+
    œ°³jéS  ã                   ó´  € ^ 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 ^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$H%t% ^RI&H't'H(t( ^RI)H*t* ^RI+H,t, ]! R4       ! R R]PZ                  4      4       t. ! R R]PZ                  4      t/R R lt0R-R R llt1]! R4      R.R l4       t2R t3]! ]24       ! R R ]PZ                  4      4       t4 ! R! R"]PZ                  4      t5 ! R# R$]4      t6]" ! R% R&]4      4       t7]" ! R' R(]74      4       t8]" ! R) R*]7]4      4       t9 ! R+ R,]]74      t:. R/Ot;R# )0é    )ÚCallableN)ÚTransformersKwargs)ÚACT2FN)ÚCacheÚDynamicCache)ÚGenerationMixin)Úuse_kernel_forward_from_hubÚuse_kernelized_func)Úcreate_causal_mask)Ú GenericForSequenceClassificationÚGradientCheckpointingLayer)ÚBaseModelOutputWithPastÚCausalLMOutputWithPast)ÚROPE_INIT_FUNCTIONSÚdynamic_rope_update)ÚALL_ATTENTION_FUNCTIONSÚPreTrainedModel)ÚUnpack)Úauto_docstringÚcan_return_tuple)Údeprecate_kwarg)Úmaybe_autocastÚmerge_with_config_defaults)Úcapture_outputs©ÚOlmo2ConfigÚRMSNormc                   óZ   a a€ ] tR t^2t 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Olmo2RMSNormc                ó$   <€ V ^8„  d   QhRS[ RR/# )é   ÚepsÚreturnN)Úfloat)ÚformatÚ__classdict__s   "€Úi/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/olmo2/modeling_olmo2.pyÚ__annotate__ÚOlmo2RMSNorm.__annotate__4   s   ø€ ÷ $ñ $©ð $¸$ñ $ó    c                óŽ   <€ \         SV `  4        \        P                  ! \        P
                  ! V4      4      V n        W n        R# )z+
Olmo2RMSNorm is equivalent to T5LayerNorm
N)ÚsuperÚ__init__ÚnnÚ	ParameterÚtorchÚonesÚweightÚvariance_epsilon)ÚselfÚhidden_sizer"   Ú	__class__s   &&&€r'   r-   ÚOlmo2RMSNorm.__init__4   s/   ø€ ô 	‰ÑÔÜ—l’l¤5§:¢:¨kÓ#:Ó;ˆŒØ #Ör*   c                ó4   <€ V ^8„  d   QhRS[ P                  /# )r!   r#   )r0   ÚTensor)r%   r&   s   "€r'   r(   r)   <   s   ø€ ÷ =ñ =©¯©ñ =r*   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      # )r!   T)Úkeepdiméÿÿÿÿ)	ÚdtypeÚtor0   Úfloat32ÚpowÚmeanÚrsqrtr3   r2   )r4   Úhidden_statesÚinput_dtypeÚvariances   &&  r'   ÚforwardÚOlmo2RMSNorm.forward<   sw   € Ø#×)Ñ)ˆØ%×(Ñ(¬¯©Ó7ˆØ ×$Ñ$ QÓ'×,Ñ,¨R¸Ð,Ó>ˆØ%¬¯ª°H×?TÑ?TÕ4TÓ(UÕUˆØ—‘˜mÕ+×/Ñ/°Ó<Ð<r*   c                ó^   € \        V P                  P                  4       R V P                   2# )z, eps=)Útupler2   Úshaper3   )r4   s   &r'   Ú
extra_reprÚOlmo2RMSNorm.extra_reprC   s*   € Ü˜Ÿ™×)Ñ)Ó*Ð+¨6°$×2GÑ2GÐ1HÐIÐIr*   )r3   r2   )g�íµ ÷Æ°>)
Ú__name__Ú
__module__Ú__qualname__Ú__firstlineno__r-   rF   rK   Ú__static_attributes__Ú__classdictcell__Ú__classcell__©r6   r&   s   @@r'   r   r   2   s%   ù‡ € ÷$õ $÷=ð =÷Jò Jr*   r   c                   óÎ   a a€ ] tR t^Gt o]! RRR7      R
V3R lV 3R lll4       t]]! RRR7      R
V3R lR ll4       4       t]P                  ! 4       ]
R 4       4       tR	tVtV ;t# )ÚOlmo2RotaryEmbeddingÚdevicez5.18)Úversionc                ó    <€ V ^8„  d   QhRS[ /# ©r!   Úconfigr   )r%   r&   s   "€r'   r(   Ú!Olmo2RotaryEmbedding.__annotate__I   s   ø€ ÷ Oñ O™{ñ Or*   c                óä  <€ \         SV `  4        VP                  V n        VP                  V n        Wn        V P
                  P                  R ,          V n        V P                  pV P                  R8w  d   \        V P                  ,          pV! V P
                  V4      w  q@n
        \        P                  ! VRR7      V n        \        P                  ! VP                  4       RR7      V n        R# )Ú	rope_typeÚdefaultF)Ú
persistentN)r,   r-   Úmax_position_embeddingsÚmax_seq_len_cachedÚoriginal_max_seq_lenr[   Úrope_parametersr^   Úcompute_default_rope_parametersr   Úattention_scalingr.   ÚBufferÚinv_freqÚcloneÚoriginal_inv_freq)r4   r[   rW   Úrope_init_fnrh   r6   s   &&&  €r'   r-   ÚOlmo2RotaryEmbedding.__init__H   s¬   ø€ ä‰ÑÔØ"(×"@Ñ"@ˆÔØ$*×$BÑ$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r*   c                óP   <€ V ^8„  d   QhRS[ RS[S[P                  S[3,          /# )r!   r[   r#   )r   rI   r0   r9   r$   )r%   r&   s   "€r'   r(   r\   [   s.   ø€ ÷ 5ñ 5±ð 5ÑW\Ñ]b×]iÑ]iÑkpÐ]pÕWqñ 5r*   c           	     ó0  € V P                   R,          p\        V RR4      ;'       g    V P                  V P                  ,          pRpRV\        P
                  ! ^ V^\        P                  R7      V,          ,          ,          pVP                  V4      V3# )a~  
Computes the inverse frequencies according to the original RoPE implementation
Args:
    config ([`~transformers.PreTrainedConfig`]):
        The model configuration.
Returns:
    Tuple of (`torch.Tensor`, `float`), containing the inverse frequencies for the RoPE embeddings and the
    post-processing scaling factor applied to the computed cos/sin (unused in this type of RoPE).
Ú
rope_thetaÚhead_dimNg      ð?)r=   )rd   Úgetattrr5   Únum_attention_headsr0   Úaranger$   r>   )r[   rW   ÚkwargsÚbaseÚdimÚattention_factorrh   s   &&,    r'   re   Ú4Olmo2RotaryEmbedding.compute_default_rope_parametersY   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$4Ð4Ð4r*   c                ó0  € V P                   R,          P                  4       P                  VP                  ^ ,          R^4      P	                  VP
                  4      pVR,          P                  4       p\        VP
                  P                  \        4      '       d2   VP
                  P                  R8w  d   VP
                  P                  MRp\        VRR7      ;_uu_ 4        VP                  4       VP                  4       ,          P                  ^^4      p\        P                  ! Wf3RR7      pVP                  4       V P                  ,          pVP                  4       V P                  ,          p	R R R 4       W‰3#   + '       g   i     XX	3# ; i)	NÚmpsÚcpuF)Údevice_typeÚenabled©rv   )NºNNNNr<   )r   Nr   )rh   r$   ÚexpandrJ   r>   rW   Ú
isinstanceÚtypeÚstrr   Ú	transposer0   ÚcatÚcosrf   Úsin)
r4   ÚxÚposition_idsÚinv_freq_expandedÚposition_ids_expandedr|   ÚfreqsÚembr†   r‡   s
   &&&       r'   rF   ÚOlmo2RotaryEmbedding.forwardm   s.  € ð !ŸM™M¨-Õ8×>Ñ>Ó@×GÑGÈ×HZÑHZÐ[\ÕH]Ð_aÐcdÓe×hÑhÐij×iqÑiqÓrÐØ ,¨ZÕ 8× >Ñ >Ó @Ðä'1°!·(±(·-±-Ä×'EÒ'EÈ!Ï(É(Ï-É-Ð[`ÔJ`�a—h‘h—m’mÐfkˆÜ¨¸U×CÖCØ&×,Ñ,Ó.Ð1F×1LÑ1LÓ1NÕN×YÑYÐZ[Ð]^Ó_ˆEÜ—)’)˜U˜N°Ô3ˆCØ—'‘'“)˜d×4Ñ4Õ4ˆCØ—'‘'“)˜d×4Ñ4Õ4ˆC÷	 Dð
 ˆxˆ÷ DÖCð
 �Cˆxˆús   Ã&BFÆF	)rf   r[   rh   rb   rj   rc   r^   ©N)rM   rN   rO   rP   r   r-   Ústaticmethodre   r0   Úno_gradr   rF   rQ   rR   rS   rT   s   @@r'   rV   rV   G   su   ù‡ € Ù�X vÔ.÷Oô Oó /ðOð  Ù�X vÔ.÷5ñ 5ó /ó ð5ð$ ‡]‚]ƒ_Øñ
ó ó ÷
ð 
r*   rV   c                ód   € V ^8„  d   QhR\         P                  R\        R\         P                  /# )r!   rC   Ún_repr#   )r0   r9   Úint)r%   s   "r'   r(   r(   |   s.   € ÷ 	Uñ 	UœUŸ\™\ð 	U´#ð 	U¼%¿,¹,ñ 	Ur*   c                ó˜   € V P                   w  r#rEV^8X  d   V # V R,          P                  W#WV4      p V P                  W#V,          WE4      # )zÈ
This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,
num_key_value_heads, seqlen, head_dim) to (batch, num_attention_heads, seqlen, head_dim)
)r   r   Nr   r   )rJ   r€   Úreshape)rC   r“   ÚbatchÚnum_key_value_headsÚslenrp   s   &&    r'   Ú	repeat_kvrš   |   sU   € ð
 2?×1DÑ1DÑ.€E Ø�„zØÐØ!Ð"2Õ3×:Ñ:¸5ÐW\ÐdlÓm€MØ× Ñ  ¸eÕ(CÀTÓTÐTr*   c                ó   € V ^8„  d   QhR\         P                  R\        P                  R\        P                  R\        P                  R\        P                  R,          R\        R\        R	\
        \        ,          /# )
r!   ÚmoduleÚqueryÚkeyÚvalueÚattention_maskNÚscalingÚdropoutrt   )r.   ÚModuler0   r9   r$   r   r   )r%   s   "r'   r(   r(   ˆ   sw   € ÷ %ñ %Ü�I‰Ið%ä�<‰<ð%ô 
�‰ð%ô �<‰<ð	%ô
 —L‘L 4Õ'ð%ô ð%ô ð%ô Ô'Õ(ñ%r*   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# )r!   )rv   r=   )ÚpÚtrainingr<   )rš   Únum_key_value_groupsr0   Úmatmulr„   r.   Ú
functionalÚsoftmaxr?   r>   r=   r¢   r¦   Ú
contiguous)rœ   r�   rž   rŸ   r    r¡   r¢   rt   Ú
key_statesÚvalue_statesÚattn_weightsÚattn_outputs   &&&&&&&,    r'   Úeager_attention_forwardr°   ˆ   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$Ð$r*   Úrotary_pos_embc                ó4  € V P                   VP                   reVP                  V4      pVP                  V4      pW,          \        V 4      V,          ,           pW,          \        V4      V,          ,           pVP                  V4      VP                  V4      3# )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.
)r=   Ú	unsqueezeÚrotate_halfr>   )	ÚqÚkr†   r‡   Úunsqueeze_dimÚq_typeÚk_typeÚq_embedÚk_embeds	   &&&&&    r'   Úapply_rotary_pos_embr¼   ¡   sv   € ð& —W‘W˜aŸg™gˆFØ
�-‰-˜Ó
&€CØ
�-‰-˜Ó
&€CØ�wœ; q›>¨CÕ/Õ0€GØ�wœ; q›>¨CÕ/Õ0€GØ�:‰:�fÓ˜wŸz™z¨&Ó1Ð1Ð1r*   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<   )rJ   r0   r…   )rˆ   Úx1Úx2s   &  r'   r´   r´   ¼   sZ   € à	
ˆ3Ð"�!—'‘'˜"•+ Õ"Ð"Ð"Õ	#€BØ	
ˆ3�—‘˜•˜qÕ Ñ"Ð"Õ	#€BÜ�9Š9�r�c˜2�Y BÔ'Ð'r*   c                   ó\   a a€ ] tR t^Ãt 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Olmo2Attentionz=Multi-headed attention from 'Attention Is All You Need' paperc                ó4   <€ V ^8„  d   QhRS[ RS[R,          /# )r!   r[   Ú	layer_idxN©r   r”   )r%   r&   s   "€r'   r(   ÚOlmo2Attention.__annotate__Ç   s#   ø€ ÷ dñ d™{ð d±s¸Tµzñ dr*   c                óz  <€ \         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                  ,          VP*                  4      V n        \)        VP                  V P                  ,          VP*                  4      V n        R# )rp   T©ÚbiasNg      à¿)r,   r-   r[   rÃ   rq   r5   rr   rp   r˜   r§   r¡   Úattention_dropoutÚ	is_causalr.   ÚLinearÚattention_biasÚq_projÚk_projÚv_projÚo_projr   Úrms_norm_epsÚq_normÚk_norm©r4   r[   rÃ   r6   s   &&&€r'   r-   ÚOlmo2Attention.__init__Ç   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 # 6×#=Ñ#=ÀÇÁÕ#MÈv×ObÑObÓcˆŒÜ" 6×#=Ñ#=ÀÇÁÕ#MÈv×ObÑObÓcˆŽr*   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                  R,          3,          /# )r!   rC   Úposition_embeddingsr    NÚpast_key_valuesrt   r#   )r0   r9   rI   r   r   r   )r%   r&   s   "€r'   r(   rÅ   à   s‡   ø€ ÷ *)ñ *)á—|‘|ð*)ñ #¡5§<¡<±·±Ð#=Õ>ð*)ñ Ÿ™ tÕ+ð	*)ñ
  �ð*)ñ Ñ+Õ,ð*)ñ 
‰u�|‰|™UŸ\™\¨DÕ0Ð0Õ	1ñ*)r*   c                óX  € VP                   R R p. VORNV P                  N5pV P                  V P                  V4      4      pV P	                  V P                  V4      4      p	V P                  V4      p
VP                  V4      P                  ^^4      pV	P                  V4      P                  ^^4      p	V
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$                  RV P&                  /VB w  rïVP(                  ! . VORN5!  P+                  4       pV P-                  V4      pWï3# )Nr¢   ç        r¡   r<   )rJ   rp   rÒ   rÍ   rÓ   rÎ   rÏ   Úviewr„   r¼   ÚupdaterÃ   r   Úget_interfacer[   Ú_attn_implementationr°   r¦   rÉ   r¡   r–   r«   rÐ   )r4   rC   r×   r    rØ   rt   Úinput_shapeÚhidden_shapeÚquery_statesr¬   r­   r†   r‡   Úattention_interfacer¯   r®   s   &&&&&,          r'   rF   ÚOlmo2Attention.forwardà   s£  € ð $×)Ñ)¨#¨2Ð.ˆØ8˜Ð8 bÐ8¨$¯-©-Ñ8ˆà—{‘{ 4§;¡;¨}Ó#=Ó>ˆØ—[‘[ §¡¨]Ó!;Ó<ˆ
Ø—{‘{ =Ó1ˆà#×(Ñ(¨Ó6×@Ñ@ÀÀAÓFˆØ—_‘_ \Ó2×<Ñ<¸QÀÓBˆ
Ø#×(Ñ(¨Ó6×@Ñ@ÀÀAÓFˆ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(r*   )rÉ   r[   rp   rÊ   rÓ   rÎ   rÃ   r§   rÐ   rÒ   rÍ   r¡   rÏ   r�   )
rM   rN   rO   rP   Ú__doc__r-   rF   rQ   rR   rS   rT   s   @@r'   rÁ   rÁ   Ã   s#   ù‡ € áG÷dõ d÷2*)÷ *)ò *)r*   rÁ   c                   ó8   a a€ ] tR tRt oV 3R ltR tRtVtV ;t# )ÚOlmo2MLPi  c                óØ  <€ \         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        \
        P                  ! V P                  V P                  R R7      V n	        \        VP                  ,          V n        R# ©FrÇ   N)r,   r-   r[   r5   Úintermediate_sizer.   rË   Ú	gate_projÚup_projÚ	down_projr   Ú
hidden_actÚact_fn©r4   r[   r6   s   &&€r'   r-   ÚOlmo2MLP.__init__  s¤   ø€ Ü‰ÑÔØŒØ!×-Ñ-ˆÔØ!'×!9Ñ!9ˆÔÜŸš 4×#3Ñ#3°T×5KÑ5KÐRWÔXˆŒ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Žr*   c                ó�   € V P                  V P                  V P                  V4      4      V P                  V4      ,          4      pV# r�   )rì   rî   rê   rë   )r4   rˆ   rì   s   && r'   rF   ÚOlmo2MLP.forward  s6   € Ø—N‘N 4§;¡;¨t¯~©~¸aÓ/@Ó#AÀDÇLÁLÐQRÃOÕ#SÓTˆ	ØÐr*   )rî   r[   rì   rê   r5   ré   rë   ©	rM   rN   rO   rP   r-   rF   rQ   rR   rS   rT   s   @@r'   ræ   ræ     s   ù‡ € õ0÷ò r*   ræ   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Olmo2DecoderLayeri  c                ó&   <€ V ^8„  d   QhRS[ RS[/# )r!   r[   rÃ   rÄ   )r%   r&   s   "€r'   r(   ÚOlmo2DecoderLayer.__annotate__  s   ø€ ÷ dñ d™{ð d±sñ dr*   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[   rÃ   ©r"   N)r,   r-   r5   rÁ   Ú	self_attnræ   Úmlpr   rÑ   Úpost_attention_layernormÚpost_feedforward_layernormrÔ   s   &&&€r'   r-   ÚOlmo2DecoderLayer.__init__  sj   ø€ Ü‰ÑÔØ!×-Ñ-ˆÔÜ'¨vÔKˆŒä˜FÓ#ˆŒÜ(4°V×5GÑ5GÈV×M`ÑM`Ô(aˆÔ%Ü*6°v×7IÑ7IÈv×ObÑObÔ*cˆÖ'r*   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                  /# )
r!   rC   r    Nr‰   rØ   Ú	use_cacher×   rt   r#   )r0   r9   Ú
LongTensorr   ÚboolrI   r   r   )r%   r&   s   "€r'   r(   r÷   '  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r*   c                óÔ   € TpV P                   ! RR VRVRVRVRVRV/VB w  rV P                  V4      pW�,           pTpV P                  V4      pV P                  V4      pW�,           pV# )rC   r    r‰   rØ   r   r×   © )rú   rü   rû   rý   )
r4   rC   r    r‰   rØ   r   r×   rt   ÚresidualÚ_s
   &&&&&&&,  r'   rF   ÚOlmo2DecoderLayer.forward'  s©   € ð !ˆØŸ>š>ñ 
Ø'ð
à)ð
ð &ð
ð ,ð	
ð
  ð
ð !4ð
ð ñ
Ñˆð ×5Ñ5°mÓDˆØ Õ0ˆð !ˆØŸ™ Ó/ˆØ×7Ñ7¸ÓFˆØ Õ0ˆØÐr*   )r5   rû   rü   rý   rú   )NNNFNró   rT   s   @@r'   rõ   rõ     s    ù‡ € ÷dó d÷÷ ò r*   rõ   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Olmo2PreTrainedModeliF  ÚmodelTrõ   rØ   rC   Ú
attentionsc                ó&   <€ V ^8„  d   Qh/ S[ ;R&   # rZ   r   )r%   r&   s   "€r'   r(   Ú!Olmo2PreTrainedModel.__annotate__F  s   ø‡ ‚ áÑò r*   r  N)rM   rN   rO   rP   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_backendrõ   rÁ   Ú_can_record_outputsÚ__annotate_func__rQ   rR   )r&   s   @r'   r	  r	  F  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 r*   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
Olmo2ModeliY  c                ó    <€ V ^8„  d   QhRS[ /# rZ   r   )r%   r&   s   "€r'   r(   ÚOlmo2Model.__annotate__[  s   ø€ ÷ ñ ™{ñ r*   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 )rù   ©r[   FN)r,   r-   Úpad_token_idÚpadding_idxÚ
vocab_sizer.   Ú	Embeddingr5   Úembed_tokensÚ
ModuleListÚrangeÚnum_hidden_layersrõ   Úlayersr   rÑ   ÚnormrV   Ú
rotary_embÚgradient_checkpointingÚ	post_initrÔ   s   && €r'   r-   ÚOlmo2Model.__init__[  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[/# )
r!   Ú	input_idsNr    r‰   rØ   Úinputs_embedsr   rt   r#   )	r0   r  r9   r   ÚFloatTensorr  r   r   r   )r%   r&   s   "€r'   r(   r  n  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
r*   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  )rW   )r[   r/  r    rØ   r‰   )r‰   r    r×   r‰   rØ   r   )Úlast_hidden_staterØ   )Ú
ValueErrorr#  r   r[   Úget_seq_lengthr0   rs   rJ   rW   r³   r   r)  r'  r&  r(  r   )r4   r.  r    r‰   rØ   r/  r   rt   Úpast_seen_tokensÚcausal_maskrC   r×   Údecoder_layers   &&&&&&&,     r'   rF   ÚOlmo2Model.forwardk  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 	
r*   )r#  r*  r'  r(  r   r)  r!  )NNNNNN)rM   rN   rO   rP   r-   r   r   r   rF   rQ   rR   rS   rT   s   @@r'   r  r  Y  s=   ù‡ € ÷ó ð   ØØ÷2
ñ 2
ó ó ó  ÷2
ð 2
r*   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Olmo2ForCausalLMi£  zlm_head.weightzmodel.embed_tokens.weightÚlm_headÚcolwise_gather_outputrC   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# rè   )
r,   r-   r  r
  r!  r.   rË   r5   r;  r+  rï   s   &&€r'   r-   ÚOlmo2ForCausalLM.__init__ª  sU   ø€ Ü‰Ñ˜Ô Ü Ó'ˆŒ
Ø ×+Ñ+ˆŒÜ—y’y ×!3Ñ!3°V×5FÑ5FÈUÔSˆŒð 	�‰Ör*   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[	/
# )r!   r.  Nr    r‰   rØ   r/  Úlabelsr   Úlogits_to_keeprt   r#   )
r0   r  r9   r   r0  r  r”   r   r   r   )r%   r&   s   "€r'   r(   ÚOlmo2ForCausalLM.__annotate__µ  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
r*   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, Olmo2ForCausalLM

>>> model = Olmo2ForCausalLM.from_pretrained("meta-olmo2/Olmo2-2-7b-hf")
>>> tokenizer = AutoTokenizer.from_pretrained("meta-olmo2/Olmo2-2-7b-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.  r    r‰   rØ   r/  r   Nr   r=  rB  r!  )Úlossr=  rØ   rC   r  r  )r
  r2  r�   r”   Úslicer;  Úloss_functionr[   r!  r   rØ   rC   r  )r4   r.  r    r‰   rØ   r/  rB  r   rC  rt   ÚoutputsrC   Úslice_indicesr=  rF  s   &&&&&&&&&,     r'   rF   ÚOlmo2ForCausalLM.forward³  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 	
r*   )r;  r
  r!  )NNNNNNNr   )rM   rN   rO   rP   Ú_tied_weights_keysÚ_tp_planÚ_pp_planÚ
_fsdp_planr-   r   r   rF   rQ   rR   rS   rT   s   @@r'   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
r*   r:  c                   ó   € ] tR tRtRtR# )ÚOlmo2ForSequenceClassificationiî  r  N)rM   rN   rO   rP   rQ   r  r*   r'   rQ  rQ  î  s   † Ûr*   rQ  )rÚ   )é   )r:  rQ  r  r	  )<Úcollections.abcr   r0   Útorch.nnr.   Útransformers.utils.genericr   Úactivationsr   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   Úutils.deprecationr   Úutils.genericr   r   Úutils.output_capturingr   Úconfiguration_olmo2r   r£   r   rV   rš   r°   r¼   r´   rÁ   ræ   rõ   r	  r  r:  rQ  Ú__all__r  r*   r'   Ú<module>rf     s^  ðõ4 %ã Ý å 9å !ß .Ý )ß LÝ /ß [ß Oß Kß FÝ &ß 5Ý 0ß GÝ 5Ý ,ñ ˜YÓ'ôJ�2—9‘9ó Jó (ðJô(2˜2Ÿ9™9ô 2õj	U÷%ñ2 Ð-Ó.ó2ó /ð2ò4(ñ Ð)Ó*ôF)�R—Y‘Yó F)ó +ðF)ôRˆr�y‰yô ô &Ð2ô &ðR ô˜?ó ó ðð$ ôF
Ð%ó F
ó ðF
ðR ôG
Ð+¨_ó G
ó ðG
ôT	Ð%EÐG[ô 	ò g‚r*   