
    bCiR                        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  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%  SSK&J'r'  SSK(J)r)  SSK*J+r+   " S S\RX                  5      r-\" S5       " S S\RX                  5      5       r. " S S\RX                  5      r/S r0S>S jr1S\Rd                  S\3S \Rd                  4S! jr4 S?S"\RX                  S#\Rd                  S$\Rd                  S%\Rd                  S&\\Rd                     S'\5S(\5S)\"\$   4S* jjr6 " S+ S,\RX                  5      r7 " S- S.\5      r8\ " S/ S0\ 5      5       r9\ " S1 S2\95      5       r:\" S3S49 " S5 S6\9\5      5       r;\" S3S49 " S7 S8\\95      5       r<\" S3S49 " S9 S:\\95      5       r=\" S3S49 " S; S<\\95      5       r>/ S=Qr?g)@    )CallableOptionalUnionN)nn)auto_docstring   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_forward_from_hub)create_causal_mask)GenericForQuestionAnswering GenericForSequenceClassificationGenericForTokenClassificationGradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargscan_return_tuple)deprecate_kwarg)check_model_inputs   )ArceeConfigc                   .   ^  \ rS rSrU 4S jrS rSrU =r$ )ArceeMLP2   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	        [        UR                     U l        g )Nbias)super__init__confighidden_sizeintermediate_sizer   Linearmlp_biasup_proj	down_projr	   
hidden_actact_fnselfr(   	__class__s     b/home/james-whalen/.local/lib/python3.13/site-packages/transformers/models/arcee/modeling_arcee.pyr'   ArceeMLP.__init__3   s    !--!'!9!9yy!1!143I3IPVP_P_`4#9#94;K;KRXRaRabV../    c                 `    U R                  U R                  U R                  U5      5      5      $ N)r.   r0   r-   )r2   xs     r4   forwardArceeMLP.forward<   s"    ~~dkk$,,q/:;;r6   )r0   r(   r.   r)   r*   r-   )__name__
__module____qualname____firstlineno__r'   r:   __static_attributes____classcell__r3   s   @r4   r!   r!   2   s    0< <r6   r!   RMSNormc                   8   ^  \ rS rSrSU 4S jjrS rS rSrU =r$ )ArceeRMSNorm@   c                    > [         TU ]  5         [        R                  " [        R
                  " U5      5      U l        X l        g)z+
ArceeRMSNorm is equivalent to T5LayerNorm
N)r&   r'   r   	Parametertorchonesweightvariance_epsilon)r2   r)   epsr3   s      r4   r'   ArceeRMSNorm.__init__B   s/     	ll5::k#:; #r6   c                    UR                   nUR                  [        R                  5      nUR	                  S5      R                  SSS9nU[        R                  " X0R                  -   5      -  nU R                  UR                  U5      -  $ )N   T)keepdim)	dtypetorI   float32powmeanrsqrtrL   rK   )r2   hidden_statesinput_dtypevariances       r4   r:   ArceeRMSNorm.forwardJ   sw    #))%((7 $$Q',,R,>%H?T?T4T(UU{{]--k:::r6   c                 ^    [        U R                  R                  5       SU R                   3$ )Nz, eps=)tuplerK   shaperL   )r2   s    r4   
extra_reprArceeRMSNorm.extra_reprQ   s*    ))*+6$2G2G1HIIr6   )rL   rK   )gư>)	r<   r=   r>   r?   r'   r:   r`   r@   rA   rB   s   @r4   rE   rE   @   s    $;J Jr6   rE   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$ )ArceeRotaryEmbeddingU   inv_freqr(   c                   > [         TU ]  5         [        US5      (       aZ  [        UR                  [
        5      (       a;  UR                  R                  SUR                  R                  S5      5      U l        OSU l        UR                  U l	        UR                  U l
        Xl        [        U R                     U l        U R                  U R                  U5      u  o0l        U R                  SUSS9  U R                   U l        g )Nrope_scaling	rope_typetypedefaultre   F)
persistent)r&   r'   hasattr
isinstancerg   dictgetrh   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenr(   r   rope_init_fnattention_scalingregister_bufferre   original_inv_freq)r2   r(   devicere   r3   s       r4   r'   ArceeRotaryEmbedding.__init__X   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   rQ   r   mpscpuF)device_typeenabledrP   dim)rS   )re   floatexpandr_   rT   rw   rm   ri   strrI   autocast	transposecatcosrt   sinrS   )
r2   r9   position_idsinv_freq_expandedposition_ids_expandedr|   freqsembr   r   s
             r4   r:   ArceeRotaryEmbedding.forwardi   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   $BF  
F.)rt   r(   rq   rv   rr   rs   rh   r8   )r<   r=   r>   r?   rI   Tensor__annotations__r   r'   no_gradr   r:   r@   rA   rB   s   @r4   rc   rc   U   s@    ll/{ / /" ]]_<  <r6   rc   c                     U SSU R                   S   S-  24   nU SU R                   S   S-  S24   n[        R                  " U* U4SS9$ )z*Rotates half the hidden dims of the input..NrQ   rP   r~   )r_   rI   r   )r9   x1x2s      r4   rotate_halfr   y   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.
)	unsqueezer   )qkr   r   r   unsqueeze_dimq_embedk_embeds           r4   apply_rotary_pos_embr      sS    ( --
&C
--
&Cw;q>C/0Gw;q>C/0Gr6   rY   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)r_   r   reshape)rY   r   batchnum_key_value_headsslenhead_dims         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"  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$ )NrP   r   rQ   )r   rS   )ptrainingr   )r   num_key_value_groupsrI   matmulr   r_   r   
functionalsoftmaxrU   rT   rS   r   r   
contiguous)r   r   r   r   r   r   r   r   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r4   eager_attention_forwardr      s     3 ; ;<JU$?$?@L<<';';Aq'ABWLL!$Q1.D
0@0@0D.D%DE#1==((2U]](SVVW\WbWbcL==((6??([L,,|:K''1-88:K$$r6   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$ )ArceeAttention   z=Multi-headed attention from 'Attention Is All You Need' paperr(   	layer_idxc                 P  > [         TU ]  5         Xl        X l        [	        USUR
                  UR                  -  5      U l        UR                  UR                  -  U l	        U R                  S-  U l
        UR                  U l        SU l        [        R                  " UR
                  UR                  U R                  -  UR                  S9U l        [        R                  " UR
                  UR                  U R                  -  UR                  S9U l        [        R                  " UR
                  UR                  U R                  -  UR                  S9U l        [        R                  " UR                  U R                  -  UR
                  UR                  S9U l        g )Nr   g      Tr$   )r&   r'   r(   r   getattrr)   num_attention_headsr   r   r   r   attention_dropout	is_causalr   r+   attention_biasq_projk_projv_projo_projr2   r(   r   r3   s      r4   r'   ArceeAttention.__init__   sI   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
r6   past_key_valuepast_key_values4.58new_nameversionrY   position_embeddingsr   cache_positionr   r   c                 4   UR                   S S n/ UQSPU R                  P7nU R                  U5      R                  U5      R	                  SS5      n	U R                  U5      R                  U5      R	                  SS5      n
U R                  U5      R                  U5      R	                  SS5      nUu  p[        XX5      u  pUb$  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$ )NrQ   r   rP   )r   r   r   eager        )r   r   )r_   r   r   viewr   r   r   r   updater   r   r(   _attn_implementationr   r   r   r   r   r   r   )r2   rY   r   r   r   r   r   input_shapehidden_shapequery_statesr   r   r   r   cache_kwargsattention_interfacer   r   s                     r4   r:   ArceeAttention.forward   s    $))#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$2H2HLL	%
 	%
!\ "));;;;FFHkk+.L((r6   )r   r(   r   r   r   r   r   r   r   r   r   )NN)r<   r=   r>   r?   __doc__r   intr'   r   rI   r   r^   r   r
   
LongTensorr   r   r:   r@   rA   rB   s   @r4   r   r      s    G
{ 
s 
. %0A6R ,059))||)) #5<<#=>)) !.	))
 "%)) !!1!12)) +,)) 
u||U\\)	*)) S))r6   r   c                   H  ^  \ rS rSrS\S\4U 4S jjr\" SSSS9      SS	\R                  S
\
\R                     S\
\R                     S\
\   S\
\   S\
\R                     S\
\\R                  \R                  4      S\\   S\R                  4S jj5       rSrU =r$ )ArceeDecoderLayeri  r(   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)r(   r   rM   )r&   r'   r)   r   	self_attnr!   mlprE   rms_norm_epsinput_layernormpost_attention_layernormr   s      r4   r'   ArceeDecoderLayer.__init__	  sj    !--'vKF#+F,>,>FDWDWX(4V5G5GVM`M`(a%r6   r   r   r   r   rY   r   r   	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$ )N)rY   r   r   r   r   r   r    )r   r   r   r   )r2   rY   r   r   r   r   r   r   r   residual_s              r4   r:   ArceeDecoderLayer.forward  s     !,,];>> 	
')%+) 3	
 	
 !0 !55mD/ 0r6   )r)   r   r   r   r   )NNNFNN)r<   r=   r>   r?   r   r   r'   r   rI   r   r   r   r
   boolr^   r   r   r:   r@   rA   rB   s   @r4   r   r     s    b{ bs b %0A6R 2637+/$)59KO|| !. u//0	
 "% D> !!1!12 &eELL%,,,F&GH +, 
 S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	)
ArceePreTrainedModeli6  r(   modelTr   r   )rY   
attentionsr   N)r<   r=   r>   r?   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_outputsr@   r   r6   r4   r   r   6  sQ    &*#,-#4"5N!"&*$r6   r   c                   "  ^  \ rS rSrS\4U 4S jjr\" 5       \       SS\\	R                     S\\	R                     S\\	R                     S\\   S\\	R                     S	\\	R                     S
\\   S\\   S\4S jj5       5       rSrU =r$ )
ArceeModeliI  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        [        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   r(   F)r&   r'   pad_token_idpadding_idx
vocab_sizer   	Embeddingr)   embed_tokens
ModuleListrangenum_hidden_layersr   layersrE   r   normrc   
rotary_embgradient_checkpointing	post_initr   s      r4   r'   ArceeModel.__init__K  s     !.. ++LL):):F<N<NPTP`P`ammCHIaIaCbcCbiv1Cbc
 !!3!39L9LM	.f=&+# 	 ds   C?	input_idsr   r   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$ )	Nz:You must specify exactly one of input_ids or inputs_embedsr  r   r   )rw   )r(   input_embedsr   r   r   r   )r   r   r   r   r   )last_hidden_stater   )
ValueErrorr  r   r(   get_seq_lengthrI   aranger_   rw   r   r   r  r  r  r  r   )r2   r  r   r   r   r  r   r   r   past_seen_tokensr   rY   r   decoder_layers                 r4   r:   ArceeModel.forward[  sR    -t";<YZZ *.*;*;I*FM0*$++>O!CRC^==?de+0<< ]5H5H5K"KTaThTh,N )33A6L(;;&))+%
 &"oomJ![[)H4;;+H+HIM)*) /-$7 M J 		-0&++
 	
r6   )r  r  r  r  r  r  r	  )NNNNNNN)r<   r=   r>   r?   r   r'   r   r   r   rI   r   r   r
   FloatTensorr   r   r   r   r:   r@   rA   rB   s   @r4   r  r  I  s    {    151537+/5959$(8
E,,-8
 !.8
 u//0	8

 "%8
   1 128
 !!1!128
 D>8
 +,8
 
!8
  8
r6   r  zarcee-ai/AFM-4.5B)
checkpointc                   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$ )ArceeForCausalLMi  zlm_head.weightlm_headcolwise_reprY   logitsc                    > [         TU ]  U5        [        U5      U l        UR                  U l        [
        R                  " UR                  UR                  SS9U l        U R                  5         g )NFr$   )
r&   r'   r  r   r	  r   r+   r)   r$  r  r1   s     r4   r'   ArceeForCausalLM.__init__  sU     '
 ++yy!3!3V5F5FUS 	r6   r  r   r   r   r  labelsr   r   logits_to_keepr   r   c
                 ~   U R                   " SUUUUUUUS.U
D6nUR                  n[        U	[        5      (       a  [	        U	* S5      OU	nU R                  USS2USS24   5      nSnUb)  U R                  " SXU R                  R                  S.U
D6n[        UUUR                  UR                  UR                  S9$ )ao  
Example:

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

>>> model = ArceeForCausalLM.from_pretrained("meta-arcee/Arcee-2-7b-hf")
>>> tokenizer = AutoTokenizer.from_pretrained("meta-arcee/Arcee-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   r   N)r&  r)  r	  )lossr&  r   rY   r   r   )r   r  rm   r   slicer$  loss_functionr(   r	  r   r   rY   r   )r2   r  r   r   r   r  r)  r   r   r*  r   outputsrY   slice_indicesr&  r,  s                   r4   r:   ArceeForCausalLM.forward  s    @ ,0:: 	,
)%+')	,
 	,
  118B>SV8W8W~ot4]kmA}a,?@A%%pVt{{OeOepiopD%#33!//))
 	
r6   )r$  r   r	  )	NNNNNNNNr   )r<   r=   r>   r?   _tied_weights_keys_tp_plan_pp_planr'   r   r   r   rI   r   r   r
   r   r   r   r   r   r   r   r:   r@   rA   rB   s   @r4   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
r6   r#  c                       \ rS rSrSrg)ArceeForSequenceClassificationi  r   Nr<   r=   r>   r?   r@   r   r6   r4   r6  r6        r6   r6  c                       \ rS rSrSrSrg)ArceeForQuestionAnsweringi  transformerr   N)r<   r=   r>   r?   r   r@   r   r6   r4   r:  r:    s    %r6   r:  c                       \ rS rSrSrg)ArceeForTokenClassificationi  r   Nr7  r   r6   r4   r=  r=    r8  r6   r=  )r#  r:  r6  r=  r  r   )Nr   )r   )@typingr   r   r   rI   r   transformers.utilsr   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   utils.deprecationr   utils.genericr   configuration_arceer   Moduler!   rE   rc   r   r   r   r   r   r   r   r   r   r   r  r#  r6  r:  r=  __all__r   r6   r4   <module>rP     s1  , - ,   - ! . ) 7 /  P K F & 9 0 / ,<ryy < Y'J299 J (J(!<299 !<H(6	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 U\\*% % % '(%4D)RYY D)N+2 +\ ?  $ K
% K
 K
\ ./H
+_ H
 0H
V ./	%EG[ 	 0	 ./& ;=Q & 0& ./	"?AU 	 0	r6   