+
    œ°³j¼Q  ã                   ó  € ^ 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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"H#t#H$t$ ^RI%H&t& ^RI'H(t(H)t) ^RI*H+t+ ^RI,H-t- ]$P\                  ! ]/4      t0]! R4       ! R R]Pb                  4      4       t2 ! R R]Pb                  4      t3R t4]! R4      R1R l4       t5 ! R R]Pb                  4      t6R R lt7R2R R  llt8]! ]54       ! R! R"]Pb                  4      4       t9 ! R# R$]4      t:]" ! R% R&]4      4       t;]" ! R' R(];4      4       t<]" ! R) R*];]
4      4       t= ! R+ R,]];4      t> ! R- R.]];4      t? ! R/ R0]];4      t@. R3OtAR# )4é    )ÚCallableN)Únn)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auto_docstringÚcan_return_tupleÚlogging)Údeprecate_kwarg)Úmaybe_autocastÚmerge_with_config_defaults)Úcapture_outputs©ÚLlamaConfigÚRMSNormc                   óZ   a a€ ] tR t^4t 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LlamaRMSNormc                ó$   <€ V ^8„  d   QhRS[ RR/# )é   ÚepsÚreturnN)Úfloat)ÚformatÚ__classdict__s   "€Úi/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/llama/modeling_llama.pyÚ__annotate__ÚLlamaRMSNorm.__annotate__6   s   ø€ ÷ $ñ $©ð $¸$ñ $ó    c                óŽ   <€ \         SV `  4        \        P                  ! \        P
                  ! V4      4      V n        W n        R# )z+
LlamaRMSNorm is equivalent to T5LayerNorm
N)ÚsuperÚ__init__r   Ú	ParameterÚtorchÚonesÚweightÚvariance_epsilon)ÚselfÚhidden_sizer&   Ú	__class__s   &&&€r+   r1   ÚLlamaRMSNorm.__init__6   s/   ø€ ô 	‰ÑÔÜ—l’l¤5§:¢:¨kÓ#:Ó;ˆŒØ #Ör.   c                óN   <€ V ^8„  d   QhRS[ P                  RS[ P                  /# )r%   Úhidden_statesr'   )r3   ÚTensor)r)   r*   s   "€r+   r,   r-   >   s#   ø€ ÷ ;ñ ;¡U§\¡\ð ;±e·l±lñ ;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tor3   Úfloat32ÚpowÚmeanÚrsqrtr6   r5   )r7   r<   Úinput_dtypeÚvariances   &&  r+   ÚforwardÚLlamaRMSNorm.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�{‰{˜]×-Ñ-¨kÓ:Õ:Ð:r.   c                ó^   € \        V P                  P                  4       R V P                   2# )z, eps=)Útupler5   Úshaper6   )r7   s   &r+   Ú
extra_reprÚLlamaRMSNorm.extra_reprE   s*   € Ü˜Ÿ™×)Ñ)Ó*Ð+¨6°$×2GÑ2GÐ1HÐIÐIr.   )r6   r5   )g�íµ ÷Æ°>)
Ú__name__Ú
__module__Ú__qualname__Ú__firstlineno__r1   rI   rN   Ú__static_attributes__Ú__classdictcell__Ú__classcell__©r9   r*   s   @@r+   r#   r#   4   s%   ù‡ € ÷$õ $÷;ð ;÷Jò Jr.   r#   c                   óÎ   a a€ ] tR t^It o]! RRR7      R
V3R lV 3R lll4       t]]! RRR7      R
V3R lR ll4       4       t]P                  ! 4       ]
R 4       4       tR	tVtV ;t# )ÚLlamaRotaryEmbeddingÚdevicez5.18)Úversionc                ó    <€ V ^8„  d   QhRS[ /# ©r%   Úconfigr   )r)   r*   s   "€r+   r,   Ú!LlamaRotaryEmbedding.__annotate__K   s   ø€ ÷ Oñ O™{ñ Or.   c                óä  <€ \         SV `  4        VP                  V n        VP                  V n        Wn        V P
                  P                  R ,          V n        V P                  pV P                  R8w  d   \        V P                  ,          pV! V P
                  V4      w  q@n
        \        P                  ! VRR7      V n        \        P                  ! VP                  4       RR7      V n        R# )Ú	rope_typeÚdefaultF)Ú
persistentN)r0   r1   Úmax_position_embeddingsÚmax_seq_len_cachedÚoriginal_max_seq_lenr^   Úrope_parametersra   Úcompute_default_rope_parametersr   Úattention_scalingr   ÚBufferÚinv_freqÚcloneÚoriginal_inv_freq)r7   r^   rZ   Úrope_init_fnrk   r9   s   &&&  €r+   r1   ÚLlamaRotaryEmbedding.__init__J   s¬   ø€ ä‰ÑÔØ"(×"@Ñ"@ˆÔØ$*×$BÑ$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    rL   r3   r=   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?©rA   )rg   Úgetattrr8   Únum_attention_headsr3   Úaranger(   rB   )r^   rZ   ÚkwargsÚbaseÚdimÚattention_factorrk   s   &&,    r+   rh   Ú4LlamaRotaryEmbedding.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$4Ð4Ð4r.   c                ó^  € V P                   R,          P                  VP                  ^ ,          R	^4      P                  \        P
                  VP                  R7      pVR
,          P                  4       p\        VP                  P                  \        4      '       d2   VP                  P                  R8w  d   VP                  P                  MRp\        VRR7      ;_uu_ 4        W4,          P                  ^^4      p\        P                  ! Wf3R	R7      pVP                  4       V P                  ,          pVP                  4       V P                  ,          p	R R R 4       XP                  VP                   R7      X	P                  VP                   R7      3#   + '       g   i     LH; i)N)rA   rZ   ÚmpsÚcpuF)Údevice_typeÚenabled©rz   rt   )NºNNNNr@   )rƒ   Nrƒ   )rk   ÚexpandrM   rB   r3   r(   rZ   Ú
isinstanceÚtypeÚstrr   Ú	transposeÚcatÚcosri   ÚsinrA   )
r7   ÚxÚposition_idsÚinv_freq_expandedÚposition_ids_expandedr€   ÚfreqsÚembrŠ   r‹   s
   &&&       r+   rI   ÚLlamaRotaryEmbedding.forwardo   s2  € ð �M‰M˜-Õ(×/Ñ/°×0BÑ0BÀ1Õ0EÀrÈ1ÓM×PÑPÔW\×WbÑWbÐkl×ksÑksÐPÓtð 	ð !-¨ZÕ 8× >Ñ >Ó @Ðä'1°!·(±(·-±-Ä×'EÒ'EÈ!Ï(É(Ï-É-Ð[`ÔJ`�a—h‘h—m’mÐfkˆä¨¸U×CÖCØ&Õ>×IÑIÈ!ÈQÓOˆEÜ—)’)˜U˜N°Ô3ˆCØ—'‘'“)˜d×4Ñ4Õ4ˆCØ—'‘'“)˜d×4Ñ4Õ4ˆC÷	 Dð �v‰v˜AŸG™GˆvÓ$ c§f¡f°1·7±7 fÓ&;Ð;Ð;÷ D×Cús   Ã(A4FÆF,	)ri   r^   rk   re   rm   rf   ra   ©N)rP   rQ   rR   rS   r   r1   Ústaticmethodrh   r3   Úno_gradr   rI   rT   rU   rV   rW   s   @@r+   rY   rY   I   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.   rY   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@   )rM   r3   r‰   )rŒ   Úx1Úx2s   &  r+   Úrotate_halfr™   ‚   sZ   € à	
ˆ3Ð"�!—'‘'˜"•+ Õ"Ð"Ð"Õ	#€BØ	
ˆ3�—‘˜•˜qÕ Ñ"Ð"Õ	#€BÜ�9Š9�r�c˜2�Y BÔ'Ð'r.   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krŠ   r‹   Úunsqueeze_dimÚq_embedÚk_embeds   &&&&&  r+   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r.   c                   ó8   a a€ ] tR t^£t oV 3R ltR tRtVtV ;t# )ÚLlamaMLPc                ó  <€ \         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	        \
        P                  ! V P                  V P                  VP                  R 7      V n
        \        VP                  ,          V n        R# )©ÚbiasN)r0   r1   r^   r8   Úintermediate_sizer   ÚLinearÚmlp_biasÚ	gate_projÚup_projÚ	down_projr   Ú
hidden_actÚact_fn©r7   r^   r9   s   &&€r+   r1   ÚLlamaMLP.__init__¤   s¶   ø€ Ü‰ÑÔØŒØ!×-Ñ-ˆÔØ!'×!9Ñ!9ˆÔÜŸš 4×#3Ñ#3°T×5KÑ5KÐRX×RaÑRaÔbˆŒ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r.   c                ó�   € V P                  V P                  V P                  V4      4      V P                  V4      ,          4      pV# r“   )r­   r¯   r«   r¬   )r7   rŒ   r­   s   && r+   rI   ÚLlamaMLP.forward®   s6   € Ø—N‘N 4§;¡;¨t¯~©~¸aÓ/@Ó#AÀDÇLÁLÐQRÃOÕ#SÓTˆ	ØÐr.   )r¯   r^   r­   r«   r8   r¨   r¬   ©	rP   rQ   rR   rS   r1   rI   rT   rU   rV   rW   s   @@r+   r¤   r¤   £   s   ù‡ € õ0÷ò r.   r¤   c                ód   € V ^8„  d   QhR\         P                  R\        R\         P                  /# )r%   r<   Ún_repr'   )r3   r=   Úint)r)   s   "r+   r,   r,   ³   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)
)rƒ   rƒ   Nrƒ   rƒ   )rM   r„   Úreshape)r<   r¶   ÚbatchÚnum_key_value_headsÚslenrs   s   &&    r+   Ú	repeat_kvr½   ³   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dropoutrx   )r   ÚModuler3   r=   r(   r   r   )r)   s   "r+   r,   r,   ¿   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%   )rz   rA   )ÚpÚtrainingr@   )r½   Únum_key_value_groupsr3   Úmatmulrˆ   r   Ú
functionalÚsoftmaxrC   rB   rA   rÅ   rÉ   Ú
contiguous)r¿   rÀ   rÁ   rÂ   rÃ   rÄ   rÅ   rx   Ú
key_statesÚvalue_statesÚattn_weightsÚattn_outputs   &&&&&&&,    r+   Úeager_attention_forwardrÓ   ¿   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.   c                   óX   a a€ ] tR t^Øt 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LlamaAttentionz=Multi-headed attention from 'Attention Is All You Need' paperc                ó&   <€ V ^8„  d   QhRS[ RS[/# ©r%   r^   Ú	layer_idx©r    r·   )r)   r*   s   "€r+   r,   ÚLlamaAttention.__annotate__Ü   s   ø€ ÷ 
ñ 
™{ð 
±sñ 
r.   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# )rs   Tr¦   Ng      à¿)r0   r1   r^   rØ   ru   r8   rv   rs   r»   rÊ   rÄ   Úattention_dropoutÚ	is_causalr   r©   Úattention_biasÚq_projÚk_projÚv_projÚo_proj©r7   r^   rØ   r9   s   &&&€r+   r1   ÚLlamaAttention.__init__Ü   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r.   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,          /# )r%   r<   Úposition_embeddingsNrÃ   Úpast_key_valuesrx   r'   )r3   r=   rL   r   r   r   )r)   r*   s   "€r+   r,   rÚ   ó   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&)r.   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$                  ! . VORN5!  P'                  4       pV P)                  V4      pWï3# )NrÅ   ç        rÄ   r@   )rM   rs   rß   Úviewrˆ   rà   rá   r¢   ÚupdaterØ   r   Úget_interfacer^   Ú_attn_implementationrÓ   rÉ   rÜ   rÄ   r¹   rÎ   râ   )r7   r<   ræ   rÃ   rç   rx   Úinput_shapeÚhidden_shapeÚquery_statesrÏ   rÐ   rŠ   r‹   Úattention_interfacerÒ   rÑ   s   &&&&&,          r+   rI   ÚLlamaAttention.forwardó   s‡  € ð $×)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(r.   )rÜ   r^   rs   rÝ   rà   rØ   rÊ   râ   rß   rÄ   rá   )NNN)
rP   rQ   rR   rS   Ú__doc__r1   rI   rT   rU   rV   rW   s   @@r+   rÕ   rÕ   Ø   s!   ù‡ € áG÷
ó 
÷.&)÷ &)ò &)r.   rÕ   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LlamaDecoderLayeri  c                ó&   <€ V ^8„  d   QhRS[ RS[/# r×   rÙ   )r)   r*   s   "€r+   r,   ÚLlamaDecoderLayer.__annotate__  s   ø€ ÷ bñ b™{ð b±sñ b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^   rØ   ©r&   N)r0   r1   r8   rÕ   Ú	self_attnr¤   Úmlpr#   Úrms_norm_epsÚinput_layernormÚpost_attention_layernormrã   s   &&&€r+   r1   ÚLlamaDecoderLayer.__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%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%   r<   rÃ   Nr�   rç   Ú	use_cacheræ   rx   r'   )r3   r=   Ú
LongTensorr   ÚboolrL   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                  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# )r<   rÃ   r�   rç   r  ræ   © )rý   rú   rþ   rû   )
r7   r<   rÃ   r�   rç   r  ræ   rx   ÚresidualÚ_s
   &&&&&&&,  r+   rI   ÚLlamaDecoderLayer.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r.   )r8   rý   rû   rþ   rú   )NNNFNr´   rW   s   @@r+   rõ   rõ     s    ù‡ € ÷bó b÷÷ 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LlamaPreTrainedModeliG  ÚmodelTrõ   rç   r<   Ú
attentionsc                ó&   <€ V ^8„  d   Qh/ S[ ;R&   # r]   r   )r)   r*   s   "€r+   r,   Ú!LlamaPreTrainedModel.__annotate__G  s   ø‡ ‚ áÑò r.   r  N)rP   rQ   rR   rS   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   rÕ   Ú_can_record_outputsÚ__annotate_func__rT   rU   )r*   s   @r+   r
  r
  G  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
LlamaModeliZ  c                ó    <€ V ^8„  d   QhRS[ /# r]   r   )r)   r*   s   "€r+   r,   ÚLlamaModel.__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)r0   r1   Úpad_token_idÚpadding_idxÚ
vocab_sizer   Ú	Embeddingr8   Úembed_tokensÚ
ModuleListÚrangeÚnum_hidden_layersrõ   Úlayersr#   rü   ÚnormrY   Ú
rotary_embÚgradient_checkpointingÚ	post_initrã   s   && €r+   r1   ÚLlamaModel.__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_idsNrÃ   r�   rç   Úinputs_embedsr  rx   r'   )	r3   r  r=   r   ÚFloatTensorr  r   r   r   )r)   r*   s   "€r+   r,   r  o  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  )rZ   )r^   r0  rÃ   rç   r�   )r�   rÃ   ræ   r�   rç   r  )Úlast_hidden_staterç   )Ú
ValueErrorr$  r   r^   Úget_seq_lengthr3   rw   rM   rZ   rœ   r   r*  r(  r'  r)  r   )r7   r/  rÃ   r�   rç   r0  r  rx   Úpast_seen_tokensÚcausal_maskr<   ræ   Údecoder_layers   &&&&&&&,     r+   rI   ÚLlamaModel.forwardl  se  € ð ˜Ð -°tÐ";×<Ô<ÜÐYÓZÐZàÒ Ø*.×*;Ñ*;¸IÓ*FˆMç˜Ò0Ü*°$·+±+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)rP   rQ   rR   rS   r1   r   r   r   rI   rT   rU   rV   rW   s   @@r+   r  r  Z  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LlamaForCausalLMi¤  zlm_head.weightzmodel.embed_tokens.weightÚlm_headÚcolwise_gather_outputr<   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)
r0   r1   r  r  r"  r   r©   r8   r<  r,  r°   s   &&€r+   r1   ÚLlamaForCausalLM.__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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/  NrÃ   r�   rç   r0  Úlabelsr  Úlogits_to_keeprx   r'   )
r3   r  r=   r   r1  r  r·   r   r   r   )r)   r*   s   "€r+   r,   ÚLlamaForCausalLM.__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
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, LlamaForCausalLM

>>> model = LlamaForCausalLM.from_pretrained("meta-llama/Llama-2-7b-hf")
>>> tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-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/  rÃ   r�   rç   r0  r  Nrƒ   r>  rC  r"  )Úlossr>  rç   r<   r  r  )r  r3  r…   r·   Úslicer<  Úloss_functionr^   r"  r   rç   r<   r  )r7   r/  rÃ   r�   rç   r0  rC  r  rD  rx   Úoutputsr<   Úslice_indicesr>  rG  s   &&&&&&&&&,     r+   rI   ÚLlamaForCausalLM.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 	
r.   )r<  r  r"  )NNNNNNNr   )rP   rQ   rR   rS   Ú_tied_weights_keysÚ_tp_planÚ_pp_planÚ
_fsdp_planr1   r   r   rI   rT   rU   rV   rW   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LlamaForSequenceClassificationiï  r  N©rP   rQ   rR   rS   rT   r  r.   r+   rR  rR  ï  s   † Ó^ar.   rR  c                   ó   € ] tR tRtRtRtR# )ÚLlamaForQuestionAnsweringiò  Útransformerr  N)rP   rQ   rR   rS   r  rT   r  r.   r+   rU  rU  ò  s   † Ø%Ôr.   rU  c                   ó   € ] tR tRtRtR# )ÚLlamaForTokenClassificationiö  r  NrS  r  r.   r+   rX  rX  ö  s   † ÓX[r.   rX  )é   )ré   )r;  r  r
  rR  rU  rX  )BÚcollections.abcr   r3   r   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   r   r   Úutils.deprecationr   Úutils.genericr   r   Úutils.output_capturingr   Úconfiguration_llamar    Ú
get_loggerrP   ÚloggerrÆ   r#   rY   r™   r¢   r¤   r½   rÓ   rÕ   rõ   r
  r  r;  rR  rU  rX  Ú__all__r  r.   r+   Ú<module>rm     s™  ðõ& %ã Ý å !ß .Ý )ß LÝ /÷ó ÷÷ Lß FÝ &ß RÓ RÝ 0ß GÝ 5Ý ,ð 
×	Ò	˜HÓ	%€ñ ˜YÓ'ôJ�2—9‘9ó Jó (ðJô(6<˜2Ÿ9™9ô 6<òr(ñ Ð-Ó.óó /ðô2ˆr�y‰yô õ 	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
ðR ôG
Ð+¨_ó G
ó ðG
ôT bÐ%EÐG[Ô aô&Ð ;Ð=Qô &ô \Ð"?ÐAUÔ [ò‚r.   