
    3jR                     >   S SK r 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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$J%r%J&r&  SSK'J(r(  SSK)J*r*   " S S\RV                  5      r, " S S\RV                  5      r- " S S\RV                  5      r.S\R^                  S\0S\R^                  4S jr1 S7S\RV                  S\R^                  S\R^                  S \R^                  S!\R^                  S-  S"\2S#\2S$\\!   4S% jjr3S& r4S8S' jr5 " S( S)\RV                  5      r6 " S* S+\5      r7\" " S, S-\5      5       r8\" " S. S/\85      5       r9\" " S0 S1\8\5      5       r: " S2 S3\\85      r; " S4 S5\\85      r</ S6Qr=g)9    N)Callable)Optional   )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)maybe_autocastmerge_with_config_defaults)capture_outputs   )HeliumConfigc                   8   ^  \ rS rSrSU 4S jjrS rS rSrU =r$ )HeliumRMSNorm/   c                    > [         TU ]  5         [        R                  " [        R
                  " U5      5      U l        X l        g N)super__init__nn	Parametertorchonesweightvariance_epsilon)selfhidden_sizeeps	__class__s      d/home/wildlama/miniconda3/lib/python3.13/site-packages/transformers/models/helium/modeling_helium.pyr#   HeliumRMSNorm.__init__0   s-    ll5::k#:; #    c                 V   UR                   nUR                  [        R                  5      nUR	                  S5      R                  SSS9nU[        R                  " X0R                  -   5      -  nU R                  R                  [        R                  5      U-  R                  U5      $ )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\	   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$ )HeliumRotaryEmbedding@   inv_freqNconfigc                   > [         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defaultrO   F)
persistentoriginal_inv_freq)r"   r#   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrP   rope_parametersrR   compute_default_rope_parametersr   attention_scalingregister_bufferclone)r*   rP   devicerope_init_fnrO   r-   s        r.   r#   HeliumRotaryEmbedding.__init__C   s    "("@"@$*$B$B!44[A!%!E!E>>Y&.t~~>L+7V+L((ZeD0(..2BuUr0   r^   ztorch.deviceseq_lenreturnztorch.Tensorc           	         U R                   S   n[        U SS5      =(       d    U R                  U R                  -  nSnSU[        R
                  " SUS[        R                  S9R                  U[        R                  S9U-  -  -  nXe4$ )	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_thetahead_dimNg      ?r   r2   r5   )r^   r5   )	rY   getattrr+   num_attention_headsr&   arangeint64r6   float)rP   r^   ra   basedimattention_factorrO   s          r.   rZ   5HeliumRotaryEmbedding.compute_default_rope_parametersS   s    & %%l3fj$/c63E3EIcIc3c U\\!S!5;;?BB&X]XcXcBdgjjk
 ))r0   c                 L   U R                   S S S 2S 4   R                  5       R                  UR                  S   SS5      R	                  UR
                  5      nUS S 2S S S 24   R                  5       n[        UR
                  R                  [        5      (       a0  UR
                  R                  S:w  a  UR
                  R                  OSn[        USS9   UR                  5       UR                  5       -  R                  SS5      n[        R                  " Xf4SS	9nUR                  5       U R                  -  nUR                  5       U R                  -  n	S S S 5        WR	                  UR                   S
9W	R	                  UR                   S
94$ ! , (       d  f       N@= f)Nr   r3   r   mpscpuF)device_typeenabledr2   rm   rf   )rO   rk   expandrB   r6   r^   
isinstancetypestrr   	transposer&   catcosr[   sinr5   )
r*   xposition_idsinv_freq_expandedposition_ids_expandedrs   freqsembr|   r}   s
             r.   r>   HeliumRotaryEmbedding.forwardq   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[   rP   rW   rX   rR   r!   NNN)rE   rF   rG   rH   r&   Tensor__annotations__r   r#   staticmethodr   intrA   rk   rZ   no_gradr   r>   rI   rJ   rK   s   @r.   rM   rM   @   s    llV| V V  &*+/"*t#*(* t* 
~u$	%	* *: ]]_<  <r0   rM   c                   .   ^  \ rS rSrU 4S jrS rSrU =r$ )	HeliumMLP   c                   > [         TU ]  5         Xl        UR                  U l        UR                  U l        [
        R                  " U R                  U R                  UR                  S9U l        [
        R                  " U R                  U R                  UR                  S9U l	        [
        R                  " U R                  U R                  UR                  S9U l
        [        UR                     U l        g )Nbias)r"   r#   rP   r+   intermediate_sizer$   Linearmlp_bias	gate_projup_proj	down_projr   
hidden_actact_fnr*   rP   r-   s     r.   r#   HeliumMLP.__init__   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$ r!   )r   r   r   r   )r*   r~   r   s      r.   r>   HeliumMLP.forward   s6    NN4;;t~~a/@#ADLLQRO#ST	r0   )r   rP   r   r   r+   r   r   )rE   rF   rG   rH   r#   r>   rI   rJ   rK   s   @r.   r   r      s    0 r0   r   r;   n_reprb   c                     U R                   u  p#pEUS:X  a  U $ 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      $ )z
This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,
num_key_value_heads, seqlen, head_dim) to (batch, num_attention_heads, seqlen, head_dim)
r   N)rB   rv   reshape)r;   r   batchnum_key_value_headsslenre   s         r.   	repeat_kvr      s_    
 2?1D1D.Ez!!Qa"23::5W\dlmM  e(CTTTr0   modulequerykeyvalueattention_maskscalingdropoutkwargsc                    [        X R                  5      n[        X0R                  5      n	[        R                  " XR	                  SS5      5      U-  n
Ub  X-   n
[
        R                  R                  U
S[        R                  S9R                  UR                  5      n
[
        R                  R                  XU R                  S9n
[        R                  " X5      nUR	                  SS5      R                  5       nX4$ )Nr2   r   r3   )rm   r5   )ptrainingr   )r   num_key_value_groupsr&   matmulrz   r$   
functionalsoftmaxr7   r6   r5   r   r   
contiguous)r   r   r   r   r   r   r   r   
key_statesvalue_statesattn_weightsattn_outputs               r.   eager_attention_forwardr      s     3 ; ;<JU$?$?@L<<';';Aq'ABWLL!#4==((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      $ )	z*Rotates half the hidden dims of the input..r   Nr2   r   r3   ru   )r&   stackflatten)r~   x1x2s      r.   rotate_halfr      sJ    	
319B	
319B;;Ryb)11"55r0   c                 4   UR                  U5      nUR                  U5      nUSSUR                  S   S-  24   R                  SSS9nUSSUR                  S   S-  24   R                  SSS9nX-  [        U 5      U-  -   nX-  [        U5      U-  -   nXV4$ )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.
.Nr3   r2   ru   )	unsqueezerB   repeat_interleaver   )qkr|   r}   unsqueeze_dimq_embedk_embeds          r.   apply_rotary_pos_embr      s    $ --
&C
--
&C c'SYYr]a'''
(
:
:1"
:
EC
c'SYYr]a'''
(
:
:1"
:
ECw;q>C/0Gw;q>C/0Gr0   c                     ^  \ rS rSrSrSS\S\S-  4U 4S jjjr   SS\R                  S\
\R                  \R                  4   S-  S	\R                  S-  S
\S-  S\\   S\
\R                  \R                  4   4S jjrSrU =r$ )HeliumAttention   z=Multi-headed attention from 'Attention Is All You Need' paperNrP   	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 )Nre   r   Tr   F)r"   r#   rP   r   rg   r+   rh   re   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$*$>$>&B\B\$\!499T]]33!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii 2 2F4F4FUSr0   r;   position_embeddingsr   past_key_valuesr   rb   c                    UR                   S S n/ UQSPU R                  P7nU R                  U5      R                  U5      R	                  SS5      nU R                  U5      R                  U5      R	                  SS5      n	U R                  U5      R                  U5      R	                  SS5      n
Uu  p[        XX5      u  pUb  UR                  XU R                  5      u  p[        R                  " U R                  R                  [        5      nU" U UU	U
U4U R                  (       d  SOU R                   U R"                  S.UD6u  pUR$                  " / UQSP76 R'                  5       nU R)                  U5      nX4$ )Nr3   r   r2           )r   r   )rB   re   r   viewrz   r   r   r   updater   r   get_interfacerP   _attn_implementationr   r   r   r   r   r   r   )r*   r;   r   r   r   r   input_shapehidden_shapequery_statesr   r   r|   r}   attention_interfacer   r   s                   r.   r>   HeliumAttention.forward   s~    $))#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#[ &'6'='=jX\XfXf'g$J(?(M(MKK,,.E)
 %8	%
  $}}C$2H2HLL	%
 	%
! "));;;;FFHkk+.((r0   )r   rP   re   r   r   r   r   r   r   r   r   r!   r   )rE   rF   rG   rH   __doc__r   r   r#   r&   r   rA   r   r   r   r>   rI   rJ   rK   s   @r.   r   r      s    GT| Td
 T T0 IM.2(,&)||&) #5<<#=>E&) t+	&)
 &) +,&) 
u||U\\)	*&) &)r0   r   c                     ^  \ rS rSrSS\S\S-  4U 4S jjjr     SS\R                  S\R                  S-  S\R                  S-  S	\
S-  S
\S-  S\\R                  \R                  4   S-  S\\   S\R                  4S jjrSrU =r$ )HeliumDecoderLayeri  NrP   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$,V-?-?VEXEXY(5f6H6HfNaNa(b%r0   r;   r   r   r   	use_cacher   r   rb   c           
          UnU R                  U5      nU R                  " SUUUUUUS.UD6u  pX-   nUnU R                  U5      nU R                  U5      nX-   nU$ )N)r;   r   r   r   r   r    )r   r   r   r   )
r*   r;   r   r   r   r   r   r   residual_s
             r.   r>   HeliumDecoderLayer.forward(  s     !,,];>> 
')%+ 3
 
 !0 !55mD/ 0r0   )r+   r   r   r   r   r!   )NNNFN)rE   rF   rG   rH   r   r   r#   r&   r   
LongTensorr   boolrA   r   r   r>   rI   rJ   rK   s   @r.   r   r     s    c| cd
 c c /304(,!&HL|| t+ &&-	
  $; #5<<#=>E +, 
 r0   r   c                   R    \ rS rSr% \\S'   SrSrS/rS/r	Sr
SrSrSrSr\\S.rSrg	)
HeliumPreTrainedModeliH  rP   modelTr   r   )r;   
attentionsr   N)rE   rF   rG   rH   r   r   base_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_supports_sdpa_supports_flex_attn_can_compile_fullgraph_supports_attention_backendr   r   _can_record_outputsrI   r   r0   r.   r   r   H  sQ    &*#-.#4"5N!"&+%r0   r   c                     ^  \ rS rSrS\4U 4S jjr\\\      SS\	R                  S-  S\	R                  S-  S\	R                  S-  S\S-  S	\	R                  S-  S
\S-  S\\   S\4S jj5       5       5       rSrU =r$ )HeliumModeli[  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S9U l        SU l        U R)                  5         g s  snf )Nr   rP   F)r"   r#   pad_token_idpadding_idx
vocab_sizer$   	Embeddingr+   embed_tokens
ModuleListrangenum_hidden_layersr   layersr   r   normrM   
rotary_embgradient_checkpointing	post_initr   s      r.   r#   HeliumModel.__init__]  s     !.. ++LL):):F<N<NPTP`P`ammDI&JbJbDcdDcy2Dcd
 "&"4"4&:M:MN	/v>&+# 	 es   C?N	input_idsr   r   r   inputs_embedsr   r   rb   c           
      >   US L US L-  (       a  [        S5      eUc  U R                  U5      nU(       a  Uc  [        U R                  S9nUcU  Ub  UR	                  5       OSn[
        R                  " UR                  S   UR                  S9U-   nUR                  S5      n[        U R                  UUUUS9n	Un
U R                  XS9nU R                  S U R                  R                    H  nU" U
4U	UUUUS.UD6n
M     U R                  U
5      n
[        U
US	9$ )
Nz:You must specify exactly one of input_ids or inputs_embedsr
  r   r   )r^   )rP   r  r   r   r   )r   )r   r   r   r   r   )last_hidden_stater   )
ValueErrorr  r   rP   get_seq_lengthr&   ri   rB   r^   r   r
   r  r  r  r  r   )r*   r  r   r   r   r  r   r   past_seen_tokenscausal_maskr;   r   decoder_layers                r.   r>   HeliumModel.forwardm  sF    -t";<YZZ *.*;*;I*FM0*$++>OCRC^==?de <<(;(;A(>}G[G[\_ooL'11!4L(;;')+%
 &"oomoW![[)H4;;+H+HIM)*$7) /# M J 		-0&++
 	
r0   )r  r  r  r  r  r  r  )NNNNNN)rE   rF   rG   rH   r   r#   r   r   r   r&   r   r   r   FloatTensorr   r   r   r   r>   rI   rJ   rK   s   @r.   r  r  [  s    |     .2.204(,26!%2
##d*2
 t+2
 &&-	2

 2
 ((4/2
 $;2
 +,2
 
!2
    2
r0   r  c                   P  ^  \ rS rSrSS0rSS0rSS/S/40rU 4S jr\\	        SS
\
R                  S	-  S\
R                  S	-  S\
R                  S	-  S\S	-  S\
R                  S	-  S\
R                  S	-  S\S	-  S\\
R                  -  S\\   S\4S jj5       5       rSrU =r$ )HeliumForCausalLMi  zlm_head.weightzmodel.embed_tokens.weightlm_headcolwise_gather_outputr;   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$   r   r+   r&  r  r   s     r.   r#   HeliumForCausalLM.__init__  sU      (
 ++yy!3!3V5F5FUS 	r0   Nr  r   r   r   r  labelsr   logits_to_keepr   rb   c	           
      |   U R                   " SUUUUUUS.U	D6n
U
R                  n[        U[        5      (       a  [	        U* S5      OUnU R                  USS2USS24   5      nSnUb)  U R                  " SXU R                  R                  S.U	D6n[        UUU
R                  U
R                  U
R                  S9$ )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   r   r   r  r   N)r(  r+  r  )lossr(  r   r;   r   r   )r   r  rw   r   slicer&  loss_functionrP   r  r   r   r;   r   )r*   r  r   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  )NNNNNNNr   )rE   rF   rG   rH   _tied_weights_keys_tp_plan_pp_planr#   r   r   r&   r   r   r   r#  r   r   r   r   r   r>   rI   rJ   rK   s   @r.   r%  r%    s   *,GH23H_-z:;H  .2.204(,26*.!%-.6
##d*6
 t+6
 &&-	6

 6
 ((4/6
   4'6
 $;6
 ell*6
 +,6
 
 6
  6
r0   r%  c                       \ rS rSrSrg)HeliumForSequenceClassificationi  r   NrE   rF   rG   rH   rI   r   r0   r.   r8  r8        r0   r8  c                       \ rS rSrSrg)HeliumForTokenClassificationi  r   Nr9  r   r0   r.   r<  r<    r:  r0   r<  )r   r  r%  r8  r<  )r   )r   )>r   collections.abcr   typingr   r&   torch.nnr$   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.genericr   r   utils.output_capturingr   configuration_heliumr   Moduler   rM   r   r   r   r   rk   r   r   r   r   r   r   r  r%  r8  r<  __all__r   r0   r.   <module>rO     s  *  $    ! . ) / 
 P K F & I I G 5 .JBII J"><BII ><B		  	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 LL4'% % % '(%26>>)bii >)B(3 (V O  $ F
' F
 F
R F
- F
 F
R	&FH] 		#@BW 	r0   