
    Z je                        S SK Jr  S SK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  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JrJrJr  SSKJrJr  SSKJrJ r   SSK!J"r"  SSK#J$r$  SSK%J&r&J'r'J(r(J)r)  SSK*J+r+  SSK,J-r-  \" S5       " S S\R\                  5      5       r/S r0\" S5      S;S j5       r1S\Rd                  S\3S\Rd                  4S jr4 S<S\R\                  S \Rd                  S!\Rd                  S"\Rd                  S#\Rd                  S-  S$\5S%\5S&\"\&   4S' jjr6\" \15       " S( S)\R\                  5      5       r7 " S* S+\R\                  5      r8 " S, S-\5      r9\$ " S. S/\ 5      5       r: " S0 S1\R\                  5      r;\$ " S2 S3\:5      5       r<\$ " S4 S5\:5      5       r=\$ " S6 S7\:5      5       r>\$ " S8 S9\:5      5       r?/ S:Qr@g)=    )Callable)OptionalN)nn)BCEWithLogitsLossCrossEntropyLossMSELoss   )ACT2FN)Cache)use_kernel_forward_from_hubuse_kernel_func_from_hubuse_kernelized_func)create_bidirectional_mask)GradientCheckpointingLayer)BaseModelOutputMaskedLMOutputSequenceClassifierOutputTokenClassifierOutput)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)auto_docstring)TransformersKwargscan_return_tuplemaybe_autocastmerge_with_config_defaults)capture_outputs   )EuroBertConfigRMSNormc                   p   ^  \ rS rSrSS	U 4S jjjrS\R                  S\R                  4S jrS rSr	U =r
$ )
EuroBertRMSNorm,   returnc                    > [         TU ]  5         [        R                  " [        R
                  " U5      5      U l        X l        g)z.
EuroBertRMSNorm is equivalent to T5LayerNorm
N)super__init__r   	Parametertorchonesweightvariance_epsilon)selfhidden_sizeeps	__class__s      /root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/eurobert/modeling_eurobert.pyr)   EuroBertRMSNorm.__init__.   s/     	ll5::k#:; #    hidden_statesc                    UR                   nUR                  [        R                  5      nUR	                  S5      R                  SSS9nU[        R                  " X0R                  -   5      -  nU R                  UR                  U5      -  $ )N   T)keepdim)	dtypetor+   float32powmeanrsqrtr.   r-   )r/   r6   input_dtypevariances       r3   forwardEuroBertRMSNorm.forward6   sw    #))%((7 $$Q',,R,>%H?T?T4T(UU{{]--k:::r5   c                 ^    [        U R                  R                  5       SU R                   3$ )Nz, eps=)tupler-   shaper.   r/   s    r3   
extra_reprEuroBertRMSNorm.extra_repr=   s*    ))*+6$2G2G1HIIr5   )r.   r-   )gh㈵>)r&   N)__name__
__module____qualname____firstlineno__r)   r+   TensorrC   rI   __static_attributes____classcell__r2   s   @r3   r$   r$   ,   s4    $ $;U\\ ;ell ;J Jr5   r$   c                     U SSU R                   S   S-  24   nU SU R                   S   S-  S24   n[        R                  " U* U4SS9$ )z*Rotates half the hidden dims of the input..Nr9   r8   dim)rG   r+   cat)xx1x2s      r3   rotate_halfrZ   A   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r5   rotary_pos_embc                     UR                  U5      nUR                  U5      nX-  [        U 5      U-  -   nX-  [        U5      U-  -   nXV4$ )aI  Applies Rotary Position Embedding to the query and key tensors.

Args:
    q (`torch.Tensor`): The query tensor.
    k (`torch.Tensor`): The key tensor.
    cos (`torch.Tensor`): The cosine part of the rotary embedding.
    sin (`torch.Tensor`): The sine part of the rotary embedding.
    unsqueeze_dim (`int`, *optional*, defaults to 1):
        The 'unsqueeze_dim' argument specifies the dimension along which to unsqueeze cos[position_ids] and
        sin[position_ids] so that they can be properly broadcasted to the dimensions of q and k. For example, note
        that cos[position_ids] and sin[position_ids] have the shape [batch_size, seq_len, head_dim]. Then, if q and
        k have the shape [batch_size, heads, seq_len, head_dim], then setting unsqueeze_dim=1 makes
        cos[position_ids] and sin[position_ids] broadcastable to the shapes of q and k. Similarly, if q and k have
        the shape [batch_size, seq_len, heads, head_dim], then set unsqueeze_dim=2.
Returns:
    `tuple(torch.Tensor)` comprising of the query and key tensors rotated using the Rotary Position Embedding.
)	unsqueezerZ   )qkcossinunsqueeze_dimq_embedk_embeds          r3   apply_rotary_pos_embre   H   sS    & --
&C
--
&Cw;q>C/0Gw;q>C/0Gr5   r6   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)rG   expandreshape)r6   rf   batchnum_key_value_headsslenhead_dims         r3   	repeat_kvrn   b   s_    
 2?1D1D.Ez!!Qa"23::5W\dlmM  e(CTTTr5   modulequerykeyvalueattention_maskscalingdropoutkwargsc                    [        X R                  5      n[        X0R                  5      n	[        R                  " XR	                  SS5      5      U-  n
Ub  X-   n
[
        R                  R                  U
S[        R                  S9R                  UR                  5      n
[
        R                  R                  XU R                  S9n
[        R                  " X5      nUR	                  SS5      R                  5       nX4$ )Nr8   r	   r9   )rU   r;   )ptrainingr    )rn   num_key_value_groupsr+   matmul	transposer   
functionalsoftmaxr=   r<   r;   ru   ry   
contiguous)ro   rp   rq   rr   rs   rt   ru   rv   
key_statesvalue_statesattn_weightsattn_outputs               r3   eager_attention_forwardr   n   s     3 ; ;<JU$?$?@L<<';';Aq'ABWLL!#4==((2U]](SVVW\WbWbcL==((6??([L,,|:K''1-88:K$$r5   c                     ^  \ rS rSrSrS\S\4U 4S jjr   SS\R                  S\
\R                  \R                  4   S-  S	\R                  S-  S
\S-  S\\   S\
\R                  \R                  4   4S jjrSrU =r$ )EuroBertAttention   z=Multi-headed attention from 'Attention Is All You Need' paperconfig	layer_idxc                 P  > [         TU ]  5         Xl        X l        [	        USUR
                  UR                  -  5      U l        UR                  UR                  -  U l	        U R                  S-  U l
        UR                  U l        SU l        [        R                  " UR
                  UR                  U R                  -  UR                  S9U l        [        R                  " UR
                  UR                  U R                  -  UR                  S9U l        [        R                  " UR
                  UR                  U R                  -  UR                  S9U l        [        R                  " UR                  U R                  -  UR
                  UR                  S9U l        g )Nrm   g      Fbias)r(   r)   r   r   getattrr0   num_attention_headsrm   rk   rz   rt   attention_dropout	is_causalr   Linearattention_biasq_projk_projv_projo_projr/   r   r   r2   s      r3   r)   EuroBertAttention.__init__   sI   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
r5   Nr6   position_embeddingsrs   past_key_valuesrv   r&   c                    UR                   S S n/ UQSPU R                  P7nU R                  U5      R                  U5      R	                  SS5      nU R                  U5      R                  U5      R	                  SS5      n	U R                  U5      R                  U5      R	                  SS5      n
Uu  p[        XX5      u  pUb  UR                  XU R                  5      u  p[        R                  " U R                  R                  [        5      nU" U UU	U
U4U R                  (       d  SOU R                   U R"                  S.UD6u  pUR$                  " / UQSP76 R'                  5       nU R)                  U5      nX4$ )Nr9   r    r8           )ru   rt   )rG   rm   r   viewr|   r   r   re   updater   r   get_interfacer   _attn_implementationr   ry   r   rt   ri   r   r   )r/   r6   r   rs   r   rv   input_shapehidden_shapequery_statesr   r   r`   ra   attention_interfacer   r   s                   r3   rC   EuroBertAttention.forward   s~    $))#2.88b8$--8{{=166|DNNqRST[[/44\BLLQPQR
{{=166|DNNqRST&#7RU#[ &'6'='=jX\XfXf'g$J(?(M(MKK,,.E)
 %8	%
  $}}C$2H2HLL	%
 	%
! "));;;;FFHkk+.((r5   )r   r   rm   r   r   r   rz   r   r   rt   r   NNN)rK   rL   rM   rN   __doc__r!   intr)   r+   rO   rF   r   r   r   rC   rP   rQ   rR   s   @r3   r   r      s    G
~ 
# 
4 IM.2(,&)||&) #5<<#=>E&) t+	&)
 &) +,&) 
u||U\\)	*&) &)r5   r   c                   .   ^  \ rS rSrU 4S jrS rSrU =r$ )EuroBertMLP   c                   > [         TU ]  5         Xl        UR                  U l        UR                  U l        [
        R                  " U R                  U R                  UR                  S9U l        [
        R                  " U R                  U R                  UR                  S9U l	        [
        R                  " U R                  U R                  UR                  S9U l
        [        UR                     U l        g )Nr   )r(   r)   r   r0   intermediate_sizer   r   mlp_bias	gate_projup_proj	down_projr
   
hidden_actact_fnr/   r   r2   s     r3   r)   EuroBertMLP.__init__   s    !--!'!9!94#3#3T5K5KRXRaRabyy!1!143I3IPVP_P_`4#9#94;K;KRXRaRabV../r5   c                     U R                  U R                  U R                  U5      5      U R                  U5      -  5      nU$ N)r   r   r   r   )r/   rW   r   s      r3   rC   EuroBertMLP.forward   s6    NN4;;t~~a/@#ADLLQRO#ST	r5   )r   r   r   r   r0   r   r   )rK   rL   rM   rN   r)   rC   rP   rQ   rR   s   @r3   r   r      s    0 r5   r   c                     ^  \ rS rSrS\S\4U 4S jjr     SS\R                  S\R                  S-  S\R                  S-  S	\
S-  S
\S-  S\\R                  \R                  4   S-  S\\   S\R                  4S jjrSrU =r$ )EuroBertDecoderLayer   r   r   c                   > [         TU ]  5         UR                  U l        [        XS9U l        [        U5      U l        [        UR                  UR                  S9U l	        [        UR                  UR                  S9U l
        g )N)r   r   r1   )r(   r)   r0   r   	self_attnr   mlpr$   rms_norm_epsinput_layernormpost_attention_layernormr   s      r3   r)   EuroBertDecoderLayer.__init__   sk    !--*&Nv&.v/A/AvGZGZ[(78J8JPVPcPc(d%r5   Nr6   rs   position_idsr   	use_cacher   rv   r&   c           
          UnU R                  U5      nU R                  " SUUUUUUS.UD6u  pX-   nUnU R                  U5      nU R                  U5      nX-   nU$ )N)r6   rs   r   r   r   r    )r   r   r   r   )
r/   r6   rs   r   r   r   r   rv   residual_s
             r3   rC   EuroBertDecoderLayer.forward   s     !,,];>> 
')%+ 3
 
 !0 !55mD/ 0r5   )r0   r   r   r   r   )NNNFN)rK   rL   rM   rN   r!   r   r)   r+   rO   
LongTensorr   boolrF   r   r   rC   rP   rQ   rR   s   @r3   r   r      s    e~ e# e /304(,!&HL|| t+ &&-	
  $; #5<<#=>E +, 
 r5   r   c                   R    \ rS rSr% \\S'   SrSrS/rS/r	Sr
SrSrSrSr\\S.rSrg	)
EuroBertPreTrainedModeli  r   modelTr   r   )r6   
attentionsr   N)rK   rL   rM   rN   r!   __annotations__base_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_supports_sdpa_supports_flex_attn_can_compile_fullgraph_supports_attention_backendr   r   _can_record_outputsrP   r   r5   r3   r   r     sQ    &*#/0#4"5N!"&-'r5   r   c                      ^  \ rS rSr% \R
                  \S'   SS\4U 4S jjjr\	   SS\S-  S\
S   S\S-  S	\S
\4   4S jj5       r\R                  " 5       \S 5       5       rSrU =r$ )EuroBertRotaryEmbeddingi  inv_freqNr   c                   > [         TU ]  5         UR                  U l        UR                  U l        Xl        U R
                  R                  S   U l        U R                  nU R                  S:w  a  [        U R                     nU" U R
                  U5      u  o@l
        U R                  SUSS9  U R                  SUR                  5       SS9  g )N	rope_typedefaultr   F)
persistentoriginal_inv_freq)r(   r)   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenr   rope_parametersr   compute_default_rope_parametersr   attention_scalingregister_bufferclone)r/   r   devicerope_init_fnr   r2   s        r3   r)    EuroBertRotaryEmbedding.__init__  s    "("@"@$*$B$B!44[A!%!E!E>>Y&.t~~>L+7V+L((ZeD0(..2BuUr5   r   ztorch.deviceseq_lenr&   ztorch.Tensorc           	         U R                   S   n[        U SS5      =(       d    U R                  U R                  -  nSnSU[        R
                  " SUS[        R                  S9R                  U[        R                  S9U-  -  -  nXe4$ )	aH  
Computes the inverse frequencies according to the original RoPE implementation
Args:
    config ([`~transformers.PreTrainedConfig`]):
        The model configuration.
    device (`torch.device`):
        The device to use for initialization of the inverse frequencies.
    seq_len (`int`, *optional*):
        The current sequence length. Unused for this type of RoPE.
Returns:
    Tuple of (`torch.Tensor`, `float`), containing the inverse frequencies for the RoPE embeddings and the
    post-processing scaling factor applied to the computed cos/sin (unused in this type of RoPE).

rope_thetarm   Ng      ?r   r8   r;   )r   r;   )	r   r   r0   r   r+   arangeint64r<   float)r   r   r   baserU   attention_factorr   s          r3   r   7EuroBertRotaryEmbedding.compute_default_rope_parameters,  s    & %%l3fj$/c63E3EIcIc3c U\\!S!5;;?BB&X]XcXcBdgjjk
 ))r5   c                 L   U R                   S S S 2S 4   R                  5       R                  UR                  S   SS5      R	                  UR
                  5      nUS S 2S S S 24   R                  5       n[        UR
                  R                  [        5      (       a0  UR
                  R                  S:w  a  UR
                  R                  OSn[        USS9   UR                  5       UR                  5       -  R                  SS5      n[        R                  " Xf4SS	9nUR                  5       U R                  -  nUR                  5       U R                  -  n	S S S 5        WR	                  UR                   S
9W	R	                  UR                   S
94$ ! , (       d  f       N@= f)Nr   r9   r    mpscpuF)device_typeenabledr8   rT   r   )r   r   rh   rG   r<   r   
isinstancetypestrr   r|   r+   rV   r`   r   ra   r;   )
r/   rW   r   inv_freq_expandedposition_ids_expandedr   freqsembr`   ra   s
             r3   rC   EuroBertRotaryEmbedding.forwardJ  sN    !MM$4-8>>@GGHZHZ[\H]_acdehhijiqiqr ,QaZ 8 > > @'1!((--'E'E!((--[`J`ahhmmfkUC&,,.1F1L1L1NNYYZ[]^_E))UN3C'')d444C'')d444C	 D vvAGGv$cff177f&;;; DCs   BF
F#)r   r   r   r   r   r   r   )rK   rL   rM   rN   r+   rO   r   r!   r)   staticmethodr   r   rF   r   r   no_gradr   rC   rP   rQ   rR   s   @r3   r   r     s    llV~ V V  (,+/"*%*(* t* 
~u$	%	* *: ]]_<  <r5   r   c                      ^  \ rS rSrS\4U 4S jjr\\\    SS\	R                  S\	R                  S-  S\	R                  S-  S\	R                  S-  S	\\   S
\\-  4S jj5       5       5       rSrU =r$ )EuroBertModeliZ  r   c           	        > [         TU ]  U5        UR                  U l        UR                  U l        [
        R                  " UR                  UR                  U R                  5      U l        [
        R                  " [        UR                  5       Vs/ s H  n[        X5      PM     sn5      U l        [        UR                  UR                  S9U l        [#        US9U l        SU l        U R)                  5         g s  snf )Nr   )r   F)r(   r)   pad_token_idpadding_idx
vocab_sizer   	Embeddingr0   embed_tokens
ModuleListrangenum_hidden_layersr   layersr$   r   normr   
rotary_embgradient_checkpointing	post_initr   s      r3   r)   EuroBertModel.__init__\  s     !.. ++LL):):F<N<NPTP`P`ammFKFLdLdFefFe!&4Fef
 $F$6$6F<O<OP	1@&+# 	 gs   C?N	input_idsrs   r   inputs_embedsrv   r&   c                    US L US L-  (       a  [        S5      eUc  U R                  U5      nUc;  [        R                  " UR                  S   UR
                  S9R                  S5      n[        U R                  UUS9nUnU R                  XsS9nU R                  S U R                  R                    H  n	U	" U4UUUS.UD6nM     U R                  U5      n[        US9$ )	Nz:You must specify exactly one of input_ids or inputs_embedsr    )r   r   )r   r  rs   )r   )rs   r   r   )last_hidden_state)
ValueErrorr  r+   r   rG   r   r]   r   r   r  r  r  r  r   )
r/   r  rs   r   r  rv   bidirectional_maskr6   r   encoder_layers
             r3   rC   EuroBertModel.forwardl  s    -t";<YZZ *.*;*;I*FM <<(;(;A(>}G[G[\ffghiL6;;')
 &"oomoW![[)H4;;+H+HIM)1$7)	
 M J 		-0+
 	
r5   )r  r  r  r  r  r  r  )NNNN)rK   rL   rM   rN   r!   r)   r   r   r   r+   r   rO   FloatTensorr   r   rF   r   rC   rP   rQ   rR   s   @r3   r	  r	  Z  s    ~     '+.20426&
##&
 t+&
 &&-	&

 ((4/&
 +,&
 
	 &
    &
r5   r	  c                   @  ^  \ rS rSrSS0rSS0rSS/S/40rS\4U 4S	 jjr\	\
     SS\R                  S
-  S\R                  S
-  S\R                  S
-  S\R                  S
-  S\R                  S
-  S\\   S\\R                     \-  4S jj5       5       rSrU =r$ )EuroBertForMaskedLMi  zlm_head.weightzmodel.embed_tokens.weightlm_headcolwise_gather_outputr6   logitsr   c                    > [         TU ]  U5        [        U5      U l        [        R
                  " UR                  UR                  UR                  5      U l	        U R                  5         g r   )r(   r)   r	  r   r   r   r0   r  r   r$  r  r   s     r3   r)   EuroBertForMaskedLM.__init__  sL     "6*
yy!3!3V5F5FX 	r5   Nr  rs   r   r  labelsrv   r&   c                    U R                   " SUUUUS.UD6nU R                  UR                  5      nSn	Ub)  U R                  " SXU R                  R
                  S.UD6n	[        U	UUR                  UR                  S9$ )a  
Example:

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

>>> model = EuroBertForMaskedLM.from_pretrained("EuroBERT/EuroBERT-210m")
>>> tokenizer = AutoTokenizer.from_pretrained("EuroBERT/EuroBERT-210m")

>>> text = "The capital of France is <|mask|>."
>>> inputs = tokenizer(text, return_tensors="pt")
>>> outputs = model(**inputs)

>>> # To get predictions for the mask:
>>> masked_index = inputs["input_ids"][0].tolist().index(tokenizer.mask_token_id)
>>> predicted_token_id = outputs.logits[0, masked_index].argmax(axis=-1)
>>> predicted_token = tokenizer.decode(predicted_token_id)
>>> print("Predicted token:", predicted_token)
Predicted token:  Paris
```)r  rs   r   r  N)r&  r)  r  lossr&  r6   r   r   )	r   r$  r  loss_functionr   r  r   r6   r   )
r/   r  rs   r   r  r)  rv   outputsr&  r,  s
             r3   rC   EuroBertForMaskedLM.forward  s    > $(:: $
)%'	$

 $
 g778%%pVt{{OeOepiopD!//))	
 	
r5   )r$  r   NNNNN)rK   rL   rM   rN   _tied_weights_keys_tp_plan_pp_planr!   r)   r   r   r+   r   rO   r!  r   r   rF   r   rC   rP   rQ   rR   s   @r3   r#  r#    s    *,GH23H_-z:;H~   .2.20426*./
##d*/
 t+/
 &&-	/

 ((4//
   4'/
 +,/
 
u||	~	-/
  /
r5   r#  c                      ^  \ rS rSrS\4U 4S jjr\\     SS\R                  S-  S\R                  S-  S\R                  S-  S\R                  S-  S	\R                  S-  S
\\   S\\R                     \-  4S jj5       5       rSrU =r$ )!EuroBertForSequenceClassificationi  r   c                   > [         TU ]  U5        UR                  U l        UR                  U l        [	        U5      U l        [        R                  " UR                  UR                  5      U l	        [        R                  " 5       U l        [        R                  " UR                  U R                  5      U l        U R                  5         g r   )r(   r)   
num_labelsclassifier_poolingr	  r   r   r   r0   denseGELU
activation
classifierr  r   s     r3   r)   *EuroBertForSequenceClassification.__init__  s      ++"(";";"6*
YYv1163E3EF
'')))F$6$6Hr5   Nr  rs   r   r  r)  rv   r&   c                    U R                   " U4UUUS.UD6nUS   nU R                  S;   a  U R                  S:X  a
  US S 2S4   n	OpU R                  S:X  a`  Uc  UR                  SS9n	OMUR                  UR                  5      nXR                  S5      -  R                  SS9n	XR                  SS	S
9-  n	U R                  W	5      n	U R                  U	5      n	U R                  U	5      n
OU R                  S:X  a  U R                  U5      nU R                  U5      nU R                  U5      n
Uc  U
R                  SS9n
OMUR                  U
R                  5      nXR                  S5      -  R                  SS9n
XR                  SS	S
9-  n
S nUGb  UR                  W
R                  5      nU R                  R                  c  U R                  S:X  a  SU R                  l        OoU R                  S:  aN  UR                  [        R                  :X  d  UR                  [        R                   :X  a  SU R                  l        OSU R                  l        U R                  R                  S:X  aI  [#        5       nU R                  S:X  a&  U" U
R%                  5       UR%                  5       5      nOU" X5      nOU R                  R                  S:X  a=  ['        5       nU" U
R)                  SU R                  5      UR)                  S5      5      nO,U R                  R                  S:X  a  [+        5       nU" X5      n[-        UW
UR.                  UR0                  S9$ )Nrs   r   r  r   )bosr?   r@  r?   r    rT   r9   T)rU   r:   late
regressionsingle_label_classificationmulti_label_classificationr+  )r   r8  r?   r<   r   r]   sumr9  r;  r<  r   problem_typer7  r;   r+   longr   r   squeezer   r   r   r   r6   r   )r/   r  rs   r   r  r)  rv   encoder_outputr  pooled_outputr&  rW   r,  loss_fcts                 r3   rC   )EuroBertForSequenceClassification.forward  s    
)%'	

 
 +1-""o5&&%/ 1!Q$ 7((F2!)$5$:$:q$:$AM%3%6%67H7O7O%PN%69Q9QRT9U%U$Z$Z_`$Z$aM!%7%7At%7%LLM JJ}5M OOM:M__]3F$$.

,-A"A__Q'F%+!/!2!26==!A #;#;B#??DDDK,,D,AAYYv}}-F{{''/??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,./'(66%00	
 	
r5   )r;  r<  r8  r9  r   r7  r0  )rK   rL   rM   rN   r!   r)   r   r   r+   r   rO   r!  r   r   rF   r   rC   rP   rQ   rR   s   @r3   r5  r5    s    	~ 	  .2.20426*.J
##d*J
 t+J
 &&-	J

 ((4/J
   4'J
 +,J
 
u||	7	7J
  J
r5   r5  c                     ^  \ rS rSrS\4U 4S jjrS rS r\\	     SS\
R                  S-  S\
R                  S-  S	\
R                  S-  S
\
R                  S-  S\
R                  S-  S\\   S\\-  4S jj5       5       rSrU =r$ )EuroBertForTokenClassificationi6  r   c                    > [         TU ]  U5        UR                  U l        [        U5      U l        [
        R                  " UR                  UR                  5      U l        U R                  5         g r   )
r(   r)   r7  r	  r   r   r   r0   r<  r  r   s     r3   r)   'EuroBertForTokenClassification.__init__8  sQ      ++"6*
))F$6$68I8IJr5   c                 .    U R                   R                  $ r   r   r  rH   s    r3   get_input_embeddings3EuroBertForTokenClassification.get_input_embeddings@  s    zz&&&r5   c                 $    XR                   l        g r   rR  )r/   rr   s     r3   set_input_embeddings3EuroBertForTokenClassification.set_input_embeddingsC  s    "'

r5   Nr  rs   r   r  r)  rv   r&   c                    U R                   " U4UUUS.UD6nUS   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
U	UR                  UR                  S9$ )ae  
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).
r?  r   Nr9   r+  )r   r<  r   r   r7  r   r6   r   )r/   r  rs   r   r  r)  rv   r.  sequence_outputr&  r,  rK  s               r3   rC   &EuroBertForTokenClassification.forwardF  s    " **
)%'	

 
 "!*1')HFKKDOO<fkk"oND$!//))	
 	
r5   )r<  r   r7  r0  )rK   rL   rM   rN   r!   r)   rS  rV  r   r   r+   r   rO   r!  r   r   rF   r   rC   rP   rQ   rR   s   @r3   rN  rN  6  s    ~ '(  .2.20426*.#
##d*#
 t+#
 &&-	#

 ((4/#
   4'#
 +,#
 
&	&#
  #
r5   rN  )r   r	  r#  r5  rN  )r    )r   )Acollections.abcr   typingr   r+   r   torch.nnr   r   r   activationsr
   cache_utilsr   integrationsr   r   r   masking_utilsr   modeling_layersr   modeling_outputsr   r   r   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   utils.genericr   r   r   r   utils.output_capturingr   configuration_eurobertr!   Moduler$   rZ   re   rO   r   rn   r   r   r   r   r   r   r   r	  r#  r5  rN  __all__r   r5   r3   <module>rm     s  , %    A A !   f f 6 9 p p K F & # m m 5 2 Y'Jbii J (J(( *+ ,2	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 LL4'% % % '(%2 )*@)		 @) +@)F"))  (5 (V o  $><bii ><B :
+ :
 :
z >
1 >
 >
B X
(? X
 X
v 4
%< 4
 4
nr5   