
    cCik                        S SK JrJr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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Jr  SSKJrJr  SSKJ r J!r!  SSK"J#r#  SSK$J%r%J&r&J'r'  SSK(J)r)  SSK*J+r+  SSK,J-r-  \" S5       " S S\R\                  5      5       r/ " S S\R\                  5      r0S r1S:S jr2S\Rf                  S\4S\Rf                  4S jr5 S;S \R\                  S!\Rf                  S"\Rf                  S#\Rf                  S$\\Rf                     S%\6S&\6S'\#\%   4S( jjr7 " S) S*\R\                  5      r8 " S+ S,\R\                  5      r9 " S- S.\R\                  5      r: " S/ S0\R\                  5      r; " S1 S2\5      r<\& " S3 S4\!5      5       r=\& " S5 S6\=5      5       r>\& " S7 S8\=\5      5       r?/ S9Qr@g)<    )CallableOptionalUnionN)nn   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_forward_from_hub)create_causal_mask!create_sliding_window_causal_mask)FlashAttentionKwargs)GradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuple)deprecate_kwarg)check_model_inputs   )Dots1Config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$ )Dots1RMSNorm,   epsreturnNc                    > [         TU ]  5         [        R                  " [        R
                  " U5      5      U l        X l        g)z+
Dots1RMSNorm is equivalent to T5LayerNorm
N)super__init__r   	Parametertorchonesweightvariance_epsilon)selfhidden_sizer#   	__class__s      b/home/james-whalen/.local/lib/python3.13/site-packages/transformers/models/dots1/modeling_dots1.pyr'   Dots1RMSNorm.__init__.   s/     	ll5::k#:; #    hidden_statesc                    UR                   nUR                  [        R                  5      nUR	                  S5      R                  SSS9nU[        R                  " X0R                  -   5      -  nU R                  UR                  U5      -  $ )N   T)keepdim)	dtypetor)   float32powmeanrsqrtr,   r+   )r-   r3   input_dtypevariances       r0   forwardDots1RMSNorm.forward6   sw    #))%((7 $$Q',,R,>%H?T?T4T(UU{{]--k:::r2   c                 ^    [        U R                  R                  5       SU R                   3$ )Nz, eps=)tupler+   shaper,   )r-   s    r0   
extra_reprDots1RMSNorm.extra_repr=   s*    ))*+6$2G2G1HIIr2   )r,   r+   )gư>)__name__
__module____qualname____firstlineno__floatr'   r)   Tensorr@   rE   __static_attributes____classcell__r/   s   @r0   r!   r!   ,   sB    $ $$ $ $;U\\ ;ell ;J Jr2   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$ )Dots1RotaryEmbeddingA   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defaultrS   F)
persistent)r&   r'   hasattr
isinstancerV   dictgetrW   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrT   r   rope_init_fnattention_scalingregister_bufferrS   original_inv_freq)r-   rT   devicerS   r/   s       r0   r'   Dots1RotaryEmbedding.__init__D   s    6>**z&:M:Mt/T/T#0044[&BUBUBYBYZ`BabDN&DN"("@"@$*$B$B!/?+/+<+<T[[&+Q((ZeD!%r2   c                 b   U R                   S S S 2S 4   R                  5       R                  UR                  S   SS5      R	                  UR
                  5      nUS S 2S S S 24   R                  5       n[        UR
                  R                  [        5      (       a0  UR
                  R                  S:w  a  UR
                  R                  OSn[        R                  " USS9   UR                  5       UR                  5       -  R                  SS5      n[        R                  " Xf4SS	9nUR                  5       U R                  -  nUR                  5       U R                  -  n	S S S 5        WR	                  UR                   S
9W	R	                  UR                   S
94$ ! , (       d  f       N@= f)Nr   r6   r   mpscpuF)device_typeenabledr5   dimr8   )rS   rK   expandrD   r9   rf   r\   rX   strr)   autocast	transposecatcosrc   sinr8   )
r-   xposition_idsinv_freq_expandedposition_ids_expandedrk   freqsembru   rv   s
             r0   r@   Dots1RotaryEmbedding.forwardU   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   $BF  
F.)rc   rT   r`   re   ra   rb   rW   N)rG   rH   rI   rJ   r)   rL   __annotations__r   r'   no_gradr   r@   rM   rN   rO   s   @r0   rQ   rQ   A   s@    ll/{ / /" ]]_<  <r2   rQ   c                     U SSU R                   S   S-  24   nU SU R                   S   S-  S24   n[        R                  " U* U4SS9$ )z*Rotates half the hidden dims of the input..Nr6   r5   rm   )rD   r)   rt   )rw   x1x2s      r0   rotate_halfr   e   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r2   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kru   rv   rx   unsqueeze_dimq_embedk_embeds           r0   apply_rotary_pos_embr   l   sS    ( --
&C
--
&Cw;q>C/0Gw;q>C/0Gr2   r3   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      $ )z
This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,
num_key_value_heads, seqlen, head_dim) to (batch, num_attention_heads, seqlen, head_dim)
r   N)rD   rp   reshape)r3   r   batchnum_key_value_headsslenhead_dims         r0   	repeat_kvr      s_    
 2?1D1D.Ez!!Qa"23::5W\dlmM  e(CTTTr2   modulequerykeyvalueattention_maskscalingdropoutkwargsc                 @   [        X R                  5      n[        X0R                  5      n	[        R                  " XR	                  SS5      5      U-  n
Ub"  US S 2S S 2S S 2S UR
                  S   24   nX-   n
[        R                  R                  U
S[        R                  S9R                  UR                  5      n
[        R                  R                  XU R                  S9n
[        R                  " X5      nUR	                  SS5      R                  5       nX4$ )Nr5   r   r6   )rn   r8   )ptrainingr   )r   num_key_value_groupsr)   matmulrs   rD   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                r0   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$$r2   c                   :  ^  \ 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$ )Dots1Attention   z=Multi-headed attention from 'Attention Is All You Need' paperrT   	layer_idxc                 4  > [         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        [)        U R                  UR*                  S9U l        [)        U R                  UR*                  S9U l        UR0                  U   S:X  a  UR2                  U l        g S U l        g )Nr   g      Tbiasr#   sliding_attention)r&   r'   rT   r   getattrr.   num_attention_headsr   r   r   r   attention_dropout	is_causalr   Linearattention_biasq_projk_projv_projo_projr!   rms_norm_epsq_normk_normlayer_typessliding_windowr-   rT   r   r/   s      r0   r'   Dots1Attention.__init__   s   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
 #4==f6I6IJ"4==f6I6IJ7=7I7I)7TXk7kf33qur2   past_key_valuepast_key_values4.58new_nameversionr3   position_embeddingsr   cache_positionr   r$   c                    UR                   S S n/ UQSPU R                  P7nU R                  U R                  U5      R	                  U5      5      R                  SS5      n	U R                  U R                  U5      R	                  U5      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$  XUS.nUR                  XU R                  U5      u  p[        nU R                  R                  S:w  a  [        U R                  R                     nU" U U	U
UU4U R                   (       d  SOU R"                  U R$                  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$ )Nr6   r   r5   )rv   ru   r   eager        )r   r   r   )rD   r   r   r   viewrs   r   r   r   r   updater   r   rT   _attn_implementationr   r   r   r   r   r   r   r   )r-   r3   r   r   r   r   r   input_shapehidden_shapequery_statesr   r   ru   rv   cache_kwargsattention_interfacer   r   s                     r0   r@   Dots1Attention.forward   s    $))#2.88b8$--8{{4;;}#=#B#B<#PQ[[\]_`a[[]!;!@!@!NOYYZ[]^_
{{=166|DNNqRST&#7RU#[ &#&nUL'6'='=jX\XfXfht'u$J(?;;++w6"9$++:Z:Z"[$7
%
  $}}C$2H2HLL..
%
 
%
!\ "));;;;FFHkk+.L((r2   )r   rT   r   r   r   r   r   r   r   r   r   r   r   r   NN)rG   rH   rI   rJ   __doc__r   intr'   r   r)   rL   rC   r   r	   
LongTensorr   r   r@   rM   rN   rO   s   @r0   r   r      s    Gv{ vs v4 %0A6R ,059*)||*) #5<<#=>*) !.	*)
 "%*) !!1!12*) -.*) 
u||Xell33	4*) S*)r2   r   c                   2   ^  \ rS rSrSU 4S jjrS rSrU =r$ )Dots1MLP   c                   > [         TU ]  5         Xl        Uc  UR                  OUU l        Uc  UR                  OUU l        [
        R                  " U R                  U R                  SS9U l        [
        R                  " U R                  U R                  SS9U l        [
        R                  " U R                  U R                  SS9U l	        [        UR                     U l        g NFr   )r&   r'   rT   r.   intermediate_sizer   r   	gate_projup_proj	down_projr   
hidden_actact_fn)r-   rT   r.   r   r/   s       r0   r'   Dots1MLP.__init__   s    1<1D6--+=N=V!9!9\m4#3#3T5K5KRWXyy!1!143I3IPUV4#9#94;K;KRWXV../r2   c                     U R                  U R                  U R                  U5      5      U R                  U5      -  5      nU$ r~   )r   r   r   r   )r-   rw   r   s      r0   r@   Dots1MLP.forward  s6    NN4;;t~~a/@#ADLLQRO#ST	r2   )r   rT   r   r   r.   r   r   r   )rG   rH   rI   rJ   r'   r@   rM   rN   rO   s   @r0   r   r      s    	0 r2   r   c                      ^  \ rS rSrSrU 4S jrS\R                  S\R                  S\R                  4S jrS r	S	r
U =r$ )
Dots1MoEi	  z2
A mixed expert module containing shared experts.
c           
      B  > [         TU ]  5         Xl        [        R                  " [        UR                  5       Vs/ s H  n[        XR                  S9PM     sn5      U l	        [        U5      U l        [        XR                  UR                  -  S9U l        g s  snf )N)r   )rT   r   )r&   r'   rT   r   
ModuleListrangen_routed_expertsr   moe_intermediate_sizeexpertsDots1TopkRoutergaten_shared_expertsshared_experts)r-   rT   _r/   s      r0   r'   Dots1MoE.__init__  s    }}W\]c]t]tWuvWuRSXf0L0LMWuv
 $F+	&-I-IFLcLc-c
 ws   Br3   topk_indicestopk_weightsc                 J   [         R                  " XR                  S9n[         R                  R                  R                  U[        U R                  5      S9nUR                  SSS5      n[        [        U R                  5      5       H{  nU R                  U   nXV   n[         R                  " U5      u  pU	R                  5       S:  d  MD  X9U
4   nX   nU" U5      nXR                  S5      -  nUR                  SX5        M}     UR                  UR                  5      $ )z
CALL FOR CONTRIBUTION! I don't have time to optimise this right now, but expert weights need to be fused
to not have to do a loop here (deepseek has 256 experts soooo yeah).
ro   )num_classesr5   r   r   r6   )r)   
zeros_liker8   r   r   one_hotlenr   permuter   wherenumelr   
index_add_rX   )r-   r3   r   r   final_hidden_statesexpert_mask
expert_idxexpertmasktoken_indicesweight_indicesexpert_weightsexpert_inputexpert_outputweighted_outputs                  r0   moeDots1MoE.moe  s   
 $..}DVDVWhh))11,CPTP\P\L]1^!))!Q2DLL 12J\\*-F*D,1KK,=)M""$q(!-^.K!L,; &| 4"/2J2J22N"N#..q-Q 3 #''(;(;<<r2   c                     UnUR                   nU R                  U5      u  pEUR                  SUR                   S   5      nU R                  XU5      R                  " U6 nXR	                  U5      -   nU$ )Nr6   )rD   r   r   r  r   )r-   r3   	residuals
orig_shaper   r   s         r0   r@   Dots1MoE.forward3  su    !	"((
%)YY}%="%**2}/B/B2/FGlKPPR\]%(;(;I(FFr2   )rT   r   r   r   )rG   rH   rI   rJ   r   r'   r)   rL   r  r@   rM   rN   rO   s   @r0   r   r   	  s@    	
= =U\\ =Y^YeYe =4 r2   r   c                   \   ^  \ rS rSrU 4S jr\R                  " 5       S 5       rS rSr	U =r
$ )r   i=  c                   > [         TU ]  5         Xl        UR                  U l        UR
                  U l        UR                  U l        UR                  U l        UR                  U l        UR                  U l	        [        R                  " [        R                  " U R
                  UR                  45      5      U l        U R!                  S[        R"                  " U R
                  5      5        g )Ne_score_correction_bias)r&   r'   rT   num_experts_per_toktop_kr   routed_scaling_factorn_group
topk_groupnorm_topk_probr   r(   r)   emptyr.   r+   rd   zerosr-   rT   r/   s     r0   r'   Dots1TopkRouter.__init__>  s    //
 & 7 7%+%A%A"~~ ++$33ll5;;0E0EvGYGY/Z#[\6DDYDY8Z[r2   c                    UR                  SU R                  5      U R                  R                  S5      -   nUR                  SU R                  U R                  U R                  -  5      R                  SSS9S   R                  SS9n[        R
                  " X0R                  SSS9S   n[        R                  " U5      nUR                  SUS5        UR                  S5      R                  SU R                  U R                  U R                  -  5      R                  SU R                  5      nUR                  UR                  5       ) S5      n[        R
                  " X R                  SSS9S   nU$ )	Nr6   r   r5   rm   F)r   rn   sortedr   r   )r   r   r  r   r  topksumr)   r  r   scatter_rp   r   masked_fillboolr  )r-   scoresscores_for_choicegroup_scores	group_idx
group_mask
score_maskr   s           r0   get_topk_indices Dots1TopkRouter.get_topk_indicesK  sB   "KKD,A,ABTEaEaEkEklmEnn""2t||T5J5Jdll5Z[T!T_Q SRS[ 	
 JJ|BuUVWX	%%l3
Ay!,  $VBd&;&;t||&KLWR../ 	
 .99:??;L:LcRzz"3zzrRWXYZ[r2   c                    UR                  SU R                  R                  5      n[        R                  " UR                  [        R                  5      U R                  R                  [        R                  5      5      nUR                  5       nU R                  U5      nUR                  SU5      nU R                  (       a  UR                  SSS9S-   nXV-  nXPR                  -  nXE4$ )Nr6   r   T)rn   r7   g#B;)r   rT   r.   FlinearrX   r)   r:   r+   sigmoidr0  gatherr  r&  r  )r-   r3   router_logitsr*  r   r   denominators          r0   r@   Dots1TopkRouter.forward_  s    %**2t{{/F/FG!3!3EMM!BDKKDTDTUZUbUbDcd&&(,,V4}}Q5&**r4*@5HK'L#&@&@@))r2   )rT   r  r   r  r  r  r  r+   )rG   rH   rI   rJ   r'   r)   r   r0  r@   rM   rN   rO   s   @r0   r   r   =  s-    \ ]]_ &
* 
*r2   r   c                   H  ^  \ rS rSrS\S\4U 4S jjr\" SSSS9      SS	\R                  S
\
\R                     S\
\R                     S\
\   S\
\   S\
\R                     S\
\\R                  \R                  4      S\\   S\R                  4S jj5       rSrU =r$ )Dots1DecoderLayeril  rT   r   c                 t  > [         TU ]  5         UR                  U l        [        XS9U l        X!R
                  :  a  [        U5      U l        O[        U5      U l        [        UR                  UR                  S9U l        [        UR                  UR                  S9U l        UR                  U   U l        g )N)rT   r   r   )r&   r'   r.   r   	self_attnfirst_k_dense_replacer   mlpr   r!   r   input_layernormpost_attention_layernormr   attention_typer   s      r0   r'   Dots1DecoderLayer.__init__m  s    !--'vK444'DH'DH+F,>,>FDWDWX(4V5G5GVM`M`(a%$00;r2   r   r   r   r   r3   r   rx   	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)r3   r   rx   r   rD  r   r    )r@  r=  rA  r?  )r-   r3   r   rx   r   rD  r   r   r   residualr   s              r0   r@   Dots1DecoderLayer.forward|  s     !,,];>> 	
')%+) 3	
 	
 !0 !55mD/ 0r2   )rB  r.   r@  r?  rA  r=  )NNNFNN)rG   rH   rI   rJ   r   r   r'   r   r)   rL   r   r   r	   r)  rC   r   r   r@   rM   rN   rO   s   @r0   r;  r;  l  s    <{ <s < %0A6R 2637+/$)59KO|| !. u//0	
 "% D> !!1!12 &eELL%,,,F&GH +, 
 Sr2   r;  c                   f   ^  \ rS rSr% \\S'   SrSrS/rS/r	Sr
SrSrSrSr\\S.rU 4S	 jrS
rU =r$ )Dots1PreTrainedModeli  rT   modelTr;  r   F)r3   
attentionsc                    > [         TU ]  U5        [        U[        5      (       a9  UR                  R
                  R                  SU R                  R                  S9  g g )Nr   )r<   std)	r&   _init_weightsr\   r   r+   datanormal_rT   initializer_range)r-   r   r/   s     r0   rO  "Dots1PreTrainedModel._init_weights  sI    f%fo..MM&&CT[[5R5R&S /r2   rF  )rG   rH   rI   rJ   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_outputsrO  rM   rN   rO   s   @r0   rJ  rJ    s^    &*#,-#4"5N""&*$
T Tr2   rJ  c                   "  ^  \ rS rSrS\4U 4S jjr\" 5       \       SS\\	R                     S\\	R                     S\\	R                     S\\   S\\	R                     S	\\   S
\\	R                     S\\   S\4S jj5       5       rSrU =r$ )
Dots1Modeli  rT   c           	      D  > [         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        SU R(                  R*                  ;   U l        U R/                  5         g s  snf )Nr   rT   Fr   )r&   r'   pad_token_idpadding_idx
vocab_sizer   	Embeddingr.   embed_tokensr   r   num_hidden_layersr;  layersr!   r   normrQ   
rotary_embgradient_checkpointingrT   r   has_sliding_layers	post_initr   s      r0   r'   Dots1Model.__init__  s     !.. ++LL):):F<N<NPTP`P`ammCHIaIaCbcCbiv1Cbc
 !!3!39L9LM	.f=&+#"59P9P"P 	 ds   D	input_idsr   rx   r   inputs_embedsrD  r   r   r$   c                    US L US L-  (       a  [        S5      eUc  U R                  U5      nU(       a  Uc  [        U R                  S9nUcD  Ub  UR	                  5       OSn	[
        R                  " XUR                  S   -   UR                  S9nUc  UR                  S5      n[        U=n
[        5      (       d?  U R                  UUUUUS.nS[        S0 UD60n
U R                  (       a  [        S0 UD6U
S'   UnU R                  X5      nU R                   S U R                  R"                    H  nU" U4XR$                     UUUUUS	.UD6nM!     U R'                  U5      n[)        UU(       a  US
9$ S S
9$ )Nz:You must specify exactly one of input_ids or inputs_embedsra  r   r   )rf   )rT   input_embedsr   r   r   rx   full_attentionr   )r   rx   r   rD  r   r   )last_hidden_stater   rF  )
ValueErrorrf  r
   rT   get_seq_lengthr)   arangerD   rf   r   r\   r]   r   rl  r   rj  rh  rg  rB  ri  r   )r-   ro  r   rx   r   rp  rD  r   r   past_seen_tokenscausal_mask_mappingmask_kwargsr3   r   decoder_layers                  r0   r@   Dots1Model.forward  s    -t";<YZZ  --i8M0*$++>O!CRC^==?de"\\ ]5H5H5K"KTaThThN )33A6L ?-FF ++ -"0"0#2 ,K !"4"C{"C# &&;\;k_j;k#$78% #oomJ![[)H4;;+H+HIM)	23O3OP) /#-$7	 	M J 		-0&+/8O
 	
>B
 	
r2   )rf  rk  rl  rh  ri  rc  rj  rd  )NNNNNNN)rG   rH   rI   rJ   r   r'   r   r   r   r)   r   rL   r	   FloatTensorr)  r   r   r   r@   rM   rN   rO   s   @r0   r_  r_    s    { "  151537+/59$(59E
E,,-E
 !.E
 u//0	E

 "%E
   1 12E
 D>E
 !!1!12E
 +,E
 
!E
  E
r2   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$ )Dots1ForCausalLMi  zlm_head.weightlm_headcolwise_repr3   logitsc                    > [         TU ]  U5        [        U5      U l        UR                  U l        [
        R                  " UR                  UR                  SS9U l        U R                  5         g r   )
r&   r'   r_  rK  rd  r   r   r.   r  rm  r!  s     r0   r'   Dots1ForCausalLM.__init__  sU     '
 ++yy!3!3V5F5FUS 	r2   ro  r   rx   r   rp  labelsrD  r   logits_to_keepr   r$   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$ )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, Dots1ForCausalLM

>>> model = Dots1ForCausalLM.from_pretrained("rednote-hilab/dots1.llm1.inst")
>>> tokenizer = AutoTokenizer.from_pretrained("rednote-hilab/dots1.llm1.inst")

>>> 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."
```)ro  r   rx   r   rp  rD  r   N)r  r  rd  )lossr  r   r3   rL  rF  )rK  rt  r\   r   slicer  loss_functionrT   rd  r   r   r3   rL  )r-   ro  r   rx   r   rp  r  rD  r   r  r   outputsr3   slice_indicesr  r  s                   r0   r@   Dots1ForCausalLM.forward"  s    J ,0:: 	,
)%+')	,
 	,
  118B>SV8W8W~ot4]kmA}a,?@A%%pVt{{OeOepiopD%#33!//))
 	
r2   )r  rK  rd  )	NNNNNNNNr   )rG   rH   rI   rJ   _tied_weights_keys_tp_plan_pp_planr'   r   r   r   r)   r   rL   r	   r}  r)  r   r   r   r   r   r@   rM   rN   rO   s   @r0   r  r    s0   *+=)H_-z:;H  151537+/59-1$(5934=
E,,-=
 !.=
 u//0	=

 "%=
   1 12=
 ))*=
 D>=
 !!1!12=
 c5<</0=
 +,=
 
 =
  =
r2   r  )rJ  r_  r  )Nr   )r   )Atypingr   r   r   r)   torch.nn.functionalr   r   r3  activationsr   cache_utilsr	   r
   
generationr   integrationsr   masking_utilsr   r   modeling_flash_attention_utilsr   modeling_layersr   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.deprecationr   utils.genericr   configuration_dots1r   Moduler!   rQ   r   r   rL   r   r   rK   r   r   r   r   r   r;  rJ  r_  r  __all__rF  r2   r0   <module>r     s  * - ,     ! . ) 7 R B 9 O K F & I I 0 / , Y'J299 J (J(!<299 !<H(6	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 U\\*% % % '(%4H)RYY H)Vryy "1ryy 1h,*bii ,*^02 0f T? T T, Y
% Y
 Y
x M
+_ M
 M
` Er2   