§
    ‚Štj}w  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mZmZ ddlmZmZ ddlmZ ddlmZmZm Z 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/m0Z0 ddl1m2Z2m3Z3 ddl4m5Z5m6Z6 ddl7m8Z8 e G d„ dej9        ¦  «        ¦   «         Z: G d„ dej9        ¦  «        Z; G d„ dej9        ¦  «        Z< ed¦  «         G d„ dej9        ¦  «        ¦   «         Z= G d „ d!ej9        ¦  «        Z>d"„ Z? ed#¦  «        dHd$„¦   «         Z@d%ejA        d&eBd'ejA        fd(„ZC	 dId*ej9        d+ejA        d,ejA        d-ejA        d.ejA        dz  d/eDd0eDd1e,e.         fd2„ZE ee@¦  «         G d3„ d4ej9        ¦  «        ¦   «         ZF G d5„ d6e!¦  «        ZGe/ G d7„ d8e*¦  «        ¦   «         ZHe/ G d9„ d:eH¦  «        ¦   «         ZI	 	 	 dJd<ejA        eJejA                 z  dz  d=eBdz  d.ejA        dz  d'ejA        eBz  fd>„ZKe/ G d?„ d@eHe¦  «        ¦   «         ZL G dA„ dBeeH¦  «        ZM G dC„ dDe eH¦  «        ZN G dE„ dFeeH¦  «        ZOg dG¢ZPdS )Ké    )ÚCallable)ÚOptionalN)Únné   )Úinitialization)ÚACT2FN)ÚCacheÚDynamicCache)ÚGenerationMixin)Úuse_experts_implementationÚuse_kernel_forward_from_hubÚuse_kernel_func_from_hubÚuse_kernelized_func)Úcreate_causal_maskÚ!create_sliding_window_causal_mask)ÚFlashAttentionKwargs)ÚGenericForQuestionAnsweringÚ GenericForSequenceClassificationÚGenericForTokenClassificationÚGradientCheckpointingLayer)ÚMoeCausalLMOutputWithPastÚMoeModelOutputWithPast)ÚROPE_INIT_FUNCTIONSÚdynamic_rope_update)ÚALL_ATTENTION_FUNCTIONSÚPreTrainedModel)ÚUnpack)ÚTransformersKwargsÚauto_docstringÚcan_return_tuple)Úmaybe_autocastÚmerge_with_config_defaults)ÚOutputRecorderÚcapture_outputsé   )ÚMixtralConfigc                   óh   ‡ — e Zd ZdZdefˆ fd„Zdej        dej        dej        dej        fd„Zˆ xZ	S )	ÚMixtralExpertsz2Collection of expert weights stored as 3D tensors.Úconfigc                 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 )Né   )ÚsuperÚ__init__Únum_local_expertsÚnum_expertsÚhidden_sizeÚ
hidden_dimÚintermediate_sizeÚintermediate_dimr   Ú	ParameterÚtorchÚemptyÚgate_up_projÚ	down_projr   Ú
hidden_actÚact_fn©Úselfr)   Ú	__class__s     €új/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/transformers/models/mixtral/modeling_mixtral.pyr-   zMixtralExperts.__init__A   s£   ø€ Ý‰Œ×ÒÑÔÐØ!Ô3ˆÔØ Ô,ˆŒØ &Ô 8ˆ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ó    Úhidden_statesÚtop_k_indexÚtop_k_weightsÚreturnc                 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_classesr+   r%   r   )éÿÿÿÿéþÿÿÿ©ÚdimrF   )r5   Ú
zeros_likeÚno_gradr   Ú
functionalÚone_hotr/   ÚpermuteÚgreaterÚsumÚnonzeroÚwhereÚlinearr7   Úchunkr:   r8   Ú
index_add_ÚtoÚdtype)r<   r@   rA   rB   Úfinal_hidden_statesÚexpert_maskÚ
expert_hitÚ
expert_idxÚ	top_k_posÚ	token_idxÚcurrent_stateÚgateÚupÚcurrent_hidden_statess                 r>   ÚforwardzMixtralExperts.forwardJ   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)
Ú__name__Ú
__module__Ú__qualname__Ú__doc__r&   r-   r5   ÚTensorrb   Ú__classcell__©r=   s   @r>   r(   r(   =   sŒ   ø€ € € € € à<Ð<ð0˜}ð 0ð 0ð 0ð 0ð 0ð 0ð#à”|ð#ð ”\ð#ð ”|ð	#ð
 
Œð#ð #ð #ð #ð #ð #ð #ð #r?   r(   c                   ó$   ‡ — e Zd Zˆ fd„Zd„ Zˆ xZS )ÚMixtralTopKRouterc                 óü   •— t          ¦   «                              ¦   «          |j        | _        |j        | _        |j        | _        t          j	        t          j        | j        | j        ¦  «        ¦  «        | _        d S ©N)r,   r-   Únum_experts_per_tokÚtop_kr.   r/   r0   r1   r   r4   r5   r6   Úweightr;   s     €r>   r-   zMixtralTopKRouter.__init__f   s^   ø€ Ý‰Œ×ÒÑÔÐØÔ/ˆŒ
Ø!Ô3ˆÔØ Ô,ˆŒÝ”l¥5¤;¨tÔ/?ÀÄÑ#QÔ#QÑRÔRˆŒˆˆr?   c                 ó\  — |                      d| j        ¦  «        }t          j        || j        ¦  «        }t
          j        j                             | 	                    ¦   «         d¬¦  «        }t          j
        || j        d¬¦  «        \  }}||                     dd¬¦  «        z  }|}|||fS )NrF   rH   T)rI   Úkeepdim)Úreshaper1   ÚFrS   rp   r5   r   rL   ÚsoftmaxÚfloatÚtopkro   rP   )r<   r@   Úrouter_logitsÚrouter_probsÚrouter_top_valueÚrouter_indicesÚrouter_scoress          r>   rb   zMixtralTopKRouter.forwardm   s¥   € Ø%×-Ò-¨b°$´/ÑBÔBˆÝœ °´Ñ<Ô<ˆÝ”xÔ*×2Ò2°=×3FÒ3FÑ3HÔ3HÈbÐ2ÑQÔQˆÝ+0¬:°lÀDÄJÐTVÐ+WÑ+WÔ+WÑ(Ð˜.ØÐ,×0Ò0°RÀÐ0ÑFÔFÑFÐØ(ˆØ˜m¨^Ð;Ð;r?   )rc   rd   re   r-   rb   rh   ri   s   @r>   rk   rk   e   sL   ø€ € € € € ðSð Sð Sð Sð Sð<ð <ð <ð <ð <ð <ð <r?   rk   c                   ó\   ‡ — e Zd Zˆ fd„Zdej        deej        ej        f         fd„Zˆ xZS )ÚMixtralSparseMoeBlockc                 óÈ   •— t          ¦   «                              ¦   «          |j        | _        |j        | _        t          |¦  «        | _        t          |¦  «        | _	        d S rm   )
r,   r-   rn   ro   Úrouter_jitter_noiseÚjitter_noiserk   r_   r(   Úexpertsr;   s     €r>   r-   zMixtralSparseMoeBlock.__init__x   sP   ø€ Ý‰Œ×ÒÑÔÐØÔ/ˆŒ
Ø"Ô6ˆÔÝ% fÑ-Ô-ˆŒ	Ý% fÑ-Ô-ˆŒˆˆr?   r@   rC   c                 ó†  — |j         \  }}}| j        rF| j        dk    r;|t          j        |¦  «                             d| j        z
  d| j        z   ¦  «        z  }|                     d|j         d         ¦  «        }|                      |¦  «        \  }}}|                      |||¦  «        }| 	                    |||¦  «        }|S )Nr   ç      ð?rF   )
ÚshapeÚtrainingr�   r5   Ú
empty_likeÚuniform_Úviewr_   r‚   rs   )r<   r@   Ú
batch_sizeÚsequence_lengthr1   Ú_rB   rA   s           r>   rb   zMixtralSparseMoeBlock.forward   sÇ   € Ø2?Ô2EÑ/ˆ
�O ZØŒ=ð 	x˜TÔ.°Ò2Ð2Ø�UÔ-¨mÑ<Ô<×EÒEÀcÈDÔL]ÑF]Ð_bÐeiÔevÑ_vÑwÔwÑwˆMØ%×*Ò*¨2¨}Ô/BÀ2Ô/FÑGÔGˆØ(,¯	ª	°-Ñ(@Ô(@Ñ%ˆˆ=˜+ØŸš ]°KÀÑOÔOˆØ%×-Ò-¨j¸/È:ÑVÔVˆØÐr?   )	rc   rd   re   r-   r5   rg   Útuplerb   rh   ri   s   @r>   r~   r~   w   sj   ø€ € € € € ð.ð .ð .ð .ð .ð U¤\ð °e¸E¼LÈ%Ì,Ð<VÔ6Wð ð ð ð ð ð ð ð r?   r~   Ú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MixtralRMSNormç�íµ ÷Æ°>ÚepsrC   Nc                 ó¬   •— t          ¦   «                              ¦   «          t          j        t	          j        |¦  «        ¦  «        | _        || _        dS )z=
        MixtralRMSNorm is equivalent to T5LayerNorm
        N)r,   r-   r   r4   r5   Úonesrp   Úvariance_epsilon)r<   r0   r’   r=   s      €r>   r-   zMixtralRMSNorm.__init__Œ   sD   ø€ õ 	‰Œ×ÒÑÔÐÝ”l¥5¤:¨kÑ#:Ô#:Ñ;Ô;ˆŒØ #ˆÔÐÐr?   r@   c                 ó  — |j         }|                     t          j        ¦  «        }|                     d¦  «                             dd¬¦  «        }|t          j        || j        z   ¦  «        z  }| j        |                     |¦  «        z  S )Nr+   rF   T)rr   )	rW   rV   r5   Úfloat32ÚpowÚmeanÚrsqrtr•   rp   )r<   r@   Úinput_dtypeÚvariances       r>   rb   zMixtralRMSNorm.forward”   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:r?   c                 óH   — t          | j        j        ¦  «        › d| j        › �S )Nz, eps=)r�   rp   r…   r•   )r<   s    r>   Ú
extra_reprzMixtralRMSNorm.extra_repr›   s&   € Ý˜œÔ)Ñ*Ô*ÐIÐI°$Ô2GÐIÐIÐIr?   )r‘   )
rc   rd   re   rv   r-   r5   rg   rb   rž   rh   ri   s   @r>   r�   r�   Š   sŒ   ø€ € € € € ð$ð $¨ð $¸$ð $ð $ð $ð $ð $ð $ð; U¤\ð ;°e´lð ;ð ;ð ;ð ;ðJð Jð Jð Jð Jð Jð Jr?   r�   c                   óÔ   ‡ — e Zd ZU ej        ed<   ddefˆ fd„Ze	 	 	 ddedz  de	d         de
dz  ded	ef         fd
„¦   «         Z ej        ¦   «         ed„ ¦   «         ¦   «         Zˆ xZS )ÚMixtralRotaryEmbeddingÚinv_freqNr)   c                 ó²  •— t          ¦   «                              ¦   «          |j        | _        |j        | _        || _        | j        j        d         | _        | j        }| j        dk    rt          | j                 } || j        |¦  «        \  }| _
        |                      d|d¬¦  «         |                      d|                     ¦   «         d¬¦  «         d S )NÚ	rope_typeÚdefaultr¡   F)Ú
persistentÚoriginal_inv_freq)r,   r-   Úmax_position_embeddingsÚmax_seq_len_cachedÚoriginal_max_seq_lenr)   Úrope_parametersr£   Úcompute_default_rope_parametersr   Úattention_scalingÚregister_bufferÚclone)r<   r)   ÚdeviceÚrope_init_fnr¡   r=   s        €r>   r-   zMixtralRotaryEmbedding.__init__¢   sÊ   ø€ Ý‰Œ×ÒÑÔÐØ"(Ô"@ˆÔØ$*Ô$BˆÔ!àˆŒàœÔ4°[ÔAˆŒØ!%Ô!EˆØŒ>˜YÒ&Ð&Ý.¨t¬~Ô>ˆLØ+7¨<¸¼ÀVÑ+LÔ+LÑ(ˆ�$Ô(à×Ò˜Z¨¸eÐÑDÔDÐDØ×ÒÐ0°(·.².Ñ2BÔ2BÈuÐÑUÔUÐUÐUÐUr?   r¯   ztorch.deviceÚseq_lenrC   ztorch.Tensorc                 óü   — | j         d         }t          | dd¦  «        p| j        | j        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.
        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head_dimNr„   r   r+   ©rW   )r¯   rW   )	rª   Úgetattrr0   Únum_attention_headsr5   ÚarangeÚint64rV   rv   )r)   r¯   r±   ÚbaserI   Úattention_factorr¡   s          r>   r«   z6MixtralRotaryEmbedding.compute_default_rope_parameters²   sŒ   € ð& Ô% lÔ3ˆÝ�f˜j¨$Ñ/Ô/Ðc°6Ô3EÈÔIcÑ3cˆàÐð Ø•U”\ ! S¨!µ5´;Ð?Ñ?Ô?×BÒBÈ&ÕX]ÔXcÐBÑdÔdÐgjÑjÑkñ
ˆð Ð)Ð)Ð)r?   c                 óN  — | j         d d d …d f                              ¦   «                              |j        d         dd¦  «                             |j        ¦  «        }|d d …d d d …f                              ¦   «         }t          |j        j        t          ¦  «        r|j        j        dk    r|j        j        nd}t          |d¬¦  «        5  |                     ¦   «         |                     ¦   «         z   
                    dd¦  «        }t          j        ||fd¬	¦  «        }|                     ¦   «         | j        z  }|                     ¦   «         | j        z  }	d d d ¦  «         n# 1 swxY w Y   |                     |j        ¬
¦  «        |	                     |j        ¬
¦  «        fS )Nr   rF   r%   ÚmpsÚcpuF)Údevice_typeÚenabledr+   rH   rµ   )r¡   rv   Úexpandr…   rV   r¯   Ú
isinstanceÚtypeÚstrr!   Ú	transposer5   ÚcatÚcosr¬   ÚsinrW   )
r<   ÚxÚposition_idsÚinv_freq_expandedÚposition_ids_expandedr¿   ÚfreqsÚembrÇ   rÈ   s
             r>   rb   zMixtralRotaryEmbedding.forwardÐ   s·  € ð !œM¨$°°°°4¨-Ô8×>Ò>Ñ@Ô@×GÒGÈÔHZÐ[\ÔH]Ð_aÐcdÑeÔe×hÒhÐijÔiqÑrÔrÐ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 	5ð 	5Ø&×,Ò,Ñ.Ô.Ð1F×1LÒ1LÑ1NÔ1NÑN×YÒYÐZ[Ð]^Ñ_Ô_ˆEÝ”)˜U E˜N°Ð3Ñ3Ô3ˆCØ—'’'‘)”)˜dÔ4Ñ4ˆCØ—'’'‘)”)˜dÔ4Ñ4ˆCð		5ð 	5ð 	5ñ 	5ô 	5ð 	5ð 	5ð 	5ð 	5ð 	5ð 	5øøøð 	5ð 	5ð 	5ð 	5ð �vŠv˜AœGˆvÑ$Ô$ c§f¢f°1´7 fÑ&;Ô&;Ð;Ð;s   ÃBE&Å&E*Å-E*rm   )NNN)rc   rd   re   r5   rg   Ú__annotations__r&   r-   Ústaticmethodr   Úintr�   rv   r«   rK   r   rb   rh   ri   s   @r>   r    r    Ÿ   sù   ø€ € € € € € ØŒlÐÐÑðVð V˜}ð Vð Vð Vð Vð Vð Vð  à'+Ø+/Ø"ð*ð *Ø Ñ$ð*à˜Ô(ð*ð �t‘ð*ð 
ˆ~˜uÐ$Ô	%ð	*ð *ð *ñ „\ð*ð: €U„]�_„_Øð<ð <ñ Ôñ „_ð<ð <ð <ð <ð <r?   r    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..NrF   r+   rH   )r…   r5   rÆ   )rÉ   Úx1Úx2s      r>   Úrotate_halfrÕ   à   s]   € à	
ˆ3Ð"�!”'˜"”+ Ñ"Ð"Ð"Ô	#€BØ	
ˆ3�”˜”˜qÑ Ð"Ð"Ð"Ô	#€BÝŒ9�r�c˜2�Y BÐ'Ñ'Ô'Ð'r?   Úrotary_pos_embc                 ó¾   — |                      |¦  «        }|                      |¦  «        }| |z  t          | ¦  «        |z  z   }||z  t          |¦  «        |z  z   }||fS )a…  Applies Rotary Position Embedding to the query and key tensors.

    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.
    )Ú	unsqueezerÕ   )ÚqÚkrÇ   rÈ   Úunsqueeze_dimÚq_embedÚk_embeds          r>   Úapply_rotary_pos_embrÞ   ç   sc   € ð& �-Š-˜Ñ
&Ô
&€CØ
�-Š-˜Ñ
&Ô
&€CØ�3‰w�; q™>œ>¨CÑ/Ñ0€GØ�3‰w�; q™>œ>¨CÑ/Ñ0€GØ�GÐÐr?   r@   Ún_reprC   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)r…   rÁ   rs   )r@   rß   ÚbatchÚnum_key_value_headsÚslenr´   s         r>   Ú	repeat_kvrä     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Tr?   ç        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 )Nr+   r   rF   )rI   rW   )Úpr†   r%   )rä   Únum_key_value_groupsr5   ÚmatmulrÅ   r   rL   ru   r—   rV   rW   rì   r†   Ú
contiguous)ræ   rç   rè   ré   rê   rë   rì   rí   Ú
key_statesÚvalue_statesÚattn_weightsÚattn_outputs               r>   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$Ð$r?   c                   óÊ   ‡ — e Zd ZdZ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MixtralAttentionz=Multi-headed attention from 'Attention Is All You Need' paperr)   Ú	layer_idxc                 óŠ  •— t          ¦   «                              ¦   «          || _        || _        t	          |dd ¦  «        p|j        |j        z  | _        |j        |j        z  | _	        | j        dz  | _
        |j        | _        d| _        t          j        |j        |j        | j        z  d¬¦  «        | _        t          j        |j        |j        | j        z  d¬¦  «        | _        t          j        |j        |j        | j        z  d¬¦  «        | _        t          j        |j        | j        z  |j        d¬¦  «        | _        d S )Nr´   g      à¿TF©Úbias)r,   r-   r)   rú   r¶   r0   r·   r´   râ   rð   rë   Úattention_dropoutÚ	is_causalr   ÚLinearÚq_projÚk_projÚv_projÚo_proj©r<   r)   rú   r=   s      €r>   r-   zMixtralAttention.__init__*  s   ø€ Ý‰Œ×ÒÑÔÐØˆŒØ"ˆŒÝ ¨
°DÑ9Ô9Ðm¸VÔ=OÐSYÔSmÑ=mˆŒØ$*Ô$>À&ÔB\Ñ$\ˆÔ!Ø”} dÑ*ˆŒØ!'Ô!9ˆÔØˆŒÝ”i Ô 2°FÔ4NÐQUÔQ^Ñ4^ÐejÐkÑkÔkˆŒÝ”i Ô 2°FÔ4NÐQUÔQ^Ñ4^ÐejÐkÑkÔkˆŒÝ”i Ô 2°FÔ4NÐQUÔQ^Ñ4^ÐejÐkÑkÔkˆŒÝ”i Ô :¸T¼]Ñ JÈFÔL^ÐejÐkÑkÔkˆŒˆˆr?   Nr@   Úposition_embeddingsrê   Úpast_key_valuesrí   rC   c           
      óL  — |j         d d…         }g |¢d‘| j        ‘R }|                      |¦  «                             |¦  «                             dd¦  «        }|                      |¦  «                             |¦  «                             dd¦  «        }	|                      |¦  «                             |¦  «                             dd¦  «        }
|\  }}t          ||	||¦  «        \  }}	|�|                     |	|
| j	        ¦  «        \  }	}
t          j        | j        j        t          ¦  «        } || ||	|
|f| j        sdn| j        | j        t%          | j        dd ¦  «        dœ|¤Ž\  }} |j        g |¢d‘R Ž                      ¦   «         }|                      |¦  «        }||fS )NrF   r%   r+   rå   Úsliding_window)rì   rë   r	  )r…   r´   r  r‰   rÅ   r  r  rÞ   Úupdaterú   r   Úget_interfacer)   Ú_attn_implementationr÷   r†   rþ   rë   r¶   rs   rò   r  )r<   r@   r  rê   r  rí   Úinput_shapeÚhidden_shapeÚquery_statesró   rô   rÇ   rÈ   Úattention_interfacerö   rõ   s                   r>   rb   zMixtralAttention.forward8  sÒ  € ð $Ô)¨#¨2¨#Ô.ˆØ8˜Ð8 bÐ8¨$¬-Ð8Ð8ˆà—{’{ =Ñ1Ô1×6Ò6°|ÑDÔD×NÒNÈqÐRSÑTÔTˆØ—[’[ Ñ/Ô/×4Ò4°\ÑBÔB×LÒLÈQÐPQÑRÔRˆ
Ø—{’{ =Ñ1Ô1×6Ò6°|ÑDÔD×NÒNÈqÐRSÑTÔTˆ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”LÝ" 4¤;Ð0@À$ÑGÔGð
%
ð 
%
ð ð
%
ð 
%
Ñ!ˆ�\ð *�kÔ)Ð;¨;Ð;¸Ð;Ð;Ð;×FÒFÑHÔHˆØ—k’k +Ñ.Ô.ˆØ˜LÐ(Ð(r?   rm   )rc   rd   re   rf   r&   rÑ   r-   r5   rg   r�   r	   r   r   rb   rh   ri   s   @r>   rù   rù   &  så   ø€ € € € € àGÐGðl˜}ð l¸ð lð lð lð lð lð lð& )-ð')ð ')à”|ð')ð # 5¤<°´Ð#=Ô>ð')ð œ tÑ+ð	')ð
  ™ð')ð Ð-Ô.ð')ð 
ˆuŒ|˜Uœ\¨DÑ0Ð0Ô	1ð')ð ')ð ')ð ')ð ')ð ')ð ')ð ')r?   rù   c                   óÆ   ‡ — e Zd Zdedefˆ fd„Z	 	 	 	 ddej        deej        ej        f         dz  dej        dz  dej	        dz  d	e
dz  d
ee         dej        fd„Zˆ xZS )ÚMixtralDecoderLayerr)   rú   c                 ó2  •— t          ¦   «                              ¦   «          |j        | _        t          ||¦  «        | _        t          |¦  «        | _        t          |j        |j        ¬¦  «        | _	        t          |j        |j        ¬¦  «        | _
        d S )N©r’   )r,   r-   r0   rù   Ú	self_attnr~   Úmlpr�   Úrms_norm_epsÚinput_layernormÚpost_attention_layernormr  s      €r>   r-   zMixtralDecoderLayer.__init__c  s€   ø€ Ý‰Œ×ÒÑÔÐØ!Ô-ˆÔå)¨&°)Ñ<Ô<ˆŒå(¨Ñ0Ô0ˆŒÝ-¨fÔ.@ÀfÔFYÐZÑZÔZˆÔÝ(6°vÔ7IÈvÔObÐ(cÑ(cÔ(cˆÔ%Ð%Ð%r?   Nr@   r  rê   rÊ   r  rí   rC   c           	      óÌ   — |}|                       |¦  «        } | j        d|||||dœ|¤Ž\  }}||z   }|}|                      |¦  «        }|                      |¦  «        }||z   }|S )N)r@   r  rê   rÊ   r  © )r  r  r  r  )	r<   r@   r  rê   rÊ   r  rí   ÚresidualrŒ   s	            r>   rb   zMixtralDecoderLayer.forwardm  sœ   € ð !ˆØ×,Ò,¨]Ñ;Ô;ˆØ)˜4œ>ð 
Ø'Ø 3Ø)Ø%Ø+ð
ð 
ð ð
ð 
Ñˆ�qð ! =Ñ0ˆØ ˆØ×5Ò5°mÑDÔDˆØŸš Ñ/Ô/ˆØ  =Ñ0ˆØÐr?   )NNNN)rc   rd   re   r&   rÑ   r-   r5   rg   r�   Ú
LongTensorr	   r   r   rb   rh   ri   s   @r>   r  r  b  sð   ø€ € € € € ðd˜}ð d¸ð dð dð dð dð dð dð IMØ.2Ø04Ø(,ðð à”|ðð # 5¤<°´Ð#=Ô>ÀÑEðð œ tÑ+ð	ð
 Ô&¨Ñ-ðð  ™ðð Ð+Ô,ðð 
Œðð ð ð ð ð ð ð r?   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MixtralPreTrainedModelr)   ÚmodelTr  r  r   )Úindex)rx   r@   Ú
attentionsc                 óf  •— t          ¦   «                              |¦  «         | j        j        }t	          |t
          ¦  «        r:t          j        |j        d|¬¦  «         t          j        |j	        d|¬¦  «         d S t	          |t          ¦  «        rt          j        |j        d|¬¦  «         d S d S )Nrå   )r™   Ústd)r,   Ú_init_weightsr)   Úinitializer_rangerÂ   r(   ÚinitÚnormal_r7   r8   rk   rp   )r<   ræ   r$  r=   s      €r>   r%  z$MixtralPreTrainedModel._init_weights›  s­   ø€ å‰Œ×Ò˜fÑ%Ô%Ð%ØŒkÔ+ˆÝ�f�nÑ-Ô-ð 	;ÝŒL˜Ô,°3¸CÐ@Ñ@Ô@Ð@ÝŒL˜Ô)°¸Ð=Ñ=Ô=Ð=Ð=Ð=Ý˜Õ 1Ñ2Ô2ð 	;ÝŒL˜œ¨S°cÐ:Ñ:Ô:Ð:Ð:Ð:ð	;ð 	;r?   )rc   rd   re   r&   rÏ   Úbase_model_prefixÚsupports_gradient_checkpointingÚ_no_split_modulesÚ_skip_keys_device_placementÚ_supports_flash_attnÚ_supports_sdpaÚ_supports_flex_attnÚ_can_compile_fullgraphÚ_supports_attention_backendr#   rk   r  rù   Ú_can_record_outputsr5   rK   r%  rh   ri   s   @r>   r  r  ˆ  s»   ø€ € € € € € àÐÐÑØÐØ&*Ð#Ø.Ð/ÐØ#4Ð"5ÐØÐØ€NØÐà!ÐØ"&Ðà'˜Ð(9ÀÐCÑCÔCØ,Ø&ðð Ðð €U„]�_„_ð;ð ;ð ;ð ;ñ „_ð;ð ;ð ;ð ;ð ;r?   r  c                   óâ   ‡ — e Zd Zdefˆ fd„Zeee	 	 	 	 	 	 ddej	        dz  dej
        dz  dej	        dz  dedz  dej        dz  d	edz  d
ee         defd„¦   «         ¦   «         ¦   «         Zˆ xZS )ÚMixtralModelr)   c                 óÞ  •‡— t          ¦   «                              ‰¦  «         ‰j        | _        ‰j        | _        t          j        ‰j        ‰j        | j        ¦  «        | _        t          j	        ˆfd„t          ‰j        ¦  «        D ¦   «         ¦  «        | _        t          ‰j        ‰j        ¬¦  «        | _        t!          ‰¬¦  «        | _        d| _        |                      ¦   «          d S )Nc                 ó0   •— g | ]}t          ‰|¦  «        ‘ŒS r  )r  )Ú.0rú   r)   s     €r>   ú
<listcomp>z)MixtralModel.__init__.<locals>.<listcomp>¯  s$   ø€ ÐeÐeÐe¸	Õ  ¨Ñ3Ô3ÐeÐeÐer?   r  ©r)   F)r,   r-   Úpad_token_idÚpadding_idxÚ
vocab_sizer   Ú	Embeddingr0   Úembed_tokensÚ
ModuleListÚrangeÚnum_hidden_layersÚlayersr�   r  Únormr    Ú
rotary_embÚgradient_checkpointingÚ	post_initr;   s    `€r>   r-   zMixtralModel.__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eÐeÐeÐeÅUÈ6ÔKcÑEdÔEdÐeÑeÔeñ
ô 
ˆŒõ # 6Ô#5¸6Ô;NÐOÑOÔOˆŒ	Ý0¸Ð?Ñ?Ô?ˆŒØ&+ˆÔ#ð 	�ŠÑÔÐÐÐr?   NÚ	input_idsrê   rÊ   r  Úinputs_embedsÚ	use_cacherí   rC   c           
      ót  — |d u |d uz  rt          d¦  «        ‚|r|€t          | j        ¬¦  «        }|€|                      |¦  «        }|€V|�|                     ¦   «         nd}t          j        |j        d         |j        ¬¦  «        |z   }| 	                    d¦  «        }| j        j
        €t          nt          }	 |	| j        ||||¬¦  «        }
|}|                      ||¬¦  «        }| j        d | j        j        …         D ]} ||f|
||||dœ|¤Ž}Œ|                      |¦  «        }t#          ||¬	¦  «        S )
Nz:You must specify exactly one of input_ids or inputs_embedsr9  r   r%   )r¯   )r)   rH  rê   r  rÊ   )rÊ   )rê   rÊ   r  rI  r  )Úlast_hidden_stater  )Ú
ValueErrorr
   r)   r>  Úget_seq_lengthr5   r¸   r…   r¯   rØ   r	  r   r   rD  rB  rA  rC  r   )r<   rG  rê   rÊ   r  rH  rI  rí   Úpast_seen_tokensÚmask_functionÚcausal_maskr@   r  Údecoder_layers                 r>   rb   zMixtralModel.forward¸  s¢  € ð ˜Ð -°tÐ";Ñ<ð 	[ÝÐYÑZÔZÐZàð 	?˜Ð0Ý*°$´+Ð>Ñ>Ô>ˆOàÐ Ø ×-Ò-¨iÑ8Ô8ˆMàÐØCRÐC^˜×=Ò=Ñ?Ô?Ð?ÐdeÐÝ œ<¨Ô(;¸AÔ(>À}ÔG[Ð\Ñ\Ô\Ð_oÑoˆLØ'×1Ò1°!Ñ4Ô4ˆLà.2¬kÔ.HÐ.PÕ*Ð*ÕVwˆØ#�mØ”;Ø'Ø)Ø+Ø%ð
ñ 
ô 
ˆð &ˆØ"Ÿošo¨mÈ,˜oÑWÔWÐà!œ[Ð)H¨4¬;Ô+HÐ)HÔIð 		ð 		ˆMØ)˜MØðà*Ø)Ø /Ø#Ø$7ðð ð ðð ˆMˆMð Ÿ	š	 -Ñ0Ô0ˆå%Ø+Ø+ð
ñ 
ô 
ð 	
r?   )NNNNNN)rc   rd   re   r&   r-   r"   r$   r   r5   r  rg   r	   ÚFloatTensorÚboolr   r   r   rb   rh   ri   s   @r>   r4  r4  ¦  s  ø€ € € € € ð˜}ð ð ð ð ð ð ð   ØØð .2Ø.2Ø04Ø(,Ø26Ø!%ð4
ð 4
àÔ# dÑ*ð4
ð œ tÑ+ð4
ð Ô&¨Ñ-ð	4
ð
  ™ð4
ð Ô(¨4Ñ/ð4
ð ˜$‘;ð4
ð Ð+Ô,ð4
ð 
 ð4
ð 4
ð 4
ñ „^ñ „_ñ  Ôð4
ð 4
ð 4
ð 4
ð 4
r?   r4  r+   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 r  )rV   )r7  Ú
layer_gateÚcompute_devices     €r>   r8  z,load_balancing_loss_func.<locals>.<listcomp>  s&   ø€ Ð-jÐ-jÐ-jÐPZ¨j¯mªm¸NÑ.KÔ.KÐ-jÐ-jÐ-jr?   rH   rF   )rÂ   r�   r¯   r5   rÆ   r   rL   ru   rw   rM   r™   rv   r…   rÁ   rs   rV   rP   rØ   )rT  r/   ro   rê   Úconcatenated_gate_logitsÚrouting_weightsrŒ   Úselected_expertsrY   Útokens_per_expertÚrouter_prob_per_expertrŠ   r‹   rA  Úexpert_attention_maskÚ router_per_expert_attention_maskÚoverall_lossrX  s                    @r>   Úload_balancing_loss_funcra  ò  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%r?   c                   ó$  ‡ — e Zd ZddiZddiZddgdgfiZˆ fd„Zee	 	 	 	 	 	 	 	 	 dd
e	j
        dz  de	j        dz  de	j
        dz  dedz  de	j        dz  de	j
        dz  dedz  dedz  dee	j        z  dee         defd„¦   «         ¦   «         Zˆ xZS )ÚMixtralForCausalLMzlm_head.weightzmodel.embed_tokens.weightÚlm_headÚcolwise_gather_outputr@   Úlogitsc                 óF  •— t          ¦   «                              |¦  «         t          |¦  «        | _        |j        | _        t          j        |j        |j        d¬¦  «        | _        |j	        | _	        |j
        | _        |j        | _        |                      ¦   «          d S )NFrü   )r,   r-   r4  r   r<  r   r   r0   rd  Úrouter_aux_loss_coefr.   r/   rn   rF  r;   s     €r>   r-   zMixtralForCausalLM.__init__J  s‹   ø€ Ý‰Œ×Ò˜Ñ Ô Ð Ý! &Ñ)Ô)ˆŒ
Ø Ô+ˆŒÝ”y Ô!3°VÔ5FÈUÐSÑSÔSˆŒØ$*Ô$?ˆÔ!Ø!Ô3ˆÔØ#)Ô#=ˆÔ ð 	�ŠÑÔÐÐÐr?   Nr   rG  rê   rÊ   r  rH  ÚlabelsrI  Úoutput_router_logitsÚlogits_to_keeprí   rC   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]`.

        Example:

        ```python
        >>> from transformers import AutoTokenizer, MixtralForCausalLM

        >>> model = MixtralForCausalLM.from_pretrained("mistralai/Mixtral-8x7B-v0.1")
        >>> tokenizer = AutoTokenizer.from_pretrained("mistralai/Mixtral-8x7B-v0.1")

        >>> prompt = "Hey, are you conscious? Can you talk to me?"
        >>> inputs = tokenizer(prompt, return_tensors="pt")

        >>> # Generate
        >>> generate_ids = model.generate(inputs.input_ids, max_length=30)
        >>> tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
        "Hey, are you conscious? Can you talk to me?\nI'm not conscious, but I can talk to you."
        ```N)rG  rê   rÊ   r  rH  rI  rj  )ÚlossÚaux_lossrf  r  r@   r"  rx   r  )r)   rj  r   rK  rÂ   rÑ   Úslicerd  Úloss_functionr<  ra  rx   r/   rn   rh  rV   r¯   r   r  r@   r"  )r<   rG  rê   rÊ   r  rH  ri  rI  rj  rk  rí   Úoutputsr@   Úslice_indicesrf  rm  rn  s                    r>   rb   zMixtralForCausalLM.forwardV  sn  € ðN %9Ð$DÐ Ð È$Ì+ÔJjð 	ð
 +5¨$¬*ð 	+
ØØ)Ø%Ø+Ø'ØØ!5ð	+
ð 	+
ð ð	+
ð 	+
ˆð  Ô1ˆå8BÀ>ÕSVÑ8WÔ8WÐk�˜~˜o¨tÑ4Ô4Ð4Ð]kˆØ—’˜m¨A¨A¨A¨}¸a¸a¸aÐ,?Ô@ÑAÔAˆàˆØÐØ%�4Ô% f¨f°d´oÐPÐPÈÐPÐPˆDàˆØð 	MÝ/ØÔ%ØÔ ØÔ(Øñ	ô ˆHð Ð!Ø˜Ô1°H·K²KÀÄÑ4LÔ4LÑLÑL�å(ØØØØ#Ô3Ø!Ô/ØÔ)Ø!Ô/ð
ñ 
ô 
ð 	
r?   )	NNNNNNNNr   )rc   rd   re   Ú_tied_weights_keysÚ_tp_planÚ_pp_planr-   r    r   r5   r  rg   r	   rR  rS  rÑ   r   r   r   rb   rh   ri   s   @r>   rc  rc  D  sp  ø€ € € € € à*Ð,GÐHÐØÐ2Ð3€HØ˜_Ð-°¨zÐ:Ð;€Hð
ð 
ð 
ð 
ð 
ð Øð .2Ø.2Ø04Ø(,Ø26Ø*.Ø!%Ø,0Ø-.ðP
ð P
àÔ# dÑ*ðP
ð œ tÑ+ðP
ð Ô&¨Ñ-ð	P
ð
  ™ðP
ð Ô(¨4Ñ/ðP
ð Ô  4Ñ'ðP
ð ˜$‘;ðP
ð # T™kðP
ð ˜eœlÑ*ðP
ð Ð+Ô,ðP
ð 
#ðP
ð P
ð P
ñ „^ñ ÔðP
ð P
ð P
ð P
ð P
r?   rc  c                   ó   — e Zd ZdS )Ú MixtralForSequenceClassificationN©rc   rd   re   r  r?   r>   rw  rw  «  ó   € € € € € Ø€Dr?   rw  c                   ó   — e Zd ZdS )ÚMixtralForTokenClassificationNrx  r  r?   r>   r{  r{  ¯  ry  r?   r{  c                   ó   — e Zd ZdS )ÚMixtralForQuestionAnsweringNrx  r  r?   r>   r}  r}  ³  ry  r?   r}  )rc  r}  r4  r  rw  r{  )r%   )rå   )Nr+   N)QÚcollections.abcr   Útypingr   r5   Útorch.nn.functionalr   rL   rt   Ú r   r'  Úactivationsr   Úcache_utilsr	   r
   Ú
generationr   Úintegrationsr   r   r   r   Úmasking_utilsr   r   Úmodeling_flash_attention_utilsr   Úmodeling_layersr   r   r   r   Úmodeling_outputsr   r   Úmodeling_rope_utilsr   r   Úmodeling_utilsr   r   Úprocessing_utilsr   Úutilsr   r   r    Úutils.genericr!   r"   Úutils.output_capturingr#   r$   Úconfiguration_mixtralr&   ÚModuler(   rk   r~   r�   r    rÕ   rÞ   rg   rÑ   rä   rv   r÷   rù   r  r  r4  r�   ra  rc  rw  r{  r}  Ú__all__r  r?   r>   ú<module>r“     sK  ðð4 %Ð $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 )ðð ð ð ð ð ð ð ð ð ð ð ð SÐ RÐ RÐ RÐ RÐ RÐ RÐ RØ BÐ BÐ BÐ BÐ BÐ Bðð ð ð ð ð ð ð ð ð ð ð ð RÐ 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 IÐ IÐ IÐ IÐ IÐ IÐ IÐ IÐ IÐ IØ GÐ GÐ GÐ GÐ GÐ GÐ GÐ GØ EÐ EÐ EÐ EÐ EÐ EÐ EÐ EØ 0Ð 0Ð 0Ð 0Ð 0Ð 0ð ð$#ð $#ð $#ð $#ð $#�R”Yñ $#ô $#ñ Ôð$#ðN<ð <ð <ð <ð <˜œ	ñ <ô <ð <ð$ð ð ð ð ˜BœIñ ô ð ð& Ð˜YÑ'Ô'ðJð Jð Jð Jð J�R”Yñ Jô Jñ (Ô'ðJð(><ð ><ð ><ð ><ð ><˜RœYñ ><ô ><ð ><ðB(ð (ð (ð ÐÐ*Ñ+Ô+ðð ð ñ ,Ô+ðð2	U˜Uœ\ð 	U°#ð 	U¸%¼,ð 	Uð 	Uð 	Uð 	Uð& ð%ð %ØŒIð%àŒ<ð%ð 
Œð%ð Œ<ð	%ð
 ”L 4Ñ'ð%ð ð%ð ð%ð Ð'Ô(ð%ð %ð %ð %ð2 ÐÐ)Ñ*Ô*ð8)ð 8)ð 8)ð 8)ð 8)�r”yñ 8)ô 8)ñ +Ô*ð8)ðv#ð #ð #ð #ð #Ð4ñ #ô #ð #ðL ð;ð ;ð ;ð ;ð ;˜_ñ ;ô ;ñ „ð;ð: ðH
ð H
ð H
ð H
ð H
Ð)ñ H
ô H
ñ „ðH
ðZ #Ø
Ø*.ð	O&ð O&Ø”  e¤lÔ 3Ñ3°dÑ:ðO&à�t‘ðO&ð ”L 4Ñ'ð	O&ð
 „\�CÑðO&ð O&ð O&ð O&ðd ðc
ð c
ð c
ð c
ð c
Ð/°ñ c
ô c
ñ „ðc
ðL	ð 	ð 	ð 	ð 	Ð'GÐI_ñ 	ô 	ð 	ð	ð 	ð 	ð 	ð 	Ð$AÐCYñ 	ô 	ð 	ð	ð 	ð 	ð 	ð 	Ð"=Ð?Uñ 	ô 	ð 	ðð ð €€€r?   