§
    9²¸j]  ã                   óŒ  — d dl mZ d dl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 dd	lmZ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$m%Z% ddl&m'Z'm(Z( ddl)m*Z* ddl+m,Z,  ed¦  «         G d„ dej-        ¦  «        ¦   «         Z. G d„ dej-        ¦  «        Z/d„ Z0 ed¦  «        d>d„¦   «         Z1dej2        de3dej2        fd „Z4	 d?d"ej-        d#ej2        d$ej2        d%ej2        d&ej2        dz  d'e5d(e5d)ee!         fd*„Z6 G d+„ d,ej-        ¦  «        Z7 G d-„ d.ej-        ¦  «        Z8 G d/„ d0e¦  «        Z9e" G d1„ d2e¦  «        ¦   «         Z:e" G d3„ d4e:¦  «        ¦   «         Z;e" G d5„ d6e:e
¦  «        ¦   «         Z< G d7„ d8ee:¦  «        Z= G d9„ d:ee:¦  «        Z> G d;„ d<ee:¦  «        Z?g d=¢Z@dS )@é    )ÚCallableN)Únné   )ÚACT2FN)ÚCacheÚDynamicCache)ÚGenerationMixin)Úuse_kernel_forward_from_hub)Úcreate_causal_maskÚ!create_sliding_window_causal_mask)ÚGenericForQuestionAnsweringÚ GenericForSequenceClassificationÚGenericForTokenClassificationÚGradientCheckpointingLayer)ÚBaseModelOutputWithPastÚCausalLMOutputWithPast)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capture_outputsé   )ÚExaone4ConfigÚ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Exaone4RMSNormç�íµ ÷Æ°>ÚepsÚreturnNc                 ó¬   •— t          ¦   «                              ¦   «          t          j        t	          j        |¦  «        ¦  «        | _        || _        dS )z=
        Exaone4RMSNorm is equivalent to T5LayerNorm
        N)ÚsuperÚ__init__r   Ú	ParameterÚtorchÚonesÚweightÚvariance_epsilon)ÚselfÚhidden_sizer%   Ú	__class__s      €ú|/root/private/project/pallet_detection_v2/.venv/lib/python3.11/site-packages/transformers/models/exaone4/modeling_exaone4.pyr)   zExaone4RMSNorm.__init__3   sD   ø€ õ 	‰Œ×ÒÑÔÐÝ”l¥5¤:¨kÑ#:Ô#:Ñ;Ô;ˆŒØ #ˆÔÐÐó    Úhidden_statesc                 ó  — |j         }|                     t          j        ¦  «        }|                     d¦  «                             dd¬¦  «        }|t          j        || j        z   ¦  «        z  }| j        |                     |¦  «        z  S )Né   éÿÿÿÿT)Úkeepdim)	ÚdtypeÚtor+   Úfloat32ÚpowÚmeanÚrsqrtr.   r-   )r/   r4   Úinput_dtypeÚvariances       r2   ÚforwardzExaone4RMSNorm.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:r3   c                 óH   — t          | j        j        ¦  «        › d| j        › �S )Nz, eps=)Útupler-   Úshaper.   )r/   s    r2   Ú
extra_reprzExaone4RMSNorm.extra_reprB   s&   € Ý˜œÔ)Ñ*Ô*ÐIÐI°$Ô2GÐIÐIÐIr3   )r$   )
Ú__name__Ú
__module__Ú__qualname__Úfloatr)   r+   ÚTensorrA   rE   Ú__classcell__©r1   s   @r2   r#   r#   1   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r3   r#   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Exaone4RotaryEmbeddingÚdevicez5.18)ÚversionNÚconfigc                 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_lenrQ   Úrope_parametersrS   Úcompute_default_rope_parametersr   Úattention_scalingr   ÚBufferÚinv_freqÚcloneÚoriginal_inv_freq)r/   rQ   rO   Úrope_init_fnr]   r1   s        €r2   r)   zExaone4RotaryEmbedding.__init__G   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�$Ô(åœ	 (°uÐ=Ñ=Ô=ˆŒÝ!#¤¨8¯>ª>Ñ+;Ô+;ÈÐ!NÑ!NÔ!NˆÔÐÐr3   r&   c                 óä   — | j         d         }t          | dd¦  «        p| j        | j        z  }d}d|t	          j        d|dt          j        ¬¦  «        |z  z  z  }|                     |¦  «        |fS )a¾  
        Computes the inverse frequencies according to the original RoPE implementation
        Args:
            config ([`~transformers.PreTrainedConfig`]):
                The model configuration.
        Returns:
            Tuple of (`torch.Tensor`, `float`), containing the inverse frequencies for the RoPE embeddings and the
            post-processing scaling factor applied to the computed cos/sin (unused in this type of RoPE).
        Ú
rope_thetaÚhead_dimNg      ð?r   r6   ©r9   )rY   Úgetattrr0   Únum_attention_headsr+   ÚarangerI   r:   )rQ   rO   ÚkwargsÚbaseÚdimÚattention_factorr]   s          r2   rZ   z6Exaone4RotaryEmbedding.compute_default_rope_parametersX   sz   € ð Ô% lÔ3ˆÝ�f˜j¨$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$4Ð4Ð4r3   c                 óN  — | j         d d d …d f                              ¦   «                              |j        d         dd¦  «                             |j        ¦  «        }|d d …d d d …f                              ¦   «         }t          |j        j        t          ¦  «        r|j        j        dk    r|j        j        nd}t          |d¬¦  «        5  |                     ¦   «         |                     ¦   «         z   
                    dd¦  «        }t          j        ||fd¬	¦  «        }|                     ¦   «         | j        z  }|                     ¦   «         | j        z  }	d d d ¦  «         n# 1 swxY w Y   |                     |j        ¬
¦  «        |	                     |j        ¬
¦  «        fS )Nr   r7   r   ÚmpsÚcpuF)Údevice_typeÚenabledr6   ©rj   rd   )r]   rI   ÚexpandrD   r:   rO   Ú
isinstanceÚtypeÚstrr   Ú	transposer+   ÚcatÚcosr[   Úsinr9   )
r/   ÚxÚposition_idsÚinv_freq_expandedÚposition_ids_expandedro   ÚfreqsÚembrx   ry   s
             r2   rA   zExaone4RotaryEmbedding.forwardl   s·  € ð !œM¨$°°°°4¨-Ô8×>Ò>Ñ@Ô@×GÒGÈÔHZÐ[\ÔH]Ð_aÐcdÑeÔe×hÒhÐijÔiqÑrÔrÐØ ,¨Q¨Q¨Q°°a°a°a¨ZÔ 8× >Ò >Ñ @Ô @Ðå'1°!´(´-ÅÑ'EÔ'EÐkÈ!Ì(Ì-Ð[`ÒJ`ÐJ`�a”h”m�mÐfkˆÝ¨¸UÐCÑCÔCð 	5ð 	5Ø&×,Ò,Ñ.Ô.Ð1F×1LÒ1LÑ1NÔ1NÑN×YÒYÐZ[Ð]^Ñ_Ô_ˆEÝ”)˜U E˜N°Ð3Ñ3Ô3ˆCØ—'’'‘)”)˜dÔ4Ñ4ˆCØ—'’'‘)”)˜dÔ4Ñ4ˆCð		5ð 	5ð 	5ñ 	5ô 	5ð 	5ð 	5ð 	5ð 	5ð 	5ð 	5øøøð 	5ð 	5ð 	5ð 	5ð �vŠv˜AœGˆvÑ$Ô$ c§f¢f°1´7 fÑ&;Ô&;Ð;Ð;s   ÃBE&Å&E*Å-E*©N)rF   rG   rH   r   r    r)   ÚstaticmethodrC   r+   rJ   rI   rZ   Úno_gradr   rA   rK   rL   s   @r2   rN   rN   F   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 <r3   rN   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..Nr7   r6   rq   )rD   r+   rw   )rz   Úx1Úx2s      r2   Úrotate_halfr†   |   s]   € à	
ˆ3Ð"�!”'˜"”+ Ñ"Ð"Ð"Ô	#€BØ	
ˆ3�”˜”˜qÑ Ð"Ð"Ð"Ô	#€BÝŒ9�r�c˜2�Y BÐ'Ñ'Ô'Ð'r3   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	unsqueezer†   )ÚqÚkrx   ry   Úunsqueeze_dimÚq_embedÚk_embeds          r2   Úapply_rotary_pos_embr�   ƒ   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r3   r4   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)rD   rr   Úreshape)r4   r�   ÚbatchÚnum_key_value_headsÚslenrc   s         r2   Ú	repeat_kvr–   �   s„   € ð
 2?Ô1DÑ.€EÐ  hØ�‚z€zØÐØ! ! ! ! Q Q Q¨¨a¨a¨a°°°Ð"2Ô3×:Ò:¸5ÐBUÐW\Ð^bÐdlÑmÔm€MØ× Ò  Ð(;¸eÑ(CÀTÈ8ÑTÔTÐTr3   ç        ÚmoduleÚqueryÚkeyÚvalueÚattention_maskÚscalingÚdropoutrh   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 )Nr6   r   r7   )rj   r9   )ÚpÚtrainingr   )r–   Únum_key_value_groupsr+   Úmatmulrv   r   Ú
functionalÚsoftmaxr;   r:   r9   rž   r¡   Ú
contiguous)r˜   r™   rš   r›   rœ   r�   rž   rh   Ú
key_statesÚvalue_statesÚattn_weightsÚattn_outputs               r2   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$Ð$r3   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ej        dz  de	dz  d	e
e         d
eej        ej        dz  eej                 dz  f         fd„Zˆ xZS )ÚExaone4AttentionrQ   Ú	layer_idxc                 óÒ  •— t          ¦   «                              ¦   «          || _        || _        |j        | _        |j        | _        |j        | _        t          |d|j        |j        z  ¦  «        | _        |j        |j        z  | _	        |j
        | _
        d| _        | j        dz  | _        |j        | _        |j        | _        t          |d¦  «        r|j        |         nd }|dk    | _        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¬¦  «        | _        t1          | j        |j        ¬¦  «        | _        t1          | j        |j        ¬¦  «        | _        d S )	Nrc   Tg      à¿Úlayer_typesÚsliding_attentionF©Úbias©r%   )r(   r)   rQ   r®   rf   r”   r0   re   rc   r¢   Úattention_dropoutÚ	is_causalr�   Úsliding_windowÚsliding_window_patternÚhasattrr°   Ú
is_slidingr   ÚLinearÚq_projÚk_projÚv_projÚo_projr#   Úrms_norm_epsÚq_normÚk_norm)r/   rQ   r®   Ú
layer_typer1   s       €r2   r)   zExaone4Attention.__init__Ã   s¬  ø€ Ý‰Œ×ÒÑÔÐØˆŒØ"ˆŒØ#)Ô#=ˆÔ Ø#)Ô#=ˆÔ Ø!Ô-ˆÔÝ ¨
°FÔ4FÈ&ÔJdÑ4dÑeÔeˆŒØ$*Ô$>À&ÔB\Ñ$\ˆÔ!Ø!'Ô!9ˆÔØˆŒØ”} dÑ*ˆŒØ$Ô3ˆÔØ&,Ô&CˆÔ#Ý6=¸fÀmÑ6TÔ6TÐ^�VÔ'¨	Ô2Ð2ÐZ^ˆ
Ø$Ð(;Ò;ˆŒå”i Ô 0°$Ô2JÈTÌ]Ñ2ZÐafÐgÑgÔgˆŒÝ”i Ô 0°$Ô2JÈTÌ]Ñ2ZÐafÐgÑgÔgˆŒÝ”i Ô 0°$Ô2JÈTÌ]Ñ2ZÐafÐgÑgÔgˆŒÝ”i Ô 8¸4¼=Ñ HÈ$ÔJZÐafÐgÑgÔgˆŒå$ T¤]¸Ô8KÐLÑLÔLˆŒÝ$ T¤]¸Ô8KÐLÑLÔLˆŒˆˆr3   Nr4   Úposition_embeddingsrœ   Úpast_key_valuesrh   r&   c                 ó°  — |j         d d…         }g |¢d‘| j        ‘R }|                      |¦  «                             |¦  «                             dd¦  «        }|                      |¦  «                             |¦  «                             dd¦  «        }	|                      |¦  «                             |¦  «                             dd¦  «        }
|                      |¦  «        }|                      |	¦  «        }	|\  }}| j	        �| j
        rt          ||	||¦  «        \  }}	|�|                     |	|
| j        ¦  «        \  }	}
t          j        | j        j        t$          ¦  «        } || ||	|
|f| j        sdn| j        | j        | j
        r| j	        nd dœ|¤Ž\  }} |j        g |¢d‘R Ž                      ¦   «         }|                      |¦  «        }||fS )Nr7   r   r6   r—   )rž   r�   r·   )rD   rc   r¼   Úviewrv   r½   r¾   rÁ   rÂ   r·   rº   r�   Úupdater®   r   Úget_interfacerQ   Ú_attn_implementationr«   r¡   rµ   r�   r’   r¦   r¿   )r/   r4   rÄ   rœ   rÅ   rh   Úinput_shapeÚhidden_shapeÚquery_statesr§   r¨   rx   ry   Úattention_interfacerª   r©   s                   r2   rA   zExaone4Attention.forwardÜ   s  € ð $Ô)¨#¨2¨#Ô.ˆØ8˜Ð8 bÐ8¨$¬-Ð8Ð8ˆà—{’{ =Ñ1Ô1×6Ò6°|ÑDÔD×NÒNÈqÐRSÑTÔTˆØ—[’[ Ñ/Ô/×4Ò4°\ÑBÔB×LÒLÈQÐPQÑRÔRˆ
Ø—{’{ =Ñ1Ô1×6Ò6°|ÑDÔD×NÒNÈqÐRSÑTÔTˆð —{’{ <Ñ0Ô0ˆØ—[’[ Ñ,Ô,ˆ
à&‰ˆˆSàÔÐ&¨$¬/Ð&Ý';¸LÈ*ÐVYÐ[^Ñ'_Ô'_Ñ$ˆL˜*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”LØ26´/ÐK˜4Ô.Ð.Àtð
%
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(r3   )NN)rF   rG   rH   r    Úintr)   r+   rJ   rC   r   r   r   rA   rK   rL   s   @r2   r­   r­   Â   sð   ø€ € € € € ðM˜}ð M¸ð Mð Mð Mð Mð Mð Mð: /3Ø(,ð-)ð -)à”|ð-)ð # 5¤<°´Ð#=Ô>ð-)ð œ tÑ+ð	-)ð
  ™ð-)ð Ð+Ô,ð-)ð 
ˆuŒ|˜Uœ\¨DÑ0°%¸¼Ô2EÈÑ2LÐLÔ	Mð-)ð -)ð -)ð -)ð -)ð -)ð -)ð -)r3   r­   c                   ó$   ‡ — e Zd Zˆ fd„Zd„ Zˆ xZS )Ú
Exaone4MLPc                 ó˜  •— t          ¦   «                              ¦   «          || _        |j        | _        |j        | _        t          j        | j        | j        d¬¦  «        | _        t          j        | j        | j        d¬¦  «        | _        t          j        | j        | j        d¬¦  «        | _	        t          |j                 | _        d S ©NFr²   )r(   r)   rQ   r0   Úintermediate_sizer   r»   Ú	gate_projÚup_projÚ	down_projr   Ú
hidden_actÚact_fn©r/   rQ   r1   s     €r2   r)   zExaone4MLP.__init__  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r3   c                 ó¨   — |                       |                      |                      |¦  «        ¦  «        |                      |¦  «        z  ¦  «        }|S r€   )r×   rÙ   rÕ   rÖ   )r/   rz   r×   s      r2   rA   zExaone4MLP.forward  sA   € Ø—N’N 4§;¢;¨t¯~ª~¸aÑ/@Ô/@Ñ#AÔ#AÀDÇLÂLÐQRÁOÄOÑ#SÑTÔTˆ	ØÐr3   )rF   rG   rH   r)   rA   rK   rL   s   @r2   rÑ   rÑ     sG   ø€ € € € € ð0ð 0ð 0ð 0ð 0ðð ð ð ð ð ð r3   rÑ   c                   óÒ   ‡ — e Zd Zdedefˆ fd„Z	 	 	 	 	 ddej        dej        dz  dej        dz  d	e	dz  d
e
dz  deej        ej        f         dz  dee         dej        fd„Zˆ xZS )ÚExaone4DecoderLayerrQ   r®   c                 ó4  •— t          ¦   «                              ¦   «          |j        | _        t          ||¬¦  «        | _        t          |¦  «        | _        t          |j        |j        ¬¦  «        | _	        t          |j        |j        ¬¦  «        | _
        d S )N)rQ   r®   r´   )r(   r)   r0   r­   Ú	self_attnrÑ   Úmlpr#   rÀ   Úpost_attention_layernormÚpost_feedforward_layernorm)r/   rQ   r®   r1   s      €r2   r)   zExaone4DecoderLayer.__init__  s„   ø€ Ý‰Œ×ÒÑÔÐØ!Ô-ˆÔÝ)°À9ÐMÑMÔMˆŒå˜fÑ%Ô%ˆŒÝ(6°vÔ7IÈvÔObÐ(cÑ(cÔ(cˆÔ%Ý*8¸Ô9KÐQWÔQdÐ*eÑ*eÔ*eˆÔ'Ð'Ð'r3   NFr4   rœ   r{   rÅ   Ú	use_cacherÄ   rh   r&   c           
      óÎ   — |} | j         d||||||dœ|¤Ž\  }}	|                      |¦  «        }||z   }|}|                      |¦  «        }|                      |¦  «        }||z   }|S )N)r4   rœ   r{   rÅ   rã   rÄ   © )rß   rá   rà   râ   )
r/   r4   rœ   r{   rÅ   rã   rÄ   rh   ÚresidualÚ_s
             r2   rA   zExaone4DecoderLayer.forward&  s¡   € ð !ˆØ)˜4œ>ð 
Ø'Ø)Ø%Ø+ØØ 3ð
ð 
ð ð
ð 
Ñˆ�qð ×5Ò5°mÑDÔDˆØ  =Ñ0ˆð !ˆØŸš Ñ/Ô/ˆØ×7Ò7¸ÑFÔFˆØ  =Ñ0ˆØÐr3   )NNNFN)rF   rG   rH   r    rÏ   r)   r+   rJ   Ú
LongTensorr   ÚboolrC   r   r   rA   rK   rL   s   @r2   rÝ   rÝ     sÿ   ø€ € € € € ðf˜}ð f¸ð fð fð fð fð fð fð /3Ø04Ø(,Ø!&ØHLðð à”|ðð œ tÑ+ðð Ô&¨Ñ-ð	ð
  ™ðð ˜$‘;ðð # 5¤<°´Ð#=Ô>ÀÑEðð Ð+Ô,ðð 
Œðð ð ð ð ð ð ð r3   rÝ   c                   óP   — 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œZeZdS )ÚExaone4PreTrainedModelrQ   ÚmodelTrÝ   rÅ   )r4   Ú
attentionsN)rF   rG   rH   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_backendrÝ   r­   Ú_can_record_outputsÚconfig_classrå   r3   r2   rë   rë   E  sq   € € € € € € àÐÐÑØÐØ&*Ð#Ø.Ð/ÐØ#4Ð"5ÐØÐØ€NØÐà!ÐØ"&Ðà,Ø&ðð Ðð !€L€L€Lr3   rë   c                   óØ   ‡ — e Zd 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dz  d
ee         deez  fd„¦   «         ¦   «         Zˆ xZS )ÚExaone4ModelrQ   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 rå   )rÝ   )Ú.0r®   rQ   s     €r2   ú
<listcomp>z)Exaone4Model.__init__.<locals>.<listcomp>b  s$   ø€ ÐeÐeÐe¸	Õ  ¨Ñ3Ô3ÐeÐeÐer3   r´   ©rQ   F)r(   r)   Úpad_token_idÚpadding_idxÚ
vocab_sizer   Ú	Embeddingr0   Úembed_tokensÚ
ModuleListÚrangeÚnum_hidden_layersÚlayersr#   rÀ   ÚnormrN   Ú
rotary_embÚgradient_checkpointingÚ	post_initrÚ   s    `€r2   r)   zExaone4Model.__init__[  sÔ   øø€ Ý‰Œ×Ò˜Ñ Ô Ð Ø!Ô.ˆÔØ Ô+ˆŒåœL¨Ô):¸FÔ<NÐPTÔP`ÑaÔaˆÔÝ”mØeÐeÐeÐeÅUÈ6ÔKcÑEdÔEdÐeÑeÔeñ
ô 
ˆŒõ # 6Ô#5¸6Ô;NÐOÑOÔOˆŒ	Ý0¸Ð?Ñ?Ô?ˆŒØ&+ˆÔ#ð 	�ŠÑÔÐÐÐr3   NÚ	input_idsrœ   r{   rÅ   Úinputs_embedsrã   rh   r&   c           
      óæ  — |d u |d uz  rt          d¦  «        ‚|€|                      |¦  «        }|r|€t          | j        ¬¦  «        }|€V|�|                     ¦   «         nd}t          j        |j        d         |j        ¬¦  «        |z   }| 	                    d¦  «        }t          |x}	t          ¦  «        s8| j        ||||dœ}
dt          di |
¤Ži}	d| j        j        v rt          di |
¤Ž|	d<   |}|                      ||¦  «        }t!          | j        ¦  «        D ],\  }}| j        j        |         } ||f|	|         ||||d	œ|¤Ž}Œ-|                      |¦  «        }t'          ||r|nd ¬
¦  «        S )Nz:You must specify exactly one of input_ids or inputs_embedsr   r   r   )rO   )rQ   r  rœ   rÅ   r{   Úfull_attentionr±   )rœ   r{   rÅ   rã   rÄ   )Úlast_hidden_staterÅ   rå   )Ú
ValueErrorr  r   rQ   Úget_seq_lengthr+   rg   rD   rO   r‰   rs   Údictr   r°   r   r  Ú	enumerater	  r
  r   )r/   r  rœ   r{   rÅ   r  rã   rh   Úpast_seen_tokensÚcausal_mask_mappingÚmask_kwargsr4   rÄ   ÚiÚdecoder_layerrÃ   s                   r2   rA   zExaone4Model.forwardk  s   € ð ˜Ð -°tÐ";Ñ<ð 	[ÝÐYÑZÔZÐZàÐ Ø ×-Ò-¨iÑ8Ô8ˆMàð 	?˜Ð0Ý*°$´+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4ˆLõ °Ð?Ð-ÅÑFÔFð 	lð œ+Ø!.Ø"0Ø#2Ø ,ðð ˆKð !Õ"4Ð"CÐ"C°{Ð"CÐ"Cð#Ðð # d¤kÔ&=Ð=Ð=Ý;\Ð;kÐ;kÐ_jÐ;kÐ;kÐ#Ð$7Ñ8à%ˆØ"Ÿošo¨m¸\ÑJÔJÐå )¨$¬+Ñ 6Ô 6ð 
	ð 
	ÑˆAˆ}ØœÔ0°Ô3ˆJØ)˜MØðà2°:Ô>Ø)Ø /Ø#Ø$7ðð ð ðð ˆMˆMð Ÿ	š	 -Ñ0Ô0ˆå&Ø+Ø/8ÐB˜O˜O¸dð
ñ 
ô 
ð 	
r3   )NNNNNN)rF   rG   rH   r    r)   r   r   r+   rè   rJ   r   ÚFloatTensorré   r   r   rC   r   rA   rK   rL   s   @r2   rû   rû   Y  s	  ø€ € € € € ð˜}ð ð ð ð ð ð ð   Øð .2Ø.2Ø04Ø(,Ø26Ø!%ð=
ð =
àÔ# dÑ*ð=
ð œ tÑ+ð=
ð Ô&¨Ñ-ð	=
ð
  ™ð=
ð Ô(¨4Ñ/ð=
ð ˜$‘;ð=
ð Ð+Ô,ð=
ð 
Ð(Ñ	(ð=
ð =
ð =
ñ „_ñ  Ôð=
ð =
ð =
ð =
ð =
r3   rû   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e
j        z  dee         defd„¦   «         ¦   «         Zˆ xZS )ÚExaone4ForCausalLMzlm_head.weightzmodel.embed_tokens.weightÚlm_headÚcolwise_gather_outputr4   ÚlogitsÚkeep_full_weightc                 óþ   •— t          ¦   «                              |¦  «         t          |¦  «        | _        |j        | _        t          j        |j        |j        d¬¦  «        | _        |  	                    ¦   «          d S rÓ   )
r(   r)   rû   rì   r  r   r»   r0   r  r  rÚ   s     €r2   r)   zExaone4ForCausalLM.__init__´  sj   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ð 	�ŠÑÔÐÐÐr3   Nr   r  rœ   r{   rÅ   r  Úlabelsrã   Úlogits_to_keeprh   r&   c	           
      óP  —  | j         d||||||dœ|	¤Ž}
|
j        }t          |t          ¦  «        rt	          | d¦  «        n|}|                      |dd…|dd…f         ¦  «        }d}|� | j        d||| j        j        dœ|	¤Ž}t          |||
j
        |
j        |
j        ¬¦  «        S )u�  
        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 AutoModelForCausalLM, AutoTokenizer
        >>> model = AutoModelForCausalLM.from_pretrained("LGAI-EXAONE/EXAONE-4.0-32B")
        >>> tokenizer = AutoTokenizer.from_pretrained("LGAI-EXAONE/EXAONE-4.0-32B")

        >>> prompt = "Explain how wonderful you are"
        >>> messages = [
            {"role": "system", "content": "You are a helpful assistant."},
            {"role": "user", "content": prompt}
        ]
        >>> input_ids = tokenizer.apply_chat_template(
            messages,
            tokenize=True,
            add_generation_prompt=True,
            return_tensors="pt",
            enable_thinking=False,
        )

        >>> output = model.generate(input_ids, max_new_tokens=128)
        >>> tokenizer.decode(output[0], skip_special_tokens=False)
        "[|system|]\nYou are a helpful assistant.[|endofturn|]\n[|user|]\nExplain how wonderful you are[|endofturn|]\n[|assistant|]\n<think>\n\n</think>\n\nOh, thank you for such a kind and lovely question! ðŸ˜Š  \n\nIâ€™m *so* wonderful because Iâ€™m here to make your life easier, brighter, and more fun! Whether you need help with:  \n\nâœ¨ **Learning** â€“ I can explain anything, from quantum physics to baking the perfect cake!  \nðŸ’¡ **Creativity** â€“ Need a poem, story, or a wild idea? Iâ€™ve got you covered!  \nðŸ¤– **Problem-solving** â€“ Stuck on a math problem or a tricky decision? Iâ€™ll help you figure it out"
        ```
        )r  rœ   r{   rÅ   r  rã   N)r!  r$  r  )Úlossr!  rÅ   r4   rí   rå   )rì   r  rs   rÏ   Úslicer  Úloss_functionrQ   r  r   rÅ   r4   rí   )r/   r  rœ   r{   rÅ   r  r$  rã   r%  rh   Úoutputsr4   Úslice_indicesr!  r'  s                  r2   rA   zExaone4ForCausalLM.forward½  sõ   € ðZ ,6¨4¬:ð ,
ØØ)Ø%Ø+Ø'Øð,
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%Ðp¨V¸FÈtÌ{ÔOeÐpÐpÐioÐpÐpˆDå%ØØØ#Ô3Ø!Ô/ØÔ)ð
ñ 
ô 
ð 	
r3   )NNNNNNNr   )rF   rG   rH   Ú_tied_weights_keysÚ_tp_planÚ_pp_planÚ
_fsdp_planr)   r   r   r+   rè   rJ   r   r  ré   rÏ   r   r   r   rA   rK   rL   s   @r2   r  r  ­  si  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-.ðD
ð D
àÔ# dÑ*ðD
ð œ tÑ+ðD
ð Ô&¨Ñ-ð	D
ð
  ™ðD
ð Ô(¨4Ñ/ðD
ð Ô  4Ñ'ðD
ð ˜$‘;ðD
ð ˜eœlÑ*ðD
ð Ð+Ô,ðD
ð 
 ðD
ð D
ð D
ñ „^ñ ÔðD
ð D
ð D
ð D
ð D
r3   r  c                   ó   — e Zd ZdS )Ú Exaone4ForSequenceClassificationN©rF   rG   rH   rå   r3   r2   r1  r1    ó   € € € € € Ø€Dr3   r1  c                   ó   — e Zd ZdS )ÚExaone4ForTokenClassificationNr2  rå   r3   r2   r5  r5  
  r3  r3   r5  c                   ó   — e Zd ZdZdS )ÚExaone4ForQuestionAnsweringÚtransformerN)rF   rG   rH   rï   rå   r3   r2   r7  r7    s   € € € € € Ø%ÐÐÐr3   r7  )rë   rû   r  r1  r5  r7  )r   )r—   )AÚcollections.abcr   r+   r   Úactivationsr   Úcache_utilsr   r   Ú
generationr	   Úintegrationsr
   Úmasking_utilsr   r   Úmodeling_layersr   r   r   r   Úmodeling_outputsr   r   Úmodeling_rope_utilsr   r   Úmodeling_utilsr   r   Úprocessing_utilsr   Úutilsr   r   r   Úutils.deprecationr   Úutils.genericr   r   Úutils.output_capturingr   Úconfiguration_exaone4r    ÚModuler#   rN   r†   r�   rJ   rÏ   r–   rI   r«   r­   rÑ   rÝ   rë   rû   r  r1  r5  r7  Ú__all__rå   r3   r2   ú<module>rK     së  ðð, %Ð $Ð $Ð $Ð $Ð $à €€€Ø Ð Ð Ð Ð Ð à !Ð !Ð !Ð !Ð !Ð !Ø .Ð .Ð .Ð .Ð .Ð .Ð .Ð .Ø )Ð )Ð )Ð )Ð )Ð )Ø 7Ð 7Ð 7Ð 7Ð 7Ð 7Ø RÐ RÐ RÐ RÐ RÐ RÐ RÐ Rðð ð ð ð ð ð ð ð ð ð ð ð PÐ OÐ OÐ OÐ OÐ OÐ OÐ OØ 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 5Ð 5Ð 5Ð 5Ð 5Ð 5Ø 0Ð 0Ð 0Ð 0Ð 0Ð 0ð Ð˜YÑ'Ô'ðJð Jð Jð Jð J�R”Yñ Jô Jñ (Ô'ðJð(3<ð 3<ð 3<ð 3<ð 3<˜RœYñ 3<ô 3<ð 3<ðl(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 %ð2G)ð G)ð G)ð G)ð G)�r”yñ G)ô G)ð G)ðTð ð ð ð �”ñ ô ð ð &ð &ð &ð &ð &Ð4ñ &ô &ð &ðR ð!ð !ð !ð !ð !˜_ñ !ô !ñ „ð!ð& ðP
ð P
ð P
ð P
ð P
Ð)ñ P
ô P
ñ „ðP
ðf ðU
ð U
ð U
ð U
ð U
Ð/°ñ U
ô U
ñ „ðU
ðp	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 €€€r3   