
    Z j\                        S SK Jr  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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   SSK!J"r"J#r#  SSK$J%r%  SSK&J'r'J(r(J)r)  SSK*J+r+J,r,  SSK-J.r.  SSK/J0r0   " S S\Rb                  5      r2 " S S\Rb                  5      r3S r4\" S5      S9S j5       r5S\Rl                  S\7S\Rl                  4S  jr8   S:S!\Rb                  S"\Rl                  S#\Rl                  S$\Rl                  S%\Rl                  S-  S&\9\7-  S'\9S-  S(\9S-  S\:\Rl                  \Rl                  4   4S) jjr;\" \55       " S* S+\Rb                  5      5       r< " S, S-\5      r= " S. S/\Rb                  5      r> " S0 S1\R~                  5      r@\( " S2 S3\#5      5       rA\( " S4 S5\A5      5       rB\( " S6 S7\A\5      5       rC/ S8QrDg);    )Callable)OptionalN   )initialization)ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_func_from_hubuse_kernelized_func)create_causal_mask!create_sliding_window_causal_mask)FlashAttentionKwargs)GradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuple)maybe_autocastmerge_with_config_defaults)capture_outputs   )VaultGemmaConfigc                   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$ )
VaultGemmaRMSNorm.   dimepsc                    > [         TU ]  5         X l        [        R                  " [
        R                  " U5      5      U l        g N)super__init__r$   nn	Parametertorchzerosweight)selfr#   r$   	__class__s      ڃ/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/vaultgemma/modeling_vaultgemma.pyr(   VaultGemmaRMSNorm.__init__/   s,    ll5;;s#34    c                     U[         R                  " UR                  S5      R                  SSS9U R                  -   5      -  $ )N   T)keepdim)r+   rsqrtpowmeanr$   )r.   xs     r0   _normVaultGemmaRMSNorm._norm4   s4    5;;quuQx}}R}>IJJJr2   c                     U R                  UR                  5       5      nUSU R                  R                  5       -   -  nUR                  U5      $ )N      ?)r;   floatr-   type_as)r.   r:   outputs      r0   forwardVaultGemmaRMSNorm.forward7   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VaultGemmaRMSNorm.extra_repr>   s'    ))*+6$((<<r2   )r$   r-   )gư>)__name__
__module____qualname____firstlineno__intr?   r(   r;   rB   rG   __static_attributes____classcell__r/   s   @r0   r!   r!   .   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$ )VaultGemmaMLPB   c                   > [         TU ]  5         Xl        UR                  U l        UR                  U l        [
        R                  " U R                  U R                  SS9U l        [
        R                  " U R                  U R                  SS9U l        [
        R                  " U R                  U R                  SS9U l	        [        UR                     U l        g NFbias)r'   r(   confighidden_sizeintermediate_sizer)   Linear	gate_projup_proj	down_projr   hidden_activationact_fnr.   rX   r/   s     r0   r(   VaultGemmaMLP.__init__C   s    !--!'!9!94#3#3T5K5KRWXyy!1!143I3IPUV4#9#94;K;KRWXV556r2   c                     U R                  U R                  U R                  U5      5      U R                  U5      -  5      nU$ r&   )r^   r`   r\   r]   )r.   r:   r^   s      r0   rB   VaultGemmaMLP.forwardM   s6    NN4;;t~~a/@#ADLLQRO#ST	r2   )r`   rX   r^   r\   rY   rZ   r]   )rI   rJ   rK   rL   r(   rB   rN   rO   rP   s   @r0   rR   rR   B   s    7 r2   rR   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$ )z*Rotates half the hidden dims of the input..Nr5   r4   r#   )rF   r+   cat)r:   x1x2s      r0   rotate_halfrj   R   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r2   rotary_pos_embc                     UR                  U5      nUR                  U5      nX-  [        U 5      U-  -   nX-  [        U5      U-  -   nXV4$ )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.
)	unsqueezerj   )qkcossinunsqueeze_dimq_embedk_embeds          r0   apply_rotary_pos_embru   Y   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)rF   expandreshape)rv   rw   batchnum_key_value_headsslenhead_dims         r0   	repeat_kvr   s   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                 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$ )N      r4   r   r5   )r#   dtype)ptrainingr   )r   r   num_key_value_groupsr+   matmul	transposetanhr)   
functionalsoftmaxfloat32tor   r   r   
contiguous)r   r   r   r   r   r   r   r   kwargs
key_statesvalue_statesattn_weightsattn_outputs                r0   eager_attention_forwardr      s    //4'3 ; ;<JU$?$?@L<<';';Aq'ABWLL#-zz,/#-!#4 ==((2U]](SVVW\WbWbcL==((6??([L,,|:K''1-88:K$$r2   c                   0  ^  \ rS 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$ )VaultGemmaAttention   z=Multi-headed attention from 'Attention Is All You Need' paperrX   	layer_idxc                 :  > [         TU ]  5         [        US5      (       a  UR                  U   OS U l        Xl        X l        [        USUR                  UR                  -  5      U l
        UR                  UR                  -  U l        UR                  S-  U l        U R
                  R                  U l        SU l        ["        R$                  " 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
                  R0                  U l        U R                  S:X  a  UR2                  U l        g S U l        g )Nlayer_typesr   r   TrV   sliding_attention)r'   r(   hasattrr   
layer_typerX   r   getattrrY   num_attention_headsr   r}   r   query_pre_attn_scalarr   attention_dropout	is_causalr)   r[   attention_biasq_projk_projv_projo_projattn_logit_softcappingsliding_windowr.   rX   r   r/   s      r0   r(   VaultGemmaAttention.__init__   s   ;B6=;Y;Y&,,Y7_c"
F4F4F&JdJd4de$*$>$>&B\B\$\!33T9!%!>!>ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
 '+kk&H&H#7;J]7]f33cgr2   Nrv   position_embeddingsr   past_key_valuesr   rx   c                 4   UR                   S S n/ UQSPU R                  P7nU R                  U5      R                  U5      R	                  SS5      nU R                  U5      R                  U5      R	                  SS5      n	U R                  U5      R                  U5      R	                  SS5      n
Uu  p[        XX5      u  pUb  UR                  XU R                  5      u  p[        R                  " U R                  R                  [        5      nU" U UU	U
U4U R                  (       a  U R                   OSU R"                  U R$                  U R&                  S.UD6u  pUR(                  " / UQSP76 R+                  5       nU R-                  U5      nX4$ )Nr5   r   r4           )r   r   r   r   )rF   r   r   viewr   r   r   ru   updater   r   get_interfacerX   _attn_implementationr   r   r   r   r   r   r{   r   r   )r.   rv   r   r   r   r   input_shapehidden_shapequery_statesr   r   rp   rq   attention_interfacer   r   s                   r0   rB   VaultGemmaAttention.forward   s    $))#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$J(?(M(MKK,,.E)
 %8%
 /3mmD**LL..//%
 %
! "));;;;FFHkk+.((r2   )r   r   rX   r   r   r   r   r   r   r   r   r   r   r   NNN)rI   rJ   rK   rL   __doc__r   rM   r(   r+   TensorrE   r   r   r   rB   rN   rO   rP   s   @r0   r   r      s    Gh/ hC h: IM.2(,()||() #5<<#=>E() t+	()
 () -.() 
u||U\\D0%2E2LL	M() ()r2   r   c                   6  ^  \ rS rSrS\S\4U 4S jjr   SS\R                  S\	\R                  \R                  4   S\R                  S-  S	\R                  S-  S
\S-  S\	\R                  \	\R                  \R                  4   S-  4   4S jjrSrU =r$ )VaultGemmaDecoderLayer   rX   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        g )N)rX   r   r$   )r'   r(   rY   rX   r   	self_attnrR   mlpr!   rms_norm_epsinput_layernormpre_feedforward_layernormr   s      r0   r(   VaultGemmaDecoderLayer.__init__   sp    !--,FP (01C1CI\I\]):6;M;MSYSfSf)g&r2   Nrv   r   r   position_idsr   rx   c           	          UnU R                  U5      nU R                  " SUUUUUS.UD6u  pXq-   nUnU R                  U5      nU R                  U5      nXq-   nU$ )N)rv   r   r   r   r    )r   r   r   r   )	r.   rv   r   r   r   r   r   residual_s	            r0   rB   VaultGemmaDecoderLayer.forward   s     !,,];>> 
' 3)%+
 
 !0 66}E/ 0r2   )rX   rY   r   r   r   r   r   )rI   rJ   rK   rL   r   rM   r(   r+   r   rE   
LongTensorr   FloatTensorrB   rN   rO   rP   s   @r0   r   r      s    h/ hC h /304(,|| #5<<#=> t+	
 &&-  
u  %(9(95;L;L(L"MPT"TT	U r2   r   c                      ^  \ rS rSr% \R
                  \S'   SS\4U 4S jjjr\	   SS\S-  S\
S   S\S-  S	\S
\4   4S jj5       r\R                  " 5       \S 5       5       rSrU =r$ )VaultGemmaRotaryEmbeddingi  inv_freqNrX   c                   > [         TU ]  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defaultr   F
persistentoriginal_inv_freq)r'   r(   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrX   rope_parametersr   compute_default_rope_parametersr   attention_scalingregister_bufferclone)r.   rX   devicerope_init_fnr   r/   s        r0   r(   "VaultGemmaRotaryEmbedding.__init__  s    "("@"@$*$B$B!44[A!%!E!E>>Y&.t~~>L+7V+L((ZeD0(..2BuUr2   r   ztorch.deviceseq_lenrx   ztorch.Tensorc           	         U R                   S   n[        U SS5      =(       d    U R                  U R                  -  nSnSU[        R
                  " SUS[        R                  S9R                  U[        R                  S9U-  -  -  nXe4$ )	aH  
Computes the inverse frequencies according to the original RoPE implementation
Args:
    config ([`~transformers.PreTrainedConfig`]):
        The model configuration.
    device (`torch.device`):
        The device to use for initialization of the inverse frequencies.
    seq_len (`int`, *optional*):
        The current sequence length. Unused for this type of RoPE.
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).

rope_thetar   Nr>   r   r4   r   )r   r   )	r   r   rY   r   r+   arangeint64r   r?   )rX   r   r   baser#   attention_factorr   s          r0   r   9VaultGemmaRotaryEmbedding.compute_default_rope_parameters&  s    & %%l3fj$/c63E3EIcIc3c U\\!S!5;;?BB&X]XcXcBdgjjk
 ))r2   c                 L   U R                   S S S 2S 4   R                  5       R                  UR                  S   SS5      R	                  UR
                  5      nUS S 2S S S 24   R                  5       n[        UR
                  R                  [        5      (       a0  UR
                  R                  S:w  a  UR
                  R                  OSn[        USS9   UR                  5       UR                  5       -  R                  SS5      n[        R                  " Xf4SS	9nUR                  5       U R                  -  nUR                  5       U R                  -  n	S S S 5        WR	                  UR                   S
9W	R	                  UR                   S
94$ ! , (       d  f       N@= f)Nr   r5   r   mpscpuF)device_typeenabledr4   rf   r   )r   r?   rz   rF   r   r   
isinstancetypestrr   r   r+   rg   rp   r   rq   r   )
r.   r:   r   inv_freq_expandedposition_ids_expandedr   freqsembrp   rq   s
             r0   rB   !VaultGemmaRotaryEmbedding.forwardD  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   rX   r   r   r   r&   r   )rI   rJ   rK   rL   r+   r   __annotations__r   r(   staticmethodr   rM   rE   r?   r   no_gradr   rB   rN   rO   rP   s   @r0   r   r     s    llV/ V V  *.+/"* 4'*(* t* 
~u$	%	* *: ]]_<  <r2   r   c            	       l   ^  \ rS rSrSrSS\S\S\S\4U 4S jjjrS\R                  4U 4S	 jjr
S
rU =r$ )!VaultGemmaTextScaledWordEmbeddingiT  zT
This module overrides nn.Embeddings' forward by multiplying with embeddings scale.
num_embeddingsembedding_dimpadding_idxembed_scalec                 |   > [         TU ]  XU5        X@l        U R                  S[        R
                  " U5      SS9  g )Nr	  Fr   )r'   r(   scalar_embed_scaler   r+   tensor)r.   r  r  r  r	  r/   s        r0   r(   *VaultGemmaTextScaledWordEmbedding.__init__Y  s7    D"-]ELL,ERWXr2   	input_idsc                    > [         TU ]  U5      U R                  R                  U R                  R
                  5      -  $ r&   )r'   rB   r	  r   r-   r   )r.   r  r/   s     r0   rB   )VaultGemmaTextScaledWordEmbedding.forward^  s2    wy)D,<,<,?,?@Q@Q,RRRr2   )r  )r>   )rI   rJ   rK   rL   r   rM   r?   r(   r+   r   rB   rN   rO   rP   s   @r0   r  r  T  sM    Ys Y3 YS Y_d Y Y
S S Sr2   r  c                      ^  \ 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\R&                  " 5       U 4S j5       rS	rU =r$ )
VaultGemmaPreTrainedModelib  rX   modelTr   r   )rv   
attentionsc                   > [         TU ]  U5        SUR                  R                  ;   a!  [        R
                  " UR                  5        g [        U[        5      (       a,  [        R                  " UR                  UR                  5        g g )NRMSNorm)r'   _init_weightsr/   rI   initzeros_r-   r   r  	constant_r	  r  )r.   r   r/   s     r0   r  'VaultGemmaPreTrainedModel._init_weightst  sb    f%((111KK& ABBNN6--v/H/HI Cr2   r   )rI   rJ   rK   rL   r   r  base_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_supports_sdpa_supports_flex_attn_can_compile_fullgraph_supports_attention_backendr   r   _can_record_outputsr+   r  r  rN   rO   rP   s   @r0   r  r  b  sn    &*#12#4"5N!"&/)
 ]]_J Jr2   r  c                     ^  \ rS rSrS\4U 4S jjr\\\      SS\	R                  S-  S\	R                  S-  S\	R                  S-  S\S-  S	\	R                  S-  S
\S-  S\\   S\4S jj5       5       5       rSrU =r$ )VaultGemmaModeli~  rX   c           	      "  > [         TU ]  U5        UR                  U l        UR                  U l        [        UR                  UR                  U R                  U R                  R                  S-  S9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5      U l        SU l        U R+                  5         g s  snf )Ng      ?)r	  r   F)r'   r(   pad_token_idr  
vocab_sizer  rY   rX   embed_tokensr)   
ModuleListrangenum_hidden_layersr   layersr!   r   normr   
rotary_embgradient_checkpointing	post_initr   s      r0   r(   VaultGemmaModel.__init__  s     !.. ++=v1143C3CQUQ\Q\QhQhjmQm
 mmHMfNfNfHghHg9#F6Hgh
 &f&8&8f>Q>QR	3F;&+# 	 is    DNr  r   r   r   inputs_embeds	use_cacher   rx   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)rX   r   r   )r   )rX   r5  r   r   r   )full_attentionr   )r   r   r   r   )last_hidden_stater   r   )
ValueErrorr+  r	   rX   get_seq_lengthr+   r   rF   r   rm   r   dictr   r   r1  	enumerater/  r.  r   r0  r   )r.   r  r   r   r   r5  r6  r   past_seen_tokenscausal_mask_mappingmask_kwargsrv   r   idecoder_layers                  r0   rB   VaultGemmaModel.forward  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$7) / M !X 		-0&++
 	
r2   )r+  r2  r/  r0  r  r1  r*  )NNNNNN)rI   rJ   rK   rL   r   r(   r   r   r   r+   r   r   r   r   boolr   r   r   rB   rN   rO   rP   s   @r0   r'  r'  ~  s    / $   .2.204(,26!%;
##d*;
 t+;
 &&-	;

 ;
 ((4/;
 $;;
 +,;
 
!;
    ;
r2   r'  c                   P  ^  \ rS rSrSS0rSS0rSS/S/40rU 4S jr\\	        SS
\
R                  S	-  S\
R                  S	-  S\
R                  S	-  S\S	-  S\
R                  S	-  S\
R                  S	-  S\S	-  S\\
R                  -  S\\   S\4S jj5       5       rSrU =r$ )VaultGemmaForCausalLMi  zlm_head.weightzmodel.embed_tokens.weightlm_headcolwise_gather_outputrv   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 rU   )
r'   r(   r'  r  r*  r)   r[   rY   rG  r3  ra   s     r0   r(   VaultGemmaForCausalLM.__init__  sU     $V,
 ++yy!3!3V5F5FUS 	r2   Nr  r   r   r   r5  labelsr6  logits_to_keepr   rx   c	           
          U R                   " SUUUUUUS.U	D6n
U
R                  n[        U[        5      (       a  [	        U* S5      OUnU R                  USS2USS24   5      nU R                  R                  bF  XR                  R                  -  n[        R                  " U5      nXR                  R                  -  nSnUb  U R                  " XU R                  40 U	D6n[        UUU
R                  U
R                  U
R                  S9$ )a*  
Example:

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

>>> model = VaultGemmaForCausalLM.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  r   r   r   r5  r6  N)lossrI  r   rv   r  r   )r  r9  r   rM   slicerG  rX   final_logit_softcappingr+   r   loss_functionr*  r   r   rv   r  )r.   r  r   r   r   r5  rL  r6  rM  r   outputsrv   slice_indicesrI  rO  s                  r0   rB   VaultGemmaForCausalLM.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!//))
 	
r2   )rG  r  r*  )NNNNNNNr   )rI   rJ   rK   rL   _tied_weights_keys_tp_plan_pp_planr(   r   r   r+   r   r   r   r   rD  rM   r   r   r   rB   rN   rO   rP   s   @r0   rF  rF    s   *,GH23H_-z:;H  .2.204(,26*.!%-.;
##d*;
 t+;
 &&-	;

 ;
 ((4/;
   4';
 $;;
 ell*;
 +,;
 
 ;
  ;
r2   rF  )rF  r'  r  )r   )r   NN)Ecollections.abcr   typingr   r+   torch.nnr)    r   r  activationsr   cache_utilsr   r	   
generationr
   integrationsr   r   masking_utilsr   r   modeling_flash_attention_utilsr   modeling_layersr   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.genericr   r   utils.output_capturingr   configuration_vaultgemmar   Moduler!   rR   rj   ru   r   rM   r   r?   rE   r   r   r   r   	Embeddingr  r  r'  rF  __all__r   r2   r0   <module>ro     s  , %    & ! . ) I R B 9 O K F & I I G 5 6=		 =(BII  ( *+ ,2	UU\\ 	U# 	U%,, 	U$   %II%<<% 
% <<	%
 LL4'% S[% T\% T\% 5<<%&%D )*E)")) E) +E)P&7 &R><		 ><BS S J J J6 Q
/ Q
 Q
h K
5 K
 K
\ Tr2   