
    fThg                        S SK JrJr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  SS	KJr  SS
KJr  SSKJr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!  SSK"J#r#J$r$J%r%J&r&J'r'  SSK(J)r)  \&" 5       (       a  S SK*J+r+  SSK,J-r-  \'R\                  " \/5      r0 " S S\Rb                  5      r2 " S S\Rb                  5      r3 " S S\Rb                  5      r4S r5S;S jr6S\Rn                  S\8S\Rn                  4S jr9 S<S \Rb                  S!\Rn                  S"\Rn                  S#\Rn                  S$\\Rn                     S%\:S&\:4S' jjr; " S( S)\Rb                  5      r< " S* S+\5      r=\$ " S, S-\5      5       r>\$ " S. S/\>5      5       r? " S0 S1\\#5      r@\$ " S2 S3\>\5      5       rA\$" S4S59 " S6 S7\>5      5       rB\$ " S8 S9\>5      5       rC/ S:QrDg)=    )CallableListOptionalTupleUnionN)nn   )ACT2FN)CacheDynamicCache)GenerationMixin)AttentionMaskConverter)FlashAttentionKwargs)GradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast SequenceClassifierOutputWithPastTokenClassifierOutput)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)
LossKwargsauto_docstringcan_return_tupleis_torch_flex_attn_availablelogging   )GemmaConfig)	BlockMask)make_flex_block_causal_maskc                   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$ )
GemmaRMSNorm7   dimepsc                    > [         TU ]  5         X l        [        R                  " [
        R                  " U5      5      U l        g N)super__init__r'   r   	Parametertorchzerosweight)selfr&   r'   	__class__s      `/var/www/auris/envauris/lib/python3.13/site-packages/transformers/models/gemma/modeling_gemma.pyr+   GemmaRMSNorm.__init__8   s,    ll5;;s#34    c                     U[         R                  " UR                  S5      R                  SSS9U R                  -   5      -  $ )N   T)keepdim)r-   rsqrtpowmeanr'   )r0   xs     r2   _normGemmaRMSNorm._norm=   s4    5;;quuQx}}R}>IJJJr4   c                     U R                  UR                  5       5      nUSU R                  R                  5       -   -  nUR                  U5      $ )N      ?)r=   floatr/   type_as)r0   r<   outputs      r2   forwardGemmaRMSNorm.forward@   sC    AGGI& 3!2!2!445~~a  r4   c                 ^    [        U R                  R                  5       SU R                   3$ )Nz, eps=)tupler/   shaper'   r0   s    r2   
extra_reprGemmaRMSNorm.extra_reprG   s'    ))*+6$((<<r4   )r'   r/   )gư>)__name__
__module____qualname____firstlineno__intrA   r+   r=   rD   rJ   __static_attributes____classcell__r1   s   @r2   r$   r$   7   s0    5C 5e 5 5
K!= =r4   r$   c                   .   ^  \ rS rSrU 4S jrS rSrU =r$ )GemmaMLPK   c                   > [         TU ]  5         Xl        UR                  U l        UR                  U l        [
        R                  " U R                  U R                  SS9U l        [
        R                  " U R                  U R                  SS9U l        [
        R                  " U R                  U R                  SS9U l	        [        UR                     U l        g NFbias)r*   r+   confighidden_sizeintermediate_sizer   Linear	gate_projup_proj	down_projr
   
hidden_actact_fnr0   r[   r1   s     r2   r+   GemmaMLP.__init__L   s    !--!'!9!94#3#3T5K5KRWXyy!1!143I3IPUV4#9#94;K;KRWXV../r4   c                     U R                  U R                  U R                  U5      5      U R                  U5      -  5      nU$ r)   )ra   rc   r_   r`   )r0   r<   ra   s      r2   rD   GemmaMLP.forwardV   s6    NN4;;t~~a/@#ADLLQRO#ST	r4   )rc   r[   ra   r_   r\   r]   r`   )rL   rM   rN   rO   r+   rD   rQ   rR   rS   s   @r2   rU   rU   K   s    0 r4   rU   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$ )GemmaRotaryEmbedding[   r[   c                   > [         TU ]  5         [        US5      (       aH  UR                  b;  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+   hasattrrl   getrm   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenr[   r   rope_init_fnattention_scalingregister_bufferrp   original_inv_freq)r0   r[   devicerp   r1   s       r2   r+   GemmaRotaryEmbedding.__init__\   s    6>**v/B/B/N#0044[&BUBUBYBYZ`BabDN&DN"("@"@$*$B$B!/?+/+<+<T[[&+Q((ZeD!%r4   c                 b   U R                   S S S 2S 4   R                  5       R                  UR                  S   SS5      R	                  UR
                  5      nUS S 2S S S 24   R                  5       n[        UR
                  R                  [        5      (       a0  UR
                  R                  S:w  a  UR
                  R                  OSn[        R                  " USS9   UR                  5       UR                  5       -  R                  SS5      n[        R                  " Xf4SS	9nUR                  5       U R                  -  nUR                  5       U R                  -  n	S S S 5        WR	                  UR                   S
9W	R	                  UR                   S
94$ ! , (       d  f       N@= f)Nr   r7   r   mpscpuF)device_typeenabledr6   r&   dtype)rp   rA   expandrH   tor{   
isinstancern   strr-   autocast	transposecatcosrx   sinr   )
r0   r<   position_idsinv_freq_expandedposition_ids_expandedr   freqsembr   r   s
             r2   rD   GemmaRotaryEmbedding.forwardm   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   $BF  
F.)rx   r[   ru   rz   rv   rw   rm   r)   )rL   rM   rN   rO   r    r+   r-   no_gradr   rD   rQ   rR   rS   s   @r2   ri   ri   [   s6    /{ / /" ]]_<  <r4   ri   c                     U SSU R                   S   S-  24   nU SU R                   S   S-  S24   n[        R                  " U* U4SS9$ )z*Rotates half the hidden dims of the input..Nr7   r6   r   )rH   r-   r   )r<   x1x2s      r2   rotate_halfr   }   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r4   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           r2   apply_rotary_pos_embr      sS    ( --
&C
--
&Cw;q>C/0Gw;q>C/0Gr4   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)rH   r   reshape)r   r   batchnum_key_value_headsslenhead_dims         r2   	repeat_kvr      s_    
 2?1D1D.Ez!!Qa"23::5W\dlmM  e(CTTTr4   modulequerykeyvalueattention_maskscalingdropoutc                 @   [        X R                  5      n[        X0R                  5      n	[        R                  " XR	                  SS5      5      U-  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$ )Nr6   r	   r7   )r&   r   )ptrainingr   )r   num_key_value_groupsr-   matmulr   rH   r   
functionalsoftmaxfloat32r   r   r   r   
contiguous)r   r   r   r   r   r   r   kwargs
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r2   eager_attention_forwardr      s     3 ; ;<JU$?$?@L<<';';Aq'ABWLL!$Q1.D
0@0@0D.D%DE#1==((2U]](SVVW\WbWbcL==((6??([L,,|:K''1-88:K$$r4   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$ )GemmaAttention   z=Multi-headed attention from 'Attention Is All You Need' paperr[   	layer_idxc                 P  > [         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                  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        g )Nr   g      TrY   )r*   r+   r[   r   getattrr\   num_attention_headsr   r   r   r   attention_dropout	is_causalr   r^   attention_biasq_projk_projv_projo_projr0   r[   r   r1   s      r2   r+   GemmaAttention.__init__   sI   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
r4   r   position_embeddingsr   past_key_valuecache_positionr   r   c                    UR                   S S n/ UQSPU R                  P7nU R                  U5      R                  U5      R	                  SS5      n	U R                  U5      R                  U5      R	                  SS5      n
U R                  U5      R                  U5      R	                  SS5      nUu  p[        XX5      u  pUb$  XUS.nUR                  XU R                  U5      u  p[        nU R                  R                  S:w  ad  U R                  R                  S:X  a-  UR                  SS5      (       a  [        R                  S	5        O[         U R                  R                     nU" U U	U
UU4U R"                  (       d  S
OU R$                  U R&                  S.UD6u  nnUR(                  " / UQSP76 R+                  5       nU R-                  U5      nUU4$ )Nr7   r   r6   )r   r   r   eagersdpaoutput_attentionsFz`torch.nn.functional.scaled_dot_product_attention` does not support `output_attentions=True`. Falling back to eager attention. This warning can be removed using the argument `attn_implementation="eager"` when loading the model.        )r   r   )rH   r   r   viewr   r   r   r   updater   r   r[   _attn_implementationrs   loggerwarning_oncer   r   r   r   r   r   r   )r0   r   r   r   r   r   r   input_shapehidden_shapequery_statesr   r   r   r   cache_kwargsattention_interfacer   r   s                     r2   rD   GemmaAttention.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{{//69fjjI\^c>d>d##L
 '>dkk>^>^&_#$7	%
  $}}C$2H2HLL	%
 	%
!\ "));;;;FFHkk+.L((r4   )r   r[   r   r   r   r   r   r   r   r   r   )NN)rL   rM   rN   rO   __doc__r    rP   r+   r-   Tensorr   r   r   
LongTensorr   r   rD   rQ   rR   rS   s   @r2   r   r      s    G
{ 
s 
8 +/590)||0) #5<<#=>0) !.	0)
 !0) !!1!120) -.0) 
u||Xell3XeELL>Q5RR	S0) 0)r4   r   c                     ^  \ rS rSrS\S\4U 4S jjr       SS\R                  S\	\R                     S\	\R                     S\	\   S	\	\   S
\	\   S\	\R                     S\	\\R                  \R                  4      S\\   S\\R                   \	\\R                   \R                   4      4   4S jjrSrU =r$ )GemmaDecoderLayeri  r[   r   c                   > [         TU ]  5         UR                  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
        g )N)r[   r   r'   )r*   r+   r\   r   	self_attnrU   mlpr$   rms_norm_epsinput_layernormpost_attention_layernormr   s      r2   r+   GemmaDecoderLayer.__init__  sj    !--'vKF#+F,>,>FDWDWX(4V5G5GVM`M`(a%r4   r   r   r   r   r   	use_cacher   r   r   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X-   nUn
U R                  U5      nU R                  U5      nX-   nU4nU(       a  X4-  nU$ )N)r   r   r   r   r   r   r   r    )r   r   r   r   )r0   r   r   r   r   r   r   r   r   r   residualself_attn_weightsoutputss                r2   rD   GemmaDecoderLayer.forward  s     !,,]; ,0>> 
,
')%)/) 3
,
 
,
( !0 !55mD/ 0 "++Gr4   )r\   r   r   r   r   )NNNFFNN)rL   rM   rN   rO   r    rP   r+   r-   r   r   r   r   boolr   r   r   FloatTensorrD   rQ   rR   rS   s   @r2   r   r     s   b{ bs b 2637*.,1$)59KO'||' !.' u//0	'
 !' $D>' D>' !!1!12' &eELL%,,,F&GH' -.' 
u  (51B1BEDUDU1U+V"WW	X' 'r4   r   c                   N    \ rS rSr\rSrSrS/rS/r	Sr
SrSrSrSrSrSrS rSrg)	GemmaPreTrainedModeliG  modelTr   past_key_valuesc                    U R                   R                  n[        U[        R                  5      (       aW  UR
                  R                  R                  SUS9  UR                  b%  UR                  R                  R                  5         g g [        U[        R                  5      (       ad  UR
                  R                  R                  SUS9  UR                  b2  UR
                  R                  UR                     R                  5         g g [        U[        5      (       a&  UR
                  R                  R                  S5        g g )Nr   )r;   stdr@   )r[   initializer_ranger   r   r^   r/   datanormal_rZ   zero_	Embeddingpadding_idxr$   fill_)r0   r   r  s      r2   _init_weights"GemmaPreTrainedModel._init_weightsV  s    kk++fbii((MM&&CS&9{{&  &&( '--MM&&CS&9!!-""6#5#56<<> .--MM$$S) .r4   r   N)rL   rM   rN   rO   r    config_classbase_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_2_supports_sdpa_supports_flex_attn_supports_cache_class_supports_quantized_cache_supports_static_cache_supports_attention_backendr	  rQ   r   r4   r2   r   r   G  sS    L&*#,-#4"5!N  $!"&*r4   r   c                   (  ^  \ rS rSrS\4U 4S jjrS rS r\\	         SS\
\R                     S\
\R                     S\
\R                     S	\
\\\\R"                     4      S
\
\R"                     S\
\   S\
\   S\
\   S\
\R                     S\4S jj5       5       r SS\\R                  S4   S\R                  S\R                  S	\S\4
S jjr\S\R                  S\S\S\R0                  S\R                  S\4S j5       rSrU =r$ )
GemmaModelid  r[   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   )r[   F)r*   r+   pad_token_idr  
vocab_sizer   r  r\   embed_tokens
ModuleListrangenum_hidden_layersr   layersr$   r   normri   
rotary_embgradient_checkpointing	post_initr   s      r2   r+   GemmaModel.__init__f  s     !.. ++LL):):F<N<NPTP`P`ammCHIaIaCbcCbiv1Cbc
 !!3!39L9LM	.f=&+# 	 ds   C?c                     U R                   $ r)   r  rI   s    r2   get_input_embeddingsGemmaModel.get_input_embeddingsv  s       r4   c                     Xl         g r)   r'  r0   r   s     r2   set_input_embeddingsGemmaModel.set_input_embeddingsy  s    !r4   	input_idsr   r   r   inputs_embedsr   r   output_hidden_statesr   r   c
                 d   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
  [        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 R#                  X%XU5      nUnU R%                  X5      n[        R&                  " U R                   R(                  S-  UR*                  S9nX-  nU(       a  S	OS nU(       a  S	OS nU R,                  S U R                   R.                    H4  nU(       a  UU4-  nU" UUUUUUU	US
9nUS   nU(       d  M+  UUS   4-  nM6     U R1                  U5      nU(       a  UU4-  n[3        UU(       a  UOS 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{   g      ?r   r   )r   r   r   r   r   r   r   )last_hidden_stater   r   
attentions)r[   r   r0  r   
ValueErrorr#  r   r   r   r  r   get_seq_lengthr-   arangerH   r{   r   _update_causal_maskr"  tensorr\   r   r   r  r!  r   )r0   r.  r   r   r   r/  r   r   r0  r   r   past_seen_tokensr   r   r   
normalizerall_hidden_statesall_self_attnsdecoder_layerlayer_outputss                       r2   rD   GemmaModel.forward|  sI    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..>L]

 & #oomJ
 \\$++"9"93">mFYFYZ
%2 #7BD0d![[)H4;;+H+HIM#!m%55!)*)."3#-$7	M *!,M  =#3"55% J( 		-0  -!11&+/8Od+%	
 	
r4   r!   input_tensorc           	         U R                   R                  S:X  a  Ub  US:H  R                  5       (       a  U$ g U R                   R                  S:X  a,  [        U[        R
                  5      (       a  [        U5      nU$ Ub  UR                  5       OSnUb  UR                  OSnU R                   R                  S:X  a5  U(       d.  U(       d'  [        R                  " UUUU R                  S9(       a  g UR                  nUR                  S   n	U(       a  UR                  5       n
O5[        U[        R
                  5      (       a  UR                  S	   OXi-   S-   n
U R                  UU	U
UUUR                  S   S
9nU R                   R                  S:X  aZ  UbW  UR                   R"                  S;   a=  U(       d6  [        R$                  " U5      R&                  n[        R(                  " X5      nU$ )Nflash_attention_2r   flex_attentionr   Fr   )r/  past_key_values_lengthis_trainingr   r7   )sequence_lengthtarget_lengthr   r   
batch_size)cudaxpunpu)r[   r   anyr   r-   r   r"   r6  is_compileabler   _ignore_causal_mask_sdpar   r   rH   get_max_cache_shape5_prepare_4d_causal_attention_mask_with_cache_positionr{   rn   finfomin_unmask_unattended)r0   r   rA  r   r   r   r:  using_compilable_cacher   rG  rH  r   	min_dtypes                r2   r8  GemmaModel._update_causal_mask  s    ;;++/BB)~/D.I.I.K.K%%;;++/??.%,,77!<^!L!!
 @O?Z?99;`aCRC^!?!?di ;;++v5>T]n%>>*'7 MM	 ""&,,Q/!+??AM nell;; $$R(%7!;  PP+')#))!, Q 
 KK,,6*%%**.DD%
 E*..I0CCK[Kr4   rG  rH  r   rI  c                    U b  U R                  5       S:X  a  U nU$ [        R                  " U5      R                  n[        R                  " X4XUR
                  S9nUS:w  a  [        R                  " USS9nU[        R                  " X$R
                  S9UR                  SS5      :  -  nUSSSS2SS24   R                  USSS5      nU b  UR                  5       nU R                  S   n	USS2SS2SS2SU	24   U SS2SSSS24   R                  UR
                  5      -   n
U
S:H  n
USS2SS2SS2SU	24   R                  X5      USS2SS2SS2SU	24'   U$ )	a  
Creates a causal 4D mask of shape `(batch_size, 1, query_length, key_value_length)` from a 2D mask of shape
`(batch_size, key_value_length)`, or if the input `attention_mask` is already 4D, do nothing.

Args:
    attention_mask (`torch.Tensor`):
        A 2D attention mask of shape `(batch_size, key_value_length)` or a 4D attention mask of shape
        `(batch_size, 1, query_length, key_value_length)`.
    sequence_length (`int`):
        The sequence length being processed.
    target_length (`int`):
        The target length: when generating with static cache, the mask should be as long as the static cache,
        to account for the 0 padding, the part of the cache that is not filled yet.
    dtype (`torch.dtype`):
        The dtype to use for the 4D attention mask.
    cache_position (`torch.Tensor`):
        Indices depicting the position of the input sequence tokens in the sequence.
    batch_size (`torch.Tensor`):
        Batch size.
N   )
fill_valuer   r{   r   )diagonalr2  r7   r   )r&   r-   rR  rS  fullr{   triur7  r   r   clonerH   r   masked_fill)r   rG  rH  r   r   rI  r   r   rV  mask_lengthpadding_masks              r2   rQ  @GemmaModel._prepare_4d_causal_attention_mask_with_cache_position"  s}   < %.*<*<*>!*C(K* ' E*..I** 0Y\j\q\qK !##jjqA5<<>S>STWeWmWmnprsWtttK%dD!Q&67>>z1bRTUK))//1,2226*1aL[L+@ANSTVZ\`bcScDdDgDg&&E    ,q05@Aq,;,AV5W5c5c 6Aq!\k\12 r4   )r  r#  r   r!  r  r"  r  	NNNNNNNNN)F)rL   rM   rN   rO   r    r+   r(  r,  r   r   r   r-   r   r   r   r   r   r   r   r   rD   r8  staticmethodrP   r   rQ  rQ   rR   rS   s   @r2   r  r  d  s   {  !"  151537KO59$(,0/359^
E,,-^
 !.^
 u//0	^

 "%tE4E4E/F(F"GH^
   1 12^
 D>^
 $D>^
 'tn^
 !!1!12^
 
!^
  ^
L #(BellK78B llB 	B
 B  BH 444 4 {{	4
 4 4 4r4   r  c                       \ rS rSrSrg)KwargsForCausalLMiZ  r   N)rL   rM   rN   rO   rQ   r   r4   r2   rf  rf  Z  s    3r4   rf  c                     ^  \ rS rSrS/rSS0rSS/S/40rU 4S jrS rS	 r	S
 r
S rS rS r\\           SS\\R$                     S\\R&                     S\\R$                     S\\   S\\R*                     S\\R$                     S\\   S\\   S\\   S\\R$                     S\\\R&                  4   S\\   S\4S jj5       5       rSrU =r$ )GemmaForCausalLMi]  zlm_head.weightlm_headcolwise_repr   logitsc                    > [         TU ]  U5        [        U5      U l        UR                  U l        [
        R                  " UR                  UR                  SS9U l        U R                  5         g rX   )
r*   r+   r  r   r  r   r^   r\   ri  r$  rd   s     r2   r+   GemmaForCausalLM.__init__c  sU     '
 ++yy!3!3V5F5FUS 	r4   c                 .    U R                   R                  $ r)   r   r  rI   s    r2   r(  %GemmaForCausalLM.get_input_embeddingsl      zz&&&r4   c                 $    XR                   l        g r)   ro  r+  s     r2   r,  %GemmaForCausalLM.set_input_embeddingso      "'

r4   c                     U R                   $ r)   ri  rI   s    r2   get_output_embeddings&GemmaForCausalLM.get_output_embeddingsr  s    ||r4   c                     Xl         g r)   rv  )r0   new_embeddingss     r2   set_output_embeddings&GemmaForCausalLM.set_output_embeddingsu  s    %r4   c                     Xl         g r)   r   )r0   decoders     r2   set_decoderGemmaForCausalLM.set_decoderx  s    
r4   c                     U R                   $ r)   r~  rI   s    r2   get_decoderGemmaForCausalLM.get_decoder{  s    zzr4   r.  r   r   r   r/  labelsr   r   r0  r   logits_to_keepr   r   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SnUb)  U R                  " SUX`R                   R                  S.UD6n[        UUUR                  UR                  UR                  S9$ )a  
labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
    Labels for computing the masked language modeling loss. Indices should either be in `[0, ...,
    config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored
    (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`.

Example:

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

>>> model = GemmaForCausalLM.from_pretrained("google/gemma-7b")
>>> tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b")

>>> 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   r0  r   )rk  r  r  lossrk  r   r   r4  r   )r[   r   r0  r   r3  r   rP   sliceri  loss_functionr  r   r   r   r4  )r0   r.  r   r   r   r/  r  r   r   r0  r   r  r   r   r   slice_indicesrk  r  s                     r2   rD   GemmaForCausalLM.forward~  s   N 2C1N-TXT_T_TqTq$8$D $++JjJj 	
 ,0:: ,
)%+'/!5),
 ,
  118B>SV8W8W~ot4]kmA}a,?@A%%pVF{{OeOepiopD%#33!//))
 	
r4   )ri  r   r  )NNNNNNNNNNr   )rL   rM   rN   rO   _tied_weights_keys_tp_plan_pp_planr+   r(  r,  rw  r{  r  r  r   r   r   r-   r   r   r   r   r   r   rP   r   rf  r   rD   rQ   rR   rS   s   @r2   rh  rh  ]  s   *+=)H_-z:;H'(&  151537+/59-1$(,0/35934G
E,,-G
 !.G
 u//0	G

 "%G
   1 12G
 ))*G
 D>G
 $D>G
 'tnG
 !!1!12G
 c5<</0G
 *+G
 
 G
  G
r4   rh  a  
    The Gemma Model transformer with a sequence classification head on top (linear layer).

    [`GemmaForSequenceClassification`] uses the last token in order to do the classification, as other causal models
    (e.g. GPT-2) do.

    Since it does classification on the last token, it requires to know the position of the last token. If a
    `pad_token_id` is defined in the configuration, it finds the last token that is not a padding token in each row. If
    no `pad_token_id` is defined, it simply takes the last value in each row of the batch. Since it cannot guess the
    padding tokens when `inputs_embeds` are passed instead of `input_ids`, it does the same (take the last value in
    each row of the batch).
    )custom_introc                   *  ^  \ rS rS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\4S jj5       5       rSrU =r$ )GemmaForSequenceClassificationi  c                    > [         TU ]  U5        UR                  U l        [        U5      U l        [
        R                  " UR                  U R                  SS9U l        U R                  5         g rX   )
r*   r+   
num_labelsr  r   r   r^   r\   scorer$  rd   s     r2   r+   'GemmaForSequenceClassification.__init__  sS      ++'
YYv114??O
 	r4   c                 .    U R                   R                  $ r)   ro  rI   s    r2   r(  3GemmaForSequenceClassification.get_input_embeddings  rq  r4   c                 $    XR                   l        g r)   ro  r+  s     r2   r,  3GemmaForSequenceClassification.set_input_embeddings  rt  r4   r.  r   r   r   r/  r  r   r   r0  r   c
                    U R                  UUUUUUUU	S9n
U
R                  nU R                  U5      nUb  UR                  S   nOUR                  S   nU R                  R
                  c  US:w  a  [        S5      eU R                  R
                  c  SnOUb  XR                  R
                  :g  R                  UR                  [        R                  5      n[        R                  " UR                  S   UR                  [        R                  S9nUU-  R                  S5      nO.Sn[        R                  U R                  R                    S35        U[        R                  " XR                  S	9U4   nSnUb  U R#                  XUU R                  S
9n[%        UUU
R&                  U
R(                  U
R*                  S9$ )e  
labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
    Labels for computing the sequence classification/regression loss. Indices should be in `[0, ...,
    config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If
    `config.num_labels > 1` a classification loss is computed (Cross-Entropy).
r   r   r   r/  r   r   r0  Nr   r   z=Cannot handle batch sizes > 1 if no padding token is defined.r7   )r{   r   z will not detect padding tokens in `inputs_embeds`. Results may be unexpected if using padding tokens in conjunction with `inputs_embeds.`r2  )rk  r  pooled_logitsr[   r  )r   r3  r  rH   r[   r  r5  r   r{   r-   int32r7  argmaxr   r   r1   rL   r  r   r   r   r4  )r0   r.  r   r   r   r/  r  r   r   r0  transformer_outputsr   rk  rI  last_non_pad_tokennon_pad_masktoken_indicesr  r  s                      r2   rD   &GemmaForSequenceClassification.forward  s   * 8<zz)%+'/!5 8B 	8
 ,==M* "+J&,,Q/J;;##+
a\]];;##+!#"%)A)AAEEfmmUZU`U`aL!LL)<V]]Z_ZeZefM"/,">!F!Fr!J!#>>**+ ,Z Z
 u||J}}MOaab%%VR_hlhshs%tD/ /??-;;*55
 	
r4   )r   r  r  rc  )rL   rM   rN   rO   r+   r(  r,  r   r   r   r-   r   r   r   r   r   r   rD   rQ   rR   rS   s   @r2   r  r    s    '(  151537+/59-1$(,0/3A
E,,-A
 !.A
 u//0	A

 "%A
   1 12A
 ))*A
 D>A
 $D>A
 'tnA
 
*A
  A
r4   r  c                   *  ^  \ rS rSrU 4S jrS rS r\\         SS\	\
R                     S\	\
R                     S\	\
R                     S\	\   S	\	\
R                     S
\	\
R                     S\	\   S\	\   S\	\   S\4S jj5       5       rSrU =r$ )GemmaForTokenClassificationi.  c                   > [         TU ]  U5        UR                  U l        [        U5      U l        [        USS 5      b  UR                  nO[        USS 5      b  UR                  nOSn[        R                  " U5      U l
        [        R                  " UR                  UR                  5      U l        U R                  5         g )Nclassifier_dropouthidden_dropoutg?)r*   r+   r  r  r   r   r  r  r   Dropoutr   r^   r\   r  r$  )r0   r[   r  r1   s      r2   r+   $GemmaForTokenClassification.__init__0  s      ++'
6/6B!'!:!:V-t4@!'!6!6!$zz"45YYv1163D3DE
 	r4   c                 .    U R                   R                  $ r)   ro  rI   s    r2   r(  0GemmaForTokenClassification.get_input_embeddings@  rq  r4   c                 $    XR                   l        g r)   ro  r+  s     r2   r,  0GemmaForTokenClassification.set_input_embeddingsC  rt  r4   r.  r   r   r   r/  r  r   r   r0  r   c
                    U R                  UUUUUUUU	S9n
U
R                  nU R                  U5      nU R                  U5      nSnUb  U R	                  XU R
                  5      n[        UUU
R                  U
R                  S9$ )r  r  N)r  rk  r   r4  )	r   r3  r   r  r  r[   r   r   r4  )r0   r.  r   r   r   r/  r  r   r   r0  r   sequence_outputrk  r  s                 r2   rD   #GemmaForTokenClassification.forwardF  s    * ,0::)%+'/!5 ,6 	,
 "33,,7O,%%fdkkBD$!//))	
 	
r4   )r   r   r  r  rc  )rL   rM   rN   rO   r+   r(  r,  r   r   r   r-   r   r   r   r   r   r   rD   rQ   rR   rS   s   @r2   r  r  .  s     '(  151537+/59-1$(,0/3*
E,,-*
 !.*
 u//0	*

 "%*
   1 12*
 ))**
 D>*
 $D>*
 'tn*
 
*
  *
r4   r  )r  rh  r  r  r   )Nr   )r   )Etypingr   r   r   r   r   r-   r   activationsr
   cache_utilsr   r   
generationr   modeling_attn_mask_utilsr   modeling_flash_attention_utilsr   modeling_layersr   modeling_outputsr   r   r   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   r   r   configuration_gemmar    !torch.nn.attention.flex_attentionr!   integrations.flex_attentionr"   
get_loggerrL   r   Moduler$   rU   ri   r   r   r   rP   r   rA   r   r   r   r   r  rf  rh  r  r  __all__r   r4   r2   <module>r     s	  , : 9   ! . ) > B 9  L F & h h ,  !!;J 
		H	%=299 =(ryy  <299 <D(6	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 U\\*% % %4J)RYY J)Z22 2j *? * *8 r% r rj ?,j > i
+_ i
 i
X S
%9 S
S
l C
"6 C
 C
Lr4   