
    <hoS                        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\RR                  5      r*S r+S5S jr,S\RZ                  S\.S\RZ                  4S jr/ S6S\RR                  S\RZ                  S\RZ                  S\RZ                  S\\RZ                     S \0S!\0S"\"\$   4S# jjr1 " S$ S%\RR                  5      r2 " S& S'\5      r3 " S( S)\RR                  5      r4\% " S* S+\ 5      5       r5\% " S, S-\55      5       r6\% " S. S/\5\5      5       r7 " S0 S1\\55      r8 " S2 S3\\55      r9/ S4Qr:g)7    )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   )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$ )Starcoder2MLP4   configc                 D  > [         TU ]  5         UR                  n[        R                  " X!R
                  UR                  S9U l        [        R                  " UR
                  X!R                  S9U l        [        UR                     U l        UR                  U l        g )Nbias)super__init__hidden_sizer   Linearintermediate_sizeuse_biasc_fcc_projr	   
hidden_actactresidual_dropout)selfr"   	embed_dim	__class__s      j/var/www/html/shao/venv/lib/python3.13/site-packages/transformers/models/starcoder2/modeling_starcoder2.pyr'   Starcoder2MLP.__init__5   sq    &&	IIi)A)AX	ii 8 8)//Z&++, & 7 7    hidden_statesreturnc                     U R                  U5      nU R                  U5      nU R                  U5      n[        R                  R                  XR                  U R                  S9nU$ )Nptraining)r,   r/   r-   r   
functionaldropoutr0   r<   )r1   r7   s     r4   forwardStarcoder2MLP.forward=   sX    		-0/M2--m?T?T_c_l_l-mr6   )r/   r,   r-   r0   )__name__
__module____qualname____firstlineno__r   r'   r   tupletorchFloatTensorr?   __static_attributes____classcell__r3   s   @r4   r    r    4   s>    8/ 8XeE4E4E.F%G EL]L]  r6   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$ )z*Rotates half the hidden dims of the input..N   dim)shaperF   cat)xx1x2s      r4   rotate_halfrU   E   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r6   c                     UR                  U5      nUR                  U5      nX-  [        U 5      U-  -   nX-  [        U5      U-  -   nXg4$ )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.
)	unsqueezerU   )qkcossinposition_idsunsqueeze_dimq_embedk_embeds           r4   apply_rotary_pos_embr`   L   sS    ( --
&C
--
&Cw;q>C/0Gw;q>C/0Gr6   r7   n_repr8   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)rP   expandreshape)r7   ra   batchnum_key_value_headsslenhead_dims         r4   	repeat_kvri   g   s_    
 2?1D1D.Ez!!Qa"23::5W\dlmM  e(CTTTr6   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$ )NrM   r   rL   )rO   dtyper:   r   )ri   num_key_value_groupsrF   matmul	transposerP   r   r=   softmaxfloat32tors   r>   r<   
contiguous)rj   rk   rl   rm   rn   ro   r>   rp   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r4   eager_attention_forwardr   s   s     3 ; ;<JU$?$?@L<<';';Aq'ABWLL!$Q1.D
0@0@0D.D%DE#1==((2U]](SVVW\WbWbcL==((6??([L,,|:K''1-88:K$$r6   c                   P  ^  \ rS rSrSrSS\S\\   4U 4S jjjr  SS\	R                  S\\	R                  \	R                  4   S\\	R                     S	\\   S
\\	R                     S\\   S\\	R                  \\	R                     \\\	R                        4   4S jjrSrU =r$ )Starcoder2Attention   z=Multi-headed attention from 'Attention Is All You Need' paperr"   	layer_idxc                   > [         TU ]  5         Xl        X l        [	        USS 5      =(       d    UR
                  UR                  -  U l        UR                  UR                  -  U l	        U R                  S-  U l
        UR                  U l        SU l        [        R                  " UR
                  UR                  U R                  -  UR                  S9U l        [        R                  " UR
                  UR                  U R                  -  UR                  S9U l        [        R                  " UR
                  UR                  U R                  -  UR                  S9U l        [        R                  " UR                  U R                  -  UR
                  UR                  S9U l        UR(                  U l        g )Nrh   g      Tr$   )r&   r'   r"   r   getattrr(   num_attention_headsrh   rf   rt   ro   attention_dropout	is_causalr   r)   r+   q_projk_projv_projo_projr0   r1   r"   r   r3   s      r4   r'   Starcoder2Attention.__init__   sT   "
D9mV=O=OSYSmSm=m$*$>$>&B\B\$\!}}d*!'!9!9ii 2 2F4N4NQUQ^Q^4^eketetuii 2 2F4N4NQUQ^Q^4^eketetuii 2 2F4N4NQUQ^Q^4^eketetuii : :T]] JFL^L^eketetu & 7 7r6   r7   position_embeddingsrn   past_key_valuecache_positionrp   r8   c           
         UR                   S S n/ UQSPU R                  P7nU R                  U5      R                  U5      R	                  SS5      n	U R                  U5      R                  U5      R	                  SS5      n
U R                  U5      R                  U5      R	                  SS5      nUu  p[        XX5      u  pUb$  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$                  " / UQSP76 R'                  5       nU R)                  U5      n[*        R,                  R/                  UU R0                  U R                  S	9nUU4$ )
NrL   r   rM   )r[   rZ   r   eager        sliding_window)r>   ro   r   r:   )rP   rh   r   viewrv   r   r   r`   updater   r   r"   _attn_implementationr   r<   r   ro   r   rd   rz   r   r   r=   r>   r0   )r1   r7   r   rn   r   r   rp   input_shapehidden_shapequery_statesr{   r|   rZ   r[   cache_kwargsattention_interfacer   r}   s                     r4   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'5'<'<ZW[WeWegs't$J(?;;++w6"9$++:Z:Z"[$7
%
  $}}C$2H2HLL"4;;0@$G
%
 
%
!\ "));;;;FFHkk+.mm++4004== , 
 L((r6   )r   r"   rh   r   r   r   rt   r   r   r0   ro   r   N)NN)rA   rB   rC   rD   __doc__r   r   intr'   rF   TensorrE   r
   
LongTensorr   r   r?   rH   rI   rJ   s   @r4   r   r      s    G8/ 8HSM 8 8( +/59.)||.) #5<<#=>.) !.	.)
 !.) !!1!12.) -..) 
u||Xell3XeELL>Q5RR	S.) .)r6   r   c                   8  ^  \ rS rSrS\S\4U 4S jjr      SS\R                  S\	\R                     S\	\R                     S\	\   S	\	\   S
\	\R                     S\	\\R                  \R                  4      S\\   S\\R                     4S jjrSrU =r$ )Starcoder2DecoderLayer   r"   r   c                 8  > [         TU ]  5         UR                  U l        [        XS9U l        [        U5      U l        [        R                  " UR                  UR                  S9U l
        [        R                  " UR                  UR                  S9U l        g )N)r"   r   eps)r&   r'   r(   r   	self_attnr    mlpr   	LayerNormnorm_epsiloninput_layernormpost_attention_layernormr   s      r4   r'   Starcoder2DecoderLayer.__init__   sr    !--,FP (!||F,>,>FDWDWX(*V5G5GVM`M`(a%r6   r7   rn   r\   r   	use_cacher   r   rp   r8   c                     Un	U R                  U5      nU R                  " SUUUUUUUS.UD6u  pX-   nUn	U R                  U5      nU R                  U5      nX-   nU$ )N)r7   rn   r\   r   r   r   r    )r   r   r   r   )r1   r7   rn   r\   r   r   r   r   rp   residual_s              r4   r?   Starcoder2DecoderLayer.forward   s     !,,];>> 	
')%)) 3	
 	
 !0 !55mD/ 0r6   )r(   r   r   r   r   )NNNFNN)rA   rB   rC   rD   r   r   r'   rF   r   r   r   r
   boolrE   r   r   r?   rH   rI   rJ   s   @r4   r   r      s    b/ bC b 2637*.$)59KO|| !. u//0	
 ! D> !!1!12 &eELL%,,,F&GH +, 
u||	 r6   r   c                   l   ^  \ rS rSrSS\4U 4S jjjr\R                  " 5       \S 5       5       r	Sr
U =r$ )Starcoder2RotaryEmbedding   r"   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defaultinv_freqF)
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)r1   r"   devicer   r3   s       r4   r'   "Starcoder2RotaryEmbedding.__init__   s    6>**z&:M:Mt/T/T#0044[&BUBUBYBYZ`BabDN&DN"("@"@$*$B$B!/?+/+<+<T[[&+Q((ZeD!%r6   c                 b   U R                   S S S 2S 4   R                  5       R                  UR                  S   SS5      R	                  UR
                  5      nUS S 2S S S 24   R                  5       n[        UR
                  R                  [        5      (       a0  UR
                  R                  S:w  a  UR
                  R                  OSn[        R                  " USS9   UR                  5       UR                  5       -  R                  SS5      n[        R                  " Xf4SS	9nUR                  5       U R                  -  nUR                  5       U R                  -  n	S S S 5        WR	                  UR                   S
9W	R	                  UR                   S
94$ ! , (       d  f       N@= f)Nr   rL   r   mpscpuF)device_typeenabledrM   rN   )rs   )r   floatrc   rP   ry   r   r   r   strrF   autocastrv   rQ   rZ   r   r[   rs   )
r1   rR   r\   inv_freq_expandedposition_ids_expandedr   freqsembrZ   r[   s
             r4   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   $BF  
F.)r   r"   r   r   r   r   r   r   )rA   rB   rC   rD   r   r'   rF   no_gradr   r?   rH   rI   rJ   s   @r4   r   r      s7    // / /" ]]_<  <r6   r   c                   R    \ rS rSr% \\S'   SrSrS/rS/r	Sr
SrSrSrSr\\S.rSrg	)
Starcoder2PreTrainedModeli  r"   modelTr   past_key_values)r7   
attentionsr   N)rA   rB   rC   rD   r   __annotations__base_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_supports_sdpa_supports_flex_attn_can_compile_fullgraph_supports_attention_backendr   r   _can_record_outputsrH   r   r6   r4   r   r     sQ    &*#12#4"5N!"&/)r6   r   c                   2  ^  \ rS rSrS\4U 4S jjr\       SS\\R                     S\\R                     S\\R                     S\\\\\R                     4      S\\R                     S	\\   S
\\R                     S\\   S\4S jj5       rSrU =r$ )Starcoder2Modeli0  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      r4   r'   Starcoder2Model.__init__2  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_idsrn   r\   r   inputs_embedsr   r   rp   r8   c                    US L US L-  (       a  [        S5      eUc  U R                  U5      nU(       a  Uc
  [        5       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"   input_embedsrn   r   r   r\   r:   )rn   r\   r   r   r   r   )last_hidden_stater   )
ValueErrorr   r   get_seq_lengthrF   arangerP   r   rW   r"   r   r   r   r   r=   r>   r   r<   r   r   r   r   r   )r1   r   rn   r\   r   r  r   r   rp   past_seen_tokensmask_functionr~   r7   r   decoder_layers                  r4   r?   Starcoder2Model.forwardC  s    -t";<YZZ  --i8M0*nO!CRC^==?de"\\ ]5H5H5K"KTaThThN )33A6L.2kk.H.H.P*Vw#;;&))+%
 &--33dmm . 

 #oomJ![[)H4;;+H+HIM)	*).#-$7	 	M J 		-0&+/8O
 	
>B
 	
r6   )r   r   r   r   r   r   r   r   )NNNNNNN)rA   rB   rC   rD   r   r'   r   r   rF   r   r   r   r
   listrG   r   r   r   r   r?   rH   rI   rJ   s   @r4   r   r   0  s    / "  151537KO59$(59?
E,,-?
 !.?
 u//0	?

 "%tE4E4E/F(F"GH?
   1 12?
 D>?
 !!1!12?
 +,?
 
!?
 ?
r6   r   c                   ~  ^  \ rS rSrS/rSS0rSS/S/40rU 4S jrS rS	 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$ )Starcoder2ForCausalLMi  zlm_head.weightlm_headcolwise_repr7   logitsc                    > [         TU ]  U5        [        U5      U l        UR                  U l        [
        R                  " UR                  UR                  SS9U l        U R                  5         g )NFr$   )
r&   r'   r   r   r   r   r)   r(   r  r   )r1   r"   r3   s     r4   r'   Starcoder2ForCausalLM.__init__  sU     $V,
 ++yy!3!3V5F5FUS 	r6   c                     Xl         g r   r   )r1   decoders     r4   set_decoder!Starcoder2ForCausalLM.set_decoder  s    
r6   c                     U R                   $ r   r  )r1   s    r4   get_decoder!Starcoder2ForCausalLM.get_decoder  s    zzr6   r   rn   r\   r   r  labelsr   r   logits_to_keeprp   r8   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   rn   r\   r   r  r   r   N)r  r  r   )lossr  r   r7   r   r   )r   r  r   r   slicer  loss_functionr"   r   r   r   r7   r   )r1   r   rn   r\   r   r  r  r   r   r  rp   outputsr7   slice_indicesr  r  s                   r4   r?   Starcoder2ForCausalLM.forward  s    @ ,0:: 	,
)%+')	,
 	,
  118B>SV8W8W~ot4]kmA}a,?@A%%pVt{{OeOepiopD%#33!//))
 	
r6   )r  r   r   )	NNNNNNNNr   )rA   rB   rC   rD   _tied_weights_keys_tp_plan_pp_planr'   r  r  r   r   r   rF   r   r   r
   rG   r   r   r   r   r   r   r?   rH   rI   rJ   s   @r4   r  r    s:   *+=)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
r6   r  c                       \ rS rSrSrg)#Starcoder2ForSequenceClassificationi  r   NrA   rB   rC   rD   rH   r   r6   r4   r)  r)        r6   r)  c                       \ rS rSrSrg) Starcoder2ForTokenClassificationi  r   Nr*  r   r6   r4   r-  r-    r+  r6   r-  )r  r   r   r)  r-  )Nr   )r   );typingr   r   r   rF   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   configuration_starcoder2r   Moduler    rU   r`   r   r   ri   r   r   r   r   r   r   r   r  r)  r-  __all__r   r6   r4   <module>r>     s  6 - ,   9 ! . ) R B 
 P K F & I I 6BII "(6	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 U\\*% % % '(%4@)")) @)F(7 (V<		 <D   $ R
/ R
 R
j N
5 N
 N
b	*JLe 		'DF_ 	r6   