+
    œ°³jxT  ã                   ó°  € ^ RI Ht ^ RIt^ RIHt ^RIHtHt ^RIHtH	t	 ^RI
Ht ^RIHtHt ^RIHt ^R	IHtHt ^R
IHtHt ^RIHtHt ^RIHtHt ^RIHt ^RIH t H!t!H"t" ^RI#H$t$ ^RI%H&t&H't' ^RI(H)t) ^RI*H+t+  ! R R]PX                  4      t-]! R4       ! R R]PX                  4      4       t. ! R R]PX                  4      t/R t0]! R4      R-R l4       t1R R lt2R.R R  llt3]! ]14       ! R! R"]PX                  4      4       t4 ! R# R$]4      t5]! ! R% R&]4      4       t6]! ! R' R(]64      4       t7]! ! R) R*]6]4      4       t8 ! R+ R,]]64      t9. R/Ot:R# )0é    )ÚCallableN)Únn)ÚACT2CLSÚACT2FN)ÚCacheÚDynamicCache)ÚGenerationMixin)Úuse_kernel_forward_from_hubÚuse_kernelized_func)Úcreate_causal_mask)Ú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_outputs©ÚApertusConfigc                   ó8   a a€ ] tR t^+t oV 3R ltR tRtVtV ;t# )Ú
ApertusMLPc                óà  <€ \         SV `  4        Wn        VP                  V n        VP                  V n        \
        P                  ! V P                  V P                  R R7      V n        \
        P                  ! V P                  V P                  R R7      V n        \        VP                  ,          V n        VP                  R8X  d&   \        R,          ! VP                  R7      V n        R# R# )F©ÚbiasÚxielu©ÚdtypeN)ÚsuperÚ__init__ÚconfigÚhidden_sizeÚintermediate_sizer   ÚLinearÚup_projÚ	down_projr   Ú
hidden_actÚact_fnr   r&   ©Úselfr)   Ú	__class__s   &&€Úm/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/apertus/modeling_apertus.pyr(   ÚApertusMLP.__init__,   s«   ø€ Ü‰ÑÔØŒØ!×-Ñ-ˆÔØ!'×!9Ñ!9ˆÔÜ—y’y ×!1Ñ!1°4×3IÑ3IÐPUÔVˆŒÜŸš 4×#9Ñ#9¸4×;KÑ;KÐRWÔXˆŒÜ˜V×.Ñ.Õ/ˆŒØ×Ñ Ô'Ü! 'Ö*°·±Ô>ˆDŽKñ (ó    c                ó`   € V P                  V P                  V P                  V4      4      4      # ©N)r.   r0   r-   )r2   Úxs   &&r4   ÚforwardÚApertusMLP.forward7   s"   € Ø�~‰~˜dŸk™k¨$¯,©,°q«/Ó:Ó;Ð;r6   )r0   r)   r.   r*   r+   r-   ©	Ú__name__Ú
__module__Ú__qualname__Ú__firstlineno__r(   r:   Ú__static_attributes__Ú__classdictcell__Ú__classcell__©r3   Ú__classdict__s   @@r4   r    r    +   s   ù‡ € õ	?÷<ò <r6   r    ÚRMSNormc                   óZ   a a€ ] tR t^;t oRV3R lV 3R llltV3R lR ltR tRtVtV ;t	# )ÚApertusRMSNormc                ó$   <€ V ^8„  d   QhRS[ RR/# )é   ÚepsÚreturnN)Úfloat)ÚformatrE   s   "€r4   Ú__annotate__ÚApertusRMSNorm.__annotate__=   s   ø€ ÷ $ñ $©ð $¸$ñ $r6   c                óŽ   <€ \         SV `  4        \        P                  ! \        P
                  ! V4      4      V n        W n        R# )z-
ApertusRMSNorm is equivalent to T5LayerNorm
N)r'   r(   r   Ú	ParameterÚtorchÚonesÚweightÚvariance_epsilon)r2   r*   rK   r3   s   &&&€r4   r(   ÚApertusRMSNorm.__init__=   s/   ø€ ô 	‰ÑÔÜ—l’l¤5§:¢:¨kÓ#:Ó;ˆŒØ #Ör6   c                óN   <€ V ^8„  d   QhRS[ P                  RS[ P                  /# )rJ   Úhidden_statesrL   )rS   ÚTensor)rN   rE   s   "€r4   rO   rP   E   s#   ø€ ÷ ;ñ ;¡U§\¡\ð ;±e·l±lñ ;r6   c                ó:  € VP                   pVP                  \        P                  4      pVP	                  ^4      P                  RRR7      pV\        P                  ! W0P                  ,           4      ,          pV P                  VP                  V4      ,          # )rJ   T)Úkeepdiméÿÿÿÿ)	r&   ÚtorS   Úfloat32ÚpowÚmeanÚrsqrtrV   rU   )r2   rY   Úinput_dtypeÚvariances   &&  r4   r:   ÚApertusRMSNorm.forwardE   sw   € Ø#×)Ñ)ˆØ%×(Ñ(¬¯©Ó7ˆØ ×$Ñ$ QÓ'×,Ñ,¨R¸Ð,Ó>ˆØ%¬¯ª°H×?TÑ?TÕ4TÓ(UÕUˆØ�{‰{˜]×-Ñ-¨kÓ:Õ:Ð:r6   c                ó^   € \        V P                  P                  4       R V P                   2# )z, eps=)ÚtuplerU   ÚshaperV   )r2   s   &r4   Ú
extra_reprÚApertusRMSNorm.extra_reprL   s*   € Ü˜Ÿ™×)Ñ)Ó*Ð+¨6°$×2GÑ2GÐ1HÐIÐIr6   )rV   rU   )g�íµ ÷Æ°>)
r=   r>   r?   r@   r(   r:   ri   rA   rB   rC   rD   s   @@r4   rH   rH   ;   s%   ù‡ € ÷$õ $÷;ð ;÷Jò Jr6   rH   c                   óÎ   a a€ ] tR t^Pt o]! RRR7      R
V3R lV 3R lll4       t]]! RRR7      R
V3R lR ll4       4       t]P                  ! 4       ]
R 4       4       tR	tVtV ;t# )ÚApertusRotaryEmbeddingÚdevicez5.18)Úversionc                ó    <€ V ^8„  d   QhRS[ /# ©rJ   r)   r   )rN   rE   s   "€r4   rO   Ú#ApertusRotaryEmbedding.__annotate__R   s   ø€ ÷ Oñ O™}ñ Or6   c                óä  <€ \         SV `  4        VP                  V n        VP                  V n        Wn        V P
                  P                  R ,          V n        V P                  pV P                  R8w  d   \        V P                  ,          pV! V P
                  V4      w  q@n
        \        P                  ! VRR7      V n        \        P                  ! VP                  4       RR7      V n        R# )Ú	rope_typeÚdefaultF)Ú
persistentN)r'   r(   Úmax_position_embeddingsÚmax_seq_len_cachedÚoriginal_max_seq_lenr)   Úrope_parametersrs   Úcompute_default_rope_parametersr   Úattention_scalingr   ÚBufferÚinv_freqÚcloneÚoriginal_inv_freq)r2   r)   rm   Úrope_init_fnr}   r3   s   &&&  €r4   r(   ÚApertusRotaryEmbedding.__init__Q   s¬   ø€ ä‰ÑÔØ"(×"@Ñ"@ˆÔØ$*×$BÑ$BˆÔ!àŒàŸ™×4Ñ4°[ÕAˆŒØ!%×!EÑ!EˆØ�>‰>˜YÔ&Ü.¨t¯~©~Õ>ˆLÙ+7¸¿¹ÀVÓ+LÑ(ˆÔ(äŸ	š	 (°uÔ=ˆŒÜ!#§¢¨8¯>©>Ó+;ÈÔ!NˆÖr6   c                óP   <€ V ^8„  d   QhRS[ RS[S[P                  S[3,          /# )rJ   r)   rL   )r   rg   rS   rZ   rM   )rN   rE   s   "€r4   rO   rq   d   s.   ø€ ÷ 5ñ 5±ð 5ÑY^Ñ_d×_kÑ_kÑmrÐ_rÕYsñ 5r6   c           	     ó0  € V P                   R,          p\        V RR4      ;'       g    V P                  V P                  ,          pRpRV\        P
                  ! ^ V^\        P                  R7      V,          ,          ,          pVP                  V4      V3# )a~  
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%   )ry   Úgetattrr*   Únum_attention_headsrS   ÚarangerM   r^   )r)   rm   ÚkwargsÚbaseÚdimÚattention_factorr}   s   &&,    r4   rz   Ú6ApertusRotaryEmbedding.compute_default_rope_parametersb   s~   € ð ×%Ñ% lÕ3ˆÜ�f˜j¨$Ó/×cÐc°6×3EÑ3EÈ×IcÑIcÕ3cˆàÐà˜$¤5§<¢<°°3¸ÄÇÁÔ#MÐPSÕ#SÕTÕUˆØ�{‰{˜6Ó"Ð$4Ð4Ð4r6   c                ó^  € V P                   R,          P                  VP                  ^ ,          R	^4      P                  \        P
                  VP                  R7      pVR
,          P                  4       p\        VP                  P                  \        4      '       d2   VP                  P                  R8w  d   VP                  P                  MRp\        VRR7      ;_uu_ 4        W4,          P                  ^^4      p\        P                  ! Wf3R	R7      pVP                  4       V P                  ,          pVP                  4       V P                  ,          p	R R R 4       XP                  VP                   R7      X	P                  VP                   R7      3#   + '       g   i     LH; i)N)r&   rm   ÚmpsÚcpuF)Údevice_typeÚenabled©r‹   r%   )NºNNNNr]   )r”   Nr”   )r}   Úexpandrh   r^   rS   rM   rm   Ú
isinstanceÚtypeÚstrr   Ú	transposeÚcatÚcosr{   Úsinr&   )
r2   r9   Úposition_idsÚinv_freq_expandedÚposition_ids_expandedr‘   ÚfreqsÚembr›   rœ   s
   &&&       r4   r:   ÚApertusRotaryEmbedding.forwardv   s2  € ð �M‰M˜-Õ(×/Ñ/°×0BÑ0BÀ1Õ0EÀrÈ1ÓM×PÑPÔW\×WbÑWbÐkl×ksÑksÐPÓtð 	ð !-¨ZÕ 8× >Ñ >Ó @Ðä'1°!·(±(·-±-Ä×'EÒ'EÈ!Ï(É(Ï-É-Ð[`ÔJ`�a—h‘h—m’mÐfkˆä¨¸U×CÖCØ&Õ>×IÑIÈ!ÈQÓOˆEÜ—)’)˜U˜N°Ô3ˆCØ—'‘'“)˜d×4Ñ4Õ4ˆCØ—'‘'“)˜d×4Ñ4Õ4ˆC÷	 Dð �v‰v˜AŸG™GˆvÓ$ c§f¡f°1·7±7 fÓ&;Ð;Ð;÷ D×Cús   Ã(A4FÆF,	)r{   r)   r}   rw   r   rx   rs   r8   )r=   r>   r?   r@   r   r(   Ústaticmethodrz   rS   Úno_gradr   r:   rA   rB   rC   rD   s   @@r4   rl   rl   P   su   ù‡ € Ù�X vÔ.÷Oô Oó /ðOð  Ù�X vÔ.÷5ñ 5ó /ó ð5ð$ ‡]‚]ƒ_Øñ<ó ó ÷<ð <r6   rl   c                óÌ   € V RRV P                   R,          ^,          13,          pV RV P                   R,          ^,          R13,          p\        P                  ! V) V3RR7      # )z*Rotates half the hidden dims of the input..Nr“   r]   )rh   rS   rš   )r9   Úx1Úx2s   &  r4   Úrotate_halfr¨   ‰   sZ   € à	
ˆ3Ð"�!—'‘'˜"•+ Õ"Ð"Ð"Õ	#€BØ	
ˆ3�—‘˜•˜qÕ Ñ"Ð"Õ	#€BÜ�9Š9�r�c˜2�Y BÔ'Ð'r6   Úrotary_pos_embc                óÈ   € VP                  V4      pVP                  V4      pW,          \        V 4      V,          ,           pW,          \        V4      V,          ,           pWV3# )aI  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kr›   rœ   Úunsqueeze_dimÚq_embedÚk_embeds   &&&&&  r4   Úapply_rotary_pos_embr±   �   sS   € ð& �-‰-˜Ó
&€CØ
�-‰-˜Ó
&€CØ�wœ; q›>¨CÕ/Õ0€GØ�wœ; q›>¨CÕ/Õ0€GØÐÐr6   c                ód   € V ^8„  d   QhR\         P                  R\        R\         P                  /# )rJ   rY   Ún_reprL   )rS   rZ   Úint)rN   s   "r4   rO   rO   ª   s.   € ÷ 	Uñ 	UœUŸ\™\ð 	U´#ð 	U¼%¿,¹,ñ 	Ur6   c                ó˜   € V P                   w  r#rEV^8X  d   V # V R,          P                  W#WV4      p V P                  W#V,          WE4      # )zÈ
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”   r”   Nr”   r”   )rh   r•   Úreshape)rY   r³   ÚbatchÚnum_key_value_headsÚslenr…   s   &&    r4   Ú	repeat_kvrº   ª   sU   € ð
 2?×1DÑ1DÑ.€E Ø�„zØÐØ!Ð"2Õ3×:Ñ:¸5ÐW\ÐdlÓm€MØ× Ñ  ¸eÕ(CÀTÓTÐTr6   c                ó   € V ^8„  d   QhR\         P                  R\        P                  R\        P                  R\        P                  R\        P                  R,          R\        R\        R	\
        \        ,          /# )
rJ   ÚmoduleÚqueryÚkeyÚvalueÚattention_maskNÚscalingÚdropoutr‰   )r   ÚModulerS   rZ   rM   r   r   )rN   s   "r4   rO   rO   ¶   sw   € ÷ %ñ %Ü�I‰Ið%ä�<‰<ð%ô 
�‰ð%ô �<‰<ð	%ô
 —L‘L 4Õ'ð%ô ð%ô ð%ô Ô'Õ(ñ%r6   c                 ó"  € \        W P                  4      p\        W0P                  4      p	\        P                  ! WP	                  ^^4      4      V,          p
Ve	   W¤,           p
\
        P                  P                  V
R\        P                  R7      P                  VP                  4      p
\
        P                  P                  W¦V P                  R7      p
\        P                  ! W©4      pVP	                  ^^4      P                  4       pWº3# )rJ   )r‹   r&   )ÚpÚtrainingr]   )rº   Únum_key_value_groupsrS   Úmatmulr™   r   Ú
functionalÚsoftmaxr_   r^   r&   rÂ   rÆ   Ú
contiguous)r¼   r½   r¾   r¿   rÀ   rÁ   rÂ   r‰   Ú
key_statesÚvalue_statesÚattn_weightsÚattn_outputs   &&&&&&&,    r4   Úeager_attention_forwardrÐ   ¶   sÒ   € ô ˜3× ;Ñ ;Ó<€JÜ˜U×$?Ñ$?Ó@€Lä—<’< ×';Ñ';¸A¸qÓ'AÓBÀWÕL€LØÒ!Ø#Õ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$Ð$r6   c                   ó\   a a€ ] tR t^Ït oRtRV3R lV 3R llltRV3R lR lltRtVtV ;t	# )ÚApertusAttentionz=Multi-headed attention from 'Attention Is All You Need' paperc                ó4   <€ V ^8„  d   QhRS[ RS[R,          /# )rJ   r)   Ú	layer_idxN©r   r´   )rN   rE   s   "€r4   rO   ÚApertusAttention.__annotate__Ó   s#   ø€ ÷ Iñ I™}ð I¹¸t½ñ Ir6   c                ó6  <€ \         SV `  4        Wn        W n        \	        VR VP
                  VP                  ,          4      V n        VP                  VP                  ,          V n	        V P                  R,          V n
        VP                  V n        RV n        \        P                  ! VP
                  VP                  V P                  ,          VP                  R7      V n        \        P                  ! VP
                  VP                  V P                  ,          VP                  R7      V n        \        P                  ! VP
                  VP                  V P                  ,          VP                  R7      V n        \        P                  ! VP                  V P                  ,          VP
                  VP                  R7      V n        \)        V P                  VP*                  4      V n        \)        V P                  VP*                  4      V n        R# )r…   Tr"   Ng      à¿)r'   r(   r)   rÔ   r†   r*   r‡   r…   r¸   rÇ   rÁ   Úattention_dropoutÚ	is_causalr   r,   Úattention_biasÚq_projÚk_projÚv_projÚo_projrH   Úrms_norm_epsÚq_normÚk_norm©r2   r)   rÔ   r3   s   &&&€r4   r(   ÚApertusAttention.__init__Ó   s{  ø€ Ü‰ÑÔØŒØ"ŒÜ ¨
°F×4FÑ4FÈ&×JdÑJdÕ4dÓeˆŒØ$*×$>Ñ$>À&×B\ÑB\Õ$\ˆÔ!Ø—}‘} dÕ*ˆŒØ!'×!9Ñ!9ˆÔØˆŒä—i’iØ×Ñ × :Ñ :¸T¿]¹]Õ JÐQW×QfÑQfô
ˆŒô —i’iØ×Ñ × :Ñ :¸T¿]¹]Õ JÐQW×QfÑQfô
ˆŒô —i’iØ×Ñ × :Ñ :¸T¿]¹]Õ JÐQW×QfÑQfô
ˆŒô —i’iØ×&Ñ&¨¯©Õ6¸×8JÑ8JÐQW×QfÑQfô
ˆŒô % T§]¡]°F×4GÑ4GÓHˆŒÜ$ T§]¡]°F×4GÑ4GÓHˆŽr6   c                ó  <€ V ^8„  d   QhRS[ P                  RS[S[ P                  S[ P                  3,          RS[ P                  R,          RS[R,          RS[S[,          RS[S[ P                  S[ P                  3,          /# )rJ   rY   Úposition_embeddingsrÀ   NÚpast_key_valuesr‰   rL   )rS   rZ   rg   r   r   r   )rN   rE   s   "€r4   rO   rÖ   ì   s‚   ø€ ÷ ()ñ ()á—|‘|ð()ñ #¡5§<¡<±·±Ð#=Õ>ð()ñ Ÿ™ tÕ+ð	()ñ
  �ð()ñ Ñ+Õ,ð()ñ 
‰u�|‰|™UŸ\™\Ð)Õ	*ñ()r6   c                óT  € VP                   R R p. VORNV P                  N5pV P                  V4      P                  V4      P	                  ^^4      pV P                  V4      P                  V4      P	                  ^^4      p	V P                  V4      P                  V4      P	                  ^^4      p
V P                  V4      pV P                  V	4      p	Vw  r¼\        W‰W¼4      w  r‰Ve   VP                  WšV P                  4      w  rš\        P                  ! V P                  P                  \         4      pT! V VV	V
V3RV P"                  '       g   RMV P$                  RV P&                  /VB w  rïVP(                  ! . VORN5!  P+                  4       pV P-                  V4      pWï3# )NrÂ   ç        rÁ   r]   )rh   r…   rÛ   Úviewr™   rÜ   rÝ   rà   rá   r±   ÚupdaterÔ   r   Úget_interfacer)   Ú_attn_implementationrÐ   rÆ   rØ   rÁ   r¶   rË   rÞ   )r2   rY   rå   rÀ   ræ   r‰   Úinput_shapeÚhidden_shapeÚquery_statesrÌ   rÍ   r›   rœ   Úattention_interfacerÏ   rÎ   s   &&&&&,          r4   r:   ÚApertusAttention.forwardì   s£  € ð $×)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Ø—{‘{ <Ó0ˆØ—[‘[ Ó,ˆ
à&‰ˆÜ#7¸ÐRUÓ#[Ñ ˆàÒ&Ø'6×'=Ñ'=¸jÐX\×XfÑXfÓ'gÑ$ˆJä(?×(MÒ(MØ�K‰K×,Ñ,Ô.Eó)
Ðñ %8ØØØØØñ	%
ð  $Ÿ}Ÿ}˜}‘C°$×2HÑ2Hð	%
ð —L‘Lð	%
ð ñ	%
Ñ!ˆð "×)Ò)Ð;¨;Ð;¸Ó;×FÑFÓHˆØ—k‘k +Ó.ˆØÐ(Ð(r6   )rØ   r)   r…   rÙ   rá   rÜ   rÔ   rÇ   rÞ   rà   rÛ   rÁ   rÝ   r8   )
r=   r>   r?   r@   Ú__doc__r(   r:   rA   rB   rC   rD   s   @@r4   rÒ   rÒ   Ï   s#   ù‡ € áG÷Iõ I÷2()÷ ()ò ()r6   rÒ   c                   óT   a a€ ] tR tRt oV3R lV 3R lltRV3R lR lltRtVtV ;t# )ÚApertusDecoderLayeri  c                ó&   <€ V ^8„  d   QhRS[ RS[/# )rJ   r)   rÔ   rÕ   )rN   rE   s   "€r4   rO   Ú ApertusDecoderLayer.__annotate__  s   ø€ ÷ añ a™}ð a¹ñ ar6   c                ó   <€ \         SV `  4        VP                  V n        \        WR 7      V n        \        V4      V n        \        VP                  VP                  R7      V n	        \        VP                  VP                  R7      V n
        R# ))r)   rÔ   ©rK   N)r'   r(   r*   rÒ   Ú	self_attnr    ÚmlprH   rß   Úattention_layernormÚfeedforward_layernormrâ   s   &&&€r4   r(   ÚApertusDecoderLayer.__init__  sj   ø€ Ü‰ÑÔØ!×-Ñ-ˆÔä)°ÔMˆŒä˜fÓ%ˆŒÜ#1°&×2DÑ2DÈ&×J]ÑJ]Ô#^ˆÔ Ü%3°F×4FÑ4FÈF×L_ÑL_Ô%`ˆÖ"r6   c                ó.  <€ V ^8„  d   QhRS[ P                  RS[ P                  R,          RS[ P                  R,          RS[R,          RS[R,          RS[S[ P                  S[ P                  3,          R,          RS[S[,          R	S[ P                  /# )
rJ   rY   rÀ   Nr�   ræ   Ú	use_cacherå   r‰   rL   )rS   rZ   Ú
LongTensorr   Úboolrg   r   r   )rN   rE   s   "€r4   rO   rö   "  sœ   ø€ ÷ ñ á—|‘|ðñ Ÿ™ tÕ+ðñ ×&Ñ&¨Õ-ð	ñ
  �ðñ ˜$•;ðñ #¡5§<¡<±·±Ð#=Õ>ÀÕEðñ Ñ+Õ,ðñ 
�‰ñr6   c                óÔ   € TpV P                  V4      pV P                  ! RR VRVRVRVRVRV/VB w  rW�,           pTpV P                  V4      pV P                  V4      pW�,           pV# )rY   rÀ   r�   ræ   rÿ   rå   © )rû   rù   rü   rú   )
r2   rY   rÀ   r�   ræ   rÿ   rå   r‰   ÚresidualÚ_s
   &&&&&&&,  r4   r:   ÚApertusDecoderLayer.forward"  s©   € ð !ˆØ×0Ñ0°Ó?ˆØŸ>š>ñ 
Ø'ð
à)ð
ð &ð
ð ,ð	
ð
  ð
ð !4ð
ð ñ
Ñˆð !Õ0ˆð !ˆØ×2Ñ2°=ÓAˆØŸ™ Ó/ˆØ Õ0ˆØÐr6   )rû   rü   r*   rú   rù   )NNNFNr<   rD   s   @@r4   rô   rô     s    ù‡ € ÷aó a÷÷ ò r6   rô   c                   ó`   a € ] tR tRt o RtRtR.tR.tRtRt	Rt
RtRtR]R]/tV 3R ltR	tV tR
# )ÚApertusPreTrainedModeliA  ÚmodelTrô   ræ   rY   Ú
attentionsc                ó&   <€ V ^8„  d   Qh/ S[ ;R&   # rp   r   )rN   rE   s   "€r4   rO   Ú#ApertusPreTrainedModel.__annotate__A  s   ø‡ ‚ áÑò r6   r  N)r=   r>   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_backendrô   rÒ   Ú_can_record_outputsÚ__annotate_func__rA   rB   )rE   s   @r4   r  r  A  s]   ø‡ € ð  ÐØ&*Ð#Ø.Ð/ÐØ#4Ð"5ÐØÐØ€NØÐà!ÐØ"&ÐàÐ,ØÐ&ðÐ÷ ƒ r6   r  c                   ór   a a€ ] tR tRt oV3R lV 3R llt]]]RV3R lR ll4       4       4       tRt	Vt
V ;t# )ÚApertusModeliT  c                ó    <€ V ^8„  d   QhRS[ /# rp   r   )rN   rE   s   "€r4   rO   ÚApertusModel.__annotate__V  s   ø€ ÷ ñ ™}ñ r6   c           	     ó  <€ \         SV `  V4       VP                  V n        VP                  V n        \
        P                  ! VP                  VP                  V P                  4      V n        \
        P                  ! \        VP                  4       Uu. uF  p\        W4      NK  	  up4      V n        \        VP                  VP                  R 7      V n        \#        VR7      V n        RV n        V P)                  4        R# u upi )rø   ©r)   FN)r'   r(   Úpad_token_idÚpadding_idxÚ
vocab_sizer   Ú	Embeddingr*   Úembed_tokensÚ
ModuleListÚrangeÚnum_hidden_layersrô   ÚlayersrH   rß   Únormrl   Ú
rotary_embÚgradient_checkpointingÚ	post_initrâ   s   && €r4   r(   ÚApertusModel.__init__V  sÊ   ø€ Ü‰Ñ˜Ô Ø!×.Ñ.ˆÔØ ×+Ñ+ˆŒäŸLšL¨×):Ñ):¸F×<NÑ<NÐPT×P`ÑP`ÓaˆÔÜ—m’mÜEJÈ6×KcÑKcÔEdÓeÑEd¸	Ô  Ö3ÑEdÑeó
ˆŒô # 6×#5Ñ#5¸6×;NÑ;NÔOˆŒ	Ü0¸Ô?ˆŒØ&+ˆÔ#ð 	�‰Öùò fs   ÂDc                óþ   <€ V ^8„  d   QhRS[ P                  R,          RS[ P                  R,          RS[ P                  R,          RS[R,          RS[ P                  R,          RS[R,          RS[S[,          R	S[/# )
rJ   Ú	input_idsNrÀ   r�   ræ   Úinputs_embedsrÿ   r‰   rL   )	rS   r   rZ   r   ÚFloatTensorr  r   r   r   )rN   rE   s   "€r4   rO   r  i  s“   ø€ ÷ 2
ñ 2
á×#Ñ# dÕ*ð2
ñ Ÿ™ tÕ+ð2
ñ ×&Ñ&¨Õ-ð	2
ñ
  �ð2
ñ ×(Ñ(¨4Õ/ð2
ñ ˜$•;ð2
ñ Ñ+Õ,ð2
ñ 
!ñ2
r6   c                óˆ  € VR J VR J,          '       d   \        R4      hVf   V P                  V4      pV'       d   Vf   \        V P                  R7      pVfb   Ve   VP	                  4       M^ p\
        P                  ! VP                  ^,          VP                  R7      V,           pVP                  ^ 4      p\        V P                  VVVVR7      p	Tp
V P                  W£R7      pV P                  R V P                  P                    F  pV! V
3RV	RVRVR	VR
V/VB p
K  	  V P                  V
4      p
\        V
VR7      # )Nz:You must specify exactly one of input_ids or inputs_embedsr  )rm   )r)   r.  rÀ   ræ   r�   )r�   rÀ   rå   r�   ræ   rÿ   )Úlast_hidden_stateræ   )Ú
ValueErrorr"  r   r)   Úget_seq_lengthrS   rˆ   rh   rm   r«   r   r(  r&  r%  r'  r   )r2   r-  rÀ   r�   ræ   r.  rÿ   r‰   Úpast_seen_tokensÚcausal_maskrY   rå   Údecoder_layers   &&&&&&&,     r4   r:   ÚApertusModel.forwardf  se  € ð ˜Ð -°tÐ";×<Ô<ÜÐYÓZÐZàÒ Ø*.×*;Ñ*;¸IÓ*FˆMç˜Ò0Ü*°$·+±+Ô>ˆOàÒØCRÒC^˜×=Ñ=Ô?ÐdeÐÜ Ÿ<š<¨×(;Ñ(;¸AÕ(>À}×G[ÑG[Ô\Ð_oÕoˆLØ'×1Ñ1°!Ó4ˆLä(Ø—;‘;Ø'Ø)Ø+Ø%ô
ˆð &ˆØ"Ÿo™o¨m˜oÓWÐà!Ÿ[™[Ð)H¨4¯;©;×+HÑ+HÓIˆMÙ)Øñà*ðð %8ðð *ð	ð
 !0ðð $ðð ñŠMñ Jð Ÿ	™	 -Ó0ˆÜ&Ø+Ø+ô
ð 	
r6   )r"  r)  r&  r'  r  r(  r   )NNNNNN)r=   r>   r?   r@   r(   r   r   r   r:   rA   rB   rC   rD   s   @@r4   r  r  T  s=   ù‡ € ÷ó ð   ØØ÷2
ñ 2
ó ó ó  ÷2
ð 2
r6   r  c                   ó„   a a€ ] tR tRt oRR/tRR/tRR.R.3/tRR/tV 3R	 lt]	]
RV3R
 lR ll4       4       tRtVtV ;t# )ÚApertusForCausalLMiž  zlm_head.weightzmodel.embed_tokens.weightÚlm_headÚcolwise_gather_outputrY   ÚlogitsÚkeep_full_weightc                óì   <€ \         SV `  V4       \        V4      V n        VP                  V n        \
        P                  ! VP                  VP                  R R7      V n        V P                  4        R# )Fr"   N)
r'   r(   r  r	  r   r   r,   r*   r:  r*  r1   s   &&€r4   r(   ÚApertusForCausalLM.__init__¥  sU   ø€ Ü‰Ñ˜Ô Ü! &Ó)ˆŒ
Ø ×+Ñ+ˆŒÜ—y’y ×!3Ñ!3°V×5FÑ5FÈUÔSˆŒð 	�‰Ör6   c                óP  <€ V ^8„  d   QhRS[ P                  R,          RS[ P                  R,          RS[ P                  R,          RS[R,          RS[ P                  R,          RS[ P                  R,          RS[R,          R	S[S[ P                  ,          R
S[S[,          RS[	/
# )rJ   r-  NrÀ   r�   ræ   r.  Úlabelsrÿ   Úlogits_to_keepr‰   rL   )
rS   r   rZ   r   r/  r  r´   r   r   r   )rN   rE   s   "€r4   rO   ÚApertusForCausalLM.__annotate__°  s»   ø€ ÷ ;
ñ ;
á×#Ñ# dÕ*ð;
ñ Ÿ™ tÕ+ð;
ñ ×&Ñ&¨Õ-ð	;
ñ
  �ð;
ñ ×(Ñ(¨4Õ/ð;
ñ × Ñ  4Õ'ð;
ñ ˜$•;ð;
ñ ™eŸl™lÕ*ð;
ñ Ñ+Õ,ð;
ñ 
 ñ;
r6   c	                ó–  € V P                   ! RRVRVRVRVRVRV/V	B p
V
P                  p\        V\        4      '       d   \	        V) R4      MTpV P                  VRVR3,          4      pRpVe-   V P                  ! RR	VR
VRV P                  P                  /V	B p\        VVV
P                  V
P                  V
P                  R7      # )a
  
labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
    Labels for computing the masked language modeling loss. Indices should either be in `[0, ...,
    config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored
    (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`.

Example:

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

>>> model = ApertusForCausalLM.from_pretrained("swiss-ai/Apertus-8B-Instruct-2509")
>>> tokenizer = AutoTokenizer.from_pretrained("swiss-ai/Apertus-8B-Instruct-2509")

>>> 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."
```r-  rÀ   r�   ræ   r.  rÿ   Nr”   r<  rA  r   )Úlossr<  ræ   rY   r
  r  )r	  r1  r–   r´   Úslicer:  Úloss_functionr)   r   r   ræ   rY   r
  )r2   r-  rÀ   r�   ræ   r.  rA  rÿ   rB  r‰   ÚoutputsrY   Úslice_indicesr<  rE  s   &&&&&&&&&,     r4   r:   ÚApertusForCausalLM.forward®  s   € ðH ,0¯:ª:ñ ,
Øð,
à)ð,
ð &ð,
ð ,ð	,
ð
 (ð,
ð  ð,
ð ñ,
ˆð  ×1Ñ1ˆä8BÀ>ÔSV×8WÒ8Wœ˜~˜o¨tÔ4Ð]kˆØ—‘˜m¨A¨}¸aÐ,?Õ@ÓAˆàˆØÒØ×%Ò%Ñp¨VÐp¸FÐpÈtÏ{É{×OeÑOeÐpÐioÑpˆDä%ØØØ#×3Ñ3Ø!×/Ñ/Ø×)Ñ)ô
ð 	
r6   )r:  r	  r   )NNNNNNNr   )r=   r>   r?   r@   Ú_tied_weights_keysÚ_tp_planÚ_pp_planÚ
_fsdp_planr(   r   r   r:   rA   rB   rC   rD   s   @@r4   r9  r9  ž  sf   ù‡ € à*Ð,GÐHÐØÐ2Ð3€HØ˜_Ð-°¨zÐ:Ð;€HØÐ/Ð0€Jõð Ø÷;
ñ ;
ó ó ÷;
ð ;
r6   r9  c                   ó   € ] tR tRtRtR# )ÚApertusForTokenClassificationiî  r  N)r=   r>   r?   r@   rA   r  r6   r4   rP  rP  î  s   † Ûr6   rP  )é   )rè   )r  r9  rP  r  );Úcollections.abcr   rS   r   Úactivationsr   r   Úcache_utilsr   r   Ú
generationr	   Úintegrationsr
   r   Úmasking_utilsr   Úmodeling_layersr   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_apertusr   rÃ   r    rH   rl   r¨   r±   rº   rÐ   rÒ   rô   r  r  r9  rP  Ú__all__r  r6   r4   Ú<module>rc     s^  ðõ* %ã Ý ç *ß .Ý )ß LÝ /ß Xß Oß Kß FÝ &ß IÑ IÝ 0ß GÝ 5Ý 0ô<�—‘ô <ñ  ˜YÓ'ôJ�R—Y‘Yó Jó (ðJô(6<˜RŸY™Yô 6<òr(ñ Ð-Ó.óó /ðõ2	U÷%ñ2 Ð)Ó*ôD)�r—y‘yó D)ó +ðD)ôN'Ð4ô 'ðT ô˜_ó ó ðð$ ôF
Ð)ó F
ó ðF
ðR ôL
Ð/°ó L
ó ðL
ô^	Ð$AÐCYô 	ò l‚r6   