
    cCi&                    (   S r SSKrSSKJrJr  SSKrSSKJr  SSKJrJ	r	J
r
  SSKJr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JrJrJrJrJrJrJr  SSKJ r   SSK!J"r"J#r#J$r$  SSK%J&r&J'r'  SSK(J)r)  SSK*J+r+  \'RX                  " \-5      r. " S S\R^                  5      r0 " S S\R^                  5      r1 " S S\R^                  5      r2 " S S\R^                  5      r3 " S S\R^                  5      r4 " S S\R^                  5      r5 " S S\R^                  5      r6 " S  S!\5      r7 " S" S#\R^                  5      r8 " S$ S%\R^                  5      r9\& " S& S'\ 5      5       r:\&" S(S)9 " S* S+\:5      5       r;\&" S,S)9 " S- S.\:\5      5       r<\& " S/ S0\:5      5       r= " S1 S2\R^                  5      r>\&" S3S)9 " S4 S5\:5      5       r?\& " S6 S7\:5      5       r@\& " S8 S9\:5      5       rA " S: S;\R^                  5      rB\& " S< S=\:5      5       rCS@S> jrD/ S?QrEg)AzPyTorch X-MOD model.    N)OptionalUnion)nn)BCEWithLogitsLossCrossEntropyLossMSELoss   )ACT2FNgelu)CacheDynamicCacheEncoderDecoderCache)GenerationMixin)GradientCheckpointingLayer))BaseModelOutputWithPastAndCrossAttentions,BaseModelOutputWithPoolingAndCrossAttentions!CausalLMOutputWithCrossAttentionsMaskedLMOutputMultipleChoiceModelOutputQuestionAnsweringModelOutputSequenceClassifierOutputTokenClassifierOutput)PreTrainedModel)apply_chunking_to_forward find_pruneable_heads_and_indicesprune_linear_layer)auto_docstringlogging)deprecate_kwarg   )
XmodConfigc                   >   ^  \ rS rSrSrU 4S jr SS jrS rSrU =r	$ )XmodEmbeddings1   zN
Same as BertEmbeddings with a tiny tweak for positional embeddings indexing.
c                   > [         TU ]  5         [        R                  " UR                  UR
                  UR                  S9U l        [        R                  " UR                  UR
                  5      U l	        [        R                  " UR                  UR
                  5      U l        [        R                  " UR
                  UR                  S9U l        [        R                  " UR                  5      U l        [#        USS5      U l        U R'                  S[(        R*                  " UR                  5      R-                  S5      SS9  U R'                  S	[(        R.                  " U R0                  R3                  5       [(        R4                  S
9SS9  UR                  U l        [        R                  " UR                  UR
                  U R6                  S9U l	        g )N)padding_idxepsposition_embedding_typeabsoluteposition_ids)r    F)
persistenttoken_type_idsdtype)super__init__r   	Embedding
vocab_sizehidden_sizepad_token_idword_embeddingsmax_position_embeddingsposition_embeddingstype_vocab_sizetoken_type_embeddings	LayerNormlayer_norm_epsDropouthidden_dropout_probdropoutgetattrr)   register_buffertorcharangeexpandzerosr+   sizelongr&   selfconfig	__class__s     `/home/james-whalen/.local/lib/python3.13/site-packages/transformers/models/xmod/modeling_xmod.pyr2   XmodEmbeddings.__init__7   si   !||F,=,=v?Q?Q_e_r_rs#%<<0N0NPVPbPb#c %'\\&2H2H&J\J\%]" f&8&8f>S>STzz&"<"<='.v7PR\']$ELL)G)GHOOPWXej 	 	
 	ekk$*;*;*@*@*B%**Ubg 	 	

 "..#%<<**F,>,>DL\L\$
     c                    Uc+  Ub  [        XR                  U5      nOU R                  U5      nUb  UR                  5       nOUR                  5       S S nUS   nUcv  [	        U S5      (       a-  U R
                  S S 2S U24   nUR                  US   U5      n	U	nO8[        R                  " U[        R                  U R                  R                  S9nUc  U R                  U5      nU R                  U5      n
XJ-   nU R                  S:X  a  U R                  U5      nX-  nU R!                  U5      nU R#                  U5      nU$ )Nr,   r    r.   r   r0   devicer*   )"create_position_ids_from_input_idsr&   &create_position_ids_from_inputs_embedsrG   hasattrr.   rE   rC   rF   rH   r+   rR   r7   r;   r)   r9   r<   r@   )rJ   	input_idsr.   r+   inputs_embedspast_key_values_lengthinput_shape
seq_lengthbuffered_token_type_ids buffered_token_type_ids_expandedr;   
embeddingsr9   s                rM   forwardXmodEmbeddings.forwardP   sM    $A)M]M]_uv#JJ=Y #..*K',,.s3K ^

 !t-..*.*=*=a*n*M'3J3Q3QR]^_R`bl3m0!A!&[

SWSdSdSkSk!l  00;M $ : :> J":
'':5"&":":<"H-J^^J/
\\*-
rO   c                    UR                  5       SS nUS   n[        R                  " U R                  S-   X0R                  -   S-   [        R                  UR
                  S9nUR                  S5      R                  U5      $ )z
We are provided embeddings directly. We cannot infer which are padded so just generate sequential position ids.

Args:
    inputs_embeds: torch.Tensor

Returns: torch.Tensor
Nr,   r    rQ   r   )rG   rC   rD   r&   rH   rR   	unsqueezerE   )rJ   rW   rY   sequence_lengthr+   s        rM   rT   5XmodEmbeddings.create_position_ids_from_inputs_embedsx   s~     $((*3B/%a.||q /4D4D"Dq"HPUPZPZcpcwcw
 %%a(//<<rO   )r<   r@   r&   r)   r9   r;   r7   )NNNNr   )
__name__
__module____qualname____firstlineno____doc__r2   r^   rT   __static_attributes____classcell__rL   s   @rM   r#   r#   1   s$    

4 rs&P= =rO   r#   c                     ^  \ rS rSrSU 4S jjr\" SSSS9      SS\R                  S\\R                     S	\\R                     S
\\R                     S\\
   S\\   S\\R                     S\\R                     4S jj5       rSrU =r$ )XmodSelfAttention   c                   > [         TU ]  5         UR                  UR                  -  S:w  a7  [	        US5      (       d&  [        SUR                   SUR                   S35      eUR                  U l        [        UR                  UR                  -  5      U l        U R                  U R                  -  U l        [        R                  " UR                  U R                  5      U l        [        R                  " UR                  U R                  5      U l        [        R                  " UR                  U R                  5      U l        [        R                  " UR                  5      U l        U=(       d    [#        USS5      U l        U R$                  S:X  d  U R$                  S	:X  aG  UR&                  U l        [        R(                  " S
UR&                  -  S-
  U R                  5      U l        UR,                  U l        X0l        g )Nr   embedding_sizezThe hidden size (z6) is not a multiple of the number of attention heads ()r)   r*   relative_keyrelative_key_query   r    )r1   r2   r5   num_attention_headsrU   
ValueErrorintattention_head_sizeall_head_sizer   Linearquerykeyvaluer>   attention_probs_dropout_probr@   rA   r)   r8   r3   distance_embedding
is_decoder	layer_idxrJ   rK   r)   r   rL   s       rM   r2   XmodSelfAttention.__init__   s    : ::a?PVXhHiHi#F$6$6#7 8 445Q8 
 $*#=#= #&v'9'9F<V<V'V#W !558P8PPYYv1143E3EF
99V//1C1CDYYv1143E3EF
zz&"E"EF'> (
'-zC
$ ''>9T=Y=Y]q=q+1+I+ID(&(ll1v7U7U3UXY3Y[_[s[s&tD# ++"rO   past_key_valuepast_key_values4.58new_nameversionhidden_statesattention_mask	head_maskencoder_hidden_statesoutput_attentionscache_positionreturnc                 	   UR                   u  pn
U R                  U5      nUR                  USU R                  U R                  5      R                  SS5      nSnUS LnUb]  [        U[        5      (       aF  UR                  R                  U R                  5      nU(       a  UR                  nOUR                  nOUnU(       a  UOUnU(       aQ  UbN  U(       aG  WR                  U R                     R                  nUR                  U R                     R                  nOU R!                  U5      nUR                  USU R                  U R                  5      R                  SS5      nU R#                  U5      nUR                  USU R                  U R                  5      R                  SS5      nUbc  U(       d  UOS nWR%                  UUU R                  SU05      u  nnU(       a.  [        U[        5      (       a  SUR                  U R                  '   [&        R(                  " UUR                  SS5      5      nU R*                  S:X  d  U R*                  S	:X  Ga  UR                   S   UR                   S   nnUbB  [&        R,                  " US-
  [&        R.                  UR0                  S
9R                  SS5      nO>[&        R2                  " U[&        R.                  UR0                  S
9R                  SS5      n[&        R2                  " U[&        R.                  UR0                  S
9R                  SS5      nUU-
  nU R5                  UU R6                  -   S-
  5      nUR9                  UR:                  S9nU R*                  S:X  a  [&        R<                  " SUU5      nUU-   nOHU R*                  S	:X  a8  [&        R<                  " SUU5      n[&        R<                  " SUU5      nUU-   U-   nU[>        R@                  " U R                  5      -  nUb  UU-   n[B        RD                  RG                  USS9nU RI                  U5      nUb  UU-  n[&        R(                  " UU5      nURK                  SSSS5      RM                  5       nURO                  5       S S U RP                  4-   nUR                  U5      nUU4$ )Nr,   r    rt   Fr   Trr   rs   rQ   r/   zbhld,lrd->bhlrzbhrd,lrd->bhlrdimr   r	   ))shaper{   viewru   rx   	transpose
isinstancer   
is_updatedgetr   cross_attention_cacheself_attention_cachelayerskeysvaluesr|   r}   updaterC   matmulr)   tensorrH   rR   rD   r   r8   tor0   einsummathsqrtr   
functionalsoftmaxr@   permute
contiguousrG   ry   )rJ   r   r   r   r   r   r   r   
batch_sizerZ   _query_layerr   is_cross_attentioncurr_past_key_valuecurrent_states	key_layervalue_layerattention_scoresquery_length
key_lengthposition_ids_lposition_ids_rdistancepositional_embeddingrelative_position_scoresrelative_position_scores_queryrelative_position_scores_keyattention_probscontext_layernew_context_layer_shapes                                  rM   r^   XmodSelfAttention.forward   sa    %2$7$7!
jj/!&&z2t7O7OQUQiQijttq
 
2$>&/+>??,77;;DNNK
%*9*O*O'*9*N*N'&5#2D.-/"=*+224>>BGGI-44T^^DKKK0I!z2t7O7OQUQiQijtt1I **^4K%**B 8 8$:R:Ri1o  *7It)<)C)C{DNN=M~<^*&	; &*_FY*Z*ZAEO..t~~> !<<Y5H5HR5PQ''>9T=Y=Y]q=q'2'8'8';Y__Q=O*L*!&j1nEJJWdWkWk!l!q!q" "'l%**UbUiUi!j!o!oprtu!v"\\*EJJ}OcOcdiijkmopN%6H#'#:#:8dFbFb;bef;f#g #7#:#:ARAR#:#S ++~=+0<<8H+Wk+l(#36N#N --1EE16>NP[]q1r./4||<LiYm/n,#36T#TWs#s +dii8P8P.QQ%/.@ --//0@b/I ,,7  -	9O_kB%--aAq9DDF"/"4"4"6s";t?Q?Q>S"S%**+BCo--rO   )ry   rx   r   r@   r   r|   r   r8   ru   r)   r{   r}   NNNNNNFN)rd   re   rf   rg   r2   r   rC   Tensorr   FloatTensorr   booltupler^   ri   rj   rk   s   @rM   rm   rm      s    #6 %0A6R 7;15=A+/,115e.||e. !!2!23e. E--.	e.
  ((9(9:e. "%e. $D>e. !.e. 
u||	e. Se.rO   rm   c                   z   ^  \ rS rSrU 4S jrS\R                  S\R                  S\R                  4S jrSrU =r	$ )XmodSelfOutputi  c                 (  > [         TU ]  5         [        R                  " UR                  UR                  5      U l        [        R                  " UR                  UR                  S9U l        [        R                  " UR                  5      U l
        g Nr'   )r1   r2   r   rz   r5   denser<   r=   r>   r?   r@   rI   s     rM   r2   XmodSelfOutput.__init__  s`    YYv1163E3EF
f&8&8f>S>STzz&"<"<=rO   r   input_tensorr   c                 R    U R                  U5      nU R                  U5      nX-   nU$ N)r   r@   )rJ   r   r   s      rM   r^   XmodSelfOutput.forward  s,    

=1]3%4rO   )r<   r   r@   
rd   re   rf   rg   r2   rC   r   r^   ri   rj   rk   s   @rM   r   r     s6    >U\\  RWR^R^  rO   r   c                   $  ^  \ rS rSrSU 4S jjrS r\" SSSS9      SS\R                  S	\	\R                     S
\	\R                     S\	\R                     S\	\   S\	\   S\	\R                     S\\R                     4S jj5       rSrU =r$ )XmodAttentioni  c                    > [         TU ]  5         [        XUS9U l        [	        U5      U l        [        5       U l        UR                  U l        g )Nr)   r   )	r1   r2   rm   rJ   r   outputsetpruned_headspre_normr   s       rM   r2   XmodAttention.__init__   s>    %firs	$V,ErO   c                 6   [        U5      S:X  a  g [        XR                  R                  U R                  R                  U R
                  5      u  p[        U R                  R                  U5      U R                  l        [        U R                  R                  U5      U R                  l        [        U R                  R                  U5      U R                  l	        [        U R                  R                  USS9U R                  l        U R                  R                  [        U5      -
  U R                  l        U R                  R                  U R                  R                  -  U R                  l        U R
                  R                  U5      U l        g )Nr   r    r   )lenr   rJ   ru   rx   r   r   r{   r|   r}   r   r   ry   union)rJ   headsindexs      rM   prune_headsXmodAttention.prune_heads(  s   u:?79900$))2O2OQUQbQb

 -TYY__eD		*499==%@		,TYY__eD		.t{{/@/@%QO )-		(E(EE
(R		%"&))"?"?$))B_B_"_		 --33E:rO   r   r   r   r   r   r   r   r   r   r   r   c           	      $   UnU R                   (       a  U R                  R                  U5      nU R                  UUUUUUU5      n	U R                  U	S   U5      n
U R                   (       d  U R                  R                  U
5      n
U
4U	SS  -   nU$ )Nr   r    )r   r   r<   rJ   )rJ   r   r   r   r   r   r   r   residualself_outputsattention_outputoutputss               rM   r^   XmodAttention.forward:  s     !== KK11-@Myy!
  ;;|AA}}#{{445EF#%QR(88rO   )r   r   r   rJ   r   r   )rd   re   rf   rg   r2   r   r   rC   r   r   r   r   r   r   r^   ri   rj   rk   s   @rM   r   r     s    (;$ %0A6R 7;15=A+/,115|| !!2!23 E--.	
  ((9(9: "% $D> !. 
u||	 SrO   r   c                   b   ^  \ rS rSrU 4S jrS\R                  S\R                  4S jrSrU =r	$ )XmodIntermediateiY  c                   > [         TU ]  5         [        R                  " UR                  UR
                  5      U l        [        UR                  [        5      (       a  [        UR                     U l        g UR                  U l        g r   )r1   r2   r   rz   r5   intermediate_sizer   r   
hidden_actstrr
   intermediate_act_fnrI   s     rM   r2   XmodIntermediate.__init__Z  s`    YYv1163K3KL
f''--'-f.?.?'@D$'-'8'8D$rO   r   r   c                 J    U R                  U5      nU R                  U5      nU$ r   r   r   rJ   r   s     rM   r^   XmodIntermediate.forwardb  s&    

=100?rO   r   r   rk   s   @rM   r   r   Y  s(    9U\\ ell  rO   r   c                   b   ^  \ rS rSrU 4S jrS\R                  S\R                  4S jrSrU =r	$ )XmodAdapterih  c                   > [         TU ]  5         UR                  UR                  -  U l        [
        R                  " UR                  U R                  5      U l        [
        R                  " U R                  UR                  5      U l        [        UR                  [        5      (       a  [        UR                     U l        g UR                  U l        g r   )r1   r2   r5   adapter_reduction_factorbottleneck_sizer   rz   dense1dense2r   r   r   r
   adapter_act_fnrI   s     rM   r2   XmodAdapter.__init__i  s    %11V5T5TTii 2 2D4H4HIii 4 4f6H6HIf''--"():):";D"("3"3DrO   r   r   c                 l    U R                  U5      nU R                  U5      nU R                  U5      nU$ r   )r   r   r   r   s     rM   r^   XmodAdapter.forwards  s4    M2++M:M2rO   )r   r   r   r   r   rk   s   @rM   r   r   h  s(    4U\\ ell  rO   r   c                      ^  \ rS rSrU 4S jrS\R                  S\R                  S\R                  S\R                  4S jrS\R                  S\R                  4S jrS	r	U =r
$ )

XmodOutputiz  c                   > [         TU ]  5         [        R                  " UR                  UR
                  5      U l        [        R                  " UR
                  UR                  S9U l        UR                  U l	        [        R                  " UR                  5      U l        UR                  (       a/  [        R                  " UR
                  UR                  S9U l        OS U l        UR                  U l        [        R                  " 0 5      U l        UR"                   H$  n[%        U5      U R                   ['        U5      '   M&     g r   )r1   r2   r   rz   r   r5   r   r<   r=   ln_before_adapterr>   r?   r@   adapter_layer_normadapter_reuse_layer_norm
ModuleDictadapter_modules	languagesr   r   )rJ   rK   languagerL   s      rM   r2   XmodOutput.__init__{  s    YYv779K9KL
f&8&8f>S>ST!'!9!9zz&"<"<=$$&(ll63E3E6K`K`&aD#&*D#(.(G(G%!}}R0((H2=f2ED  X/ )rO   r   r   lang_idsr   c                 t    U R                  U5      nU R                  U5      nX-   nU R                  X15      nU$ r   )r   r@   lang_adapter)rJ   r   r   r
  s       rM   r^   XmodOutput.forward  s<    

=1]3%4))(BrO   c                    [         R                  " USS9u  pU R                  (       d  UnU R                  b  U R                  U5      nO"U R                  (       a  U R                  U5      nU R                  (       a  Un[         R                  " X#R                  5       S5      n/ n[        [        X5      5       Hi  u  nu  p[        U R                  R                  5       5      [        UR                  5       5         n
UR                  U R                  U
   " U	5      5        Mk     [         R                   " US5      nU R#                  U5      nUW-  nU$ )NT)return_countsr   )rC   unique_consecutiver  r  r  r<   splittolist	enumerateziplistr  r   rw   itemappendcatr@   )rJ   r
  r   lang_lengthsr   split_hidden_stateslang_wise_outputsilang_idsplit_hidden_statelangs              rM   r  XmodOutput.lang_adapter  s   !&!9!9(RV!W%%$H"". 33MBM** NN=9M!!$H#kk-9L9L9NPQR09#h:\0],A,,,1134S5HID$$T%9%9$%?@R%ST 1^ 		"3Q7]3!rO   )r<   r  r  r  r   r@   r  )rd   re   rf   rg   r2   rC   r   r^   r  ri   rj   rk   s   @rM   r   r   z  s`    FU\\  Y^YeYe jojvjv U\\ %,,  rO   r   c                   \  ^  \ rS rSrSU 4S jjr\" SSSS9       SS\R                  S\R                  S	\\R                     S
\\R                     S\\R                     S\\R                     S\\
   S\\   S\\R                     S\\R                     4S jj5       rS rSrU =r$ )	XmodLayeri  c                   > [         TU ]  5         UR                  U l        SU l        [	        XS9U l        UR                  U l        UR                  U l        U R                  (       a/  U R                  (       d  [        U  S35      e[	        USUS9U l	        [        U5      U l        [        U5      U l        UR                  U l        g )Nr    r   z> should be used as a decoder model if cross attention is addedr*   r   )r1   r2   chunk_size_feed_forwardseq_len_dimr   	attentionr   add_cross_attentionrv   crossattentionr   intermediater   r   r   )rJ   rK   r   rL   s      rM   r2   XmodLayer.__init__  s    '-'E'E$&vC ++#)#=#= ##?? D6)g!hii"/PZfo"pD,V4 (rO   r   r   r   r   r   r
  r   r   r   encoder_attention_maskr   r   r   c
           
      $   U R                  UUUUUU	S9n
U
S   nU
SS  nU R                  (       aD  UbA  [        U S5      (       d  [        SU  S35      eU R	                  UUUUUUU	S9nUS   nXSS  -   nUnU R
                  (       a  U R                  R                  U5      n[        U R                  U R                  U R                  U5      nU R                  XU5      nU R
                  (       d  U R                  R                  U5      nU4U-   $ )N)r   r   r   r   r   r   r    r)  z'If `encoder_hidden_states` are passed, z` has to be instantiated with cross-attention layers by setting `config.add_cross_attention=True`)r   r   r   r   r   r   )r'  r   rU   rv   r)  r   r   r<   r   feed_forward_chunkr%  r&  )rJ   r   r
  r   r   r   r,  r   r   r   self_attention_outputsr   r   cross_attention_outputsr   intermediate_outputlayer_outputs                    rM   r^   XmodLayer.forward  sN    "&)/+) "0 "
 2!4(,??4@4!122 =dV DD D 
 '+&9&9 5#&; /"3- ': '#  7q9 ;;G#==#{{445EF7##((	
 {{#6(K}};;00>L((rO   c                 $    U R                  U5      $ r   )r*  )rJ   r   s     rM   r.  XmodLayer.feed_forward_chunk  s      !122rO   )	r(  r'  r%  r)  r*  r   r   r   r&  r   )NNNNNFN)rd   re   rf   rg   r2   r   rC   r   r   r   r   r   r   r^   r.  ri   rj   rk   s   @rM   r"  r"    s    ( %0A6R
 7;15=A>B+/,1156)||6) ,,6) !!2!23	6)
 E--.6)  ((9(9:6) !)):): ;6) "%6) $D>6) !.6) 
u||	6) S6)p3 3rO   r"  c                   j  ^  \ rS rSrU 4S jr          SS\R                  S\R                  S\\R                     S\\R                     S\\R                     S\\R                     S	\\	   S
\\
   S\\
   S\\
   S\\
   S\\R                     S\\\R                     \4   4S jjrSrU =r$ )XmodEncoderi  c           
      r  > [         TU ]  5         Xl        [        R                  " [        UR                  5       Vs/ s H  n[        XS9PM     sn5      U l        UR                  U l
        U R                  (       a.  [        R                  " UR                  UR                  S9U l        SU l        g s  snf )Nr$  r'   F)r1   r2   rK   r   
ModuleListrangenum_hidden_layersr"  layerr   is_pre_normr<   r5   r=   gradient_checkpointing)rJ   rK   r  rL   s      rM   r2   XmodEncoder.__init__  s    ]]ERXRjRjLk#lLkqIf$BLk#lm
!??\\&*<*<&BWBWXDN&+#	 $ms   B4r   r
  r   r   r   r,  r   	use_cacher   output_hidden_statesreturn_dictr   r   c                    U R                   (       a/  U R                  (       a  U(       a  [        R                  S5        SnU(       a1  Uc.  [	        [        U R                  S9[        U R                  S95      nU(       a@  [        U[        5      (       a+  [        R                  S5        [        R                  " U5      nU
(       a  SOS nU	(       a  SOS nU	(       a  U R                  R                  (       a  SOS n[        U R                  5       Hi  u  nnU
(       a  X4-   nUb  UU   OS nU" UUUUUUUU	U5	      nUS   nU	(       d  M:  UUS   4-   nU R                  R                  (       d  M`  UUS   4-   nMk     U R                  (       a  U R                  U5      nU
(       a  X4-   nU(       d  [        S	 UUUUU4 5       5      $ [        UUUUUS
9$ )NzZ`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...F)rK   zPassing a tuple of `past_key_values` is deprecated and will be removed in Transformers v4.58.0. You should pass an instance of `EncoderDecoderCache` instead, e.g. `past_key_values=EncoderDecoderCache.from_legacy_cache(past_key_values)`. r   r    rt   c              3   0   #    U  H  nUc  M  Uv   M     g 7fr   rD  ).0vs     rM   	<genexpr>&XmodEncoder.forward.<locals>.<genexpr>F  s"      
A  s   	)last_hidden_stater   r   
attentionscross_attentions)r>  trainingloggerwarning_oncer   r   rK   r   r   from_legacy_cacher(  r  r<  r=  r<   r   )rJ   r   r
  r   r   r   r,  r   r@  r   rA  rB  r   all_hidden_statesall_self_attentionsall_cross_attentionsr  layer_modulelayer_head_masklayer_outputss                       rM   r^   XmodEncoder.forward  s    &&4==##p "	01,dkk2RT`hlhshsTtuOOU;;\
 2CCOTO"6BD$5b4%64;;;Z;Zr`d(4OA|#$58H$H!.7.CilO(%&!
M *!,M  &9]1=M<O&O#;;222+?=QRCSBU+U(-  50  NN=9M 14D D 
 "#%'(
 
 
 9+++*1
 	
rO   )r<   rK   r>  r=  r<  )
NNNNNNFFTN)rd   re   rf   rg   r2   rC   r   r   r   r   r   r   r   r   r^   ri   rj   rk   s   @rM   r7  r7    s&   , 7;15=A>B+/$(,1/4&*15T
||T
 ,,T
 !!2!23	T

 E--.T
  ((9(9:T
 !)):): ;T
 "%T
 D>T
 $D>T
 'tnT
 d^T
 !.T
 
uU\\"$MM	NT
 T
rO   r7  c                   b   ^  \ rS rSrU 4S jrS\R                  S\R                  4S jrSrU =r	$ )
XmodPooleri[  c                    > [         TU ]  5         [        R                  " UR                  UR                  5      U l        [        R                  " 5       U l        g r   )r1   r2   r   rz   r5   r   Tanh
activationrI   s     rM   r2   XmodPooler.__init__\  s9    YYv1163E3EF
'')rO   r   r   c                 \    US S 2S4   nU R                  U5      nU R                  U5      nU$ Nr   )r   r\  )rJ   r   first_token_tensorpooled_outputs       rM   r^   XmodPooler.forwarda  s6     +1a40

#566rO   )r\  r   r   rk   s   @rM   rY  rY  [  s(    $
U\\ ell  rO   rY  c                   B    \ rS rSr% \\S'   SrSrS rS\	4S jr
S rS	rg
)XmodPreTrainedModelij  rK   robertaTc                    [        U[        R                  5      (       ak  UR                  R                  R                  SU R                  R                  S9  UR                  b%  UR                  R                  R                  5         gg[        U[        R                  5      (       ax  UR                  R                  R                  SU R                  R                  S9  UR                  b2  UR                  R                  UR                     R                  5         gg[        U[        R                  5      (       aJ  UR                  R                  R                  5         UR                  R                  R                  S5        g[        U[        5      (       a%  UR                  R                  R                  5         gg)zInitialize the weightsg        )meanstdNg      ?)r   r   rz   weightdatanormal_rK   initializer_rangebiaszero_r3   r&   r<   fill_
XmodLMHead)rJ   modules     rM   _init_weights!XmodPreTrainedModel._init_weightsq  s2   fbii(( MM&&CT[[5R5R&S{{&  &&( '--MM&&CT[[5R5R&S!!-""6#5#56<<> .--KK""$MM$$S)
++KK""$ ,rO   r  c           	          XR                   R                  ;  a0  [        U  SU S[        U R                   R                  5       35      eXR                   l        g)z
Set the default language code for the model. This is used when the language is not specified in the input.

Args:
    language (`str`): The language code, such as `"en_XX"` or `"de_DE"`.
z does not have an adapter for z. Supported languages: N)rK   r  rv   r  default_language)rJ   r  s     rM   set_default_language(XmodPreTrainedModel.set_default_language  sW     ;;000&6xj@WX\]a]h]h]r]rXsWtu  (0$rO   c                     [         R                  S5        U R                  R                  R	                  5        H
  nSUl        M     [         R                  S5        U R                  R                  R                   H~  nUR                  R                  b2  UR                  R                  R	                  5        H
  nSUl        M     UR                  R                  R	                  5        H
  nSUl        M     M     g)z
Freeze the embeddings and language adapters of the model. Usually, this is applied before the model is
fine-tuned on a downstream task.
zFreezing embeddingsFzFreezing adaptersN)rN  infore  r]   
parametersrequires_gradencoderr<  r   r  r  )rJ   	parameterr<  s      rM   'freeze_embeddings_and_language_adapters;XmodPreTrainedModel.freeze_embeddings_and_language_adapters  s    
 	)*00;;=I&+I# >'(\\))//E||..:!&!@!@!K!K!MI.3I+ "N"\\99DDF	*/	' G	 0rO   rD  N)rd   re   rf   rg   r!   __annotations__base_model_prefixsupports_gradient_checkpointingrr  r   rv  r~  ri   rD  rO   rM   rd  rd  j  s*    !&*#%$0S 00rO   rd  a0  
    The model can behave as an encoder (with only self-attention) as well as a decoder, in which case a layer of
    cross-attention is added between the self-attention layers, following the architecture described in *Attention is
    all you need*_ by Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz
    Kaiser and Illia Polosukhin.

    To behave as an decoder the model needs to be initialized with the `is_decoder` argument of the configuration set
    to `True`. To be used in a Seq2Seq model, the model needs to initialized with both `is_decoder` argument and
    `add_cross_attention` set to `True`; an `encoder_hidden_states` is then expected as an input to the forward pass.

    .. _*Attention is all you need*: https://huggingface.co/papers/1706.03762
    )custom_introc            $         ^  \ rS rSrSU 4S jjrS rS rS r\               SS\	\
R                     S\	\
R                     S\	\
R                     S	\	\
R                     S
\	\
R                     S\	\
R                     S\	\
R                     S\	\
R                     S\	\
R                     S\	\   S\	\   S\	\   S\	\   S\	\   S\	\
R                     S\\\
R                     \4   4 S jj5       rSrU =r$ )	XmodModeli  c                    > [         TU ]  U5        Xl        [        U5      U l        [        U5      U l        U(       a  [        U5      OSU l        U R                  5         g)z^
add_pooling_layer (bool, *optional*, defaults to `True`):
    Whether to add a pooling layer
N)
r1   r2   rK   r#   r]   r7  r|  rY  pooler	post_init)rJ   rK   add_pooling_layerrL   s      rM   r2   XmodModel.__init__  sK    
 	 (0"6*,=j(4 	rO   c                 .    U R                   R                  $ r   r]   r7   rJ   s    rM   get_input_embeddingsXmodModel.get_input_embeddings  s    ...rO   c                 $    XR                   l        g r   r  )rJ   r}   s     rM   set_input_embeddingsXmodModel.set_input_embeddings  s    */'rO   c                     UR                  5        H7  u  p#U R                  R                  U   R                  R	                  U5        M9     g)z
Prunes heads of the model. heads_to_prune: dict of {layer_num: list of heads to prune in this layer} See base
class PreTrainedModel
N)itemsr|  r<  r'  r   )rJ   heads_to_pruner<  r   s       rM   _prune_headsXmodModel._prune_heads  s<    
 +002LELLu%//;;EB 3rO   rV   r
  r   r.   r+   r   rW   r   r,  r   r@  r   rA  rB  r   r   c                 Z   Ub  UOU R                   R                  nUb  UOU R                   R                  nUb  UOU R                   R                  nU R                   R                  (       a  Ub  UOU R                   R
                  nOSnUb  Ub  [        S5      eUb"  U R                  X5        UR                  5       nO"Ub  UR                  5       SS nO[        S5      eUu  nnUb  UR                  OUR                  nSnU
b:  [        U
[        5      (       d  U
S   S   R                  S   OU
R                  5       nUc  U R                   R                  c  [        S5      e[        U R                   R"                  S   R$                  R&                  R)                  5       5      nUR+                  U R                   R                  5      nU[,        R.                  " UUS	9-  nUc  [,        R.                  " UUU-   4US	9nUcs  [1        U R2                  S
5      (       a4  U R2                  R4                  SS2SU24   nUR7                  UU5      nUnO$[,        R8                  " U[,        R:                  US9nU R=                  UU5      nU R                   R                  (       aE  UbB  UR                  5       u  nnnUU4nU	c  [,        R.                  " UUS	9n	U R?                  U	5      nOSnU RA                  X`R                   RB                  5      nU R3                  UUUUUS9nU R!                  UUUUUUU
UUUUUS9n U S   n!U RD                  b  U RE                  U!5      OSn"U(       d
  U!U"4U SS -   $ [G        U!U"U RH                  U RJ                  U RL                  U RN                  S9$ )
lang_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
    Indices of the language adapters that should be activated for each sample, respectively. Default: the index
    that corresponds to `self.config.default_language`.
NFzDYou cannot specify both input_ids and inputs_embeds at the same timer,   z5You have to specify either input_ids or inputs_embedsr   r   zPInput language unknown. Please call `XmodPreTrainedModel.set_default_language()`)rR   r.   rQ   )rV   r+   r.   rW   rX   )r
  r   r   r   r,  r   r@  r   rA  rB  r   r    )rJ  pooler_outputr   r   rK  rL  )(rK   r   rA  use_return_dictr   r@  rv   %warn_if_padding_and_no_attention_maskrG   rR   r   r   r   get_seq_lengthru  r  r|  r<  r   r  r   r   rC   onesrU   r]   r.   rE   rF   rH   get_extended_attention_maskinvert_attention_maskget_head_maskr;  r  r   r   r   rK  rL  )#rJ   rV   r
  r   r.   r+   r   rW   r   r,  r   r@  r   rA  rB  r   rY   r   rZ   rR   rX   adapter_languagesdefault_lang_idr[   r\   extended_attention_maskencoder_batch_sizeencoder_sequence_lengthr   encoder_hidden_shapeencoder_extended_attention_maskembedding_outputencoder_outputssequence_outputra  s#                                      rM   r^   XmodModel.forward  s   0 2C1N-TXT_T_TqTq$8$D $++JjJj 	 &1%<k$++B]B];;!!%.%:	@U@UII ]%>cdd"66yQ#..*K&',,.s3KTUU!,
J%.%:!!@T@T!"& "/599  "1%++B/$335 # {{++3 !stt $T\\%7%7%:%A%A%Q%Q%V%V%X Y/55dkk6R6RSO&Jv)NNH!"ZZ*jCY6Y)ZdjkN!t(899*.//*H*HKZK*X'3J3Q3QR\^h3i0!A!&[

SY!Z 150P0PQ_al0m ;;!!&;&G=R=W=W=Y: 7$68O#P %-).4HQW)X&.2.H.HI_.`+.2+ &&y++2O2OP	??%)'#9 + 
 ,,2"7#B+/!5#) ' 
 *!,8<8OO4UY#]3oab6III;-'+;;)77&11,==
 	
rO   )rK   r]   r|  r  )T)NNNNNNNNNNNNNNN)rd   re   rf   rg   r2   r  r  r  r   r   rC   r   
LongTensorr   r   r   r   r   r^   ri   rj   rk   s   @rM   r  r    s    "/0C  -1/31515/3,0048<9=+/$(,0/3&*15!A
ELL)A
 5++,A
 !.	A

 !.A
 u||,A
 ELL)A
  -A
  (5A
 !) 6A
 "%A
 D>A
 $D>A
 'tnA
 d^A
  !.!A
" 
uU\\"$PP	Q#A
 A
rO   r  zQ
    X-MOD Model with a `language modeling` head on top for CLM fine-tuning.
    c            &         ^  \ rS rSrSS/rU 4S j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\	\   S\	\   S\	\   S\	\   S\	\   S\	\
R                     S\\\
R                     \4   4"S jj5       rSrU =r$ )XmodForCausalLMiW  lm_head.decoder.weightlm_head.decoder.biasc                    > [         TU ]  U5        UR                  (       d  [        R	                  S5        [        USS9U l        [        U5      U l        U R                  5         g )NzLIf you want to use `XmodLMHeadModel` as a standalone, add `is_decoder=True.`Fr  
r1   r2   r   rN  warningr  re  rp  lm_headr  rI   s     rM   r2   XmodForCausalLM.__init__`  sL       NNij 5A!&) 	rO   c                 .    U R                   R                  $ r   r  decoderr  s    rM   get_output_embeddings%XmodForCausalLM.get_output_embeddingsm      ||###rO   c                 $    XR                   l        g r   r  rJ   new_embeddingss     rM   set_output_embeddings%XmodForCausalLM.set_output_embeddingsq      -rO   rV   r
  r   r.   r+   r   rW   r   r,  labelsr   r@  r   rA  rB  r   r   c                    Ub  UOU R                   R                  nU
b  SnU R                  UUUUUUUUU	UUUUUUS9nUS   nU R                  U5      nSnU
b*  U R                  " UU
4SU R                   R
                  0UD6nU(       d  U4USS -   nUb  U4U-   $ U$ [        UUUR                  UR                  UR                  UR                  S9$ )a  
lang_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
    Indices of the language adapters that should be activated for each sample, respectively. Default: the index
    that corresponds to `self.config.default_language`.
labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
    Labels for computing the left-to-right language modeling loss (next word prediction). Indices should be in
    `[-100, 0, ..., config.vocab_size]` (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, XmodForCausalLM, AutoConfig
>>> import torch

>>> tokenizer = AutoTokenizer.from_pretrained("FacebookAI/xlm-roberta-base")
>>> config = AutoConfig.from_pretrained("facebook/xmod-base")
>>> config.is_decoder = True
>>> model = XmodForCausalLM.from_pretrained("facebook/xmod-base", config=config)
>>> model.set_default_language("en_XX")

>>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
>>> outputs = model(**inputs)

>>> prediction_logits = outputs.logits
```NF)r
  r   r.   r+   r   rW   r   r,  r   r@  r   rA  rB  r   r   r4   rt   )losslogitsr   r   rK  rL  )rK   r  re  r  loss_functionr4   r   r   r   rK  rL  )rJ   rV   r
  r   r.   r+   r   rW   r   r,  r  r   r@  r   rA  rB  r   kwargsr   r  prediction_scoreslm_lossr   s                          rM   r^   XmodForCausalLM.forwardt  s%   ^ &1%<k$++B]B]I,,))%'"7#9+/!5#)  
$ "!* LL9((!  ;;11 	G ')GABK7F,3,?WJ'KVK0$#33!//))$55
 	
rO   r  re  )NNNNNNNNNNNNNNNN)rd   re   rf   rg   _tied_weights_keysr2   r  r  r   r   rC   r  r   r   r   r   r   r   r   r^   ri   rj   rk   s   @rM   r  r  W  s    34JK
$.  15/36:59371559=A>B-1+/$(,0/3&*15#[
E,,-[
 5++,[
 !!2!23	[

 !!1!12[
 u//0[
 E--.[
   1 12[
  ((9(9:[
 !)):): ;[
 ))*[
 "%[
 D>[
 $D>[
 'tn[
  d^![
" !.#[
& 
uU\\"$EE	F'[
 [
rO   r  c                      ^  \ rS rSrSS/rU 4S j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\	\   S\	\   S\	\   S\\\
R                      \4   4S jj5       rSrU =r$ )XmodForMaskedLMi  r  r  c                    > [         TU ]  U5        UR                  (       a  [        R	                  S5        [        USS9U l        [        U5      U l        U R                  5         g )NzkIf you want to use `XmodForMaskedLM` make sure `config.is_decoder=False` for bi-directional self-attention.Fr  r  rI   s     rM   r2   XmodForMaskedLM.__init__  sR     NN1
 !5A!&) 	rO   c                 .    U R                   R                  $ r   r  r  s    rM   r  %XmodForMaskedLM.get_output_embeddings  r  rO   c                 $    XR                   l        g r   r  r  s     rM   r  %XmodForMaskedLM.set_output_embeddings  r  rO   rV   r
  r   r.   r+   r   rW   r   r,  r  r   rA  rB  r   c                    Ub  UOU R                   R                  nU R                  UUUUUUUUU	UUUS9nUS   nU R                  U5      nSnU
bF  [	        5       nU" UR                  SU R                   R                  5      U
R                  S5      5      nU(       d  U4USS -   nUb  U4U-   $ U$ [        UUUR                  UR                  S9$ )av  
lang_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
    Indices of the language adapters that should be activated for each sample, respectively. Default: the index
    that corresponds to `self.config.default_language`.
labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
    Labels for computing the masked language modeling loss. Indices should be in `[-100, 0, ...,
    config.vocab_size]` (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]`
N)r
  r   r.   r+   r   rW   r   r,  r   rA  rB  r   r,   rt   r  r  r   rK  )
rK   r  re  r  r   r   r4   r   r   rK  )rJ   rV   r
  r   r.   r+   r   rW   r   r,  r  r   rA  rB  r   r  r  masked_lm_lossloss_fctr   s                       rM   r^   XmodForMaskedLM.forward  s   4 &1%<k$++B]B],,))%'"7#9/!5#  
 "!* LL9')H%&7&<&<RAWAW&XZ`ZeZefhZijN')GABK7F3A3M^%.YSYY$!//))	
 	
rO   r  )NNNNNNNNNNNNN)rd   re   rf   rg   r  r2   r  r  r   r   rC   r  r   r   r   r   r   r   r^   ri   rj   rk   s   @rM   r  r    sr   24JK $.  15/36:59371559=A>B-1,0/3&*:
E,,-:
 5++,:
 !!2!23	:

 !!1!12:
 u//0:
 E--.:
   1 12:
  ((9(9::
 !)):): ;:
 ))*:
 $D>:
 'tn:
 d^:
 
uU\\"N2	3:
 :
rO   r  c                   8   ^  \ rS rSrSrU 4S jrS rS rSrU =r	$ )rp  i.  z*Roberta Head for masked language modeling.c                   > [         TU ]  5         [        R                  " UR                  UR                  5      U l        [        R                  " UR                  UR                  S9U l        [        R                  " UR                  UR                  5      U l
        [        R                  " [        R                  " UR                  5      5      U l        U R                  U R                  l        g r   )r1   r2   r   rz   r5   r   r<   r=   
layer_normr4   r  	ParameterrC   rF   rm  rI   s     rM   r2   XmodLMHead.__init__1  s    YYv1163E3EF
,,v'9'9v?T?TUyy!3!3V5F5FGLLV->->!?@	 IIrO   c                     U R                  U5      n[        U5      nU R                  U5      nU R                  U5      nU$ r   )r   r   r  r  rJ   featuresr  xs       rM   r^   XmodLMHead.forward:  s;    JJx GOOA LLOrO   c                     U R                   R                  R                  R                  S:X  a  U R                  U R                   l        g U R                   R                  U l        g )Nmeta)r  rm  rR   typer  s    rM   _tie_weightsXmodLMHead._tie_weightsD  sC     <<##((F2 $		DLL))DIrO   )rm  r  r   r  )
rd   re   rf   rg   rh   r2   r^   r  ri   rj   rk   s   @rM   rp  rp  .  s    4&* *rO   rp  z
    X-MOD Model transformer with a sequence classification/regression head on top (a linear layer on top of the pooled
    output) e.g. for GLUE tasks.
    c                     ^  \ rS rSrU 4S jr\           SS\\R                     S\\R                     S\\R                     S\\R                     S\\R                     S\\R                     S	\\R                     S
\\R                     S\\
   S\\
   S\\
   S\\\R                     \4   4S jj5       rSrU =r$ )XmodForSequenceClassificationiM  c                    > [         TU ]  U5        UR                  U l        Xl        [	        USS9U l        [        U5      U l        U R                  5         g NFr  )	r1   r2   
num_labelsrK   r  re  XmodClassificationHead
classifierr  rI   s     rM   r2   &XmodForSequenceClassification.__init__U  sH      ++ 5A08 	rO   rV   r
  r   r.   r+   r   rW   r  r   rA  rB  r   c                 2   Ub  UOU R                   R                  nU R                  UUUUUUUU	U
US9
nUS   nU R                  U5      nSnUGb  U R                   R                  c  U R
                  S:X  a  SU R                   l        OoU R
                  S:  aN  UR                  [        R                  :X  d  UR                  [        R                  :X  a  SU R                   l        OSU R                   l        U R                   R                  S:X  aI  [        5       nU R
                  S:X  a&  U" UR                  5       UR                  5       5      nOU" X5      nOU R                   R                  S:X  a=  [        5       nU" UR                  SU R
                  5      UR                  S5      5      nO,U R                   R                  S:X  a  [        5       nU" X5      nU(       d  U4US	S -   nUb  U4U-   $ U$ [        UUUR                   UR"                  S
9$ )aa  
lang_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
    Indices of the language adapters that should be activated for each sample, respectively. Default: the index
    that corresponds to `self.config.default_language`.
labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
    Labels for computing the sequence classification/regression loss. Indices should be in `[0, ...,
    config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If
    `config.num_labels > 1` a classification loss is computed (Cross-Entropy).
N	r
  r   r.   r+   r   rW   r   rA  rB  r   r    
regressionsingle_label_classificationmulti_label_classificationr,   rt   r  )rK   r  re  r  problem_typer  r0   rC   rH   rw   r   squeezer   r   r   r   r   rK  rJ   rV   r
  r   r.   r+   r   rW   r  r   rA  rB  r   r  r  r  r  r   s                     rM   r^   %XmodForSequenceClassification.forward`  s   0 &1%<k$++B]B],,))%'/!5#  
 "!*1{{''/??a'/;DKK,__q(fllejj.HFLL\a\e\eLe/LDKK,/KDKK,{{''<7"9??a'#FNN$4fnn6FGD#F3D))-JJ+-B @&++b/R))-II,./Y,F)-)9TGf$EvE'!//))	
 	
rO   )r  rK   r  re  NNNNNNNNNNN)rd   re   rf   rg   r2   r   r   rC   r  r   r   r   r   r   r   r^   ri   rj   rk   s   @rM   r  r  M  s;   	  15/36:59371559-1,0/3&*H
E,,-H
 5++,H
 !!2!23	H

 !!1!12H
 u//0H
 E--.H
   1 12H
 ))*H
 $D>H
 'tnH
 d^H
 
uU\\"$<<	=H
 H
rO   r  c                     ^  \ rS rSrU 4S jr\           SS\\R                     S\\R                     S\\R                     S\\R                     S\\R                     S\\R                     S	\\R                     S
\\R                     S\\
   S\\
   S\\
   S\\\R                     \4   4S jj5       rSrU =r$ )XmodForMultipleChoicei  c                    > [         TU ]  U5        [        U5      U l        [        R
                  " UR                  5      U l        [        R                  " UR                  S5      U l
        U R                  5         g )Nr    )r1   r2   r  re  r   r>   r?   r@   rz   r5   r  r  rI   s     rM   r2   XmodForMultipleChoice.__init__  sV      (zz&"<"<=))F$6$6: 	rO   rV   r
  r.   r   r  r+   r   rW   r   rA  rB  r   c                    Ub  UOU R                   R                  nUb  UR                  S   OUR                  S   nUb!  UR                  SUR	                  S5      5      OSnUb2  UR                  UR	                  S5      UR	                  S5      -  5      OSnUb!  UR                  SUR	                  S5      5      OSnUb!  UR                  SUR	                  S5      5      OSnUb!  UR                  SUR	                  S5      5      OSnUb1  UR                  SUR	                  S5      UR	                  S5      5      OSnU R                  UUUUUUUU	U
US9
nUS   nU R                  U5      nU R                  U5      nUR                  SU5      nSnUb  [        5       nU" UU5      nU(       d  U4USS -   nUb  U4U-   $ U$ [        UUUR                  UR                  S9$ )	a  
input_ids (`torch.LongTensor` of shape `(batch_size, num_choices, sequence_length)`):
    Indices of input sequence tokens in the vocabulary.

    Indices can be obtained using [`AutoTokenizer`]. See [`PreTrainedTokenizer.encode`] and
    [`PreTrainedTokenizer.__call__`] for details.

    [What are input IDs?](../glossary#input-ids)
lang_ids (`torch.LongTensor` of shape `(batch_size, num_choices, sequence_length)`, *optional*):
    Indices of the language adapters that should be activated for each sample, respectively. Default: the index
    that corresponds to `self.config.default_language`.
token_type_ids (`torch.LongTensor` of shape `(batch_size, num_choices, sequence_length)`, *optional*):
    Segment token indices to indicate first and second portions of the inputs. Indices are selected in `[0,
    1]`:

    - 0 corresponds to a *sentence A* token,
    - 1 corresponds to a *sentence B* token.

    [What are token type IDs?](../glossary#token-type-ids)
labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
    Labels for computing the multiple choice classification loss. Indices should be in `[0, ...,
    num_choices-1]` where `num_choices` is the size of the second dimension of the input tensors. (See
    `input_ids` above)
position_ids (`torch.LongTensor` of shape `(batch_size, num_choices, sequence_length)`, *optional*):
    Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0,
    config.max_position_embeddings - 1]`.

    [What are position IDs?](../glossary#position-ids)
inputs_embeds (`torch.FloatTensor` of shape `(batch_size, num_choices, sequence_length, hidden_size)`, *optional*):
    Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This
    is useful if you want more control over how to convert `input_ids` indices into associated vectors than the
    model's internal embedding lookup matrix.
Nr    r,   r   r   )	r
  r+   r.   r   r   rW   r   rA  rB  rt   r  )rK   r  r   r   rG   repeatre  r@   r  r   r   r   rK  )rJ   rV   r
  r.   r   r  r+   r   rW   r   rA  rB  num_choicesflat_input_idsflat_lang_idsflat_position_idsflat_token_type_idsflat_attention_maskflat_inputs_embedsr   ra  r  reshaped_logitsr  r  r   s                             rM   r^   XmodForMultipleChoice.forward  s   ` &1%<k$++B]B],5,Aiooa(}GZGZ[\G]CLCXINN2,>?^bRZRf	q(9INN1<M(MNlpLXLdL--b,2C2CB2GHjnR`Rln11"n6I6I"6MNrvR`Rln11"n6I6I"6MNrv ( r=#5#5b#9=;M;Mb;QR 	 ,,"*..,/!5#  
  
]3/ ++b+6')HOV4D%''!"+5F)-)9TGf$EvE("!//))	
 	
rO   )r  r@   re  r  )rd   re   rf   rg   r2   r   r   rC   r  r   r   r   r   r   r   r^   ri   rj   rk   s   @rM   r  r    s;     15/3596:-1371559,0/3&*]
E,,-]
 5++,]
 !!1!12	]

 !!2!23]
 ))*]
 u//0]
 E--.]
   1 12]
 $D>]
 'tn]
 d^]
 
uU\\"$==	>]
 ]
rO   r  c                     ^  \ rS rSrU 4S jr\           SS\\R                     S\\R                     S\\R                     S\\R                     S\\R                     S\\R                     S	\\R                     S
\\R                     S\\
   S\\
   S\\
   S\\\R                     \4   4S jj5       rSrU =r$ )XmodForTokenClassificationi  c                 d  > [         TU ]  U5        UR                  U l        [        USS9U l        UR
                  b  UR
                  OUR                  n[        R                  " U5      U l	        [        R                  " UR                  UR                  5      U l        U R                  5         g r  )r1   r2   r  r  re  classifier_dropoutr?   r   r>   r@   rz   r5   r  r  rJ   rK   r  rL   s      rM   r2   #XmodForTokenClassification.__init__  s      ++ 5A)/)B)B)NF%%TZTnTn 	 zz"45))F$6$68I8IJ 	rO   rV   r
  r   r.   r+   r   rW   r  r   rA  rB  r   c                    Ub  UOU R                   R                  nU R                  UUUUUUUU	U
US9
nUS   nU R                  U5      nU R	                  U5      nSnUb<  [        5       nU" UR                  SU R                  5      UR                  S5      5      nU(       d  U4USS -   nUb  U4U-   $ U$ [        UUUR                  UR                  S9$ )a  
lang_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
    Indices of the language adapters that should be activated for each sample, respectively. Default: the index
    that corresponds to `self.config.default_language`.
labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
    Labels for computing the token classification loss. Indices should be in `[0, ..., config.num_labels - 1]`.
Nr  r   r,   rt   r  )rK   r  re  r@   r  r   r   r  r   r   rK  r  s                     rM   r^   "XmodForTokenClassification.forward+  s    , &1%<k$++B]B],,))%'/!5#  
 "!*,,71')HFKKDOO<fkk"oNDY,F)-)9TGf$EvE$!//))	
 	
rO   )r  r@   r  re  r  )rd   re   rf   rg   r2   r   r   rC   r  r   r   r   r   r   r   r^   ri   rj   rk   s   @rM   r  r    s-     15/36:59371559-1,0/3&*7
E,,-7
 5++,7
 !!2!23	7

 !!1!127
 u//07
 E--.7
   1 127
 ))*7
 $D>7
 'tn7
 d^7
 
uU\\"$99	:7
 7
rO   r  c                   2   ^  \ rS rSrSrU 4S jrS rSrU =r$ )r  ig  z-Head for sentence-level classification tasks.c                 b  > [         TU ]  5         [        R                  " UR                  UR                  5      U l        UR                  b  UR                  OUR                  n[        R                  " U5      U l	        [        R                  " UR                  UR                  5      U l        g r   )r1   r2   r   rz   r5   r   r  r?   r>   r@   r  out_projr  s      rM   r2   XmodClassificationHead.__init__j  s    YYv1163E3EF
)/)B)B)NF%%TZTnTn 	 zz"45		&"4"4f6G6GHrO   c                     US S 2SS S 24   nU R                  U5      nU R                  U5      n[        R                  " U5      nU R                  U5      nU R	                  U5      nU$ r_  )r@   r   rC   tanhr  r  s       rM   r^   XmodClassificationHead.forwards  sY    Q1WLLOJJqMJJqMLLOMM!rO   )r   r@   r  )	rd   re   rf   rg   rh   r2   r^   ri   rj   rk   s   @rM   r  r  g  s    7I rO   r  c                     ^  \ rS rSrU 4S jr\            SS\\R                     S\\R                     S\\R                     S\\R                     S\\R                     S\\R                     S	\\R                     S
\\R                     S\\R                     S\\
   S\\
   S\\
   S\\\R                     \4   4S jj5       rSrU =r$ )XmodForQuestionAnsweringi}  c                    > [         TU ]  U5        UR                  U l        [        USS9U l        [
        R                  " UR                  UR                  5      U l        U R                  5         g r  )
r1   r2   r  r  re  r   rz   r5   
qa_outputsr  rI   s     rM   r2   !XmodForQuestionAnswering.__init__  sU      ++ 5A))F$6$68I8IJ 	rO   rV   r
  r   r.   r+   r   rW   start_positionsend_positionsr   rA  rB  r   c                 (   Ub  UOU R                   R                  nU R                  UUUUUUUU
UUS9
nUS   nU R                  U5      nUR	                  SSS9u  nnUR                  S5      R                  5       nUR                  S5      R                  5       nSnUb  U	b  [        UR                  5       5      S:  a  UR                  S5      n[        U	R                  5       5      S:  a  U	R                  S5      n	UR                  S5      nUR                  SU5      nU	R                  SU5      n	[        US9nU" UU5      nU" UU	5      nUU-   S-  nU(       d  UU4USS -   nUb  U4U-   $ U$ [        UUUUR                  UR                  S	9$ )
r  Nr  r   r    r,   r   )ignore_indexrt   )r  start_logits
end_logitsr   rK  )rK   r  re  r  r  r  r   r   rG   clampr   r   r   rK  )rJ   rV   r
  r   r.   r+   r   rW   r   r!  r   rA  rB  r   r  r  r$  r%  
total_lossignored_indexr  
start_lossend_lossr   s                           rM   r^    XmodForQuestionAnswering.forward  s   * &1%<k$++B]B],,))%'/!5#  
 "!*1#)<<r<#: j#++B/::<''+668

&=+D?'')*Q."1"9"9""==%%'(1, - 5 5b 9(--a0M-33A}EO)//=AM']CH!,@J
M:H$x/14J"J/'!"+=F/9/EZMF*Q6Q+%!!//))
 	
rO   )r  r  re  )NNNNNNNNNNNN)rd   re   rf   rg   r2   r   r   rC   r  r   r   r   r   r   r   r^   ri   rj   rk   s   @rM   r  r  }  sT     15/36:593715596:48,0/3&*E
E,,-E
 5++,E
 !!2!23	E

 !!1!12E
 u//0E
 E--.E
   1 12E
 "%"2"23E
   0 01E
 $D>E
 'tnE
 d^E
 
uU\\"$@@	AE
 E
rO   r  c                     U R                  U5      R                  5       n[        R                  " USS9R	                  U5      U-   U-  nUR                  5       U-   $ )z
Replace non-padding symbols with their position numbers. Position numbers begin at padding_idx+1. Padding symbols
are ignored. This is modified from fairseq's `utils.make_positions`.

Args:
    x: torch.Tensor x:

Returns: torch.Tensor
r    r   )nerw   rC   cumsumtype_asrH   )rV   r&   rX   maskincremental_indicess        rM   rS   rS     sW     <<$((*D <<!4<<TBE[[_cc##%33rO   )r  r  r  r  r  r  r  rd  )r   )Frh   r   typingr   r   rC   r   torch.nnr   r   r   activationsr
   r   cache_utilsr   r   r   
generationr   modeling_layersr   modeling_outputsr   r   r   r   r   r   r   r   modeling_utilsr   pytorch_utilsr   r   r   utilsr   r   utils.deprecationr   configuration_xmodr!   
get_loggerrd   rN  Moduler#   rm   r   r   r   r   r   r"  r7  rY  rd  r  r  r  rp  r  r  r  r  r  rS   __all__rD  rO   rM   <module>rA     sS     "   A A ' C C ) 9	 	 	 . l l , 0 * 
		H	%V=RYY V=tB.		 B.JRYY 6BII 6tryy ")) $/ /dJ3* J3Z^
")) ^
D  30/ 30 30l e
# e
e
P 
t
)? t

t
n V
) V
 V
t* *> V
$7 V
V
r j
/ j
 j
Z H
!4 H
 H
XRYY , R
2 R
 R
l4 	rO   