
    cCibc                        S SK JrJrJr  S SKrS SKJr  SSKJr  SSK	J
r
Jr  SSKJr  SSKJrJr  SSKJr  SS	KJrJrJr  SS
KJrJr  SSKJrJr  SSKJrJr  SSK J!r!  SSK"J#r#J$r$J%r%J&r&  SSK'J(r(  SSK)J*r*  SSK+J,r,  \&RZ                  " \.5      r/ " S S\R`                  5      r1 " S S\R`                  5      r2 " S S\R`                  5      r3S r4S7S jr5S\Rl                  S\7S\Rl                  4S jr8   S8S\R`                  S \Rl                  S!\Rl                  S"\Rl                  S#\\Rl                     S$\9S%\\9   S&\\9   S\:\Rl                  \Rl                  4   4S' jjr; " S( S)\R`                  5      r< " S* S+\5      r=\$ " S, S-\5      5       r>\$ " S. S/\>5      5       r?\$ " S0 S1\>\5      5       r@ " S2 S3\\>5      rA " S4 S5\\>5      rB/ S6QrCg)9    )CallableOptionalUnionN   )ACT2FN)CacheDynamicCache)GenerationMixin)create_causal_mask!create_sliding_window_causal_mask)FlashAttentionKwargs) GenericForSequenceClassificationGenericForTokenClassificationGradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuplelogging)deprecate_kwarg)check_model_inputs   )Gemma2Configc                   J   ^  \ rS rSrS	S\S\4U 4S jjjrS rS rS r	Sr
U =r$ )
Gemma2RMSNorm2   dimepsc                    > [         TU ]  5         X l        [        R                  " [
        R                  " U5      5      U l        g N)super__init__r$   nn	Parametertorchzerosweight)selfr#   r$   	__class__s      d/home/james-whalen/.local/lib/python3.13/site-packages/transformers/models/gemma2/modeling_gemma2.pyr(   Gemma2RMSNorm.__init__3   s,    ll5;;s#34    c                     U[         R                  " UR                  S5      R                  SSS9U R                  -   5      -  $ )N   T)keepdim)r+   rsqrtpowmeanr$   )r.   xs     r0   _normGemma2RMSNorm._norm8   s4    5;;quuQx}}R}>IJJJr2   c                     U R                  UR                  5       5      nUSU R                  R                  5       -   -  nUR                  U5      $ )Ng      ?)r;   floatr-   type_as)r.   r:   outputs      r0   forwardGemma2RMSNorm.forward;   sC    AGGI& 3!2!2!445~~a  r2   c                 ^    [        U R                  R                  5       SU R                   3$ )Nz, eps=)tupler-   shaper$   )r.   s    r0   
extra_reprGemma2RMSNorm.extra_reprB   s'    ))*+6$((<<r2   )r$   r-   )gư>)__name__
__module____qualname____firstlineno__intr>   r(   r;   rA   rF   __static_attributes____classcell__r/   s   @r0   r!   r!   2   s0    5C 5e 5 5
K!= =r2   r!   c                   .   ^  \ rS rSrU 4S jrS rSrU =r$ )	Gemma2MLPF   c                   > [         TU ]  5         Xl        UR                  U l        UR                  U l        [
        R                  " U R                  U R                  SS9U l        [
        R                  " U R                  U R                  SS9U l        [
        R                  " U R                  U R                  SS9U l	        [        UR                     U l        g NFbias)r'   r(   confighidden_sizeintermediate_sizer)   Linear	gate_projup_proj	down_projr   hidden_activationact_fnr.   rW   r/   s     r0   r(   Gemma2MLP.__init__G   s    !--!'!9!94#3#3T5K5KRWXyy!1!143I3IPUV4#9#94;K;KRWXV556r2   c                     U R                  U R                  U R                  U5      5      U R                  U5      -  5      nU$ r&   )r]   r_   r[   r\   )r.   r:   r]   s      r0   rA   Gemma2MLP.forwardQ   s6    NN4;;t~~a/@#ADLLQRO#ST	r2   )r_   rW   r]   r[   rX   rY   r\   )rH   rI   rJ   rK   r(   rA   rM   rN   rO   s   @r0   rQ   rQ   F   s    7 r2   rQ   c                      ^  \ rS rSr% \R
                  \S'   SS\4U 4S jjjr\R                  " 5       \
S 5       5       rSrU =r$ )Gemma2RotaryEmbeddingV   inv_freqrW   c                   > [         TU ]  5         [        US5      (       aZ  [        UR                  [
        5      (       a;  UR                  R                  SUR                  R                  S5      5      U l        OSU l        UR                  U l	        UR                  U l
        Xl        [        U R                     U l        U R                  U R                  U5      u  o0l        U R                  SUSS9  U R                   U l        g )Nrope_scaling	rope_typetypedefaultrg   F)
persistent)r'   r(   hasattr
isinstanceri   dictgetrj   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrW   r   rope_init_fnattention_scalingregister_bufferrg   original_inv_freq)r.   rW   devicerg   r/   s       r0   r(   Gemma2RotaryEmbedding.__init__Y   s    6>**z&:M:Mt/T/T#0044[&BUBUBYBYZ`BabDN&DN"("@"@$*$B$B!/?+/+<+<T[[&+Q((ZeD!%r2   c                 b   U R                   S S S 2S 4   R                  5       R                  UR                  S   SS5      R	                  UR
                  5      nUS S 2S S S 24   R                  5       n[        UR
                  R                  [        5      (       a0  UR
                  R                  S:w  a  UR
                  R                  OSn[        R                  " USS9   UR                  5       UR                  5       -  R                  SS5      n[        R                  " Xf4SS	9nUR                  5       U R                  -  nUR                  5       U R                  -  n	S S S 5        WR	                  UR                   S
9W	R	                  UR                   S
94$ ! , (       d  f       N@= f)Nr   r5   r   mpscpuF)device_typeenabledr4   r#   dtype)rg   r>   expandrE   tory   ro   rk   strr+   autocast	transposecatcosrv   sinr   )
r.   r:   position_idsinv_freq_expandedposition_ids_expandedr~   freqsembr   r   s
             r0   rA   Gemma2RotaryEmbedding.forwardj   sR    !MM$4-8>>@GGHZHZ[\H]_acdehhijiqiqr ,QaZ 8 > > @'1!((--'E'E!((--[`J`ahhmmfk^^UC&,,.1F1L1L1NNYYZ[]^_E))UN3C'')d444C'')d444C	 D vvAGGv$cff177f&;;; DCs   $BF  
F.)rv   rW   rs   rx   rt   ru   rj   r&   )rH   rI   rJ   rK   r+   Tensor__annotations__r   r(   no_gradr   rA   rM   rN   rO   s   @r0   re   re   V   s@    ll/| / /" ]]_<  <r2   re   c                     U SSU R                   S   S-  24   nU SU R                   S   S-  S24   n[        R                  " U* U4SS9$ )z*Rotates half the hidden dims of the input..Nr5   r4   r   )rE   r+   r   )r:   x1x2s      r0   rotate_halfr   z   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r2   c                     UR                  U5      nUR                  U5      nX-  [        U 5      U-  -   nX-  [        U5      U-  -   nXg4$ )a  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.
    position_ids (`torch.Tensor`, *optional*):
        Deprecated and unused.
    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.
)	unsqueezer   )qkr   r   r   unsqueeze_dimq_embedk_embeds           r0   apply_rotary_pos_embr      sS    ( --
&C
--
&Cw;q>C/0Gw;q>C/0Gr2   hidden_statesn_repreturnc                     U R                   u  p#pEUS:X  a  U $ U SS2SS2SSS2SS24   R                  X#XU5      n U R                  X#U-  XE5      $ )z
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   N)rE   r   reshape)r   r   batchnum_key_value_headsslenhead_dims         r0   	repeat_kvr      s_    
 2?1D1D.Ez!!Qa"23::5W\dlmM  e(CTTTr2   modulequerykeyvalueattention_maskdropoutscalingsoftcapc                    Uc  U R                   S-  n[        X R                  5      n	[        X0R                  5      n
[        R                  " XR                  SS5      5      U-  nUb  X-  n[        R                  " U5      nX-  nUb"  US S 2S S 2S S 2S U	R                  S   24   nX-   n[        R                  R                  US[        R                  S9R                  UR                  5      n[        R                  R                  XU R                  S9n[        R                  " X5      nUR                  SS5      R!                  5       nX4$ )	N      r4   r   r5   )r#   r   )ptrainingr   )r   r   num_key_value_groupsr+   matmulr   tanhrE   r)   
functionalsoftmaxfloat32r   r   r   r   
contiguous)r   r   r   r   r   r   r   r   kwargs
key_statesvalue_statesattn_weightscausal_maskattn_outputs                 r0   eager_attention_forwardr      s/    //4'3 ; ;<JU$?$?@L<<';';Aq'ABWLL#-zz,/#-!$Q1.D
0@0@0D.D%DE#1 ==((2U]](SVVW\WbWbcL==((6??([L,,|:K''1-88:K$$r2   c                   \  ^  \ rS rSrSrS\S\4U 4S jjr\" SSSS	9  SS
\	R                  S\\	R                  \	R                  4   S\\	R                     S\\   S\\	R                     S\\   S\\	R                  \\	R                     \\\	R                        4   4S jj5       rSrU =r$ )Gemma2Attention   z=Multi-headed attention from 'Attention Is All You Need' paperrW   	layer_idxc                   > [         TU ]  5         Xl        X l        [	        USUR
                  UR                  -  5      U l        UR                  UR                  -  U l	        UR                  S-  U l        U R                  R                  U l        SU l        [        R                  " UR
                  UR                  U R                  -  UR                   S9U l        [        R                  " UR
                  UR                  U R                  -  UR                   S9U l        [        R                  " UR
                  UR                  U R                  -  UR                   S9U l        [        R                  " UR                  U R                  -  UR
                  UR                   S9U l        U R                  R*                  U l        UR,                  U   S:X  a  UR.                  U l        g S U l        g )Nr   r   TrU   sliding_attention)r'   r(   rW   r   getattrrX   num_attention_headsr   r   r   query_pre_attn_scalarr   attention_dropout	is_causalr)   rZ   attention_biasq_projk_projv_projo_projattn_logit_softcappinglayer_typessliding_windowr.   rW   r   r/   s      r0   r(   Gemma2Attention.__init__   s   "
F4F4F&JdJd4de$*$>$>&B\B\$\!33T9!%!>!>ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
 '+kk&H&H#7=7I7I)7TXk7kf33qur2   past_key_valuepast_key_values4.58new_nameversionr   position_embeddingsr   cache_positionr   r   c                 `   UR                   S S n/ UQSPU R                  P7nU R                  U5      R                  U5      R	                  SS5      n	U R                  U5      R                  U5      R	                  SS5      n
U R                  U5      R                  U5      R	                  SS5      nUu  p[        XX5      u  pUb$  XUS.nUR                  XU R                  U5      u  p[        nU R                  R                  S:w  a  [        U R                  R                     nU" U U	U
UU4U R                  (       a  U R                  OSU R                   U R"                  U R$                  S.UD6u  nnUR&                  " / UQSP76 R)                  5       nU R+                  U5      nUU4$ )Nr5   r   r4   )r   r   r   eager        )r   r   r   r   )rE   r   r   viewr   r   r   r   updater   r   rW   _attn_implementationr   r   r   r   r   r   r   r   r   )r.   r   r   r   r   r   r   input_shapehidden_shapequery_statesr   r   r   r   cache_kwargsattention_interfacer   r   s                     r0   rA   Gemma2Attention.forward   s    $))#2.88b8$--8{{=166|DNNqRST[[/44\BLLQPQR
{{=166|DNNqRST&#7RU#[ &#&nUL'6'='=jX\XfXfht'u$J(?;;++w6"9$++:Z:Z"[$7%
 /3mmD**LL..//%
 %
!\ "));;;;FFHkk+.L((r2   )r   r   rW   r   r   r   r   r   r   r   r   r   r   )NN)rH   rI   rJ   rK   __doc__r   rL   r(   r   r+   r   rD   r   r   
LongTensorr   r   rA   rM   rN   rO   s   @r0   r   r      s    Gv| v v2 %0A6R ,059+)||+) #5<<#=>+) !.	+)
 "%+) !!1!12+) -.+) 
u||Xell3XeELL>Q5RR	S+) S+)r2   r   c                     ^  \ rS rSrS\S\4U 4S jjr\" SSSS9      SS	\R                  S
\
\R                  \R                  4   S\\R                     S\\R                     S\\   S\\   S\\   S\\R                     S\
\R                  \\
\R                  \R                  4      4   4S jj5       rSrU =r$ )Gemma2DecoderLayeri  rW   r   c                   > [         TU ]  5         UR                  U l        Xl        UR                  U   U l        [        XS9U l        [        U5      U l	        [        UR                  UR                  S9U l        [        UR                  UR                  S9U l        [        UR                  UR                  S9U l        [        UR                  UR                  S9U l        g )N)rW   r   r$   )r'   r(   rX   rW   r   attention_typer   	self_attnrQ   mlpr!   rms_norm_epsinput_layernormpost_attention_layernormpre_feedforward_layernormpost_feedforward_layernormr   s      r0   r(   Gemma2DecoderLayer.__init__  s    !--$00;(LV$,V-?-?VEXEXY(5f6H6HfNaNa(b%)6v7I7IvObOb)c&*78J8JPVPcPc*d'r2   r   r   r   r   r   r   r   r   output_attentions	use_cacher   r   c	                     Un
U R                  U5      nU R                  " SUUUUUUUUS.U	D6u  pU R                  U5      nX-   nUn
U R                  U5      nU R	                  U5      nU R                  U5      nX-   nU4nU(       a  X4-  nU$ )N)r   r   r   r   r   r   r   r    )r   r   r   r   r   r   )r.   r   r   r   r   r   r   r   r   r   residualself_attn_weightsoutputss                r0   rA   Gemma2DecoderLayer.forward$  s     !,,]; ,0>> 
,
' 3)%+/)
,
 
,
( 55mD 0 66}E/77F 0 "++Gr2   )	r   rW   rX   r   r   r   r   r   r   )NNNFFN)rH   rI   rJ   rK   r   rL   r(   r   r+   r   rD   r   r   r   boolFloatTensorrA   rM   rN   rO   s   @r0   r   r     s   e| e e %0A6R
 2637+/,1$)59*||* #5<<#=>* !.	*
 u//0* "%* $D>* D>* !!1!12* 
u  (51B1BEDUDU1U+V"WW	X* S*r2   r   c                   f   ^  \ rS rSr% \\S'   SrSrS/rS/r	Sr
SrSrSrSr\\S.rU 4S jrS	rU =r$ )
Gemma2PreTrainedModeliR  rW   modelTr   r   )r   
attentionsc                    > [         TU ]  U5        SUR                  R                  ;   a%  UR                  R
                  R                  5         g g )NRMSNorm)r'   _init_weightsr/   rH   r-   datazero_)r.   r   r/   s     r0   r  #Gemma2PreTrainedModel._init_weightsd  sA    f% ((111MM$$& 2r2   r   )rH   rI   rJ   rK   r   r   base_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_supports_sdpa_supports_flex_attn_can_compile_fullgraph_supports_attention_backendr   r   _can_record_outputsr  rM   rN   rO   s   @r0   r  r  R  s\    &*#-.#4"5N!"&+%
' 'r2   r  c                   :  ^  \ rS rSrS\4U 4S jjr\" 5       \         SS\\	R                     S\\	R                     S\\	R                     S\\   S\\	R                     S	\\   S
\\   S\\   S\\	R                     S\\   S\4S jj5       5       rSrU =r$ )Gemma2Modelil  rW   c           	        > [         TU ]  U5        UR                  U l        UR                  U l        [
        R                  " UR                  UR                  U R                  5      U l        [
        R                  " [        UR                  5       Vs/ s H  n[        X5      PM     sn5      U l        [        UR                  UR                  S9U l        [#        US9U l        SU l        U R)                  5         g s  snf )Nr   rW   F)r'   r(   pad_token_idpadding_idx
vocab_sizer)   	EmbeddingrX   embed_tokens
ModuleListrangenum_hidden_layersr   layersr!   r   normre   
rotary_embgradient_checkpointing	post_initr   s      r0   r(   Gemma2Model.__init__n  s     !.. ++LL):):F<N<NPTP`P`ammDI&JbJbDcdDcy2Dcd
 "&"4"4&:M:MN	/v>&+# 	 es   C?	input_idsr   r   r   inputs_embedsr   r   output_hidden_statesr   r   r   c
                    Ub  UOU R                   R                  nUb  UOU R                   R                  nUb  UOU R                   R                  nUS L US L-  (       a  [	        S5      eU R
                  (       a/  U R                  (       a  U(       a  [        R                  S5        SnUc  U R                  U5      nU(       a'  Uc$  U R                  (       d  [        U R                   S9nU	cD  Ub  UR                  5       OSn[        R                  " XUR                  S   -   UR                  S9n	Uc  U	R!                  S5      n[#        U=n[$        5      (       d*  U R                   UUU	UUS.n['        S0 UD6[)        S0 UD6S	.nUnU R+                  X5      n[        R,                  " U R                   R.                  S
-  UR0                  S9nUU-  nU(       a  SOS nU(       a  SOS nU R2                  S U R                   R4                    HE  nU(       a  UU4-  nU" U4UUUR6                     UUUUU	S.U
D6nUS   nU(       d  M<  UUS   4-  nMG     U R9                  U5      nU(       a  UU4-  n[;        UUUUS9$ )Nz:You must specify exactly one of input_ids or inputs_embedszX`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`.Fr  r   r   )ry   )rW   input_embedsr   r   r   r   )full_attentionr   g      ?r   r   )r   r   r   r   r   r   r   )last_hidden_stater   r   r
  )rW   r   r/  r   
ValueErrorr*  r   loggerwarning_oncer#  r	   get_seq_lengthr+   arangerE   ry   r   ro   rp   r   r   r)  tensorrX   r   r'  r&  r   r(  r   )r.   r-  r   r   r   r.  r   r   r/  r   r   past_seen_tokenscausal_mask_mappingmask_kwargsr   r   
normalizerall_hidden_statesall_self_attnsdecoder_layerlayer_outputss                        r0   rA   Gemma2Model.forward~  s    2C1N-TXT_T_TqTq$8$D $++JjJj 	 "+!6IDKK<Q<Q	-t";<YZZ&&4==Yj I  --i8M0*$++>O!CRC^==?de"\\ ]5H5H5K"KTaThThN )33A6L ?-FF ++ -"0"0#2 ,K #5"C{"C%F%U%U# & #oomJ
 \\$++"9"93">mFYFYZ
%
2 #7BD0d![[)H4;;+H+HIM#!m%55!)
$72=3O3OP) /"3#-
 
M *!,M  =#3"55' J* 		-0-!11&+++%	
 	
r2   )r#  r*  r'  r(  r   r)  r!  )	NNNNNNNNN)rH   rI   rJ   rK   r   r(   r   r   r   r+   r   r   r   r  r  r   r   r   rA   rM   rN   rO   s   @r0   r  r  l  s   |    151537+/59$(,0/359k
E,,-k
 !.k
 u//0	k

 "%k
   1 12k
 D>k
 $D>k
 'tnk
 !!1!12k
 +,k
 
!k
  k
r2   r  c                     ^  \ rS rSrS/rSS0rSS/S/40rU 4S jr\\	           SS\
\R                     S	\
\R                     S
\
\R                     S\
\   S\
\R                     S\
\R                     S\
\   S\
\   S\
\   S\
\R                     S\\\R                  4   S\4S jj5       5       rSrU =r$ )Gemma2ForCausalLMi  zlm_head.weightlm_headcolwise_repr   logitsc                    > [         TU ]  U5        [        U5      U l        UR                  U l        [
        R                  " UR                  UR                  SS9U l        U R                  5         g rT   )
r'   r(   r  r	  r!  r)   rZ   rX   rE  r+  r`   s     r0   r(   Gemma2ForCausalLM.__init__  sU      (
 ++yy!3!3V5F5FUS 	r2   r-  r   r   r   r.  labelsr   r   r/  r   logits_to_keepr   c                    Ub  UOU R                   R                  nU	b  U	OU R                   R                  n	U R                  " SUUUUUUUU	U
S.	UD6nUR                  n[        U[        5      (       a  [        U* S5      OUnU R                  USS2USS24   5      nU R                   R                  bH  UU R                   R                  -  n[        R                  " U5      nUU R                   R                  -  nSnUb  U R                  " UX`R                  40 UD6n[        UUUR                  UR                   UR"                  S9$ )a"  
Example:

```python
>>> from transformers import AutoTokenizer, Gemma2ForCausalLM

>>> model = Gemma2ForCausalLM.from_pretrained("google/gemma-2-9b")
>>> tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-9b")

>>> prompt = "What is your favorite condiment?"
>>> 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]
"What is your favorite condiment?"
```N)	r-  r   r   r   r.  r   r   r/  r   )lossrG  r   r   r
  r   )rW   r   r/  r	  r3  ro   rL   slicerE  final_logit_softcappingr+   r   loss_functionr!  r   r   r   r
  )r.   r-  r   r   r   r.  rJ  r   r   r/  r   rK  r   r  r   slice_indicesrG  rM  s                     r0   rA   Gemma2ForCausalLM.forward  sT   F 2C1N-TXT_T_TqTq$8$D $++JjJj 	 ,0:: ,
)%+'/!5),
 ,
  118B>SV8W8W~ot4]kmA}a,?@A;;..:dkkAAAFZZ'FdkkAAAF%%ffooPPD%#33!//))
 	
r2   )rE  r	  r!  )NNNNNNNNNNr   )rH   rI   rJ   rK   _tied_weights_keys_tp_plan_pp_planr(   r   r   r   r+   r   r   r   r  r  r   rL   r   rA   rM   rN   rO   s   @r0   rD  rD    sP   *+=)H_-z:;H  151537+/59-1$(,0/35934F
E,,-F
 !.F
 u//0	F

 "%F
   1 12F
 ))*F
 D>F
 $D>F
 'tnF
 !!1!12F
 c5<</0F
 
 F
  F
r2   rD  c                       \ rS rSrSrg)Gemma2ForSequenceClassificationiH  r   NrH   rI   rJ   rK   rM   r   r2   r0   rW  rW  H      r2   rW  c                       \ rS rSrSrg)Gemma2ForTokenClassificationiL  r   NrX  r   r2   r0   r[  r[  L  rY  r2   r[  )rD  r  r  rW  r[  )Nr   )r   NN)Dtypingr   r   r   r+   torch.nnr)   activationsr   cache_utilsr   r	   
generationr
   masking_utilsr   r   modeling_flash_attention_utilsr   modeling_layersr   r   r   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   r   utils.deprecationr   utils.genericr   configuration_gemma2r   
get_loggerrH   r5  Moduler!   rQ   re   r   r   r   rL   r   r>   rD   r   r   r   r  r  rD  rW  r[  __all__r   r2   r0   <module>ro     s  , - ,   ! . ) R B 
 P K F & R R 0 / . 
		H	%=BII =(		  !<BII !<H(6	UU\\ 	U# 	U%,, 	U$ ## %II %<< % 
 % <<	 %
 U\\* %  % e_ % e_ % 5<<%& %FH)bii H)V93 9x 'O ' '2 ~
' ~
 ~
B V
- V
 V
r	&FH] 		#@BW 	r2   