+
    œ°³j_M  ã                   óP  € ^ RI Ht ^ RI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 ^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$H%t%H&t& ^RI'H(t( ^RI)H*t*  ! R R]PV                  4      t,R t-]! R4      R'R l4       t.R R lt/R(R R llt0]! ].4       ! R R]PV                  4      4       t1 ! R R]4      t2]  ! R R ]4      4       t3 ! R! R"]PV                  4      t4]  ! R# R$]34      4       t5]  ! R% R&]3]4      4       t6. R)Ot7R# )*é    )ÚCallableN)ÚACT2FN)ÚCacheÚDynamicCache)ÚGenerationMixin)Úuse_kernel_forward_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deprecate_kwarg)Úmaybe_autocastÚmerge_with_config_defaults)Úcapture_outputs©ÚJais2Configc                   ó8   a a€ ] tR t^,t oV 3R ltR tRtVtV ;t# )ÚJais2MLPc                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_sizeÚnnÚ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/jais2/modeling_jais2.pyr"   ÚJais2MLP.__init__-   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)   )r.   Úxs   &&r0   ÚforwardÚJais2MLP.forward6   s"   € Ø�~‰~˜dŸk™k¨$¯,©,°q«/Ó:Ó;Ð;r2   )r,   r#   r*   r$   r%   r)   ©	Ú__name__Ú
__module__Ú__qualname__Ú__firstlineno__r"   r6   Ú__static_attributes__Ú__classdictcell__Ú__classcell__©r/   Ú__classdict__s   @@r0   r   r   ,   s   ù‡ € õ0÷<ò <r2   r   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..N©Údiméÿÿÿÿ)ÚshapeÚtorchÚcat)r5   Úx1Úx2s   &  r0   Úrotate_halfrK   :   sZ   € à	
ˆ3Ð"�!—'‘'˜"•+ Õ"Ð"Ð"Õ	#€BØ	
ˆ3�—‘˜•˜qÕ Ñ"Ð"Õ	#€BÜ�9Š9�r�c˜2�Y BÔ'Ð'r2   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	unsqueezerK   )ÚqÚkÚcosÚsinÚunsqueeze_dimÚq_embedÚk_embeds   &&&&&  r0   Úapply_rotary_pos_embrV   A   sS   € ð& �-‰-˜Ó
&€CØ
�-‰-˜Ó
&€CØ�wœ; q›>¨CÕ/Õ0€GØ�wœ; q›>¨CÕ/Õ0€GØÐÐr2   c                ód   € V ^8„  d   QhR\         P                  R\        R\         P                  /# )é   Úhidden_statesÚn_repÚreturn)rG   ÚTensorÚint)Úformats   "r0   Ú__annotate__r_   [   s.   € ÷ 	Uñ 	UœUŸ\™\ð 	U´#ð 	U¼%¿,¹,ñ 	Ur2   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)
)ºNNNra   Nra   ra   )rF   ÚexpandÚreshape)rY   rZ   ÚbatchÚnum_key_value_headsÚslenÚhead_dims   &&    r0   Ú	repeat_kvrh   [   sU   € ð
 2?×1DÑ1DÑ.€E Ø�„zØÐØ!Ð"2Õ3×:Ñ:¸5ÐW\ÐdlÓm€MØ× Ñ  ¸eÕ(CÀTÓTÐTr2   c                ó   € V ^8„  d   QhR\         P                  R\        P                  R\        P                  R\        P                  R\        P                  R,          R\        R\        R	\
        \        ,          /# )
rX   ÚmoduleÚqueryÚkeyÚvalueÚattention_maskNÚscalingÚdropoutÚkwargs)r&   ÚModulerG   r\   Úfloatr   r   )r^   s   "r0   r_   r_   g   sw   € ÷ %ñ %Ü�I‰Ið%ä�<‰<ð%ô 
�‰ð%ô �<‰<ð	%ô
 —L‘L 4Õ'ð%ô ð%ô ð%ô Ô'Õ(ñ%r2   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# )rX   )rD   Údtype)ÚpÚtrainingrE   )rh   Únum_key_value_groupsrG   ÚmatmulÚ	transposer&   Ú
functionalÚsoftmaxÚfloat32Útoru   rp   rw   Ú
contiguous)rj   rk   rl   rm   rn   ro   rp   rq   Ú
key_statesÚvalue_statesÚattn_weightsÚattn_outputs   &&&&&&&,    r0   Úeager_attention_forwardr„   g   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$Ð$r2   c                   óX   a a€ ] tR t^€t 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Jais2Attentionz=Multi-headed attention from 'Attention Is All You Need' paperc                ó&   <€ V ^8„  d   QhRS[ RS[/# ©rX   r#   Ú	layer_idx©r   r]   )r^   rA   s   "€r0   r_   ÚJais2Attention.__annotate__„   s   ø€ ÷ 
ñ 
™{ð 
±sñ 
r2   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# )rg   Tr   Ng      à¿)r!   r"   r#   r‰   Úgetattrr$   Únum_attention_headsrg   re   rx   ro   Úattention_dropoutÚ	is_causalr&   r'   Úattention_biasÚq_projÚk_projÚv_projÚo_proj©r.   r#   r‰   r/   s   &&&€r0   r"   ÚJais2Attention.__init__„   sI  ø€ Ü‰ÑÔØŒØ"ŒÜ ¨
°F×4FÑ4FÈ&×JdÑJdÕ4dÓeˆŒØ$*×$>Ñ$>À&×B\ÑB\Õ$\ˆÔ!Ø—}‘} dÕ*ˆŒØ!'×!9Ñ!9ˆÔØˆŒä—i’iØ×Ñ × :Ñ :¸T¿]¹]Õ JÐQW×QfÑQfô
ˆŒô —i’iØ×Ñ × :Ñ :¸T¿]¹]Õ JÐQW×QfÑQfô
ˆŒô —i’iØ×Ñ × :Ñ :¸T¿]¹]Õ JÐQW×QfÑQfô
ˆŒô —i’iØ×&Ñ&¨¯©Õ6¸×8JÑ8JÐQW×QfÑQfô
ˆŽr2   c                ó  <€ V ^8„  d   QhRS[ P                  RS[S[ P                  S[ P                  3,          R,          RS[ P                  R,          RS[R,          RS[S[,          RS[S[ P                  S[ P                  3,          /# )rX   rY   Úposition_embeddingsNrn   Úpast_key_valuesrq   r[   )rG   r\   Útupler   r   r   )r^   rA   s   "€r0   r_   r‹   ›   s‡   ø€ ÷ &)ñ &)á—|‘|ð&)ñ #¡5§<¡<±·±Ð#=Õ>ÀÕEð&)ñ Ÿ™ tÕ+ð	&)ñ
  �ð&)ñ Ñ+Õ,ð&)ñ 
‰u�|‰|™UŸ\™\Ð)Õ	*ñ&)r2   c                ó  € VP                   R R p. VORNV P                  N5pV P                  V4      P                  V4      P	                  ^^4      pV P                  V4      P                  V4      P	                  ^^4      p	V P                  V4      P                  V4      P	                  ^^4      p
Vw  r¼\        W‰W¼4      w  r‰Ve   VP                  WšV P                  4      w  rš\        P                  ! V P                  P                  \        4      pT! V VV	V
V3RV P                  '       g   RMV P                   RV P"                  /VB w  rïVP$                  ! . VORN5!  P'                  4       pV P)                  V4      pWï3# )Nrp   ç        ro   rE   )rF   rg   r’   Úviewrz   r“   r”   rV   Úupdater‰   r   Úget_interfacer#   Ú_attn_implementationr„   rw   r�   ro   rc   r   r•   )r.   rY   r™   rn   rš   rq   Úinput_shapeÚhidden_shapeÚquery_statesr€   r�   rQ   rR   Úattention_interfacerƒ   r‚   s   &&&&&,          r0   r6   ÚJais2Attention.forward›   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(r2   )r�   r#   rg   r�   r“   r‰   rx   r•   r’   ro   r”   )NNN)
r9   r:   r;   r<   Ú__doc__r"   r6   r=   r>   r?   r@   s   @@r0   r†   r†   €   s!   ù‡ € áG÷
ó 
÷.&)÷ &)ò &)r2   r†   c                   óT   a a€ ] tR t^Ät 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Jais2DecoderLayerc                ó&   <€ V ^8„  d   QhRS[ RS[/# rˆ   rŠ   )r^   rA   s   "€r0   r_   ÚJais2DecoderLayer.__annotate__Å   s   ø€ ÷ dñ d™{ð d±sñ dr2   c                óL  <€ \         SV `  4        VP                  V n        \        WR 7      V n        \        V4      V n        \        P                  ! VP                  VP                  R7      V n
        \        P                  ! VP                  VP                  R7      V n        R# ))r#   r‰   ©ÚepsN)r!   r"   r$   r†   Ú	self_attnr   Úmlpr&   Ú	LayerNormÚlayer_norm_epsÚinput_layernormÚpost_attention_layernormr–   s   &&&€r0   r"   ÚJais2DecoderLayer.__init__Å   sr   ø€ Ü‰ÑÔØ!×-Ñ-ˆÔä'¨vÔKˆŒä˜FÓ#ˆŒÜ!Ÿ|š|¨F×,>Ñ,>ÀF×DYÑDYÔZˆÔÜ(*¯ª°V×5GÑ5GÈV×MbÑMbÔ(cˆÖ%r2   c                ó.  <€ V ^8„  d   QhRS[ P                  RS[ P                  R,          RS[ P                  R,          RS[R,          RS[R,          RS[S[ P                  S[ P                  3,          R,          RS[S[,          R	S[ P                  /# )
rX   rY   rn   NÚposition_idsrš   Ú	use_cacher™   rq   r[   )rG   r\   Ú
LongTensorr   Úboolr›   r   r   )r^   rA   s   "€r0   r_   r«   Ï   sœ   ø€ ÷ ñ á—|‘|ðñ Ÿ™ tÕ+ðñ ×&Ñ&¨Õ-ð	ñ
  �ðñ ˜$•;ðñ #¡5§<¡<±·±Ð#=Õ>ÀÕEðñ Ñ+Õ,ðñ 
�‰ñr2   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   rn   r·   rš   r¸   r™   © )r³   r¯   r´   r°   )
r.   rY   rn   r·   rš   r¸   r™   rq   ÚresidualÚ_s
   &&&&&&&,  r0   r6   ÚJais2DecoderLayer.forwardÏ   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r2   )r$   r³   r°   r´   r¯   )NNNFNr8   r@   s   @@r0   r©   r©   Ä   s    ù‡ € ÷dó d÷÷ ò r2   r©   c                   ó`   a € ] tR t^ït 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Jais2PreTrainedModelÚmodelTr©   rš   rY   Ú
attentionsc                ó&   <€ V ^8„  d   Qh/ S[ ;R&   # ©rX   r#   r   )r^   rA   s   "€r0   r_   Ú!Jais2PreTrainedModel.__annotate__ï   s   ø‡ ‚ áÑò r2   r¼   N)r9   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_backendr©   r†   Ú_can_record_outputsÚ__annotate_func__r=   r>   )rA   s   @r0   rÁ   rÁ   ï   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 r2   rÁ   c                   óÎ   a a€ ] tR tRt 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Jais2RotaryEmbeddingi  Údevicez5.18)Úversionc                ó    <€ V ^8„  d   QhRS[ /# rÅ   r   )r^   rA   s   "€r0   r_   Ú!Jais2RotaryEmbedding.__annotate__  s   ø€ ÷ Oñ O™{ñ Or2   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_parametersrÙ   Úcompute_default_rope_parametersr   Úattention_scalingr&   ÚBufferÚinv_freqÚcloneÚoriginal_inv_freq)r.   r#   rÔ   Úrope_init_fnrã   r/   s   &&&  €r0   r"   ÚJais2RotaryEmbedding.__init__  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r2   c                óP   <€ V ^8„  d   QhRS[ RS[S[P                  S[3,          /# )rX   r#   r[   )r   r›   rG   r\   rs   )r^   rA   s   "€r0   r_   r×     s.   ø€ ÷ 5ñ 5±ð 5ÑW\Ñ]b×]iÑ]iÑkpÐ]pÕWqñ 5r2   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_thetarg   Ng      ð?©ru   )rß   r�   r$   rŽ   rG   Úarangers   r~   )r#   rÔ   rq   ÚbaserD   Úattention_factorrã   s   &&,    r0   rà   Ú4Jais2RotaryEmbedding.compute_default_rope_parameters  s~   € ð ×%Ñ% lÕ3ˆÜ�f˜j¨$Ó/×cÐc°6×3EÑ3EÈ×IcÑIcÕ3cˆàÐà˜$¤5§<¢<°°3¸ÄÇÁÔ#MÐPSÕ#SÕTÕUˆØ�{‰{˜6Ó"Ð$4Ð4Ð4r2   c                ó^  € V P                   R,          P                  VP                  ^ ,          R	^4      P                  \        P
                  VP                  R7      pVR
,          P                  4       p\        VP                  P                  \        4      '       d2   VP                  P                  R8w  d   VP                  P                  MRp\        VRR7      ;_uu_ 4        W4,          P                  ^^4      p\        P                  ! Wf3R	R7      pVP                  4       V P                  ,          pVP                  4       V P                  ,          p	R R R 4       XP                  VP                   R7      X	P                  VP                   R7      3#   + '       g   i     LH; i)N)ru   rÔ   ÚmpsÚcpuF)Údevice_typeÚenabledrC   rë   )Nra   NrE   )ra   Nra   )rã   rb   rF   r~   rG   rs   rÔ   Ú
isinstanceÚtypeÚstrr   rz   rH   rQ   rá   rR   ru   )
r.   r5   r·   Úinv_freq_expandedÚposition_ids_expandedró   ÚfreqsÚembrQ   rR   s
   &&&       r0   r6   ÚJais2RotaryEmbedding.forward(  s2  € ð �M‰M˜-Õ(×/Ñ/°×0BÑ0BÀ1Õ0EÀrÈ1ÓM×PÑPÔW\×WbÑWbÐkl×ksÑksÐPÓtð 	ð !-¨ZÕ 8× >Ñ >Ó @Ðä'1°!·(±(·-±-Ä×'EÒ'EÈ!Ï(É(Ï-É-Ð[`ÔJ`�a—h‘h—m’mÐfkˆä¨¸U×CÖCØ&Õ>×IÑIÈ!ÈQÓOˆEÜ—)’)˜U˜N°Ô3ˆCØ—'‘'“)˜d×4Ñ4Õ4ˆCØ—'‘'“)˜d×4Ñ4Õ4ˆC÷	 Dð �v‰v˜AŸG™GˆvÓ$ c§f¡f°1·7±7 fÓ&;Ð;Ð;÷ D×Cús   Ã(A4FÆF,	)rá   r#   rã   rÝ   rå   rÞ   rÙ   r4   )r9   r:   r;   r<   r   r"   Ústaticmethodrà   rG   Úno_gradr   r6   r=   r>   r?   r@   s   @@r0   rÓ   rÓ     su   ù‡ € Ù�X vÔ.÷Oô Oó /ðOð  Ù�X vÔ.÷5ñ 5ó /ó ð5ð$ ‡]‚]ƒ_Øñ<ó ó ÷<ð <r2   rÓ   c                   ór   a a€ ] tR tRt oV3R lV 3R llt]]]RV3R lR ll4       4       4       tRt	Vt
V ;t# )Ú
Jais2Modeli;  c                ó    <€ V ^8„  d   QhRS[ /# rÅ   r   )r^   rA   s   "€r0   r_   ÚJais2Model.__annotate__=  s   ø€ ÷ ñ ™{ñ r2   c           	     ó*  <€ \         SV `  V4       VP                  V n        VP                  V n        \
        P                  ! VP                  VP                  V P                  4      V n        \
        P                  ! \        VP                  4       Uu. uF  p\        W4      NK  	  up4      V n        \
        P                  ! VP                  VP                  R 7      V n        \#        VR7      V n        RV n        V P)                  4        R# u upi )r­   ©r#   FN)r!   r"   Úpad_token_idÚpadding_idxÚ
vocab_sizer&   Ú	Embeddingr$   Úembed_tokensÚ
ModuleListÚrangeÚnum_hidden_layersr©   Úlayersr±   r²   ÚnormrÓ   Ú
rotary_embÚgradient_checkpointingÚ	post_initr–   s   && €r0   r"   ÚJais2Model.__init__=  sÎ   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 —L’L ×!3Ñ!3¸×9NÑ9NÔOˆ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[/# )
rX   Ú	input_idsNrn   r·   rš   Úinputs_embedsr¸   rq   r[   )	rG   r¹   r\   r   ÚFloatTensorrº   r   r   r   )r^   rA   s   "€r0   r_   r  P  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 ˜$•;ð2
ñ Ñ+Õ,ð2
ñ 
!ñ2
r2   c                óˆ  € VR J VR J,          '       d   \        R4      hVf   V P                  V4      pV'       d   Vf   \        V P                  R7      pVfb   Ve   VP	                  4       M^ p\
        P                  ! VP                  ^,          VP                  R7      V,           pVP                  ^ 4      p\        V P                  VVVVR7      p	Tp
V P                  W£R7      pV P                  R V P                  P                    F  pV! V
3RV	RVRVR	VR
V/VB p
K  	  V P                  V
4      p
\        V
VR7      # )Nz:You must specify exactly one of input_ids or inputs_embedsr  )rÔ   )r#   r  rn   rš   r·   )r·   rn   r™   r·   rš   r¸   )Úlast_hidden_staterš   )Ú
ValueErrorr	  r   r#   Úget_seq_lengthrG   rì   rF   rÔ   rN   r
   r  r  r  r  r   )r.   r  rn   r·   rš   r  r¸   rq   Úpast_seen_tokensÚcausal_maskrY   r™   Údecoder_layers   &&&&&&&,     r0   r6   ÚJais2Model.forwardM  se  € ð ˜Ð -°tÐ";×<Ô<ÜÐYÓZÐZàÒ Ø*.×*;Ñ*;¸IÓ*FˆMç˜Ò0Ü*°$·+±+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 $ðð ñŠMñ Jð Ÿ	™	 -Ó0ˆÜ&Ø+Ø+ô
ð 	
r2   )r	  r  r  r  r  r  r  )NNNNNN)r9   r:   r;   r<   r"   r   r   r   r6   r=   r>   r?   r@   s   @@r0   r   r   ;  s=   ù‡ € ÷ó ð   ØØ÷2
ñ 2
ó ó ó  ÷2
ð 2
r2   r   c                   ó„   a a€ ] tR tRt oRR/tRR/tRR.R.3/tRR/tV 3R	 lt]	]
RV3R
 lR ll4       4       tRtVtV ;t# )ÚJais2ForCausalLMi…  zlm_head.weightzmodel.embed_tokens.weightÚlm_headÚcolwise_gather_outputrY   ÚlogitsÚkeep_full_weightc                óì   <€ \         SV `  V4       \        V4      V n        VP                  V n        \
        P                  ! VP                  VP                  R R7      V n        V P                  4        R# )Fr   N)
r!   r"   r   rÂ   r  r&   r'   r$   r!  r  r-   s   &&€r0   r"   ÚJais2ForCausalLM.__init__Œ  sU   ø€ Ü‰Ñ˜Ô Ü Ó'ˆŒ
Ø ×+Ñ+ˆŒÜ—y’y ×!3Ñ!3°V×5FÑ5FÈUÔSˆŒð 	�‰Ör2   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[	/
# )rX   r  Nrn   r·   rš   r  Úlabelsr¸   Úlogits_to_keeprq   r[   )
rG   r¹   r\   r   r  rº   r]   r   r   r   )r^   rA   s   "€r0   r_   ÚJais2ForCausalLM.__annotate__—  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
r2   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      # )as  
Example:

```python
>>> from transformers import AutoTokenizer, Jais2ForCausalLM

>>> model = Jais2ForCausalLM.from_pretrained("inceptionai/Jais-2-8B-Chat")
>>> tokenizer = AutoTokenizer.from_pretrained("inceptionai/Jais-2-8B-Chat")

>>> 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  rn   r·   rš   r  r¸   Nra   r#  r(  r  )Úlossr#  rš   rY   rÃ   r¼   )rÂ   r  rõ   r]   Úslicer!  Úloss_functionr#   r  r   rš   rY   rÃ   )r.   r  rn   r·   rš   r  r(  r¸   r)  rq   ÚoutputsrY   Úslice_indicesr#  r,  s   &&&&&&&&&,     r0   r6   ÚJais2ForCausalLM.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 	
r2   )r!  rÂ   r  )NNNNNNNr   )r9   r:   r;   r<   Ú_tied_weights_keysÚ_tp_planÚ_pp_planÚ
_fsdp_planr"   r   r   r6   r=   r>   r?   r@   s   @@r0   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
r2   r   )é   )r�   )r   r   rÁ   )8Úcollections.abcr   rG   Útorch.nnr&   Úactivationsr   Úcache_utilsr   r   Ú
generationr   Úintegrationsr   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.deprecationr   Úutils.genericr   r   Úutils.output_capturingr   Úconfiguration_jais2r   rr   r   rK   rV   rh   r„   r†   r©   rÁ   rÓ   r   r   Ú__all__r¼   r2   r0   Ú<module>rI     s'  ðõ, %ã Ý å !ß .Ý )ß LÝ /Ý 9ß Oß Kß FÝ &ß IÑ IÝ 0ß GÝ 5Ý ,ô<ˆr�y‰yô <ò(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ô$6<˜2Ÿ9™9ô 6<ðr ôF
Ð%ó F
ó ðF
ðR ôG
Ð+¨_ó G
ó ðG
òT E‚r2   