§
    ‚Štjëe  ã                   ó®  — d dl mZ d dlmZ d dlZd dlmZ d dlmZmZm	Z	 ddl
mZ ddlmZ dd	lmZmZmZ dd
lmZ ddlmZ ddlmZmZmZmZ ddlmZmZ ddlmZm Z  ddl!m"Z" ddl#m$Z$ ddl%m&Z&m'Z'm(Z(m)Z) ddl*m+Z+ ddl,m-Z-  ed¦  «         G d„ dej.        ¦  «        ¦   «         Z/d„ Z0 ed¦  «        d<d„¦   «         Z1dej2        de3dej2        fd„Z4	 d=d ej.        d!ej2        d"ej2        d#ej2        d$ej2        dz  d%e5d&e5d'e"e&         fd(„Z6 ee1¦  «         G d)„ d*ej.        ¦  «        ¦   «         Z7 G d+„ d,ej.        ¦  «        Z8 G d-„ d.e¦  «        Z9e$ G d/„ d0e ¦  «        ¦   «         Z: G d1„ d2ej.        ¦  «        Z;e$ G d3„ d4e:¦  «        ¦   «         Z<e$ G d5„ d6e:¦  «        ¦   «         Z=e$ G d7„ d8e:¦  «        ¦   «         Z>e$ G d9„ d:e:¦  «        ¦   «         Z?g d;¢Z@dS )>é    )ÚCallable)ÚOptionalN)Únn)ÚBCEWithLogitsLossÚCrossEntropyLossÚMSELossé   )ÚACT2FN)ÚCache)Úuse_kernel_forward_from_hubÚuse_kernel_func_from_hubÚuse_kernelized_func)Úcreate_bidirectional_mask)ÚGradientCheckpointingLayer)ÚBaseModelOutputÚMaskedLMOutputÚSequenceClassifierOutputÚTokenClassifierOutput)ÚROPE_INIT_FUNCTIONSÚdynamic_rope_update)ÚALL_ATTENTION_FUNCTIONSÚPreTrainedModel)ÚUnpack)Úauto_docstring)ÚTransformersKwargsÚcan_return_tupleÚmaybe_autocastÚmerge_with_config_defaults)Úcapture_outputsé   )ÚEuroBertConfigÚRMSNormc                   óL   ‡ — e Zd Zdd	ˆ fd„Zdej        dej        fd„Zd„ Zˆ xZS )
ÚEuroBertRMSNormçñhãˆµøä>ÚreturnNc                 ó¬   •— t          ¦   «                              ¦   «          t          j        t	          j        |¦  «        ¦  «        | _        || _        dS )z>
        EuroBertRMSNorm is equivalent to T5LayerNorm
        N)ÚsuperÚ__init__r   Ú	ParameterÚtorchÚonesÚweightÚvariance_epsilon)ÚselfÚhidden_sizeÚepsÚ	__class__s      €úl/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/transformers/models/eurobert/modeling_eurobert.pyr)   zEuroBertRMSNorm.__init__.   sD   ø€ õ 	‰Œ×ÒÑÔÐÝ”l¥5¤:¨kÑ#:Ô#:Ñ;Ô;ˆŒØ #ˆÔÐÐó    Úhidden_statesc                 ó  — |j         }|                     t          j        ¦  «        }|                     d¦  «                             dd¬¦  «        }|t          j        || j        z   ¦  «        z  }| j        |                     |¦  «        z  S )Né   éÿÿÿÿT)Úkeepdim)	ÚdtypeÚtor+   Úfloat32ÚpowÚmeanÚrsqrtr.   r-   )r/   r5   Úinput_dtypeÚvariances       r3   ÚforwardzEuroBertRMSNorm.forward6   s|   € Ø#Ô)ˆØ%×(Ò(­¬Ñ7Ô7ˆØ ×$Ò$ QÑ'Ô'×,Ò,¨R¸Ð,Ñ>Ô>ˆØ%­¬°H¸tÔ?TÑ4TÑ(UÔ(UÑUˆØŒ{˜]×-Ò-¨kÑ:Ô:Ñ:Ð:r4   c                 óH   — t          | j        j        ¦  «        › d| j        › �S )Nz, eps=)Útupler-   Úshaper.   ©r/   s    r3   Ú
extra_reprzEuroBertRMSNorm.extra_repr=   s&   € Ý˜œÔ)Ñ*Ô*ÐIÐI°$Ô2GÐIÐIÐIr4   )r%   )r&   N)	Ú__name__Ú
__module__Ú__qualname__r)   r+   ÚTensorrB   rG   Ú__classcell__©r2   s   @r3   r$   r$   ,   s~   ø€ € € € € ð$ð $ð $ð $ð $ð $ð $ð; U¤\ð ;°e´lð ;ð ;ð ;ð ;ðJð Jð Jð Jð Jð Jð Jr4   r$   c                 óœ   — | dd| j         d         dz  …f         }| d| j         d         dz  d…f         }t          j        | |fd¬¦  «        S )z*Rotates half the hidden dims of the input..Nr8   r7   ©Údim)rE   r+   Úcat)ÚxÚx1Úx2s      r3   Úrotate_halfrU   A   s]   € à	
ˆ3Ð"�!”'˜"”+ Ñ"Ð"Ð"Ô	#€BØ	
ˆ3�”˜”˜qÑ Ð"Ð"Ð"Ô	#€BÝŒ9�r�c˜2�Y BÐ'Ñ'Ô'Ð'r4   Úrotary_pos_embc                 ó¾   — |                      |¦  «        }|                      |¦  «        }| |z  t          | ¦  «        |z  z   }||z  t          |¦  «        |z  z   }||fS )a…  Applies Rotary Position Embedding to the query and key tensors.

    Args:
        q (`torch.Tensor`): The query tensor.
        k (`torch.Tensor`): The key tensor.
        cos (`torch.Tensor`): The cosine part of the rotary embedding.
        sin (`torch.Tensor`): The sine part of the rotary embedding.
        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.
    )Ú	unsqueezerU   )ÚqÚkÚcosÚsinÚunsqueeze_dimÚq_embedÚk_embeds          r3   Úapply_rotary_pos_embr`   H   sc   € ð& �-Š-˜Ñ
&Ô
&€CØ
�-Š-˜Ñ
&Ô
&€CØ�3‰w�; q™>œ>¨CÑ/Ñ0€GØ�3‰w�; q™>œ>¨CÑ/Ñ0€GØ�GÐÐr4   r5   Ún_repr&   c                 ó¸   — | j         \  }}}}|dk    r| S | dd…dd…ddd…dd…f                              |||||¦  «        } |                      |||z  ||¦  «        S )zÔ
    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)rE   ÚexpandÚreshape)r5   ra   ÚbatchÚnum_key_value_headsÚslenÚhead_dims         r3   Ú	repeat_kvri   b   s„   € ð
 2?Ô1DÑ.€EÐ  hØ�‚z€zØÐØ! ! ! ! Q Q Q¨¨a¨a¨a°°°Ð"2Ô3×:Ò:¸5ÐBUÐW\Ð^bÐdlÑmÔm€MØ× Ò  Ð(;¸eÑ(CÀTÈ8ÑTÔTÐTr4   ç        ÚmoduleÚqueryÚkeyÚvalueÚattention_maskÚscalingÚdropoutÚkwargsc                 ó  — t          || j        ¦  «        }t          || j        ¦  «        }	t          j        ||                     dd¦  «        ¦  «        |z  }
|�|
|z   }
t
          j                             |
dt          j        ¬¦  «         	                    |j
        ¦  «        }
t
          j                             |
|| j        ¬¦  «        }
t          j        |
|	¦  «        }|                     dd¦  «                             ¦   «         }||
fS )Nr7   r	   r8   )rP   r:   )ÚpÚtrainingr    )ri   Únum_key_value_groupsr+   ÚmatmulÚ	transposer   Ú
functionalÚsoftmaxr<   r;   r:   rq   ru   Ú
contiguous)rk   rl   rm   rn   ro   rp   rq   rr   Ú
key_statesÚvalue_statesÚattn_weightsÚattn_outputs               r3   Úeager_attention_forwardr€   n   sé   € õ ˜3 Ô ;Ñ<Ô<€JÝ˜U FÔ$?Ñ@Ô@€Lå”<  z×';Ò';¸A¸qÑ'AÔ'AÑBÔBÀWÑL€LØÐ!Ø# nÑ4ˆå”=×(Ò(¨¸2ÅUÄ]Ð(ÑSÔS×VÒVÐW\ÔWbÑcÔc€LÝ”=×(Ò(¨¸È6Ì?Ð(Ñ[Ô[€LÝ”,˜|¨\Ñ:Ô:€KØ×'Ò'¨¨1Ñ-Ô-×8Ò8Ñ:Ô:€Kà˜Ð$Ð$r4   c                   óÎ   ‡ — e Zd ZdZdedefˆ fd„Z	 	 	 ddej        de	ej        ej        f         dz  dej        dz  d	e
dz  d
ee         de	ej        ej        f         fd„Zˆ xZS )ÚEuroBertAttentionz=Multi-headed attention from 'Attention Is All You Need' paperÚconfigÚ	layer_idxc                 ó®  •— t          ¦   «                              ¦   «          || _        || _        t	          |d|j        |j        z  ¦  «        | _        |j        |j        z  | _	        | j        dz  | _
        |j        | _        d| _        t          j        |j        |j        | j        z  |j        ¬¦  «        | _        t          j        |j        |j        | j        z  |j        ¬¦  «        | _        t          j        |j        |j        | j        z  |j        ¬¦  «        | _        t          j        |j        | j        z  |j        |j        ¬¦  «        | _        d S )Nrh   g      à¿F©Úbias)r(   r)   rƒ   r„   Úgetattrr0   Únum_attention_headsrh   rf   rv   rp   Úattention_dropoutÚ	is_causalr   ÚLinearÚattention_biasÚq_projÚk_projÚv_projÚo_proj©r/   rƒ   r„   r2   s      €r3   r)   zEuroBertAttention.__init__‹   sB  ø€ Ý‰Œ×ÒÑÔÐØˆŒØ"ˆŒÝ ¨
°FÔ4FÈ&ÔJdÑ4dÑeÔeˆŒØ$*Ô$>À&ÔB\Ñ$\ˆÔ!Ø”} dÑ*ˆŒØ!'Ô!9ˆÔØˆŒå”iØÔ Ô :¸T¼]Ñ JÐQWÔQfð
ñ 
ô 
ˆŒõ ”iØÔ Ô :¸T¼]Ñ JÐQWÔQfð
ñ 
ô 
ˆŒõ ”iØÔ Ô :¸T¼]Ñ JÐQWÔQfð
ñ 
ô 
ˆŒõ ”iØÔ&¨¬Ñ6¸Ô8JÐQWÔQfð
ñ 
ô 
ˆŒˆˆr4   Nr5   Úposition_embeddingsro   Úpast_key_valuesrr   r&   c                 ó"  — |j         d d…         }g |¢d‘| j        ‘R }|                      |¦  «                             |¦  «                             dd¦  «        }|                      |¦  «                             |¦  «                             dd¦  «        }	|                      |¦  «                             |¦  «                             dd¦  «        }
|\  }}t          ||	||¦  «        \  }}	|�|                     |	|
| j	        ¦  «        \  }	}
t          j        | j        j        t          ¦  «        } || ||	|
|f| j        sdn| j        | j        dœ|¤Ž\  }} |j        g |¢d‘R Ž                      ¦   «         }|                      |¦  «        }||fS )Nr8   r    r7   rj   )rq   rp   )rE   rh   rŽ   Úviewrx   r�   r�   r`   Úupdater„   r   Úget_interfacerƒ   Ú_attn_implementationr€   ru   rŠ   rp   rd   r{   r‘   )r/   r5   r“   ro   r”   rr   Úinput_shapeÚhidden_shapeÚquery_statesr|   r}   r[   r\   Úattention_interfacer   r~   s                   r3   rB   zEuroBertAttention.forward¢   sÀ  € ð $Ô)¨#¨2¨#Ô.ˆØ8˜Ð8 bÐ8¨$¬-Ð8Ð8ˆà—{’{ =Ñ1Ô1×6Ò6°|ÑDÔD×NÒNÈqÐRSÑTÔTˆØ—[’[ Ñ/Ô/×4Ò4°\ÑBÔB×LÒLÈQÐPQÑRÔRˆ
Ø—{’{ =Ñ1Ô1×6Ò6°|ÑDÔD×NÒNÈqÐRSÑTÔTˆà&‰ˆˆSÝ#7¸ÀjÐRUÐWZÑ#[Ô#[Ñ ˆ�jàÐ&Ø'6×'=Ò'=¸jÈ,ÐX\ÔXfÑ'gÔ'gÑ$ˆJ˜å(?Ô(MØŒKÔ,Õ.Eñ)
ô )
Ðð %8Ð$7ØØØØØð	%
ð  $œ}ÐH�C�C°$Ô2HØ”Lð	%
ð 	%
ð ð	%
ð 	%
Ñ!ˆ�\ð *�kÔ)Ð;¨;Ð;¸Ð;Ð;Ð;×FÒFÑHÔHˆØ—k’k +Ñ.Ô.ˆØ˜LÐ(Ð(r4   ©NNN)rH   rI   rJ   Ú__doc__r!   Úintr)   r+   rK   rD   r   r   r   rB   rL   rM   s   @r3   r‚   r‚   ‡   så   ø€ € € € € àGÐGð
˜~ð 
¸#ð 
ð 
ð 
ð 
ð 
ð 
ð4 IMØ.2Ø(,ð&)ð &)à”|ð&)ð # 5¤<°´Ð#=Ô>ÀÑEð&)ð œ tÑ+ð	&)ð
  ™ð&)ð Ð+Ô,ð&)ð 
ˆuŒ|˜Uœ\Ð)Ô	*ð&)ð &)ð &)ð &)ð &)ð &)ð &)ð &)r4   r‚   c                   ó$   ‡ — e Zd Zˆ fd„Zd„ Zˆ xZS )ÚEuroBertMLPc                 ó¶  •— t          ¦   «                              ¦   «          || _        |j        | _        |j        | _        t          j        | j        | j        |j        ¬¦  «        | _        t          j        | j        | j        |j        ¬¦  «        | _	        t          j        | j        | j        |j        ¬¦  «        | _
        t          |j                 | _        d S )Nr†   )r(   r)   rƒ   r0   Úintermediate_sizer   rŒ   Úmlp_biasÚ	gate_projÚup_projÚ	down_projr
   Ú
hidden_actÚact_fn©r/   rƒ   r2   s     €r3   r)   zEuroBertMLP.__init__Ì   s¯   ø€ Ý‰Œ×ÒÑÔÐØˆŒØ!Ô-ˆÔØ!'Ô!9ˆÔÝœ 4Ô#3°TÔ5KÐRXÔRaÐbÑbÔbˆŒÝ”y Ô!1°4Ô3IÐPVÔP_Ð`Ñ`Ô`ˆŒÝœ 4Ô#9¸4Ô;KÐRXÔRaÐbÑbÔbˆŒÝ˜VÔ.Ô/ˆŒˆˆr4   c                 ó¨   — |                       |                      |                      |¦  «        ¦  «        |                      |¦  «        z  ¦  «        }|S ©N)r¨   rª   r¦   r§   )r/   rR   r¨   s      r3   rB   zEuroBertMLP.forwardÖ   sA   € Ø—N’N 4§;¢;¨t¯~ª~¸aÑ/@Ô/@Ñ#AÔ#AÀDÇLÂLÐQRÁOÄOÑ#SÑTÔTˆ	ØÐr4   )rH   rI   rJ   r)   rB   rL   rM   s   @r3   r¢   r¢   Ë   sG   ø€ € € € € ð0ð 0ð 0ð 0ð 0ðð ð ð ð ð ð r4   r¢   c                   óÒ   ‡ — e Zd Zdedefˆ fd„Z	 	 	 	 	 ddej        dej        dz  dej        dz  d	e	dz  d
e
dz  deej        ej        f         dz  dee         dej        fd„Zˆ xZS )ÚEuroBertDecoderLayerrƒ   r„   c                 ó4  •— t          ¦   «                              ¦   «          |j        | _        t          ||¬¦  «        | _        t          |¦  «        | _        t          |j        |j        ¬¦  «        | _	        t          |j        |j        ¬¦  «        | _
        d S )N)rƒ   r„   ©r1   )r(   r)   r0   r‚   Ú	self_attnr¢   Úmlpr$   Úrms_norm_epsÚinput_layernormÚpost_attention_layernormr’   s      €r3   r)   zEuroBertDecoderLayer.__init__Ü   s„   ø€ Ý‰Œ×ÒÑÔÐØ!Ô-ˆÔå*°&ÀIÐNÑNÔNˆŒå˜vÑ&Ô&ˆŒÝ.¨vÔ/AÀvÔGZÐ[Ñ[Ô[ˆÔÝ(7¸Ô8JÐPVÔPcÐ(dÑ(dÔ(dˆÔ%Ð%Ð%r4   NFr5   ro   Úposition_idsr”   Ú	use_cacher“   rr   r&   c           
      óÎ   — |}|                       |¦  «        } | j        d||||||dœ|¤Ž\  }}	||z   }|}|                      |¦  «        }|                      |¦  «        }||z   }|S )N)r5   ro   r·   r”   r¸   r“   © )rµ   r²   r¶   r³   )
r/   r5   ro   r·   r”   r¸   r“   rr   ÚresidualÚ_s
             r3   rB   zEuroBertDecoderLayer.forwardæ   s¡   € ð !ˆØ×,Ò,¨]Ñ;Ô;ˆà)˜4œ>ð 
Ø'Ø)Ø%Ø+ØØ 3ð
ð 
ð ð
ð 
Ñˆ�qð ! =Ñ0ˆð !ˆØ×5Ò5°mÑDÔDˆØŸš Ñ/Ô/ˆØ  =Ñ0ˆØÐr4   )NNNFN)rH   rI   rJ   r!   r    r)   r+   rK   Ú
LongTensorr   ÚboolrD   r   r   rB   rL   rM   s   @r3   r¯   r¯   Û   sÿ   ø€ € € € € ðe˜~ð e¸#ð eð eð eð eð eð eð /3Ø04Ø(,Ø!&ØHLðð à”|ðð œ tÑ+ðð Ô&¨Ñ-ð	ð
  ™ðð ˜$‘;ðð # 5¤<°´Ð#=Ô>ÀÑEðð Ð+Ô,ðð 
Œðð ð ð ð ð ð ð r4   r¯   c                   óL   — e Zd ZU eed<   dZdZdgZdgZdZ	dZ
dZdZdZeedœZdS )ÚEuroBertPreTrainedModelrƒ   ÚmodelTr¯   r”   )r5   Ú
attentionsN)rH   rI   rJ   r!   Ú__annotations__Úbase_model_prefixÚsupports_gradient_checkpointingÚ_no_split_modulesÚ_skip_keys_device_placementÚ_supports_flash_attnÚ_supports_sdpaÚ_supports_flex_attnÚ_can_compile_fullgraphÚ_supports_attention_backendr¯   r‚   Ú_can_record_outputsrº   r4   r3   rÀ   rÀ     sl   € € € € € € àÐÐÑØÐØ&*Ð#Ø/Ð0ÐØ#4Ð"5ÐØÐØ€NØÐà!ÐØ"&Ðà-Ø'ðð ÐÐÐr4   rÀ   c                   óÔ   ‡ — e Zd ZU ej        ed<   ddefˆ fd„Ze	 	 	 ddedz  de	d         de
dz  ded	ef         fd
„¦   «         Z ej        ¦   «         ed„ ¦   «         ¦   «         Zˆ xZS )ÚEuroBertRotaryEmbeddingÚinv_freqNrƒ   c                 ó²  •— t          ¦   «                              ¦   «          |j        | _        |j        | _        || _        | j        j        d         | _        | j        }| j        dk    rt          | j                 } || j        |¦  «        \  }| _
        |                      d|d¬¦  «         |                      d|                     ¦   «         d¬¦  «         d S )NÚ	rope_typeÚdefaultrÐ   F)Ú
persistentÚoriginal_inv_freq)r(   r)   Úmax_position_embeddingsÚmax_seq_len_cachedÚoriginal_max_seq_lenrƒ   Úrope_parametersrÒ   Úcompute_default_rope_parametersr   Úattention_scalingÚregister_bufferÚclone)r/   rƒ   ÚdeviceÚrope_init_fnrÐ   r2   s        €r3   r)   z EuroBertRotaryEmbedding.__init__  sÊ   ø€ Ý‰Œ×ÒÑÔÐØ"(Ô"@ˆÔØ$*Ô$BˆÔ!àˆŒàœÔ4°[ÔAˆŒØ!%Ô!EˆØŒ>˜YÒ&Ð&Ý.¨t¬~Ô>ˆLØ+7¨<¸¼ÀVÑ+LÔ+LÑ(ˆ�$Ô(à×Ò˜Z¨¸eÐÑDÔDÐDØ×ÒÐ0°(·.².Ñ2BÔ2BÈuÐÑUÔUÐUÐUÐUr4   rÞ   ztorch.deviceÚseq_lenr&   ztorch.Tensorc                 óü   — | j         d         }t          | dd¦  «        p| j        | j        z  }d}d|t	          j        d|dt          j        ¬¦  «                             |t          j        ¬¦  «        |z  z  z  }||fS )	a¨  
        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).
        Ú
rope_thetarh   Ng      ð?r   r7   ©r:   )rÞ   r:   )	rÙ   rˆ   r0   r‰   r+   ÚarangeÚint64r;   Úfloat)rƒ   rÞ   rà   ÚbaserP   Úattention_factorrÐ   s          r3   rÚ   z7EuroBertRotaryEmbedding.compute_default_rope_parameters,  sŒ   € ð& Ô% lÔ3ˆÝ�f˜j¨$Ñ/Ô/Ðc°6Ô3EÈÔIcÑ3cˆàÐð Ø•U”\ ! S¨!µ5´;Ð?Ñ?Ô?×BÒBÈ&ÕX]ÔXcÐBÑdÔdÐgjÑjÑkñ
ˆð Ð)Ð)Ð)r4   c                 óN  — | j         d d d …d f                              ¦   «                              |j        d         dd¦  «                             |j        ¦  «        }|d d …d d d …f                              ¦   «         }t          |j        j        t          ¦  «        r|j        j        dk    r|j        j        nd}t          |d¬¦  «        5  |                     ¦   «         |                     ¦   «         z   
                    dd¦  «        }t          j        ||fd¬	¦  «        }|                     ¦   «         | j        z  }|                     ¦   «         | j        z  }	d d d ¦  «         n# 1 swxY w Y   |                     |j        ¬
¦  «        |	                     |j        ¬
¦  «        fS )Nr   r8   r    ÚmpsÚcpuF)Údevice_typeÚenabledr7   rO   rã   )rÐ   ræ   rc   rE   r;   rÞ   Ú
isinstanceÚtypeÚstrr   rx   r+   rQ   r[   rÛ   r\   r:   )
r/   rR   r·   Úinv_freq_expandedÚposition_ids_expandedrì   ÚfreqsÚembr[   r\   s
             r3   rB   zEuroBertRotaryEmbedding.forwardJ  s·  € ð !œM¨$°°°°4¨-Ô8×>Ò>Ñ@Ô@×GÒGÈÔHZÐ[\ÔH]Ð_aÐcdÑeÔe×hÒhÐijÔiqÑrÔrÐØ ,¨Q¨Q¨Q°°a°a°a¨ZÔ 8× >Ò >Ñ @Ô @Ðå'1°!´(´-ÅÑ'EÔ'EÐkÈ!Ì(Ì-Ð[`ÒJ`ÐJ`�a”h”m�mÐfkˆÝ¨¸UÐCÑCÔCð 	5ð 	5Ø&×,Ò,Ñ.Ô.Ð1F×1LÒ1LÑ1NÔ1NÑN×YÒYÐZ[Ð]^Ñ_Ô_ˆEÝ”)˜U E˜N°Ð3Ñ3Ô3ˆCØ—'’'‘)”)˜dÔ4Ñ4ˆCØ—'’'‘)”)˜dÔ4Ñ4ˆCð		5ð 	5ð 	5ñ 	5ô 	5ð 	5ð 	5ð 	5ð 	5ð 	5ð 	5øøøð 	5ð 	5ð 	5ð 	5ð �vŠv˜AœGˆvÑ$Ô$ c§f¢f°1´7 fÑ&;Ô&;Ð;Ð;s   ÃBE&Å&E*Å-E*r­   rž   )rH   rI   rJ   r+   rK   rÃ   r!   r)   Ústaticmethodr   r    rD   ræ   rÚ   Úno_gradr   rB   rL   rM   s   @r3   rÏ   rÏ     sù   ø€ € € € € € ØŒlÐÐÑðVð V˜~ð Vð Vð Vð Vð Vð Vð  à(,Ø+/Ø"ð*ð *Ø Ñ%ð*à˜Ô(ð*ð �t‘ð*ð 
ˆ~˜uÐ$Ô	%ð	*ð *ð *ñ „\ð*ð: €U„]�_„_Øð<ð <ñ Ôñ „_ð<ð <ð <ð <ð <r4   rÏ   c                   óÊ   ‡ — e Zd Zdefˆ fd„Zeee	 	 	 	 ddej	        dej
        dz  dej	        dz  dej        dz  dee         d	eez  fd
„¦   «         ¦   «         ¦   «         Zˆ xZS )ÚEuroBertModelrƒ   c                 óÞ  •‡— t          ¦   «                              ‰¦  «         ‰j        | _        ‰j        | _        t          j        ‰j        ‰j        | j        ¦  «        | _        t          j	        ˆfd„t          ‰j        ¦  «        D ¦   «         ¦  «        | _        t          ‰j        ‰j        ¬¦  «        | _        t!          ‰¬¦  «        | _        d| _        |                      ¦   «          d S )Nc                 ó0   •— g | ]}t          ‰|¦  «        ‘ŒS rº   )r¯   )Ú.0r„   rƒ   s     €r3   ú
<listcomp>z*EuroBertModel.__init__.<locals>.<listcomp>c  s$   ø€ ÐfÐfÐf¸Õ! &¨)Ñ4Ô4ÐfÐfÐfr4   r±   )rƒ   F)r(   r)   Úpad_token_idÚpadding_idxÚ
vocab_sizer   Ú	Embeddingr0   Úembed_tokensÚ
ModuleListÚrangeÚnum_hidden_layersÚlayersr$   r´   ÚnormrÏ   Ú
rotary_embÚgradient_checkpointingÚ	post_initr«   s    `€r3   r)   zEuroBertModel.__init__\  sÔ   øø€ Ý‰Œ×Ò˜Ñ Ô Ð Ø!Ô.ˆÔØ Ô+ˆŒåœL¨Ô):¸FÔ<NÐPTÔP`ÑaÔaˆÔÝ”mØfÐfÐfÐfÅeÈFÔLdÑFeÔFeÐfÑfÔfñ
ô 
ˆŒõ $ FÔ$6¸FÔ<OÐPÑPÔPˆŒ	Ý1¸Ð@Ñ@Ô@ˆŒØ&+ˆÔ#ð 	�ŠÑÔÐÐÐr4   NÚ	input_idsro   r·   Úinputs_embedsrr   r&   c                 óÒ  — |d u |d uz  rt          d¦  «        ‚|€|                      |¦  «        }|€9t          j        |j        d         |j        ¬¦  «                             d¦  «        }t          | j        ||¬¦  «        }|}|  	                    ||¬¦  «        }| j
        d | j        j        …         D ]}	 |	|f|||dœ|¤Ž}Œ|                      |¦  «        }t          |¬¦  «        S )	Nz:You must specify exactly one of input_ids or inputs_embedsr    )rÞ   r   )rƒ   r  ro   )r·   )ro   r“   r·   )Úlast_hidden_state)Ú
ValueErrorr  r+   rä   rE   rÞ   rX   r   rƒ   r  r  r  r  r   )
r/   r
  ro   r·   r  rr   Úbidirectional_maskr5   r“   Úencoder_layers
             r3   rB   zEuroBertModel.forwardl  s6  € ð ˜Ð -°tÐ";Ñ<ð 	[ÝÐYÑZÔZÐZàÐ Ø*.×*;Ò*;¸IÑ*FÔ*FˆMàÐÝ œ<¨Ô(;¸AÔ(>À}ÔG[Ð\Ñ\Ô\×fÒfÐghÑiÔiˆLå6Ø”;Ø'Ø)ð
ñ 
ô 
Ðð &ˆØ"Ÿošo¨mÈ,˜oÑWÔWÐà!œ[Ð)H¨4¬;Ô+HÐ)HÔIð 	ð 	ˆMØ)˜MØðà1Ø$7Ø)ð	ð ð
 ðð ˆMˆMð Ÿ	š	 -Ñ0Ô0ˆÝØ+ð
ñ 
ô 
ð 	
r4   )NNNN)rH   rI   rJ   r!   r)   r   r   r   r+   r½   rK   ÚFloatTensorr   r   rD   r   rB   rL   rM   s   @r3   rø   rø   Z  së   ø€ € € € € ð˜~ð ð ð ð ð ð ð   ØØð '+Ø.2Ø04Ø26ð&
ð &
àÔ#ð&
ð œ tÑ+ð&
ð Ô&¨Ñ-ð	&
ð
 Ô(¨4Ñ/ð&
ð Ð+Ô,ð&
ð 
�Ñ	 ð&
ð &
ð &
ñ „^ñ „_ñ  Ôð&
ð &
ð &
ð &
ð &
r4   rø   c                   ó  ‡ — e Zd ZddiZddiZddgdgfiZdefˆ fd„Zee		 	 	 	 	 dd
e
j        d	z  de
j        d	z  de
j        d	z  de
j        d	z  de
j        d	z  dee         dee
j                 ez  fd„¦   «         ¦   «         Zˆ xZS )ÚEuroBertForMaskedLMzlm_head.weightzmodel.embed_tokens.weightÚlm_headÚcolwise_gather_outputr5   Úlogitsrƒ   c                 óî   •— t          ¦   «                              |¦  «         t          |¦  «        | _        t	          j        |j        |j        |j        ¦  «        | _	        |  
                    ¦   «          d S r­   )r(   r)   rø   rÁ   r   rŒ   r0   rÿ   r¥   r  r	  r«   s     €r3   r)   zEuroBertForMaskedLM.__init__ž  s_   ø€ Ý‰Œ×Ò˜Ñ Ô Ð Ý" 6Ñ*Ô*ˆŒ
Ý”y Ô!3°VÔ5FÈÌÑXÔXˆŒð 	�ŠÑÔÐÐÐr4   Nr
  ro   r·   r  Úlabelsrr   r&   c                 óÒ   —  | j         d||||dœ|¤Ž}|                      |j        ¦  «        }d}	|� | j        d||| j        j        dœ|¤Ž}	t          |	||j        |j        ¬¦  «        S )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
  ro   r·   r  N)r  r  rÿ   ©Úlossr  r5   rÂ   rº   )	rÁ   r  r  Úloss_functionrƒ   rÿ   r   r5   rÂ   )
r/   r
  ro   r·   r  r  rr   Úoutputsr  r  s
             r3   rB   zEuroBertForMaskedLM.forward¦  s¨   € ð> $. 4¤:ð $
ØØ)Ø%Ø'ð	$
ð $
ð
 ð$
ð $
ˆð —’˜gÔ7Ñ8Ô8ˆØˆØÐØ%�4Ô%Ðp¨V¸FÈtÌ{ÔOeÐpÐpÐioÐpÐpˆDåØØØ!Ô/ØÔ)ð	
ñ 
ô 
ð 	
r4   ©NNNNN)rH   rI   rJ   Ú_tied_weights_keysÚ_tp_planÚ_pp_planr!   r)   r   r   r+   r½   rK   r  r   r   rD   r   rB   rL   rM   s   @r3   r  r  ˜  s-  ø€ € € € € à*Ð,GÐHÐØÐ2Ð3€HØ˜_Ð-°¨zÐ:Ð;€Hð˜~ð ð ð ð ð ð ð Øð .2Ø.2Ø04Ø26Ø*.ð/
ð /
àÔ# dÑ*ð/
ð œ tÑ+ð/
ð Ô&¨Ñ-ð	/
ð
 Ô(¨4Ñ/ð/
ð Ô  4Ñ'ð/
ð Ð+Ô,ð/
ð 
ˆuŒ|Ô	˜~Ñ	-ð/
ð /
ð /
ñ „^ñ Ôð/
ð /
ð /
ð /
ð /
r4   r  c                   óì   ‡ — e Zd Zdefˆ fd„Zee	 	 	 	 	 ddej        dz  dej	        dz  dej        dz  dej
        dz  dej        dz  d	ee         d
eej	                 ez  fd„¦   «         ¦   «         Zˆ xZS )Ú!EuroBertForSequenceClassificationrƒ   c                 óŠ  •— t          ¦   «                              |¦  «         |j        | _        |j        | _        t	          |¦  «        | _        t          j        |j        |j        ¦  «        | _	        t          j
        ¦   «         | _        t          j        |j        | j        ¦  «        | _        |                      ¦   «          d S r­   )r(   r)   Ú
num_labelsÚclassifier_poolingrø   rÁ   r   rŒ   r0   ÚdenseÚGELUÚ
activationÚ
classifierr	  r«   s     €r3   r)   z*EuroBertForSequenceClassification.__init__Ü  s“   ø€ Ý‰Œ×Ò˜Ñ Ô Ð Ø Ô+ˆŒØ"(Ô";ˆÔå" 6Ñ*Ô*ˆŒ
Ý”Y˜vÔ1°6Ô3EÑFÔFˆŒ
Ýœ'™)œ)ˆŒÝœ) FÔ$6¸¼ÑHÔHˆŒØ�ŠÑÔÐÐÐr4   Nr
  ro   r·   r  r  rr   r&   c                 ó²  —  | j         |f|||dœ|¤Ž}|d         }| j        dv rÜ| j        dk    r|d d …df         }	n„| j        dk    ry|€|                     d¬¦  «        }	n`|                     |j        ¦  «        }||                     d¦  «        z                       d¬¦  «        }	|	|                     dd	¬
¦  «        z  }	|                      |	¦  «        }	|                      |	¦  «        }	|  	                    |	¦  «        }
nÃ| j        dk    r¸|                      |¦  «        }|                      |¦  «        }|  	                    |¦  «        }
|€|
                     d¬¦  «        }
n`|                     |
j        ¦  «        }|
|                     d¦  «        z                       d¬¦  «        }
|
|                     dd	¬
¦  «        z  }
d }|��t|                     |
j        ¦  «        }| j
        j        €f| j        dk    rd| j
        _        nN| j        dk    r7|j        t          j        k    s|j        t          j        k    rd| j
        _        nd| j
        _        | j
        j        dk    rWt#          ¦   «         }| j        dk    r1 ||
                     ¦   «         |                     ¦   «         ¦  «        }nŽ ||
|¦  «        }n�| j
        j        dk    rGt'          ¦   «         } ||
                     d| j        ¦  «        |                     d¦  «        ¦  «        }n*| j
        j        dk    rt+          ¦   «         } ||
|¦  «        }t-          ||
|j        |j        ¬¦  «        S )N©ro   r·   r  r   )Úbosr>   r-  r>   r    rO   r8   T)rP   r9   ÚlateÚ
regressionÚsingle_label_classificationÚmulti_label_classificationr  )rÁ   r&  r>   r;   rÞ   rX   Úsumr'  r)  r*  rƒ   Úproblem_typer%  r:   r+   Úlongr    r   Úsqueezer   r–   r   r   r5   rÂ   )r/   r
  ro   r·   r  r  rr   Úencoder_outputr  Úpooled_outputr  rR   r  Úloss_fcts                 r3   rB   z)EuroBertForSequenceClassification.forwardç  sp  € ð $˜œØð
à)Ø%Ø'ð	
ð 
ð
 ð
ð 
ˆð +¨1Ô-ÐàÔ" oÐ5Ð5ØÔ&¨%Ò/Ð/Ø 1°!°!°!°Q°$Ô 7��àÔ(¨FÒ2Ð2Ø!Ð)Ø$5×$:Ò$:¸qÐ$:Ñ$AÔ$A�M�Mà%3×%6Ò%6Ð7HÔ7OÑ%PÔ%P�NØ%6¸×9QÒ9QÐRTÑ9UÔ9UÑ%U×$ZÒ$ZÐ_`Ð$ZÑ$aÔ$a�MØ! ^×%7Ò%7¸AÀtÐ%7Ñ%LÔ%LÑL�Mà ŸJšJ }Ñ5Ô5ˆMØ ŸOšO¨MÑ:Ô:ˆMØ—_’_ ]Ñ3Ô3ˆFˆFàÔ$¨Ò.Ð.Ø—
’
Ð,Ñ-Ô-ˆAØ—’ Ñ"Ô"ˆAØ—_’_ QÑ'Ô'ˆFØÐ%ØŸš¨˜Ñ+Ô+��à!/×!2Ò!2°6´=Ñ!AÔ!A�Ø  >×#;Ò#;¸BÑ#?Ô#?Ñ?×DÒDÈÐDÑKÔK�Ø˜.×,Ò,°¸DÐ,ÑAÔAÑA�àˆØÑØ—Y’Y˜vœ}Ñ-Ô-ˆFØŒ{Ô'Ð/Ø”? aÒ'Ð'Ø/;�D”KÔ,Ð,Ø”_ qÒ(Ð(¨f¬l½e¼jÒ.HÐ.HÈFÌLÕ\aÔ\eÒLeÐLeØ/L�D”KÔ,Ð,à/K�D”KÔ,àŒ{Ô'¨<Ò7Ð7Ý"™9œ9�Ø”? aÒ'Ð'Ø#˜8 F§N¢NÑ$4Ô$4°f·n²nÑ6FÔ6FÑGÔG�D�Dà#˜8 F¨FÑ3Ô3�D�DØ”Ô)Ð-JÒJÐJÝ+Ñ-Ô-�Ø�x §¢¨B°´Ñ @Ô @À&Ç+Â+ÈbÁ/Ä/ÑRÔR��Ø”Ô)Ð-IÒIÐIÝ,Ñ.Ô.�Ø�x ¨Ñ/Ô/�å'ØØØ(Ô6Ø%Ô0ð	
ñ 
ô 
ð 	
r4   r  )rH   rI   rJ   r!   r)   r   r   r+   r½   rK   r  r   r   rD   r   rB   rL   rM   s   @r3   r#  r#  Ú  s  ø€ € € € € ð	˜~ð 	ð 	ð 	ð 	ð 	ð 	ð Øð .2Ø.2Ø04Ø26Ø*.ðJ
ð J
àÔ# dÑ*ðJ
ð œ tÑ+ðJ
ð Ô&¨Ñ-ð	J
ð
 Ô(¨4Ñ/ðJ
ð Ô  4Ñ'ðJ
ð Ð+Ô,ðJ
ð 
ˆuŒ|Ô	Ð7Ñ	7ðJ
ð J
ð J
ñ „^ñ ÔðJ
ð J
ð J
ð J
ð J
r4   r#  c                   óâ   ‡ — e Zd Zdefˆ fd„Zd„ Zd„ Zee	 	 	 	 	 dde	j
        dz  de	j        dz  de	j
        dz  d	e	j        dz  d
e	j
        dz  dee         deez  fd„¦   «         ¦   «         Zˆ xZS )ÚEuroBertForTokenClassificationrƒ   c                 óú   •— t          ¦   «                              |¦  «         |j        | _        t          |¦  «        | _        t          j        |j        |j        ¦  «        | _        |  	                    ¦   «          d S r­   )
r(   r)   r%  rø   rÁ   r   rŒ   r0   r*  r	  r«   s     €r3   r)   z'EuroBertForTokenClassification.__init__8  sc   ø€ Ý‰Œ×Ò˜Ñ Ô Ð Ø Ô+ˆŒÝ" 6Ñ*Ô*ˆŒ
åœ) FÔ$6¸Ô8IÑJÔJˆŒØ�ŠÑÔÐÐÐr4   c                 ó   — | j         j        S r­   ©rÁ   r  rF   s    r3   Úget_input_embeddingsz3EuroBertForTokenClassification.get_input_embeddings@  s   € ØŒzÔ&Ð&r4   c                 ó   — || j         _        d S r­   r=  )r/   rn   s     r3   Úset_input_embeddingsz3EuroBertForTokenClassification.set_input_embeddingsC  s   € Ø"'ˆŒ
ÔÐÐr4   Nr
  ro   r·   r  r  rr   r&   c                 ó.  —  | j         |f|||dœ|¤Ž}|d         }|                      |¦  «        }	d}
|�Ft          ¦   «         } ||	                     d| j        ¦  «        |                     d¦  «        ¦  «        }
t          |
|	|j        |j        ¬¦  «        S )a�  
        labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
            Labels for computing the sequence classification/regression loss. Indices should be in `[0, ...,
            config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If
            `config.num_labels > 1` a classification loss is computed (Cross-Entropy).
        r,  r   Nr8   r  )rÁ   r*  r   r–   r%  r   r5   rÂ   )r/   r
  ro   r·   r  r  rr   r  Úsequence_outputr  r  r8  s               r3   rB   z&EuroBertForTokenClassification.forwardF  s½   € ð" �$”*Øð
à)Ø%Ø'ð	
ð 
ð
 ð
ð 
ˆð " !œ*ˆØ—’ Ñ1Ô1ˆàˆØÐÝ'Ñ)Ô)ˆHØ�8˜FŸKšK¨¨D¬OÑ<Ô<¸f¿kºkÈ"¹o¼oÑNÔNˆDå$ØØØ!Ô/ØÔ)ð	
ñ 
ô 
ð 	
r4   r  )rH   rI   rJ   r!   r)   r>  r@  r   r   r+   r½   rK   r  r   r   rD   r   rB   rL   rM   s   @r3   r:  r:  6  s  ø€ € € € € ð˜~ð ð ð ð ð ð ð'ð 'ð 'ð(ð (ð (ð Øð .2Ø.2Ø04Ø26Ø*.ð#
ð #
àÔ# dÑ*ð#
ð œ tÑ+ð#
ð Ô&¨Ñ-ð	#
ð
 Ô(¨4Ñ/ð#
ð Ô  4Ñ'ð#
ð Ð+Ô,ð#
ð 
Ð&Ñ	&ð#
ð #
ð #
ñ „^ñ Ôð#
ð #
ð #
ð #
ð #
r4   r:  )rÀ   rø   r  r#  r:  )r    )rj   )AÚcollections.abcr   Útypingr   r+   r   Útorch.nnr   r   r   Úactivationsr
   Úcache_utilsr   Úintegrationsr   r   r   Úmasking_utilsr   Úmodeling_layersr   Úmodeling_outputsr   r   r   r   Úmodeling_rope_utilsr   r   Úmodeling_utilsr   r   Úprocessing_utilsr   Úutilsr   Úutils.genericr   r   r   r   Úutils.output_capturingr   Úconfiguration_eurobertr!   ÚModuler$   rU   r`   rK   r    ri   ræ   r€   r‚   r¢   r¯   rÀ   rÏ   rø   r  r#  r:  Ú__all__rº   r4   r3   ú<module>rU     sË  ðð, %Ð $Ð $Ð $Ð $Ð $Ø Ð Ð Ð Ð Ð à €€€Ø Ð Ð Ð Ð Ð Ø AÐ AÐ AÐ AÐ AÐ AÐ AÐ AÐ AÐ Aà !Ð !Ð !Ð !Ð !Ð !Ø  Ð  Ð  Ð  Ð  Ð  Ø fÐ fÐ fÐ fÐ fÐ fÐ fÐ fÐ fÐ fØ 6Ð 6Ð 6Ð 6Ð 6Ð 6Ø 9Ð 9Ð 9Ð 9Ð 9Ð 9Ø pÐ pÐ pÐ pÐ pÐ pÐ pÐ pÐ pÐ pÐ pÐ pØ KÐ KÐ KÐ KÐ KÐ KÐ KÐ KØ FÐ FÐ FÐ FÐ FÐ FÐ FÐ FØ &Ð &Ð &Ð &Ð &Ð &Ø #Ð #Ð #Ð #Ð #Ð #Ø mÐ mÐ mÐ mÐ mÐ mÐ mÐ mÐ mÐ mÐ mÐ mØ 5Ð 5Ð 5Ð 5Ð 5Ð 5Ø 2Ð 2Ð 2Ð 2Ð 2Ð 2ð Ð˜YÑ'Ô'ðJð Jð Jð Jð J�b”iñ Jô Jñ (Ô'ðJð((ð (ð (ð ÐÐ*Ñ+Ô+ðð ð ñ ,Ô+ðð2	U˜Uœ\ð 	U°#ð 	U¸%¼,ð 	Uð 	Uð 	Uð 	Uð& ð%ð %ØŒIð%àŒ<ð%ð 
Œð%ð Œ<ð	%ð
 ”L 4Ñ'ð%ð ð%ð ð%ð Ð'Ô(ð%ð %ð %ð %ð2 ÐÐ)Ñ*Ô*ð@)ð @)ð @)ð @)ð @)˜œ	ñ @)ô @)ñ +Ô*ð@)ðFð ð ð ð �"”)ñ ô ð ð (ð (ð (ð (ð (Ð5ñ (ô (ð (ðV ðð ð ð ð ˜oñ ô ñ „ðð$><ð ><ð ><ð ><ð ><˜bœiñ ><ô ><ð ><ðB ð:
ð :
ð :
ð :
ð :
Ð+ñ :
ô :
ñ „ð:
ðz ð>
ð >
ð >
ð >
ð >
Ð1ñ >
ô >
ñ „ð>
ðB ðX
ð X
ð X
ð X
ð X
Ð(?ñ X
ô X
ñ „ðX
ðv ð4
ð 4
ð 4
ð 4
ð 4
Ð%<ñ 4
ô 4
ñ „ð4
ðnð ð €€€r4   