
    Z j}w                        S SK Jr  S SKJr  S SKrS SKJs  Jr  S SKJr  SSK	J
r  SSKJr  SSKJrJr  SS	KJr  SS
KJrJr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&J'r'  SSK(J)r)J*r*  SSK+J,r,  SSK-J.r.J/r/J0r0  SSK1J2r2J3r3  SSK4J5r5J6r6  SSK7J8r8  \ " S S\Rr                  5      5       r: " S S\Rr                  5      r; " S S\Rr                  5      r<\" S5       " S S\Rr                  5      5       r= " S  S!\Rr                  5      r>S" r?\" S#5      SFS$ j5       r@S%\R                  S&\BS'\R                  4S( jrC SGS)\Rr                  S*\R                  S+\R                  S,\R                  S-\R                  S-  S.\DS/\DS0\,\.   4S1 jjrE\" \@5       " S2 S3\Rr                  5      5       rF " S4 S5\!5      rG\/ " S6 S7\*5      5       rH\/ " S8 S9\H5      5       rI   SHS:\R                  \J\R                     -  S-  S;\BS-  S-\R                  S-  S'\R                  \B-  4S< jjrK\/ " S= S>\H\5      5       rL " S? S@\\H5      rM " SA SB\ \H5      rN " SC SD\\H5      rO/ SEQrPg)I    )Callable)OptionalN)nn   )initialization)ACT2FN)CacheDynamicCache)GenerationMixin)use_experts_implementationuse_kernel_forward_from_hubuse_kernel_func_from_hubuse_kernelized_func)create_causal_mask!create_sliding_window_causal_mask)FlashAttentionKwargs)GenericForQuestionAnswering GenericForSequenceClassificationGenericForTokenClassificationGradientCheckpointingLayer)MoeCausalLMOutputWithPastMoeModelOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuple)maybe_autocastmerge_with_config_defaults)OutputRecordercapture_outputs   )MixtralConfigc                      ^  \ rS rSrSrS\4U 4S jjrS\R                  S\R                  S\R                  S\R                  4S	 jr	S
r
U =r$ )MixtralExperts=   z2Collection of expert weights stored as 3D tensors.configc                   > [         TU ]  5         UR                  U l        UR                  U l        UR                  U l        [        R                  " [        R                  " U R                  SU R                  -  U R
                  5      5      U l        [        R                  " [        R                  " U R                  U R
                  U R                  5      5      U l        [        UR                     U l        g )N   )super__init__num_local_expertsnum_expertshidden_size
hidden_dimintermediate_sizeintermediate_dimr   	Parametertorchemptygate_up_proj	down_projr   
hidden_actact_fnselfr*   	__class__s     }/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/mixtral/modeling_mixtral.pyr.   MixtralExperts.__init__A   s    !33 ,, & 8 8LLT5E5Eq4K`K`G`bfbqbq)rsekk$2B2BDOOUYUjUj&klV../    hidden_statestop_k_indextop_k_weightsreturnc                 X   [         R                  " U5      n[         R                  " 5          [         R                  R                  R                  X R                  S9nUR                  SSS5      n[         R                  " UR                  SS9S5      R                  5       nS S S 5        W H  nUS   nXpR                  :X  a  M  [         R                  " WU   5      u  pX   n
[        R                  R                  XR                  U   5      R                  SSS9u  pU R                  U5      U-  n[        R                  R                  XR                   U   5      nXXS 4   -  nUR#                  SXR%                  UR&                  5      5        M     U$ ! , (       d  f       N= f)N)num_classesr,   r%   r   )dimrH   )r6   
zeros_likeno_gradr   
functionalone_hotr0   permutegreatersumnonzerowherelinearr8   chunkr;   r9   
index_add_todtype)r=   rB   rC   rD   final_hidden_statesexpert_mask
expert_hit
expert_idx	top_k_pos	token_idxcurrent_stategateupcurrent_hidden_statess                 r?   forwardMixtralExperts.forwardJ   so    $..}=]]_((--55kO_O_5`K%--aA6K{8'DaHPPRJ 
 %J#AJ---#(;;{:/F#G I)4M}}++M;L;LZ;XY__`agi_jHD$(KK$5$:!$&MM$8$89NP^P^_iPj$k!$9)`dJd<e$e!**1i9Q9QReRkRk9lm % #"# _s   A7F
F))r;   r9   r8   r2   r4   r0   )__name__
__module____qualname____firstlineno____doc__r&   r.   r6   Tensorrd   __static_attributes____classcell__r>   s   @r?   r(   r(   =   sR    <0} 0#||# \\# ||	#
 
# #rA   r(   c                   .   ^  \ rS rSrU 4S jrS rSrU =r$ )MixtralTopKRoutere   c                   > [         TU ]  5         UR                  U l        UR                  U l        UR                  U l        [        R                  " [        R                  " U R
                  U R                  5      5      U l        g N)r-   r.   num_experts_per_toktop_kr/   r0   r1   r2   r   r5   r6   r7   weightr<   s     r?   r.   MixtralTopKRouter.__init__f   s[    //
!33 ,,ll5;;t/?/?#QRrA   c                 X   UR                  SU R                  5      n[        R                  " XR                  5      n[
        R                  R                  R                  UR                  5       SS9n[
        R                  " X0R                  SS9u  pEXDR                  SSS9-  nUnX&U4$ )NrH   rJ   T)rK   keepdim)reshaper2   FrU   rv   r6   r   rN   softmaxfloattopkru   rR   )r=   rB   router_logitsrouter_probsrouter_top_valuerouter_indicesrouter_scoress          r?   rd   MixtralTopKRouter.forwardm   s    %--b$//B<xx**22=3F3F3Hb2Q+0::lJJTV+W(00R0FF(^;;rA   )r2   r0   ru   rv   )rf   rg   rh   ri   r.   rd   rl   rm   rn   s   @r?   rp   rp   e   s    S< <rA   rp   c                      ^  \ rS rSrU 4S jrS\R                  S\\R                  \R                  4   4S jrSr	U =r
$ )MixtralSparseMoeBlockw   c                    > [         TU ]  5         UR                  U l        UR                  U l        [        U5      U l        [        U5      U l	        g rs   )
r-   r.   rt   ru   router_jitter_noisejitter_noiserp   ra   r(   expertsr<   s     r?   r.   MixtralSparseMoeBlock.__init__x   sA    //
"66%f-	%f-rA   rB   rE   c                    UR                   u  p#nU R                  (       aS  U R                  S:  aC  U[        R                  " U5      R                  SU R                  -
  SU R                  -   5      -  nUR                  SUR                   S   5      nU R                  U5      u  pVnU R                  XU5      nUR                  X#U5      nU$ )Nr         ?rH   )
shapetrainingr   r6   
empty_likeuniform_viewra   r   rz   )r=   rB   
batch_sizesequence_lengthr2   _rD   rC   s           r?   rd   MixtralSparseMoeBlock.forward   s    2?2E2E/
Z==T..2U--m<EEcDL]L]F]_beievev_vwwM%**2}/B/B2/FG(,		-(@%+]O%--j:VrA   )r   ra   r   ru   )rf   rg   rh   ri   r.   r6   rk   tuplerd   rl   rm   rn   s   @r?   r   r   w   s6    .U\\ eELL%,,<V6W  rA   r   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$ )MixtralRMSNorm   epsrE   Nc                    > [         TU ]  5         [        R                  " [        R
                  " U5      5      U l        X l        g)z-
MixtralRMSNorm is equivalent to T5LayerNorm
N)r-   r.   r   r5   r6   onesrv   variance_epsilon)r=   r1   r   r>   s      r?   r.   MixtralRMSNorm.__init__   s/     	ll5::k#:; #rA   rB   c                    UR                   nUR                  [        R                  5      nUR	                  S5      R                  SSS9nU[        R                  " X0R                  -   5      -  nU R                  UR                  U5      -  $ )Nr,   rH   T)ry   )	rY   rX   r6   float32powmeanrsqrtr   rv   )r=   rB   input_dtypevariances       r?   rd   MixtralRMSNorm.forward   sw    #))%((7 $$Q',,R,>%H?T?T4T(UU{{]--k:::rA   c                 ^    [        U R                  R                  5       SU R                   3$ )Nz, eps=)r   rv   r   r   )r=   s    r?   
extra_reprMixtralRMSNorm.extra_repr   s*    ))*+6$2G2G1HIIrA   )r   rv   )gư>)rf   rg   rh   ri   r}   r.   r6   rk   rd   r   rl   rm   rn   s   @r?   r   r      sB    $ $$ $ $;U\\ ;ell ;J JrA   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$ )MixtralRotaryEmbedding   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)r=   r*   devicerope_init_fnr   r>   s        r?   r.   MixtralRotaryEmbedding.__init__   s    "("@"@$*$B$B!44[A!%!E!E>>Y&.t~~>L+7V+L((ZeD0(..2BuUrA   r   ztorch.deviceseq_lenrE   ztorch.Tensorc           	         U R                   S   n[        U SS5      =(       d    U R                  U R                  -  nSnSU[        R
                  " SUS[        R                  S9R                  U[        R                  S9U-  -  -  nXe4$ )	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_dimNr   r   r,   rY   )r   rY   )	r   getattrr1   num_attention_headsr6   arangeint64rX   r}   )r*   r   r   baserK   attention_factorr   s          r?   r   6MixtralRotaryEmbedding.compute_default_rope_parameters   s    & %%l3fj$/c63E3EIcIc3c U\\!S!5;;?BB&X]XcXcBdgjjk
 ))rA   c                 L   U R                   S S S 2S 4   R                  5       R                  UR                  S   SS5      R	                  UR
                  5      nUS S 2S S S 24   R                  5       n[        UR
                  R                  [        5      (       a0  UR
                  R                  S:w  a  UR
                  R                  OSn[        USS9   UR                  5       UR                  5       -  R                  SS5      n[        R                  " Xf4SS	9nUR                  5       U R                  -  nUR                  5       U R                  -  n	S S S 5        WR	                  UR                   S
9W	R	                  UR                   S
94$ ! , (       d  f       N@= f)Nr   rH   r%   mpscpuF)device_typeenabledr,   rJ   r   )r   r}   expandr   rX   r   
isinstancetypestrr!   	transposer6   catcosr   sinrY   )
r=   xposition_idsinv_freq_expandedposition_ids_expandedr   freqsembr   r   s
             r?   rd   MixtralRotaryEmbedding.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   rs   )NNN)rf   rg   rh   ri   r6   rk   __annotations__r&   r.   staticmethodr   intr   r}   r   rM   r   rd   rl   rm   rn   s   @r?   r   r      s    llV} V V  '++/"*$*(* t* 
~u$	%	* *: ]]_<  <rA   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$ )z*Rotates half the hidden dims of the input..NrH   r,   rJ   )r   r6   r   )r   x1x2s      r?   rotate_halfr      sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''rA   rotary_pos_embc                     UR                  U5      nUR                  U5      nX-  [        U 5      U-  -   nX-  [        U5      U-  -   nXV4$ )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          r?   apply_rotary_pos_embr      sS    & --
&C
--
&Cw;q>C/0Gw;q>C/0GrA   rB   n_reprE   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)r   r   rz   )rB   r   batchnum_key_value_headsslenr   s         r?   	repeat_kvr     s_    
 2?1D1D.Ez!!Qa"23::5W\dlmM  e(CTTTrA   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$ )Nr,   r   rH   )rK   rY   )pr   r%   )r   num_key_value_groupsr6   matmulr   r   rN   r|   r   rX   rY   r   r   
contiguous)r   r   r   r   r   r   r   r   
key_statesvalue_statesattn_weightsattn_outputs               r?   eager_attention_forwardr    s     3 ; ;<JU$?$?@L<<';';Aq'ABWLL!#4==((2U]](SVVW\WbWbcL==((6??([L,,|:K''1-88:K$$rA   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	\R                  S-  S
\S-  S\\   S\
\R                  \R                  S-  4   4S jjrSrU =r$ )MixtralAttentioni&  z=Multi-headed attention from 'Attention Is All You Need' paperr*   	layer_idxc                   > [         TU ]  5         Xl        X l        [	        USS 5      =(       d    UR
                  UR                  -  U l        UR                  UR                  -  U l	        U R                  S-  U l
        UR                  U l        SU l        [        R                  " UR
                  UR                  U R                  -  SS9U l        [        R                  " UR
                  UR                  U R                  -  SS9U l        [        R                  " UR
                  UR                  U R                  -  SS9U l        [        R                  " UR                  U R                  -  UR
                  SS9U l        g )Nr   g      TFbias)r-   r.   r*   r  r   r1   r   r   r   r  r   attention_dropout	is_causalr   Linearq_projk_projv_projo_projr=   r*   r  r>   s      r?   r.   MixtralAttention.__init__*  s.   "
D9mV=O=OSYSmSm=m$*$>$>&B\B\$\!}}d*!'!9!9ii 2 2F4N4NQUQ^Q^4^ejkii 2 2F4N4NQUQ^Q^4^ejkii 2 2F4N4NQUQ^Q^4^ejkii : :T]] JFL^L^ejkrA   NrB   position_embeddingsr   past_key_valuesr   rE   c           
      4   UR                   S S n/ UQSPU R                  P7nU R                  U5      R                  U5      R	                  SS5      nU R                  U5      R                  U5      R	                  SS5      n	U R                  U5      R                  U5      R	                  SS5      n
Uu  p[        XX5      u  pUb  UR                  XU R                  5      u  p[        R                  " U R                  R                  [        5      nU" U UU	U
U4U R                  (       d  SOU R                   U R"                  [%        U R                  SS 5      S.UD6u  pUR&                  " / UQSP76 R)                  5       nU R+                  U5      nX4$ )NrH   r%   r,           sliding_window)r   r   r  )r   r   r  r   r   r  r  r   updater  r   get_interfacer*   _attn_implementationr  r   r  r   r   rz   r  r  )r=   rB   r  r   r  r   input_shapehidden_shapequery_statesr  r  r   r   attention_interfacer  r  s                   r?   rd   MixtralAttention.forward8  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+.((rA   )r  r*   r   r  r  r  r  r  r  r   r  rs   )rf   rg   rh   ri   rj   r&   r   r.   r6   rk   r   r	   r   r   rd   rl   rm   rn   s   @r?   r
  r
  &  s    Gl} l l& )-')||') #5<<#=>') t+	')
 ') -.') 
u||U\\D00	1') ')rA   r
  c                     ^  \ 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	\R                  S-  S
\S-  S\\   S\R                  4S jjrSrU =r$ )MixtralDecoderLayerib  r*   r  c                   > [         TU ]  5         UR                  U l        [        X5      U l        [        U5      U l        [        UR                  UR                  S9U l	        [        UR                  UR                  S9U l
        g )Nr   )r-   r.   r1   r
  	self_attnr   mlpr   rms_norm_epsinput_layernormpost_attention_layernormr  s      r?   r.   MixtralDecoderLayer.__init__c  sj    !--)&<(0-f.@.@fFYFYZ(6v7I7IvObOb(c%rA   NrB   r  r   r   r  r   rE   c           	          UnU R                  U5      nU R                  " SUUUUUS.UD6u  pXq-   nUnU R                  U5      nU R                  U5      nXq-   nU$ )N)rB   r  r   r   r   )r,  r)  r-  r*  )	r=   rB   r  r   r   r  r   residualr   s	            r?   rd   MixtralDecoderLayer.forwardm  s     !,,];>> 
' 3)%+
 
 !0 55mD/ 0rA   )r1   r,  r*  r-  r)  )NNNN)rf   rg   rh   ri   r&   r   r.   r6   rk   r   
LongTensorr	   r   r   rd   rl   rm   rn   s   @r?   r&  r&  b  s    d} d d IM.204(,|| #5<<#=>E t+	
 &&-  +, 
 rA   r&  c                      ^  \ 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S9\\S	.r\R*                  " 5       U 4S
 j5       rSrU =r$ )MixtralPreTrainedModeli  r*   modelTr&  r  r   )index)r   rB   
attentionsc                 h  > [         TU ]  U5        U R                  R                  n[	        U[
        5      (       aA  [        R                  " UR                  SUS9  [        R                  " UR                  SUS9  g [	        U[        5      (       a!  [        R                  " UR                  SUS9  g g )Nr  )r   std)r-   _init_weightsr*   initializer_ranger   r(   initnormal_r8   r9   rp   rv   )r=   r   r:  r>   s      r?   r;  $MixtralPreTrainedModel._init_weights  s    f%kk++fn--LL,,3C@LL))= 122LLSc: 3rA   r0  )rf   rg   rh   ri   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#   rp   r&  r
  _can_record_outputsr6   rM   r;  rl   rm   rn   s   @r?   r5  r5    sw    &*#./#4"5N!"&'(9C,& ]]_; ;rA   r5  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$ )MixtralModeli  r*   c           	        > [         TU ]  U5        UR                  U l        UR                  U l        [
        R                  " UR                  UR                  U R                  5      U l        [
        R                  " [        UR                  5       Vs/ s H  n[        X5      PM     sn5      U l        [        UR                  UR                  S9U l        [#        US9U l        SU l        U R)                  5         g s  snf )Nr(  r*   F)r-   r.   pad_token_idpadding_idx
vocab_sizer   	Embeddingr1   embed_tokens
ModuleListrangenum_hidden_layersr&  layersr   r+  normr   
rotary_embgradient_checkpointing	post_initr  s      r?   r.   MixtralModel.__init__  s     !.. ++LL):):F<N<NPTP`P`ammEJ6KcKcEdeEd	 3Ede
 #6#5#56;N;NO	0?&+# 	 fs   C?N	input_idsr   r   r  inputs_embeds	use_cacher   rE   c           
      ~   US L US L-  (       a  [        S5      eU(       a  Uc  [        U R                  S9nUc  U R                  U5      nUcU  Ub  UR	                  5       OSn[
        R                  " UR                  S   UR                  S9U-   nUR                  S5      nU R                  R                  c  [        O[        n	U	" U R                  UUUUS9n
UnU R                  XS9nU R                  S U R                  R                    H  nU" U4U
UUUUS.UD6nM     U R!                  U5      n[#        UUS	9$ )
Nz:You must specify exactly one of input_ids or inputs_embedsrM  r   r%   )r   )r*   r]  r   r  r   )r   )r   r   r  r^  r  )last_hidden_stater  )
ValueErrorr
   r*   rR  get_seq_lengthr6   r   r   r   r   r  r   r   rX  rV  rU  rW  r   )r=   r\  r   r   r  r]  r^  r   past_seen_tokensmask_functioncausal_maskrB   r  decoder_layers                 r?   rd   MixtralModel.forward  s^    -t";<YZZ0*$++>O  --i8MCRC^==?de <<(;(;A(>}G[G[\_ooL'11!4L.2kk.H.H.P*Vw#;;')+%
 &"oomoW![[)H4;;+H+HIM)*) /#$7 M J 		-0%++
 	
rA   )rR  rY  rV  rW  rO  rX  rP  )NNNNNN)rf   rg   rh   ri   r&   r.   r"   r$   r   r6   r3  rk   r	   FloatTensorboolr   r   r   rd   rl   rm   rn   s   @r?   rK  rK    s    }     .2.204(,26!%4
##d*4
 t+4
 &&-	4

 4
 ((4/4
 $;4
 +,4
 
 4
    4
rA   rK  gate_logitsr0   c                    U b  [        U [        5      (       d  g[        U [        5      (       aC  U S   R                  n[        R                  " U  Vs/ s H  oUR                  U5      PM     snSS9n[        R                  R                  R                  WSS9n[        R                  " XrSS9u  p[        R                  R                  R                  X5      n
Uc:  [        R                  " U
R                  5       SS9n[        R                  " USS9nGOUR                  u  pUR                  S   X-  -  nUSSS2SS2SS4   R                  XXU45      R                  SX!5      R                  W5      n[        R                   " U
R                  5       U-  SS9[        R                   " USS9-  nUSSS2SS2S4   R                  XX45      R                  SU5      R                  U5      n[        R                   " UU-  SS9[        R                   " USS9-  n[        R                   " XR#                  S5      -  5      nUU-  $ s  snf )ax  
Computes auxiliary load balancing loss as in Switch Transformer - implemented in Pytorch.

See Switch Transformer (https://huggingface.co/papers/2101.03961) for more details. This function implements the loss
function presented in equations (4) - (6) of the paper. It aims at penalizing cases where the routing between
experts is too unbalanced.

Args:
    gate_logits:
        Logits from the `gate`, should be a tuple of model.config.num_hidden_layers tensors of
        shape [batch_size X sequence_length, num_experts].
    num_experts:
        Number of experts
    top_k:
        The number of experts to route per-token, can be also interpreted as the `top-k` routing
        parameter.
    attention_mask (`torch.Tensor`, *optional*):
        The attention_mask used in forward function
        shape [batch_size X sequence_length] if not None.

Returns:
    The auxiliary loss.
Nr   rJ   rH   )r   r   r   r6   r   rX   r   rN   r|   r~   rO   r   r}   r   r   rz   rR   r   )rj  r0   ru   r   compute_device
layer_gateconcatenated_gate_logitsrouting_weightsr   selected_expertsr[   tokens_per_expertrouter_prob_per_expertr   r   rU  expert_attention_mask router_per_expert_attention_maskoverall_losss                      r?   load_balancing_loss_funcrv    s+   : *[%"@"@+u%%$Q..#(99^i-j^iPZmmN.K^i-jpq#r hh))112JPR1SO**_DA((%%--.>LK!JJ{'8'8':B "'O!C&4&:&:#
4::1=*B^_ 4AtT12V&OKXYWR,R	 	 "IIk&7&7&9<Q&QWXY\a\e\e!q]
 
 4At+,V&OQRWR%R	 	) "'?=]+]cd!ehmhqhq,!i
 "
 99.1Q1QRS1TTUL+%%[ .ks   Ic                   \  ^  \ rS rSrSS0rSS0rSS/S/40rU 4S jr\\	         SS
\
R                  S	-  S\
R                  S	-  S\
R                  S	-  S\S	-  S\
R                  S	-  S\
R                  S	-  S\S	-  S\S	-  S\\
R                  -  S\\   S\4S jj5       5       rSrU =r$ )MixtralForCausalLMiD  zlm_head.weightzmodel.embed_tokens.weightlm_headcolwise_gather_outputrB   logitsc                 J  > [         TU ]  U5        [        U5      U l        UR                  U l        [
        R                  " UR                  UR                  SS9U l        UR                  U l	        UR                  U l        UR                  U l        U R                  5         g )NFr  )r-   r.   rK  r6  rP  r   r  r1   ry  router_aux_loss_coefr/   r0   rt   rZ  r<   s     r?   r.   MixtralForCausalLM.__init__J  s     !&)
 ++yy!3!3V5F5FUS$*$?$?!!33#)#=#=  	rA   Nr\  r   r   r  r]  labelsr^  output_router_logitslogits_to_keepr   rE   c
                 z   Ub  UOU R                   R                  nU R                  " SUUUUUUUS.U
D6nUR                  n[	        U	[
        5      (       a  [        U	* S5      OU	nU R                  USS2USS24   5      nSnUb  U R                  " XU R                  40 U
D6nSnU(       aY  [        UR                  U R                  U R                  U5      nUb*  XR                  UR                  UR                   5      -  -  n[#        UUUUR$                  UR&                  UR(                  UR                  S9$ )a  
labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
    Labels for computing the masked language modeling loss. Indices should either be in `[0, ...,
    config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored
    (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`.

Example:

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

>>> model = MixtralForCausalLM.from_pretrained("mistralai/Mixtral-8x7B-v0.1")
>>> tokenizer = AutoTokenizer.from_pretrained("mistralai/Mixtral-8x7B-v0.1")

>>> 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."
```N)r\  r   r   r  r]  r^  r  )lossaux_lossr{  r  rB   r8  r   r0  )r*   r  r6  r`  r   r   slicery  loss_functionrP  rv  r   r0   rt   r}  rX   r   r   r  rB   r8  )r=   r\  r   r   r  r]  r  r^  r  r  r   outputsrB   slice_indicesr{  r  r  s                    r?   rd   MixtralForCausalLM.forwardV  sP   N %9$D $++JjJj 	
 +/** 	+
)%+'!5	+
 	+
  118B>SV8W8W~ot4]kmA}a,?@A%%fdooPPD/%%  ((	H !11HKK4LLL(#33!//))!//
 	
rA   )ry  r6  r0   rt   r}  rP  )	NNNNNNNNr   )rf   rg   rh   ri   _tied_weights_keys_tp_plan_pp_planr.   r    r   r6   r3  rk   r	   rh  ri  r   r   r   r   rd   rl   rm   rn   s   @r?   rx  rx  D  s5   *,GH23H_-z:;H
  .2.204(,26*.!%,0-.P
##d*P
 t+P
 &&-	P

 P
 ((4/P
   4'P
 $;P
 #TkP
 ell*P
 +,P
 
#P
  P
rA   rx  c                       \ rS rSrSrg) MixtralForSequenceClassificationi  r0  Nrf   rg   rh   ri   rl   r0  rA   r?   r  r        rA   r  c                       \ rS rSrSrg)MixtralForTokenClassificationi  r0  Nr  r0  rA   r?   r  r    r  rA   r  c                       \ rS rSrSrg)MixtralForQuestionAnsweringi  r0  Nr  r0  rA   r?   r  r    r  rA   r  )rx  r  rK  r5  r  r  )r%   )r  )Nr,   N)Qcollections.abcr   typingr   r6   torch.nn.functionalr   rN   r{    r   r=  activationsr   cache_utilsr	   r
   
generationr   integrationsr   r   r   r   masking_utilsr   r   modeling_flash_attention_utilsr   modeling_layersr   r   r   r   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r    utils.genericr!   r"   utils.output_capturingr#   r$   configuration_mixtralr&   Moduler(   rp   r   r   r   r   r   rk   r   r   r}   r  r
  r&  r5  rK  r   rv  rx  r  r  r  __all__r0  rA   r?   <module>r     s  4 %      & ! . )  S B  R K F & I I G E 0 $#RYY $# $#N<		 <$BII & Y'JRYY J (J(><RYY ><B( *+ ,2	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 LL4'% % % '(%2 )*8)ryy 8) +8)v#4 #L ;_ ; ;: H
) H
 H
Z #
*.	O&ell 33d:O&tO& LL4'	O&
 \\CO&d c
/ c
 c
L	'GI_ 		$ACY 		"=?U 	rA   