+
    œ°³jÍS  ã                   óB  € ^ RI Ht ^ RIt^ RIHt ^ RI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 ^R
IHtHt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$t$ ^RI%H&t& ^RI'H(t(H)t) ^RI*H+t+ ^RI,H-t-  ! R R]P\                  4      t/]! R4       ! R R]P\                  4      4       t0 ! R R]P\                  4      t1R t2]! R4      R4R l4       t3R R lt4R5R  R! llt5]! ]34       ! R" R#]P\                  4      4       t6 ! R$ R%]4      t7] ! R& R']4      4       t8] ! R( R)]84      4       t9]! R*R+7       ! R, R-]8]4      4       t:]! R*R+7       ! R. R/]]84      4       t;]! R*R+7       ! R0 R1]]84      4       t<]! R*R+7       ! R2 R3]]84      4       t=. R6Ot>R# )7é    )ÚCallableN)Únn)Úauto_docstring)ÚACT2FN)ÚCacheÚDynamicCache)ÚGenerationMixin)Úuse_kernel_forward_from_hubÚuse_kernelized_func)Úcreate_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can_return_tuple)Údeprecate_kwarg)Úmaybe_autocastÚmerge_with_config_defaults)Úcapture_outputs©ÚArceeConfigc                   ó8   a a€ ] tR t^2t oV 3R ltR tRtVtV ;t# )ÚArceeMLPc                óœ  <€ \         SV `  4        Wn        VP                  V n        VP                  V n        \
        P                  ! V P                  V P                  VP                  R 7      V n        \
        P                  ! V P                  V P                  VP                  R 7      V n	        \        VP                  ,          V n        R# )©ÚbiasN)ÚsuperÚ__init__ÚconfigÚhidden_sizeÚintermediate_sizer   ÚLinearÚmlp_biasÚup_projÚ	down_projr   Ú
hidden_actÚact_fn©Úselfr'   Ú	__class__s   &&€Úi/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/arcee/modeling_arcee.pyr&   ÚArceeMLP.__init__3   s�   ø€ Ü‰ÑÔØŒØ!×-Ñ-ˆÔØ!'×!9Ñ!9ˆÔÜ—y’y ×!1Ñ!1°4×3IÑ3IÐPV×P_ÑP_Ô`ˆŒÜŸš 4×#9Ñ#9¸4×;KÑ;KÐRX×RaÑRaÔbˆŒÜ˜V×.Ñ.Õ/ˆŽó    c                ó`   € V P                  V P                  V P                  V4      4      4      # ©N)r-   r/   r,   )r1   Úxs   &&r3   ÚforwardÚArceeMLP.forward<   s"   € Ø�~‰~˜dŸk™k¨$¯,©,°q«/Ó:Ó;Ð;r5   )r/   r'   r-   r(   r)   r,   ©	Ú__name__Ú
__module__Ú__qualname__Ú__firstlineno__r&   r9   Ú__static_attributes__Ú__classdictcell__Ú__classcell__©r2   Ú__classdict__s   @@r3   r!   r!   2   s   ù‡ € õ0÷<ò <r5   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ArceeRMSNormc                ó$   <€ V ^8„  d   QhRS[ RR/# )é   ÚepsÚreturnN)Úfloat)ÚformatrD   s   "€r3   Ú__annotate__ÚArceeRMSNorm.__annotate__B   s   ø€ ÷ $ñ $©ð $¸$ñ $r5   c                óŽ   <€ \         SV `  4        \        P                  ! \        P
                  ! V4      4      V n        W n        R# )z+
ArceeRMSNorm is equivalent to T5LayerNorm
N)r%   r&   r   Ú	ParameterÚtorchÚonesÚweightÚvariance_epsilon)r1   r(   rJ   r2   s   &&&€r3   r&   ÚArceeRMSNorm.__init__B   s/   ø€ ô 	‰ÑÔÜ—l’l¤5§:¢:¨kÓ#:Ó;ˆŒØ #Ör5   c                óN   <€ V ^8„  d   QhRS[ P                  RS[ P                  /# )rI   Úhidden_statesrK   )rR   ÚTensor)rM   rD   s   "€r3   rN   rO   J   s#   ø€ ÷ ;ñ ;¡U§\¡\ð ;±e·l±lñ ;r5   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      ,          # )rI   T)Úkeepdiméÿÿÿÿ)	ÚdtypeÚtorR   Úfloat32ÚpowÚmeanÚrsqrtrU   rT   )r1   rX   Úinput_dtypeÚvariances   &&  r3   r9   ÚArceeRMSNorm.forwardJ   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:r5   c                ó^   € \        V P                  P                  4       R V P                   2# )z, eps=)ÚtuplerT   ÚshaperU   )r1   s   &r3   Ú
extra_reprÚArceeRMSNorm.extra_reprQ   s*   € Ü˜Ÿ™×)Ñ)Ó*Ð+¨6°$×2GÑ2GÐ1HÐIÐIr5   )rU   rT   )g�íµ ÷Æ°>)
r<   r=   r>   r?   r&   r9   ri   r@   rA   rB   rC   s   @@r3   rG   rG   @   s%   ù‡ € ÷$õ $÷;ð ;÷Jò Jr5   rG   c                   óÎ   a a€ ] tR t^Ut o]! RRR7      R
V3R lV 3R lll4       t]]! RRR7      R
V3R lR ll4       4       t]P                  ! 4       ]
R 4       4       tR	tVtV ;t# )ÚArceeRotaryEmbeddingÚdevicez5.18)Úversionc                ó    <€ V ^8„  d   QhRS[ /# ©rI   r'   r   )rM   rD   s   "€r3   rN   Ú!ArceeRotaryEmbedding.__annotate__W   s   ø€ ÷ Oñ O™{ñ Or5   c                óä  <€ \         SV `  4        VP                  V n        VP                  V n        Wn        V P
                  P                  R ,          V n        V P                  pV P                  R8w  d   \        V P                  ,          pV! V P
                  V4      w  q@n
        \        P                  ! VRR7      V n        \        P                  ! VP                  4       RR7      V n        R# )Ú	rope_typeÚdefaultF)Ú
persistentN)r%   r&   Úmax_position_embeddingsÚmax_seq_len_cachedÚoriginal_max_seq_lenr'   Úrope_parametersrs   Úcompute_default_rope_parametersr   Úattention_scalingr   ÚBufferÚinv_freqÚcloneÚoriginal_inv_freq)r1   r'   rm   Úrope_init_fnr}   r2   s   &&&  €r3   r&   ÚArceeRotaryEmbedding.__init__V   s¬   ø€ ä‰ÑÔØ"(×"@Ñ"@ˆÔØ$*×$BÑ$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r5   c                óP   <€ V ^8„  d   QhRS[ RS[S[P                  S[3,          /# )rI   r'   rK   )r   rg   rR   rY   rL   )rM   rD   s   "€r3   rN   rq   i   s.   ø€ ÷ 5ñ 5±ð 5ÑW\Ñ]b×]iÑ]iÑkpÐ]pÕWqñ 5r5   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_headsrR   ÚarangerL   r^   )r'   rm   ÚkwargsÚbaseÚdimÚattention_factorr}   s   &&,    r3   rz   Ú4ArceeRotaryEmbedding.compute_default_rope_parametersg   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$4Ð4Ð4r5   c                ó^  € V P                   R,          P                  VP                  ^ ,          R	^4      P                  \        P
                  VP                  R7      pVR
,          P                  4       p\        VP                  P                  \        4      '       d2   VP                  P                  R8w  d   VP                  P                  MRp\        VRR7      ;_uu_ 4        W4,          P                  ^^4      p\        P                  ! Wf3R	R7      pVP                  4       V P                  ,          pVP                  4       V P                  ,          p	R R R 4       XP                  VP                   R7      X	P                  VP                   R7      3#   + '       g   i     LH; i)N)r]   rm   ÚmpsÚcpuF)Údevice_typeÚenabled©rŒ   r†   )NºNNNNr\   )r•   Nr•   )r}   Úexpandrh   r^   rR   rL   rm   Ú
isinstanceÚtypeÚstrr   Ú	transposeÚcatÚcosr{   Úsinr]   )
r1   r8   Úposition_idsÚinv_freq_expandedÚposition_ids_expandedr’   ÚfreqsÚembrœ   r�   s
   &&&       r3   r9   ÚArceeRotaryEmbedding.forward{   s2  € ð �M‰M˜-Õ(×/Ñ/°×0BÑ0BÀ1Õ0EÀrÈ1ÓM×PÑPÔW\×WbÑWbÐkl×ksÑksÐPÓtð 	ð !-¨ZÕ 8× >Ñ >Ó @Ðä'1°!·(±(·-±-Ä×'EÒ'EÈ!Ï(É(Ï-É-Ð[`ÔJ`�a—h‘h—m’mÐfkˆä¨¸U×CÖCØ&Õ>×IÑIÈ!ÈQÓOˆEÜ—)’)˜U˜N°Ô3ˆCØ—'‘'“)˜d×4Ñ4Õ4ˆCØ—'‘'“)˜d×4Ñ4Õ4ˆC÷	 Dð �v‰v˜AŸG™GˆvÓ$ c§f¡f°1·7±7 fÓ&;Ð;Ð;÷ D×Cús   Ã(A4FÆF,	)r{   r'   r}   rw   r   rx   rs   r7   )r<   r=   r>   r?   r   r&   Ústaticmethodrz   rR   Úno_gradr   r9   r@   rA   rB   rC   s   @@r3   rl   rl   U   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 <r5   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   rR   r›   )r8   Úx1Úx2s   &  r3   Úrotate_halfr©   Ž   sZ   € à	
ˆ3Ð"�!—'‘'˜"•+ Õ"Ð"Ð"Õ	#€BØ	
ˆ3�—‘˜•˜qÕ Ñ"Ð"Õ	#€BÜ�9Š9�r�c˜2�Y BÔ'Ð'r5   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krœ   r�   Úunsqueeze_dimÚq_embedÚk_embeds   &&&&&  r3   Úapply_rotary_pos_embr²   •   sS   € ð& �-‰-˜Ó
&€CØ
�-‰-˜Ó
&€CØ�wœ; q›>¨CÕ/Õ0€GØ�wœ; q›>¨CÕ/Õ0€GØÐÐr5   c                ód   € V ^8„  d   QhR\         P                  R\        R\         P                  /# )rI   rX   Ún_reprK   )rR   rY   Úint)rM   s   "r3   rN   rN   ¯   s.   € ÷ 	Uñ 	UœUŸ\™\ð 	U´#ð 	U¼%¿,¹,ñ 	Ur5   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)rX   r´   ÚbatchÚnum_key_value_headsÚslenr…   s   &&    r3   Ú	repeat_kvr»   ¯   sU   € ð
 2?×1DÑ1DÑ.€E Ø�„zØÐØ!Ð"2Õ3×:Ñ:¸5ÐW\ÐdlÓm€MØ× Ñ  ¸eÕ(CÀTÓTÐTr5   c                ó   € V ^8„  d   QhR\         P                  R\        P                  R\        P                  R\        P                  R\        P                  R,          R\        R\        R	\
        \        ,          /# )
rI   ÚmoduleÚqueryÚkeyÚvalueÚattention_maskNÚscalingÚdropoutrŠ   )r   ÚModulerR   rY   rL   r   r   )rM   s   "r3   rN   rN   »   sw   € ÷ %ñ %Ü�I‰Ið%ä�<‰<ð%ô 
�‰ð%ô �<‰<ð	%ô
 —L‘L 4Õ'ð%ô ð%ô ð%ô Ô'Õ(ñ%r5   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# )rI   )rŒ   r]   )ÚpÚtrainingr\   )r»   Únum_key_value_groupsrR   Úmatmulrš   r   Ú
functionalÚsoftmaxr_   r^   r]   rÃ   rÇ   Ú
contiguous)r½   r¾   r¿   rÀ   rÁ   rÂ   rÃ   rŠ   Ú
key_statesÚvalue_statesÚattn_weightsÚattn_outputs   &&&&&&&,    r3   Úeager_attention_forwardrÑ   »   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$Ð$r5   c                   óX   a a€ ] tR t^Ôt oRt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ArceeAttentionz=Multi-headed attention from 'Attention Is All You Need' paperc                ó&   <€ V ^8„  d   QhRS[ RS[/# ©rI   r'   Ú	layer_idx©r   rµ   )rM   rD   s   "€r3   rN   ÚArceeAttention.__annotate__Ø   s   ø€ ÷ 
ñ 
™{ð 
±sñ 
r5   c                ó¢  <€ \         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        R# )r…   Tr#   Ng      à¿)r%   r&   r'   rÖ   r‡   r(   rˆ   r…   r¹   rÈ   rÂ   Úattention_dropoutÚ	is_causalr   r*   Úattention_biasÚq_projÚk_projÚv_projÚo_proj©r1   r'   rÖ   r2   s   &&&€r3   r&   ÚArceeAttention.__init__Ø   sI  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Žr5   c                ó  <€ V ^8„  d   QhRS[ P                  RS[S[ P                  S[ P                  3,          R,          RS[ P                  R,          RS[R,          RS[S[,          RS[S[ P                  S[ P                  3,          /# )rI   rX   Úposition_embeddingsNrÁ   Úpast_key_valuesrŠ   rK   )rR   rY   rg   r   r   r   )rM   rD   s   "€r3   rN   rØ   ï   s‡   ø€ ÷ &)ñ &)á—|‘|ð&)ñ #¡5§<¡<±·±Ð#=Õ>ÀÕEð&)ñ Ÿ™ tÕ+ð	&)ñ
  �ð&)ñ Ñ+Õ,ð&)ñ 
‰u�|‰|™UŸ\™\Ð)Õ	*ñ&)r5   c                ó  € 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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$                  ! . VORN5!  P'                  4       pV P)                  V4      pWï3# )NrÃ   ç        rÂ   r\   )rh   r…   rÝ   Úviewrš   rÞ   rß   r²   ÚupdaterÖ   r   Úget_interfacer'   Ú_attn_implementationrÑ   rÇ   rÚ   rÂ   r·   rÌ   rà   )r1   rX   rä   rÁ   rå   rŠ   Úinput_shapeÚhidden_shapeÚquery_statesrÍ   rÎ   rœ   r�   Úattention_interfacerÐ   rÏ   s   &&&&&,          r3   r9   ÚArceeAttention.forwardï   s‡  € ð $×)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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(r5   )rÚ   r'   r…   rÛ   rÞ   rÖ   rÈ   rà   rÝ   rÂ   rß   )NNN)
r<   r=   r>   r?   Ú__doc__r&   r9   r@   rA   rB   rC   s   @@r3   rÓ   rÓ   Ô   s!   ù‡ € áG÷
ó 
÷.&)÷ &)ò &)r5   rÓ   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ArceeDecoderLayeri  c                ó&   <€ V ^8„  d   QhRS[ RS[/# rÕ   r×   )rM   rD   s   "€r3   rN   ÚArceeDecoderLayer.__annotate__  s   ø€ ÷ bñ b™{ð b±sñ br5   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'   rÖ   ©rJ   N)r%   r&   r(   rÓ   Ú	self_attnr!   ÚmlprG   Úrms_norm_epsÚinput_layernormÚpost_attention_layernormrá   s   &&&€r3   r&   ÚArceeDecoderLayer.__init__  sj   ø€ Ü‰ÑÔØ!×-Ñ-ˆÔä'¨vÔKˆŒä˜FÓ#ˆŒÜ+¨F×,>Ñ,>ÀF×DWÑDWÔXˆÔÜ(4°V×5GÑ5GÈV×M`ÑM`Ô(aˆÖ%r5   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                  /# )
rI   rX   rÁ   Nrž   rå   Ú	use_cacherä   rŠ   rK   )rR   rY   Ú
LongTensorr   Úboolrg   r   r   )rM   rD   s   "€r3   rN   rõ   #  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r5   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# )rX   rÁ   rž   rå   rÿ   rä   © )rû   rø   rü   rù   )
r1   rX   rÁ   rž   rå   rÿ   rä   rŠ   ÚresidualÚ_s
   &&&&&&&,  r3   r9   ÚArceeDecoderLayer.forward#  s©   € ð !ˆØ×,Ñ,¨]Ó;ˆà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×5Ñ5°mÓDˆØŸ™ Ó/ˆØ Õ0ˆØÐr5   )r(   rû   rù   rü   rø   )NNNFNr;   rC   s   @@r3   ró   ró     s    ù‡ € ÷bó b÷÷ ò r5   ró   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ArceePreTrainedModeliC  ÚmodelTró   rå   rX   Ú
attentionsc                ó&   <€ V ^8„  d   Qh/ S[ ;R&   # rp   r   )rM   rD   s   "€r3   rN   Ú!ArceePreTrainedModel.__annotate__C  s   ø‡ ‚ áÑò r5   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_backendró   rÓ   Ú_can_record_outputsÚ__annotate_func__r@   rA   )rD   s   @r3   r  r  C  s\   ø‡ € ð  ÐØ&*Ð#Ø,Ð-ÐØ#4Ð"5ÐØÐØ€NØÐà!ÐØ"&ÐàÐ*Ø�nðÐ÷ ƒ r5   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
ArceeModeliV  c                ó    <€ V ^8„  d   QhRS[ /# rp   r   )rM   rD   s   "€r3   rN   ÚArceeModel.__annotate__X  s   ø€ ÷ ñ ™{ñ r5   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 )r÷   ©r'   FN)r%   r&   Úpad_token_idÚpadding_idxÚ
vocab_sizer   Ú	Embeddingr(   Úembed_tokensÚ
ModuleListÚrangeÚnum_hidden_layersró   ÚlayersrG   rú   Únormrl   Ú
rotary_embÚgradient_checkpointingÚ	post_initrá   s   && €r3   r&   ÚArceeModel.__init__X  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’mÜCHÈ×IaÑIaÔCbÓcÑCb°iÔ˜vÖ1ÑCbÑcó
ˆŒô ! ×!3Ñ!3¸×9LÑ9LÔMˆŒ	Ü.°fÔ=ˆŒØ&+ˆÔ#ð 	�‰Öùò d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[/# )
rI   Ú	input_idsNrÁ   rž   rå   Úinputs_embedsrÿ   rŠ   rK   )	rR   r   rY   r   ÚFloatTensorr  r   r   r   )rM   rD   s   "€r3   rN   r  k  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
r5   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.  rÁ   rå   rž   )rž   rÁ   rä   rž   rå   rÿ   )Úlast_hidden_staterå   )Ú
ValueErrorr"  r   r'   Úget_seq_lengthrR   r‰   rh   rm   r¬   r   r(  r&  r%  r'  r   )r1   r-  rÁ   rž   rå   r.  rÿ   rŠ   Úpast_seen_tokensÚcausal_maskrX   rä   Údecoder_layers   &&&&&&&,     r3   r9   ÚArceeModel.forwardh  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 	
r5   )r"  r)  r&  r'  r  r(  r   )NNNNNN)r<   r=   r>   r?   r&   r   r   r   r9   r@   rA   rB   rC   s   @@r3   r  r  V  s=   ù‡ € ÷ó ð   ØØ÷2
ñ 2
ó ó ó  ÷2
ð 2
r5   r  zarcee-ai/AFM-4.5B)Ú
checkpointc                   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ArceeForCausalLMi   zlm_head.weightzmodel.embed_tokens.weightÚlm_headÚcolwise_gather_outputrX   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*  r0   s   &&€r3   r&   ÚArceeForCausalLM.__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r5   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[	/
# )rI   r-  NrÁ   rž   rå   r.  Úlabelsrÿ   Úlogits_to_keeprŠ   rK   )
rR   r   rY   r   r/  r  rµ   r   r   r   )rM   rD   s   "€r3   rN   ÚArceeForCausalLM.__annotate__²  s»   ø€ ÷ 6
ñ 6
á×#Ñ# dÕ*ð6
ñ Ÿ™ tÕ+ð6
ñ ×&Ñ&¨Õ-ð	6
ñ
  �ð6
ñ ×(Ñ(¨4Õ/ð6
ñ × Ñ  4Õ'ð6
ñ ˜$•;ð6
ñ ™eŸl™lÕ*ð6
ñ Ñ+Õ,ð6
ñ 
 ñ6
r5   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      # )ao  
Example:

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

>>> model = ArceeForCausalLM.from_pretrained("meta-arcee/Arcee-2-7b-hf")
>>> tokenizer = AutoTokenizer.from_pretrained("meta-arcee/Arcee-2-7b-hf")

>>> 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-  rÁ   rž   rå   r.  rÿ   Nr•   r=  rB  r   )Úlossr=  rå   rX   r
  r  )r	  r1  r—   rµ   Úslicer;  Úloss_functionr'   r   r   rå   rX   r
  )r1   r-  rÁ   rž   rå   r.  rB  rÿ   rC  rŠ   ÚoutputsrX   Úslice_indicesr=  rF  s   &&&&&&&&&,     r3   r9   ÚArceeForCausalLM.forward°  sÿ   € ð> ,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 	
r5   )r;  r	  r   )NNNNNNNr   )r<   r=   r>   r?   Ú_tied_weights_keysÚ_tp_planÚ_pp_planÚ
_fsdp_planr&   r   r   r9   r@   rA   rB   rC   s   @@r3   r:  r:     sf   ù‡ € à*Ð,GÐHÐØÐ2Ð3€HØ˜_Ð-°¨zÐ:Ð;€HØÐ/Ð0€Jõð Ø÷6
ñ 6
ó ó ÷6
ð 6
r5   r:  c                   ó   € ] tR tRtRtR# )ÚArceeForSequenceClassificationië  r  N©r<   r=   r>   r?   r@   r  r5   r3   rQ  rQ  ë  ó   † ãr5   rQ  c                   ó   € ] tR tRtRtRtR# )ÚArceeForQuestionAnsweringið  Útransformerr  N)r<   r=   r>   r?   r  r@   r  r5   r3   rU  rU  ð  s   † à%Ôr5   rU  c                   ó   € ] tR tRtRtR# )ÚArceeForTokenClassificationiõ  r  NrR  r  r5   r3   rX  rX  õ  rS  r5   rX  )é   )rç   )r:  rU  rQ  rX  r  r  )?Úcollections.abcr   rR   r   Útransformers.utilsr   Úactivationsr   Úcache_utilsr   r   Ú
generationr	   Úintegrationsr
   r   Úmasking_utilsr   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   Úutils.deprecationr   Úutils.genericr   r   Úutils.output_capturingr   Úconfiguration_arceer   rÄ   r!   rG   rl   r©   r²   r»   rÑ   rÓ   ró   r  r  r:  rQ  rU  rX  Ú__all__r  r5   r3   Ú<module>rl     sÌ  ðõ* %ã Ý å -å !ß .Ý )ß LÝ /÷ó ÷ Pß Kß FÝ &ß 9Ý 0ß GÝ 5Ý ,ô<ˆr�y‰yô <ñ ˜YÓ'ôJ�2—9‘9ó Jó (ðJô(6<˜2Ÿ9™9ô 6<òr(ñ Ð-Ó.óó /ðõ2	U÷%ñ2 Ð)Ó*ô@)�R—Y‘Yó @)ó +ð@)ôF(Ð2ô (ðV ô˜?ó ó ðð$ ôF
Ð%ó F
ó ðF
ñR Ð.Ô/ôG
Ð+¨_ó G
ó 0ðG
ñT Ð.Ô/ô	Ð%EÐG[ó 	ó 0ð	ñ Ð.Ô/ô&Ð ;Ð=Qó &ó 0ð&ñ Ð.Ô/ô	Ð"?ÐAUó 	ó 0ð	ò‚r5   