
    cCiQ                     6   S SK r 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$J%r%  SSK&J'r'  SSK(J)r)   " S S\RT                  5      r+ " S S\RT                  5      r, " S S\RT                  5      r-S\R\                  S\/S\R\                  4S jr0 S6S\RT                  S\R\                  S\R\                  S\R\                  S \\R\                     S!\1S"\1S#\\!   4S$ jjr2S% r3S7S& jr4 " S' S(\RT                  5      r5 " S) S*\5      r6\" " S+ S,\5      5       r7\" " S- S.\75      5       r8\" " S/ S0\7\5      5       r9 " S1 S2\\75      r: " S3 S4\\75      r;/ S5Qr<g)8    N)CallableOptionalUnion   )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   )HeliumConfigc                   8   ^  \ rS rSrSU 4S jjrS rS rSrU =r$ )HeliumRMSNorm/   c                    > [         TU ]  5         [        R                  " [        R
                  " U5      5      U l        X l        g N)super__init__nn	Parametertorchonesweightvariance_epsilon)selfhidden_sizeeps	__class__s      d/home/james-whalen/.local/lib/python3.13/site-packages/transformers/models/helium/modeling_helium.pyr#   HeliumRMSNorm.__init__0   s-    ll5::k#:; #    c                 V   UR                   nUR                  [        R                  5      nUR	                  S5      R                  SSS9nU[        R                  " X0R                  -   5      -  nU R                  R                  [        R                  5      U-  R                  U5      $ )N   T)keepdim)	dtypetor&   float32powmeanrsqrtr)   r(   )r*   hidden_statesinput_dtypevariances       r.   forwardHeliumRMSNorm.forward5   s    #))%((7 $$Q',,R,>%H?T?T4T(UUu}}-=AA+NNr0   c                 ^    [        U R                  R                  5       SU R                   3$ )Nz, eps=)tupler(   shaper)   )r*   s    r.   
extra_reprHeliumRMSNorm.extra_repr<   s*    ))*+6$2G2G1HIIr0   )r)   r(   )gư>)	__name__
__module____qualname____firstlineno__r#   r>   rC   __static_attributes____classcell__r-   s   @r.   r   r   /   s    $
OJ Jr0   r   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$ )HeliumRotaryEmbedding@   inv_freqconfigc                   > [         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defaultrO   F)
persistent)r"   r#   hasattr
isinstancerR   dictgetrS   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrP   r   rope_init_fnattention_scalingregister_bufferrO   original_inv_freq)r*   rP   devicerO   r-   s       r.   r#   HeliumRotaryEmbedding.__init__C   s    6>**z&:M:Mt/T/T#0044[&BUBUBYBYZ`BabDN&DN"("@"@$*$B$B!/?+/+<+<T[[&+Q((ZeD!%r0   c                 b   U R                   S S S 2S 4   R                  5       R                  UR                  S   SS5      R	                  UR
                  5      nUS S 2S S S 24   R                  5       n[        UR
                  R                  [        5      (       a0  UR
                  R                  S:w  a  UR
                  R                  OSn[        R                  " USS9   UR                  5       UR                  5       -  R                  SS5      n[        R                  " Xf4SS	9nUR                  5       U R                  -  nUR                  5       U R                  -  n	S S S 5        WR	                  UR                   S
9W	R	                  UR                   S
94$ ! , (       d  f       N@= f)Nr   r3   r   mpscpuF)device_typeenabledr2   dim)r5   )rO   floatexpandrB   r6   rb   rX   rT   strr&   autocast	transposecatcosr_   sinr5   )
r*   xposition_idsinv_freq_expandedposition_ids_expandedrg   freqsembrq   rr   s
             r.   r>   HeliumRotaryEmbedding.forwardT   sR    !MM$4-8>>@GGHZHZ[\H]_acdehhijiqiqr ,QaZ 8 > > @'1!((--'E'E!((--[`J`ahhmmfk^^UC&,,.1F1L1L1NNYYZ[]^_E))UN3C'')d444C'')d444C	 D vvAGGv$cff177f&;;; DCs   $BF  
F.)r_   rP   r\   ra   r]   r^   rS   r!   )rE   rF   rG   rH   r&   Tensor__annotations__r   r#   no_gradr   r>   rI   rJ   rK   s   @r.   rM   rM   @   s@    ll/| / /" ]]_<  <r0   rM   c                   .   ^  \ rS rSrU 4S jrS rSrU =r$ )	HeliumMLPd   c                   > [         TU ]  5         Xl        UR                  U l        UR                  U l        [
        R                  " U R                  U R                  UR                  S9U l        [
        R                  " U R                  U R                  UR                  S9U l	        [
        R                  " U R                  U R                  UR                  S9U l
        [        UR                     U l        g )Nbias)r"   r#   rP   r+   intermediate_sizer$   Linearmlp_bias	gate_projup_proj	down_projr   
hidden_actact_fnr*   rP   r-   s     r.   r#   HeliumMLP.__init__e   s    !--!'!9!94#3#3T5K5KRXRaRabyy!1!143I3IPVP_P_`4#9#94;K;KRXRaRabV../r0   c                     U R                  U R                  U R                  U5      5      U R                  U5      -  5      nU$ r!   )r   r   r   r   )r*   rs   r   s      r.   r>   HeliumMLP.forwardo   s6    NN4;;t~~a/@#ADLLQRO#ST	r0   )r   rP   r   r   r+   r   r   )rE   rF   rG   rH   r#   r>   rI   rJ   rK   s   @r.   r~   r~   d   s    0 r0   r~   r;   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   rl   reshape)r;   r   batchnum_key_value_headsslenhead_dims         r.   	repeat_kvr   t   s_    
 2?1D1D.Ez!!Qa"23::5W\dlmM  e(CTTTr0   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$ )Nr2   r   r3   )rj   r5   )ptrainingr   )r   num_key_value_groupsr&   matmulro   rB   r$   
functionalsoftmaxr7   r6   r5   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$$r0   c                 x    U SSSS24   nU SSSS24   n[         R                  " U* U4SS9R                  S5      $ )	z*Rotates half the hidden dims of the input..r   Nr2   r   r3   ri   r   )r&   stackflatten)rs   x1x2s      r.   rotate_halfr      sJ    	
319B	
319B;;Ryb)11"55r0   c                 4   UR                  U5      nUR                  U5      nUSSUR                  S   S-  24   R                  SSS9nUSSUR                  S   S-  24   R                  SSS9nX-  [        U 5      U-  -   nX-  [        U5      U-  -   nXg4$ )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.
.Nr3   r2   ri   )	unsqueezerB   repeat_interleaver   )qkrq   rr   rt   unsqueeze_dimq_embedk_embeds           r.   apply_rotary_pos_embr      s    ( --
&C
--
&C c'SYYr]a'''
(
:
:1"
:
EC
c'SYYr]a'''
(
:
:1"
:
ECw;q>C/0Gw;q>C/0Gr0   c                   >  ^  \ rS rSrSrSS\S\\   4U 4S j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$ )HeliumAttention   z=Multi-headed attention from 'Attention Is All You Need' paperrP   	layer_idxc                 J  > [         TU ]  5         Xl        X l        [	        USUR
                  UR                  -  5      U l        UR                  UR                  -  U l	        S[        R                  " U R                  5      -  U l        UR                  U l        SU l        [        R                   " UR
                  UR                  U R                  -  UR"                  S9U l        [        R                   " UR
                  UR                  U R                  -  UR"                  S9U l        [        R                   " UR
                  UR                  U R                  -  UR"                  S9U l        [        R                   " UR
                  UR
                  SS9U l        g )Nr   r   Tr   F)r"   r#   rP   r   getattrr+   num_attention_headsr   r   r   mathsqrtr   attention_dropout	is_causalr$   r   attention_biasq_projk_projv_projo_projr*   rP   r   r-   s      r.   r#   HeliumAttention.__init__   s?   "
F4F4F&JdJd4de$*$>$>&B\B\$\!499T]]33!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii 2 2F4F4FUSr0   past_key_valuepast_key_values4.58new_nameversionr;   position_embeddingsr   cache_positionr   r   c                 4   UR                   S S n/ UQSPU R                  P7nU R                  U5      R                  U5      R	                  SS5      n	U R                  U5      R                  U5      R	                  SS5      n
U R                  U5      R                  U5      R	                  SS5      nUu  p[        XX5      u  pUb$  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$ )Nr3   r   r2   )rr   rq   r   eager        )r   r   )rB   r   r   viewro   r   r   r   updater   r   rP   _attn_implementationr   r   r   r   r   r   r   )r*   r;   r   r   r   r   r   input_shapehidden_shapequery_statesr   r   rq   rr   cache_kwargsattention_interfacer   r   s                     r.   r>   HeliumAttention.forward   s    $))#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$2H2HLL	%
 	%
!\ "));;;;FFHkk+.L((r0   )r   rP   r   r   r   r   r   r   r   r   r   r!   )NN)rE   rF   rG   rH   __doc__r   r   intr#   r   r&   rz   rA   r   
LongTensorr   r   r>   rI   rJ   rK   s   @r.   r   r      s    GT| T T T* %0A6R ,059))||)) #5<<#=>)) !.	))
 "%)) !!1!12)) +,)) 
u||U\\)	*)) S))r0   r   c                   R  ^  \ rS rSrSS\S\\   4U 4S jjjr\" SSSS9      SS	\	R                  S
\\	R                     S\\	R                     S\\   S\\   S\\	R                     S\\\	R                  \	R                  4      S\\   S\	R                  4S jj5       rSrU =r$ )HeliumDecoderLayeri  rP   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)rP   r   r,   )r"   r#   r+   r   	self_attnr~   mlpr   rms_norm_epsinput_layernormpost_attention_layernormr   s      r.   r#   HeliumDecoderLayer.__init__  sj    !--(LV$,V-?-?VEXEXY(5f6H6HfNaNa(b%r0   r   r   r   r   r;   r   rt   	use_cacher   r   r   r   c                     Un	U R                  U5      nU R                  " SUUUUUUUS.UD6u  pX-   nUn	U R                  U5      nU R                  U5      nX-   nU$ )N)r;   r   rt   r   r   r   r    )r   r   r   r   )r*   r;   r   rt   r   r   r   r   r   residual_s              r.   r>   HeliumDecoderLayer.forward  s     !,,];>> 	
')%+) 3	
 	
 !0 !55mD/ 0r0   )r+   r   r   r   r   r!   )NNNFNN)rE   rF   rG   rH   r   r   r   r#   r   r&   rz   r   r   boolrA   r   r   r>   rI   rJ   rK   s   @r.   r   r     s    c| c c c %0A6R 2637+/$)59KO|| !. u//0	
 "% D> !!1!12 &eELL%,,,F&GH +, 
 Sr0   r   c                   R    \ rS rSr% \\S'   SrSrS/rS/r	Sr
SrSrSrSr\\S.rSrg	)
HeliumPreTrainedModeli5  rP   modelTr   r   )r;   
attentionsr   N)rE   rF   rG   rH   r   r{   base_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_supports_sdpa_supports_flex_attn_can_compile_fullgraph_supports_attention_backendr   r   _can_record_outputsrI   r   r0   r.   r   r   5  sQ    &*#-.#4"5N!"&+%r0   r   c                   "  ^  \ rS rSrS\4U 4S jjr\" 5       \       SS\\	R                     S\\	R                     S\\	R                     S\\   S\\	R                     S	\\	R                     S
\\   S\\   S\4S jj5       5       rSrU =r$ )HeliumModeliH  rP   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5      U l        SU l        U R)                  5         g s  snf )Nr   F)r"   r#   pad_token_idpadding_idx
vocab_sizer$   	Embeddingr+   embed_tokens
ModuleListrangenum_hidden_layersr   layersr   r   normrM   
rotary_embgradient_checkpointing	post_initr   s      r.   r#   HeliumModel.__init__J  s     !.. ++LL):):F<N<NPTP`P`ammDI&JbJbDcdDcy2Dcd
 "&"4"4&:M:MN	/7&+# 	 es   D	input_idsr   rt   r   inputs_embedsr   r   r   r   c           
      J   US L US L-  (       a  [        S5      eUc  U R                  U5      nU(       a  Uc  [        U R                  S9nUcD  Ub  UR	                  5       OSn	[
        R                  " XUR                  S   -   UR                  S9nUc  UR                  S5      n[        U R                  UUUUUS9n
UnU R                  X5      nU R                  S U R                  R                    H  nU" U4U
UUUUS.UD6nM     U R                  U5      n[        UUS9$ )	Nz:You must specify exactly one of input_ids or inputs_embeds)rP   r   r   )rb   )rP   input_embedsr   r   r   rt   )r   rt   r   r   r   )last_hidden_stater   )
ValueErrorr  r	   rP   get_seq_lengthr&   arangerB   rb   r   r   r  r  r  r  r   )r*   r  r   rt   r   r  r   r   r   past_seen_tokensr   r;   r   decoder_layers                 r.   r>   HeliumModel.forwardZ  sR    -t";<YZZ *.*;*;I*FM0*$++>O!CRC^==?de+0<< ]5H5H5K"KTaThTh,N )33A6L(;;&))+%
 &"oomJ![[)H4;;+H+HIM)*) /-$7 M J 		-0&++
 	
r0   )r  r  r  r  r
  r  r  )NNNNNNN)rE   rF   rG   rH   r   r#   r   r   r   r&   r   rz   r   FloatTensorr   r   r   r   r>   rI   rJ   rK   s   @r.   r  r  H  s    |    151537+/5959$(8
E,,-8
 !.8
 u//0	8

 "%8
   1 128
 !!1!128
 D>8
 +,8
 
!8
  8
r0   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$ )HeliumForCausalLMi  zlm_head.weightlm_headcolwise_repr;   logitsc                    > [         TU ]  U5        [        U5      U l        UR                  U l        [
        R                  " UR                  UR                  SS9U l        U R                  5         g )NFr   )
r"   r#   r  r   r  r$   r   r+   r%  r  r   s     r.   r#   HeliumForCausalLM.__init__  sU      (
 ++yy!3!3V5F5FUS 	r0   r  r   rt   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, HeliumForCausalLM

>>> model = HeliumForCausalLM.from_pretrained("google/helium-7b")
>>> tokenizer = AutoTokenizer.from_pretrained("google/helium-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   rt   r   r  r   r   N)r'  r*  r  )lossr'  r   r;   r   r   )r   r  rX   r   slicer%  loss_functionrP   r  r   r   r;   r   )r*   r  r   rt   r   r  r*  r   r   r+  r   outputsr;   slice_indicesr'  r-  s                   r.   r>   HeliumForCausalLM.forward  s    @ ,0:: 	,
)%+')	,
 	,
  118B>SV8W8W~ot4]kmA}a,?@A%%pVt{{OeOepiopD%#33!//))
 	
r0   )r%  r   r  )	NNNNNNNNr   )rE   rF   rG   rH   _tied_weights_keys_tp_plan_pp_planr#   r   r   r   r&   r   rz   r   r"  r   r   r   r   r   r   r>   rI   rJ   rK   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
r0   r$  c                       \ rS rSrSrg)HeliumForSequenceClassificationi  r   NrE   rF   rG   rH   rI   r   r0   r.   r7  r7        r0   r7  c                       \ rS rSrSrg)HeliumForTokenClassificationi  r   Nr8  r   r0   r.   r;  r;    r9  r0   r;  )r   r  r$  r7  r;  )r   )Nr   )=r   typingr   r   r   r&   torch.nnr$   activationsr   cache_utilsr   r	   
generationr
   masking_utilsr   modeling_layersr   r   r   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.deprecationr   utils.genericr   configuration_heliumr   Moduler   rM   r~   rz   r   r   rk   r   r   r   r   r   r   r  r$  r7  r;  __all__r   r0   r.   <module>rM     s  ,  , ,   ! . ) / 
 P K F & I I 0 / .JBII J"!<BII !<H		  	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 U\\*% % % '(%46BB)bii B)J+3 +\ O  $ K
' K
 K
\ H
- H
 H
V	&FH] 		#@BW 	r0   