+
    œ°³jyT  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 ^RIHt ^RI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" ^RI#H$t$ ^RI%H&t&H't' ^RI(H)t) ^RI*H+t+  ! R R]PX                  4      t- ! R R]PX                  4      t.R R lt/R-R R llt0R t1R.R lt2 ! R R]PX                  4      t3]! R4       ! R R ]PX                  4      4       t4 ! R! R"]4      t5]! ! R# R$]4      4       t6]! ! R% R&]64      4       t7]! ! R' R(]6]4      4       t8 ! R) R*]]64      t9 ! R+ R,]]64      t:. R/Ot;R# )0é    )ÚCallableN)ÚACT2FN)ÚCacheÚDynamicCache)ÚGenerationMixin)Úuse_kernel_forward_from_hub)Úcreate_causal_mask)Ú GenericForSequenceClassificationÚGenericForTokenClassificationÚGradientCheckpointingLayer)ÚBaseModelOutputWithPastÚCausalLMOutputWithPast)ÚROPE_INIT_FUNCTIONSÚdynamic_rope_update)ÚALL_ATTENTION_FUNCTIONSÚPreTrainedModel)ÚUnpack)ÚTransformersKwargsÚauto_docstringÚcan_return_tuple)Údeprecate_kwarg)Úmaybe_autocastÚmerge_with_config_defaults)Úcapture_outputs©Ú	GlmConfigc                   óD   a a€ ] tR t^0t oV 3R ltV3R lR ltRtVtV ;t# )ÚGlmMLPc                ó>  <€ \         SV `  4        Wn        \        P                  ! VP
                  ^VP                  ,          RR7      V n        \        P                  ! VP                  VP
                  RR7      V n        \        VP                  ,          V n        R# )é   F©ÚbiasN)ÚsuperÚ__init__ÚconfigÚnnÚLinearÚhidden_sizeÚintermediate_sizeÚgate_up_projÚ	down_projr   Ú
hidden_actÚactivation_fn©Úselfr%   Ú	__class__s   &&€Úe/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/glm/modeling_glm.pyr$   ÚGlmMLP.__init__1   sn   ø€ Ü‰ÑÔàŒÜŸIšI f×&8Ñ&8¸!¸f×>VÑ>VÕ:VÐ]bÔcˆÔÜŸš 6×#;Ñ#;¸V×=OÑ=OÐV[Ô\ˆŒÜ# F×$5Ñ$5Õ6ˆÖó    c                óN   <€ V ^8„  d   QhRS[ P                  RS[ P                  /# ©r    Úhidden_statesÚreturn)ÚtorchÚFloatTensor)ÚformatÚ__classdict__s   "€r1   Ú__annotate__ÚGlmMLP.__annotate__9   s'   ø€ ÷ )ñ )¡U×%6Ñ%6ð )¹5×;LÑ;Lñ )r3   c                óž   € V P                  V4      pVP                  ^RR7      w  r2W P                  V4      ,          pV P                  V4      # )r    ©Údiméÿÿÿÿ)r*   Úchunkr-   r+   )r/   r6   Ú	up_statesÚgates   &&  r1   ÚforwardÚGlmMLP.forward9   sH   € Ø×%Ñ% mÓ4ˆ	à#Ÿ/™/¨!°˜/Ó4‰ˆØ× 2Ñ 2°4Ó 8Õ8ˆ	à�~‰~˜iÓ(Ð(r3   )r-   r%   r+   r*   ©	Ú__name__Ú
__module__Ú__qualname__Ú__firstlineno__r$   rE   Ú__static_attributes__Ú__classdictcell__Ú__classcell__©r0   r;   s   @@r1   r   r   0   s   ù‡ € õ7÷)÷ )ð )r3   r   c                   óÎ   a a€ ] tR t^Bt 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GlmRotaryEmbeddingÚdevicez5.18)Úversionc                ó    <€ V ^8„  d   QhRS[ /# ©r    r%   r   )r:   r;   s   "€r1   r<   ÚGlmRotaryEmbedding.__annotate__D   s   ø€ ÷ Oñ O™yñ Or3   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$   Úmax_position_embeddingsÚmax_seq_len_cachedÚoriginal_max_seq_lenr%   Úrope_parametersrX   Úcompute_default_rope_parametersr   Úattention_scalingr&   ÚBufferÚinv_freqÚcloneÚoriginal_inv_freq)r/   r%   rR   Úrope_init_fnrb   r0   s   &&&  €r1   r$   ÚGlmRotaryEmbedding.__init__C   s¬   ø€ ä‰ÑÔØ"(×"@Ñ"@ˆÔØ$*×$BÑ$BˆÔ!àŒàŸ™×4Ñ4°[ÕAˆŒØ!%×!EÑ!EˆØ�>‰>˜YÔ&Ü.¨t¯~©~Õ>ˆLÙ+7¸¿¹ÀVÓ+LÑ(ˆÔ(äŸ	š	 (°uÔ=ˆŒÜ!#§¢¨8¯>©>Ó+;ÈÔ!NˆÖr3   c                óP   <€ V ^8„  d   QhRS[ RS[S[P                  S[3,          /# )r    r%   r7   )r   Útupler8   ÚTensorÚfloat)r:   r;   s   "€r1   r<   rV   V   s.   ø€ ÷ 5ñ 5±	ð 5ÑUZÑ[`×[gÑ[gÑinÐ[nÕUoñ 5r3   c           	     óŠ  € V P                   R,          pV P                   P                  RR4      p\        V RR4      ;'       g    V P                  V P                  ,          p\        WT,          4      pRpRV\        P                  ! ^ V^\        P                  R7      V,          ,          ,          pVP                  V4      V3# )a~  
Computes the inverse frequencies according to the original RoPE implementation
Args:
    config ([`~transformers.PreTrainedConfig`]):
        The model configuration.
Returns:
    Tuple of (`torch.Tensor`, `float`), containing the inverse frequencies for the RoPE embeddings and the
    post-processing scaling factor applied to the computed cos/sin (unused in this type of RoPE).
Ú
rope_thetaÚpartial_rotary_factorg      ð?Úhead_dimN©Údtype)
r^   ÚgetÚgetattrr(   Únum_attention_headsÚintr8   Úarangerj   Úto)	r%   rR   ÚkwargsÚbaserm   rn   r@   Úattention_factorrb   s	   &&,      r1   r_   Ú2GlmRotaryEmbedding.compute_default_rope_parametersT   s¦   € ð ×%Ñ% lÕ3ˆØ &× 6Ñ 6× :Ñ :Ð;RÐTWÓ XÐÜ˜6 :¨tÓ4×hÐh¸×8JÑ8JÈf×NhÑNhÕ8hˆÜ�(Õ2Ó3ˆàÐà˜$¤5§<¢<°°3¸ÄÇÁÔ#MÐPSÕ#SÕTÕUˆØ�{‰{˜6Ó"Ð$4Ð4Ð4r3   c                ó^  € V P                   R,          P                  VP                  ^ ,          R	^4      P                  \        P
                  VP                  R7      pVR
,          P                  4       p\        VP                  P                  \        4      '       d2   VP                  P                  R8w  d   VP                  P                  MRp\        VRR7      ;_uu_ 4        W4,          P                  ^^4      p\        P                  ! Wf3R	R7      pVP                  4       V P                  ,          pVP                  4       V P                  ,          p	R R R 4       XP                  VP                   R7      X	P                  VP                   R7      3#   + '       g   i     LH; i)N)rp   rR   ÚmpsÚcpuF)Údevice_typeÚenabledr?   ro   )NºNNNNrA   )r€   Nr€   )rb   ÚexpandÚshaperv   r8   rj   rR   Ú
isinstanceÚtypeÚstrr   Ú	transposeÚcatÚcosr`   Úsinrp   )
r/   ÚxÚposition_idsÚinv_freq_expandedÚposition_ids_expandedr~   ÚfreqsÚembrˆ   r‰   s
   &&&       r1   rE   ÚGlmRotaryEmbedding.forwardj   s2  € ð �M‰M˜-Õ(×/Ñ/°×0BÑ0BÀ1Õ0EÀrÈ1ÓM×PÑPÔW\×WbÑWbÐkl×ksÑksÐPÓtð 	ð !-¨ZÕ 8× >Ñ >Ó @Ðä'1°!·(±(·-±-Ä×'EÒ'EÈ!Ï(É(Ï-É-Ð[`ÔJ`�a—h‘h—m’mÐfkˆä¨¸U×CÖCØ&Õ>×IÑIÈ!ÈQÓOˆEÜ—)’)˜U˜N°Ô3ˆCØ—'‘'“)˜d×4Ñ4Õ4ˆCØ—'‘'“)˜d×4Ñ4Õ4ˆC÷	 Dð �v‰v˜AŸG™GˆvÓ$ c§f¡f°1·7±7 fÓ&;Ð;Ð;÷ D×Cús   Ã(A4FÆF,	)r`   r%   rb   r\   rd   r]   rX   ©N)rH   rI   rJ   rK   r   r$   Ústaticmethodr_   r8   Úno_gradr   rE   rL   rM   rN   rO   s   @@r1   rQ   rQ   B   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 <r3   rQ   c                ód   € V ^8„  d   QhR\         P                  R\        R\         P                  /# )r    r6   Ún_repr7   )r8   ri   rt   )r:   s   "r1   r<   r<   }   s.   € ÷ 	Uñ 	UœUŸ\™\ð 	U´#ð 	U¼%¿,¹,ñ 	Ur3   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€   )r‚   r�   Úreshape)r6   r•   ÚbatchÚnum_key_value_headsÚslenrn   s   &&    r1   Ú	repeat_kvr›   }   sU   € ð
 2?×1DÑ1DÑ.€E Ø�„zØÐØ!Ð"2Õ3×:Ñ:¸5ÐW\ÐdlÓm€MØ× Ñ  ¸eÕ(CÀTÓTÐTr3   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dropoutrw   )r&   ÚModuler8   ri   rj   r   r   )r:   s   "r1   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%r3   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    )r@   rp   )ÚpÚtrainingrA   )r›   Únum_key_value_groupsr8   Úmatmulr†   r&   Ú
functionalÚsoftmaxÚfloat32rv   rp   r£   r§   Ú
contiguous)r�   rž   rŸ   r    r¡   r¢   r£   rw   Ú
key_statesÚvalue_statesÚattn_weightsÚattn_outputs   &&&&&&&,    r1   Úeager_attention_forwardr²   ‰   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$Ð$r3   c                óz   € V R,          pV R,          p\         P                  ! V) V3RR7      P                  R4      # )z*Rotates half the hidden dims of the input.r?   ).:r   Nr    ).:é   Nr    rA   éþÿÿÿ)r8   ÚstackÚflatten)rŠ   Úx1Úx2s   &  r1   Úrotate_halfrº   ¢   s6   € à	
ˆ9�€BØ	
ˆ9�€BÜ�;Š;˜˜˜R�y bÔ)×1Ñ1°"Ó5Ð5r3   c                óŽ  € VP                  V4      pVP                  V4      pVRRVP                  R,          ^,          13,          P                  ^RR7      pVRRVP                  R,          ^,          13,          P                  ^RR7      pVP                  R,          pV RRV13,          V RVR13,          rvVRRV13,          VRVR13,          r˜Wb,          \        V4      V,          ,           p
W‚,          \        V4      V,          ,           p\        P
                  ! W§.RR7      p
\        P
                  ! W¹.RR7      pW«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.
.Nr?   rA   )Ú	unsqueezer‚   Úrepeat_interleaverº   r8   r‡   )ÚqÚkrˆ   r‰   Úunsqueeze_dimÚ
rotary_dimÚq_rotÚq_passÚk_rotÚk_passÚq_embedÚk_embeds   &&&&&       r1   Úapply_rotary_pos_embrÈ   ©   s6  € ð$ �-‰-˜Ó
&€CØ
�-‰-˜Ó
&€Cð ˆcÐ'�S—Y‘Y˜r•] aÕ'Ð'Ð'Õ
(×
:Ñ
:¸1À"Ð
:Ó
E€CØ
ˆcÐ'�S—Y‘Y˜r•] aÕ'Ð'Ð'Õ
(×
:Ñ
:¸1À"Ð
:Ó
E€Cð —‘˜2•€JØ�c˜;˜J˜;Ð&Õ'¨¨3°
±Ð+;Õ)<ˆ6Ø�c˜;˜J˜;Ð&Õ'¨¨3°
±Ð+;Õ)<ˆ6ð �{œ{¨5Ó1°CÕ7Õ8€GØ�{œ{¨5Ó1°CÕ7Õ8€Gô �iŠi˜Ð)¨rÔ2€GÜ�iŠi˜Ð)¨rÔ2€GØÐÐr3   c                   ó\   a a€ ] tR t^Ñt oRtRV3R lV 3R llltRV3R lR lltRtVtV ;t	# )	ÚGlmAttentionz=Multi-headed attention from 'Attention Is All You Need' paperc                ó4   <€ V ^8„  d   QhRS[ RS[R,          /# )r    r%   Ú	layer_idxN©r   rt   )r:   r;   s   "€r1   r<   ÚGlmAttention.__annotate__Ô   s#   ø€ ÷ lñ l™yð l±S¸4µZñ lr3   c                óŽ  <€ \         SV `  4        Wn        W n        \	        VR VP
                  VP                  ,          4      V n        VP                  VP                  ,          V n	        V P                  R,          V n
        VP                  V n        RV n        \        P                  ! VP
                  VP                  V P                  ,          VP                  R7      V n        \        P                  ! VP
                  VP                  V P                  ,          VP                  R7      V n        \        P                  ! VP
                  VP                  V P                  ,          VP                  R7      V n        \        P                  ! VP                  V P                  ,          VP
                  RR7      V n        R# )rn   Tr!   FNg      à¿)r#   r$   r%   rÌ   rr   r(   rs   rn   r™   r¨   r¢   Úattention_dropoutÚ	is_causalr&   r'   Úattention_biasÚq_projÚk_projÚv_projÚo_proj©r/   r%   rÌ   r0   s   &&&€r1   r$   ÚGlmAttention.__init__Ô   s@  ø€ Ü‰ÑÔØŒØ"ŒÜ ¨
°F×4FÑ4FÈ&×JdÑJdÕ4dÓeˆŒØ$*×$>Ñ$>À&×B\ÑB\Õ$\ˆÔ!Ø—}‘} dÕ*ˆŒØ!'×!9Ñ!9ˆÔØˆŒä—i’iØ×Ñ × :Ñ :¸T¿]¹]Õ JÐQW×QfÑQfô
ˆŒô —i’iØ×Ñ × :Ñ :¸T¿]¹]Õ JÐQW×QfÑQfô
ˆŒô —i’iØ×Ñ × :Ñ :¸T¿]¹]Õ JÐQW×QfÑQfô
ˆŒô —i’i × :Ñ :¸T¿]¹]Õ JÈF×L^ÑL^ÐejÔkˆŽr3   c                ó  <€ V ^8„  d   QhRS[ P                  RS[S[ P                  S[ P                  3,          R,          RS[ P                  R,          RS[R,          RS[S[,          RS[S[ P                  S[ P                  3,          /# )r    r6   Úposition_embeddingsNr¡   Úpast_key_valuesrw   r7   )r8   ri   rh   r   r   r   )r:   r;   s   "€r1   r<   rÎ   é   s‡   ø€ ÷ &)ñ &)á—|‘|ð&)ñ #¡5§<¡<±·±Ð#=Õ>ÀÕEð&)ñ Ÿ™ tÕ+ð	&)ñ
  �ð&)ñ Ñ+Õ,ð&)ñ 
‰u�|‰|™UŸ\™\Ð)Õ	*ñ&)r3   c                ó  € VP                   R R p. VORNV P                  N5pV P                  V4      P                  V4      P	                  ^^4      pV P                  V4      P                  V4      P	                  ^^4      p	V P                  V4      P                  V4      P	                  ^^4      p
Vw  r¼\        W‰W¼4      w  r‰Ve   VP                  WšV P                  4      w  rš\        P                  ! V P                  P                  \        4      pT! V VV	V
V3RV P                  '       g   RMV P                   RV P"                  /VB w  rïVP$                  ! . VORN5!  P'                  4       pV P)                  V4      pWï3# )Nr£   ç        r¢   rA   )r‚   rn   rÓ   Úviewr†   rÔ   rÕ   rÈ   ÚupdaterÌ   r   Úget_interfacer%   Ú_attn_implementationr²   r§   rÐ   r¢   r—   r­   rÖ   )r/   r6   rÚ   r¡   rÛ   rw   Úinput_shapeÚhidden_shapeÚquery_statesr®   r¯   rˆ   r‰   Úattention_interfacer±   r°   s   &&&&&,          r1   rE   ÚGlmAttention.forwardé   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(r3   )rÐ   r%   rn   rÑ   rÔ   rÌ   r¨   rÖ   rÓ   r¢   rÕ   r‘   )NNN)
rH   rI   rJ   rK   Ú__doc__r$   rE   rL   rM   rN   rO   s   @@r1   rÊ   rÊ   Ñ   s#   ù‡ € ÙG÷lõ l÷*&)÷ &)ò &)r3   rÊ   ÚRMSNormc                   óZ   a a€ ] tR tRt oRV3R lV 3R llltV3R lR ltR tRtVtV ;t	# )	Ú
GlmRMSNormi  c                ó$   <€ V ^8„  d   QhRS[ RR/# )r    Úepsr7   N)rj   )r:   r;   s   "€r1   r<   ÚGlmRMSNorm.__annotate__  s   ø€ ÷ $ñ $©ð $¸$ñ $r3   c                óŽ   <€ \         SV `  4        \        P                  ! \        P
                  ! V4      4      V n        W n        R# )z)
GlmRMSNorm is equivalent to T5LayerNorm
N)r#   r$   r&   Ú	Parameterr8   ÚonesÚweightÚvariance_epsilon)r/   r(   rì   r0   s   &&&€r1   r$   ÚGlmRMSNorm.__init__  s/   ø€ ô 	‰ÑÔÜ—l’l¤5§:¢:¨kÓ#:Ó;ˆŒØ #Ör3   c                óN   <€ V ^8„  d   QhRS[ P                  RS[ P                  /# r5   )r8   ri   )r:   r;   s   "€r1   r<   rí     s#   ø€ ÷ ;ñ ;¡U§\¡\ð ;±e·l±lñ ;r3   c                ó:  € VP                   pVP                  \        P                  4      pVP	                  ^4      P                  RRR7      pV\        P                  ! W0P                  ,           4      ,          pV P                  VP                  V4      ,          # )r    T)ÚkeepdimrA   )	rp   rv   r8   r¬   ÚpowÚmeanÚrsqrtrò   rñ   )r/   r6   Úinput_dtypeÚvariances   &&  r1   rE   ÚGlmRMSNorm.forward  sw   € Ø#×)Ñ)ˆØ%×(Ñ(¬¯©Ó7ˆØ ×$Ñ$ QÓ'×,Ñ,¨R¸Ð,Ó>ˆØ%¬¯ª°H×?TÑ?TÕ4TÓ(UÕUˆØ�{‰{˜]×-Ñ-¨kÓ:Õ:Ð:r3   c                ó^   € \        V P                  P                  4       R V P                   2# )z, eps=)rh   rñ   r‚   rò   )r/   s   &r1   Ú
extra_reprÚGlmRMSNorm.extra_repr#  s*   € Ü˜Ÿ™×)Ñ)Ó*Ð+¨6°$×2GÑ2GÐ1HÐIÐIr3   )rò   rñ   )g�íµ ÷Æ°>)
rH   rI   rJ   rK   r$   rE   rþ   rL   rM   rN   rO   s   @@r1   rê   rê     s%   ù‡ € ÷$õ $÷;ð ;÷Jò Jr3   rê   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GlmDecoderLayeri'  c                ó&   <€ V ^8„  d   QhRS[ RS[/# )r    r%   rÌ   rÍ   )r:   r;   s   "€r1   r<   ÚGlmDecoderLayer.__annotate__(  s   ø€ ÷ `ñ `™yð `±Sñ `r3   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%   rÌ   ©rì   N)r#   r$   r(   rÊ   Ú	self_attnr   Úmlprê   Úrms_norm_epsÚinput_layernormÚpost_attention_layernormr×   s   &&&€r1   r$   ÚGlmDecoderLayer.__init__(  si   ø€ Ü‰ÑÔØ!×-Ñ-ˆÔä%¨VÔIˆŒä˜&“>ˆŒÜ)¨&×*<Ñ*<À&×BUÑBUÔVˆÔÜ(2°6×3EÑ3EÈ6×K^ÑK^Ô(_ˆÖ%r3   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    r6   r¡   Nr‹   rÛ   Ú	use_cacherÚ   rw   r7   )r8   ri   Ú
LongTensorr   Úboolrh   r   r   )r:   r;   s   "€r1   r<   r  2  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r3   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# )r6   r¡   r‹   rÛ   r  rÚ   © )r	  r  r
  r  )
r/   r6   r¡   r‹   rÛ   r  rÚ   rw   ÚresidualÚ_s
   &&&&&&&,  r1   rE   ÚGlmDecoderLayer.forward2  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r3   )r(   r	  r  r
  r  )NNNFNrG   rO   s   @@r1   r  r  '  s    ù‡ € ÷`ó `÷÷ ò r3   r  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GlmPreTrainedModeliR  ÚmodelTr  rÛ   r6   Ú
attentionsc                ó&   <€ V ^8„  d   Qh/ S[ ;R&   # rU   r   )r:   r;   s   "€r1   r<   ÚGlmPreTrainedModel.__annotate__R  s   ø‡ ‚ áÑò r3   r  N)rH   rI   rJ   rK   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  rÊ   Ú_can_record_outputsÚ__annotate_func__rL   rM   )r;   s   @r1   r  r  R  s[   ø‡ € ð  ÐØ&*Ð#Ø*Ð+ÐØ#4Ð"5ÐØÐØ€NØÐà!ÐØ"&Ðà˜Ø�lðÐ÷ ƒ r3   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GlmModelie  c                ó    <€ V ^8„  d   QhRS[ /# rU   r   )r:   r;   s   "€r1   r<   ÚGlmModel.__annotate__g  s   ø€ ÷ ñ ™yñ r3   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_layersr  Úlayersrê   r  ÚnormrQ   Ú
rotary_embÚgradient_checkpointingÚ	post_initr×   s   && €r1   r$   ÚGlmModel.__init__g  sÉ   ø€ Ü‰Ñ˜Ô Ø!×.Ñ.ˆÔØ ×+Ñ+ˆŒäŸLšL¨×):Ñ):¸F×<NÑ<NÐPT×P`ÑP`ÓaˆÔÜ—m’mÜAFÀv×G_ÑG_ÔA`ÓaÑA`°IŒ_˜VÖ/ÑA`Ñaó
ˆŒô ˜v×1Ñ1°v×7JÑ7JÔKˆŒ	Ü,°FÔ;ˆŒØ&+ˆÔ#ð 	�‰Öùò bs   ÂDc                óþ   <€ V ^8„  d   QhRS[ P                  R,          RS[ P                  R,          RS[ P                  R,          RS[R,          RS[ P                  R,          RS[R,          RS[S[,          R	S[/# )
r    Ú	input_idsNr¡   r‹   rÛ   Úinputs_embedsr  rw   r7   )	r8   r  ri   r   r9   r  r   r   r   )r:   r;   s   "€r1   r<   r)  z  s“   ø€ ÷ 2
ñ 2
á×#Ñ# dÕ*ð2
ñ Ÿ™ tÕ+ð2
ñ ×&Ñ&¨Õ-ð	2
ñ
  �ð2
ñ ×(Ñ(¨4Õ/ð2
ñ ˜$•;ð2
ñ Ñ+Õ,ð2
ñ 
!ñ2
r3   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+  )rR   )r%   r<  r¡   rÛ   r‹   )r‹   r¡   rÚ   r‹   rÛ   r  )Úlast_hidden_staterÛ   )Ú
ValueErrorr0  r   r%   Úget_seq_lengthr8   ru   r‚   rR   r¼   r	   r6  r4  r3  r5  r   )r/   r;  r¡   r‹   rÛ   r<  r  rw   Úpast_seen_tokensÚcausal_maskr6   rÚ   Údecoder_layers   &&&&&&&,     r1   rE   ÚGlmModel.forwardw  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 	
r3   )r0  r7  r4  r5  r-  r6  r.  )NNNNNN)rH   rI   rJ   rK   r$   r   r   r   rE   rL   rM   rN   rO   s   @@r1   r'  r'  e  s=   ù‡ € ÷ó ð   ØØ÷2
ñ 2
ó ó ó  ÷2
ð 2
r3   r'  c                   ó„   a a€ ] tR tRt oRR/tRR/tRR.R.3/tRR/tV 3R	 lt]	]
RV3R
 lR ll4       4       tRtVtV ;t# )ÚGlmForCausalLMi¯  zlm_head.weightzmodel.embed_tokens.weightÚlm_headÚcolwise_gather_outputr6   ÚlogitsÚkeep_full_weightc                óì   <€ \         SV `  V4       \        V4      V n        VP                  V n        \
        P                  ! VP                  VP                  R R7      V n        V P                  4        R# )Fr!   N)
r#   r$   r'  r  r.  r&   r'   r(   rG  r8  r.   s   &&€r1   r$   ÚGlmForCausalLM.__init__¶  sU   ø€ Ü‰Ñ˜Ô Ü˜fÓ%ˆŒ
Ø ×+Ñ+ˆŒÜ—y’y ×!3Ñ!3°V×5FÑ5FÈUÔSˆŒð 	�‰Ör3   c                óP  <€ V ^8„  d   QhRS[ P                  R,          RS[ P                  R,          RS[ P                  R,          RS[R,          RS[ P                  R,          RS[ P                  R,          RS[R,          R	S[S[ P                  ,          R
S[S[,          RS[	/
# )r    r;  Nr¡   r‹   rÛ   r<  Úlabelsr  Úlogits_to_keeprw   r7   )
r8   r  ri   r   r9   r  rt   r   r   r   )r:   r;   s   "€r1   r<   ÚGlmForCausalLM.__annotate__Á  s»   ø€ ÷ 6
ñ 6
á×#Ñ# dÕ*ð6
ñ Ÿ™ tÕ+ð6
ñ ×&Ñ&¨Õ-ð	6
ñ
  �ð6
ñ ×(Ñ(¨4Õ/ð6
ñ × Ñ  4Õ'ð6
ñ ˜$•;ð6
ñ ™eŸl™lÕ*ð6
ñ Ñ+Õ,ð6
ñ 
 ñ6
r3   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      # )ac  
Example:

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

>>> model = GlmForCausalLM.from_pretrained("meta-glm/Glm-2-7b-hf")
>>> tokenizer = AutoTokenizer.from_pretrained("meta-glm/Glm-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‹   rÛ   r<  r  Nr€   rI  rN  r.  )ÚlossrI  rÛ   r6   r  r  )r  r>  rƒ   rt   ÚslicerG  Úloss_functionr%   r.  r   rÛ   r6   r  )r/   r;  r¡   r‹   rÛ   r<  rN  r  rO  rw   Úoutputsr6   Úslice_indicesrI  rR  s   &&&&&&&&&,     r1   rE   ÚGlmForCausalLM.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 	
r3   )rG  r  r.  )NNNNNNNr   )rH   rI   rJ   rK   Ú_tied_weights_keysÚ_tp_planÚ_pp_planÚ
_fsdp_planr$   r   r   rE   rL   rM   rN   rO   s   @@r1   rF  rF  ¯  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
r3   rF  c                   ó   € ] tR tRtRtR# )ÚGlmForSequenceClassificationiú  r  N©rH   rI   rJ   rK   rL   r  r3   r1   r]  r]  ú  ó   † Ûr3   r]  c                   ó   € ] tR tRtRtR# )ÚGlmForTokenClassificationiþ  r  Nr^  r  r3   r1   ra  ra  þ  r_  r3   ra  )rÝ   )r´   )r  r'  rF  r]  ra  )<Úcollections.abcr   r8   Útorch.nnr&   Úactivationsr   Úcache_utilsr   r   Ú
generationr   Úintegrationsr   Úmasking_utilsr	   Úmodeling_layersr
   r   r   Úmodeling_outputsr   r   Úmodeling_rope_utilsr   r   Úmodeling_utilsr   r   Úprocessing_utilsr   Úutilsr   r   r   Úutils.deprecationr   Úutils.genericr   r   Úutils.output_capturingr   Úconfiguration_glmr   r¤   r   rQ   r›   r²   rº   rÈ   rÊ   rê   r  r  r'  rF  r]  ra  Ú__all__r  r3   r1   Ú<module>rt     sK  ðõ, %ã Ý å !ß .Ý )Ý 7Ý /÷ñ ÷
 Pß Kß FÝ &ß IÑ IÝ 0ß GÝ 5Ý (ô)ˆR�Y‰Yô )ô$8<˜Ÿ™ô 8<õv	U÷%ò26ô%ôP>)�2—9‘9ô >)ñB ˜YÓ'ôJ�—‘ó Jó (ðJô((Ð0ô (ðV ô˜ó ó ðð$ ôF
Ð!ó F
ó ðF
ðR ôG
Ð'¨ó G
ó ðG
ôT	Ð#CÐEWô 	ô	Ð =Ð?Qô 	ò‚r3   