
    cCi#T                        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	  SSK
JrJr  SSK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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\RV                  5      r,S r-S6S jr.S\R^                  S\0S\R^                  4S jr1 S7S\RV                  S\R^                  S\R^                  S\R^                  S \\R^                     S!\2S"\2S#\"\$   4S$ jjr3 " S% S&\RV                  5      r4 " S' S(\5      r5 " S) S*\RV                  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    )CallableOptionalUnionN)nn)check_model_inputs   )ACT2FN)CacheDynamicCache)GenerationMixin)create_causal_mask!create_sliding_window_causal_mask)FlashAttentionKwargs) GenericForSequenceClassificationGenericForTokenClassificationGradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuple)deprecate_kwarg   )Starcoder2Configc                   v   ^  \ rS rSrS\4U 4S jjrS\\\R                        S\R                  4S jr
SrU =r$ )Starcoder2MLP5   configc                 D  > [         TU ]  5         UR                  n[        R                  " X!R
                  UR                  S9U l        [        R                  " UR
                  X!R                  S9U l        [        UR                     U l        UR                  U l        g )Nbias)super__init__hidden_sizer   Linearintermediate_sizeuse_biasc_fcc_projr	   
hidden_actactresidual_dropout)selfr#   	embed_dim	__class__s      l/home/james-whalen/.local/lib/python3.13/site-packages/transformers/models/starcoder2/modeling_starcoder2.pyr(   Starcoder2MLP.__init__6   sq    &&	IIi)A)AX	ii 8 8)//Z&++, & 7 7    hidden_statesreturnc                     U R                  U5      nU R                  U5      nU R                  U5      n[        R                  R                  XR                  U R                  S9nU$ )Nptraining)r-   r0   r.   r   
functionaldropoutr1   r=   )r2   r8   s     r5   forwardStarcoder2MLP.forward>   sX    		-0/M2--m?T?T_c_l_l-mr7   )r0   r-   r.   r1   )__name__
__module____qualname____firstlineno__r   r(   r   tupletorchFloatTensorr@   __static_attributes____classcell__r4   s   @r5   r!   r!   5   s>    8/ 8XeE4E4E.F%G EL]L]  r7   r!   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$ )z*Rotates half the hidden dims of the input..N   dim)shaperG   cat)xx1x2s      r5   rotate_halfrV   F   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r7   c                     UR                  U5      nUR                  U5      nX-  [        U 5      U-  -   nX-  [        U5      U-  -   nXg4$ )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.
)	unsqueezerV   )qkcossinposition_idsunsqueeze_dimq_embedk_embeds           r5   apply_rotary_pos_embra   M   sS    ( --
&C
--
&Cw;q>C/0Gw;q>C/0Gr7   r8   n_repr9   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)rQ   expandreshape)r8   rb   batchnum_key_value_headsslenhead_dims         r5   	repeat_kvrj   h   s_    
 2?1D1D.Ez!!Qa"23::5W\dlmM  e(CTTTr7   modulequerykeyvalueattention_maskscalingr?   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$ )NrN   r   rM   )rP   dtyper;   r   )rj   num_key_value_groupsrG   matmul	transposerQ   r   r>   softmaxfloat32tort   r?   r=   
contiguous)rk   rl   rm   rn   ro   rp   r?   rq   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r5   eager_attention_forwardr   t   s     3 ; ;<JU$?$?@L<<';';Aq'ABWLL!$Q1.D
0@0@0D.D%DE#1==((2U]](SVVW\WbWbcL==((6??([L,,|:K''1-88:K$$r7   c                   f  ^  \ 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                     \\\
R                        4   4S jj5       rSrU =r$ )Starcoder2Attention   z=Multi-headed attention from 'Attention Is All You Need' paperr#   	layer_idxc                   > [         TU ]  5         Xl        X l        [	        USS 5      =(       d    UR
                  UR                  -  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 l        g )Nri   g      Tr%   )r'   r(   r#   r   getattrr)   num_attention_headsri   rg   ru   rp   attention_dropout	is_causalr   r*   r,   q_projk_projv_projo_projr1   r2   r#   r   r4   s      r5   r(   Starcoder2Attention.__init__   sT   "
D9mV=O=OSYSmSm=m$*$>$>&B\B\$\!}}d*!'!9!9ii 2 2F4N4NQUQ^Q^4^eketetuii 2 2F4N4NQUQ^Q^4^eketetuii 2 2F4N4NQUQ^Q^4^eketetuii : :T]] JFL^L^eketetu & 7 7r7   past_key_valuepast_key_values4.58new_nameversionr8   position_embeddingsro   cache_positionrq   r9   c           
         UR                   S S n/ UQSPU R                  P7nU R                  U5      R                  U5      R	                  SS5      n	U R                  U5      R                  U5      R	                  SS5      n
U R                  U5      R                  U5      R	                  SS5      nUu  p[        XX5      u  pUb$  XUS.nUR                  XU R                  U5      u  p[        nU R                  R                  S:w  a  [        U R                  R                     nU" U U	U
UU4U R                  (       d  SOU R                  U R                   [#        U R                  SS 5      S.UD6u  nnUR$                  " / UQSP76 R'                  5       nU R)                  U5      n[*        R,                  R/                  UU R0                  U R                  S	9nUU4$ )
NrM   r   rN   )r\   r[   r   eager        sliding_window)r?   rp   r   r;   )rQ   ri   r   viewrw   r   r   ra   updater   r   r#   _attn_implementationr   r=   r   rp   r   re   r{   r   r   r>   r?   r1   )r2   r8   r   ro   r   r   rq   input_shapehidden_shapequery_statesr|   r}   r[   r\   cache_kwargsattention_interfacer   r~   s                     r5   r@   Starcoder2Attention.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$2H2HLL"4;;0@$G
%
 
%
!\ "));;;;FFHkk+.mm++4004== , 
 L((r7   )r   r#   ri   r   r   r   ru   r   r   r1   rp   r   N)NN)rB   rC   rD   rE   __doc__r   r   intr(   r   rG   TensorrF   r
   
LongTensorr   r   r@   rI   rJ   rK   s   @r5   r   r      s    G8/ 8HSM 8 8 %0A6R ,059.)||.) #5<<#=>.) !.	.)
 "%.) !!1!12.) -..) 
u||Xell3XeELL>Q5RR	S.) S.)r7   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$ )Starcoder2DecoderLayer   r#   r   c                 8  > [         TU ]  5         UR                  U l        [        XS9U l        [        U5      U l        [        R                  " UR                  UR                  S9U l
        [        R                  " UR                  UR                  S9U l        g )N)r#   r   eps)r'   r(   r)   r   	self_attnr!   mlpr   	LayerNormnorm_epsiloninput_layernormpost_attention_layernormr   s      r5   r(   Starcoder2DecoderLayer.__init__   sr    !--,FP (!||F,>,>FDWDWX(*V5G5GVM`M`(a%r7   r   r   r   r   r8   ro   r]   	use_cacher   r   rq   r9   c                     Un	U R                  U5      nU R                  " SUUUUUUUS.UD6u  pX-   nUn	U R                  U5      nU R                  U5      nX-   nU$ )N)r8   ro   r]   r   r   r   r    )r   r   r   r   )r2   r8   ro   r]   r   r   r   r   rq   residual_s              r5   r@   Starcoder2DecoderLayer.forward   s     !,,];>> 	
')%+) 3	
 	
 !0 !55mD/ 0r7   )r)   r   r   r   r   )NNNFNN)rB   rC   rD   rE   r   r   r(   r   rG   r   r   r   r
   boolrF   r   r   r@   rI   rJ   rK   s   @r5   r   r      s    b/ bC b %0A6R 2637+/$)59KO|| !. u//0	
 "% D> !!1!12 &eELL%,,,F&GH +, 
 Sr7   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$ )Starcoder2RotaryEmbedding   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defaultr   F)
persistent)r'   r(   hasattr
isinstancer   dictgetr   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenr#   r   rope_init_fnattention_scalingregister_bufferr   original_inv_freq)r2   r#   devicer   r4   s       r5   r(   "Starcoder2RotaryEmbedding.__init__  s    6>**z&:M:Mt/T/T#0044[&BUBUBYBYZ`BabDN&DN"("@"@$*$B$B!/?+/+<+<T[[&+Q((ZeD!%r7   c                 b   U R                   S S S 2S 4   R                  5       R                  UR                  S   SS5      R	                  UR
                  5      nUS S 2S S S 24   R                  5       n[        UR
                  R                  [        5      (       a0  UR
                  R                  S:w  a  UR
                  R                  OSn[        R                  " USS9   UR                  5       UR                  5       -  R                  SS5      n[        R                  " Xf4SS	9nUR                  5       U R                  -  nUR                  5       U R                  -  n	S S S 5        WR	                  UR                   S
9W	R	                  UR                   S
94$ ! , (       d  f       N@= f)Nr   rM   r   mpscpuF)device_typeenabledrN   rO   )rt   )r   floatrd   rQ   rz   r   r   r   strrG   autocastrw   rR   r[   r   r\   rt   )
r2   rS   r]   inv_freq_expandedposition_ids_expandedr   freqsembr[   r\   s
             r5   r@   !Starcoder2RotaryEmbedding.forward  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   $BF  
F.)r   r#   r   r   r   r   r   r   )rB   rC   rD   rE   rG   r   __annotations__r   r(   no_gradr   r@   rI   rJ   rK   s   @r5   r   r      sA    ll// / /" ]]_<  <r7   r   c                   R    \ rS rSr% \\S'   SrSrS/rS/r	Sr
SrSrSrSr\\S.rSrg	)
Starcoder2PreTrainedModeli"  r#   modelTr   r   )r8   
attentionsr   N)rB   rC   rD   rE   r   r   base_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_supports_sdpa_supports_flex_attn_can_compile_fullgraph_supports_attention_backendr   r   _can_record_outputsrI   r   r7   r5   r   r   "  sQ    &*#12#4"5N!"&/)r7   r   c                   <  ^  \ rS rSrS\4U 4S jjr\" 5              SS\\R                     S\\R                     S\\R                     S\\\\\R                     4      S\\R                     S	\\   S
\\R                     S\\   S\4S jj5       rSrU =r$ )Starcoder2Modeli5  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        [
        R                  " UR                  UR                  S9U l        [#        US9U l        SU l        UR(                  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   layersr   r   normr   
rotary_embgradient_checkpointingembedding_dropout	post_initr   s      r5   r(   Starcoder2Model.__init__7  s     !.. ++LL):):F<N<NPTP`P`ammHMfNfNfHghHg9#F6Hgh
 LL!3!39L9LM	36B&+#!'!9!9 	 is   D	input_idsro   r]   r   inputs_embedsr   r   rq   r9   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                  R                  c  [        O[        n
U
" U R                  UUUUUS9nUn[        R                  R                  XR                   U R"                  S9nU R%                  X5      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   )r   )r#   input_embedsro   r   r   r]   r;   )ro   r]   r   r   r   r   )last_hidden_stater   )
ValueErrorr   r   r#   get_seq_lengthrG   arangerQ   r   rX   r   r   r   r   r>   r?   r  r=   r  r   r   r   r   )r2   r  ro   r]   r   r  r   r   rq   past_seen_tokensmask_functionr   r8   r   decoder_layers                  r5   r@   Starcoder2Model.forwardH  s    -t";<YZZ  --i8M0*$++>O!CRC^==?de"\\ ]5H5H5K"KTaThThN )33A6L.2kk.H.H.P*Vw#;;&))+%
 &--33dmm . 

 #oomJ![[)H4;;+H+HIM)	*) /#-$7	 	M J 		-0&+/8O
 	
>B
 	
r7   )r   r  r  r   r   r   r  r   )NNNNNNN)rB   rC   rD   rE   r   r(   r   r   rG   r   r   r   r
   listrH   r   r   r   r   r@   rI   rJ   rK   s   @r5   r   r   5  s    / "  151537KO59$(59?
E,,-?
 !.?
 u//0	?

 "%tE4E4E/F(F"GH?
   1 12?
 D>?
 !!1!12?
 +,?
 
!?
 ?
r7   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$ )Starcoder2ForCausalLMi  zlm_head.weightlm_headcolwise_repr8   logitsc                    > [         TU ]  U5        [        U5      U l        UR                  U l        [
        R                  " UR                  UR                  SS9U l        U R                  5         g )NFr%   )
r'   r(   r   r   r   r   r*   r)   r  r  )r2   r#   r4   s     r5   r(   Starcoder2ForCausalLM.__init__  sU     $V,
 ++yy!3!3V5F5FUS 	r7   r  ro   r]   r   r  labelsr   r   logits_to_keeprq   r9   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, Starcoder2ForCausalLM

>>> model = Starcoder2ForCausalLM.from_pretrained("meta-starcoder2/Starcoder2-2-7b-hf")
>>> tokenizer = AutoTokenizer.from_pretrained("meta-starcoder2/Starcoder2-2-7b-hf")

>>> 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  ro   r]   r   r  r   r   N)r  r  r   )lossr  r   r8   r   r   )r   r
  r   r   slicer  loss_functionr#   r   r   r   r8   r   )r2   r  ro   r]   r   r  r  r   r   r  rq   outputsr8   slice_indicesr  r  s                   r5   r@   Starcoder2ForCausalLM.forward  s    @ ,0:: 	,
)%+')	,
 	,
  118B>SV8W8W~ot4]kmA}a,?@A%%pVt{{OeOepiopD%#33!//))
 	
r7   )r  r   r   )	NNNNNNNNr   )rB   rC   rD   rE   _tied_weights_keys_tp_plan_pp_planr(   r   r   r   rG   r   r   r
   rH   r   r   r   r   r   r   r@   rI   rJ   rK   s   @r5   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
r7   r  c                       \ rS rSrSrg)#Starcoder2ForSequenceClassificationi  r   NrB   rC   rD   rE   rI   r   r7   r5   r'  r'        r7   r'  c                       \ rS rSrSrg) Starcoder2ForTokenClassificationi  r   Nr(  r   r7   r5   r+  r+    r)  r7   r+  )r  r   r   r'  r+  )Nr   )r   )=typingr   r   r   rG   r   transformers.utils.genericr   activationsr	   cache_utilsr
   r   
generationr   masking_utilsr   r   modeling_flash_attention_utilsr   modeling_layersr   r   r   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.deprecationr   configuration_starcoder2r   Moduler!   rV   ra   r   r   rj   r   r   r   r   r   r   r   r  r'  r+  __all__r   r7   r5   <module>r=     s  6 - ,   9 ! . ) R B 
 P K F & I I 0 6BII "(6	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 U\\*% % % '(%4A)")) A)H)7 )X!<		 !<H   $ R
/ R
 R
j H
5 H
 H
V	*JLe 		'DF_ 	r7   