Zˆ xZS )ÚLagunaTopKRouterc                 óx  •— t          ¦   «                              ¦   «          |j        | _        |j        | _        |j        | _        t          j        t          j
        | j        | j        ¦  «        ¦  «        | _        t          j        t          j
        |j        ¦  «        d¬¦  «        | _        |j        | _        d S )NF)Úrequires_grad)r)   r*   Únum_experts_per_tokÚtop_kÚnum_expertsr1   Ú
hidden_dimr   r+   r,   Úzerosr.   Úe_score_correction_biasÚmoe_router_logit_softcappingÚrouter_logit_softcapping©r0   rQ   r2   s     €r3   r*   zLagunaTopKRouter.__init__¤   s�   ø€ Ý‰Œ×ÒÑÔÐØÔ/ˆŒ
Ø!Ô-ˆÔØ Ô,ˆŒÝ”l¥5¤;¨tÔ/?ÀÄÑ#QÔ#QÑRÔRˆŒÝ')¤|µE´KÀÔ@RÑ4SÔ4SÐchÐ'iÑ'iÔ'iˆÔ$Ø(.Ô(KˆÔ%Ð%Ð%r4   r5   r'   c                 ó6  — |                      d| j        ¦  «        }t          j        || j        ¦  «                             ¦   «         }| j        dk    r$t          j        || j        z  ¦  «        | j        z  }t          j	        |¦  «        }|| j
                             |j        ¦  «        z   }t          j        || j        d¬¦  «        \  }}|                     d|¦  «        }||                     dd¬¦  «        z  }|                     |j        ¦  «        }|||fS )Nr8   ç        r   T)rx   r9   )Úreshaper¨   ÚFÚlinearr.   rJ   r¬   r,   ÚtanhÚsigmoidrª   r;   r:   Útopkr¦   ÚgatherÚsum)r0   r5   Úrouter_logitsÚrouting_scoresÚscores_for_selectionÚ_Úselected_expertsÚrouting_weightss           r3   rB   zLagunaTopKRouter.forward­   s  € ð &×-Ò-¨b°$´/ÑBÔBˆÝœ °´Ñ<Ô<×BÒBÑDÔDˆàÔ(¨3Ò.Ð.Ý!œJ }°tÔ7TÑ'TÑUÔUÐX\ÔXuÑuˆMåœ }Ñ5Ô5ˆà-°Ô0L×0OÒ0OÐP^ÔPdÑ0eÔ0eÑeÐÝ#œjÐ)=¸t¼zÈrÐRÑRÔRÑˆÐØ(×/Ò/°Ð4DÑEÔEˆØ)¨O×,?Ò,?ÀBÐPTÐ,?Ñ,UÔ,UÑUˆØ)×,Ò,¨]Ô-@ÑAÔAˆà˜oÐ/?Ð?Ð?r4   )	rG   rH   rI   r*   r,   rK   rD   rB   rL   rM   s   @r3   r¢   r¢   £   s�   ø€ € € € € ðLð Lð Lð Lð Lð@à”|ð@ð 
ˆuŒ|˜Uœ\¨5¬<Ð7Ô	8ð@ð @ð @ð @ð @ð @ð @ð @r4   r¢   c                   ób   ‡ — e Zd ZdZˆ fd„Zdej        dej        dej        dej        fd„Zˆ xZS )ÚLagunaExpertsz2Collection of expert weights stored as 3D tensors.c                 ó´  •— t          ¦   «                              ¦   «          |j        | _        |j        | _        |j        | _        t          j        t          j
        | j        d| j        z  | j        ¦  «        ¦  «        | _        t          j        t          j
        | j        | j        | j        ¦  «        ¦  «        | _        t          |j                 | _        d S )Nr7   )r)   r*   r§   r1   r¨   Úmoe_intermediate_sizeÚintermediate_dimr   r+   r,   ÚemptyÚgate_up_projr�   r   rž   rŸ   r­   s     €r3   r*   zLagunaExperts.__init__Æ   s£   ø€ Ý‰Œ×ÒÑÔÐØ!Ô-ˆÔØ Ô,ˆŒØ &Ô <ˆÔÝœL­¬°TÔ5EÀqÈ4ÔK`ÑG`ÐbfÔbqÑ)rÔ)rÑsÔsˆÔÝœ¥e¤k°$Ô2BÀDÄOÐUYÔUjÑ&kÔ&kÑlÔlˆŒÝ˜VÔ.Ô/ˆŒˆˆr4   r5   Útop_k_indexÚtop_k_weightsr'   c                 ó€  — t          j        |¦  «        }t          j        ¦   «         5  t           j        j                             || j        ¬¦  «        }|                     ddd¦  «        }t          j        | 	                    d¬¦  «        d¦  «         
                    ¦   «         }d d d ¦  «         n# 1 swxY w Y   |D ]þ}|d         }|| j        k    rŒt          j        ||         ¦  «        \  }}	||	         }
t          j                             |
| j        |         ¦  «                             dd¬¦  «        \  }}|                      |¦  «        |z  }t          j                             || j        |         ¦  «        }|||	|d f         z  }|                     d|	|                     |j        ¦  «        ¦  «         Œÿ|S )N)Únum_classesr7   r    r   )r8   éþÿÿÿr   r8   )r,   Ú
zeros_liker’   r   Ú
functionalÚone_hotr§   ÚpermuteÚgreaterr·   ÚnonzeroÚwherer²   rÄ   ÚchunkrŸ   r�   Ú
index_add_r;   r:   )r0   r5   rÅ   rÆ   Úfinal_hidden_statesÚexpert_maskÚ
expert_hitÚ
expert_idxÚ	top_k_posÚ	token_idxÚcurrent_stateÚgateÚupÚcurrent_hidden_statess                 r3   rB   zLagunaExperts.forwardÏ   sø  € õ $Ô.¨}Ñ=Ô=ÐÝŒ]‰_Œ_ð 	Sð 	SÝœ(Ô-×5Ò5°kÈtÔO_Ð5Ñ`Ô`ˆKØ%×-Ò-¨a°°AÑ6Ô6ˆKÝœ {§¢¸8 Ñ'DÔ'DÀaÑHÔH×PÒPÑRÔRˆJð	Sð 	Sð 	Sñ 	Sô 	Sð 	Sð 	Sð 	Sð 	Sð 	Sð 	Søøøð 	Sð 	Sð 	Sð 	Sð
 %ð 
	nð 
	nˆJØ# AœˆJØ˜TÔ-Ò-Ð-ØÝ#(¤;¨{¸:Ô/FÑ#GÔ#GÑ ˆI�yØ)¨)Ô4ˆMÝ”}×+Ò+¨M¸4Ô;LÈZÔ;XÑYÔY×_Ò_Ð`aÐgiÐ_ÑjÔj‰HˆD�"Ø$(§K¢K°Ñ$5Ô$5¸Ñ$:Ð!Ý$&¤M×$8Ò$8Ð9NÐPTÔP^Ð_iÔPjÑ$kÔ$kÐ!Ø$9¸MÈ)ÐU^Ð`dÐJdÔ<eÑ$eÐ!Ø×*Ò*¨1¨iÐ9N×9QÒ9QÐReÔRkÑ9lÔ9lÑmÔmÐmÐmà"Ð"s   ¨A>B2Â2B6Â9B6)	rG   rH   rI   Ú__doc__r*   r,   rK   rB   rL   rM   s   @r3   r¿   r¿   Â   s€   ø€ € € € € à<Ð<ð0ð 0ð 0ð 0ð 0ð#à”|ð#ð ”\ð#ð ”|ð	#ð
 
Œð#ð #ð #ð #ð #ð #ð #ð #r4   r¿   c                   óH   ‡ — e Zd Zdefˆ fd„Zdej        dej        fd„Zˆ xZS )ÚLagunaSparseMoeBlockrQ   c                 óæ   •— t          ¦   «                              ¦   «          t          |¦  «        | _        t	          |¦  «        | _        t          ||j        ¬¦  «        | _        |j	        | _
        d S )N©r™   )r)   r*   r¿   Úexpertsr¢   rÚ   r”   Úshared_expert_intermediate_sizeÚshared_expertsÚmoe_routed_scaling_factorÚrouted_scaling_factorr­   s     €r3   r*   zLagunaSparseMoeBlock.__init__ë   s`   ø€ Ý‰Œ×ÒÑÔÐÝ$ VÑ,Ô,ˆŒÝ$ VÑ,Ô,ˆŒ	Ý'¨À&ÔBhÐiÑiÔiˆÔØ%+Ô%EˆÔ"Ð"Ð"r4   r5   r'   c                 ó  — |j         \  }}}|                     d|¦  «        }|                      |¦  «        }|                      |¦  «        \  }}}|                      |||¦  «        }|| j        z  }||z   }|                     |||¦  «        }|S )Nr8   )rE   Úviewrä   rÚ   râ   ræ   r°   )	r0   r5   Ú
batch_sizeÚsequence_lengthr¨   Úshared_outputr»   r½   r¼   s	            r3   rB   zLagunaSparseMoeBlock.forwardò   sœ   € Ø2?Ô2EÑ/ˆ
�O ZØ%×*Ò*¨2¨zÑ:Ô:ˆØ×+Ò+¨MÑ:Ô:ˆà/3¯yªy¸Ñ/GÔ/GÑ,ˆˆ?Ð,ØŸš ]Ð4DÀoÑVÔVˆà%¨Ô(BÑBˆØ%¨Ñ5ˆà%×-Ò-¨j¸/È:ÑVÔVˆØÐr4   )	rG   rH   rI   r!   r*   r,   rK   rB   rL   rM   s   @r3   rß   rß   ê   sq   ø€ € € € € ðF˜|ð Fð Fð Fð Fð Fð Fð U¤\ð °e´lð ð ð ð ð ð ð ð r4   rß   c                 óœ   — | dd| j         d         dz  …f         }| d| j         d         dz  d…f         }t          j        | |fd¬¦  «        S )z*Rotates half the hidden dims of the input..Nr8   r7   r   )rE   r,   r…   )rˆ   Úx1Úx2s      r3   Úrotate_halfrï     s]   € à	
ˆ3Ð"�!”'˜"”+ Ñ"Ð"Ð"Ô	#€BØ	
ˆ3�”˜”˜qÑ Ð"Ð"Ð"Ô	#€BÝŒ9�r�c˜2�Y BÐ'Ñ'Ô'Ð'r4   c                 ó˜  — |                      |¦  «        }|                      |¦  «        }|j        d         }| dd|…f         | d|d…f         }}|dd|…f         |d|d…f         }	}||z  t          |¦  «        |z  z   }
||z  t          |¦  «        |z  z   }t          j        |
|gd¬¦  «        }
t          j        ||	gd¬¦  «        }|
|fS )a»  Applies Rotary Position Embedding to the query and key tensors.

    Removes the interleaving of cos and sin from GLM

    Args:
        q (`torch.Tensor`): The query tensor.
        k (`torch.Tensor`): The key tensor.
        cos (`torch.Tensor`): The cosine part of the rotary embedding.
        sin (`torch.Tensor`): The sine part of the rotary embedding.
        unsqueeze_dim (`int`, *optional*, defaults to 1):
            The 'unsqueeze_dim' argument specifies the dimension along which to unsqueeze cos[position_ids] and
            sin[position_ids] so that they can be properly broadcasted to the dimensions of q and k. For example, note
            that cos[position_ids] and sin[position_ids] have the shape [batch_size, seq_len, head_dim]. Then, if q and
            k have the shape [batch_size, heads, seq_len, head_dim], then setting unsqueeze_dim=1 makes
            cos[position_ids] and sin[position_ids] broadcastable to the shapes of q and k. Similarly, if q and k have
            the shape [batch_size, seq_len, heads, head_dim], then set unsqueeze_dim=2.
    Returns:
        `tuple(torch.Tensor)` comprising of the query and key tensors rotated using the Rotary Position Embedding.
    r8   .Nr   )Ú	unsqueezerE   rï   r,   r…   )ÚqÚkr†   r‡   Úunsqueeze_dimÚ
rotary_dimÚq_rotÚq_passÚk_rotÚk_passÚq_embedÚk_embeds               r3   Úapply_rotary_pos_embrü   	  sô   € ð( �-Š-˜Ñ
&Ô
&€CØ
�-Š-˜Ñ
&Ô
&€Cð ”˜2”€JØ�c˜;˜J˜;Ð&Ô'¨¨3°
°°Ð+;Ô)<ˆ6€EØ�c˜;˜J˜;Ð&Ô'¨¨3°
°°Ð+;Ô)<ˆ6€Eð �s‰{�{¨5Ñ1Ô1°CÑ7Ñ8€GØ�s‰{�{¨5Ñ1Ô1°CÑ7Ñ8€Gõ Œi˜ &Ð)¨rÐ2Ñ2Ô2€GÝŒi˜ &Ð)¨rÐ2Ñ2Ô2€GØ�GÐÐr4   r5   Ún_repr'   c                 ó¸   — | j         \  }}}}|dk    r| S | dd…dd…ddd…dd…f                              |||||¦  «        } |                      |||z  ||¦  «        S )zÔ
    This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,
    num_key_value_heads, seqlen, head_dim) to (batch, num_attention_heads, seqlen, head_dim)
    r    N)rE   r€   r°   )r5   rý   ÚbatchÚnum_key_value_headsÚslenro   s         r3   Ú	repeat_kvr  /  s„   € ð
 2?Ô1DÑ.€EÐ  hØ�‚z€zØÐØ! ! ! ! Q Q Q¨¨a¨a¨a°°°Ð"2Ô3×:Ò:¸5ÐBUÐW\Ð^bÐdlÑmÔm€MØ× Ò  Ð(;¸eÑ(CÀTÈ8ÑTÔTÐTr4   r¯   ÚmoduleÚqueryÚkeyÚvalueÚattention_maskÚscalingÚdropoutÚkwargsc                 ó  — t          || j        ¦  «        }t          || j        ¦  «        }	t          j        ||                     dd¦  «        ¦  «        |z  }
|�|
|z   }
t
          j                             |
dt          j        ¬¦  «         	                    |j
        ¦  «        }
t
          j                             |
|| j        ¬¦  «        }
t          j        |
|	¦  «        }|                     dd¦  «                             ¦   «         }||
fS )Nr7   r   r8   )rx   r:   )ÚpÚtrainingr    )r  Únum_key_value_groupsr,   Úmatmulr„   r   rË   Úsoftmaxr<   r;   r:   r	  r  Ú
contiguous)r  r  r  r  r  r  r	  r
  Ú
key_statesÚvalue_statesÚattn_weightsÚattn_outputs               r3   Úeager_attention_forwardr  ;  sé   € õ ˜3 Ô ;Ñ<Ô<€JÝ˜U FÔ$?Ñ@Ô@€Lå”<  z×';Ò';¸A¸qÑ'AÔ'AÑBÔBÀWÑL€LØÐ!Ø# nÑ4ˆå”=×(Ò(¨¸2ÅUÄ]Ð(ÑSÔS×VÒVÐW\ÔWbÑcÔc€LÝ”=×(Ò(¨¸È6Ì?Ð(Ñ[Ô[€LÝ”,˜|¨\Ñ:Ô:€KØ×'Ò'¨¨1Ñ-Ô-×8Ò8Ñ:Ô:€Kà˜Ð$Ð$r4   c                   óÎ   ‡ — e Zd ZdZdededefˆ fd„Z	 ddej        de	ej        ej        f         d	ej        dz  d
e
dz  dee         de	ej        ej        dz  f         fd„Zˆ xZS )ÚLagunaAttentionzSAfmoe-style SWA/GQA attention with Laguna-specific gating and per-layer head count.rQ   Ú	layer_idxÚ	num_headsc                 ó@  •— t          ¦   «                              ¦   «          || _        || _        || _        t          |d|j        |j        z  ¦  «        | _        | j        |j	        z  | _
        | j        dz  | _        |j        | _        d| _        t          j        |j        | j        | j        z  |j        ¬¦  «        | _        t          j        |j        |j	        | j        z  |j        ¬¦  «        | _        t          j        |j        |j	        | j        z  |j        ¬¦  «        | _        t          j        | j        | j        z  |j        |j        ¬¦  «        | _        |j        |         dk    | _        | j        r|j        nd | _        t1          | j        |j        ¬¦  «        | _        t1          | j        |j        ¬¦  «        | _        |j        du p
|j        dk    | _        | j        r| j        n| j        | j        z  }t          j        |j        |d¬¦  «        | _        d S )	Nro   g      à¿Tr—   Úsliding_attention©r&   zper-headF)r)   r*   r  rQ   r  rr   r1   rs   ro   r   r  r  Úattention_dropoutÚ	is_causalr   rš   Úattention_biasÚq_projÚk_projÚv_projÚo_projr`   Úis_local_attentionÚsliding_windowr$   Úrms_norm_epsÚq_normÚk_normÚgatingÚgate_per_headÚg_proj)r0   rQ   r  r  Ú
g_proj_dimr2   s        €r3   r*   zLagunaAttention.__init__W  sí  ø€ Ý‰Œ×ÒÑÔÐà"ˆŒØˆŒØ"ˆŒÝ ¨
°FÔ4FÈ&ÔJdÑ4dÑeÔeˆŒØ$(¤N°fÔ6PÑ$PˆÔ!Ø”} dÑ*ˆŒØ!'Ô!9ˆÔØˆŒå”i Ô 2°D´NÀTÄ]Ñ4RÐY_ÔYnÐoÑoÔoˆŒÝ”iØÔ Ô :¸T¼]Ñ JÐQWÔQfð
ñ 
ô 
ˆŒõ ”iØÔ Ô :¸T¼]Ñ JÐQWÔQfð
ñ 
ô 
ˆŒõ ”i ¤°´Ñ >ÀÔ@RÐY_ÔYnÐoÑoÔoˆŒð #)Ô"4°YÔ"?ÐCVÒ"VˆÔØ7;Ô7NÐX˜fÔ3Ð3ÐTXˆÔå# D¤M°vÔ7JÐKÑKÔKˆŒÝ# D¤M°vÔ7JÐKÑKÔKˆŒØ#œ]¨dÐ2ÐQ°f´mÀzÒ6QˆÔØ'+Ô'9Ð]�T”^�^¸t¼~ÐPTÔP]Ñ?]ˆ
Ý”i Ô 2°JÀUÐKÑKÔKˆŒˆˆr4   Nr5   Úposition_embeddingsr  Úpast_key_valuesr
  r'   c                 ó´  — |j         d d…         }g |¢d‘| j        ‘R }|                      |¦  «                             |¦  «        }|                      |¦  «                             |¦  «        }	|                      |¦  «                             |¦  «        }
|                      |¦  «                             dd¦  «        }|                      |	¦  «                             dd¦  «        }	|
                     dd¦  «        }
|\  }}t          ||	||¦  «        \  }}	|�| 
                    |	|
| j        ¦  «        \  }	}
t          j        | j        j        t           ¦  «        } || ||	|
|f| j        sdn| j        | j        | j        dœ|¤Ž\  }} |j        g |¢d‘R Ž                      ¦   «         }t/          j        |                      |¦  «                             ¦   «         ¦  «                             |j        ¦  «        }| j        r:  |j        g |¢d‘| j        ‘R Ž |                     d¦  «        z  j        g |¢d‘R Ž }n||z  }|                      |¦  «        }||fS )Nr8   r    r7   r¯   )r	  r  r&  ) rE   ro   r!  rè   r"  r#  r(  r„   r)  rü   Úupdater  r   Úget_interfacerQ   Ú_attn_implementationr  r  r  r  r&  r°   r  r±   Úsoftplusr,  rJ   r;   r:   r+  rñ   r$  )r0   r5   r.  r  r/  r
  Úinput_shapeÚhidden_shapeÚquery_statesr  r  r†   r‡   Úattention_interfacer  r  rÚ   s                    r3   rB   zLagunaAttention.forwardv  s–  € ð $Ô)¨#¨2¨#Ô.ˆØ8˜Ð8 bÐ8¨$¬-Ð8Ð8ˆà—{’{ =Ñ1Ô1×6Ò6°|ÑDÔDˆØ—[’[ Ñ/Ô/×4Ò4°\ÑBÔBˆ
Ø—{’{ =Ñ1Ô1×6Ò6°|ÑDÔDˆà—{’{ <Ñ0Ô0×:Ò:¸1¸aÑ@Ô@ˆØ—[’[ Ñ,Ô,×6Ò6°q¸!Ñ<Ô<ˆ
Ø#×-Ò-¨a°Ñ3Ô3ˆà&‰ˆˆSÝ#7¸ÀjÐRUÐWZÑ#[Ô#[Ñ ˆ�jàÐ&Ø'6×'=Ò'=¸jÈ,ÐX\ÔXfÑ'gÔ'gÑ$ˆJ˜å(?Ô(MØŒKÔ,Õ.Eñ)
ô )
Ðð %8Ð$7ØØØØØð
%
ð  $œ}ÐH�C�C°$Ô2HØ”LØÔ.ð
%
ð 
%
ð ð
%
ð 
%
Ñ!ˆ�\ð *�kÔ)Ð;¨;Ð;¸Ð;Ð;Ð;×FÒFÑHÔHˆåŒz˜$Ÿ+š+ mÑ4Ô4×:Ò:Ñ<Ô<Ñ=Ô=×@Ò@ÀÔARÑSÔSˆØÔð 	-ØgÐ+˜;Ô+ÐL¨[ÐL¸"ÐL¸d¼mÐLÐLÐLÈtÏ~Ê~Ð^`ÑOaÔOaÑaÔgð ØðØ ðð ð ˆKˆKð &¨Ñ,ˆKà—k’k +Ñ.Ô.ˆØ˜LÐ(Ð(r4   r�   )rG   rH   rI   rÝ   r!   rt   r*   r,   rK   rD   r	   r   r   rB   rL   rM   s   @r3   r  r  T  sî   ø€ € € € € Ø]Ð]ðL˜|ð L¸ð LÈð Lð Lð Lð Lð Lð LðH )-ð3)ð 3)à”|ð3)ð # 5¤<°´Ð#=Ô>ð3)ð œ tÑ+ð	3)ð
  ™ð3)ð Ð-Ô.ð3)ð 
ˆuŒ|˜Uœ\¨DÑ0Ð0Ô	1ð3)ð 3)ð 3)ð 3)ð 3)ð 3)ð 3)ð 3)r4   r  c                   óÒ   ‡ — e Zd Zdedefˆ fd„Z	 	 	 	 	 ddej        dej        dz  dej        dz  d	e	dz  d
e
dz  deej        ej        f         dz  dee         dej        fd„Zˆ xZS )ÚLagunaDecoderLayerrQ   r  c                 ó¤  •— t          ¦   «                              ¦   «          |j        | _        t          |||j        |         ¦  «        | _        |j        |         dk    rt          |¦  «        | _        nt          ||j
        ¬¦  «        | _        t          |j        |j        ¬¦  «        | _        t          |j        |j        ¬¦  «        | _        d S )NÚsparserá   r  )r)   r*   r1   r  Únum_attention_heads_per_layerÚ	self_attnÚmlp_layer_typesrß   Úmlpr”   r™   r$   r'  Úinput_layernormÚpost_attention_layernorm)r0   rQ   r  r2   s      €r3   r*   zLagunaDecoderLayer.__init__­  s·   ø€ Ý‰Œ×ÒÑÔÐØ!Ô-ˆÔÝ(¨°¸FÔ<`ÐajÔ<kÑlÔlˆŒØÔ! )Ô,°Ò8Ð8Ý+¨FÑ3Ô3ˆDŒHˆHå  ¸6Ô;SÐTÑTÔTˆDŒHÝ,¨VÔ-?ÀVÔEXÐYÑYÔYˆÔÝ(5°fÔ6HÈfÔNaÐ(bÑ(bÔ(bˆÔ%Ð%Ð%r4   NFr5   r  r‰   r/  Ú	use_cacher.  r
  r'   c           
      óÎ   — |}|                       |¦  «        } | j        d||||||dœ|¤Ž\  }}	||z   }|}|                      |¦  «        }|                      |¦  «        }||z   }|S )N)r5   r  r‰   r/  rC  r.  © )rA  r>  rB  r@  )
r0   r5   r  r‰   r/  rC  r.  r
  Úresidualr»   s
             r3   rB   zLagunaDecoderLayer.forward¸  s¡   € ð !ˆØ×,Ò,¨]Ñ;Ô;ˆà)˜4œ>ð 
Ø'Ø)Ø%Ø+ØØ 3ð
ð 
ð ð
ð 
Ñˆ�qð ! =Ñ0ˆð !ˆØ×5Ò5°mÑDÔDˆØŸš Ñ/Ô/ˆØ  =Ñ0ˆØÐr4   )NNNFN)rG   rH   rI   r!   rt   r*   r,   rK   Ú
LongTensorr	   ÚboolrD   r   r   rB   rL   rM   s   @r3   r:  r:  ¬  sÿ   ø€ € € € € ð	c˜|ð 	c¸ð 	cð 	cð 	cð 	cð 	cð 	cð /3Ø04Ø(,Ø!&ØHLðð à”|ðð œ tÑ+ðð Ô&¨Ñ-ð	ð
  ™ðð ˜$‘;ðð # 5¤<°´Ð#=Ô>ÀÑEðð Ð+Ô,ðð 
Œðð ð ð ð ð ð ð r4   r:  c                   óž   ‡ — e Zd ZU eed<   dZdZdgZdgZdZ	dZ
dZdZdZ eed¬¦  «        eedœZ ej        ¦   «         ˆ fd	„¦   «         Zˆ xZS )
ÚLagunaPreTrainedModelrQ   ÚmodelTr:  r/  r   )Úindex)r¸   r5   Ú
attentionsc                 óD  •— t          ¦   «                              |¦  «         | j        j        }t	          |t
          ¦  «        r9t          j        |j        d|¬¦  «         t          j        |j	        d|¬¦  «         n1t	          |t          ¦  «        rt          j        |j        d|¬¦  «         t	          |t          ¦  «        r+t          j        j                             |j        ¦  «         d S t	          |t           ¦  «        r›|j        D ]•}|j        }|j        |         dk    rt(          |j        |                  } ||j        |¬¦  «        \  }}t          j        t-          ||› d�¦  «        |¦  «         t          j        t-          ||› d�¦  «        |¦  «         Œ”d S d S )Nr¯   )r>   ÚstdrT   rU   rW   rY   )r)   Ú_init_weightsrQ   Úinitializer_ranger�   r¿   ÚinitÚnormal_rÄ   r�   r¢   r.   r,   r   Úzeros_rª   rO   r`   rb   rS   r   Úcopy_rr   )r0   r  rO  rV   rg   rh   r»   r2   s          €r3   rP  z#LagunaPreTrainedModel._init_weightsë  s¤  ø€ å‰Œ×Ò˜fÑ%Ô%Ð%ØŒkÔ+ˆÝ�f�mÑ,Ô,ð 	;ÝŒL˜Ô,°3¸CÐ@Ñ@Ô@Ð@ÝŒL˜Ô)°¸Ð=Ñ=Ô=Ð=Ð=Ý˜Õ 0Ñ1Ô1ð 	;ÝŒL˜œ¨S°cÐ:Ñ:Ô:Ð:Ý�fÕ.Ñ/Ô/ð 		^ÝŒHŒM× Ò  Ô!?Ñ@Ô@Ð@Ð@Ð@Ý˜Õ 5Ñ6Ô6ð 	^Ø$Ô0ð ^ð ^�
Ø%ÔE�ØÔ# JÔ/°9Ò<Ð<Ý#6°vÔ7GÈ
Ô7SÔ#T�LØ#/ <°´È*Ð#UÑ#UÔ#UÑ �˜qÝ”
�7 6¨jÐ+CÐ+CÐ+CÑDÔDÀmÑTÔTÐTÝ”
�7 6¨jÐ+LÐ+LÐ+LÑMÔMÈ}Ñ]Ô]Ð]Ð]ð	^ð 	^ð^ð ^r4   )rG   rH   rI   r!   r�   Úbase_model_prefixÚsupports_gradient_checkpointingÚ_no_split_modulesÚ_skip_keys_device_placementÚ_supports_flash_attnÚ_supports_sdpaÚ_supports_flex_attnÚ_can_compile_fullgraphÚ_supports_attention_backendr   r¢   r:  r  Ú_can_record_outputsr,   r’   rP  rL   rM   s   @r3   rJ  rJ  Ø  sÄ   ø€ € € € € € àÐÐÑØÐØ&*Ð#Ø-Ð.ÐØ#4Ð"5ÐØÐØ€NØÐà!ÐØ"&Ðà'˜Ð(8ÀÐBÑBÔBØ+Ø%ðð Ðð €U„]�_„_ð^ð ^ð ^ð ^ñ „_ð^ð ^ð ^ð ^ð ^r4   rJ  c                   óâ   ‡ — e Zd Zdefˆ fd„Zeee	 	 	 	 	 	 ddej	        dz  dej
        dz  dej	        dz  dedz  dej        dz  d	edz  d
ee         defd„¦   «         ¦   «         ¦   «         Zˆ xZS )ÚLagunaModelrQ   c                 óÞ  •‡— t          ¦   «                              ‰¦  «         ‰j        | _        ‰j        | _        t          j        ‰j        ‰j        | j        ¦  «        | _        t          j	        ˆfd„t          ‰j        ¦  «        D ¦   «         ¦  «        | _        t          ‰j        ‰j        ¬¦  «        | _        t!          ‰¬¦  «        | _        d| _        |                      ¦   «          d S )Nc                 ó0   •— g | ]}t          ‰|¦  «        ‘ŒS rE  )r:  )Ú.0r  rQ   s     €r3   ú
<listcomp>z(LagunaModel.__init__.<locals>.<listcomp>	  s$   ø€ ÐdÐdÐd°yÕ ¨	Ñ2Ô2ÐdÐdÐdr4   r  ©rQ   F)r)   r*   Úpad_token_idÚpadding_idxÚ
vocab_sizer   Ú	Embeddingr1   Úembed_tokensÚ
ModuleListÚrangeÚnum_hidden_layersÚlayersr$   r'  ÚnormrO   Ú
rotary_embÚgradient_checkpointingÚ	post_initr­   s    `€r3   r*   zLagunaModel.__init__  sÔ   øø€ Ý‰Œ×Ò˜Ñ Ô Ð Ø!Ô.ˆÔØ Ô+ˆŒåœL¨Ô):¸FÔ<NÐPTÔP`ÑaÔaˆÔÝ”mØdÐdÐdÐdÅEÈ&ÔJbÑDcÔDcÐdÑdÔdñ
ô 
ˆŒõ " &Ô"4¸&Ô:MÐNÑNÔNˆŒ	Ý/°vÐ>Ñ>Ô>ˆŒØ&+ˆÔ#ð 	�ŠÑÔÐÐÐr4   NÚ	input_idsr  r‰   r/  Úinputs_embedsrC  r
  r'   c           	      ó˜  ‡— |d u |d uz  rt          d¦  «        ‚|€|                      |¦  «        }|r|€t          | j        ¬¦  «        }|€V|�|                     ¦   «         nd}t          j        |j        d         |j        ¬¦  «        |z   }| 	                    d¦  «        }t          |x}	t          ¦  «        sI| j        ||||dœŠˆfd„ˆfd„d	œ}
i }	t          | j        j        ¦  «        D ]} |
|         ¦   «         |	|<   Œ|}i }t          | j        j        ¦  «        D ]}|                      |||¦  «        ||<   Œt          | j        d | j        j        …         ¦  «        D ]?\  }} ||f|	| j        j        |                  || j        j        |                  ||d
œ|¤Ž}Œ@|                      |¦  «        }t'          ||r|nd ¬¦  «        S )Nz:You must specify exactly one of input_ids or inputs_embedsrf  r   r    )rj   )rQ   ru  r  r/  r‰   c                  ó   •— t          di ‰ ¤ŽS ©NrE  )r   ©Úmask_kwargss   €r3   ú<lambda>z%LagunaModel.forward.<locals>.<lambda>6  s   ø€ Õ*<Ð*KÐ*K¸{Ð*KÐ*K€ r4   c                  ó   •— t          di ‰ ¤ŽS rx  )r   ry  s   €r3   r{  z%LagunaModel.forward.<locals>.<lambda>7  s   ø€ Õ-NÐ-]Ð-]ÐQ\Ð-]Ð-]€ r4   )Úfull_attentionr  )r  r.  r‰   r/  )Úlast_hidden_stater/  )Ú
ValueErrorrk  r
   rQ   Úget_seq_lengthr,   ru   rE   rj   rñ   r�   Údictr_   r`   rq  Ú	enumeratero  rn  rp  r   )r0   rt  r  r‰   r/  ru  rC  r
  Úpast_seen_tokensÚcausal_mask_mappingÚmask_creation_functionsrV   r5   r.  ÚiÚdecoder_layerrz  s                   @r3   rB   zLagunaModel.forward  sc  ø€ ð ˜Ð -°tÐ";Ñ<ð 	[ÝÐYÑZÔZÐZàÐ Ø ×-Ò-¨iÑ8Ô8ˆMàð 	?˜Ð0Ý*°$´+Ð>Ñ>Ô>ˆOàÐØCRÐC^˜×=Ò=Ñ?Ô?Ð?ÐdeÐÝ œ<¨Ô(;¸AÔ(>À}ÔG[Ð\Ñ\Ô\Ð_oÑoˆLØ'×1Ò1°!Ñ4Ô4ˆLå°Ð?Ð-ÅÑFÔFð 	Xàœ+Ø!.Ø"0Ø#2Ø ,ðð ˆKð #LÐ"KÐ"KÐ"KØ%]Ð%]Ð%]Ð%]ð'ð 'Ð#ð #%ÐÝ! $¤+Ô"9Ñ:Ô:ð Xð X�
Ø2UÐ2IÈ*Ô2UÑ2WÔ2WÐ# JÑ/Ð/à%ˆØ ÐÝ˜dœkÔ5Ñ6Ô6ð 	gð 	gˆJØ.2¯oªo¸mÈ\Ð[eÑ.fÔ.fÐ 
Ñ+Ð+å )¨$¬+Ð6U¸¼Ô8UÐ6UÔ*VÑ WÔ Wð 	ð 	ÑˆAˆ}Ø)˜MØðà2°4´;Ô3JÈ1Ô3MÔNØ$7¸¼Ô8OÐPQÔ8RÔ$SØ)Ø /ðð ð ðð ˆMˆMð Ÿ	š	 -Ñ0Ô0ˆå%Ø+Ø/8ÐB˜O˜O¸dð
ñ 
ô 
ð 	
r4   )NNNNNN)rG   rH   rI   r!   r*   r   r   r   r,   rG  rK   r	   ÚFloatTensorrH  r   r   r   rB   rL   rM   s   @r3   ra  ra     s  ø€ € € € € ð˜|ð ð ð ð ð ð ð   ØØð .2Ø.2Ø04Ø(,Ø26Ø!%ð<
ð <
àÔ# dÑ*ð<
ð œ tÑ+ð<
ð Ô&¨Ñ-ð	<
ð
  ™ð<
ð Ô(¨4Ñ/ð<
ð ˜$‘;ð<
ð Ð+Ô,ð<
ð 
 ð<
ð <
ð <
ñ „^ñ „_ñ  Ôð<
ð <
ð <
ð <
ð <
r4   ra  r7   Úgate_logitsr§   c                 óÆ  ‡— | �t          | t          ¦  «        sdS t          | t          ¦  «        r/| d         j        Št          j        ˆfd„| D ¦   «         d¬¦  «        }t          j        j                             |d¬¦  «        }t          j        ||d¬¦  «        \  }}t          j        j         	                    ||¦  «        }|€@t          j
        |                     ¦   «         d¬¦  «        }	t          j
        |d¬¦  «        }
�n.|j        \  }}|j        d         ||z  z  }|ddd…dd…ddf                              |||||f¦  «                             d||¦  «                             ‰¦  «        }t          j        |                     ¦   «         |z  d¬¦  «        t          j        |d¬¦  «        z  }	|ddd…dd…df                              ||||f¦  «                             d|¦  «                             ‰¦  «        }t          j        ||z  d¬¦  «        t          j        |d¬¦  «        z  }
t          j        |	|
                     d¦  «        z  ¦  «        }||z  S )aÄ  
    Computes auxiliary load balancing loss as in Switch Transformer - implemented in Pytorch.

    See Switch Transformer (https://huggingface.co/papers/2101.03961) for more details. This function implements the loss
    function presented in equations (4) - (6) of the paper. It aims at penalizing cases where the routing between
    experts is too unbalanced.

    Args:
        gate_logits:
            Logits from the `gate`, should be a tuple of model.config.num_hidden_layers tensors of
            shape [batch_size X sequence_length, num_experts].
        num_experts:
            Number of experts
        top_k:
            The number of experts to route per-token, can be also interpreted as the `top-k` routing
            parameter.
        attention_mask (`torch.Tensor`, *optional*):
            The attention_mask used in forward function
            shape [batch_size X sequence_length] if not None.

    Returns:
        The auxiliary loss.
    Nr   c                 ó:   •— g | ]}|                      ‰¦  «        ‘ŒS rE  )r;   )rd  Ú
layer_gateÚcompute_devices     €r3   re  z,load_balancing_loss_func.<locals>.<listcomp>v  s&   ø€ Ð-jÐ-jÐ-jÐPZ¨j¯mªm¸NÑ.KÔ.KÐ-jÐ-jÐ-jr4   r   r8   )r�   rD   rj   r,   r…   r   rË   r  rµ   rÌ   r>   rJ   rE   r€   r°   r;   r·   rñ   )r‰  r§   r¦   r  Úconcatenated_gate_logitsr½   r»   r¼   rÔ   Útokens_per_expertÚrouter_prob_per_expertré   rê   rn  Úexpert_attention_maskÚ router_per_expert_attention_maskÚoverall_lossr�  s                    @r3   Úload_balancing_loss_funcr”  T  s�  ø€ ð: Ð¥*¨[½%Ñ"@Ô"@ÐØˆqå�+�uÑ%Ô%ð sØ$ QœÔ.ˆÝ#(¤9Ð-jÐ-jÐ-jÐ-jÐ^iÐ-jÑ-jÔ-jÐpqÐ#rÑ#rÔ#rÐ å”hÔ)×1Ò1Ð2JÐPRÐ1ÑSÔS€Oåœ* _°eÀÐDÑDÔDÑ€AÐå”(Ô%×-Ò-Ð.>ÀÑLÔL€KàÐå!œJ {×'8Ò'8Ñ':Ô':ÀÐBÑBÔBÐõ "'¤¨OÀÐ!CÑ!CÔ!CÐÑà&4Ô&:Ñ#ˆ
�OØ4Ô:¸1Ô=À*ÈÑB^Ñ_Ðð ˜4    A A A t¨TÐ1Ô2ßŠVÐ&¨
°OÀUÈKÐXÑYÔYßŠW�R˜ Ñ,Ô,ßŠR�ÑÔð	 	õ "œI k×&7Ò&7Ñ&9Ô&9Ð<QÑ&QÐWXÐYÑYÔYÕ\aÔ\eØ! qð]
ñ ]
ô ]
ñ 
Ðð ˜4    A A A tÐ+Ô,ßŠVÐ&¨
°OÀ[ÐQÑRÔRßŠW�R˜Ñ%Ô%ßŠR�ÑÔð	 	)õ "'¤¨?Ð=]Ñ+]ÐcdÐ!eÑ!eÔ!eÕhmÔhqØ,°!ði
ñ i
ô i
ñ "
Ðõ ”9Ð.Ð1G×1QÒ1QÐRSÑ1TÔ1TÑTÑUÔU€LØ˜+Ñ%Ð%r4   c                   ó$  ‡ — e Zd ZddiZddiZddgdgfiZˆ fd„Zee	 	 	 	 	 	 	 	 	 dd
e	j
        dz  de	j        dz  de	j
        dz  dedz  de	j        dz  de	j
        dz  dedz  dedz  dee	j        z  dee         defd„¦   «         ¦   «         Zˆ xZS )ÚLagunaForCausalLMzlm_head.weightzmodel.embed_tokens.weightÚlm_headÚcolwise_gather_outputr5   Úlogitsc                 óF  •— t          ¦   «                              |¦  «         t          |¦  «        | _        |j        | _        t          j        |j        |j        d¬¦  «        | _        |j	        | _	        |j
        | _
        |j        | _        |                      ¦   «          d S r–   )r)   r*   ra  rK  ri  r   rš   r1   r—  Úrouter_aux_loss_coefr§   r¥   rs  r­   s     €r3   r*   zLagunaForCausalLM.__init__¬  s‹   ø€ Ý‰Œ×Ò˜Ñ Ô Ð Ý  Ñ(Ô(ˆŒ
Ø Ô+ˆŒÝ”y Ô!3°VÔ5FÈUÐSÑSÔSˆŒØ$*Ô$?ˆÔ!Ø!Ô-ˆÔØ#)Ô#=ˆÔ ð 	�ŠÑÔÐÐÐr4   Nr   rt  r  r‰   r/  ru  ÚlabelsrC  Úoutput_router_logitsÚlogits_to_keepr
  r'   c
                 ó  — |�|n| j         j        } | j        d|||||||dœ|
¤Ž}|j        }t	          |	t
          ¦  «        rt          |	 d¦  «        n|	}|                      |dd…|dd…f         ¦  «        }d}|� | j        ||| j	        fi |
¤Ž}d}|rHt          |j        | j        | j        |¦  «        }|�%|| j        |                     |j        ¦  «        z  z  }t#          ||||j        |j        |j        |j        ¬¦  «        S )a­  
        labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
            Labels for computing the masked language modeling loss. Indices should either be in `[0, ...,
            config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored
            (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`.
        N)rt  r  r‰   r/  ru  rC  r�  )ÚlossÚaux_lossr™  r/  r5   rM  r¸   rE  )rQ   r�  rK  r~  r�   rt   Úslicer—  Úloss_functionri  r”  r¸   r§   r¥   r›  r;   rj   r   r/  r5   rM  )r0   rt  r  r‰   r/  ru  rœ  rC  r�  rž  r
  Úoutputsr5   Úslice_indicesr™  r   r¡  s                    r3   rB   zLagunaForCausalLM.forward¸  sm  € ð. %9Ð$DÐ Ð È$Ì+ÔJjð 	ð
 +5¨$¬*ð 	+
ØØ)Ø%Ø+Ø'ØØ!5ð	+
ð 	+
ð ð	+
ð 	+
ˆð  Ô1ˆå8BÀ>ÕSVÑ8WÔ8WÐk�˜~˜o¨tÑ4Ô4Ð4Ð]kˆØ—’˜m¨A¨A¨A¨}¸a¸a¸aÐ,?Ô@ÑAÔAˆàˆØÐØ%�4Ô% f¨f°d´oÐPÐPÈÐPÐPˆDàˆØð 	MÝ/ØÔ%ØÔ ØÔ(Øñ	ô ˆHð Ð!Ø˜Ô1°H·K²KÀÄÑ4LÔ4LÑLÑL�å(ØØØØ#Ô3Ø!Ô/ØÔ)Ø!Ô/ð
ñ 
ô 
ð 	
r4   )	NNNNNNNNr   )rG   rH   rI   Ú_tied_weights_keysÚ_tp_planÚ_pp_planr*   r   r   r,   rG  rK   r	   rˆ  rH  rt   r   r   r   rB   rL   rM   s   @r3   r–  r–  ¦  sp  ø€ € € € € à*Ð,GÐHÐØÐ2Ð3€HØ˜_Ð-°¨zÐ:Ð;€Hð
ð 
ð 
ð 
ð 
ð Øð .2Ø.2Ø04Ø(,Ø26Ø*.Ø!%Ø,0Ø-.ð@
ð @
àÔ# dÑ*ð@
ð œ tÑ+ð@
ð Ô&¨Ñ-ð	@
ð
  ™ð@
ð Ô(¨4Ñ/ð@
ð Ô  4Ñ'ð@
ð ˜$‘;ð@
ð # T™kð@
ð ˜eœlÑ*ð@
ð Ð+Ô,ð@
ð 
#ð@
ð @
ð @
ñ „^ñ Ôð@
ð @
ð @
ð @
ð @
r4   r–  )r–  ra  rJ  )r    )r¯   )Nr7   N)JÚcollections.abcr   Útypingr   r,   Útorch.nn.functionalr   rË   r±   Ú r   rR  Úactivationsr   Úcache_utilsr	   r
   Ú
generationr   Úintegrationsr   r   Úmasking_utilsr   r   Úmodeling_flash_attention_utilsr   Úmodeling_layersr   Úmodeling_outputsr   r   Úmodeling_rope_utilsr   r   Úmodeling_utilsr   r   Úprocessing_utilsr   Úutilsr   r   Úutils.genericr   r   r   Úutils.output_capturingr   r   Úconfiguration_lagunar!   ÚModuler$   rO   r”   r¢   r¿   rß   rï   rü   rK   rt   r  rJ   r  r  r:  rJ  ra  rD   r”  r–  Ú__all__rE  r4   r3   ú<module>r¾     s†  ðð* %Ð $Ð $Ð $Ð $Ð $Ø Ð Ð Ð Ð Ð à €€€Ø Ð Ð Ð Ð Ð Ð Ð Ð Ø Ð Ð Ð Ð Ð à &Ð &Ð &Ð &Ð &Ð &Ø !Ð !Ð !Ð !Ð !Ð !Ø .Ð .Ð .Ð .Ð .Ð .Ð .Ð .Ø )Ð )Ð )Ð )Ð )Ð )Ø SÐ SÐ SÐ SÐ SÐ SÐ SÐ SØ RÐ RÐ RÐ RÐ RÐ RÐ RÐ RØ BÐ BÐ BÐ BÐ BÐ BØ 9Ð 9Ð 9Ð 9Ð 9Ð 9Ø QÐ QÐ QÐ QÐ QÐ QÐ QÐ QØ KÐ KÐ KÐ KÐ KÐ KÐ KÐ KØ FÐ FÐ FÐ FÐ FÐ FÐ FÐ FØ &Ð &Ð &Ð &Ð &Ð &Ø 5Ð 5Ð 5Ð 5Ð 5Ð 5Ð 5Ð 5Ø [Ð [Ð [Ð [Ð [Ð [Ð [Ð [Ð [Ð [Ø EÐ EÐ EÐ EÐ EÐ EÐ EÐ EØ .Ð .Ð .Ð .Ð .Ð .ð Ð˜YÑ'Ô'ðJð Jð Jð Jð J�B”Iñ Jô Jñ (Ô'ðJð(M<ð M<ð M<ð M<ð M<˜BœIñ M<ô M<ð M<ð`ð ð ð ð �”	ñ ô ð ð @ð @ð @ð @ð @�r”yñ @ô @ð @ð> ð$#ð $#ð $#ð $#ð $#�B”Iñ $#ô $#ñ Ôð$#ðNð ð ð ð ˜2œ9ñ ô ð ð.(ð (ð (ð#ð #ð #ð #ðL	U˜Uœ\ð 	U°#ð 	U¸%¼,ð 	Uð 	Uð 	Uð 	Uð& ð%ð %ØŒIð%àŒ<ð%ð 
Œð%ð Œ<ð	%ð
 ”L 4Ñ'ð%ð ð%ð ð%ð Ð'Ô(ð%ð %ð %ð %ð2U)ð U)ð U)ð U)ð U)�b”iñ U)ô U)ð U)ðp)ð )ð )ð )ð )Ð3ñ )ô )ð )ðX ð$^ð $^ð $^ð $^ð $^˜Oñ $^ô $^ñ „ð$^ðN ðP
ð P
ð P
ð P
ð P
Ð'ñ P
ô P
ñ „ðP
ðj #Ø
Ø*.ð	O&ð O&Ø”  e¤lÔ 3Ñ3°dÑ:ðO&à�t‘ðO&ð ”L 4Ñ'ð	O&ð
 „\�CÑðO&ð O&ð O&ð O&ðd ðS
ð S
ð S
ð S
ð S
Ð-¨ñ S
ô S
ñ „ðS
ðl HÐ
GÐ
G€€€r4   