
    Z j"U                     X   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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$J%r%J&r&J'r'  SSK(J)r)J*r*  SSK+J,r,  SSK-J.r.   " S S\R^                  5      r0S r1\" S5      S9S j5       r2S\Rf                  S\4S\Rf                  4S jr5 S:S\R^                  S \Rf                  S!\Rf                  S"\Rf                  S#\Rf                  S-  S$\6S%\6S&\#\%   4S' jjr7\" \25       " S( S)\R^                  5      5       r8 " S* S+\5      r9\& " S, S-\!5      5       r: " S. S/\R^                  5      r;\& " S0 S1\:5      5       r<\& " S2 S3\:\5      5       r= " S4 S5\\:5      r> " S6 S7\\:5      r?/ S8Qr@g);    )Callable)OptionalN)nn   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_func_from_hubuse_kernelized_func)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)maybe_autocastmerge_with_config_defaults)capture_outputs   )Starcoder2Configc                   v   ^  \ rS rSrS\4U 4S jjrS\\R                     S-  S\R                  4S jr	Sr
U =r$ )	Starcoder2MLP5   configc                 D  > [         TU ]  5         UR                  n[        R                  " X!R
                  UR                  S9U l        [        R                  " UR
                  X!R                  S9U l        [        UR                     U l        UR                  U l        g )Nbias)super__init__hidden_sizer   Linearintermediate_sizeuse_biasc_fcc_projr   
hidden_actactresidual_dropout)selfr%   	embed_dim	__class__s      ڃ/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/starcoder2/modeling_starcoder2.pyr*   Starcoder2MLP.__init__6   sq    &&	IIi)A)AX	ii 8 8)//Z&++, & 7 7    hidden_statesNreturnc                     U R                  U5      nU R                  U5      nU R                  U5      n[        R                  R                  XR                  U R                  S9nU$ )Nptraining)r/   r2   r0   r   
functionaldropoutr3   r?   )r4   r:   s     r7   forwardStarcoder2MLP.forward>   sX    		-0/M2--m?T?T_c_l_l-mr9   )r2   r/   r0   r3   )__name__
__module____qualname____firstlineno__r!   r*   tupletorchFloatTensorrB   __static_attributes____classcell__r6   s   @r7   r#   r#   5   s>    8/ 8U5+<+<%=%D IZIZ  r9   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$ )z*Rotates half the hidden dims of the input..N   dim)shaperI   cat)xx1x2s      r7   rotate_halfrX   F   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r9   rotary_pos_embc                     UR                  U5      nUR                  U5      nX-  [        U 5      U-  -   nX-  [        U5      U-  -   nXV4$ )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.
)	unsqueezerX   )qkcossinunsqueeze_dimq_embedk_embeds          r7   apply_rotary_pos_embrc   M   sS    & --
&C
--
&Cw;q>C/0Gw;q>C/0Gr9   r:   n_repr;   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)rS   expandreshape)r:   rd   batchnum_key_value_headsslenhead_dims         r7   	repeat_kvrl   g   s_    
 2?1D1D.Ez!!Qa"23::5W\dlmM  e(CTTTr9   modulequerykeyvalueattention_maskscalingrA   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$ )NrP   r   rO   )rR   dtyper=   r    )rl   num_key_value_groupsrI   matmul	transposer   r@   softmaxfloat32toru   rA   r?   
contiguous)rm   rn   ro   rp   rq   rr   rA   rs   
key_statesvalue_statesattn_weightsattn_outputs               r7   eager_attention_forwardr   s   s     3 ; ;<JU$?$?@L<<';';Aq'ABWLL!#4==((2U]](SVVW\WbWbcL==((6??([L,,|:K''1-88:K$$r9   c                   0  ^  \ 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	\R                  S-  S
\S-  S\\   S\
\R                  \R                  S-  \
\R                     S-  4   4S jjrSrU =r$ )Starcoder2Attention   z=Multi-headed attention from 'Attention Is All You Need' paperNr%   	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 )Nrk   g      Tr'   )r)   r*   r%   r   getattrr+   num_attention_headsrk   ri   rv   rr   attention_dropout	is_causalr   r,   r.   q_projk_projv_projo_projr3   r4   r%   r   r6   s      r7   r*   Starcoder2Attention.__init__   sT   "
D9mV=O=OSYSmSm=m$*$>$>&B\B\$\!}}d*!'!9!9ii 2 2F4N4NQUQ^Q^4^eketetuii 2 2F4N4NQUQ^Q^4^eketetuii 2 2F4N4NQUQ^Q^4^eketetuii : :T]] JFL^L^eketetu & 7 7r9   r:   position_embeddingsrq   past_key_valuesrs   r;   c           
         UR                   S S n/ UQSPU R                  P7nU R                  U5      R                  U5      R	                  SS5      nU R                  U5      R                  U5      R	                  SS5      n	U R                  U5      R                  U5      R	                  SS5      n
Uu  p[        XX5      u  pUb  UR                  XU R                  5      u  p[        R                  " U R                  R                  [        5      nU" U UU	U
U4U R                  (       d  SOU R                   U R"                  [%        U R                  SS 5      S.UD6u  pUR&                  " / UQSP76 R)                  5       nU R+                  U5      n[,        R.                  R1                  XR2                  U R                  S9nX4$ )NrO   r    rP           sliding_window)rA   rr   r   r=   )rS   rk   r   viewrx   r   r   rc   updater   r   get_interfacer%   _attn_implementationr   r?   r   rr   r   rg   r|   r   r   r@   rA   r3   )r4   r:   r   rq   r   rs   input_shapehidden_shapequery_statesr}   r~   r^   r_   attention_interfacer   r   s                   r7   rB   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#[ &'6'='=jX\XfXf'g$J(?(M(MKK,,.E)
 %8
%
  $}}C$2H2HLL"4;;0@$G
%
 
%
! "));;;;FFHkk+.mm++004== , 
 ((r9   )r   r%   rk   r   r   r   rv   r   r   r3   rr   r   N)rD   rE   rF   rG   __doc__r!   intr*   rI   TensorrH   r   r   r   rB   rK   rL   rM   s   @r7   r   r      s    G8/ 8C$J 8 8( )-+)||+) #5<<#=>+) t+	+)
 +) -.+) 
u||U\\D0%2E2LL	M+) +)r9   r   c                     ^  \ rS rSrS\S\4U 4S jjr     SS\R                  S\R                  S-  S\R                  S-  S	\
S-  S
\S-  S\\R                  \R                  4   S-  S\\   S\R                  4S jjrSrU =r$ )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      r7   r*   Starcoder2DecoderLayer.__init__   sr    !--,FP (!||F,>,>FDWDWX(*V5G5GVM`M`(a%r9   Nr:   rq   position_idsr   	use_cacher   rs   r;   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$ )N)r:   rq   r   r   r   r    )r   r   r   r   )
r4   r:   rq   r   r   r   r   rs   residual_s
             r7   rB   Starcoder2DecoderLayer.forward   s     !,,];>> 
')%+ 3
 
 !0 !55mD/ 0r9   )r+   r   r   r   r   )NNNFN)rD   rE   rF   rG   r!   r   r*   rI   r   
LongTensorr   boolrH   r   r   rB   rK   rL   rM   s   @r7   r   r      s    b/ bC b /304(,!&HL|| t+ &&-	
  $; #5<<#=>E +, 
 r9   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	)
Starcoder2PreTrainedModel   r%   modelTr   r   )r:   
attentionsr   N)rD   rE   rF   rG   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_outputsrK   r   r9   r7   r   r      sQ    &*#12#4"5N!"&/)r9   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$ )Starcoder2RotaryEmbeddingi	  inv_freqNr%   c                   > [         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defaultr   F)
persistentoriginal_inv_freq)r)   r*   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenr%   rope_parametersr   compute_default_rope_parametersr   attention_scalingregister_bufferclone)r4   r%   devicerope_init_fnr   r6   s        r7   r*   "Starcoder2RotaryEmbedding.__init__  s    "("@"@$*$B$B!44[A!%!E!E>>Y&.t~~>L+7V+L((ZeD0(..2BuUr9   r   ztorch.deviceseq_lenr;   ztorch.Tensorc           	         U R                   S   n[        U SS5      =(       d    U R                  U R                  -  nSnSU[        R
                  " SUS[        R                  S9R                  U[        R                  S9U-  -  -  nXe4$ )	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_thetark   Ng      ?r   rP   ru   )r   ru   )	r   r   r+   r   rI   arangeint64r{   float)r%   r   r   baserR   attention_factorr   s          r7   r   9Starcoder2RotaryEmbedding.compute_default_rope_parameters  s    & %%l3fj$/c63E3EIcIc3c U\\!S!5;;?BB&X]XcXcBdgjjk
 ))r9   c                 L   U R                   S S S 2S 4   R                  5       R                  UR                  S   SS5      R	                  UR
                  5      nUS S 2S S S 24   R                  5       n[        UR
                  R                  [        5      (       a0  UR
                  R                  S:w  a  UR
                  R                  OSn[        USS9   UR                  5       UR                  5       -  R                  SS5      n[        R                  " Xf4SS	9nUR                  5       U R                  -  nUR                  5       U R                  -  n	S S S 5        WR	                  UR                   S
9W	R	                  UR                   S
94$ ! , (       d  f       N@= f)Nr   rO   r    mpscpuF)device_typeenabledrP   rQ   r   )r   r   rf   rS   r{   r   
isinstancetypestrr   rx   rI   rT   r^   r   r_   ru   )
r4   rU   r   inv_freq_expandedposition_ids_expandedr   freqsembr^   r_   s
             r7   rB   !Starcoder2RotaryEmbedding.forward:  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   r%   r   r   r   r   )NNN)rD   rE   rF   rG   rI   r   r   r!   r*   staticmethodr   r   rH   r   r   no_gradr   rB   rK   rL   rM   s   @r7   r   r   	  s    llV/ V V  *.+/"* 4'*(* t* 
~u$	%	* *: ]]_<  <r9   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       rSrU =r$ )Starcoder2ModeliJ  r%   c           	      @  > [         TU ]  U5        UR                  U l        UR                  U l        [
        R                  " UR                  UR                  U R                  5      U l        [
        R                  " [        UR                  5       Vs/ s H  n[        X5      PM     sn5      U l        [
        R                  " UR                  UR                  S9U l        [#        US9U l        SU l        UR(                  U l        U R+                  5         g s  snf )Nr   r%   F)r)   r*   pad_token_idpadding_idx
vocab_sizer   	Embeddingr+   embed_tokens
ModuleListrangenum_hidden_layersr   layersr   r   normr   
rotary_embgradient_checkpointingembedding_dropout	post_initr   s      r7   r*   Starcoder2Model.__init__L  s     !.. ++LL):):F<N<NPTP`P`ammHMfNfNfHghHg9#F6Hgh
 LL!3!39L9LM	36B&+#!'!9!9 	 is   DN	input_idsrq   r   r   inputs_embedsr   rs   r;   c           
         US L US L-  (       a  [        S5      eUc  U R                  U5      nU(       a  Uc  [        U R                  S9nUcU  Ub  UR	                  5       OSn[
        R                  " UR                  S   UR                  S9U-   nUR                  S5      nU R                  R                  c  [        O[        n	U	" U R                  UUUUS9n
Un[        R                  R                  XR                   U R"                  S9nU R%                  XS9nU R&                  S U R                  R(                    H  nU" U4U
UUUUS	.UD6nM     U R+                  U5      n[-        UU(       a  US
9$ S S
9$ )Nz:You must specify exactly one of input_ids or inputs_embedsr   r   r    )r   )r%   r	  rq   r   r   r=   )r   )rq   r   r   r   r   )last_hidden_stater   )
ValueErrorr   r	   r%   get_seq_lengthrI   r   rS   r   r[   r   r   r   r   r@   rA   r  r?   r  r  r   r  r   )r4   r  rq   r   r   r	  r   rs   past_seen_tokensmask_functioncausal_maskr:   r   decoder_layers                 r7   rB   Starcoder2Model.forward]  s    -t";<YZZ  --i8M0*$++>OCRC^==?de <<(;(;A(>}G[G[\_ooL'11!4L.2kk.H.H.P*Vw#;;')+%
 &--33dmm . 
 #oomoW![[)H4;;+H+HIM)*) /#$7 M J 		-0&+/8O
 	
>B
 	
r9   )r   r  r  r  r  r   r  r   )NNNNNN)rD   rE   rF   rG   r!   r*   r   r   rI   r   r   r   rJ   r   r   r   rH   r   rB   rK   rL   rM   s   @r7   r   r   J  s    / "   .2.204(,26!%7
##d*7
 t+7
 &&-	7

 7
 ((4/7
 $;7
 +,7
 
(	(7
   7
r9   r   c                   P  ^  \ rS rSrSS0rSS0rSS/S/40rU 4S jr\\	        SS
\
R                  S	-  S\
R                  S	-  S\
R                  S	-  S\S	-  S\
R                  S	-  S\
R                  S	-  S\S	-  S\\
R                  -  S\\   S\4S jj5       5       rSrU =r$ )Starcoder2ForCausalLMi  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  )r4   r%   r6   s     r7   r*   Starcoder2ForCausalLM.__init__  sU     $V,
 ++yy!3!3V5F5FUS 	r9   Nr  rq   r   r   r	  labelsr   logits_to_keeprs   r;   c	           
      |   U R                   " SUUUUUUS.U	D6n
U
R                  n[        U[        5      (       a  [	        U* S5      OUnU R                  USS2USS24   5      nSnUb)  U R                  " SXU R                  R                  S.U	D6n[        UUU
R                  U
R                  U
R                  S9$ )a  
Example:

```python
>>> from transformers import AutoTokenizer, 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  rq   r   r   r	  r   N)r  r  r   )lossr  r   r:   r   r   )r   r  r   r   slicer  loss_functionr%   r   r   r   r:   r   )r4   r  rq   r   r   r	  r  r   r  rs   outputsr:   slice_indicesr  r  s                  r7   rB   Starcoder2ForCausalLM.forward  s    > ,0:: ,
)%+',
 ,
  118B>SV8W8W~ot4]kmA}a,?@A%%pVt{{OeOepiopD%#33!//))
 	
r9   )r  r   r   )NNNNNNNr   )rD   rE   rF   rG   _tied_weights_keys_tp_plan_pp_planr*   r   r   rI   r   r   r   rJ   r   r   r   r   r   rB   rK   rL   rM   s   @r7   r  r    s   *,GH23H_-z:;H  .2.204(,26*.!%-.6
##d*6
 t+6
 &&-	6

 6
 ((4/6
   4'6
 $;6
 ell*6
 +,6
 
 6
  6
r9   r  c                       \ rS rSrSrg)#Starcoder2ForSequenceClassificationi  r   NrD   rE   rF   rG   rK   r   r9   r7   r'  r'        r9   r'  c                       \ rS rSrSrg) Starcoder2ForTokenClassificationi  r   Nr(  r   r9   r7   r+  r+    r)  r9   r+  )r  r   r   r'  r+  )r    )r   )Acollections.abcr   typingr   rI   r   activationsr   cache_utilsr   r	   
generationr
   integrationsr   r   masking_utilsr   r   modeling_flash_attention_utilsr   modeling_layersr   r   r   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.genericr   r   utils.output_capturingr   configuration_starcoder2r!   Moduler#   rX   rc   r   r   rl   r   r   r   r   r   r   r   r  r'  r+  __all__r   r9   r7   <module>r?     s  4 %    ! . ) I R B 
 P K F & I I G 5 6BII "( *+ ,2	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 LL4'% % % '(%2 )*=)")) =) +=)@&7 &R   $><		 ><B K
/ K
 K
\ F
5 F
 F
R	*JLe 		'DF_ 	r9   