§
    ‚Štj¬[  ã                   óL  — d dl mZ 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mZmZ dd	lmZ dd
lmZ ddlmZmZ ddlmZmZ ddlmZmZ ddlm Z  ddl!m"Z"m#Z#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„ Z/ ed¦  «        d7d„¦   «         Z0dej1        de2dej1        fd„Z3	 d8d!ej,        d"ej1        d#ej1        d$ej1        d%ej1        dz  d&e4d'e4d(e e"         fd)„Z5 ee0¦  «         G d*„ d+ej,        ¦  «        ¦   «         Z6 G d,„ d-ej,        ¦  «        Z7 G d.„ d/e¦  «        Z8e# G d0„ d1e¦  «        ¦   «         Z9e# G d2„ d3e9¦  «        ¦   «         Z:e# G d4„ d5e9e¦  «        ¦   «         Z;g d6¢Z<dS )9é    )ÚCallable)ÚOptionalNé   )ÚACT2FN)ÚCacheÚDynamicCache)ÚGenerationMixin)Úuse_kernel_forward_from_hubÚuse_kernel_func_from_hubÚuse_kernelized_func)Úcreate_causal_mask)Ú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maybe_autocastÚmerge_with_config_defaults)Úcapture_outputsé   )ÚHyperCLOVAXConfigÚ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HyperCLOVAXRMSNormç�íµ ÷Æ°>ÚepsÚreturnNc                 ó¬   •— t          ¦   «                              ¦   «          t          j        t	          j        |¦  «        ¦  «        | _        || _        dS )zA
        HyperCLOVAXRMSNorm is equivalent to T5LayerNorm
        N)ÚsuperÚ__init__ÚnnÚ	ParameterÚtorchÚonesÚweightÚvariance_epsilon)ÚselfÚhidden_sizer"   Ú	__class__s      €úr/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/transformers/models/hyperclovax/modeling_hyperclovax.pyr&   zHyperCLOVAXRMSNorm.__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rsqrtr,   r+   )r-   r2   Úinput_dtypeÚvariances       r0   ÚforwardzHyperCLOVAXRMSNorm.forward5   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:r1   c                 óH   — t          | j        j        ¦  «        › d| j        › �S )Nz, eps=)Útupler+   Úshaper,   )r-   s    r0   Ú
extra_reprzHyperCLOVAXRMSNorm.extra_repr<   s&   € Ý˜œÔ)Ñ*Ô*ÐIÐI°$Ô2GÐIÐIÐIr1   )r!   )
Ú__name__Ú
__module__Ú__qualname__Úfloatr&   r)   ÚTensorr?   rC   Ú__classcell__©r/   s   @r0   r    r    +   sŒ   ø€ € € € € ð$ð $¨ð $¸$ð $ð $ð $ð $ð $ð $ð; U¤\ð ;°e´lð ;ð ;ð ;ð ;ðJð Jð Jð Jð Jð Jð Jr1   r    c                   óÔ   ‡ — e Zd ZU ej        ed<   ddefˆ fd„Ze	 	 	 ddedz  de	d         de
dz  ded	ef         fd
„¦   «         Z ej        ¦   «         ed„ ¦   «         ¦   «         Zˆ xZS )ÚHyperCLOVAXRotaryEmbeddingÚinv_freqNÚconfigc                 ó²  •— t          ¦   «                              ¦   «          |j        | _        |j        | _        || _        | j        j        d         | _        | j        }| j        dk    rt          | j                 } || j        |¦  «        \  }| _
        |                      d|d¬¦  «         |                      d|                     ¦   «         d¬¦  «         d S )NÚ	rope_typeÚdefaultrM   F)Ú
persistentÚoriginal_inv_freq)r%   r&   Úmax_position_embeddingsÚmax_seq_len_cachedÚoriginal_max_seq_lenrN   Úrope_parametersrP   Úcompute_default_rope_parametersr   Úattention_scalingÚregister_bufferÚclone)r-   rN   ÚdeviceÚrope_init_fnrM   r/   s        €r0   r&   z#HyperCLOVAXRotaryEmbedding.__init__C   sÊ   ø€ Ý‰Œ×ÒÑÔÐØ"(Ô"@ˆÔØ$*Ô$BˆÔ!àˆŒàœÔ4°[ÔAˆŒØ!%Ô!EˆØŒ>˜YÒ&Ð&Ý.¨t¬~Ô>ˆLØ+7¨<¸¼ÀVÑ+LÔ+LÑ(ˆ�$Ô(à×Ò˜Z¨¸eÐÑDÔDÐDØ×ÒÐ0°(·.².Ñ2BÔ2BÈuÐÑUÔUÐUÐUÐUr1   r\   ztorch.deviceÚseq_lenr#   ztorch.Tensorc                 óü   — | j         d         }t          | dd¦  «        p| j        | j        z  }d}d|t	          j        d|dt          j        ¬¦  «                             |t          j        ¬¦  «        |z  z  z  }||fS )	a¨  
        Computes the inverse frequencies according to the original RoPE implementation
        Args:
            config ([`~transformers.PreTrainedConfig`]):
                The model configuration.
            device (`torch.device`):
                The device to use for initialization of the inverse frequencies.
            seq_len (`int`, *optional*):
                The current sequence length. Unused for this type of RoPE.
        Returns:
            Tuple of (`torch.Tensor`, `float`), containing the inverse frequencies for the RoPE embeddings and the
            post-processing scaling factor applied to the computed cos/sin (unused in this type of RoPE).
        Ú
rope_thetaÚhead_dimNg      ð?r   r4   ©r7   )r\   r7   )	rW   Úgetattrr.   Únum_attention_headsr)   ÚarangeÚint64r8   rG   )rN   r\   r^   ÚbaseÚdimÚattention_factorrM   s          r0   rX   z:HyperCLOVAXRotaryEmbedding.compute_default_rope_parametersS   sŒ   € ð& Ô% lÔ3ˆÝ�f˜j¨$Ñ/Ô/Ðc°6Ô3EÈÔIcÑ3cˆàÐð Ø•U”\ ! S¨!µ5´;Ð?Ñ?Ô?×BÒBÈ&ÕX]ÔXcÐBÑdÔdÐgjÑjÑkñ
ˆð Ð)Ð)Ð)r1   c                 óN  — | j         d d d …d f                              ¦   «                              |j        d         dd¦  «                             |j        ¦  «        }|d d …d d d …f                              ¦   «         }t          |j        j        t          ¦  «        r|j        j        dk    r|j        j        nd}t          |d¬¦  «        5  |                     ¦   «         |                     ¦   «         z   
                    dd¦  «        }t          j        ||fd¬	¦  «        }|                     ¦   «         | j        z  }|                     ¦   «         | j        z  }	d d d ¦  «         n# 1 swxY w Y   |                     |j        ¬
¦  «        |	                     |j        ¬
¦  «        fS )Nr   r5   r   ÚmpsÚcpuF)Údevice_typeÚenabledr4   ©rh   rb   )rM   rG   ÚexpandrB   r8   r\   Ú
isinstanceÚtypeÚstrr   Ú	transposer)   ÚcatÚcosrY   Úsinr7   )
r-   ÚxÚposition_idsÚinv_freq_expandedÚposition_ids_expandedrm   ÚfreqsÚembrv   rw   s
             r0   r?   z"HyperCLOVAXRotaryEmbedding.forwardq   s·  € ð !œM¨$°°°°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©NNN)rD   rE   rF   r)   rH   Ú__annotations__r   r&   Ústaticmethodr   ÚintrA   rG   rX   Úno_gradr   r?   rI   rJ   s   @r0   rL   rL   @   sú   ø€ € € € € € ØŒlÐÐÑðVð VÐ0ð Vð Vð Vð Vð Vð Vð  à+/Ø+/Ø"ð*ð *Ø! DÑ(ð*à˜Ô(ð*ð �t‘ð*ð 
ˆ~˜uÐ$Ô	%ð	*ð *ð *ñ „\ð*ð: €U„]�_„_Øð<ð <ñ Ôñ „_ð<ð <ð <ð <ð <r1   rL   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..Nr5   r4   ro   )rB   r)   ru   )rx   Úx1Úx2s      r0   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'r1   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krv   rw   Úunsqueeze_dimÚq_embedÚk_embeds          r0   Úapply_rotary_pos_embr�   ˆ   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r1   r2   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)rB   rp   Úreshape)r2   r‘   ÚbatchÚnum_key_value_headsÚslenra   s         r0   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Tr1   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 )Nr4   r   r5   )rh   r7   )ÚpÚtrainingr   )r—   Únum_key_value_groupsr)   Úmatmulrt   r'   Ú
functionalÚsoftmaxr9   r8   r7   rŸ   r£   Ú
contiguous)r™   rš   r›   rœ   r�   rž   rŸ   r    Ú
key_statesÚvalue_statesÚattn_weightsÚattn_outputs               r0   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$Ð$r1   c                   óÖ   ‡ — e Zd ZdZddededz  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
dz  d
ee         de	ej        ej        f         fd„Zˆ xZS )ÚHyperCLOVAXAttentionz=Multi-headed attention from 'Attention Is All You Need' paperNrN   Ú	layer_idxc                 ó¨  •— t          ¦   «                              ¦   «          || _        || _        t	          |d|j        |j        z  ¦  «        | _        |j        |j        z  | _	        |j
        | _        |j        | _        d| _        t          j        |j        |j        | j        z  |j        ¬¦  «        | _        t          j        |j        |j        | j        z  |j        ¬¦  «        | _        t          j        |j        |j        | j        z  |j        ¬¦  «        | _        t          j        |j        | j        z  |j        |j        ¬¦  «        | _        d S )Nra   T©Úbias)r%   r&   rN   r°   rc   r.   rd   ra   r•   r¤   Úattention_multiplierrž   Úattention_dropoutÚ	is_causalr'   ÚLinearÚattention_biasÚq_projÚk_projÚv_projÚo_proj©r-   rN   r°   r/   s      €r0   r&   zHyperCLOVAXAttention.__init__Ë   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$\ˆÔ!ØÔ2ˆŒØ!'Ô!9ˆÔØˆŒå”iØÔ Ô :¸T¼]Ñ JÐQWÔQfð
ñ 
ô 
ˆŒõ ”iØÔ Ô :¸T¼]Ñ JÐQWÔQfð
ñ 
ô 
ˆŒõ ”iØÔ Ô :¸T¼]Ñ JÐQWÔQfð
ñ 
ô 
ˆŒõ ”iØÔ&¨¬Ñ6¸Ô8JÐQWÔQfð
ñ 
ô 
ˆŒˆˆr1   r2   Úposition_embeddingsr�   Úpast_key_valuesr    r#   c                 ó"  — |j         d d…         }g |¢d‘| j        ‘R }|                      |¦  «                             |¦  «                             dd¦  «        }|                      |¦  «                             |¦  «                             dd¦  «        }	|                      |¦  «                             |¦  «                             dd¦  «        }
|\  }}t          ||	||¦  «        \  }}	|�|                     |	|
| j	        ¦  «        \  }	}
t          j        | j        j        t          ¦  «        } || ||	|
|f| j        sdn| j        | j        dœ|¤Ž\  }} |j        g |¢d‘R Ž                      ¦   «         }|                      |¦  «        }||fS )Nr5   r   r4   r˜   )rŸ   rž   )rB   ra   r¹   Úviewrt   rº   r»   r�   Úupdater°   r   Úget_interfacerN   Ú_attn_implementationr­   r£   rµ   rž   r“   r¨   r¼   )r-   r2   r¾   r�   r¿   r    Úinput_shapeÚhidden_shapeÚquery_statesr©   rª   rv   rw   Úattention_interfacer¬   r«   s                   r0   r?   zHyperCLOVAXAttention.forwardâ   sÀ  € ð $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”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(r1   r~   r   )rD   rE   rF   Ú__doc__r   r‚   r&   r)   rH   rA   r   r   r   r?   rI   rJ   s   @r0   r¯   r¯   Ç   sï   ø€ € € € € àGÐGð
ð 
Ð0ð 
¸SÀ4¹Zð 
ð 
ð 
ð 
ð 
ð 
ð4 IMØ.2Ø(,ð&)ð &)à”|ð&)ð # 5¤<°´Ð#=Ô>ÀÑEð&)ð œ tÑ+ð	&)ð
  ™ð&)ð Ð+Ô,ð&)ð 
ˆuŒ|˜Uœ\Ð)Ô	*ð&)ð &)ð &)ð &)ð &)ð &)ð &)ð &)r1   r¯   c                   ó$   ‡ — e Zd Zˆ fd„Zd„ Zˆ xZS )ÚHyperCLOVAXMLPc                 ó¶  •— t          ¦   «                              ¦   «          || _        |j        | _        |j        | _        t          j        | j        | j        |j        ¬¦  «        | _        t          j        | j        | j        |j        ¬¦  «        | _	        t          j        | j        | j        |j        ¬¦  «        | _
        t          |j                 | _        d S )Nr²   )r%   r&   rN   r.   Úintermediate_sizer'   r·   Úmlp_biasÚ	gate_projÚup_projÚ	down_projr   Ú
hidden_actÚact_fn©r-   rN   r/   s     €r0   r&   zHyperCLOVAXMLP.__init__  s¯   ø€ Ý‰Œ×ÒÑÔÐØˆŒØ!Ô-ˆÔØ!'Ô!9ˆÔÝœ 4Ô#3°TÔ5KÐRXÔRaÐbÑbÔbˆŒÝ”y Ô!1°4Ô3IÐPVÔP_Ð`Ñ`Ô`ˆŒÝœ 4Ô#9¸4Ô;KÐRXÔRaÐbÑbÔbˆŒÝ˜VÔ.Ô/ˆŒˆˆr1   c                 ó¨   — |                       |                      |                      |¦  «        ¦  «        |                      |¦  «        z  ¦  «        }|S r~   )rÑ   rÓ   rÏ   rÐ   )r-   rx   rÑ   s      r0   r?   zHyperCLOVAXMLP.forward  sA   € Ø—N’N 4§;¢;¨t¯~ª~¸aÑ/@Ô/@Ñ#AÔ#AÀDÇLÂLÐQRÁOÄOÑ#SÑTÔTˆ	ØÐr1   )rD   rE   rF   r&   r?   rI   rJ   s   @r0   rË   rË     sG   ø€ € € € € ð0ð 0ð 0ð 0ð 0ðð ð ð ð ð ð r1   rË   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HyperCLOVAXDecoderLayerrN   r°   c                 ó4  •— t          ¦   «                              ¦   «          |j        | _        t          ||¬¦  «        | _        t          |¦  «        | _        t          |j        |j        ¬¦  «        | _	        t          |j        |j        ¬¦  «        | _
        |j        | _        |j        rt          |j        |j        ¬¦  «        nt          j        ¦   «         | _        |j        rt          |j        |j        ¬¦  «        nt          j        ¦   «         | _        d S )N)rN   r°   ©r"   )r%   r&   r.   r¯   Ú	self_attnrË   Úmlpr    Úrms_norm_epsÚinput_layernormÚpost_attention_layernormÚresidual_multiplierÚuse_post_normr'   ÚIdentityÚ
post_norm1Ú
post_norm2r½   s      €r0   r&   z HyperCLOVAXDecoderLayer.__init__  sÿ   ø€ Ý‰Œ×ÒÑÔÐØ!Ô-ˆÔÝ-°VÀyÐQÑQÔQˆŒå! &Ñ)Ô)ˆŒÝ1°&Ô2DÈ&ÔJ]Ð^Ñ^Ô^ˆÔÝ(:¸6Ô;MÐSYÔSfÐ(gÑ(gÔ(gˆÔ%Ø#)Ô#=ˆÔ ð PVÔOcÐvÕ˜vÔ1°vÔ7JÐKÑKÔKÐKÕikÔitÑivÔivð 	Œð PVÔOcÐvÕ˜vÔ1°vÔ7JÐKÑKÔKÐKÕikÔitÑivÔivð 	Œˆˆr1   NFr2   r�   ry   r¿   Ú	use_cacher¾   r    r#   c           
      óB  — |}|                       |¦  «        } | j        d||||||dœ|¤Ž\  }}	|                      |¦  «        }||| j        z  z   }|}|                      |¦  «        }|                      |¦  «        }|                      |¦  «        }||| j        z  z   }|S )af  
        Args:
            hidden_states (`torch.FloatTensor`): input to the layer of shape `(batch, seq_len, embed_dim)`
            attention_mask (`torch.FloatTensor`, *optional*):
                attention mask of size `(batch_size, sequence_length)` if flash attention is used or `(batch_size, 1,
                query_sequence_length, key_sequence_length)` if default attention is used.
            output_attentions (`bool`, *optional*):
                Whether or not to return the attentions tensors of all attention layers. See `attentions` under
                returned tensors for more detail.
            use_cache (`bool`, *optional*):
                If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding
                (see `past_key_values`).
            past_key_values (`Cache`, *optional*): cached past key and value projection states
            position_embeddings (`tuple[torch.FloatTensor, torch.FloatTensor]`, *optional*):
                Tuple containing the cosine and sine positional embeddings of shape `(batch_size, seq_len, head_dim)`,
                with `head_dim` being the embedding dimension of each attention head.
            kwargs (`dict`, *optional*):
                Arbitrary kwargs to be ignored, used for FSDP and other methods that injects code
                into the model
        )r2   r�   ry   r¿   rä   r¾   © )rÝ   rÚ   râ   rß   rÞ   rÛ   rã   )
r-   r2   r�   ry   r¿   rä   r¾   r    ÚresidualÚ_s
             r0   r?   zHyperCLOVAXDecoderLayer.forward-  sÓ   € ð< !ˆØ×,Ò,¨]Ñ;Ô;ˆà)˜4œ>ð 
Ø'Ø)Ø%Ø+ØØ 3ð
ð 
ð ð
ð 
Ñˆ�qð Ÿš¨Ñ6Ô6ˆØ  =°4Ô3KÑ#KÑKˆð !ˆØ×5Ò5°mÑDÔDˆØŸš Ñ/Ô/ˆØŸš¨Ñ6Ô6ˆØ  =°4Ô3KÑ#KÑKˆØÐr1   )NNNFN)rD   rE   rF   r   r‚   r&   r)   rH   Ú
LongTensorr   ÚboolrA   r   r   r?   rI   rJ   s   @r0   r×   r×     sø   ø€ € € € € ð
Ð0ð 
¸Sð 
ð 
ð 
ð 
ð 
ð 
ð( /3Ø04Ø(,Ø!&ØHLð3ð 3à”|ð3ð œ tÑ+ð3ð Ô&¨Ñ-ð	3ð
  ™ð3ð ˜$‘;ð3ð # 5¤<°´Ð#=Ô>ÀÑEð3ð Ð+Ô,ð3ð 
Œð3ð 3ð 3ð 3ð 3ð 3ð 3ð 3r1   r×   c                   óL   — 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dS )ÚHyperCLOVAXPreTrainedModelrN   ÚmodelTr×   r¿   )r2   Ú
attentionsN)rD   rE   rF   r   r€   Úbase_model_prefixÚsupports_gradient_checkpointingÚ_no_split_modulesÚ_skip_keys_device_placementÚ_supports_flash_attnÚ_supports_sdpaÚ_supports_flex_attnÚ_can_compile_fullgraphÚ_supports_attention_backendr×   r¯   Ú_can_record_outputsræ   r1   r0   rì   rì   c  sl   € € € € € € àÐÐÑØÐØ&*Ð#Ø2Ð3ÐØ#4Ð"5ÐØÐØ€NØÐà!ÐØ"&Ðà0Ø*ðð ÐÐÐr1   rì   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HyperCLOVAXModelrN   c                 óö  •‡— t          ¦   «                              ‰¦  «         ‰j        | _        ‰j        | _        t          j        ‰j        ‰j        | j        ¦  «        | _        t          j	        ˆfd„t          ‰j        ¦  «        D ¦   «         ¦  «        | _        t          ‰j        ‰j        ¬¦  «        | _        t!          ‰¬¦  «        | _        d| _        ‰j        | _        |                      ¦   «          d S )Nc                 ó0   •— g | ]}t          ‰|¦  «        ‘ŒS ræ   )r×   )Ú.0r°   rN   s     €r0   ú
<listcomp>z-HyperCLOVAXModel.__init__.<locals>.<listcomp>  s$   ø€ ÐiÐiÐi¸IÕ$ V¨YÑ7Ô7ÐiÐiÐir1   rÙ   ©rN   F)r%   r&   Úpad_token_idÚpadding_idxÚ
vocab_sizer'   Ú	Embeddingr.   Úembed_tokensÚ
ModuleListÚrangeÚnum_hidden_layersÚlayersr    rÜ   ÚnormrL   Ú
rotary_embÚgradient_checkpointingÚembedding_multiplierÚ	post_initrÔ   s    `€r0   r&   zHyperCLOVAXModel.__init__x  sß   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iÐiÐiÐiÍÈvÔOgÑIhÔIhÐiÑiÔiñ
ô 
ˆŒõ ' vÔ'9¸vÔ?RÐSÑSÔSˆŒ	Ý4¸FÐCÑCÔCˆŒØ&+ˆÔ#Ø$*Ô$?ˆÔ!ð 	�ŠÑÔÐÐÐr1   NÚ	input_idsr�   ry   r¿   Úinputs_embedsrä   r    r#   c           
      ó\  — |d u |d uz  rt          d¦  «        ‚|€|                      |¦  «        }|| j        z  }|r|€t          | j        ¬¦  «        }|€V|�|                     ¦   «         nd}t          j        |j        d         |j	        ¬¦  «        |z   }| 
                    d¦  «        }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_embedsrÿ   r   r   )r\   )rN   r  r�   r¿   ry   )ry   )r�   ry   r¿   rä   r¾   )Úlast_hidden_stater¿   )Ú
ValueErrorr  r  r   rN   Úget_seq_lengthr)   re   rB   r\   rŠ   r   r
  r  r  r	  r   )r-   r  r�   ry   r¿   r  rä   r    Úpast_seen_tokensÚcausal_maskr2   r¾   Údecoder_layers                r0   r?   zHyperCLOVAXModel.forward‰  s—  € ð ˜Ð -°tÐ";Ñ<ð 	[ÝÐYÑZÔZÐZàÐ Ø ×-Ò-¨iÑ8Ô8ˆMà%¨Ô(AÑAˆà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(Ø”;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$7ðð ð ðð ˆMˆMð Ÿ	š	 -Ñ0Ô0ˆå&Ø+Ø+ð
ñ 
ô 
ð 	
r1   )NNNNNN)rD   rE   rF   r   r&   r   r   r   r)   ré   rH   r   ÚFloatTensorrê   r   r   r   r?   rI   rJ   s   @r0   rú   rú   v  s  ø€ € € € € ðÐ0ð ð ð ð ð ð ð"  ØØð .2Ø.2Ø04Ø(,Ø26Ø!%ð5
ð 5
àÔ# dÑ*ð5
ð œ tÑ+ð5
ð Ô&¨Ñ-ð	5
ð
  ™ð5
ð Ô(¨4Ñ/ð5
ð ˜$‘;ð5
ð Ð+Ô,ð5
ð 
!ð5
ð 5
ð 5
ñ „^ñ „_ñ  Ôð5
ð 5
ð 5
ð 5
ð 5
r1   rú   c                   ó  ‡ — e Zd ZddiZddiZddgdgfiZˆ fd„Zee	 	 	 	 	 	 	 	 dd
e	j
        dz  de	j        dz  de	j
        dz  dedz  de	j        dz  de	j
        dz  dedz  dee	j        z  dee         defd„¦   «         ¦   «         Zˆ xZS )ÚHyperCLOVAXForCausalLMzlm_head.weightzmodel.embed_tokens.weightÚlm_headÚcolwise_gather_outputr2   Úlogitsc                 óþ   •— t          ¦   «                              |¦  «         t          |¦  «        | _        |j        | _        t          j        |j        |j        d¬¦  «        | _        |  	                    ¦   «          d S )NFr²   )
r%   r&   rú   rí   r  r'   r·   r.   r  r  rÔ   s     €r0   r&   zHyperCLOVAXForCausalLM.__init__Ê  sj   ø€ Ý‰Œ×Ò˜Ñ Ô Ð Ý% fÑ-Ô-ˆŒ
Ø Ô+ˆŒÝ”y Ô!3°VÔ5FÈUÐSÑSÔSˆŒð 	�ŠÑÔÐÐÐr1   Nr   r  r�   ry   r¿   r  Úlabelsrä   Úlogits_to_keepr    r#   c	           
      ój  —  | j         d||||||dœ|	¤Ž}
|
j        }t          |t          ¦  «        rt	          | d¦  «        n|}|                      |dd…|dd…f         ¦  «        | j        j        z  }d}|� | j        d||| j        j	        dœ|	¤Ž}t          |||
j        |
j        |
j        ¬¦  «        S )a&  
        Example:

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

        >>> model = HyperCLOVAXForCausalLM.from_pretrained("naver-hyperclovax/HyperCLOVAX-SEED-Think-14B")
        >>> tokenizer = AutoTokenizer.from_pretrained("naver-hyperclovax/HyperCLOVAX-SEED-Think-14B")

        >>> 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? Are you okay?" The man was confused and answered, "Yes." Then the woman asked.
        ```)r  r�   ry   r¿   r  rä   N)r  r  r  )Úlossr  r¿   r2   rî   ræ   )rí   r  rq   r‚   Úslicer  rN   Úlogits_scalingÚloss_functionr  r   r¿   r2   rî   )r-   r  r�   ry   r¿   r  r  rä   r  r    Úoutputsr2   Úslice_indicesr  r!  s                  r0   r?   zHyperCLOVAXForCausalLM.forwardÓ  sþ   € ð> �$”*ð 
ØØ)Ø%Ø+Ø'Øð
ð 
ð ð
ð 
ˆð  Ô1ˆÝ8BÀ>ÕSVÑ8WÔ8WÐk�˜~˜o¨tÑ4Ô4Ð4Ð]kˆà—’˜m¨A¨A¨A¨}¸a¸a¸aÐ,?Ô@ÑAÔAÀDÄKÔD^Ñ^ˆàˆØÐØ%�4Ô%Ðp¨V¸FÈtÌ{ÔOeÐpÐpÐioÐpÐpˆDå%ØØØ#Ô3Ø!Ô/ØÔ)ð
ñ 
ô 
ð 	
r1   )NNNNNNNr   )rD   rE   rF   Ú_tied_weights_keysÚ_tp_planÚ_pp_planr&   r   r   r)   ré   rH   r   r  rê   r‚   r   r   r   r?   rI   rJ   s   @r0   r  r  Ä  sK  ø€ € € € € à*Ð,GÐHÐØÐ2Ð3€HØ˜_Ð-°¨zÐ:Ð;€Hðð ð ð ð ð Øð .2Ø.2Ø04Ø(,Ø26Ø*.Ø!%Ø-.ð6
ð 6
àÔ# dÑ*ð6
ð œ tÑ+ð6
ð Ô&¨Ñ-ð	6
ð
  ™ð6
ð Ô(¨4Ñ/ð6
ð Ô  4Ñ'ð6
ð ˜$‘;ð6
ð ˜eœlÑ*ð6
ð Ð+Ô,ð6
ð 
 ð6
ð 6
ð 6
ñ „^ñ Ôð6
ð 6
ð 6
ð 6
ð 6
r1   r  )rì   rú   r  )r   )r˜   )=Úcollections.abcr   Útypingr   r)   Útorch.nnr'   Úactivationsr   Úcache_utilsr   r   Ú
generationr	   Úintegrationsr
   r   r   Úmasking_utilsr   Úmodeling_layersr   Úmodeling_outputsr   r   Úmodeling_rope_utilsr   r   Úmodeling_utilsr   r   Úprocessing_utilsr   Úutilsr   r   r   Úutils.genericr   r   Úutils.output_capturingr   Úconfiguration_hyperclovaxr   ÚModuler    rL   r‡   r�   rH   r‚   r—   rG   r­   r¯   rË   r×   rì   rú   r  Ú__all__ræ   r1   r0   ú<module>r=     sX  ðð* %Ð $Ð $Ð $Ð $Ð $Ø Ð Ð Ð Ð Ð à €€€Ø Ð Ð Ð Ð Ð à !Ð !Ð !Ð !Ð !Ð !Ø .Ð .Ð .Ð .Ð .Ð .Ð .Ð .Ø )Ð )Ð )Ð )Ð )Ð )Ø fÐ fÐ fÐ fÐ fÐ fÐ fÐ fÐ fÐ fØ /Ð /Ð /Ð /Ð /Ð /Ø 9Ð 9Ð 9Ð 9Ð 9Ð 9Ø OÐ OÐ OÐ OÐ OÐ OÐ OÐ OØ KÐ KÐ KÐ KÐ KÐ KÐ KÐ KØ FÐ FÐ FÐ FÐ FÐ FÐ FÐ FØ &Ð &Ð &Ð &Ð &Ð &Ø IÐ IÐ IÐ IÐ IÐ IÐ IÐ IÐ IÐ IØ GÐ GÐ GÐ GÐ GÐ GÐ GÐ GØ 5Ð 5Ð 5Ð 5Ð 5Ð 5Ø 8Ð 8Ð 8Ð 8Ð 8Ð 8ð Ð˜YÑ'Ô'ðJð Jð Jð Jð J˜œñ Jô Jñ (Ô'ðJð(><ð ><ð ><ð ><ð >< ¤ñ ><ô ><ð ><ðB(ð (ð (ð ÐÐ*Ñ+Ô+ðð ð ñ ,Ô+ðð2	U˜Uœ\ð 	U°#ð 	U¸%¼,ð 	Uð 	Uð 	Uð 	Uð& ð%ð %ØŒIð%àŒ<ð%ð 
Œð%ð Œ<ð	%ð
 ”L 4Ñ'ð%ð ð%ð ð%ð Ð'Ô(ð%ð %ð %ð %ð2 ÐÐ)Ñ*Ô*ð@)ð @)ð @)ð @)ð @)˜2œ9ñ @)ô @)ñ +Ô*ð@)ðFð ð ð ð �R”Yñ ô ð ð Eð Eð Eð Eð EÐ8ñ Eô Eð EðP ðð ð ð ð  ñ ô ñ „ðð$ ðJ
ð J
ð J
ð J
ð J
Ð1ñ J
ô J
ñ „ðJ
ðZ ðF
ð F
ð F
ð F
ð F
Ð7¸ñ F
ô F
ñ „ðF
ðR WÐ
VÐ
V€€€r1   