
    <hCc                        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*  \&RV                  " \,5      r- " S S\R\                  5      r/ " S S\R\                  5      r0S r1S6S jr2S\Rf                  S\4S\Rf                  4S jr5   S7S\R\                  S\Rf                  S\Rf                  S\Rf                  S \\Rf                     S!\6S"\\6   S#\\6   S\7\Rf                  \Rf                  4   4S$ jjr8 " S% S&\R\                  5      r9 " S' S(\5      r: " S) S*\R\                  5      r;\$ " S+ S,\5      5       r<\$ " S- S.\<5      5       r=\$ " S/ S0\<\5      5       r> " S1 S2\\<5      r? " S3 S4\\<5      r@/ S5QrAg)8    )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)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$ )
Gemma2RMSNorm1   dimepsc                    > [         TU ]  5         X l        [        R                  " [
        R                  " U5      5      U l        g N)super__init__r#   nn	Parametertorchzerosweight)selfr"   r#   	__class__s      b/var/www/html/shao/venv/lib/python3.13/site-packages/transformers/models/gemma2/modeling_gemma2.pyr'   Gemma2RMSNorm.__init__2   s,    ll5;;s#34    c                     U[         R                  " UR                  S5      R                  SSS9U R                  -   5      -  $ )N   T)keepdim)r*   rsqrtpowmeanr#   )r-   xs     r/   _normGemma2RMSNorm._norm7   s4    5;;quuQx}}R}>IJJJr1   c                     U R                  UR                  5       5      nUSU R                  R                  5       -   -  nUR                  U5      $ )Ng      ?)r:   floatr,   type_as)r-   r9   outputs      r/   forwardGemma2RMSNorm.forward:   sC    AGGI& 3!2!2!445~~a  r1   c                 ^    [        U R                  R                  5       SU R                   3$ )Nz, eps=)tupler,   shaper#   r-   s    r/   
extra_reprGemma2RMSNorm.extra_reprA   s'    ))*+6$((<<r1   )r#   r,   )gư>)__name__
__module____qualname____firstlineno__intr=   r'   r:   r@   rF   __static_attributes____classcell__r.   s   @r/   r    r    1   s0    5C 5e 5 5
K!= =r1   r    c                   .   ^  \ rS rSrU 4S jrS rSrU =r$ )	Gemma2MLPE   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     r/   r'   Gemma2MLP.__init__F   s    !--!'!9!94#3#3T5K5KRWXyy!1!143I3IPUV4#9#94;K;KRWXV556r1   c                     U R                  U R                  U R                  U5      5      U R                  U5      -  5      nU$ r%   )r]   r_   r[   r\   )r-   r9   r]   s      r/   r@   Gemma2MLP.forwardP   s6    NN4;;t~~a/@#ADLLQRO#ST	r1   )r_   rW   r]   r[   rX   rY   r\   )rH   rI   rJ   rK   r'   r@   rM   rN   rO   s   @r/   rQ   rQ   E   s    7 r1   rQ   c                     U SSU R                   S   S-  24   nU SU R                   S   S-  S24   n[        R                  " U* U4SS9$ )z*Rotates half the hidden dims of the input..Nr4   r3   r"   )rD   r*   cat)r9   x1x2s      r/   rotate_halfri   U   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r1   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.
)	unsqueezeri   )qkcossinposition_idsunsqueeze_dimq_embedk_embeds           r/   apply_rotary_pos_embrt   \   sS    ( --
&C
--
&Cw;q>C/0Gw;q>C/0Gr1   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)rD   expandreshape)ru   rv   batchnum_key_value_headsslenhead_dims         r/   	repeat_kvr   w   s_    
 2?1D1D.Ez!!Qa"23::5W\dlmM  e(CTTTr1   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$ )	N      r3   r   r4   )r"   dtype)ptrainingr   )r~   r   num_key_value_groupsr*   matmul	transposetanhrD   r(   
functionalsoftmaxfloat32tor   r   r   
contiguous)r   r   r   r   r   r   r   r   kwargs
key_statesvalue_statesattn_weightscausal_maskattn_outputs                 r/   eager_attention_forwardr      s/    //4'3 ; ;<JU$?$?@L<<';';Aq'ABWLL#-zz,/#-!$Q1.D
0@0@0D.D%DE#1 ==((2U]](SVVW\WbWbcL==((6??([L,,|:K''1-88:K$$r1   c                   F  ^  \ rS rSrSrS\S\4U 4S jjr  SS\R                  S\
\R                  \R                  4   S\\R                     S	\\   S
\\R                     S\\   S\
\R                  \\R                     \\
\R                        4   4S jj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      r/   r'   Gemma2Attention.__init__   s   "
F4F4F&JdJd4de$*$>$>&B\B\$\!33T9!%!>!>ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
 '+kk&H&H#7=7I7I)7TXk7kf33qur1   ru   position_embeddingsr   past_key_valuecache_positionr   rw   c                 `   UR                   S S n/ UQSPU R                  P7nU R                  U5      R                  U5      R	                  SS5      n	U R                  U5      R                  U5      R	                  SS5      n
U R                  U5      R                  U5      R	                  SS5      nUu  p[        XX5      u  pUb$  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$                  S.UD6u  nnUR&                  " / UQSP76 R)                  5       nU R+                  U5      nUU4$ )Nr4   r   r3   )ro   rn   r   eager        )r   r   r   r   )rD   r~   r   viewr   r   r   rt   updater   r   rW   _attn_implementationr   r   r   r   r   r   rz   r   r   )r-   ru   r   r   r   r   r   input_shapehidden_shapequery_statesr   r   rn   ro   cache_kwargsattention_interfacer   r   s                     r/   r@   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'5'<'<ZW[WeWegs't$J(?;;++w6"9$++:Z:Z"[$7%
 /3mmD**LL..//%
 %
!\ "));;;;FFHkk+.L((r1   )r   r   rW   r~   r   r   r   r   r   r   r   r   r   )NN)rH   rI   rJ   rK   __doc__r   rL   r'   r*   TensorrC   r   r   
LongTensorr   r   r@   rM   rN   rO   s   @r/   r   r      s    Gv| v v< +/59+)||+) #5<<#=>+) !.	+)
 !+) !!1!12+) -.+) 
u||Xell3XeELL>Q5RR	S+) +)r1   r   c                   n  ^  \ rS rSrS\S\4U 4S jjr      SS\R                  S\	\R                  \R                  4   S\
\R                     S\
\R                     S	\
\   S
\
\   S\
\   S\
\R                     S\	\R                  \
\	\R                  \R                  4      4   4S jjrSrU =r$ )Gemma2DecoderLayer   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      r/   r'   Gemma2DecoderLayer.__init__   s    !--$00;(LV$,V-?-?VEXEXY(5f6H6HfNaNa(b%)6v7I7IvObOb)c&*78J8JPVPcPc*d'r1   ru   r   r   rp   r   output_attentions	use_cacher   rw   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$ )N)ru   r   r   rp   r   r   r   r    )r   r   r   r   r   r   )r-   ru   r   r   rp   r   r   r   r   r   residualself_attn_weightsoutputss                r/   r@   Gemma2DecoderLayer.forward   s     !,,]; ,0>> 
,
' 3)%)/)
,
 
,
( 55mD 0 66}E/77F 0 "++Gr1   )	r   rW   rX   r   r   r   r   r   r   )NNNFFN)rH   rI   rJ   rK   r   rL   r'   r*   r   rC   r   r   r   boolFloatTensorr@   rM   rN   rO   s   @r/   r   r      s    e| e e" 2637*.,1$)59*||* #5<<#=>* !.	*
 u//0* !* $D>* D>* !!1!12* 
u  (51B1BEDUDU1U+V"WW	X* *r1   r   c                   l   ^  \ rS rSrSS\4U 4S jjjr\R                  " 5       \S 5       5       r	Sr
U =r$ )Gemma2RotaryEmbeddingi+  rW   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defaultinv_freqF)
persistent)r&   r'   hasattr
isinstancer   dictgetr   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrW   r   rope_init_fnattention_scalingregister_bufferr   original_inv_freq)r-   rW   devicer   r.   s       r/   r'   Gemma2RotaryEmbedding.__init__,  s    6>**z&:M:Mt/T/T#0044[&BUBUBYBYZ`BabDN&DN"("@"@$*$B$B!/?+/+<+<T[[&+Q((ZeD!%r1   c                 b   U R                   S S S 2S 4   R                  5       R                  UR                  S   SS5      R	                  UR
                  5      nUS S 2S S S 24   R                  5       n[        UR
                  R                  [        5      (       a0  UR
                  R                  S:w  a  UR
                  R                  OSn[        R                  " USS9   UR                  5       UR                  5       -  R                  SS5      n[        R                  " Xf4SS	9nUR                  5       U R                  -  nUR                  5       U R                  -  n	S S S 5        WR	                  UR                   S
9W	R	                  UR                   S
94$ ! , (       d  f       N@= f)Nr   r4   r   mpscpuF)device_typeenabledr3   re   r   )r   r=   ry   rD   r   r   r   r   strr*   autocastr   rf   rn   r   ro   r   )
r-   r9   rp   inv_freq_expandedposition_ids_expandedr   freqsembrn   ro   s
             r/   r@   Gemma2RotaryEmbedding.forward=  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   $BF  
F.)r   rW   r   r   r   r   r   r%   )rH   rI   rJ   rK   r   r'   r*   no_gradr   r@   rM   rN   rO   s   @r/   r   r   +  s6    /| / /" ]]_<  <r1   r   c                   R    \ rS rSr% \\S'   SrSrS/rS/r	Sr
SrSrSrSr\\S.rSrg	)
Gemma2PreTrainedModeliM  rW   modelTr   past_key_values)ru   
attentionsr   N)rH   rI   rJ   rK   r   __annotations__base_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_supports_sdpa_supports_flex_attn_can_compile_fullgraph_supports_attention_backendr   r   _can_record_outputsrM   r   r1   r/   r  r  M  sQ    &*#-.#4"5N!"&+%r1   r  c                   0  ^  \ rS rSrS\4U 4S jjr\\         SS\\	R                     S\\	R                     S\\	R                     S\\   S\\	R                     S	\\   S
\\   S\\   S\\	R                     S\\   S\4S jj5       5       rSrU =r$ )Gemma2Modeli`  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   normr   
rotary_embgradient_checkpointing	post_initr   s      r/   r'   Gemma2Model.__init__b  s     !.. ++LL):):F<N<NPTP`P`ammDI&JbJbDcdDcy2Dcd
 "&"4"4&:M:MN	/v>&+# 	 es   C>	input_idsr   rp   r  inputs_embedsr   r   output_hidden_statesr   r   rw   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
  [        5       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   )rW   input_embedsr   r   r  rp   )full_attentionr   g      ?r   r   )r   r   rp   r   r   r   r   )last_hidden_stater  ru   r  )rW   r   r$  r   
ValueErrorr  r   loggerwarning_oncer  r	   get_seq_lengthr*   arangerD   r   rk   r   r   r   r   r  tensorrX   r   r  r  r   r  r   )r-   r"  r   rp   r  r#  r   r   r$  r   r   past_seen_tokenscausal_mask_mappingmask_kwargsru   r   
normalizerall_hidden_statesall_self_attnsdecoder_layerlayer_outputss                        r/   r@   Gemma2Model.forwardr  s    2C1N-TXT_T_TqTq$8$D $++JjJj 	 "+!6IDKK<Q<Q	-t";<YZZ&&4==Yj I  --i8M0*nO!CRC^==?de"\\ ]5H5H5K"KTaThThN )33A6L ?-FF ++ -"0"0#2 ,K #5"C{"C%F%U%U# & #oomJ
 \\$++"9"93">mFYFYZ
%
2 #7BD0d![[)H4;;+H+HIM#!m%55!)
$72=3O3OP)."3#-
 
M *!,M  =#3"55' J* 		-0-!11&+++%	
 	
r1   )r  r  r  r  r  r  r  )	NNNNNNNNN)rH   rI   rJ   rK   r   r'   r   r   r   r*   r   r   r   r   r   r   r   r   r@   rM   rN   rO   s   @r/   r  r  `  s   |    151537+/59$(,0/359k
E,,-k
 !.k
 u//0	k

 "%k
   1 12k
 D>k
 $D>k
 'tnk
 !!1!12k
 +,k
 
!k
  k
r1   r  c                     ^  \ rS rSrS/rSS0rSS/S/40rU 4S jrS rS	 r	\
\           SS
\\R                     S\\R                     S\\R                     S\\   S\\R"                     S\\R                     S\\   S\\   S\\   S\\R                     S\\\R                  4   S\4S jj5       5       rSrU =r$ )Gemma2ForCausalLMi  zlm_head.weightlm_headcolwise_repru   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   r:  r   r`   s     r/   r'   Gemma2ForCausalLM.__init__  sU      (
 ++yy!3!3V5F5FUS 	r1   c                     Xl         g r%   r  )r-   decoders     r/   set_decoderGemma2ForCausalLM.set_decoder  s    
r1   c                     U R                   $ r%   r@  rE   s    r/   get_decoderGemma2ForCausalLM.get_decoder  s    zzr1   r"  r   rp   r  r#  labelsr   r   r$  r   logits_to_keeprw   c                 F   U R                   (       aG  U R                  R                  S:w  a-  [        R	                  SU R                  R                   S35        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?"
```r   zhIt is strongly recommended to train Gemma2 models with the `eager` attention implementation instead of `zp`. Use `eager` with `AutoModelForCausalLM.from_pretrained('<path-to-checkpoint>', attn_implementation='eager')`.N)	r"  r   rp   r  r#  r   r   r$  r   )lossr<  r  ru   r  r   )r   rW   r   r*  r+  r   r$  r  r(  r   rL   slicer:  final_logit_softcappingr*   r   loss_functionr  r   r  ru   r  )r-   r"  r   rp   r  r#  rG  r   r   r$  r   rH  r   r   ru   slice_indicesr<  rJ  s                     r/   r@   Gemma2ForCausalLM.forward  s   F ==T[[==H#{{??@  Aqr 2C1N-TXT_T_TqTq$8$D $++JjJj 	 ,0:: ,
)%+'/!5),
 ,
  118B>SV8W8W~ot4]kmA}a,?@A;;..:dkkAAAFZZ'FdkkAAAF%%ffooPPD%#33!//))
 	
r1   )r:  r  r  )NNNNNNNNNNr   )rH   rI   rJ   rK   _tied_weights_keys_tp_plan_pp_planr'   rB  rE  r   r   r   r*   r   r   r   r   r   r   rL   r   r@   rM   rN   rO   s   @r/   r9  r9    sZ   *+=)H_-z:;H  151537+/59-1$(,0/35934K
E,,-K
 !.K
 u//0	K

 "%K
   1 12K
 ))*K
 D>K
 $D>K
 'tnK
 !!1!12K
 c5<</0K
 
 K
  K
r1   r9  c                       \ rS rSrSrg)Gemma2ForSequenceClassificationiG  r   NrH   rI   rJ   rK   rM   r   r1   r/   rT  rT  G      r1   rT  c                       \ rS rSrSrg)Gemma2ForTokenClassificationiK  r   NrU  r   r1   r/   rX  rX  K  rV  r1   rX  )r9  r  r  rT  rX  )Nr   )r   NN)Btypingr   r   r   r*   torch.nnr(   activationsr   cache_utilsr   r	   
generationr
   masking_utilsr   r   modeling_flash_attention_utilsr   modeling_layersr   r   r   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   r   utils.genericr   configuration_gemma2r   
get_loggerrH   r*  Moduler    rQ   ri   rt   r   rL   r   r=   rC   r   r   r   r   r  r  r9  rT  rX  __all__r   r1   r/   <module>rk     s  , - ,   ! . ) R B 
 P K F & R R / . 
		H	%=BII =(		  (6	UU\\ 	U# 	U%,, 	U$ ## %II %<< % 
 % <<	 %
 U\\* %  % e_ % e_ % 5<<%& %FG)bii G)T83 8v<BII <D O  $ ~
' ~
 ~
B a
- a
 a
H	&FH] 		#@BW 	r1   