
    Z jR                        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Jr  SS
KJr  SSKJr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&J'r'  SSK(J)r)J*r*  SSK+J,r,  SSK-J.r.  \'R^                  " \05      r1\" S5       " S S\Rd                  5      5       r3 " S S\Rd                  5      r4S r5\" S5      S=S j5       r6 " S S\Rd                  5      r7S\Rp                  S \9S!\Rp                  4S" jr: S>S#\Rd                  S$\Rp                  S%\Rp                  S&\Rp                  S'\Rp                  S-  S(\;S)\;S*\"\$   4S+ jjr<\" \65       " S, S-\Rd                  5      5       r= " S. S/\5      r>\% " S0 S1\ 5      5       r?\% " S2 S3\?5      5       r@\% " S4 S5\?\5      5       rA " S6 S7\\?5      rB " S8 S9\\?5      rC " S: S;\\?5      rD/ S<QrEg)?    )Callable)OptionalN)nn   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_forward_from_hubuse_kernel_func_from_hubuse_kernelized_func)create_causal_mask)GenericForQuestionAnswering GenericForSequenceClassificationGenericForTokenClassificationGradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuplelogging)maybe_autocastmerge_with_config_defaults)capture_outputs   )LlamaConfigRMSNormc                   x   ^  \ rS rSrS
S\SS4U 4S jjjrS\R                  S\R                  4S jrS r	S	r
U =r$ )LlamaRMSNorm4   epsreturnNc                    > [         TU ]  5         [        R                  " [        R
                  " U5      5      U l        X l        g)z+
LlamaRMSNorm is equivalent to T5LayerNorm
N)super__init__r   	Parametertorchonesweightvariance_epsilon)selfhidden_sizer'   	__class__s      y/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/llama/modeling_llama.pyr+   LlamaRMSNorm.__init__6   s/     	ll5::k#:; #    hidden_statesc                    UR                   nUR                  [        R                  5      nUR	                  S5      R                  SSS9nU[        R                  " X0R                  -   5      -  nU R                  UR                  U5      -  $ )N   T)keepdim)	dtypetor-   float32powmeanrsqrtr0   r/   )r1   r7   input_dtypevariances       r4   forwardLlamaRMSNorm.forward>   sw    #))%((7 $$Q',,R,>%H?T?T4T(UU{{]--k:::r6   c                 ^    [        U R                  R                  5       SU R                   3$ )Nz, eps=)tupler/   shaper0   )r1   s    r4   
extra_reprLlamaRMSNorm.extra_reprE   s*    ))*+6$2G2G1HIIr6   )r0   r/   )gư>)__name__
__module____qualname____firstlineno__floatr+   r-   TensorrD   rI   __static_attributes____classcell__r3   s   @r4   r%   r%   4   sB    $ $$ $ $;U\\ ;ell ;J Jr6   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$ )LlamaRotaryEmbeddingI   inv_freqNconfigc                   > [         TU ]  5         UR                  U l        UR                  U l        Xl        U R
                  R                  S   U l        U R                  nU R                  S:w  a  [        U R                     nU" U R
                  U5      u  o@l
        U R                  SUSS9  U R                  SUR                  5       SS9  g )N	rope_typedefaultrW   F)
persistentoriginal_inv_freq)r*   r+   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrX   rope_parametersrZ   compute_default_rope_parametersr   attention_scalingregister_bufferclone)r1   rX   devicerope_init_fnrW   r3   s        r4   r+   LlamaRotaryEmbedding.__init__L   s    "("@"@$*$B$B!44[A!%!E!E>>Y&.t~~>L+7V+L((ZeD0(..2BuUr6   rf   ztorch.deviceseq_lenr(   ztorch.Tensorc           	         U R                   S   n[        U SS5      =(       d    U R                  U R                  -  nSnSU[        R
                  " SUS[        R                  S9R                  U[        R                  S9U-  -  -  nXe4$ )	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_thetahead_dimNg      ?r   r9   r<   )rf   r<   )	ra   getattrr2   num_attention_headsr-   arangeint64r=   rO   )rX   rf   ri   basedimattention_factorrW   s          r4   rb   4LlamaRotaryEmbedding.compute_default_rope_parameters\   s    & %%l3fj$/c63E3EIcIc3c U\\!S!5;;?BB&X]XcXcBdgjjk
 ))r6   c                 L   U R                   S S S 2S 4   R                  5       R                  UR                  S   SS5      R	                  UR
                  5      nUS S 2S S S 24   R                  5       n[        UR
                  R                  [        5      (       a0  UR
                  R                  S:w  a  UR
                  R                  OSn[        USS9   UR                  5       UR                  5       -  R                  SS5      n[        R                  " Xf4SS	9nUR                  5       U R                  -  nUR                  5       U R                  -  n	S S S 5        WR	                  UR                   S
9W	R	                  UR                   S
94$ ! , (       d  f       N@= f)Nr   r:   r!   mpscpuF)device_typeenabledr9   rs   rm   )rW   rO   expandrH   r=   rf   
isinstancetypestrr   	transposer-   catcosrc   sinr<   )
r1   xposition_idsinv_freq_expandedposition_ids_expandedry   freqsembr   r   s
             r4   rD   LlamaRotaryEmbedding.forwardz   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#)rc   rX   r_   r`   rZ   NNNN)rK   rL   rM   rN   r-   rP   __annotations__r"   r+   staticmethodr   intrG   rO   rb   no_gradr   rD   rQ   rR   rS   s   @r4   rU   rU   I   s    llV{ V V  %)+/"*d"*(* t* 
~u$	%	* *: ]]_<  <r6   rU   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$ )z*Rotates half the hidden dims of the input..Nr:   r9   r{   )rH   r-   r   )r   x1x2s      r4   rotate_halfr      sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r6   rotary_pos_embc                     UR                  U5      nUR                  U5      nX-  [        U 5      U-  -   nX-  [        U5      U-  -   nXV4$ )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.
)	unsqueezer   )qkr   r   unsqueeze_dimq_embedk_embeds          r4   apply_rotary_pos_embr      sS    & --
&C
--
&Cw;q>C/0Gw;q>C/0Gr6   c                   .   ^  \ rS rSrU 4S jrS rSrU =r$ )LlamaMLP   c                   > [         TU ]  5         Xl        UR                  U l        UR                  U l        [
        R                  " U R                  U R                  UR                  S9U l        [
        R                  " U R                  U R                  UR                  S9U l	        [
        R                  " U R                  U R                  UR                  S9U l
        [        UR                     U l        g )Nbias)r*   r+   rX   r2   intermediate_sizer   Linearmlp_bias	gate_projup_proj	down_projr   
hidden_actact_fnr1   rX   r3   s     r4   r+   LlamaMLP.__init__   s    !--!'!9!94#3#3T5K5KRXRaRabyy!1!143I3IPVP_P_`4#9#94;K;KRXRaRabV../r6   c                     U R                  U R                  U R                  U5      5      U R                  U5      -  5      nU$ r   )r   r   r   r   )r1   r   r   s      r4   rD   LlamaMLP.forward   s6    NN4;;t~~a/@#ADLLQRO#ST	r6   )r   rX   r   r   r2   r   r   )rK   rL   rM   rN   r+   rD   rQ   rR   rS   s   @r4   r   r      s    0 r6   r   r7   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)rH   r|   reshape)r7   r   batchnum_key_value_headsslenrl   s         r4   	repeat_kvr      s_    
 2?1D1D.Ez!!Qa"23::5W\dlmM  e(CTTTr6   modulequerykeyvalueattention_maskscalingdropoutkwargsc                    [        X R                  5      n[        X0R                  5      n	[        R                  " XR	                  SS5      5      U-  n
Ub  X-   n
[
        R                  R                  U
S[        R                  S9R                  UR                  5      n
[
        R                  R                  XU R                  S9n
[        R                  " X5      nUR	                  SS5      R                  5       nX4$ )Nr9   r   r:   )rs   r<   )ptrainingr!   )r   num_key_value_groupsr-   matmulr   r   
functionalsoftmaxr>   r=   r<   r   r   
contiguous)r   r   r   r   r   r   r   r   
key_statesvalue_statesattn_weightsattn_outputs               r4   eager_attention_forwardr      s     3 ; ;<JU$?$?@L<<';';Aq'ABWLL!#4==((2U]](SVVW\WbWbcL==((6??([L,,|:K''1-88:K$$r6   c                     ^  \ rS rSrSrS\S\4U 4S jjr   SS\R                  S\
\R                  \R                  4   S-  S	\R                  S-  S
\S-  S\\   S\
\R                  \R                  4   4S jjrSrU =r$ )LlamaAttention   z=Multi-headed attention from 'Attention Is All You Need' paperrX   	layer_idxc                 P  > [         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        g )Nrl   g      Tr   )r*   r+   rX   r   rn   r2   ro   rl   r   r   r   attention_dropout	is_causalr   r   attention_biasq_projk_projv_projo_projr1   rX   r   r3   s      r4   r+   LlamaAttention.__init__   sI   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
r6   Nr7   position_embeddingsr   past_key_valuesr   r(   c                    UR                   S S n/ UQSPU R                  P7nU R                  U5      R                  U5      R	                  SS5      nU R                  U5      R                  U5      R	                  SS5      n	U R                  U5      R                  U5      R	                  SS5      n
Uu  p[        XX5      u  pUb  UR                  XU R                  5      u  p[        R                  " U R                  R                  [        5      nU" U UU	U
U4U R                  (       d  SOU R                   U R"                  S.UD6u  pUR$                  " / UQSP76 R'                  5       nU R)                  U5      nX4$ )Nr:   r!   r9           )r   r   )rH   rl   r   viewr   r   r   r   updater   r   get_interfacerX   _attn_implementationr   r   r   r   r   r   r   )r1   r7   r   r   r   r   input_shapehidden_shapequery_statesr   r   r   r   attention_interfacer   r   s                   r4   rD   LlamaAttention.forward   s~    $))#2.88b8$--8{{=166|DNNqRST[[/44\BLLQPQR
{{=166|DNNqRST&#7RU#[ &'6'='=jX\XfXf'g$J(?(M(MKK,,.E)
 %8	%
  $}}C$2H2HLL	%
 	%
! "));;;;FFHkk+.((r6   )r   rX   rl   r   r   r   r   r   r   r   r   r   )rK   rL   rM   rN   __doc__r"   r   r+   r-   rP   rG   r   r   r   rD   rQ   rR   rS   s   @r4   r   r      s    G
{ 
s 
4 IM.2(,&)||&) #5<<#=>E&) t+	&)
 &) +,&) 
u||U\\)	*&) &)r6   r   c                     ^  \ rS rSrS\S\4U 4S jjr     SS\R                  S\R                  S-  S\R                  S-  S	\
S-  S
\S-  S\\R                  \R                  4   S-  S\\   S\R                  4S jjrSrU =r$ )LlamaDecoderLayeri$  rX   r   c                   > [         TU ]  5         UR                  U l        [        XS9U l        [        U5      U l        [        UR                  UR                  S9U l	        [        UR                  UR                  S9U l
        g )N)rX   r   r'   )r*   r+   r2   r   	self_attnr   mlpr%   rms_norm_epsinput_layernormpost_attention_layernormr   s      r4   r+   LlamaDecoderLayer.__init__%  sj    !--'vKF#+F,>,>FDWDWX(4V5G5GVM`M`(a%r6   Nr7   r   r   r   	use_cacher   r   r(   c           
          UnU R                  U5      nU R                  " SUUUUUUS.UD6u  pX-   nUnU R                  U5      nU R                  U5      nX-   nU$ )N)r7   r   r   r   r   r    )r   r   r   r   )
r1   r7   r   r   r   r   r   r   residual_s
             r4   rD   LlamaDecoderLayer.forward/  s     !,,];>> 
')%+ 3
 
 !0 !55mD/ 0r6   )r2   r   r   r   r   )NNNFN)rK   rL   rM   rN   r"   r   r+   r-   rP   
LongTensorr   boolrG   r   r   rD   rQ   rR   rS   s   @r4   r   r   $  s    b{ bs b /304(,!&HL|| t+ &&-	
  $; #5<<#=>E +, 
 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	)
LlamaPreTrainedModeliO  rX   modelTr   r   )r7   
attentionsr   N)rK   rL   rM   rN   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_outputsrQ   r   r6   r4   r   r   O  sQ    &*#,-#4"5N!"&*$r6   r   c                     ^  \ rS rSrS\4U 4S jjr\\\      SS\	R                  S-  S\	R                  S-  S\	R                  S-  S\S-  S	\	R                  S-  S
\S-  S\\   S\4S jj5       5       5       rSrU =r$ )
LlamaModelib  rX   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   rX   F)r*   r+   pad_token_idpadding_idx
vocab_sizer   	Embeddingr2   embed_tokens
ModuleListrangenum_hidden_layersr   layersr%   r   normrU   
rotary_embgradient_checkpointing	post_initr   s      r4   r+   LlamaModel.__init__d  s     !.. ++LL):):F<N<NPTP`P`ammCHIaIaCbcCbiv1Cbc
 !!3!39L9LM	.f=&+# 	 ds   C?N	input_idsr   r   r   inputs_embedsr   r   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                  UUUUS9n	Un
U R                  XS9nU R                  S U R                  R                    H  nU" U
4U	UUUUS.UD6n
M     U R                  U
5      n
[        U
US	9$ )
Nz:You must specify exactly one of input_ids or inputs_embedsr  r   r!   )rf   )rX   r  r   r   r   )r   )r   r   r   r   r   )last_hidden_stater   )
ValueErrorr  r	   rX   get_seq_lengthr-   rp   rH   rf   r   r   r  r  r  r  r   )r1   r  r   r   r   r  r   r   past_seen_tokenscausal_maskr7   r   decoder_layers                r4   rD   LlamaModel.forwardt  sF    -t";<YZZ *.*;*;I*FM0*$++>OCRC^==?de <<(;(;A(>}G[G[\_ooL'11!4L(;;')+%
 &"oomoW![[)H4;;+H+HIM)*$7) /# M J 		-0&++
 	
r6   )r  r  r  r  r  r  r  )NNNNNN)rK   rL   rM   rN   r"   r+   r   r    r   r-   r   rP   r   FloatTensorr   r   r   r   rD   rQ   rR   rS   s   @r4   r	  r	  b  s    {     .2.204(,26!%2
##d*2
 t+2
 &&-	2

 2
 ((4/2
 $;2
 +,2
 
!2
    2
r6   r	  c                   P  ^  \ rS rSrSS0rSS0rSS/S/40rU 4S jr\\	        SS
\
R                  S	-  S\
R                  S	-  S\
R                  S	-  S\S	-  S\
R                  S	-  S\
R                  S	-  S\S	-  S\\
R                  -  S\\   S\4S jj5       5       rSrU =r$ )LlamaForCausalLMi  zlm_head.weightzmodel.embed_tokens.weightlm_headcolwise_gather_outputr7   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   r2   r'  r  r   s     r4   r+   LlamaForCausalLM.__init__  sU     '
 ++yy!3!3V5F5FUS 	r6   Nr  r   r   r   r  labelsr   logits_to_keepr   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$ )ao  
Example:

```python
>>> from transformers import AutoTokenizer, LlamaForCausalLM

>>> model = LlamaForCausalLM.from_pretrained("meta-llama/Llama-2-7b-hf")
>>> tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-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  r   r   r   r  r   N)r)  r,  r  )lossr)  r   r7   r   r   )r   r  r}   r   slicer'  loss_functionrX   r  r   r   r7   r   )r1   r  r   r   r   r  r,  r   r-  r   outputsr7   slice_indicesr)  r/  s                  r4   rD   LlamaForCausalLM.forward  s    > ,0:: ,
)%+',
 ,
  118B>SV8W8W~ot4]kmA}a,?@A%%pVt{{OeOepiopD%#33!//))
 	
r6   )r'  r   r  )NNNNNNNr   )rK   rL   rM   rN   _tied_weights_keys_tp_plan_pp_planr+   r   r   r-   r   rP   r   r$  r   r   r   r   r   rD   rQ   rR   rS   s   @r4   r&  r&    s   *,GH23H_-z:;H  .2.204(,26*.!%-.6
##d*6
 t+6
 &&-	6

 6
 ((4/6
   4'6
 $;6
 ell*6
 +,6
 
 6
  6
r6   r&  c                       \ rS rSrSrg)LlamaForSequenceClassificationi  r   NrK   rL   rM   rN   rQ   r   r6   r4   r9  r9    s    ^ar6   r9  c                       \ rS rSrSrSrg)LlamaForQuestionAnsweringi  transformerr   N)rK   rL   rM   rN   r   rQ   r   r6   r4   r<  r<    s    %r6   r<  c                       \ rS rSrSrg)LlamaForTokenClassificationi  r   Nr:  r   r6   r4   r?  r?    s    X[r6   r?  )r&  r	  r   r9  r<  r?  )r!   )r   )Fcollections.abcr   typingr   r-   r   activationsr   cache_utilsr   r	   
generationr
   integrationsr   r   r   masking_utilsr   modeling_layersr   r   r   r   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   r   utils.genericr   r   utils.output_capturingr    configuration_llamar"   
get_loggerrK   loggerModuler%   rU   r   r   r   rP   r   r   rO   r   r   r   r   r	  r&  r9  r<  r?  __all__r   r6   r4   <module>rT     s,  & %    ! . ) f f /  L F & R R G 5 , 
		H	% Y'J299 J (J(><299 ><B( *+ ,2ryy  	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 LL4'% % % '(%2 )*@)RYY @) +@)F(2 (V ?  $ F
% F
 F
R F
+_ F
 F
R b%EG[ a& ;=Q & \"?AU [r6   