
    cCiS                     .   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  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!  SSK"J#r#  SSK$J%r%  SSK&J'r'   " S S\RP                  5      r) " S S\RP                  5      r* " S S\RP                  5      r+S r,S7S jr-S\R\                  S\/S\R\                  4S jr0 S8S\RP                  S \R\                  S!\R\                  S"\R\                  S#\\R\                     S$\1S%\1S&\\   4S' jjr2 " S( S)\RP                  5      r3 " S* S+\5      r4\  " S, S-\5      5       r5\  " S. S/\55      5       r6\  " S0 S1\5\5      5       r7 " S2 S3\\55      r8 " S4 S5\\55      r9/ S6Qr:g)9    )CallableOptionalUnionN)nn   )ACT2FN)CacheDynamicCache)GenerationMixin)create_causal_mask) GenericForSequenceClassificationGenericForTokenClassificationGradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuple)deprecate_kwarg)check_model_inputs   )GemmaConfigc                   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$ )
GemmaRMSNorm.   dimepsc                    > [         TU ]  5         X l        [        R                  " [
        R                  " U5      5      U l        g N)super__init__r"   r   	Parametertorchzerosweight)selfr!   r"   	__class__s      b/home/james-whalen/.local/lib/python3.13/site-packages/transformers/models/gemma/modeling_gemma.pyr&   GemmaRMSNorm.__init__/   s,    ll5;;s#34    c                     U[         R                  " UR                  S5      R                  SSS9U R                  -   5      -  $ )N   T)keepdim)r(   rsqrtpowmeanr"   )r+   xs     r-   _normGemmaRMSNorm._norm4   s4    5;;quuQx}}R}>IJJJr/   c                     U R                  UR                  5       5      nUSU R                  R                  5       -   -  nUR                  U5      $ )Ng      ?)r8   floatr*   type_as)r+   r7   outputs      r-   forwardGemmaRMSNorm.forward7   sC    AGGI& 3!2!2!445~~a  r/   c                 ^    [        U R                  R                  5       SU R                   3$ )Nz, eps=)tupler*   shaper"   )r+   s    r-   
extra_reprGemmaRMSNorm.extra_repr>   s'    ))*+6$((<<r/   )r"   r*   )gư>)__name__
__module____qualname____firstlineno__intr;   r&   r8   r>   rC   __static_attributes____classcell__r,   s   @r-   r   r   .   s0    5C 5e 5 5
K!= =r/   r   c                   .   ^  \ rS rSrU 4S jrS rSrU =r$ )GemmaMLPB   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r+   rT   r,   s     r-   r&   GemmaMLP.__init__C   s    !--!'!9!94#3#3T5K5KRWXyy!1!143I3IPUV4#9#94;K;KRWXV../r/   c                     U R                  U R                  U R                  U5      5      U R                  U5      -  5      nU$ r$   )rZ   r\   rX   rY   )r+   r7   rZ   s      r-   r>   GemmaMLP.forwardM   s6    NN4;;t~~a/@#ADLLQRO#ST	r/   )r\   rT   rZ   rX   rU   rV   rY   )rE   rF   rG   rH   r&   r>   rJ   rK   rL   s   @r-   rN   rN   B   s    0 r/   rN   c                      ^  \ rS rSr% \R
                  \S'   SS\4U 4S jjjr\R                  " 5       \
S 5       5       rSrU =r$ )GemmaRotaryEmbeddingR   inv_freqrT   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defaultrd   F)
persistent)r%   r&   hasattr
isinstancerf   dictgetrg   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrT   r   rope_init_fnattention_scalingregister_bufferrd   original_inv_freq)r+   rT   devicerd   r,   s       r-   r&   GemmaRotaryEmbedding.__init__U   s    6>**z&:M:Mt/T/T#0044[&BUBUBYBYZ`BabDN&DN"("@"@$*$B$B!/?+/+<+<T[[&+Q((ZeD!%r/   c                 b   U R                   S S S 2S 4   R                  5       R                  UR                  S   SS5      R	                  UR
                  5      nUS S 2S S S 24   R                  5       n[        UR
                  R                  [        5      (       a0  UR
                  R                  S:w  a  UR
                  R                  OSn[        R                  " USS9   UR                  5       UR                  5       -  R                  SS5      n[        R                  " Xf4SS	9nUR                  5       U R                  -  nUR                  5       U R                  -  n	S S S 5        WR	                  UR                   S
9W	R	                  UR                   S
94$ ! , (       d  f       N@= f)Nr   r2   r   mpscpuF)device_typeenabledr1   r!   dtype)rd   r;   expandrB   torv   rl   rh   strr(   autocast	transposecatcosrs   sinr   )
r+   r7   position_idsinv_freq_expandedposition_ids_expandedr{   freqsembr   r   s
             r-   r>   GemmaRotaryEmbedding.forwardf   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   $BF  
F.)rs   rT   rp   ru   rq   rr   rg   r$   )rE   rF   rG   rH   r(   Tensor__annotations__r   r&   no_gradr   r>   rJ   rK   rL   s   @r-   rb   rb   R   s@    ll/{ / /" ]]_<  <r/   rb   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$ )z*Rotates half the hidden dims of the input..Nr2   r1   r}   )rB   r(   r   )r7   x1x2s      r-   rotate_halfr   v   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r/   c                     UR                  U5      nUR                  U5      nX-  [        U 5      U-  -   nX-  [        U5      U-  -   nXg4$ )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           r-   apply_rotary_pos_embr   }   sS    ( --
&C
--
&Cw;q>C/0Gw;q>C/0Gr/   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)rB   r   reshape)r   r   batchnum_key_value_headsslenhead_dims         r-   	repeat_kvr      s_    
 2?1D1D.Ez!!Qa"23::5W\dlmM  e(CTTTr/   modulequerykeyvalueattention_maskscalingdropoutkwargsc                 @   [        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$ )Nr1   r   r2   )r!   r   )ptrainingr   )r   num_key_value_groupsr(   matmulr   rB   r   
functionalsoftmaxfloat32r   r   r   r   
contiguous)r   r   r   r   r   r   r   r   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r-   eager_attention_forwardr      s     3 ; ;<JU$?$?@L<<';';Aq'ABWLL!$Q1.D
0@0@0D.D%DE#1==((2U]](SVVW\WbWbcL==((6??([L,,|:K''1-88:K$$r/   c                   4  ^  \ rS rSrSrS\S\4U 4S jjr\" SSSS	9  SS
\	R                  S\\	R                  \	R                  4   S\\	R                     S\\   S\\	R                     S\\   S\\	R                  \	R                  4   4S jj5       rSrU =r$ )GemmaAttention   z=Multi-headed attention from 'Attention Is All You Need' paperrT   	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      TrR   )r%   r&   rT   r   getattrrU   num_attention_headsr   r   r   r   attention_dropout	is_causalr   rW   attention_biasq_projk_projv_projo_projr+   rT   r   r,   s      r-   r&   GemmaAttention.__init__   sI   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
r/   past_key_valuepast_key_values4.58new_nameversionr   position_embeddingsr   cache_positionr   r   c                 4   UR                   S S n/ UQSPU R                  P7nU R                  U5      R                  U5      R	                  SS5      n	U R                  U5      R                  U5      R	                  SS5      n
U R                  U5      R                  U5      R	                  SS5      nUu  p[        XX5      u  pUb$  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                  (       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$ )Nr2   r   r1   )r   r   r   eager        )r   r   )rB   r   r   viewr   r   r   r   updater   r   rT   _attn_implementationr   r   r   r   r   r   r   )r+   r   r   r   r   r   r   input_shapehidden_shapequery_statesr   r   r   r   cache_kwargsattention_interfacer   r   s                     r-   r>   GemmaAttention.forward   s    $))#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'6'='=jX\XfXfht'u$J(?;;++w6"9$++:Z:Z"[$7	%
  $}}C$2H2HLL	%
 	%
!\ "));;;;FFHkk+.L((r/   )r   rT   r   r   r   r   r   r   r   r   r   )NN)rE   rF   rG   rH   __doc__r   rI   r&   r   r(   r   rA   r   r	   
LongTensorr   r   r>   rJ   rK   rL   s   @r-   r   r      s    G
{ 
s 
. %0A6R ,059))||)) #5<<#=>)) !.	))
 "%)) !!1!12)) +,)) 
u||U\\)	*)) S))r/   r   c                   H  ^  \ rS rSrS\S\4U 4S jjr\" SSSS9      SS	\R                  S
\
\R                     S\
\R                     S\
\   S\
\   S\
\R                     S\
\\R                  \R                  4      S\\   S\R                  4S jj5       rSrU =r$ )GemmaDecoderLayeri  rT   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)rT   r   r"   )r%   r&   rU   r   	self_attnrN   mlpr   rms_norm_epsinput_layernormpost_attention_layernormr   s      r-   r&   GemmaDecoderLayer.__init__  sj    !--'vKF#+F,>,>FDWDWX(4V5G5GVM`M`(a%r/   r   r   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S.UD6u  pX-   nUn	U R                  U5      nU R                  U5      nX-   nU$ )N)r   r   r   r   r   r   r    )r   r   r   r   )r+   r   r   r   r   r   r   r   r   residual_s              r-   r>   GemmaDecoderLayer.forward  s     !,,];>> 	
')%+) 3	
 	
 !0 !55mD/ 0r/   )rU   r   r   r   r   )NNNFNN)rE   rF   rG   rH   r   rI   r&   r   r(   r   r   r   r	   boolrA   r   r   r>   rJ   rK   rL   s   @r-   r   r     s    b{ bs b %0A6R 2637+/$)59KO|| !. u//0	
 "% D> !!1!12 &eELL%,,,F&GH +, 
 Sr/   r   c                   f   ^  \ rS rSr% \\S'   SrSrS/rS/r	Sr
SrSrSrSr\\S.rU 4S jrS	rU =r$ )
GemmaPreTrainedModeli3  rT   modelTr   r   )r   
attentionsc                    > [         TU ]  U5        SUR                  R                  ;   a%  UR                  R
                  R                  5         g g )NRMSNorm)r%   _init_weightsr,   rE   r*   datazero_)r+   r   r,   s     r-   r   "GemmaPreTrainedModel._init_weightsE  sA    f% ((111MM$$& 2r/   r   )rE   rF   rG   rH   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   rJ   rK   rL   s   @r-   r   r   3  s\    &*#,-#4"5N!"&*$
' 'r/   r   c                   "  ^  \ rS rSrS\4U 4S jjr\" 5       \       SS\\	R                     S\\	R                     S\\	R                     S\\   S\\	R                     S	\\   S
\\	R                     S\\   S\4S jj5       5       rSrU =r$ )
GemmaModeliM  rT   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   rT   F)r%   r&   pad_token_idpadding_idx
vocab_sizer   	EmbeddingrU   embed_tokens
ModuleListrangenum_hidden_layersr   layersr   r   normrb   
rotary_embgradient_checkpointing	post_initr   s      r-   r&   GemmaModel.__init__O  s     !.. ++LL):):F<N<NPTP`P`ammCHIaIaCbcCbiv1Cbc
 !!3!39L9LM	.f=&+# 	 ds   C?	input_idsr   r   r   inputs_embedsr   r   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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                  UUUUUS9n
UnU R                  X5      n[
        R                  " U R                  R                  S-  UR                  S9nX-  nU R                  S U R                  R                     H  nU" U4U
UUUUUS	.UD6nM     U R#                  U5      n[%        UU(       a  US
9$ S S
9$ )Nz:You must specify exactly one of input_ids or inputs_embedsr  r   r   )rv   )rT   input_embedsr   r   r   r   g      ?r~   )r   r   r   r   r   r   )last_hidden_stater   )
ValueErrorr  r
   rT   get_seq_lengthr(   arangerB   rv   r   r   r  tensorrU   r   r  r  r  r   )r+   r  r   r   r   r  r   r   r   past_seen_tokensr   r   r   
normalizerdecoder_layers                  r-   r>   GemmaModel.forward_  s    -t";<YZZ  --i8M0*$++>O!CRC^==?de"\\ ]5H5H5K"KTaThThN )33A6L(;;&))+%
 & #oomJ
 \\$++"9"93">mFYFYZ
%2![[)H4;;+H+HIM)	*) /#-$7	 	M J 		-0&+/8O
 	
>B
 	
r/   )r  r  r  r  r  r  r  )NNNNNNN)rE   rF   rG   rH   r   r&   r   r   r   r(   r   r   r	   FloatTensorr   r   r   r   r>   rJ   rK   rL   s   @r-   r  r  M  s    {    151537+/59$(59A
E,,-A
 !.A
 u//0	A

 "%A
   1 12A
 D>A
 !!1!12A
 +,A
 
!A
  A
r/   r  c                   r  ^  \ rS rSrS/rSS0rSS/S/40rU 4S jr\\	         SS\
\R                     S	\
\R                     S
\
\R                     S\
\   S\
\R                     S\
\R                     S\
\   S\
\R                     S\\\R                  4   S\\   S\4S jj5       5       rSrU =r$ )GemmaForCausalLMi  zlm_head.weightlm_headcolwise_repr   logitsc                    > [         TU ]  U5        [        U5      U l        UR                  U l        [
        R                  " UR                  UR                  SS9U l        U R                  5         g rQ   )
r%   r&   r  r   r  r   rW   rU   r,  r  r]   s     r-   r&   GemmaForCausalLM.__init__  sU     '
 ++yy!3!3V5F5FUS 	r/   r  r   r   r   r  labelsr   r   logits_to_keepr   r   c
                 ~   U R                   " SUUUUUUUS.U
D6nUR                  n[        U	[        5      (       a  [	        U	* S5      OU	nU R                  USS2USS24   5      nSnUb)  U R                  " SXU R                  R                  S.U
D6n[        UUUR                  UR                  UR                  S9$ )a  
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?"
```)r  r   r   r   r  r   r   N)r.  r1  r  )lossr.  r   r   r   r   )r   r   rl   rI   slicer,  loss_functionrT   r  r   r   r   r   )r+   r  r   r   r   r  r1  r   r   r2  r   outputsr   slice_indicesr.  r4  s                   r-   r>   GemmaForCausalLM.forward  s    @ ,0:: 	,
)%+')	,
 	,
  118B>SV8W8W~ot4]kmA}a,?@A%%pVt{{OeOepiopD%#33!//))
 	
r/   )r,  r   r  )	NNNNNNNNr   )rE   rF   rG   rH   _tied_weights_keys_tp_plan_pp_planr&   r   r   r   r(   r   r   r	   r)  r   r   rI   r   r   r   r>   rJ   rK   rL   s   @r-   r+  r+    s0   *+=)H_-z:;H  151537+/59-1$(59348
E,,-8
 !.8
 u//0	8

 "%8
   1 128
 ))*8
 D>8
 !!1!128
 c5<</08
 +,8
 
 8
  8
r/   r+  c                       \ rS rSrSrg)GemmaForSequenceClassificationi  r   NrE   rF   rG   rH   rJ   r   r/   r-   r>  r>        r/   r>  c                       \ rS rSrSrg)GemmaForTokenClassificationi  r   Nr?  r   r/   r-   rB  rB    r@  r/   rB  )r  r+  r>  rB  r   )Nr   )r   );typingr   r   r   r(   r   activationsr   cache_utilsr	   r
   
generationr   masking_utilsr   modeling_layersr   r   r   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.deprecationr   utils.genericr   configuration_gemmar   Moduler   rN   rb   r   r   r   rI   r   r;   r   r   r   r   r  r+  r>  rB  __all__r   r/   r-   <module>rS     s  , - ,   ! . ) / 
 P K F & I I 0 / ,=299 =(ryy  !<299 !<H(6	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 U\\*% % % '(%4D)RYY D)N+2 +\ '? ' '2 T
% T
 T
n H
+_ H
 H
V	%EG[ 		"?AU 	r/   