Ë
    ÛÓ^j¬[  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jX                  «      «       Z- G d„ dejX                  «      Z.d„ Z/ ed«      d6d„«       Z0dejb                  de2dejb                  fd„Z3	 d7d ejX                  d!ejb                  d"ejb                  d#ejb                  d$ejb                  dz  d%e4d&e4d'e e"   fd(„Z5 ee0«       G d)„ d*ejX                  «      «       Z6 G d+„ d,ejX                  «      Z7 G d-„ d.e«      Z8e# G d/„ d0e«      «       Z9e# G d1„ d2e9«      «       Z:e# G d3„ d4e9e«      «       Z;g d5¢Z<y)8é    )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                   óh   ‡ — 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HyperCLOVAXRMSNormÚepsÚreturnNc                 óŠ   •— t         ‰| �  «        t        j                  t	        j
                  |«      «      | _        || _        y)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      €ú/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/hyperclovax/modeling_hyperclovax.pyr%   zHyperCLOVAXRMSNorm.__init__-   s1   ø€ ô 	‰ÑÔÜ—l‘l¤5§:¡:¨kÓ#:Ó;ˆŒØ #ˆÕó    Úhidden_statesc                 ó"  — |j                   }|j                  t        j                  «      }|j	                  d«      j                  dd¬«      }|t        j                  || j                  z   «      z  }| j                  |j                  |«      z  S )Né   éÿÿÿÿT)Úkeepdim)	ÚdtypeÚtor(   Úfloat32ÚpowÚmeanÚrsqrtr+   r*   )r,   r1   Úinput_dtypeÚvariances       r/   ÚforwardzHyperCLOVAXRMSNorm.forward5   sy   € Ø#×)Ñ)ˆØ%×(Ñ(¬¯©Ó7ˆØ ×$Ñ$ QÓ'×,Ñ,¨R¸Ð,Ó>ˆØ%¬¯©°H¸t×?TÑ?TÑ4TÓ(UÑUˆØ�{‰{˜]×-Ñ-¨kÓ:Ñ:Ð:r0   c                 ó^   — t        | j                  j                  «      › d| j                  › �S )Nz, eps=)Útupler*   Úshaper+   )r,   s    r/   Ú
extra_reprzHyperCLOVAXRMSNorm.extra_repr<   s*   € Ü˜Ÿ™×)Ñ)Ó*Ð+¨6°$×2GÑ2GÐ1HÐIÐIr0   )g�íµ ÷Æ°>)
Ú__name__Ú
__module__Ú__qualname__Úfloatr%   r(   ÚTensorr>   rB   Ú__classcell__©r.   s   @r/   r    r    +   s7   ø„ ñ$¨ð $¸$õ $ð; U§\¡\ð ;°e·l±ló ;öJr0   r    c                   óÄ   ‡ — e Zd ZU ej                  ed<   ddefˆ fd„Ze	 	 	 ddedz  de	d   de
dz  ded	ef   fd
„«       Z ej                  «       ed„ «       «       Zˆ xZS )ÚHyperCLOVAXRotaryEmbeddingÚinv_freqNÚconfigc                 ó®  •— t         ‰| �  «        |j                  | _        |j                  | _        || _        | j
                  j                  d   | _        | j                  }| j                  dk7  rt        | j                     } || j
                  |«      \  }| _
        | j                  d|d¬«       | j                  d|j                  «       d¬«       y )NÚ	rope_typeÚdefaultrL   F)Ú
persistentÚoriginal_inv_freq)r$   r%   Úmax_position_embeddingsÚmax_seq_len_cachedÚoriginal_max_seq_lenrM   Úrope_parametersrO   Úcompute_default_rope_parametersr   Úattention_scalingÚregister_bufferÚclone)r,   rM   ÚdeviceÚrope_init_fnrL   r.   s        €r/   r%   z#HyperCLOVAXRotaryEmbedding.__init__C   s¶   ø€ Ü‰ÑÔØ"(×"@Ñ"@ˆÔØ$*×$BÑ$BˆÔ!àˆŒàŸ™×4Ñ4°[ÑAˆŒØ!%×!EÑ!EˆØ�>‰>˜YÒ&Ü.¨t¯~©~Ñ>ˆLÙ+7¸¿¹ÀVÓ+LÑ(ˆ�$Ô(à×Ñ˜Z¨¸eÐÔDØ×ÑÐ0°(·.±.Ó2BÈuÐÕUr0   r[   ztorch.deviceÚseq_lenr"   ztorch.Tensorc                 ó  — | j                   d   }t        | dd«      xs | j                  | j                  z  }d}d|t	        j
                  d|dt        j                  ¬«      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   r3   ©r6   )r[   r6   )	rV   Úgetattrr-   Únum_attention_headsr(   ÚarangeÚint64r7   rF   )rM   r[   r]   ÚbaseÚdimÚattention_factorrL   s          r/   rW   z:HyperCLOVAXRotaryEmbedding.compute_default_rope_parametersS   s�   € ð& ×%Ñ% lÑ3ˆÜ�f˜j¨$Ó/Òc°6×3EÑ3EÈ×IcÑIcÑ3cˆàÐð Ø”U—\‘\ ! S¨!´5·;±;Ô?×BÑBÈ&ÔX]×XcÑXcÐBÓdÐgjÑjÑkñ
ˆð Ð)Ð)Ð)r0   c                 óN  — | j                   d d d …d f   j                  «       j                  |j                  d   dd«      j	                  |j
                  «      }|d d …d d d …f   j                  «       }t        |j
                  j                  t        «      r/|j
                  j                  dk7  r|j
                  j                  nd}t        |d¬«      5  |j                  «       |j                  «       z  j                  dd«      }t        j                  ||fd¬	«      }|j                  «       | j                  z  }|j                  «       | j                  z  }	d d d «       j	                  |j                   ¬
«      	j	                  |j                   ¬
«      fS # 1 sw Y   ŒAxY w)Nr   r4   r   ÚmpsÚcpuF)Údevice_typeÚenabledr3   ©rg   ra   )rL   rF   ÚexpandrA   r7   r[   Ú
isinstanceÚtypeÚstrr   Ú	transposer(   ÚcatÚcosrX   Úsinr6   )
r,   ÚxÚposition_idsÚinv_freq_expandedÚposition_ids_expandedrl   ÚfreqsÚembru   rv   s
             r/   r>   z"HyperCLOVAXRotaryEmbedding.forwardq   sR  € ð !ŸM™M¨$²°4¨-Ñ8×>Ñ>Ó@×GÑGÈ×HZÑHZÐ[\ÑH]Ð_aÐcdÓe×hÑhÐij×iqÑiqÓrÐØ ,ªQ°²a¨ZÑ 8× >Ñ >Ó @Ðä'1°!·(±(·-±-ÄÔ'EÈ!Ï(É(Ï-É-Ð[`ÒJ`�a—h‘h—m’mÐfkˆÜ¨¸UÔCñ 	5Ø&×,Ñ,Ó.Ð1F×1LÑ1LÓ1NÑN×YÑYÐZ[Ð]^Ó_ˆEÜ—)‘)˜U E˜N°Ô3ˆCØ—'‘'“)˜d×4Ñ4Ñ4ˆCØ—'‘'“)˜d×4Ñ4Ñ4ˆC÷		5ð �v‰v˜AŸG™GˆvÓ$ c§f¡f°1·7±7 fÓ&;Ð;Ð;÷	5ð 	5ús   ÃBFÆF$©N©NNN)rC   rD   rE   r(   rG   Ú__annotations__r   r%   Ústaticmethodr   Úintr@   rF   rW   Úno_gradr   r>   rH   rI   s   @r/   rK   rK   @   s™   ø… Ø�l‰lÓñVÐ0õ Vð  à+/Ø+/Ø"ñ*Ø! DÑ(ð*à˜Ñ(ð*ð �t‘ð*ð 
ˆ~˜uÐ$Ñ	%ò	*ó ð*ð: €U‡]�]ƒ_Øñ<ó ó ô<r0   rK   c                 óš   — | 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..Nr4   r3   rn   )rA   r(   rt   )rw   Úx1Úx2s      r/   Úrotate_halfr†   �   sZ   € à	
ˆ3Ð"�!—'‘'˜"‘+ Ñ"Ð"Ð"Ñ	#€BØ	
ˆ3�—‘˜‘˜qÑ Ñ"Ð"Ñ	#€BÜ�9‰9�r�c˜2�Y BÔ'Ð'r0   Úrotary_pos_embc                 óž   — |j                  |«      }|j                  |«      }| |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kru   rv   Úunsqueeze_dimÚq_embedÚk_embeds          r/   Úapply_rotary_pos_embr�   ˆ   sY   € ð& �-‰-˜Ó
&€CØ
�-‰-˜Ó
&€CØ�3‰wœ; q›>¨CÑ/Ñ0€GØ�3‰wœ; q›>¨CÑ/Ñ0€GØ�GÐÐr0   r1   Ún_repr"   c                 óª   — | j                   \  }}}}|dk(  r| S | dd…dd…ddd…dd…f   j                  |||||«      } | j                  |||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)rA   ro   Úreshape)r1   r�   ÚbatchÚnum_key_value_headsÚslenr`   s         r/   Ú	repeat_kvr–   ¢   so   € ð
 2?×1DÑ1DÑ.€EÐ  hØ�‚zØÐØ!¢!¢Q¨ªa²Ð"2Ñ3×:Ñ:¸5ÐBUÐW\Ð^bÐdlÓm€MØ× Ñ  Ð(;¸eÑ(CÀTÈ8ÓTÐTr0   ÚmoduleÚqueryÚkeyÚvalueÚattention_maskÚscalingÚdropoutÚkwargsc                 ó  — t        || j                  «      }t        || j                  «      }	t        j                  ||j	                  dd«      «      |z  }
|�|
|z   }
t
        j                  j                  |
dt        j                  ¬«      j                  |j                  «      }
t
        j                  j                  |
|| j                  ¬«      }
t        j                  |
|	«      }|j	                  dd«      j                  «       }||
fS )Nr3   r   r4   )rg   r6   )ÚpÚtrainingr   )r–   Únum_key_value_groupsr(   Úmatmulrs   r&   Ú
functionalÚsoftmaxr8   r7   r6   r�   r¡   Ú
contiguous)r—   r˜   r™   rš   r›   rœ   r�   rž   Ú
key_statesÚvalue_statesÚattn_weightsÚattn_outputs               r/   Úeager_attention_forwardr«   ®   sà   € ô ˜3 × ;Ñ ;Ó<€JÜ˜U F×$?Ñ$?Ó@€Lä—<‘<  z×';Ñ';¸A¸qÓ'AÓBÀWÑL€LØÐ!Ø# nÑ4ˆä—=‘=×(Ñ(¨¸2ÄUÇ]Á]Ð(ÓS×VÑVÐW\×WbÑWbÓc€LÜ—=‘=×(Ñ(¨¸È6Ï?É?Ð(Ó[€LÜ—,‘,˜|¨\Ó:€KØ×'Ñ'¨¨1Ó-×8Ñ8Ó:€Kà˜Ð$Ð$r0   c                   ó   ‡ — 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' paperNrM   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                   ¬«      | _        y )Nr`   T©Úbias)r$   r%   rM   r®   rb   r-   rc   r`   r”   r¢   Úattention_multiplierrœ   Úattention_dropoutÚ	is_causalr&   ÚLinearÚattention_biasÚq_projÚk_projÚv_projÚo_proj©r,   rM   r®   r.   s      €r/   r%   zHyperCLOVAXAttention.__init__Ë   sJ  ø€ Ü‰ÑÔØˆŒØ"ˆŒÜ ¨
°F×4FÑ4FÈ&×JdÑJdÑ4dÓeˆŒØ$*×$>Ñ$>À&×B\ÑB\Ñ$\ˆÔ!Ø×2Ñ2ˆŒØ!'×!9Ñ!9ˆÔØˆŒä—i‘iØ×Ñ × :Ñ :¸T¿]¹]Ñ JÐQW×QfÑQfô
ˆŒô —i‘iØ×Ñ × :Ñ :¸T¿]¹]Ñ JÐQW×QfÑQfô
ˆŒô —i‘iØ×Ñ × :Ñ :¸T¿]¹]Ñ JÐQW×QfÑQfô
ˆŒô —i‘iØ×&Ñ&¨¯©Ñ6¸×8JÑ8JÐQW×QfÑQfô
ˆ�r0   r1   Úposition_embeddingsr›   Úpast_key_valuesrž   r"   c                 ó
  — |j                   d d }g |¢d‘| j                  ‘­}| j                  |«      j                  |«      j	                  dd«      }| j                  |«      j                  |«      j	                  dd«      }	| j                  |«      j                  |«      j	                  dd«      }
|\  }}t        ||	||«      \  }}	|� |j                  |	|
| j                  «      \  }	}
t        j                  | j                  j                  t        «      } || ||	|
|f| j                  sdn| j                   | j"                  dœ|¤Ž\  }} |j$                  g |¢d‘­Ž j'                  «       }| j)                  |«      }||fS )Nr4   r   r3   ç        )r�   rœ   )rA   r`   r·   Úviewrs   r¸   r¹   r�   Úupdater®   r   Úget_interfacerM   Ú_attn_implementationr«   r¡   r³   rœ   r’   r¦   rº   )r,   r1   r¼   r›   r½   rž   Úinput_shapeÚhidden_shapeÚquery_statesr§   r¨   ru   rv   Úattention_interfacerª   r©   s                   r/   r>   zHyperCLOVAXAttention.forwardâ   s‘  € ð $×)Ñ)¨#¨2Ð.ˆØ8˜Ð8 bÐ8¨$¯-©-Ñ8ˆà—{‘{ =Ó1×6Ñ6°|ÓD×NÑNÈqÐRSÓTˆØ—[‘[ Ó/×4Ñ4°\ÓB×LÑLÈQÐPQÓRˆ
Ø—{‘{ =Ó1×6Ñ6°|ÓD×NÑNÈqÐRSÓTˆà&‰ˆˆSÜ#7¸ÀjÐRUÐWZÓ#[Ñ ˆ�jàÐ&Ø'6×'=Ñ'=¸jÈ,ÐX\×XfÑXfÓ'gÑ$ˆJ˜ä(?×(MÑ(MØ�K‰K×,Ñ,Ô.Eó)
Ðñ %8ØØØØØð	%
ð  $Ÿ}š}‘C°$×2HÑ2HØ—L‘Lñ	%
ð ñ	%
Ñ!ˆ�\ð *�k×)Ñ)Ð;¨;Ð;¸Ò;×FÑFÓHˆØ—k‘k +Ó.ˆØ˜LÐ(Ð(r0   r}   r~   )rC   rD   rE   Ú__doc__r   r�   r%   r(   rG   r@   r   r   r   r>   rH   rI   s   @r/   r­   r­   Ç   sª   ø„ áGñ
Ð0ð 
¸SÀ4¹Zõ 
ð4 IMØ.2Ø(,ñ&)à—|‘|ð&)ð # 5§<¡<°·±Ð#=Ñ>ÀÑEð&)ð Ÿ™ tÑ+ð	&)ð
  ™ð&)ð Ð+Ñ,ð&)ð 
ˆu�|‰|˜UŸ\™\Ð)Ñ	*÷&)r0   r­   c                   ó$   ‡ — e Zd Zˆ fd„Zd„ Zˆ xZS )ÚHyperCLOVAXMLPc                 ó  •— t         ‰| �  «        || _        |j                  | _        |j                  | _        t        j                  | j                  | j                  |j                  ¬«      | _        t        j                  | j                  | j                  |j                  ¬«      | _	        t        j                  | j                  | j                  |j                  ¬«      | _
        t        |j                     | _        y )Nr°   )r$   r%   rM   r-   Úintermediate_sizer&   rµ   Úmlp_biasÚ	gate_projÚup_projÚ	down_projr   Ú
hidden_actÚact_fn©r,   rM   r.   s     €r/   r%   zHyperCLOVAXMLP.__init__  s¸   ø€ Ü‰ÑÔØˆŒØ!×-Ñ-ˆÔØ!'×!9Ñ!9ˆÔÜŸ™ 4×#3Ñ#3°T×5KÑ5KÐRX×RaÑRaÔbˆŒÜ—y‘y ×!1Ñ!1°4×3IÑ3IÐPV×P_ÑP_Ô`ˆŒÜŸ™ 4×#9Ñ#9¸4×;KÑ;KÐRX×RaÑRaÔbˆŒÜ˜V×.Ñ.Ñ/ˆ�r0   c                 óˆ   — | j                  | j                  | j                  |«      «      | j                  |«      z  «      }|S r}   )rÐ   rÒ   rÎ   rÏ   )r,   rw   rÐ   s      r/   r>   zHyperCLOVAXMLP.forward  s6   € Ø—N‘N 4§;¡;¨t¯~©~¸aÓ/@Ó#AÀDÇLÁLÐQRÃOÑ#SÓTˆ	ØÐr0   )rC   rD   rE   r%   r>   rH   rI   s   @r/   rÊ   rÊ     s   ø„ ô0ör0   rÊ   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j                  ej                  f   dz  dee   dej                  fd„Zˆ xZS )ÚHyperCLOVAXDecoderLayerrM   r®   c                 óf  •— t         ‰| �  «        |j                  | _        t        ||¬«      | _        t        |«      | _        t        |j                  |j                  ¬«      | _	        t        |j                  |j                  ¬«      | _
        |j                  | _        |j                  r!t        |j                  |j                  ¬«      nt        j                  «       | _        |j                  r't        |j                  |j                  ¬«      | _        y t        j                  «       | _        y )N)rM   r®   ©r!   )r$   r%   r-   r­   Ú	self_attnrÊ   Úmlpr    Úrms_norm_epsÚinput_layernormÚpost_attention_layernormÚresidual_multiplierÚuse_post_normr&   ÚIdentityÚ
post_norm1Ú
post_norm2r»   s      €r/   r%   z HyperCLOVAXDecoderLayer.__init__  sî   ø€ Ü‰ÑÔØ!×-Ñ-ˆÔÜ-°VÀyÔQˆŒä! &Ó)ˆŒÜ1°&×2DÑ2DÈ&×J]ÑJ]Ô^ˆÔÜ(:¸6×;MÑ;MÐSY×SfÑSfÔ(gˆÔ%Ø#)×#=Ñ#=ˆÔ ð PV×OcÒOcÔ˜v×1Ñ1°v×7JÑ7JÕKÔik×itÑitÓivð 	Œð PV×OcÒOcÔ˜v×1Ñ1°v×7JÑ7JÔKð 	�Üik×itÑitÓivð 	�r0   Nr1   r›   rx   r½   Ú	use_cacher¼   rž   r"   c           
      ó8  — |}| j                  |«      } | j                  d||||||dœ|¤Ž\  }}	| j                  |«      }||| j                  z  z   }|}| j	                  |«      }| j                  |«      }| j                  |«      }||| 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
        )r1   r›   rx   r½   rã   r¼   © )rÜ   rÙ   rá   rÞ   rÝ   rÚ   râ   )
r,   r1   r›   rx   r½   rã   r¼   rž   ÚresidualÚ_s
             r/   r>   zHyperCLOVAXDecoderLayer.forward-  sÂ   € ð< !ˆØ×,Ñ,¨]Ó;ˆà)˜4Ÿ>™>ð 
Ø'Ø)Ø%Ø+ØØ 3ñ
ð ñ
Ñˆ�qð Ÿ™¨Ó6ˆØ  =°4×3KÑ3KÑ#KÑKˆð !ˆØ×5Ñ5°mÓDˆØŸ™ Ó/ˆØŸ™¨Ó6ˆØ  =°4×3KÑ3KÑ#KÑKˆØÐr0   )NNNFN)rC   rD   rE   r   r�   r%   r(   rG   Ú
LongTensorr   Úboolr@   r   r   r>   rH   rI   s   @r/   rÖ   rÖ     s¼   ø„ ð
Ð0ð 
¸Sõ 
ð( /3Ø04Ø(,Ø!&ØHLñ3à—|‘|ð3ð Ÿ™ tÑ+ð3ð ×&Ñ&¨Ñ-ð	3ð
  ™ð3ð ˜$‘;ð3ð # 5§<¡<°·±Ð#=Ñ>ÀÑEð3ð Ð+Ñ,ð3ð 
�‰÷3r0   rÖ   c                   óJ   — 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y)ÚHyperCLOVAXPreTrainedModelrM   ÚmodelTrÖ   r½   )r1   Ú
attentionsN)rC   rD   rE   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_backendrÖ   r­   Ú_can_record_outputsrå   r0   r/   rë   rë   c  sQ   … àÓØÐØ&*Ð#Ø2Ð3ÐØ#4Ð"5ÐØÐØ€NØÐà!ÐØ"&Ðà0Ø*ñÑr0   rë   c                   óò   ‡ — 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HyperCLOVAXModelrM   c           	      ó.  •— t         ‰| �  |«       |j                  | _        |j                  | _        t        j                  |j                  |j                  | j                  «      | _        t        j                  t        |j                  «      D �cg c]  }t        ||«      ‘Œ c}«      | _        t        |j                  |j                  ¬«      | _        t#        |¬«      | _        d| _        |j(                  | _        | j+                  «        y c c}w )NrØ   ©rM   F)r$   r%   Úpad_token_idÚpadding_idxÚ
vocab_sizer&   Ú	Embeddingr-   Úembed_tokensÚ
ModuleListÚrangeÚnum_hidden_layersrÖ   Úlayersr    rÛ   ÚnormrK   Ú
rotary_embÚgradient_checkpointingÚembedding_multiplierÚ	post_initr»   s      €r/   r%   zHyperCLOVAXModel.__init__x  sÔ   ø€ Ü‰Ñ˜Ô Ø!×.Ñ.ˆÔØ ×+Ñ+ˆŒäŸL™L¨×):Ñ):¸F×<NÑ<NÐPT×P`ÑP`ÓaˆÔÜ—m‘mÜINÈv×OgÑOgÓIhÖi¸IÔ$ V¨YÕ7Òió
ˆŒô ' v×'9Ñ'9¸v×?RÑ?RÔSˆŒ	Ü4¸FÔCˆŒØ&+ˆÔ#Ø$*×$?Ñ$?ˆÔ!ð 	�‰Õùò js   ÂDNÚ	input_idsr›   rx   r½   Úinputs_embedsrã   rž   r"   c           
      óZ  — |d u |d uz  rt        d«      ‚|€| j                  |«      }|| j                  z  }|r|€t        | j                  ¬«      }|€V|�|j                  «       nd}t        j                  |j                  d   |j                  ¬«      |z   }|j                  d«      }t        | j                  ||||¬«      }	|}
| j                  |
|¬«      }| j                  d | j                  j                   D ]  } ||
f|	||||dœ|¤Ž}
Œ | j                  |
«      }
t!        |
|¬	«      S )
Nz:You must specify exactly one of input_ids or inputs_embedsrû   r   r   )r[   )rM   r  r›   r½   rx   )rx   )r›   rx   r½   rã   r¼   )Úlast_hidden_stater½   )Ú
ValueErrorr   r  r   rM   Úget_seq_lengthr(   rd   rA   r[   r‰   r   r  r  r  r  r   )r,   r
  r›   rx   r½   r  rã   rž   Úpast_seen_tokensÚcausal_maskr1   r¼   Údecoder_layers                r/   r>   zHyperCLOVAXModel.forward‰  s\  € ð ˜Ð -°tÐ";Ò<ÜÐYÓZÐZàÐ Ø ×-Ñ-¨iÓ8ˆMà%¨×(AÑ(AÑAˆá˜Ð0Ü*°$·+±+Ô>ˆOàÐØCRÐC^˜×=Ñ=Ô?ÐdeÐÜ Ÿ<™<¨×(;Ñ(;¸AÑ(>À}×G[ÑG[Ô\Ð_oÑoˆLØ'×1Ñ1°!Ó4ˆLä(Ø—;‘;Ø'Ø)Ø+Ø%ô
ˆð &ˆØ"Ÿo™o¨mÈ,˜oÓWÐà!Ÿ[™[Ð)H¨4¯;©;×+HÑ+HÐIò 		ˆMÙ)Øðà*Ø)Ø /Ø#Ø$7ñð ñ‰Mð		ð Ÿ	™	 -Ó0ˆä&Ø+Ø+ô
ð 	
r0   )NNNNNN)rC   rD   rE   r   r%   r   r   r   r(   rè   rG   r   ÚFloatTensorré   r   r   r   r>   rH   rI   s   @r/   rù   rù   v  sÎ   ø„ ðÐ0õ ð"  ØØð .2Ø.2Ø04Ø(,Ø26Ø!%ñ5
à×#Ñ# dÑ*ð5
ð Ÿ™ tÑ+ð5
ð ×&Ñ&¨Ñ-ð	5
ð
  ™ð5
ð ×(Ñ(¨4Ñ/ð5
ð ˜$‘;ð5
ð Ð+Ñ,ð5
ð 
!ò5
ó ó ó  ô5
r0   rù   c                   óB  ‡ — 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_outputr1   Úlogitsc                 óè   •— t         ‰| �  |«       t        |«      | _        |j                  | _        t        j                  |j                  |j                  d¬«      | _        | j                  «        y )NFr°   )
r$   r%   rù   rì   rþ   r&   rµ   r-   r  r	  rÓ   s     €r/   r%   zHyperCLOVAXForCausalLM.__init__Ê  sU   ø€ Ü‰Ñ˜Ô Ü% fÓ-ˆŒ
Ø ×+Ñ+ˆŒÜ—y‘y ×!3Ñ!3°V×5FÑ5FÈUÔSˆŒð 	�‰Õr0   Nr
  r›   rx   r½   r  Úlabelsrã   Úlogits_to_keeprž   r"   c	           
      ó¦  —  | j                   d||||||dœ|	¤Ž}
|
j                  }t        |t        «      rt	        | d«      n|}| j                  |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›   rx   r½   r  rã   N)r  r  rþ   )Úlossr  r½   r1   rí   rå   )rì   r  rp   r�   Úslicer  rM   Úlogits_scalingÚloss_functionrþ   r   r½   r1   rí   )r,   r
  r›   rx   r½   r  r  rã   r  rž   Úoutputsr1   Úslice_indicesr  r  s                  r/   r>   zHyperCLOVAXForCausalLM.forwardÓ  sè   € ð> �$—*‘*ð 
ØØ)Ø%Ø+Ø'Øñ
ð ñ
ˆð  ×1Ñ1ˆÜ8BÀ>ÔSVÔ8Wœ˜~˜o¨tÔ4Ð]kˆà—‘˜mªA¨}ºaÐ,?Ñ@ÓAÀDÇKÁK×D^ÑD^Ñ^ˆàˆØÐØ%�4×%Ñ%Ðp¨V¸FÈtÏ{É{×OeÑOeÑpÐioÑpˆDä%ØØØ#×3Ñ3Ø!×/Ñ/Ø×)Ñ)ô
ð 	
r0   )NNNNNNNr   )rC   rD   rE   Ú_tied_weights_keysÚ_tp_planÚ_pp_planr%   r   r   r(   rè   rG   r   r  ré   r�   r   r   r   r>   rH   rI   s   @r/   r  r  Ä  s  ø„ à*Ð,GÐHÐØÐ2Ð3€HØ˜_Ð-°¨zÐ:Ð;€Hôð Øð .2Ø.2Ø04Ø(,Ø26Ø*.Ø!%Ø-.ñ6
à×#Ñ# dÑ*ð6
ð Ÿ™ tÑ+ð6
ð ×&Ñ&¨Ñ-ð	6
ð
  ™ð6
ð ×(Ñ(¨4Ñ/ð6
ð × Ñ  4Ñ'ð6
ð ˜$‘;ð6
ð ˜eŸl™lÑ*ð6
ð Ð+Ñ,ð6
ð 
 ò6
ó ó ô6
r0   r  )rë   rù   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    rK   r†   r�   rG   r�   r–   rF   r«   r­   rÊ   rÖ   rë   rù   r  Ú__all__rå   r0   r/   ú<module>r9     sã  ðõ* %Ý ã Ý å !ß .Ý )ß fÑ fÝ /Ý 9ß Oß Kß FÝ &ß IÑ Iß GÝ 5Ý 8ñ ˜YÓ'ôJ˜Ÿ™ó Jó (ðJô(>< §¡ô ><òB(ñ Ð*Ó+òó ,ðð2	U˜UŸ\™\ð 	U°#ð 	U¸%¿,¹,ó 	Uð& ñ%Ø�I‰Ið%à�<‰<ð%ð 
�‰ð%ð �<‰<ð	%ð
 —L‘L 4Ñ'ð%ð ð%ð ð%ð Ð'Ñ(ó%ñ2 Ð)Ó*ô@)˜2Ÿ9™9ó @)ó +ð@)ôF�R—Y‘Yô ô EÐ8ô EðP ô ó ó ðð$ ôJ
Ð1ó J
ó ðJ
ðZ ôF
Ð7¸ó F
ó ðF
òR W�r0   