
    Z jH                     0   S SK Jr  S SKrS SKJ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  SSKJrJr  SSKJrJrJr  SSKJr  SSKJr  SSK J!r!J"r"J#r#  SSK$J%r%  SSK&J'r'J(r(J)r)J*r*J+r+J,r,J-r-J.r.J/r/J0r0J1r1  \#Rd                  " \35      r4\"" SS9\ " S S\5      5       5       r5 " S S\.5      r6 " S S\+5      r7 " S S\/5      r8   S6S\Rr                  S\Rt                  S\Rt                  S \Rt                  S!\Rt                  S-  S"\;\<-  S#\;S-  S$\;S-  S%\=\Rt                  \Rt                  4   4S& jjr> " S' S(\'5      r? " S) S*\5      r@ " S+ S,\-5      rA " S- S.\,5      rB " S/ S0\(5      rC " S1 S2\)5      rD " S3 S4\*5      rE/ S5QrFg)7    )CallableN)strict   )ACT2FN)CacheDynamicCache)PreTrainedConfig)create_causal_mask!create_sliding_window_causal_mask)FlashAttentionKwargs)GradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSRopeParametersdynamic_rope_update)ALL_ATTENTION_FUNCTIONS)Unpack)TransformersKwargsauto_docstringlogging)maybe_autocast   )GemmaAttentionGemmaForCausalLMGemmaForSequenceClassificationGemmaForTokenClassificationGemmaMLP
GemmaModelGemmaPreTrainedModelGemmaRMSNormGemmaRotaryEmbeddingapply_rotary_pos_emb	repeat_kvzgoogle/gemma2-7b)
checkpointc                   0  ^  \ rS rSr% SrSrS/rSSSSSSSS.rS/S	/4S
S/S
/4S
/S
/4S.rSr	\
\S'   Sr\
\S'   Sr\
\S'   Sr\
\S'   Sr\
\S'   Sr\
\S'   Sr\
\S'   Sr\\S'   Sr\
\S'   Sr\\S '   S!r\\S"'   S#r\\S$'   S%r\
S&-  \S''   S(r\
\\
   -  S&-  \S)'   S*r\
S&-  \S+'   S#r\\S,'   S&r\ \!-  S&-  \S-'   S.r"\\S/'   S0r#\
\-  S&-  \S1'   Sr$\
\S2'   S3r%\
S&-  \S4'   S&r&\\   S&-  \S5'   S6r'\S&-  \S7'   S8r(\S&-  \S9'   S&r)\S&-  \S:'   U 4S; jr*S< r+S=r,U =r-$ )>Gemma2Config7   aX  
query_pre_attn_scalar (`float`, *optional*, defaults to 256):
    scaling factor used on the attention scores
final_logit_softcapping (`float`, *optional*, defaults to 30.0):
    scaling factor when applying tanh softcapping on the logits.
attn_logit_softcapping (`float`, *optional*, defaults to 50.0):
    scaling factor when applying tanh softcapping on the attention scores.
use_bidirectional_attention (`bool`, *optional*):
    If True, the model will attend to all text tokens instead of using a causal mask.

```python
>>> from transformers import Gemma2Model, Gemma2Config
>>> # Initializing a Gemma2 gemma2-7b style configuration
>>> configuration = Gemma2Config()
>>> # Initializing a model from the gemma2-7b style configuration
>>> model = Gemma2Model(configuration)
>>> # Accessing the model configuration
>>> configuration = model.config
```gemma2past_key_valuescolwiserowwise)zlayers.*.self_attn.q_projzlayers.*.self_attn.k_projzlayers.*.self_attn.v_projzlayers.*.self_attn.o_projzlayers.*.mlp.gate_projzlayers.*.mlp.up_projzlayers.*.mlp.down_proj	input_idsinputs_embedshidden_statesattention_mask)embed_tokenslayersnormi  
vocab_sizei 	  hidden_sizei $  intermediate_size   num_hidden_layers   num_attention_heads   num_key_value_heads   head_dimgelu_pytorch_tanhhidden_activationi    max_position_embeddingsg{Gz?initializer_rangegư>rms_norm_epsT	use_cacher   Npad_token_id   eos_token_idr   bos_token_idtie_word_embeddingsrope_parametersFattention_bias        attention_dropoutquery_pre_attn_scalari   sliding_windowlayer_typesg      >@final_logit_softcappingg      I@attn_logit_softcappinguse_bidirectional_attentionc                    > U R                   cC  [        U R                  5       Vs/ s H  n[        US-   S-  5      (       a  SOSPM     snU l         [        TU ]  " S0 UD6  g s  snf )NrF   r   sliding_attentionfull_attention )rP   ranger8   boolsuper__post_init__)selfkwargsi	__class__s      z/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/gemma2/modular_gemma2.pyr[   Gemma2Config.__post_init__y   si    #X]^b^t^tXu XuSTtQUaK'8'8#>NNXu D 	''	 s   $A#c                     U R                   U R                  -  S:w  a&  [        SU R                    SU R                   S35      eg)zOPart of `@strict`-powered validation. Validates the architecture of the config.r   zThe hidden size (z6) is not a multiple of the number of attention heads (z).N)r5   r:   
ValueError)r\   s    r`   validate_architecture"Gemma2Config.validate_architecture   sS    d666!;#D$4$4#5 622327  <    )rP   ).__name__
__module____qualname____firstlineno____doc__
model_typekeys_to_ignore_at_inferencebase_model_tp_planbase_model_pp_planr4   int__annotations__r5   r6   r8   r:   r<   r>   r@   strrA   rB   floatrC   rD   rY   rE   rG   listrH   rI   rJ   r   dictrK   rM   rN   rO   rP   rQ   rR   rS   r[   rd   __static_attributes____classcell__r_   s   @r`   r'   r'   7   s   ( J#4"5%.%.%.%."+ )"+ &(9:#%568IJ!"_$56 JK!s!s    Hc0s0#'S'#u#L%It L#* +,L#S	/D(, L#*  $$48O^d*T18 ND ,/sU{T)/!$3$!%NC$J%$(KcT!(,0UT\0+/EDL//33( rf   r'   c                       \ rS rSrSrg)Gemma2RMSNorm   rW   Nrg   rh   ri   rj   rv   rW   rf   r`   rz   rz          rf   rz   c                   (   ^  \ rS rSrU 4S jrSrU =r$ )	Gemma2MLP   c                 T   > [         TU ]  U5        [        UR                     U l        g N)rZ   __init__r   r@   act_fnr\   configr_   s     r`   r   Gemma2MLP.__init__   s"     V556rf   )r   )rg   rh   ri   rj   r   rv   rw   rx   s   @r`   r   r      s    7 7rf   r   c                   ^    \ rS rSrSS\4S jjr\R                  " 5       \S 5       5       r	Sr
g)Gemma2RotaryEmbedding   Nr   c                    [         R                  R                  5         UR                  U l        UR                  U l        Xl        U R                  R                  S   U l        U R                  nU R                  S:w  a  [        U R                     nU" U R                  U5      u  o@l        U R                  SUSS9  U R                  SUR                  5       SS9  g )N	rope_typedefaultinv_freqF)
persistentoriginal_inv_freq)nnModuler   rA   max_seq_len_cachedoriginal_max_seq_lenr   rJ   r   compute_default_rope_parametersr   attention_scalingregister_bufferclone)r\   r   devicerope_init_fnr   s        r`   r   Gemma2RotaryEmbedding.__init__   s    
		"("@"@$*$B$B!44[A!%!E!E>>Y&.t~~>L+7V+L((ZeD0(..2BuUrf   c                 L   U R                   S S S 2S 4   R                  5       R                  UR                  S   SS5      R	                  UR
                  5      nUS S 2S S S 24   R                  5       n[        UR
                  R                  [        5      (       a0  UR
                  R                  S:w  a  UR
                  R                  OSn[        USS9   UR                  5       UR                  5       -  R                  SS5      n[        R                  " Xf4SS	9nUR                  5       U R                  -  nUR                  5       U R                  -  n	S S S 5        WR	                  UR                   S
9W	R	                  UR                   S
94$ ! , (       d  f       N@= f)Nr   rF   mpscpuF)device_typeenabledr   )dim)dtype)r   rs   expandshapetor   
isinstancetyperr   r   	transposetorchcatcosr   sinr   )
r\   xposition_idsinv_freq_expandedposition_ids_expandedr   freqsembr   r   s
             r`   forwardGemma2RotaryEmbedding.forward   sN    !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   r   r   r   r   r   )rg   rh   ri   rj   r'   r   r   no_gradr   r   rv   rW   rf   r`   r   r      s2    V| V  ]]_<  <rf   r   modulequerykeyvaluer0   dropoutscalingsoftcapreturnc                 j   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  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$ )N      r   r   r   )r   r   )ptrainingrF   )r>   r$   num_key_value_groupsr   matmulr   tanhr   
functionalsoftmaxfloat32r   r   r   r   
contiguous)r   r   r   r   r0   r   r   r   r]   
key_statesvalue_statesattn_weightsattn_outputs                r`   eager_attention_forwardr      s    //4'3 ; ;<JU$?$?@L<<';';Aq'ABWLL#-zz,/#-!#4 ==((2U]](SVVW\WbWbcL==((6??([L,,|:K''1-88:K$$rf   c                   ,  ^  \ rS rSrS\S\4U 4S jjr   SS\R                  S\	\R                  \R                  4   S-  S\R                  S-  S	\
S-  S
\\   S\	\R                  \R                  S-  \	\R                     S-  4   4S jjrSrU =r$ )Gemma2Attention   r   	layer_idxc                   > [        US5      (       a  UR                  U   OS U l        [        TU ]  X5        U R
                  R                  U l        U R
                  R                  U l        [        USS5      (       + U l	        UR                  S-  U l        U R                  S:X  a  UR                  U l        g S U l        g )NrP   rS   Fr   rU   )hasattrrP   
layer_typerZ   r   r   rR   rM   getattr	is_causalrN   r   rO   r\   r   r   r_   s      r`   r   Gemma2Attention.__init__   s    ;B6=;Y;Y&,,Y7_c+&*kk&H&H#!%!>!>$V-JERR33T97;J]7]f33cgrf   Nr/   position_embeddingsr0   r*   r]   r   c                 4   UR                   S S n/ UQSPU R                  P7nU R                  U5      R                  U5      R	                  SS5      nU R                  U5      R                  U5      R	                  SS5      n	U R                  U5      R                  U5      R	                  SS5      n
Uu  p[        XX5      u  pUb  UR                  XU R                  5      u  p[        R                  " U R                  R                  [        5      nU" U UU	U
U4U R                  (       a  U R                   OSU R"                  U R$                  U R&                  S.UD6u  pUR(                  " / UQSP76 R+                  5       nU R-                  U5      nX4$ )Nr   rF   r   rL   )r   r   rO   r   )r   r>   q_projviewr   k_projv_projr#   updater   r   get_interfacer   _attn_implementationr   r   rM   r   rO   rR   reshaper   o_proj)r\   r/   r   r0   r*   r]   input_shapehidden_shapequery_statesr   r   r   r   attention_interfacer   r   s                   r`   r   Gemma2Attention.forward   s    $))#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#[ &'6'='=jX\XfXf'g$J(?(M(MKK,,.E)
 %8%
 /3mmD**LL..//%
 %
! "));;;;FFHkk+.((rf   )rM   rR   r   r   r   rO   )NNN)rg   rh   ri   rj   r'   rp   r   r   Tensortupler   r   r   r   rv   rw   rx   s   @r`   r   r      s    h| h h IM.2(,()||() #5<<#=>E() t+	()
 () -.() 
u||U\\D0%2E2LL	M() ()rf   r   c                   >  ^  \ rS rSrS\S\4U 4S jjr    SS\R                  S\	\R                  \R                  4   S-  S\R                  S-  S	\R                  S-  S
\S-  S\	\R                  \	\R                  \R                  4   S-  4   4S jjrSrU =r$ )Gemma2DecoderLayeri  r   r   c                   > [         TU ]  5         UR                  U l        X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)r   r   )eps)rZ   r   r5   r   r   	self_attnr   mlprz   rC   input_layernormpost_attention_layernormpre_feedforward_layernormpost_feedforward_layernormr   s      r`   r   Gemma2DecoderLayer.__init__  s    !--(LV$,V-?-?VEXEXY(5f6H6HfNaNa(b%)6v7I7IvObOb)c&*78J8JPVPcPc*d'rf   Nr/   r   r0   r   r*   r   c           	          UnU R                  U5      nU R                  " SUUUUUS.UD6u  pU R                  U5      nXq-   nUnU R                  U5      nU R	                  U5      nU R                  U5      nXq-   nU$ )N)r/   r   r0   r   r*   rW   )r   r   r   r   r   r   )	r\   r/   r   r0   r   r*   r]   residual_s	            r`   r   Gemma2DecoderLayer.forward  s     !,,];  >> 
' 3)%+
 
 55mD 0 66}E/77F 0rf   )r   r5   r   r   r   r   r   r   )NNNN)rg   rh   ri   rj   r'   rp   r   r   r   r   
LongTensorr   FloatTensorr   rv   rw   rx   s   @r`   r   r     s    
e| 
e 
e IM.204(,|| #5<<#=>E t+	
 &&-  
u  %(9(95;L;L(L"MPT"TT	U rf   r   c                       \ rS rSrSrg)Gemma2PreTrainedModeli<  rW   Nr|   rW   rf   r`   r   r   <  r}   rf   r   c                      ^  \ rS rSrS\4U 4S jjr      SS\R                  S-  S\R                  S-  S\R                  S-  S\	S-  S	\R                  S-  S
\S-  S\\   S\4S jjrSrU =r$ )Gemma2Modeli@  r   c           	         > [         TU ]  U5        [        R                  " [	        UR
                  5       Vs/ s H  n[        X5      PM     sn5      U l        [        U5      U l	        g s  snf r   )
rZ   r   r   
ModuleListrX   r8   r   r2   r   
rotary_embr   s      r`   r   Gemma2Model.__init__A  sY     mmDI&JbJbDcdDcy2Dcd
 07 es   A*Nr-   r0   r   r*   r.   rD   r]   r   c           	         US L US L-  (       a  [        S5      eUc  U R                  U5      nU(       a  Uc  [        U R                  S9nUcU  Ub  UR	                  5       OSn[
        R                  " UR                  S   UR                  S9U-   nUR                  S5      n[        U=n	[        5      (       d)  U R                  UUUUS.n
[        S
0 U
D6[        S
0 U
D6S.n	UnU R                  X5      n[        U R                   S U R                  R"                   5       H,  u  pU" U4XR                  R$                  U      UUUS.UD6nM.     U R'                  U5      n[)        UUS	9$ )Nz:You must specify exactly one of input_ids or inputs_embeds)r   r   rF   )r   )r   r.   r0   r*   r   )rV   rU   )r0   r   r   r*   )last_hidden_stater*   rW   )rc   r1   r   r   get_seq_lengthr   aranger   r   	unsqueezer   ru   r
   r   r  	enumerater2   r8   rP   r3   r   )r\   r-   r0   r   r*   r.   rD   r]   past_seen_tokenscausal_mask_mappingmask_kwargsr/   r   r^   decoder_layers                  r`   r   Gemma2Model.forwardH  s    -t";<YZZ *.*;*;I*FM0*$++>OCRC^==?de <<(;(;A(>}G[G[\_ooL'11!4L ?-FF ++!."0#2 ,K #5"C{"C%F%U%U# &"oomJ )$++6U8U8U*V WA)2;;3J3J13MN$7) / M !X 		-0&++
 	
rf   )r2   r  )NNNNNN)rg   rh   ri   rj   r'   r   r   r   r   r   r   rY   r   r   r   r   rv   rw   rx   s   @r`   r   r   @  s    8| 8 .2.204(,26!%;
##d*;
 t+;
 &&-	;

 ;
 ((4/;
 $;;
 +,;
 
!;
 ;
rf   r   c                     ^  \ rS rSrU 4S jr        SS\R                  S-  S\R                  S-  S\R                  S-  S\S-  S\R                  S-  S	\R                  S-  S
\
S-  S\\R                  -  S\\   S\4S jjrSrU =r$ )Gemma2ForCausalLMi  c                 d   > [         TU ]  U5        [        U5      U l        U R	                  5         g r   )rZ   r   r   model	post_initr   s     r`   r   Gemma2ForCausalLM.__init__  s&      (
rf   Nr-   r0   r   r*   r.   labelsrD   logits_to_keepr]   r   c	           
          U R                   " S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                  bF  XR                  R                  -  n[        R                  " U5      nXR                  R                  -  nSnUb  U R                  " XU 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-   r0   r   r*   r.   rD   N)losslogitsr*   r/   
attentionsrW   )r  r  r   rp   slicelm_headr   rQ   r   r   loss_functionr4   r   r*   r/   r  )r\   r-   r0   r   r*   r.   r  rD   r  r]   outputsr/   slice_indicesr  r  s                  r`   r   Gemma2ForCausalLM.forward  s   < ,0:: ,
)%+',
 ,
  118B>SV8W8W~ot4]kmA}a,?@A;;..:kkAAAFZZ'FkkAAAF%%fdooPPD%#33!//))
 	
rf   )r  )NNNNNNNr   )rg   rh   ri   rj   r   r   r   r   r   r   rY   rp   r   r   r   r   rv   rw   rx   s   @r`   r  r    s     .2.204(,26*.!%-.;
##d*;
 t+;
 &&-	;

 ;
 ((4/;
   4';
 $;;
 ell*;
 +,;
 
 ;
 ;
rf   r  c                       \ rS rSrSrg)Gemma2ForSequenceClassificationi  rW   Nr|   rW   rf   r`   r#  r#    r}   rf   r#  c                       \ rS rSrSrg)Gemma2ForTokenClassificationi  rW   Nr|   rW   rf   r`   r%  r%    r}   rf   r%  )r'   r  r   r   r#  r%  )rL   NN)Gcollections.abcr   r   torch.nnr   huggingface_hub.dataclassesr   activationsr   cache_utilsr   r   configuration_utilsr	   masking_utilsr
   r   modeling_flash_attention_utilsr   modeling_layersr   modeling_outputsr   r   modeling_rope_utilsr   r   r   modeling_utilsr   processing_utilsr   utilsr   r   r   utils.genericr   gemma.modeling_gemmar   r   r   r   r   r   r    r!   r"   r#   r$   
get_loggerrg   loggerr'   rz   r   r   r   r   rs   rp   r   r   r   r   r   r   r  r#  r%  __all__rW   rf   r`   <module>r9     s   %   . ! . 3 R B 9 O 
 6 & @ @ +    
		H	% -.N# N  /Nb	L 	7 7<0 <N   %II%<<% 
% <<	%
 LL4'% S[% T\% T\% 5<<%&%D3)n 3)l,3 ,^	0 	C
* C
LA
( A
H	&D 		#> 	rf   