§
    9²¸jR¬  ã            $       ó€  — d dl mZ d dlZd dlmc mZ d dlmZ ddlmZ	 ddl
mZ ddlmZmZ ddlmZ dd	lmZmZmZmZ dd
lmZ ddlmZmZ ddlmZmZ ddlmZm Z  ddl!m"Z"m#Z# ddl$m%Z% ddl&m'Z'm(Z(m)Z) ddl*m+Z+ ddl,m-Z-m.Z.m/Z/m0Z0 ddl1m2Z2m3Z3 ddl4m5Z5  ed¦  «         G d„ dej6        ¦  «        ¦   «         Z7d„ Z8 ed¦  «        dsd„¦   «         Z9dej:        de;dej:        fd„Z<	 dtd!ej6        d"ej:        d#ej:        d$ej:        d%ej:        dz  d&e=d'e=d(e%e'         fd)„Z> ee9¦  «         G d*„ d+ej6        ¦  «        ¦   «         Z?d,„ Z@ ed-d.¦  «        	 	 dudej:        d/ej:        d0ejA        d1ejA        dz  d2eBdz  f
d3„¦   «         ZC ed4d.¦  «        	 	 dudej:        d0ejA        d1ejA        dz  d2eBdz  fd5„¦   «         ZD ed6d7¦  «        	 	 	 	 	 	 	 	 	 dvd:ej:        d;ej:        d<ej:        dz  d=ej:        d>ej:        d?ej:        d@ej:        dz  dAej:        dBej:        dz  dCej:        dz  dDej:        dz  dEej:        dz  dFeEdGej:        dz  dHej:        dz  dIej:        dz  dJe=f"dK„¦   «         ZF edLd7¦  «        	 	 	 	 dwdNej:        dej:        dOej:        dAej:        dBej:        dCej:        dDej:        dz  dPej:        dz  dQeEdRej:        dz  fdS„¦   «         ZG edTd7¦  «        	 	 	 	 	 	 	 dxdej:        dOej:        dAej:        dBej:        dCej:        dDej:        dz  dRej:        dz  dEej:        dz  dFeEdUeEdVeEdWeEfdX„¦   «         ZH eeFeHeGeDeCg¦  «         G dY„ dZej6        ¦  «        ¦   «         ZI G d[„ d\ej6        ¦  «        ZJe G d]„ d^ej6        ¦  «        ¦   «         ZK G d_„ d`ej6        ¦  «        ZL G da„ dbe¦  «        ZM G dc„ dde¦  «        ZN G de„ dfe#¦  «        ZOeMeNdgœZPe( G dh„ dieO¦  «        ¦   «         ZQ	 	 	 dydkej:        eRej:                 z  dz  dle;dz  d%ej:        dz  dej:        e;z  fdm„ZSe( G dn„ doeOe¦  «        ¦   «         ZT G dp„ dqeeO¦  «        ZUg dr¢ZVdS )zé    )ÚCallableN)Únné   )Úinitialization)ÚACT2FN)ÚCacheÚDynamicCache)ÚGenerationMixin)Úuse_experts_implementationÚuse_kernel_forward_from_hubÚ&use_kernel_func_from_hub_with_fallbackÚuse_kernelized_func)Úforce_accelerate_hooks)Úcreate_causal_maskÚcreate_recurrent_attention_mask)Ú GenericForSequenceClassificationÚGradientCheckpointingLayer)ÚMoeCausalLMOutputWithPastÚMoeModelOutputWithPast)ÚALL_ATTENTION_FUNCTIONSÚPreTrainedModel)ÚUnpack)ÚTransformersKwargsÚauto_docstringÚcan_return_tuple)Úmerge_with_config_defaults)Úis_mambapy_availableÚis_torch_greater_or_equalÚis_torchdynamo_compilingÚis_torchdynamo_exporting)ÚOutputRecorderÚcapture_outputsé   )ÚJambaConfigÚ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JambaRMSNormç�íµ ÷Æ°>ÚepsÚreturnNc                 ó¬   •— t          ¦   «                              ¦   «          t          j        t	          j        |¦  «        ¦  «        | _        || _        dS )z;
        JambaRMSNorm is equivalent to T5LayerNorm
        N)ÚsuperÚ__init__r   Ú	ParameterÚtorchÚonesÚweightÚvariance_epsilon)ÚselfÚhidden_sizer)   Ú	__class__s      €úx/root/private/project/pallet_detection_v2/.venv/lib/python3.11/site-packages/transformers/models/jamba/modeling_jamba.pyr-   zJambaRMSNorm.__init__=   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rsqrtr2   r1   )r3   r8   Úinput_dtypeÚvariances       r6   ÚforwardzJambaRMSNorm.forwardE   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:r7   c                 óH   — t          | j        j        ¦  «        › d| j        › �S )Nz, eps=)Útupler1   Úshaper2   )r3   s    r6   Ú
extra_reprzJambaRMSNorm.extra_reprL   s&   € Ý˜œÔ)Ñ*Ô*ÐIÐI°$Ô2GÐIÐIÐIr7   )r(   )
Ú__name__Ú
__module__Ú__qualname__Úfloatr-   r/   ÚTensorrE   rI   Ú__classcell__©r5   s   @r6   r'   r'   ;   sŒ   ø€ € € € € ð$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r7   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..Nr;   r:   ©Údim)rH   r/   Úcat)ÚxÚx1Úx2s      r6   Úrotate_halfrX   P   s]   € à	
ˆ3Ð"�!”'˜"”+ Ñ"Ð"Ð"Ô	#€BØ	
ˆ3�”˜”˜qÑ Ð"Ð"Ð"Ô	#€BÝŒ9�r�c˜2�Y BÐ'Ñ'Ô'Ð'r7   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	unsqueezerX   )ÚqÚkÚcosÚsinÚunsqueeze_dimÚq_embedÚk_embeds          r6   Úapply_rotary_pos_embrc   W   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r7   r8   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)rH   ÚexpandÚreshape)r8   rd   ÚbatchÚnum_key_value_headsÚslenÚhead_dims         r6   Ú	repeat_kvrl   q   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Tr7   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   r;   ©rS   r=   )ÚpÚtrainingr#   )rl   Únum_key_value_groupsr/   ÚmatmulÚ	transposer   Ú
functionalÚsoftmaxr?   r>   r=   rt   ry   Ú
contiguous)rn   ro   rp   rq   rr   rs   rt   ru   Ú
key_statesÚvalue_statesÚattn_weightsÚattn_outputs               r6   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$Ð$r7   c                   ó¤   ‡ — e Zd ZdZdedefˆ fd„Z	 	 ddej        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JambaAttentionz=Multi-headed attention from 'Attention Is All You Need' paperÚconfigÚ	layer_idxc                 ó†  •— t          ¦   «                              ¦   «          || _        || _        t	          |d|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 )Nrk   g      à¿TF©Úbias)r,   r-   r‡   rˆ   Úgetattrr4   Únum_attention_headsrk   ri   rz   rs   Úattention_dropoutÚ	is_causalr   ÚLinearÚq_projÚk_projÚv_projÚo_proj)r3   r‡   rˆ   r5   s      €r6   r-   zJambaAttention.__init__š   s  ø€ Ý‰Œ×ÒÑÔÐØˆŒØ"ˆŒÝ ¨
°FÔ4FÈ&ÔJdÑ4dÑeÔeˆŒØ$*Ô$>À&ÔB\Ñ$\ˆÔ!Ø”} dÑ*ˆŒØ!'Ô!9ˆÔØˆŒÝ”i Ô 2°FÔ4NÐQUÔQ^Ñ4^ÐejÐkÑkÔkˆŒÝ”i Ô 2°FÔ4NÐQUÔQ^Ñ4^ÐejÐkÑkÔkˆŒÝ”i Ô 2°FÔ4NÐQUÔQ^Ñ4^ÐejÐkÑkÔkˆŒÝ”i Ô :¸T¼]Ñ JÈFÔL^ÐejÐkÑkÔkˆŒˆˆr7   Nr8   rr   Úpast_key_valuesru   r*   c                 óî  — |j         d d…         }g |¢d‘| j        ‘R }|                      |¦  «                             |¦  «                             dd¦  «        }|                      |¦  «                             |¦  «                             dd¦  «        }|                      |¦  «                             |¦  «                             dd¦  «        }	|�|                     ||	| j        ¦  «        \  }}	t          j
        | j        j        t          ¦  «        }
 |
| |||	|f| j        sdn| j        | j        dœ|¤Ž\  }} |j        g |¢d‘R Ž                      ¦   «         }|                      |¦  «        }||fS )Nr;   r#   r:   rm   )rt   rs   )rH   rk   r‘   Úviewr|   r’   r“   Úupdaterˆ   r   Úget_interfacer‡   Ú_attn_implementationr„   ry   rŽ   rs   rg   r   r”   )r3   r8   rr   r•   ru   Úinput_shapeÚhidden_shapeÚquery_statesr€   r�   Úattention_interfacerƒ   r‚   s                r6   rE   zJambaAttention.forward¨   s�  € ð $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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”Lð	%
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(r7   ©NN)rJ   rK   rL   Ú__doc__r$   Úintr-   r/   rN   r   r   r   rG   rE   rO   rP   s   @r6   r†   r†   –   sÐ   ø€ € € € € àGÐGðl˜{ð l°sð lð lð lð lð lð lð" /3Ø(,ð	")ð ")à”|ð")ð œ tÑ+ð")ð  ™ð	")ð
 Ð+Ô,ð")ð 
ˆuŒ|˜Uœ\¨DÑ0Ð0Ô	1ð")ð ")ð ")ð ")ð ")ð ")ð ")ð ")r7   r†   c                 ób   — |�,| j         }| |dd…dd…df         z                       |¦  «        } | S )zm
    Tunes out the hidden states for padding tokens, see https://github.com/state-spaces/jamba/issues/66
    N)r=   r>   )r8   rr   r=   s      r6   Úapply_mask_to_padding_statesr£   Í   sC   € ð
 Ð!ØÔ#ˆØ&¨¸¸¸¸1¸1¸1¸d¸
Ô)CÑC×GÒGÈÑNÔNˆàÐr7   Úcausal_conv1d_updateÚcausal_conv1dÚ
conv_stater1   r‹   Ú
activationc                 óº  — | j         \  }}}|j         d         }t          j        || gd¬¦  «                             |j        ¦  «        }	|                     |	d d …d d …| d …f         ¦  «         t          j        |	|                     d¦  «        |d|¬¦  «        }
|
d d …d d …| d …f         }
|�t          |         |
¦  «        }
|
                     | j        ¦  «        S )Nr;   rR   r#   r   )ÚpaddingÚgroups)
rH   r/   rT   r>   r=   Úcopy_ÚFÚconv1dr[   r   )r8   r¦   r1   r‹   r§   Ú_r4   Úseq_lenÚ	state_lenÚhidden_states_newÚouts              r6   r¤   r¤   Ù   sî   € ð ,Ô1Ñ€A€{�GØÔ  Ô$€Iåœ	 :¨}Ð"=À2ÐFÑFÔF×IÒIÈ&Ì,ÑWÔWÐØ×ÒÐ& q q q¨!¨!¨!¨i¨Z¨[¨[Ð'8Ô9Ñ:Ô:Ð:Ý
Œ(Ð$ f×&6Ò&6°qÑ&9Ô&9¸4ÈÐS^Ð
_Ñ
_Ô
_€CØ
ˆaˆaˆa����W�H�I�IˆoÔ
€CØÐÝ�ZÔ  Ñ%Ô%ˆØ�6Š6�-Ô%Ñ&Ô&Ð&r7   Úcausal_conv1d_fnc                 ó@  — | j         \  }}}|j         d         dz
  }t          j        |                      |j        ¦  «        |                     d¦  «        |||¬¦  «        d d …d d …d |…f         }	|�t          |         |	¦  «        }	|	                     | j        ¦  «        S )Nr;   r#   )r1   r‹   r©   rª   )rH   r¬   r­   r>   r=   r[   r   )
r8   r1   r‹   r§   ru   r®   r4   r¯   r©   r²   s
             r6   r³   r³   í   s²   € ð ,Ô1Ñ€A€{�GØŒl˜2Ô Ñ"€Gå
Œ(Ø×Ò˜œÑ&Ô&Ø×Ò Ñ"Ô"ØØØðñ ô ð €a€aˆˆˆˆHˆWˆH€nô€Cð ÐÝ�ZÔ  Ñ%Ô%ˆØ�6Š6�-Ô%Ñ&Ô&Ð&r7   Úmamba_inner_fnÚ	mamba_ssmTr(   ÚxzÚconv1d_weightÚconv1d_biasÚx_proj_weightÚdelta_proj_weightÚout_proj_weightÚout_proj_biasÚAÚBÚCÚDÚ
delta_biasÚdelta_softplusÚb_rms_weightÚc_rms_weightÚdt_rms_weightÚb_c_dt_rms_epsc                 ó   — d S ©N© )r·   r¸   r¹   rº   r»   r¼   r½   r¾   r¿   rÀ   rÁ   rÂ   rÃ   rÄ   rÅ   rÆ   rÇ   ru   s                     r6   rµ   rµ     s	   € ð* ˆ4r7   Úselective_state_updateFÚstateÚdtÚdt_biasÚdt_softplusÚzc
                 ó„  — |j         }|�||                     |j         ¦  «        z   }|rt          j        |¦  «        }t	          j        |                     ¦   «         d         |                     ¦   «         z  ¦  «                             | j        ¬¦  «        }|                     ¦   «         d         |                     ¦   «         d d …d d d …f         z  }||                     ¦   «         d         z  }|                      ¦   «         |z  |z   }|                      |                     | j         ¦  «        ¦  «         t	          j	        |                     |j         ¦  «        | 
                    d¦  «        ¦  «                             d¦  «        }|�|||z  z   }|	�|t          j        |	¦  «        z  }|                     |¦  «        S )N©.N©Údevicer;   )r=   r>   r¬   Úsoftplusr/   ÚexprM   rÔ   r«   r{   r[   ÚsqueezeÚsilu)rÌ   r8   rÍ   r¾   r¿   rÀ   rÁ   rÎ   rÏ   rÐ   ru   rC   ÚdAÚdBÚdBxÚ	ssm_stater²   s                    r6   Úmamba_selective_state_updaterÝ     s|  € ð  Ô%€KàÐØ�'—*’*˜RœXÑ&Ô&Ñ&ˆØð ÝŒZ˜‰^Œ^ˆõ 
Œ�2—8’8‘:”:˜iÔ(¨1¯7ª7©9¬9Ñ4Ñ	5Ô	5×	8Ò	8ÀÄÐ	8Ñ	MÔ	M€Bð 
�Š‰Œ�IÔ	 §¢¡¤¨1¨1¨1¨d°A°A°A¨:Ô!6Ñ	6€Bà
ˆ}×"Ò"Ñ$Ô$ YÔ/Ñ
/€Cð —’‘” Ñ" SÑ(€IØ	‡K‚K�	—’˜Uœ[Ñ)Ô)Ñ*Ô*Ð*õ Œ,�y—|’| A¤GÑ,Ô,¨a¯kªk¸"©o¬oÑ
>Ô
>×
FÒ
FÀrÑ
JÔ
J€Cð 	€}Ø�M AÑ%Ñ%ˆà€}Ø•A”F˜1‘I”I‰oˆà�6Š6�+ÑÔÐr7   Úselective_scan_fnÚreturn_last_stateÚuse_mambapyÚuse_associative_scanc           	      óN  — t          d¦  «        rddlm} nd }t          ¦   «         rddlm} nd }| j        \  }}}| j        }|�#||                     |j        ¦  «        d         z   }|rt          j
        |¦  «        }|                     dd¦  «        }|                     dd¦  «        }t          j        |d d d …d d d …f         |d d …d d …d d …d f         z  ¦  «        }|d d …d d …d d …d f         |d d …d d d …d d …f                              ¦   «         z  }|| d d …d d …d d …d f                              ¦   «         z  }|
rƒ|�� ||                     dd¦  «        |                     dd¦  «        ¦  «        }||                     d¦  «        z                       d	¦  «                             dd¦  «        }|d d …df         }�n°|rÏ|�Ít#          ¦   «         r¿t%          ¦   «         s±d
„ }|j        j        dv rdnd} ||||fd|¬¦  «        \  }}t          j        |                     dd¦  «                             |¦  «        |                     d¦  «        ¦  «        }|                     d¦  «                             dd¦  «        }|d d …d d …df         }nßt          j        |||j        d         || j        ¬¦  «        }g }t/          |¦  «        D ]Ž}|d d …d d …|f         |z  |d d …d d …|f         z   }t          j        |                     |¦  «        |d d …|d d …f                              d¦  «        ¦  «        }|                     |d d …d d …df         ¦  «         Œ�t          j        |d¬¦  «        }|�|| |d d d …d f         z  z   }|�|t          j        |¦  «        z  }|	r||fS |S )Nz2.9.0r   )Úassociative_scan)ÚpscanrÒ   r#   r:   r;   r   c                 ó0   — | \  }}|\  }}||z  ||z  |z   fS rÉ   rÊ   )ÚleftÚrightÚa_leftÚb_leftÚa_rightÚb_rights         r6   Ú
combine_fnz(mamba_selective_scan.<locals>.combine_fnƒ  s/   € Ø!‰NˆF�FØ$ÑˆG�WØ˜GÑ# W¨vÑ%5¸Ñ%?Ð?Ð?r7   )ÚcudaÚxpuÚ	pointwiseÚgeneric)rS   Úcombine_mode©r=   rÔ   rR   )r   Ú(torch._higher_order_ops.associative_scanrã   r   Úmambapy.pscanrä   rH   r=   r>   r¬   rÕ   r|   r/   rÖ   rM   r[   r×   r   r    rÔ   Útyper{   ÚzerosÚrangeÚappendÚstackrØ   )r8   rÍ   r¾   r¿   rÀ   rÁ   rÐ   rÂ   rÃ   rß   rà   rá   ru   rã   rä   Ú
batch_sizeÚintermediate_sizer¯   rC   Ú
discrete_AÚ
discrete_BÚdeltaB_uÚ
all_statesÚscan_outputrÜ   rì   rñ   r®   Úscan_outputsÚindexs                                 r6   Úmamba_selective_scanr  J  s`  € õ" ! Ñ)Ô)ð  ØMÐMÐMÐMÐMÐMÐMàÐåÑÔð Ø'Ð'Ð'Ð'Ð'Ð'Ð'àˆà-:Ô-@Ñ*€JÐ! 7ØÔ%€KàÐØ�*—-’- ¤Ñ)Ô)¨)Ô4Ñ4ˆØð ÝŒZ˜‰^Œ^ˆð 	
�Š�A�qÑÔ€AØ	�Š�A�qÑÔ€Aõ ”˜1˜T 1 1 1 d¨A¨A¨AÐ-Ô.°°A°A°A°q°q°q¸!¸!¸!¸T°MÔ1BÑBÑCÔC€JØ�A�A�A�q�q�q˜!˜!˜!˜T�MÔ" Q q q q¨$°°°°1°1°1 }Ô%5×%;Ò%;Ñ%=Ô%=Ñ=€JØ˜M¨!¨!¨!¨Q¨Q¨Q°°°°4¨-Ô8×>Ò>Ñ@Ô@Ñ@€Hàð 28�uÐ(Ø�U˜:×/Ò/°°1Ñ5Ô5°x×7IÒ7IÈ!ÈQÑ7OÔ7OÑPÔPˆ
à! A§K¢K°¡O¤OÑ3×<Ò<¸QÑ?Ô?×IÒIÈ!ÈQÑOÔOˆØ˜q˜q˜q "˜uÔ%ˆ	‰	ð 	ð,8àÐ(å%Ñ'Ô'ð )å0HÑ0JÔ0Jð )ð
	@ð 	@ð 	@ð
 '1Ô&7Ô&<ÀÐ&OÐ&O�{�{ÐU^ˆØ(Ð(ØØ˜Ð"ØØ%ð	
ñ 
ô 
‰ˆˆ:õ ”l :×#7Ò#7¸¸1Ñ#=Ô#=×#@Ò#@ÀÑ#MÔ#MÈqÏ{Ê{Ð[]ÉÌÑ_Ô_ˆØ!×)Ò)¨"Ñ-Ô-×7Ò7¸¸1Ñ=Ô=ˆØ˜q˜q˜q ! ! ! R˜xÔ(ˆ	ˆ	õ ”KØØØŒG�BŒKØØ Ô'ð
ñ 
ô 
ˆ	ð ˆÝ˜7‘^”^ð 	6ð 	6ˆEà" 1 1 1 a a a¨ ;Ô/°)Ñ;¸hÀqÀqÀqÈ!È!È!ÈUÀ{Ô>SÑSˆIõ  œ, y§|¢|°KÑ'@Ô'@À!ÀAÀAÀAÀuÈaÈaÈaÀKÄ.×BZÒBZÐ[]ÑB^ÔB^Ñ_Ô_ˆKØ×Ò ¨A¨A¨A¨q¨q¨q°!¨GÔ 4Ñ5Ô5Ð5Ð5Ý”k ,°BÐ7Ñ7Ô7ˆà€}Ø! M°A°d¸A¸A¸A¸t°mÔ4DÑ$DÑDˆà€}Ø!¥A¤F¨1¡I¤IÑ-ˆàð &Ø˜IÐ%Ð%àÐr7   c            	       óˆ   ‡ — e Zd ZdZdefˆ fd„Z eddg¦  «        	 	 ddej        de	dz  d	ej        dz  fd
„¦   «         Z
ˆ xZS )ÚJambaMambaMixeruƒ  
    Compute âˆ†, A, B, C, and D the state space parameters and compute the `contextualized_states`.
    A, D are input independent (see Mamba paper [1] Section 3.5.2 "Interpretation of A" for why A isn't selective)
    âˆ†, B, C are input-dependent (this is a key difference between Mamba and the linear time invariant S4,
    and is why Mamba is called **selective** state spaces)
    r‡   c           	      ó�  •— t          ¦   «                              ¦   «          || _        || _        |j        | _        |j        | _        |j        | _        |j	        |j        z  | _
        |j        | _        |j        | _        |j        | _        t#          j        | j
        | j
        | j        | j        | j
        | j        dz
  ¬¦  «        | _        |j        | _        t,          |j                 | _        t#          j        | j        | j
        dz  | j        ¬¦  «        | _        t#          j        | j
        | j        | j        dz  z   d¬¦  «        | _        t#          j        | j        | j
        d¬¦  «        | _        t9          j        d| j        dz   ¦  «        d d d …f         }|                     | j
        d¦  «                             ¦   «         }t#          j         t9          j!        |¦  «        ¦  «        | _"        t#          j         t9          j#        | j
        ¦  «        ¦  «        | _$        t#          j        | j
        | j        | j        ¬¦  «        | _%        tM          | j        |j'        ¬¦  «        | _(        tM          | j        |j'        ¬¦  «        | _)        tM          | j        |j'        ¬¦  «        | _*        |j+        | _+        |j,        | _,        d S )	Nr#   )Úin_channelsÚout_channelsr‹   Úkernel_sizerª   r©   r:   rŠ   FTr;   ©r)   )-r,   r-   r‡   rˆ   r4   Úmamba_d_stateÚssm_state_sizeÚmamba_d_convÚconv_kernel_sizeÚmamba_expandrû   Úmamba_dt_rankÚtime_step_rankÚmamba_conv_biasÚuse_conv_biasÚmamba_proj_biasÚuse_biasr   ÚConv1dr­   Ú
hidden_actr§   r   Úactr�   Úin_projÚx_projÚdt_projr/   Úarangerf   r   r.   ÚlogÚA_logr0   rÁ   Úout_projr'   Úrms_norm_epsÚdt_layernormÚb_layernormÚc_layernormrà   rá   )r3   r‡   rˆ   r¾   r5   s       €r6   r-   zJambaMambaMixer.__init__Á  s\  ø€ Ý‰Œ×ÒÑÔÐØˆŒØ"ˆŒØ!Ô-ˆÔØ$Ô2ˆÔØ &Ô 3ˆÔØ!'Ô!4°vÔ7IÑ!IˆÔØ$Ô2ˆÔØ#Ô3ˆÔØÔ.ˆŒÝ”iØÔ.ØÔ/ØÔ#ØÔ-ØÔ)ØÔ)¨AÑ-ð
ñ 
ô 
ˆŒð !Ô+ˆŒÝ˜&Ô+Ô,ˆŒõ ”y Ô!1°4Ô3IÈAÑ3MÐTXÔTaÐbÑbÔbˆŒå”i Ô 6¸Ô8KÈdÔNaÐdeÑNeÑ8eÐlqÐrÑrÔrˆŒå”y Ô!4°dÔ6LÐSWÐXÑXÔXˆŒõ ŒL˜˜DÔ/°!Ñ3Ñ4Ô4°T¸1¸1¸1°WÔ=ˆØ�HŠH�TÔ+¨RÑ0Ô0×;Ò;Ñ=Ô=ˆå”\¥%¤)¨A¡,¤,Ñ/Ô/ˆŒ
Ý”�eœj¨Ô)?Ñ@Ô@ÑAÔAˆŒÝœ	 $Ô"8¸$Ô:JÐQUÔQ^Ð_Ñ_Ô_ˆŒå(¨Ô)<À&ÔBUÐVÑVÔVˆÔÝ'¨Ô(;ÀÔATÐUÑUÔUˆÔÝ'¨Ô(;ÀÔATÐUÑUÔUˆÔà!Ô-ˆÔØ$*Ô$?ˆÔ!Ð!Ð!r7   r­   r  Nr8   Úcache_paramsrr   c                 ó¨  — |j         d         }|j        }|d uo|                     | j        ¦  «        }t	          ||¦  «        }|                      |¦  «                             dd¦  «        }t          j        | j	         
                    ¦   «         ¦  «         }	|                     dd¬¦  «        \  }
}|r:|j        | j                 j        d         }|j        | j                 j        d         }|r^|dk    rX|j        | j                 j        sAt!          |
|| j        j                             d¦  «        | j        j        | j        ¬¦  «        }
nu|�"|                     |
| j        | j        ¬¦  «        }
t1          |
| j        j                             d¦  «        | j        j        fd| j        i|¤Ž}
|�|
d d …d d …| d …f         }
t	          |
                     dd¦  «        |¦  «        }
t          j        |                      |
¦  «        | j        | j        | j        gd¬¦  «        \  }}}|                      |¦  «        }|                      |¦  «        }|                      |¦  «        }tA          | j!        d	¦  «        r7|  "                    |¦  «        | j"        j        z
                       dd¦  «        }n#| j"        j        |                     dd¦  «        z  }| j"        j        �| j"        j         
                    ¦   «         nd }|rr|dk    rltG          ||
                     dd¦  «        d
         |d
         |	|d d …df         |d d …df         | j$        |d
         |d¬¦
  «
         %                    d¦  «        }n¡|d u}tM          |
                     dd¦  «        ||	|                     dd¦  «        |                     dd¦  «        | j$         
                    ¦   «         ||d|| j'        | j(        ¬¦  «        }|r!|\  }}| )                    || j        ¦  «         n|}|  *                    |                     dd¦  «         +                    |¦  «        ¦  «        }|S )Nr#   r:   rR   r   )r§   )r  r§   r;   Ú_is_quantized).r   T)rÐ   rÎ   rÏ   )rÁ   rÐ   rÂ   rÃ   rß   rà   rá   ),rH   r=   Úhas_previous_staterˆ   r£   r  r|   r/   rÖ   r  rM   ÚchunkÚlayersÚconv_statesÚrecurrent_statesÚrecord_pastr¤   r­   r1   r×   r‹   r§   Úupdate_conv_stater  r³   Úsplitr  r  r  r!  r"  r#  Úhasattrr‡   r  rÝ   rÁ   r[   r  rà   rá   Úupdate_recurrent_stater  r>   )r3   r8   r$  rr   ru   r¯   r=   Úuse_precomputed_statesÚprojected_statesr¾   Úhidden_states_B_CÚgater¦   Úrecurrent_stateÚ	time_stepr¿   rÀ   Útime_proj_biasr   Úoutput_final_stateÚscan_resultÚfinal_stateÚcontextualized_statess                          r6   rE   zJambaMambaMixer.forwardï  s›  € ð  Ô% aÔ(ˆØÔ#ˆØ!-°TÐ!9Ð!m¸l×>]Ò>]Ð^bÔ^lÑ>mÔ>mÐõ 5°]ÀNÑSÔSˆØŸ<š<¨Ñ6Ô6×@Ò@ÀÀAÑFÔFÐõ ŒY�t”z×'Ò'Ñ)Ô)Ñ*Ô*Ð*ˆà"2×"8Ò"8¸ÀÐ"8Ñ"BÔ"BÑÐ˜4à!ð 	VØ%Ô,¨T¬^Ô<ÔHÈÔKˆJØ*Ô1°$´.ÔAÔRÐSTÔUˆOð "ð 	G g°¢l l¸<Ô;NÈtÌ~Ô;^Ô;j lÝ 4Ø!ØØ”Ô"×*Ò*¨1Ñ-Ô-Ø”Ô Øœ?ð!ñ !ô !ÐÐð Ð'Ø$0×$BÒ$BØ%Ø”NØ%)Ô%:ð %Cñ %ô %Ð!õ !1Ø!Ø”Ô"×*Ò*¨1Ñ-Ô-Ø”Ô ð!ð !ð  œ?ð	!ð
 ð!ð !Ðð Ð'Ø$5°a°a°a¸¸¸¸W¸H¸I¸I°oÔ$FÐ!õ 9Ð9J×9TÒ9TÐUVÐXYÑ9ZÔ9ZÐ\jÑkÔkÐÝœ+Ø�KŠKÐ)Ñ*Ô*ØÔ  $Ô"5°tÔ7JÐKØð
ñ 
ô 
‰ˆ	�1�að ×%Ò% iÑ0Ô0ˆ	Ø×Ò˜QÑÔˆØ×Ò˜QÑÔˆõ �4”; Ñ0Ô0ð 	HØŸš iÑ0Ô0°4´<Ô3DÑD×OÒOÐPQÐSTÑUÔUˆIˆIàœÔ+¨i×.AÒ.AÀ!ÀQÑ.GÔ.GÑGˆIØ6:´lÔ6GÐ6S˜œÔ*×0Ò0Ñ2Ô2Ð2ÐY]ˆð "ð $	* g°¢l lÝ6ØØ!×+Ò+¨A¨qÑ1Ô1°&Ô9Ø˜&Ô!ØØ�!�!�!�Q�$”Ø�!�!�!�Q�$”Ø”Ø�v”,Ø&Ø ðñ ô ÷ Ši˜‰mŒmð ˆKð ".°TÐ!9ÐÝ.Ø!×+Ò+¨A¨qÑ1Ô1ØØØ—’˜A˜qÑ!Ô!Ø—’˜A˜qÑ!Ô!Ø”&—,’,‘.”.ØØ)Ø#Ø"4Ø Ô,Ø%)Ô%>ðñ ô ˆKð "ð *Ø+6Ñ(�˜[Ø×3Ò3°KÀÄÑPÔPÐPÐPà)�ð !%§¢¨k×.CÒ.CÀAÀqÑ.IÔ.I×.LÒ.LÈUÑ.SÔ.SÑ TÔ TÐØ$Ð$r7   rŸ   )rJ   rK   rL   r    r$   r-   r   r/   rN   r   rE   rO   rP   s   @r6   r  r  ¶  sÉ   ø€ € € € € ðð ð,@˜{ð ,@ð ,@ð ,@ð ,@ð ,@ð ,@ð\ Ð˜X yÐ1Ñ2Ô2ð &*Ø.2ð	s%ð s%à”|ðs%ð ˜d‘lðs%ð œ tÑ+ð	s%ð s%ð s%ñ 3Ô2ðs%ð s%ð s%ð s%ð s%r7   r  c                   ó$   ‡ — e Zd Zˆ fd„Zd„ Zˆ xZS )ÚJambaMLPc                 ó˜  •— t          ¦   «                              ¦   «          || _        |j        | _        |j        | _        t          j        | j        | j        d¬¦  «        | _        t          j        | j        | j        d¬¦  «        | _        t          j        | j        | j        d¬¦  «        | _	        t          |j                 | _        d S ©NFrŠ   )r,   r-   r‡   r4   rû   r   r�   Ú	gate_projÚup_projÚ	down_projr   r  Úact_fn©r3   r‡   r5   s     €r6   r-   zJambaMLP.__init__g  s¦   ø€ Ý‰Œ×ÒÑÔÐØˆŒØ!Ô-ˆÔØ!'Ô!9ˆ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r7   c                 ó¨   — |                       |                      |                      |¦  «        ¦  «        |                      |¦  «        z  ¦  «        }|S rÉ   )rB  rC  r@  rA  )r3   rU   rB  s      r6   rE   zJambaMLP.forwardq  sA   € Ø—N’N 4§;¢;¨t¯~ª~¸aÑ/@Ô/@Ñ#AÔ#AÀDÇLÂLÐQRÁOÄOÑ#SÑTÔTˆ	ØÐr7   )rJ   rK   rL   r-   rE   rO   rP   s   @r6   r=  r=  f  sG   ø€ € € € € ð0ð 0ð 0ð 0ð 0ðð ð ð ð ð ð r7   r=  c                   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JambaExpertsz2Collection of expert weights stored as 3D tensors.r‡   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 )Nr:   )r,   r-   Únum_local_expertsÚnum_expertsr4   Ú
hidden_dimrû   Úintermediate_dimr   r.   r/   ÚemptyÚgate_up_projrB  r   r  rC  rD  s     €r6   r-   zJambaExperts.__init__z  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r7   r8   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_classesr:   r#   r   )r;   éþÿÿÿrR   r;   )r/   Ú
zeros_likeÚno_gradr   r}   Úone_hotrJ  ÚpermuteÚgreaterÚsumÚnonzeroÚwhereÚlinearrN  r(  rC  rB  Ú
index_add_r>   r=   )r3   r8   rO  rP  Úfinal_hidden_statesÚexpert_maskÚ
expert_hitÚ
expert_idxÚ	top_k_posÚ	token_idxÚcurrent_stater4  ÚupÚcurrent_hidden_statess                 r6   rE   zJambaExperts.forwardƒ  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)
rJ   rK   rL   r    r$   r-   r/   rN   rE   rO   rP   s   @r6   rG  rG  v  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 #r7   rG  c                   óR   ‡ — e Zd ZdZdefˆ fd„Zd„ Zdej        dej        fd„Z	ˆ xZ
S )ÚJambaSparseMoeBlockaÈ  
    This implementation is
    strictly equivalent to standard MoE with full capacity (no
    dropped tokens). It's faster since it formulates MoE operations
    in terms of block-sparse operations to accommodate imbalanced
    assignments of tokens to experts, whereas standard MoE either
    (1) drop tokens at the cost of reduced performance or (2) set
    capacity factor to number of experts and thus waste computation
    and memory on padding.
    r‡   c                 ó  •— t          ¦   «                              ¦   «          |j        | _        |j        | _        |j        | _        |j        | _        t          j
        | j        | j        d¬¦  «        | _        t          |¦  «        | _        d S r?  )r,   r-   r4   rK  rû   Úffn_dimrJ  Únum_experts_per_tokÚtop_kr   r�   ÚrouterrG  ÚexpertsrD  s     €r6   r-   zJambaSparseMoeBlock.__init__ª  sr   ø€ Ý‰Œ×ÒÑÔÐØ Ô,ˆŒØÔ/ˆŒØ!Ô-ˆÔØÔ/ˆŒ
å”i ¤°Ô1AÈÐNÑNÔNˆŒÝ# FÑ+Ô+ˆŒˆˆr7   c                 óÚ   — t           j        j                             |dt           j        ¬¦  «        }t          j        || j        d¬¦  «        \  }}||                     |j        ¦  «        fS )Nr;   rw   rR   )	r/   r   r}   r~   rM   Útopkrl  r>   r=   )r3   r8   Úrouter_logitsÚrouting_weightsrP  rO  s         r6   Úroute_tokens_to_expertsz+JambaSparseMoeBlock.route_tokens_to_experts´  s_   € Ýœ(Ô-×5Ò5°mÈÕSXÔS^Ð5Ñ_Ô_ˆÝ%*¤Z°ÀÄÐQSÐ%TÑ%TÔ%TÑ"ˆ�{Ø˜M×,Ò,¨]Ô-@ÑAÔAÐAÐAr7   r8   r*   c                 ó   — |j         \  }}}|                     d|¦  «        }|                      |¦  «        }|                      ||¦  «        \  }}|                      |||¦  «        }|                     |||¦  «        }|S )Nr;   )rH   r—   rm  rs  rn  rg   )r3   r8   rú   Úsequence_lengthrK  rq  rO  rP  s           r6   rE   zJambaSparseMoeBlock.forward¹  s„   € Ø2?Ô2EÑ/ˆ
�O ZØ%×*Ò*¨2¨zÑ:Ô:ˆØŸš MÑ2Ô2ˆØ%)×%AÒ%AÀ-ÐQ^Ñ%_Ô%_Ñ"ˆ�]ØŸš ]°KÀÑOÔOˆØ%×-Ò-¨j¸/È:ÑVÔVˆØÐr7   )rJ   rK   rL   r    r$   r-   rs  r/   rN   rE   rO   rP   s   @r6   rh  rh  ž  s†   ø€ € € € € ð	ð 	ð,˜{ð ,ð ,ð ,ð ,ð ,ð ,ðBð Bð Bð
 U¤\ð °e´lð ð ð ð ð ð ð ð r7   rh  c                   ó¢   ‡ — 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         dej        fd„Zˆ xZS )ÚJambaAttentionDecoderLayerr‡   rˆ   c                 óf  •— t          ¦   «                              ¦   «          |j        r|j        |         nd}t          ||¦  «        | _        |dk    rt
          nt          } ||¦  «        | _        t          |j	        |j
        ¬¦  «        | _        t          |j	        |j
        ¬¦  «        | _        d S )Nr#   r
  )r,   r-   Úlayers_num_expertsr†   Ú	self_attnrh  r=  Úfeed_forwardr'   r4   r   Úinput_layernormÚpre_ff_layernorm©r3   r‡   rˆ   rJ  Úffn_layer_classr5   s        €r6   r-   z#JambaAttentionDecoderLayer.__init__Ä  s¦   ø€ Ý‰Œ×ÒÑÔÐØ>DÔ>WÐ^�fÔ/°	Ô:Ð:Ð]^ˆÝ'¨°	Ñ:Ô:ˆŒà1<¸q²°Õ-Ð-ÅhˆØ+˜O¨FÑ3Ô3ˆÔÝ+¨FÔ,>ÀFÔDWÐXÑXÔXˆÔÝ ,¨VÔ-?ÀVÔEXÐ YÑ YÔ YˆÔÐÐr7   NFr8   rr   Úposition_idsr•   Ú	use_cacheru   r*   c           	      óÌ   — |}|                       |¦  «        } | j        d|||||dœ|¤Ž\  }}||z   }|}|                      |¦  «        }|                      |¦  «        }||z   }|S )N)r8   rr   r€  r•   r�  rÊ   )r|  rz  r}  r{  )	r3   r8   rr   r€  r•   r�  ru   Úresidualr®   s	            r6   rE   z"JambaAttentionDecoderLayer.forwardÎ  sž   € ð !ˆØ×,Ò,¨]Ñ;Ô;ˆØ)˜4œ>ð 
Ø'Ø)Ø%Ø+Øð
ð 
ð ð
ð 
Ñˆ�qð ! =Ñ0ˆØ ˆØ×-Ò-¨mÑ<Ô<ˆØ×)Ò)¨-Ñ8Ô8ˆØ  =Ñ0ˆØÐr7   )NNNF)rJ   rK   rL   r$   r¡   r-   r/   rN   Ú
LongTensorr   Úboolr   r   ÚFloatTensorrE   rO   rP   s   @r6   rw  rw  Ã  sà   ø€ € € € € ðZ˜{ð Z°sð Zð Zð Zð Zð Zð Zð /3Ø04Ø(,Ø!&ðð à”|ðð œ tÑ+ðð Ô&¨Ñ-ð	ð
  ™ðð ˜$‘;ðð Ð+Ô,ðð 
Ô	ðð ð ð ð ð ð ð r7   rw  c                   ó–   ‡ — 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
e         d
ej        fd„Zˆ xZS )ÚJambaMambaDecoderLayerr‡   rˆ   c                 óh  •— t          ¦   «                              ¦   «          |j        r|j        |         nd}t          ||¬¦  «        | _        |dk    rt
          nt          } ||¦  «        | _        t          |j	        |j
        ¬¦  «        | _        t          |j	        |j
        ¬¦  «        | _        d S )Nr#   )r‡   rˆ   r
  )r,   r-   ry  r  Úmambarh  r=  r{  r'   r4   r   r|  r}  r~  s        €r6   r-   zJambaMambaDecoderLayer.__init__ê  s©   ø€ Ý‰Œ×ÒÑÔÐØ>DÔ>WÐ^�fÔ/°	Ô:Ð:Ð]^ˆÝ$¨F¸iÐHÑHÔHˆŒ
Ø1<¸q²°Õ-Ð-ÅhˆØ+˜O¨FÑ3Ô3ˆÔÝ+¨FÔ,>ÀFÔDWÐXÑXÔXˆÔÝ ,¨VÔ-?ÀVÔEXÐ YÑ YÔ YˆÔÐÐr7   Nr8   rr   r€  r•   ru   r*   c                 óÐ   — |}|                       |¦  «        }|                      |||¬¦  «        }||z   }|}|                      |¦  «        }|                      |¦  «        }||z   }|S )N)r8   r$  rr   )r|  rŠ  r}  r{  )r3   r8   rr   r€  r•   ru   rƒ  s          r6   rE   zJambaMambaDecoderLayer.forwardó  s„   € ð !ˆØ×,Ò,¨]Ñ;Ô;ˆØŸ
š
Ø'Ø(Ø)ð #ñ 
ô 
ˆð
 ! =Ñ0ˆØ ˆØ×-Ò-¨mÑ<Ô<ˆØ×)Ò)¨-Ñ8Ô8ˆØ  =Ñ0ˆØÐr7   )NNN)rJ   rK   rL   r$   r¡   r-   r/   rN   r„  r   r   r   r†  rE   rO   rP   s   @r6   rˆ  rˆ  é  sÏ   ø€ € € € € ðZ˜{ð Z°sð Zð Zð Zð Zð Zð Zð /3Ø04Ø(,ðð à”|ðð œ tÑ+ðð Ô&¨Ñ-ð	ð
  ™ðð Ð+Ô,ðð 
Ô	ðð ð ð ð ð ð ð r7   rˆ  c                   óª   ‡ — e Zd ZU eed<   dZdZddgZdgZdZ	dZ
dZdZeege eej        d¬¦  «        d	œZ ej        ¦   «         ˆ fd
„¦   «         Zˆ xZS )ÚJambaPreTrainedModelr‡   ÚmodelTrw  rˆ  r•   rm  )Ú
layer_name)r8   Ú
attentionsrq  c                 óp  •— t          ¦   «                              |¦  «         t          |t          ¦  «        r›t	          j        d|j        dz   ¦  «        d d d …f         }|                     |j        d¦  «         	                    ¦   «         }t          j        |j        t	          j        |¦  «        ¦  «         t          j        |j        ¦  «         d S t          |t           ¦  «        rNt          j        |j        d| j        j        ¬¦  «         t          j        |j        d| j        j        ¬¦  «         d S d S )Nr#   r;   rm   )rA   Ústd)r,   Ú_init_weightsÚ
isinstancer  r/   r  r  rf   rû   r   Úinitr«   r  r  Úones_rÁ   rG  Únormal_rN  r‡   Úinitializer_rangerB  )r3   rn   r¾   r5   s      €r6   r“  z"JambaPreTrainedModel._init_weights  s  ø€ å‰Œ×Ò˜fÑ%Ô%Ð%Ý�f�oÑ.Ô.ð 	XÝ”˜Q Ô 5¸Ñ 9Ñ:Ô:¸4ÀÀÀ¸7ÔCˆAØ—’˜Ô1°2Ñ6Ô6×AÒAÑCÔCˆAÝŒJ�v”|¥U¤Y¨q¡\¤\Ñ2Ô2Ð2ÝŒJ�v”xÑ Ô Ð Ð Ð Ý˜¥Ñ-Ô-ð 	XÝŒL˜Ô,°3¸D¼KÔ<YÐZÑZÔZÐZÝŒL˜Ô)°¸¼Ô9VÐWÑWÔWÐWÐWÐWð	Xð 	Xr7   )rJ   rK   rL   r$   Ú__annotations__Úbase_model_prefixÚsupports_gradient_checkpointingÚ_no_split_modulesÚ_skip_keys_device_placementÚ_supports_flash_attnÚ_supports_sdpaÚ_is_statefulÚ_can_compile_fullgraphrw  rˆ  r†   r!   r   r�   Ú_can_record_outputsr/   rU  r“  rO   rP   s   @r6   r�  r�  
  sÇ   ø€ € € € € € ØÐÐÑØÐØ&*Ð#Ø5Ð7OÐPÐØ#4Ð"5ÐØÐØ€NØ€LØ!Ðà4Ð6LÐMØ$Ø'˜¨¬	¸hÐGÑGÔGðð Ðð €U„]�_„_ð	Xð 	Xð 	Xð 	Xñ „_ð	Xð 	Xð 	Xð 	Xð 	Xr7   r�  )Ú	attentionrŠ  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
JambaModelr‡   c                 ó  •— t          ¦   «                              |¦  «         |j        | _        |j        | _        t          j        |j        |j        | j        ¦  «        | _        g }t          |j
        ¦  «        D ]:}t          |j        |                  }|                      |||¬¦  «        ¦  «         Œ;t          j        |¦  «        | _        t!          |j        |j        ¬¦  «        | _        d| _        |                      ¦   «          d S )N)rˆ   r
  F)r,   r-   Úpad_token_idÚpadding_idxÚ
vocab_sizer   Ú	Embeddingr4   Úembed_tokensr÷   Únum_hidden_layersÚALL_DECODER_LAYER_TYPESÚlayers_block_typerø   Ú
ModuleListr)  r'   r   Úfinal_layernormÚgradient_checkpointingÚ	post_init)r3   r‡   Údecoder_layersÚiÚlayer_classr5   s        €r6   r-   zJambaModel.__init__,  só   ø€ Ý‰Œ×Ò˜Ñ Ô Ð Ø!Ô.ˆÔØ Ô+ˆŒåœL¨Ô):¸FÔ<NÐPTÔP`ÑaÔaˆÔØˆÝ�vÔ/Ñ0Ô0ð 	Dð 	DˆAÝ1°&Ô2JÈ1Ô2MÔNˆKØ×!Ò! + +¨fÀÐ"BÑ"BÔ"BÑCÔCÐCÐCÝ”m NÑ3Ô3ˆŒå+¨FÔ,>ÀFÔDWÐXÑXÔXˆÔà&+ˆÔ#à�ŠÑÔÐÐÐr7   NÚ	input_idsrr   r€  r•   Úinputs_embedsr�  ru   r*   c           	      óˆ  — |d u |d uz  rt          d¦  «        ‚|€|                      |¦  «        }|r|€t          | j        ¬¦  «        }|€V|�|                     ¦   «         nd}t          j        |j        d         |j        ¬¦  «        |z   }| 	                    d¦  «        }t          |x}	t          ¦  «        s&| j        ||||dœ}
t          d
i |
¤Žt          d
i |
¤Ždœ}	|}t          | j        ¦  «        D ])\  }} ||f|	| j        j        |                  |||dœ|¤Ž}Œ*|                      |¦  «        }t%          ||¬	¦  «        S )Nz:You must specify exactly one of input_ids or inputs_embeds)r‡   r   r#   rÓ   )r‡   r·  rr   r•   r€  )Úfull_attentionÚlinear_attention)rr   r€  r•   r�  )Úlast_hidden_stater•   rÊ   )Ú
ValueErrorr«  r	   r‡   Úget_seq_lengthr/   r  rH   rÔ   r[   r”  Údictr   r   Ú	enumerater)  Úlayer_typesr°  r   )r3   r¶  rr   r€  r•   r·  r�  ru   Úpast_seen_tokensÚcausal_mask_mappingÚmask_kwargsr8   r´  Údecoder_layers                 r6   rE   zJambaModel.forward>  sÂ  € 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 	ð œ+Ø!.Ø"0Ø#2Ø ,ðð ˆKõ #5Ð"CÐ"C°{Ð"CÐ"CÝ$CÐ$RÐ$RÀkÐ$RÐ$Rð#ð #Ðð &ˆÝ )¨$¬+Ñ 6Ô 6ð 	ð 	ÑˆAˆ}Ø)˜MØðà2°4´;Ô3JÈ1Ô3MÔNØ)Ø /Ø#ðð ð ðð ˆMˆMð ×,Ò,¨]Ñ;Ô;ˆå%Ø+Ø+ð
ñ 
ô 
ð 	
r7   )NNNNNN)rJ   rK   rL   r$   r-   r   r"   r   r/   r„  rN   r   r†  r…  r   r   r   rE   rO   rP   s   @r6   r¥  r¥  *  s  ø€ € € € € ð˜{ð ð ð ð ð ð ð$  ØØð .2Ø.2Ø04Ø(,Ø26Ø!%ð6
ð 6
àÔ# dÑ*ð6
ð œ tÑ+ð6
ð Ô&¨Ñ-ð	6
ð
  ™ð6
ð Ô(¨4Ñ/ð6
ð ˜$‘;ð6
ð Ð+Ô,ð6
ð 
 ð6
ð 6
ð 6
ñ „^ñ „_ñ  Ôð6
ð 6
ð 6
ð 6
ð 6
r7   r¥  r:   Úgate_logitsrJ  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   rò   rm   r;   )rÔ   r=   rR   )Ú	minlength)r”  rG   rÔ   r/   rö   r?   rg   r>   r   r}   r~   rp  ÚbincountrM   rY  rH   Úscatter_add_Úrepeat_interleaver[   )rÅ  rJ  rl  rr   Úcompute_deviceÚtokens_per_expert_sumÚrouter_prob_sumÚ
total_rowsÚ	flat_maskÚ
layer_gaterr  r®   Úselected_expertsÚtokens_per_expertÚrouter_prob_per_expertÚoverall_losss                   r6   Úload_balancing_loss_funcrÕ  z  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%r7   c                   ó2  ‡ — e Zd ZddiZddiZddgdgfiZddiZdef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JambaForCausalLMzlm_head.weightzmodel.embed_tokens.weightÚlm_headÚcolwise_gather_outputr8   ÚlogitsÚkeep_full_weightr‡   c                 óF  •— t          ¦   «                              |¦  «         t          |¦  «        | _        |j        | _        t          j        |j        |j        d¬¦  «        | _        |j	        | _	        |j
        | _
        |j        | _        |                      ¦   «          d S r?  )r,   r-   r¥  rŽ  r©  r   r�   r4   rØ  Úrouter_aux_loss_coefrJ  rk  r²  rD  s     €r6   r-   zJambaForCausalLM.__init__Æ  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r7   Nr   r¶  rr   r€  r•   r·  Úlabelsr�  Úoutput_router_logitsÚlogits_to_keepru   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 )aj  
        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, JambaForCausalLM

        >>> model = JambaForCausalLM.from_pretrained("ai21labs/Jamba-v0.1")
        >>> tokenizer = AutoTokenizer.from_pretrained("ai21labs/Jamba-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)r¶  rr   r€  r•   r·  r�  rß  )ÚlossÚaux_lossrÚ  r•   r8   r�  rq  rÊ   )r‡   rß  rŽ  r»  r”  r¡   ÚslicerØ  Úloss_functionr©  rÕ  rq  rJ  rk  rÝ  r>   rÔ   r   r•   r8   r�  )r3   r¶  rr   r€  r•   r·  rÞ  r�  rß  rà  ru   Úoutputsr8   Úslice_indicesrÚ  râ  rã  s                    r6   rE   zJambaForCausalLM.forwardÒ  sn  € ðN %9Ð$DÐ Ð È$Ì+ÔJjð 	ð
 +5¨$¬*ð 	+
ØØ)Ø%Ø+Ø'ØØ!5ð	+
ð 	+
ð ð	+
ð 	+
ˆð  Ô1ˆå8BÀ>ÕSVÑ8WÔ8WÐk�˜~˜o¨tÑ4Ô4Ð4Ð]kˆØ—’˜m¨A¨A¨A¨}¸a¸a¸aÐ,?Ô@ÑAÔAˆàˆØÐØ%�4Ô% f¨f°d´oÐPÐPÈÐPÐPˆDàˆØð 	MÝ/ØÔ%ØÔ ØÔ(Øñ	ô ˆHð Ð!Ø˜Ô1°H·K²KÀÄÑ4LÔ4LÑLÑL�å(ØØØØ#Ô3Ø!Ô/ØÔ)Ø!Ô/ð
ñ 
ô 
ð 	
r7   )	NNNNNNNNr   )rJ   rK   rL   Ú_tied_weights_keysÚ_tp_planÚ_pp_planÚ
_fsdp_planr$   r-   r   r   r/   r„  rN   r   r†  r…  r¡   r   r   r   rE   rO   rP   s   @r6   r×  r×  ¿  s‡  ø€ € € € € à*Ð,GÐHÐØÐ2Ð3€HØ˜_Ð-°¨zÐ:Ð;€HØÐ/Ð0€Jð
˜{ð 
ð 
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 ˜$‘;ðP
ð # T™kðP
ð ˜eœlÑ*ðP
ð Ð+Ô,ðP
ð 
#ðP
ð P
ð P
ñ „^ñ ÔðP
ð P
ð P
ð P
ð P
r7   r×  c                   ó   — e Zd ZdS )ÚJambaForSequenceClassificationN)rJ   rK   rL   rÊ   r7   r6   rí  rí  '  s   € € € € € Ø€Dr7   rí  )r×  rí  r¥  r�  )r#   )rm   rŸ   )	NNNNTNNNr(   )NNFN)NNNFFFF)Nr:   N)WÚcollections.abcr   r/   Útorch.nn.functionalr   r}   r¬   Ú r   r•  Úactivationsr   Úcache_utilsr   r	   Ú
generationr
   Úintegrationsr   r   r   r   Úintegrations.accelerater   Úmasking_utilsr   r   Úmodeling_layersr   r   Úmodeling_outputsr   r   Úmodeling_utilsr   r   Úprocessing_utilsr   Úutilsr   r   r   Úutils.genericr   Úutils.import_utilsr   r   r   r    Úutils.output_capturingr!   r"   Úconfiguration_jambar$   ÚModuler'   rX   rc   rN   r¡   rl   rM   r„   r†   r£   r.   Ústrr¤   r³   r…  rµ   rÝ   r  r  r=  rG  rh  rw  rˆ  r�  r­  r¥  rG   rÕ  r×  rí  Ú__all__rÊ   r7   r6   ú<module>r     s8
  ðð2 %Ð $Ð $Ð $Ð $Ð $à €€€Ø Ð Ð Ð Ð Ð Ð Ð Ð Ø Ð Ð Ð Ð Ð à &Ð &Ð &Ð &Ð &Ð &Ø !Ð !Ð !Ð !Ð !Ð !Ø .Ð .Ð .Ð .Ð .Ð .Ð .Ð .Ø )Ð )Ð )Ð )Ð )Ð )ðð ð ð ð ð ð ð ð ð ð ð ð >Ð =Ð =Ð =Ð =Ð =Ø PÐ PÐ PÐ PÐ PÐ PÐ PÐ PØ [Ð [Ð [Ð [Ð [Ð [Ð [Ð [Ø QÐ QÐ QÐ QÐ QÐ QÐ QÐ QØ FÐ FÐ FÐ FÐ FÐ FÐ FÐ FØ &Ð &Ð &Ð &Ð &Ð &Ø IÐ IÐ IÐ IÐ IÐ IÐ IÐ IÐ IÐ IØ 7Ð 7Ð 7Ð 7Ð 7Ð 7ðð ð ð ð ð ð ð ð ð ð ð ð FÐ EÐ EÐ EÐ EÐ EÐ EÐ EØ ,Ð ,Ð ,Ð ,Ð ,Ð ,ð Ð˜YÑ'Ô'ðJð Jð Jð Jð J�2”9ñ Jô Jñ (Ô'ðJð((ð (ð (ð ÐÐ-Ñ.Ô.ðð ð ñ /Ô.ðð2	U˜Uœ\ð 	U°#ð 	U¸%¼,ð 	Uð 	Uð 	Uð 	Uð& ð%ð %ØŒIð%àŒ<ð%ð 
Œð%ð Œ<ð	%ð
 ”L 4Ñ'ð%ð ð%ð ð%ð Ð'Ô(ð%ð %ð %ð %ð2 ÐÐ)Ñ*Ô*ð3)ð 3)ð 3)ð 3)ð 3)�R”Yñ 3)ô 3)ñ +Ô*ð3)ðl	ð 	ð 	ð (Ð'Ð(>ÀÑPÔPð
 !%Ø!ð'ð 'Ø”<ð'à”ð'ð ŒLð'ð Œ,˜Ñ
ð	'ð
 �d‘
ð'ð 'ð 'ñ QÔPð'ð& (Ð'Ð(:¸OÑLÔLð !%Ø!ð	'ð 'Ø”<ð'àŒLð'ð Œ,˜Ñ
ð'ð �d‘
ð	'ð 'ð 'ñ MÔLð'ð, (Ð'Ð(8¸+ÑFÔFð "Ø!Ø!Ø&*ØØ(,Ø(,Ø)-Ø ð#ð ØŒðà”<ðð ” Ñ$ðð ”<ð	ð
 ”|ðð ”\ðð ”< $Ñ&ðð „|ðð „|�dÑðð „|�dÑðð „|�dÑðð ”˜tÑ#ðð ðð ”, Ñ%ðð ”, Ñ%ðð  ”< $Ñ&ð!ð" ð#ð ð ñ GÔFðð. (Ð'Ð(@À+ÑNÔNð "Ø#'ØØ!ð*ð *ØŒ<ð*à”<ð*ð 	Œð*ð „|ð	*ð
 „|ð*ð „|ð*ð „|�dÑð*ð Œ\˜DÑ ð*ð ð*ð „|�dÑð*ð *ð *ñ OÔNð*ðZ (Ð'Ð(;¸[ÑIÔIð "Ø!Ø&*Ø Ø#ØØ!&ðhð hØ”<ðhàŒðhð „|ðhð „|ð	hð
 „|ðhð „|�dÑðhð „|�dÑðhð ”˜tÑ#ðhð ðhð ðhð ðhð ðhð hð hñ JÔIðhðV ÐØÐ)Ð+GÐIYÐ[oÐpñô ðj%ð j%ð j%ð j%ð j%�b”iñ j%ô j%ñô ðj%ðZð ð ð ð ˆrŒyñ ô ð ð  ð$#ð $#ð $#ð $#ð $#�2”9ñ $#ô $#ñ Ôð$#ðN"ð "ð "ð "ð "˜"œ)ñ "ô "ð "ðJ#ð #ð #ð #ð #Ð!;ñ #ô #ð #ðLð ð ð ð Ð7ñ ô ð ðBXð Xð Xð Xð X˜?ñ Xô Xð Xð: )CÐMcÐdÐdÐ ð ðL
ð L
ð L
ð L
ð L
Ð%ñ L
ô L
ñ „ðL
ðb #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%EÐG[ñ 	ô 	ð 	ð gÐ
fÐ
f€€€r7   