§
    9²¸jÙu  ã                   ó²  — 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 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,m-Z- ddl.m/Z/ ddl0m1Z1m2Z2 ddl3m4Z4m5Z5 ddl6m7Z7 e G d„ dej8        ¦  «        ¦   «         Z9 G d„ dej8        ¦  «        Z: G d„ dej8        ¦  «        Z; ed¦  «         G d„ dej8        ¦  «        ¦   «         Z< G d „ d!ej8        ¦  «        Z=d"„ Z> ed#¦  «        dHd$„¦   «         Z?d%ej@        d&eAd'ej@        fd(„ZB	 dId*ej8        d+ej@        d,ej@        d-ej@        d.ej@        dz  d/eCd0eCd1e)e+         fd2„ZD ee?¦  «         G d3„ d4ej8        ¦  «        ¦   «         ZE G d5„ d6e¦  «        ZFe, G d7„ d8e'¦  «        ¦   «         ZGe, G d9„ d:eG¦  «        ¦   «         ZH	 	 	 dJd<ej@        eIej@                 z  dz  d=eAdz  d.ej@        dz  d'ej@        eAz  fd>„ZJe, G d?„ d@eGe¦  «        ¦   «         ZK G dA„ dBeeG¦  «        ZL G dC„ dDeeG¦  «        ZM G dE„ dFeeG¦  «        ZNg dG¢ZOdS )Ké    )ÚCallableN)Únné   )Úinitialization)ÚACT2FN)ÚCacheÚDynamicCache)ÚGenerationMixin)Úuse_experts_implementationÚuse_kernel_forward_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deprecate_kwarg)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     €ú|/root/private/project/pallet_detection_v2/.venv/lib/python3.11/site-packages/transformers/models/mixtral/modeling_mixtral.pyr,   zMixtralExperts.__init__<   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dimrE   )r4   Ú
zeros_likeÚno_gradr   Ú
functionalÚone_hotr.   ÚpermuteÚgreaterÚsumÚnonzeroÚwhereÚlinearr6   Úchunkr9   r7   Ú
index_add_ÚtoÚdtype)r;   r?   r@   rA   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.forwardE   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,   r4   ÚTensorra   Ú__classcell__©r<   s   @r=   r'   r'   8   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$   ‡ — e Zd Zˆ fd„Zd„ Zˆ xZS )ÚMixtralTopKRouterc                 óü   •— t          ¦   «                              ¦   «          |j        | _        |j        | _        |j        | _        t          j	        t          j        | j        | j        ¦  «        ¦  «        | _        d S ©N)r+   r,   Únum_experts_per_tokÚtop_kr-   r.   r/   r0   r   r3   r4   r5   Úweightr:   s     €r=   r,   zMixtralTopKRouter.__init__a   s^   ø€ Ý‰Œ×ÒÑÔÐØÔ/ˆŒ
Ø!Ô3ˆÔØ Ô,ˆŒÝ”l¥5¤;¨tÔ/?ÀÄÑ#QÔ#QÑRÔRˆŒˆˆr>   c                 ó\  — |                      d| j        ¦  «        }t          j        || j        ¦  «        }t
          j        j                             | 	                    ¦   «         d¬¦  «        }t          j
        || j        d¬¦  «        \  }}||                     dd¬¦  «        z  }|}|||fS )NrE   rG   T)rH   Úkeepdim)Úreshaper0   ÚFrR   ro   r4   r   rK   ÚsoftmaxÚfloatÚtopkrn   rO   )r;   r?   Úrouter_logitsÚrouter_probsÚrouter_top_valueÚrouter_indicesÚrouter_scoress          r=   ra   zMixtralTopKRouter.forwardh   s¥   € Ø%×-Ò-¨b°$´/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>   )rb   rc   rd   r,   ra   rg   rh   s   @r=   rj   rj   `   sL   ø€ € € € € ðSð Sð Sð Sð Sð<ð <ð <ð <ð <ð <ð <r>   rj   c                   óB   ‡ — e Zd Zˆ fd„Zdej        dej        fd„Zˆ xZS )ÚMixtralSparseMoeBlockc                 óÈ   •— t          ¦   «                              ¦   «          |j        | _        |j        | _        t          |¦  «        | _        t          |¦  «        | _	        d S rl   )
r+   r,   rm   rn   Úrouter_jitter_noiseÚjitter_noiserj   r^   r'   Úexpertsr:   s     €r=   r,   zMixtralSparseMoeBlock.__init__s   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?   rB   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?rE   )
ÚshapeÚtrainingr€   r4   Ú
empty_likeÚuniform_Úviewr^   r�   rr   )r;   r?   Ú
batch_sizeÚsequence_lengthr0   Ú_rA   r@   s           r=   ra   zMixtralSparseMoeBlock.forwardz   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>   )rb   rc   rd   r,   r4   rf   ra   rg   rh   s   @r=   r}   r}   r   s^   ø€ € € € € ð.ð .ð .ð .ð .ð U¤\ð °e´lð 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epsrB   Nc                 ó¬   •— t          ¦   «                              ¦   «          t          j        t	          j        |¦  «        ¦  «        | _        || _        dS )z=
        MixtralRMSNorm is equivalent to T5LayerNorm
        N)r+   r,   r   r3   r4   Úonesro   Úvariance_epsilon)r;   r/   r�   r<   s      €r=   r,   zMixtralRMSNorm.__init__‡   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*   rE   T)rq   )	rV   rU   r4   Úfloat32ÚpowÚmeanÚrsqrtr“   ro   )r;   r?   Úinput_dtypeÚvariances       r=   ra   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=)Útuplero   r„   r“   )r;   s    r=   Ú
extra_reprzMixtralRMSNorm.extra_repr–   s&   € Ý˜œÔ)Ñ*Ô*ÐIÐI°$Ô2GÐIÐIÐIr>   )r�   )
rb   rc   rd   ru   r,   r4   rf   ra   r�   rg   rh   s   @r=   rŽ   rŽ   …   sŒ   ø€ € € € € ð$ð $¨ð $¸$ð $ð $ð $ð $ð $ð $ð; U¤\ð ;°e´lð ;ð ;ð ;ð ;ðJð Jð Jð Jð Jð Jð Jr>   rŽ   c            	       óî   ‡ — e Zd Z edd¬¦  «        d
defˆ fd„¦   «         Ze edd¬¦  «        d
dedeej	        e
f         fd„¦   «         ¦   «         Z ej        ¦   «         ed	„ ¦   «         ¦   «         Zˆ xZS )ÚMixtralRotaryEmbeddingÚdevicez5.18)ÚversionNr(   c                 ó¾  •— t          ¦   «                              ¦   «          |j        | _        |j        | _        || _        | j        j        d         | _        | j        }| j        dk    rt          | j                 } || j        |¦  «        \  }| _
        t          j        |d¬¦  «        | _        t          j        |                     ¦   «         d¬¦  «        | _        d S )NÚ	rope_typeÚdefaultF)Ú
persistent)r+   r,   Úmax_position_embeddingsÚmax_seq_len_cachedÚoriginal_max_seq_lenr(   Úrope_parametersr£   Úcompute_default_rope_parametersr   Úattention_scalingr   ÚBufferÚinv_freqÚcloneÚoriginal_inv_freq)r;   r(   r    Úrope_init_fnr­   r<   s        €r=   r,   zMixtralRotaryEmbedding.__init__›   sÀ   ø€ å‰Œ×ÒÑÔÐØ"(Ô"@ˆÔØ$*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(åœ	 (°uÐ=Ñ=Ô=ˆŒÝ!#¤¨8¯>ª>Ñ+;Ô+;ÈÐ!NÑ!NÔ!NˆÔÐÐr>   rB   c                 óä   — | j         d         }t          | dd¦  «        p| j        | j        z  }d}d|t	          j        d|dt          j        ¬¦  «        |z  z  z  }|                     |¦  «        |fS )a¾  
        Computes the inverse frequencies according to the original RoPE implementation
        Args:
            config ([`~transformers.PreTrainedConfig`]):
                The model configuration.
        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_dimNrƒ   r   r*   ©rV   )r©   Úgetattrr/   Únum_attention_headsr4   Úarangeru   rU   )r(   r    ÚkwargsÚbaserH   Úattention_factorr­   s          r=   rª   z6MixtralRotaryEmbedding.compute_default_rope_parameters¬   sz   € ð Ô% lÔ3ˆÝ�f˜j¨$Ñ/Ô/Ðc°6Ô3EÈÔIcÑ3cˆàÐà˜$¥5¤<°°3¸ÅÄÐ#MÑ#MÔ#MÐPSÑ#SÑTÑUˆØ�{Š{˜6Ñ"Ô"Ð$4Ð4Ð4r>   c                 óú  — | j         d d d …d f                              |j        d         dd¦  «                             t          j        |j        ¬¦  «        }|d d …d d d …f                              ¦   «         }t          |j        j        t          ¦  «        r|j        j        dk    r|j        j        nd}t          |d¬¦  «        5  ||z                       dd	¦  «        }t	          j        ||fd¬
¦  «        }|                     ¦   «         | j        z  }|                     ¦   «         | j        z  }	d d d ¦  «         n# 1 swxY w Y   |                     |j        ¬¦  «        |	                     |j        ¬¦  «        fS )Nr   rE   r$   ©rV   r    ÚmpsÚcpuF)Údevice_typeÚenabledr*   rG   r´   )r­   Úexpandr„   rU   r4   ru   r    Ú
isinstanceÚtypeÚstrr    Ú	transposeÚcatÚcosr«   ÚsinrV   )
r;   ÚxÚposition_idsÚinv_freq_expandedÚposition_ids_expandedr¿   ÚfreqsÚembrÇ   rÈ   s
             r=   ra   zMixtralRotaryEmbedding.forwardÀ   s›  € ð ŒM˜$    4˜-Ô(×/Ò/°Ô0BÀ1Ô0EÀrÈ1ÑMÔM×PÒPÕW\ÔWbÐklÔksÐPÑtÔtð 	ð !-¨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å¨¸UÐCÑCÔCð 	5ð 	5Ø&Ð)>Ñ>×IÒIÈ!ÈQÑOÔOˆEÝ”)˜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A*D<Ä<E ÅE rl   )rb   rc   rd   r   r%   r,   Ústaticmethodrœ   r4   rf   ru   rª   rJ   r   ra   rg   rh   s   @r=   rŸ   rŸ   š   sö   ø€ € € € € Ø€_�X vÐ.Ñ.Ô.ðOð O˜}ð Oð Oð Oð Oð Oñ /Ô.ðOð  Ø€_�X vÐ.Ñ.Ô.ð5ð 5°ð 5ÐY^Ð_dÔ_kÐmrÐ_rÔYsð 5ð 5ð 5ñ /Ô.ñ „\ð5ð$ €U„]�_„_Øð<ð <ñ Ôñ „_ð<ð <ð <ð <ð <r>   rŸ   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..NrE   r*   rG   )r„   r4   rÆ   )rÉ   Úx1Úx2s      r=   Úrotate_halfrÓ   Ó   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	unsqueezerÓ   )ÚqÚkrÇ   rÈ   Úunsqueeze_dimÚq_embedÚk_embeds          r=   Úapply_rotary_pos_embrÜ   Ú   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_reprB   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$   N)r„   rÁ   rr   )r?   rÝ   ÚbatchÚnum_key_value_headsÚslenr³   s         r=   Ú	repeat_kvrâ   ô   s„   € ð
 2?Ô1DÑ.€EÐ  hØ�‚z€zØÐØ! ! ! ! Q Q Q¨¨a¨a¨a°°°Ð"2Ô3×:Ò:¸5ÐBUÐW\Ð^bÐdlÑmÔm€MØ× Ò  Ð(;¸eÑ(CÀTÈ8ÑTÔTÐTr>   ç        ÚmoduleÚqueryÚkeyÚvalueÚattention_maskÚscalingÚdropoutr¸   c                 ó  — t          || j        ¦  «        }t          || j        ¦  «        }	t          j        ||                     dd¦  «        ¦  «        |z  }
|�|
|z   }
t
          j                             |
dt          j        ¬¦  «         	                    |j
        ¦  «        }
t
          j                             |
|| j        ¬¦  «        }
t          j        |
|	¦  «        }|                     dd¦  «                             ¦   «         }||
fS )Nr*   r   rE   )rH   rV   )Úpr…   r$   )râ   Únum_key_value_groupsr4   ÚmatmulrÅ   r   rK   rt   r•   rU   rV   rê   r…   Ú
contiguous)rä   rå   ræ   rç   rè   ré   rê   r¸   Ú
key_statesÚvalue_statesÚattn_weightsÚattn_outputs               r=   Úeager_attention_forwardrô      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 )Nr³   g      à¿TF©Úbias)r+   r,   r(   r÷   rµ   r/   r¶   r³   rà   rí   ré   Úattention_dropoutÚ	is_causalr   ÚLinearÚq_projÚk_projÚv_projÚo_proj©r;   r(   r÷   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$\ˆÔ!Ø”} dÑ*ˆŒØ!'Ô!9ˆÔØˆŒÝ”i Ô 2°FÔ4NÐQUÔQ^Ñ4^ÐejÐkÑkÔkˆŒÝ”i Ô 2°FÔ4NÐQUÔQ^Ñ4^ÐejÐkÑkÔkˆŒÝ”i Ô 2°FÔ4NÐQUÔQ^Ñ4^ÐejÐkÑkÔkˆŒÝ”i Ô :¸T¼]Ñ JÈFÔL^ÐejÐkÑkÔkˆŒˆˆr>   Nr?   Úposition_embeddingsrè   Úpast_key_valuesr¸   rB   c           
      óL  — |j         d d…         }g |¢d‘| j        ‘R }|                      |¦  «                             |¦  «                             dd¦  «        }|                      |¦  «                             |¦  «                             dd¦  «        }	|                      |¦  «                             |¦  «                             dd¦  «        }
|\  }}t          ||	||¦  «        \  }}	|�|                     |	|
| j	        ¦  «        \  }	}
t          j        | j        j        t          ¦  «        } || ||	|
|f| j        sdn| j        | j        t%          | j        dd ¦  «        dœ|¤Ž\  }} |j        g |¢d‘R Ž                      ¦   «         }|                      |¦  «        }||fS )NrE   r$   r*   rã   Úsliding_window)rê   ré   r  )r„   r³   rþ   rˆ   rÅ   rÿ   r   rÜ   Úupdater÷   r   Úget_interfacer(   Ú_attn_implementationrô   r…   rû   ré   rµ   rr   rï   r  )r;   r?   r  rè   r  r¸   Úinput_shapeÚhidden_shapeÚquery_statesrð   rñ   rÇ   rÈ   Úattention_interfaceró   rò   s                   r=   ra   zMixtralAttention.forward+  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>   rl   )rb   rc   rd   re   r%   Úintr,   r4   rf   rœ   r   r   r   ra   rg   rh   s   @r=   rö   rö     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>   rö   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(   r÷   c                 ó2  •— t          ¦   «                              ¦   «          |j        | _        t          ||¦  «        | _        t          |¦  «        | _        t          |j        |j        ¬¦  «        | _	        t          |j        |j        ¬¦  «        | _
        d S )N©r�   )r+   r,   r/   rö   Ú	self_attnr}   ÚmlprŽ   Úrms_norm_epsÚinput_layernormÚpost_attention_layernormr  s      €r=   r,   zMixtralDecoderLayer.__init__V  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  rè   rÊ   r  r¸   rB   c           	      óÌ   — |}|                       |¦  «        } | j        d|||||dœ|¤Ž\  }}||z   }|}|                      |¦  «        }|                      |¦  «        }||z   }|S )N)r?   r  rè   rÊ   r  © )r  r  r  r  )	r;   r?   r  rè   rÊ   r  r¸   Úresidualr‹   s	            r=   ra   zMixtralDecoderLayer.forward`  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)rb   rc   rd   r%   r  r,   r4   rf   rœ   Ú
LongTensorr   r   r   ra   rg   rh   s   @r=   r  r  U  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)rw   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 )Nrã   )r—   Ústd)r+   Ú_init_weightsr(   Úinitializer_rangerÂ   r'   ÚinitÚnormal_r6   r7   rj   ro   )r;   rä   r"  r<   s      €r=   r#  z$MixtralPreTrainedModel._init_weightsŽ  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>   )rb   rc   rd   r%   Ú__annotations__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"   rj   r  rö   Ú_can_record_outputsr4   rJ   r#  rg   rh   s   @r=   r  r  {  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.0r÷   r(   s     €r=   ú
<listcomp>z)MixtralModel.__init__.<locals>.<listcomp>¢  s$   ø€ ÐeÐeÐe¸	Õ  ¨Ñ3Ô3ÐeÐeÐer>   r  ©r(   F)r+   r,   Úpad_token_idÚpadding_idxÚ
vocab_sizer   Ú	Embeddingr/   Úembed_tokensÚ
ModuleListÚrangeÚnum_hidden_layersÚlayersrŽ   r  ÚnormrŸ   Ú
rotary_embÚgradient_checkpointingÚ	post_initr:   s    `€r=   r,   zMixtralModel.__init__›  sÔ   øø€ Ý‰Œ×Ò˜Ñ Ô Ð Ø!Ô.ˆÔØ Ô+ˆŒåœL¨Ô):¸FÔ<NÐPTÔP`ÑaÔaˆÔÝ”mØeÐeÐeÐeÅUÈ6ÔKcÑEdÔEdÐeÑeÔeñ
ô 
ˆŒõ # 6Ô#5¸6Ô;NÐOÑOÔOˆŒ	Ý0¸Ð?Ñ?Ô?ˆŒØ&+ˆÔ#ð 	�ŠÑÔÐÐÐr>   NÚ	input_idsrè   rÊ   r  Úinputs_embedsÚ	use_cacher¸   rB   c           
      ót  — |d u |d uz  rt          d¦  «        ‚|r|€t          | j        ¬¦  «        }|€|                      |¦  «        }|€V|�|                     ¦   «         nd}t          j        |j        d         |j        ¬¦  «        |z   }| 	                    d¦  «        }| j        j
        €t          nt          }	 |	| j        ||||¬¦  «        }
|}|                      ||¬¦  «        }| j        d | j        j        …         D ]} ||f|
||||dœ|¤Ž}Œ|                      |¦  «        }t#          ||¬	¦  «        S )
Nz:You must specify exactly one of input_ids or inputs_embedsr8  r   r$   )r    )r(   rG  rè   r  rÊ   )rÊ   )rè   rÊ   r  rH  r  )Úlast_hidden_stater  )Ú
ValueErrorr	   r(   r=  Úget_seq_lengthr4   r·   r„   r    rÖ   r  r   r   rC  rA  r@  rB  r   )r;   rF  rè   rÊ   r  rG  rH  r¸   Úpast_seen_tokensÚmask_functionÚcausal_maskr?   r  Údecoder_layers                 r=   ra   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$7ðð ð ðð ˆMˆMð Ÿ	š	 -Ñ0Ô0ˆå%Ø+Ø+ð
ñ 
ô 
ð 	
r>   )NNNNNN)rb   rc   rd   r%   r,   r!   r#   r   r4   r  rf   r   ÚFloatTensorÚboolr   r   r   ra   rg   rh   s   @r=   r3  r3  ™  s  ø€ € € € € ð˜}ð ð ð ð ð ð ð   ØØð .2Ø.2Ø04Ø(,Ø26Ø!%ð4
ð 4
àÔ# dÑ*ð4
ð œ tÑ+ð4
ð Ô&¨Ñ-ð	4
ð
  ™ð4
ð Ô(¨4Ñ/ð4
ð ˜$‘;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>   r3  r*   Úgate_logitsr.   c           	      óÎ  — | �t          | t          ¦  «        sdS | d         j        }t          j        |t          j        |¬¦  «        }t          j        |t          j        |¬¦  «        }d}|�4|                     d¦  «                             |t          j        ¬¦  «        }| D �]‰}	t          j        j	         
                    |	                     |¦  «        d¬¦  «        }
t          j        |
|d¬¦  «        \  }}|€z|t          j        |                     d¦  «        |¬¦  «                             ¦   «         z   }||
                     ¦   «                              d¬¦  «        z   }||
j        d         z   }ŒÒ|t          j        |t          j        |¬¦  «                             d|                     d¦  «        |                     |¦  «        ¦  «        z   }||
                     ¦   «         |                     d¦  «        z                       d¬¦  «        z   }||                     ¦   «         z   }�Œ‹||z  }||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   r¼   rã   rE   )r    rV   rG   )Ú	minlength)rÂ   rœ   r    r4   Úzerosr•   rr   rU   r   rK   rt   rv   Úbincountru   rO   r„   Úscatter_add_Úrepeat_interleaverÖ   )rS  r.   rn   rè   Úcompute_deviceÚtokens_per_expert_sumÚrouter_prob_sumÚ
total_rowsÚ	flat_maskÚ
layer_gateÚrouting_weightsr‹   Úselected_expertsÚtokens_per_expertÚrouter_prob_per_expertÚoverall_losss                   r=   Úload_balancing_loss_funcre  å  sV  € ð: Ð¥*¨[½%Ñ"@Ô"@ÐØˆqð ! ”^Ô*€NÝ!œK¨½5¼=ÐQ_Ð`Ñ`Ô`ÐÝ”k +µU´]È>ÐZÑZÔZ€OØ€JàÐ!à"×*Ò*¨2Ñ.Ô.×1Ò1¸ÍuÌ}Ð1Ñ]Ô]ˆ	à!ð 6ñ 6ˆ
Ýœ(Ô-×5Ò5°j·m²mÀNÑ6SÔ6SÐY[Ð5Ñ\Ô\ˆÝ#œj¨¸%ÀRÐHÑHÔHÑˆÐØÐ!ð &­¬Ð7G×7OÒ7OÐPRÑ7SÔ7SÐ_jÐ(kÑ(kÔ(k×(qÒ(qÑ(sÔ(sÑsð "ð .°×0EÒ0EÑ0GÔ0G×0KÒ0KÐPQÐ0KÑ0RÔ0RÑRˆOØ# oÔ&;¸AÔ&>Ñ>ˆJˆJð %:½E¼KØ¥5¤=¸ð=ñ =ô =çŠl˜1Ð.×6Ò6°rÑ:Ô:¸I×<WÒ<WÐX]Ñ<^Ô<^Ñ_Ô_ñ%`Ð!ð .°×1FÒ1FÑ1HÔ1HÈ9×K^ÒK^Ð_aÑKbÔKbÑ1b×0gÒ0gÐlmÐ0gÑ0nÔ0nÑnˆOØ# i§m¢m¡o¤oÑ5ˆJ‰Jà-°
Ñ:ÐØ,¨zÑ9Ðå”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dd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logitsÚkeep_full_weightc                 óF  •— t          ¦   «                              |¦  «         t          |¦  «        | _        |j        | _        t          j        |j        |j        d¬¦  «        | _        |j	        | _	        |j
        | _        |j        | _        |                      ¦   «          d S )NFrù   )r+   r,   r3  r  r;  r   rý   r/   rh  Úrouter_aux_loss_coefr-   r.   rm   rE  r:   s     €r=   r,   zMixtralForCausalLM.__init__1  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   rF  rè   rÊ   r  rG  ÚlabelsrH  Úoutput_router_logitsÚlogits_to_keepr¸   rB   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)rF  rè   rÊ   r  rG  rH  ro  )ÚlossÚaux_lossrj  r  r?   r   rw   r  )r(   ro  r  rJ  rÂ   r  Úslicerh  Úloss_functionr;  re  rw   r.   rm   rm  rU   r    r   r  r?   r   )r;   rF  rè   rÊ   r  rG  rn  rH  ro  rp  r¸   Úoutputsr?   Úslice_indicesrj  rr  rs  s                    r=   ra   zMixtralForCausalLM.forward=  sn  € ðN %9Ð$DÐ Ð È$Ì+ÔJjð 	ð
 +5¨$¬*ð 	+
ØØ)Ø%Ø+Ø'ØØ!5ð	+
ð 	+
ð ð	+
ð 	+
ˆð  Ô1ˆå8BÀ>ÕSVÑ8WÔ8WÐk�˜~˜o¨tÑ4Ô4Ð4Ð]kˆØ—’˜m¨A¨A¨A¨}¸a¸a¸aÐ,?Ô@ÑAÔAˆàˆØÐØ%�4Ô% f¨f°d´oÐPÐPÈÐPÐPˆDàˆØð 	MÝ/ØÔ%ØÔ ØÔ(Øñ	ô ˆHð Ð!Ø˜Ô1°H·K²KÀÄÑ4LÔ4LÑLÑL�å(ØØØØ#Ô3Ø!Ô/ØÔ)Ø!Ô/ð
ñ 
ô 
ð 	
r>   )	NNNNNNNNr   )rb   rc   rd   Ú_tied_weights_keysÚ_tp_planÚ_pp_planÚ
_fsdp_planr,   r   r   r4   r  rf   r   rQ  rR  r  r   r   r   ra   rg   rh   s   @r=   rg  rg  *  s{  ø€ € € € € à*Ð,GÐHÐØÐ2Ð3€HØ˜_Ð-°¨zÐ:Ð;€HØÐ/Ð0€Jð
ð 
ð 
ð 
ð 
ð Øð .2Ø.2Ø04Ø(,Ø26Ø*.Ø!%Ø,0Ø-.ðP
ð P
àÔ# dÑ*ðP
ð œ tÑ+ðP
ð Ô&¨Ñ-ð	P
ð
  ™ðP
ð Ô(¨4Ñ/ðP
ð Ô  4Ñ'ðP
ð ˜$‘;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>   rg  c                   ó   — e Zd ZdS )Ú MixtralForSequenceClassificationN©rb   rc   rd   r  r>   r=   r}  r}  ’  ó   € € € € € Ø€Dr>   r}  c                   ó   — e Zd ZdS )ÚMixtralForTokenClassificationNr~  r  r>   r=   r�  r�  –  r  r>   r�  c                   ó   — e Zd ZdS )ÚMixtralForQuestionAnsweringNr~  r  r>   r=   rƒ  rƒ  š  r  r>   rƒ  )rg  rƒ  r3  r  r}  r�  )r$   )rã   )Nr*   N)PÚcollections.abcr   r4   Útorch.nn.functionalr   rK   rs   Ú r   r%  Úactivationsr   Úcache_utilsr   r	   Ú
generationr
   Úintegrationsr   r   r   Úmasking_utilsr   r   Úmodeling_flash_attention_utilsr   Úmodeling_layersr   r   r   r   Úmodeling_outputsr   r   Úmodeling_rope_utilsr   r   Úmodeling_utilsr   r   Úprocessing_utilsr   Úutilsr   r   r   Úutils.deprecationr   Úutils.genericr    r!   Úutils.output_capturingr"   r#   Úconfiguration_mixtralr%   ÚModuler'   rj   r}   rŽ   rŸ   rÓ   rÜ   rf   r  râ   ru   rô   rö   r  r  r3  rœ   re  rg  r}  r�  rƒ  Ú__all__r  r>   r=   ú<module>r™     s*  ðð4 %Ð $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 hÐ hÐ hÐ hÐ hÐ hÐ hÐ hÐ hÐ hØ RÐ 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 0Ð 0Ð 0Ð 0Ð 0Ð 0Ø 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$ð ð ð ð ˜BœIñ ô ð ð& Ð˜YÑ'Ô'ðJð Jð Jð Jð J�R”Yñ Jô Jñ (Ô'ðJð(6<ð 6<ð 6<ð 6<ð 6<˜RœYñ 6<ô 6<ð 6<ðr(ð (ð (ð ÐÐ-Ñ.Ô.ðð ð ñ /Ô.ðð2	U˜Uœ\ð 	U°#ð 	U¸%¼,ð 	Uð 	Uð 	Uð 	Uð& ð%ð %ØŒIð%àŒ<ð%ð 
Œð%ð Œ<ð	%ð
 ”L 4Ñ'ð%ð ð%ð ð%ð Ð'Ô(ð%ð %ð %ð %ð2 ÐÐ)Ñ*Ô*ð8)ð 8)ð 8)ð 8)ð 8)�r”yñ 8)ô 8)ñ +Ô*ð8)ðv#ð #ð #ð #ð #Ð4ñ #ô #ð #ðL ð;ð ;ð ;ð ;ð ;˜_ñ ;ô ;ñ „ð;ð: ðH
ð H
ð H
ð H
ð H
Ð)ñ H
ô H
ñ „ðH
ðZ #Ø
Ø*.ð	B&ð B&Ø”  e¤lÔ 3Ñ3°dÑ:ðB&à�t‘ðB&ð ”L 4Ñ'ð	B&ð
 „\�CÑðB&ð B&ð B&ð B&ðJ ðd
ð d
ð d
ð d
ð d
Ð/°ñ d
ô d
ñ „ðd
ðN	ð 	ð 	ð 	ð 	Ð'GÐI_ñ 	ô 	ð 	ð	ð 	ð 	ð 	ð 	Ð$AÐCYñ 	ô 	ð 	ð	ð 	ð 	ð 	ð 	Ð"=Ð?Uñ 	ô 	ð 	ðð ð €€€r>   