
    cCiP                        S SK JrJrJr  S SKrS SKJr  SSKJr  SSKJ	r	J
r
  SSKJr  SSKJr  SS	KJr  SS
KJrJr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'  SSK(J)r)  SSK*J+r+  \%RX                  " \-5      r.\" S5       " S S\R^                  5      5       r0 " S S\R^                  5      r1S r2S;S jr3 " S S\R^                  5      r4S\Rj                  S\6S\Rj                  4S  jr7 S<S!\R^                  S"\Rj                  S#\Rj                  S$\Rj                  S%\\Rj                     S&\8S'\8S(\ \"   4S) jjr9 " S* S+\R^                  5      r: " S, S-\5      r;\# " S. S/\5      5       r<\# " S0 S1\<5      5       r=\# " S2 S3\<\5      5       r> " S4 S5\\<5      r? " S6 S7\\<5      r@ " S8 S9\\<5      rA/ S:QrBg)=    )CallableOptionalUnionN)nn   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_forward_from_hub)create_causal_mask)GenericForQuestionAnswering GenericForSequenceClassificationGenericForTokenClassificationGradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuplelogging)deprecate_kwarg)check_model_inputs   )LlamaConfigRMSNormc                   8   ^  \ rS rSrSU 4S jjrS rS rSrU =r$ )LlamaRMSNorm4   c                    > [         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_sizeeps	__class__s      b/home/james-whalen/.local/lib/python3.13/site-packages/transformers/models/llama/modeling_llama.pyr'   LlamaRMSNorm.__init__6   s/     	ll5::k#:; #    c                    UR                   nUR                  [        R                  5      nUR	                  S5      R                  SSS9nU[        R                  " X0R                  -   5      -  nU R                  UR                  U5      -  $ )N   T)keepdim)	dtypetor)   float32powmeanrsqrtr,   r+   )r-   hidden_statesinput_dtypevariances       r1   forwardLlamaRMSNorm.forward>   sw    #))%((7 $$Q',,R,>%H?T?T4T(UU{{]--k:::r3   c                 ^    [        U R                  R                  5       SU R                   3$ )Nz, eps=)tupler+   shaper,   )r-   s    r1   
extra_reprLlamaRMSNorm.extra_reprE   s*    ))*+6$2G2G1HIIr3   )r,   r+   )gư>)	__name__
__module____qualname____firstlineno__r'   rA   rF   __static_attributes____classcell__r0   s   @r1   r#   r#   4   s    $;J Jr3   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$ )LlamaRotaryEmbeddingI   inv_freqconfigc                   > [         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defaultrR   F)
persistent)r&   r'   hasattr
isinstancerU   dictgetrV   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrS   r   rope_init_fnattention_scalingregister_bufferrR   original_inv_freq)r-   rS   devicerR   r0   s       r1   r'   LlamaRotaryEmbedding.__init__L   s    6>**z&:M:Mt/T/T#0044[&BUBUBYBYZ`BabDN&DN"("@"@$*$B$B!/?+/+<+<T[[&+Q((ZeD!%r3   c                 b   U R                   S S S 2S 4   R                  5       R                  UR                  S   SS5      R	                  UR
                  5      nUS S 2S S S 24   R                  5       n[        UR
                  R                  [        5      (       a0  UR
                  R                  S:w  a  UR
                  R                  OSn[        R                  " USS9   UR                  5       UR                  5       -  R                  SS5      n[        R                  " Xf4SS	9nUR                  5       U R                  -  nUR                  5       U R                  -  n	S S S 5        WR	                  UR                   S
9W	R	                  UR                   S
94$ ! , (       d  f       N@= f)Nr   r6   r   mpscpuF)device_typeenabledr5   dim)r8   )rR   floatexpandrE   r9   re   r[   rW   strr)   autocast	transposecatcosrb   sinr8   )
r-   xposition_idsinv_freq_expandedposition_ids_expandedrj   freqsembrt   ru   s
             r1   rA   LlamaRotaryEmbedding.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   $BF  
F.)rb   rS   r_   rd   r`   ra   rV   N)rH   rI   rJ   rK   r)   Tensor__annotations__r    r'   no_gradr   rA   rL   rM   rN   s   @r1   rP   rP   I   s@    ll/{ / /" ]]_<  <r3   rP   c                     U SSU R                   S   S-  24   nU SU R                   S   S-  S24   n[        R                  " U* U4SS9$ )z*Rotates half the hidden dims of the input..Nr6   r5   rl   )rE   r)   rs   )rv   x1x2s      r1   rotate_halfr   m   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r3   c                     UR                  U5      nUR                  U5      nX-  [        U 5      U-  -   nX-  [        U5      U-  -   nXg4$ )a  Applies Rotary Position Embedding to the query and key tensors.

Args:
    q (`torch.Tensor`): The query tensor.
    k (`torch.Tensor`): The key tensor.
    cos (`torch.Tensor`): The cosine part of the rotary embedding.
    sin (`torch.Tensor`): The sine part of the rotary embedding.
    position_ids (`torch.Tensor`, *optional*):
        Deprecated and unused.
    unsqueeze_dim (`int`, *optional*, defaults to 1):
        The 'unsqueeze_dim' argument specifies the dimension along which to unsqueeze cos[position_ids] and
        sin[position_ids] so that they can be properly broadcasted to the dimensions of q and k. For example, note
        that cos[position_ids] and sin[position_ids] have the shape [batch_size, seq_len, head_dim]. Then, if q and
        k have the shape [batch_size, heads, seq_len, head_dim], then setting unsqueeze_dim=1 makes
        cos[position_ids] and sin[position_ids] broadcastable to the shapes of q and k. Similarly, if q and k have
        the shape [batch_size, seq_len, heads, head_dim], then set unsqueeze_dim=2.
Returns:
    `tuple(torch.Tensor)` comprising of the query and key tensors rotated using the Rotary Position Embedding.
)	unsqueezer   )qkrt   ru   rw   unsqueeze_dimq_embedk_embeds           r1   apply_rotary_pos_embr   t   sS    ( --
&C
--
&Cw;q>C/0Gw;q>C/0Gr3   c                   .   ^  \ rS rSrU 4S jrS rSrU =r$ )LlamaMLP   c                   > [         TU ]  5         Xl        UR                  U l        UR                  U l        [
        R                  " U R                  U R                  UR                  S9U l        [
        R                  " U R                  U R                  UR                  S9U l	        [
        R                  " U R                  U R                  UR                  S9U l
        [        UR                     U l        g )Nbias)r&   r'   rS   r.   intermediate_sizer   Linearmlp_bias	gate_projup_proj	down_projr   
hidden_actact_fnr-   rS   r0   s     r1   r'   LlamaMLP.__init__   s    !--!'!9!94#3#3T5K5KRXRaRabyy!1!143I3IPVP_P_`4#9#94;K;KRXRaRabV../r3   c                     U R                  U R                  U R                  U5      5      U R                  U5      -  5      nU$ r}   )r   r   r   r   )r-   rv   r   s      r1   rA   LlamaMLP.forward   s6    NN4;;t~~a/@#ADLLQRO#ST	r3   )r   rS   r   r   r.   r   r   )rH   rI   rJ   rK   r'   rA   rL   rM   rN   s   @r1   r   r      s    0 r3   r   r>   n_repreturnc                     U R                   u  p#pEUS:X  a  U $ U SS2SS2SSS2SS24   R                  X#XU5      n U R                  X#U-  XE5      $ )z
This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,
num_key_value_heads, seqlen, head_dim) to (batch, num_attention_heads, seqlen, head_dim)
r   N)rE   ro   reshape)r>   r   batchnum_key_value_headsslenhead_dims         r1   	repeat_kvr      s_    
 2?1D1D.Ez!!Qa"23::5W\dlmM  e(CTTTr3   modulequerykeyvalueattention_maskscalingdropoutkwargsc                 @   [        X R                  5      n[        X0R                  5      n	[        R                  " XR	                  SS5      5      U-  n
Ub"  US S 2S S 2S S 2S UR
                  S   24   nX-   n
[        R                  R                  U
S[        R                  S9R                  UR                  5      n
[        R                  R                  XU R                  S9n
[        R                  " X5      nUR	                  SS5      R                  5       nX4$ )Nr5   r   r6   )rm   r8   )ptrainingr   )r   num_key_value_groupsr)   matmulrr   rE   r   
functionalsoftmaxr:   r9   r8   r   r   
contiguous)r   r   r   r   r   r   r   r   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r1   eager_attention_forwardr      s     3 ; ;<JU$?$?@L<<';';Aq'ABWLL!$Q1.D
0@0@0D.D%DE#1==((2U]](SVVW\WbWbcL==((6??([L,,|:K''1-88:K$$r3   c                   4  ^  \ rS rSrSrS\S\4U 4S jjr\" SSSS	9  SS
\	R                  S\\	R                  \	R                  4   S\\	R                     S\\   S\\	R                     S\\   S\\	R                  \	R                  4   4S jj5       rSrU =r$ )LlamaAttention   z=Multi-headed attention from 'Attention Is All You Need' paperrS   	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 )Nr   g      Tr   )r&   r'   rS   r   getattrr.   num_attention_headsr   r   r   r   attention_dropout	is_causalr   r   attention_biasq_projk_projv_projo_projr-   rS   r   r0   s      r1   r'   LlamaAttention.__init__   sI   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
r3   past_key_valuepast_key_values4.58new_nameversionr>   position_embeddingsr   cache_positionr   r   c                 4   UR                   S S n/ UQSPU R                  P7nU R                  U5      R                  U5      R	                  SS5      n	U R                  U5      R                  U5      R	                  SS5      n
U R                  U5      R                  U5      R	                  SS5      nUu  p[        XX5      u  pUb$  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                   S.UD6u  nnUR"                  " / UQSP76 R%                  5       nU R'                  U5      nUU4$ )Nr6   r   r5   )ru   rt   r   eager        )r   r   )rE   r   r   viewrr   r   r   r   updater   r   rS   _attn_implementationr   r   r   r   r   r   r   )r-   r>   r   r   r   r   r   input_shapehidden_shapequery_statesr   r   rt   ru   cache_kwargsattention_interfacer   r   s                     r1   rA   LlamaAttention.forward   s    $))#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#[ &#&nUL'6'='=jX\XfXfht'u$J(?;;++w6"9$++:Z:Z"[$7	%
  $}}C$2H2HLL	%
 	%
!\ "));;;;FFHkk+.L((r3   )r   rS   r   r   r   r   r   r   r   r   r   )NN)rH   rI   rJ   rK   __doc__r    intr'   r   r)   r~   rD   r   r	   
LongTensorr   r   rA   rL   rM   rN   s   @r1   r   r      s    G
{ 
s 
. %0A6R ,059))||)) #5<<#=>)) !.	))
 "%)) !!1!12)) +,)) 
u||U\\)	*)) S))r3   r   c                   H  ^  \ rS rSrS\S\4U 4S jjr\" SSSS9      SS	\R                  S
\
\R                     S\
\R                     S\
\   S\
\   S\
\R                     S\
\\R                  \R                  4      S\\   S\R                  4S jj5       rSrU =r$ )LlamaDecoderLayeri  rS   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)rS   r   r/   )r&   r'   r.   r   	self_attnr   mlpr#   rms_norm_epsinput_layernormpost_attention_layernormr   s      r1   r'   LlamaDecoderLayer.__init__  sj    !--'vKF#+F,>,>FDWDWX(4V5G5GVM`M`(a%r3   r   r   r   r   r>   r   rw   	use_cacher   r   r   r   c                     Un	U R                  U5      nU R                  " SUUUUUUUS.UD6u  pX-   nUn	U R                  U5      nU R                  U5      nX-   nU$ )N)r>   r   rw   r   r   r   r    )r   r   r   r   )r-   r>   r   rw   r   r   r   r   r   residual_s              r1   rA   LlamaDecoderLayer.forward  s     !,,];>> 	
')%+) 3	
 	
 !0 !55mD/ 0r3   )r.   r   r   r   r   )NNNFNN)rH   rI   rJ   rK   r    r   r'   r   r)   r~   r   r   r	   boolrD   r   r   rA   rL   rM   rN   s   @r1   r   r     s    b{ bs b %0A6R 2637+/$)59KO|| !. u//0	
 "% D> !!1!12 &eELL%,,,F&GH +, 
 Sr3   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	)
LlamaPreTrainedModeli:  rS   modelTr   r   )r>   
attentionsr   N)rH   rI   rJ   rK   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_outputsrL   r   r3   r1   r   r   :  sQ    &*#,-#4"5N!"&*$r3   r   c                   "  ^  \ rS rSrS\4U 4S jjr\" 5       \       SS\\	R                     S\\	R                     S\\	R                     S\\   S\\	R                     S	\\	R                     S
\\   S\\   S\4S jj5       5       rSrU =r$ )
LlamaModeliM  rS   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   rS   F)r&   r'   pad_token_idpadding_idx
vocab_sizer   	Embeddingr.   embed_tokens
ModuleListrangenum_hidden_layersr   layersr#   r   normrP   
rotary_embgradient_checkpointing	post_initr   s      r1   r'   LlamaModel.__init__O  s     !.. ++LL):):F<N<NPTP`P`ammCHIaIaCbcCbiv1Cbc
 !!3!39L9LM	.f=&+# 	 ds   C?	input_idsr   rw   r   inputs_embedsr   r   r   r   c           
      J   US L US L-  (       a  [        S5      eUc  U R                  U5      nU(       a  Uc  [        U R                  S9nUcD  Ub  UR	                  5       OSn	[
        R                  " XUR                  S   -   UR                  S9nUc  UR                  S5      n[        U R                  UUUUUS9n
UnU R                  X5      nU R                  S U R                  R                    H  nU" U4U
UUUUS.UD6nM     U R                  U5      n[        UUS9$ )	Nz:You must specify exactly one of input_ids or inputs_embedsr  r   r   )re   )rS   input_embedsr   r   r   rw   )r   rw   r   r   r   )last_hidden_stater   )
ValueErrorr  r
   rS   get_seq_lengthr)   arangerE   re   r   r   r  r  r  r  r   )r-   r  r   rw   r   r  r   r   r   past_seen_tokensr   r>   r   decoder_layers                 r1   rA   LlamaModel.forward_  sR    -t";<YZZ *.*;*;I*FM0*$++>O!CRC^==?de+0<< ]5H5H5K"KTaThTh,N )33A6L(;;&))+%
 &"oomJ![[)H4;;+H+HIM)*) /-$7 M J 		-0&++
 	
r3   )r  r  r  r  r
  r  r  )NNNNNNN)rH   rI   rJ   rK   r    r'   r   r   r   r)   r   r~   r	   FloatTensorr   r   r   r   rA   rL   rM   rN   s   @r1   r  r  M  s    {    151537+/5959$(8
E,,-8
 !.8
 u//0	8

 "%8
   1 128
 !!1!128
 D>8
 +,8
 
!8
  8
r3   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$ )LlamaForCausalLMi  zlm_head.weightlm_headcolwise_repr>   logitsc                    > [         TU ]  U5        [        U5      U l        UR                  U l        [
        R                  " UR                  UR                  SS9U l        U R                  5         g )NFr   )
r&   r'   r  r   r  r   r   r.   r%  r  r   s     r1   r'   LlamaForCausalLM.__init__  sU     '
 ++yy!3!3V5F5FUS 	r3   r  r   rw   r   r  labelsr   r   logits_to_keepr   r   c
                 ~   U R                   " SUUUUUUUS.U
D6nUR                  n[        U	[        5      (       a  [	        U	* S5      OU	nU R                  USS2USS24   5      nSnUb)  U R                  " SXU R                  R                  S.U
D6n[        UUUR                  UR                  UR                  S9$ )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   rw   r   r  r   r   N)r'  r*  r  )lossr'  r   r>   r   r   )r   r  r[   r   slicer%  loss_functionrS   r  r   r   r>   r   )r-   r  r   rw   r   r  r*  r   r   r+  r   outputsr>   slice_indicesr'  r-  s                   r1   rA   LlamaForCausalLM.forward  s    @ ,0:: 	,
)%+')	,
 	,
  118B>SV8W8W~ot4]kmA}a,?@A%%pVt{{OeOepiopD%#33!//))
 	
r3   )r%  r   r  )	NNNNNNNNr   )rH   rI   rJ   rK   _tied_weights_keys_tp_plan_pp_planr'   r   r   r   r)   r   r~   r	   r"  r   r   r   r   r   r   rA   rL   rM   rN   s   @r1   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
r3   r$  c                       \ rS rSrSrg)LlamaForSequenceClassificationi  r   NrH   rI   rJ   rK   rL   r   r3   r1   r7  r7    s    ^ar3   r7  c                       \ rS rSrSrSrg)LlamaForQuestionAnsweringi  transformerr   N)rH   rI   rJ   rK   r   rL   r   r3   r1   r:  r:    s    %r3   r:  c                       \ rS rSrSrg)LlamaForTokenClassificationi  r   Nr8  r   r3   r1   r=  r=    s    X[r3   r=  )r$  r  r   r7  r:  r=  )Nr   )r   )Ctypingr   r   r   r)   r   activationsr   cache_utilsr	   r
   
generationr   integrationsr   masking_utilsr   modeling_layersr   r   r   r   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   r   utils.deprecationr   utils.genericr   configuration_llamar    
get_loggerrH   loggerModuler#   rP   r   r   r   r~   r   r   rn   r   r   r   r   r  r$  r7  r:  r=  __all__r   r3   r1   <module>rQ     s  ( - ,   ! . ) 7 /  L F & R R 0 / , 
		H	% Y'J299 J (J(!<299 !<H(6ryy  	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 U\\*% % % '(%4D)RYY D)N+2 +\ ?  $ K
% K
 K
\ H
+_ H
 H
V b%EG[ a& ;=Q & \"?AU [r3   