
    bCiR                     4   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  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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\RR                  5      r*\" S5       " S S\RR                  5      5       r+ " S S\RR                  5      r,S r-S7S jr.S\R^                  S\0S\R^                  4S  jr1 S8S!\RR                  S"\R^                  S#\R^                  S$\R^                  S%\\R^                     S&\2S'\2S(\\    4S) jjr3 " S* S+\RR                  5      r4 " S, S-\5      r5\! " S. S/\5      5       r6\! " S0 S1\65      5       r7\! " S2 S3\6\5      5       r8 " S4 S5\\65      r9/ S6Qr:g)9    )CallableOptionalUnionN)nn   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_forward_from_hub)create_causal_mask)GenericForTokenClassificationGradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuple)deprecate_kwarg)check_model_inputs   )ApertusConfigc                   .   ^  \ rS rSrU 4S jrS rSrU =r$ )
ApertusMLP+   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        [        UR                     U l        g NFbias)super__init__confighidden_sizeintermediate_sizer   Linearup_proj	down_projr   
hidden_actact_fnselfr'   	__class__s     f/home/james-whalen/.local/lib/python3.13/site-packages/transformers/models/apertus/modeling_apertus.pyr&   ApertusMLP.__init__,   s    !--!'!9!9yy!1!143I3IPUV4#9#94;K;KRWXV../    c                 `    U R                  U R                  U R                  U5      5      5      $ N)r,   r.   r+   )r0   xs     r2   forwardApertusMLP.forward5   s"    ~~dkk$,,q/:;;r4   )r.   r'   r,   r(   r)   r+   )__name__
__module____qualname____firstlineno__r&   r8   __static_attributes____classcell__r1   s   @r2   r   r   +   s    0< <r4   r   RMSNormc                   8   ^  \ rS rSrSU 4S jjrS rS rSrU =r$ )ApertusRMSNorm9   c                    > [         TU ]  5         [        R                  " [        R
                  " U5      5      U l        X l        g)z-
ApertusRMSNorm is equivalent to T5LayerNorm
N)r%   r&   r   	Parametertorchonesweightvariance_epsilon)r0   r(   epsr1   s      r2   r&   ApertusRMSNorm.__init__;   s/     	ll5::k#:; #r4   c                    UR                   nUR                  [        R                  5      nUR	                  S5      R                  SSS9nU[        R                  " X0R                  -   5      -  nU R                  UR                  U5      -  $ )N   T)keepdim)	dtypetorG   float32powmeanrsqrtrJ   rI   )r0   hidden_statesinput_dtypevariances       r2   r8   ApertusRMSNorm.forwardC   sw    #))%((7 $$Q',,R,>%H?T?T4T(UU{{]--k:::r4   c                 ^    [        U R                  R                  5       SU R                   3$ )Nz, eps=)tuplerI   shaperJ   )r0   s    r2   
extra_reprApertusRMSNorm.extra_reprJ   s*    ))*+6$2G2G1HIIr4   )rJ   rI   )gư>)	r:   r;   r<   r=   r&   r8   r^   r>   r?   r@   s   @r2   rC   rC   9   s    $;J Jr4   rC   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$ )ApertusRotaryEmbeddingN   inv_freqr'   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defaultrc   F)
persistent)r%   r&   hasattr
isinstancere   dictgetrf   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenr'   r   rope_init_fnattention_scalingregister_bufferrc   original_inv_freq)r0   r'   devicerc   r1   s       r2   r&   ApertusRotaryEmbedding.__init__Q   s    6>**z&:M:Mt/T/T#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   rO   r   mpscpuF)device_typeenabledrN   dim)rQ   )rc   floatexpandr]   rR   ru   rk   rg   strrG   autocast	transposecatcosrr   sinrQ   )
r0   r7   position_idsinv_freq_expandedposition_ids_expandedrz   freqsembr   r   s
             r2   r8   ApertusRotaryEmbedding.forwardb   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   $BF  
F.)rr   r'   ro   rt   rp   rq   rf   r6   )r:   r;   r<   r=   rG   Tensor__annotations__r   r&   no_gradr   r8   r>   r?   r@   s   @r2   ra   ra   N   s@    ll/} / /" ]]_<  <r4   ra   c                     U SSU R                   S   S-  24   nU SU R                   S   S-  S24   n[        R                  " U* U4SS9$ )z*Rotates half the hidden dims of the input..NrO   rN   r|   )r]   rG   r   )r7   x1x2s      r2   rotate_halfr   r   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   y   sS    ( --
&C
--
&Cw;q>C/0Gw;q>C/0Gr4   rW   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)r]   r   reshape)rW   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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$ )NrN   r   rO   )r}   rQ   )ptrainingr   )r   num_key_value_groupsrG   matmulr   r]   r   
functionalsoftmaxrS   rR   rQ   r   r   
contiguous)r   r   r   r   r   r   r   r   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r2   eager_attention_forwardr      s     3 ; ;<JU$?$?@L<<';';Aq'ABWLL!$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                   >  ^  \ 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$ )ApertusAttention   z=Multi-headed attention from 'Attention Is All You Need' paperr'   	layer_idxc                   > [         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        [)        U R                  UR*                  5      U l        [)        U R                  UR*                  5      U l        g )Nr   g      Tr#   )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_projrC   rms_norm_epsq_normk_normr0   r'   r   r1   s      r2   r&   ApertusAttention.__init__   s{   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
 %T]]F4G4GH$T]]F4G4GHr4   past_key_valuepast_key_values4.58new_nameversionrW   position_embeddingsr   cache_positionr   r   c                 x   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 R                  U	5      n	U R                  U
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$ )NrO   r   rN   )r   r   r   eager        )r   r   )r]   r   r   viewr   r   r   r   r   r   updater   r   r'   _attn_implementationr   r   r   r   r   r   r   )r0   rW   r   r   r   r   r   input_shapehidden_shapequery_statesr   r   r   r   cache_kwargsattention_interfacer   r   s                     r2   r8   ApertusAttention.forward   s    $))#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{{<0[[,
&#7RU#[ &#&nUL'6'='=jX\XfXfht'u$J(?;;++w6"9$++:Z:Z"[$7	%
  $}}C$2H2HLL	%
 	%
!\ "));;;;FFHkk+.L((r4   )r   r'   r   r   r   r   r   r   r   r   r   r   r   r6   )NN)r:   r;   r<   r=   __doc__r   r   intr&   r   rG   r   r\   r	   
LongTensorr   r   r8   r>   r?   r@   s   @r2   r   r      s    GI} I# I I2 %0A6R ,059*)||*) #5<<#=>*) !.	*)
 "%*) !!1!12*) +,*) 
u||U\\)	**) S*)r4   r   c                   N  ^  \ rS rSrS\S\4U 4S jjr\" SSSS9      SS	\R                  S
\
\R                     S\
\R                     S\
\   S\
\   S\
\R                     S\
\\R                  \R                  4      S\\   S\\R                     4S jj5       rSrU =r$ )ApertusDecoderLayeri  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   rK   )r%   r&   r(   r   	self_attnr   mlprC   r   attention_layernormfeedforward_layernormr   s      r2   r&   ApertusDecoderLayer.__init__  sj    !--)Mf%#1&2D2D&J]J]#^ %3F4F4FFL_L_%`"r4   r   r   r   r   rW   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$ )N)rW   r   r   r   r   r   r    )r   r   r   r   )r0   rW   r   r   r   r   r   r   r   residual_s              r2   r8   ApertusDecoderLayer.forward  s     !00?>> 	
')%+) 3	
 	
 !0 !22=A/ 0r4   )r   r   r(   r   r   )NNNFNN)r:   r;   r<   r=   r   r   r&   r   rG   r   r   r   r	   boolr\   r   r   r8   r>   r?   r@   s   @r2   r   r     s    a} a a %0A6R 2637+/$)59KO|| !. u//0	
 "% D> !!1!12 &eELL%,,,F&GH +, 
u||	 Sr4   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	)
ApertusPreTrainedModeli1  r'   modelTr   r   )rW   
attentionsr   N)r:   r;   r<   r=   r   r   base_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_supports_sdpa_supports_flex_attn_can_compile_fullgraph_supports_attention_backendr   r   _can_record_outputsr>   r   r4   r2   r   r   1  sQ    &*#./#4"5N!"&,&r4   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$ )ApertusModeliD  r'   c           	        > [         TU ]  U5        UR                  U l        UR                  U l        [
        R                  " UR                  UR                  U R                  5      U l        [
        R                  " [        UR                  5       Vs/ s H  n[        X5      PM     sn5      U l        [        UR                  UR                  S9U l        [#        US9U l        SU l        U R)                  5         g s  snf )Nr   r'   F)r%   r&   pad_token_idpadding_idx
vocab_sizer   	Embeddingr(   embed_tokens
ModuleListrangenum_hidden_layersr   layersrC   r   normra   
rotary_embgradient_checkpointing	post_initr   s      r2   r&   ApertusModel.__init__F  s     !.. ++LL):):F<N<NPTP`P`ammEJ6KcKcEdeEd	 3Ede
 #6#5#56;N;NO	0?&+# 	 fs   C?	input_idsr   r   r   inputs_embedsr   r   r   r   c           
      J   US L US L-  (       a  [        S5      eUc  U R                  U5      nU(       a  Uc  [        U R                  S9nUcD  Ub  UR	                  5       OSn	[
        R                  " XUR                  S   -   UR                  S9nUc  UR                  S5      n[        U R                  UUUUUS9n
UnU R                  X5      nU R                  S U R                  R                    H  nU" U4U
UUUUS.UD6nM     U R                  U5      n[        UUS9$ )	Nz:You must specify exactly one of input_ids or inputs_embedsr  r   r   )ru   )r'   input_embedsr   r   r   r   )r   r   r   r   r   )last_hidden_stater   )
ValueErrorr  r
   r'   get_seq_lengthrG   aranger]   ru   r   r   r  r  r  r  r   )r0   r  r   r   r   r  r   r   r   past_seen_tokensr   rW   r   decoder_layers                 r2   r8   ApertusModel.forwardV  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)*) /-$7 M J 		-0&++
 	
r4   )r  r  r  r  r  r  r	  )NNNNNNN)r:   r;   r<   r=   r   r&   r   r   r   rG   r   r   r	   FloatTensorr   r   r   r   r8   r>   r?   r@   s   @r2   r  r  D  s    }    151537+/5959$(8
E,,-8
 !.8
 u//0	8

 "%8
   1 128
 !!1!128
 D>8
 +,8
 
!8
  8
r4   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$ )ApertusForCausalLMi  zlm_head.weightlm_headcolwise_reprW   logitsc                    > [         TU ]  U5        [        U5      U l        UR                  U l        [
        R                  " UR                  UR                  SS9U l        U R                  5         g r"   )
r%   r&   r  r   r	  r   r*   r(   r#  r  r/   s     r2   r&   ApertusForCausalLM.__init__  sU     !&)
 ++yy!3!3V5F5FUS 	r4   r  r   r   r   r  labelsr   r   logits_to_keepr   r   c
                 ~   U R                   " SUUUUUUUS.U
D6nUR                  n[        U	[        5      (       a  [	        U	* S5      OU	nU R                  USS2USS24   5      nSnUb)  U R                  " SXU R                  R                  S.U
D6n[        UUUR                  UR                  UR                  S9$ )a  
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, ApertusForCausalLM

>>> model = ApertusForCausalLM.from_pretrained("swiss-ai/Apertus-8B")
>>> tokenizer = AutoTokenizer.from_pretrained("swiss-ai/Apertus-8B")

>>> prompt = "Hey, are you conscious? Can you talk to me?"
>>> 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]
"Hey, are you conscious? Can you talk to me?\nI'm not conscious, but I can talk to you."
```)r  r   r   r   r  r   r   N)r%  r(  r	  )lossr%  r   rW   r   r   )r   r  rk   r   slicer#  loss_functionr'   r	  r   r   rW   r   )r0   r  r   r   r   r  r(  r   r   r)  r   outputsrW   slice_indicesr%  r+  s                   r2   r8   ApertusForCausalLM.forward  s    J ,0:: 	,
)%+')	,
 	,
  118B>SV8W8W~ot4]kmA}a,?@A%%pVt{{OeOepiopD%#33!//))
 	
r4   )r#  r   r	  )	NNNNNNNNr   )r:   r;   r<   r=   _tied_weights_keys_tp_plan_pp_planr&   r   r   r   rG   r   r   r	   r   r   r   r   r   r   r   r8   r>   r?   r@   s   @r2   r"  r"    s0   *+=)H_-z:;H  151537+/59-1$(5934=
E,,-=
 !.=
 u//0	=

 "%=
   1 12=
 ))*=
 D>=
 !!1!12=
 c5<</0=
 +,=
 
 =
  =
r4   r"  c                       \ rS rSrSrg)ApertusForTokenClassificationi  r   N)r:   r;   r<   r=   r>   r   r4   r2   r5  r5    s    r4   r5  )r  r"  r5  r   )Nr   )r   );typingr   r   r   rG   r   activationsr   cache_utilsr	   r
   
generationr   integrationsr   masking_utilsr   modeling_layersr   r   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.deprecationr   utils.genericr   configuration_apertusr   Moduler   rC   ra   r   r   r   r   r   r~   r   r   r   r   r  r"  r5  __all__r   r4   r2   <module>rG     s  , - ,   ! . ) 7 / X O K F & I I 0 / 0< < Y'JRYY J (J(!<RYY !<H(6	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 U\\*% % % '(%4G)ryy G)T*4 *Z _  $ K
) K
 K
\ M
/ M
 M
`	$ACY 	 lr4   