§
    ‚Štj¶4  ã                   ó  — 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mZ ddlmZ dd	lmZ dd
lmZ ddlmZmZ ddlmZ ddlmZmZmZmZ  ed¬¦  «        e G d„ de¦  «        ¦   «         ¦   «         Z G d„ de¦  «        Z  G d„ de¦  «        Z! G d„ de¦  «        Z" G d„ de¦  «        Z#e G d„ de"¦  «        ¦   «         Z$e G d„ de"¦  «        ¦   «         Z%e G d„ d e"¦  «        ¦   «         Z&g d!¢Z'dS )"é    N)Únn)ÚBCEWithLogitsLossÚCrossEntropyLossÚMSELossé   )Ústrict)Úcreate_bidirectional_mask)ÚBaseModelOutputÚMaskedLMOutputÚSequenceClassifierOutputÚTokenClassifierOutput)ÚRopeParameters)ÚUnpack)Úauto_docstring)ÚTransformersKwargsÚcan_return_tupleé   )ÚLlamaConfig)ÚLlamaAttentionÚ
LlamaModelÚLlamaPreTrainedModelÚLlamaRMSNormzEuroBERT/EuroBERT-210m)Ú
checkpointc                   óž  ‡ — e Zd ZU dZdZdZeed<   dZeed<   dZ	eed<   d	Z
eed
<   d	Zeed<   dZedz  ed<   dZeed<   dZeed<   dZeed<   dZeed<   dZedz  ed<   dZeee         z  dz  ed<   dZedz  ed<   dZeed<   dZeed<   dZeed <   dZeez  dz  ed!<   dZeed"<   d#Zeez  ed$<   dZ eed%<   dZ!edz  ed&<   d'Z"eed(<   ˆ fd)„Z#ˆ xZ$S )*ÚEuroBertConfiga�  
    mask_token_id (`int`, *optional*, defaults to 128002):
        Mask token id.
    classifier_pooling (`str`, *optional*, defaults to `"late"`):
        The pooling strategy to use for the classifier. Can be one of ['bos', 'mean', 'late'].

    ```python
    >>> from transformers import EuroBertModel, EuroBertConfig

    >>> # Initializing a EuroBert eurobert-base style configuration
    >>> configuration = EuroBertConfig()

    >>> # Initializing a model from the eurobert-base style configuration
    >>> model = EuroBertModel(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```Úeuroberti õ Ú
vocab_sizei   Úhidden_sizei   Úintermediate_sizeé   Únum_hidden_layersÚnum_attention_headsNÚnum_key_value_headsÚsiluÚ
hidden_acti    Úmax_position_embeddingsg{®Gáz”?Úinitializer_rangeçñhãˆµøä>Úrms_norm_epsi ô Úbos_token_idiô Úeos_token_idÚpad_token_idiô Úmask_token_idé   Úpretraining_tpFÚtie_word_embeddingsÚrope_parametersÚattention_biasg        Úattention_dropoutÚmlp_biasÚhead_dimÚlateÚclassifier_poolingc                 ó`   •— | j         €| j        | _          t          ¦   «         j        di |¤Ž d S )N© )r#   r"   ÚsuperÚ__post_init__)ÚselfÚkwargsÚ	__class__s     €úk/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/transformers/models/eurobert/modular_eurobert.pyr;   zEuroBertConfig.__post_init__N   s:   ø€ ØÔ#Ð+Ø'+Ô'?ˆDÔ$Ø�‰ŒÔÐ'Ð' Ð'Ð'Ð'Ð'Ð'ó    )%Ú__name__Ú
__module__Ú__qualname__Ú__doc__Ú
model_typer   ÚintÚ__annotations__r   r   r!   r"   r#   r%   Ústrr&   r'   Úfloatr)   r*   r+   Úlistr,   r-   r/   r0   Úboolr1   r   Údictr2   r3   r4   r5   r7   r;   Ú__classcell__©r>   s   @r?   r   r      sß  ø€ € € € € € ðð ð& €Jà€J�ÐÐÑØ€K�ÐÐÑØ!Ð�sÐ!Ð!Ñ!ØÐ�sÐÐÑØ!Ð˜Ð!Ð!Ñ!Ø&*Ð˜˜t™Ð*Ð*Ñ*Ø€J�ÐÐÑØ#'Ð˜SÐ'Ð'Ñ'Ø#Ð�uÐ#Ð#Ñ#Ø€L�%ÐÐÑØ%€L�#˜‘*Ð%Ð%Ñ%Ø+1€L�#˜˜Sœ	‘/ DÑ(Ð1Ð1Ñ1Ø%€L�#˜‘*Ð%Ð%Ñ%Ø€M�3ÐÐÑØ€N�CÐÐÑØ %Ð˜Ð%Ð%Ñ%Ø48€O�^ dÑ*¨TÑ1Ð8Ð8Ñ8Ø €N�DÐ Ð Ñ Ø%(Ð�s˜U‘{Ð(Ð(Ñ(Ø€HˆdÐÐÑØ€Hˆc�D‰jÐÐÑØ$Ð˜Ð$Ð$Ñ$ð(ð (ð (ð (ð (ð (ð (ð (ð (r@   r   c                   ó    ‡ — e Zd Zdˆ fd„	Zˆ xZS )ÚEuroBertRMSNormr(   c                 óL   •— t          ¦   «                              ||¦  «         d S ©N)r:   Ú__init__)r<   r   Úepsr>   s      €r?   rS   zEuroBertRMSNorm.__init__U   s#   ø€ Ý‰Œ×Ò˜ cÑ*Ô*Ð*Ð*Ð*r@   )r(   )rA   rB   rC   rS   rM   rN   s   @r?   rP   rP   T   s=   ø€ € € € € ð+ð +ð +ð +ð +ð +ð +ð +ð +ð +r@   rP   c                   ó(   ‡ — e Zd Zdedefˆ fd„Zˆ xZS )ÚEuroBertAttentionÚconfigÚ	layer_idxc                 óZ   •— t          ¦   «                              ||¦  «         d| _        d S )NF)r:   rS   Ú	is_causal)r<   rW   rX   r>   s      €r?   rS   zEuroBertAttention.__init__Z   s(   ø€ Ý‰Œ×Ò˜ Ñ+Ô+Ð+ØˆŒˆˆr@   )rA   rB   rC   r   rF   rS   rM   rN   s   @r?   rV   rV   Y   sK   ø€ € € € € ð˜~ð ¸#ð ð ð ð ð ð ð ð ð ð r@   rV   c                   ó   — e Zd ZdS )ÚEuroBertPreTrainedModelN)rA   rB   rC   r9   r@   r?   r\   r\   _   s   € € € € € Ø€Dr@   r\   c                   ó„   — e Zd Z	 	 	 	 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dS )
ÚEuroBertModelNÚ	input_idsÚattention_maskÚposition_idsÚinputs_embedsr=   Úreturnc                 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.   )Údevicer   )rW   rb   r`   )ra   )r`   Úposition_embeddingsra   )Úlast_hidden_state)Ú
ValueErrorÚembed_tokensÚtorchÚarangeÚshapere   Ú	unsqueezer	   rW   Ú
rotary_embÚlayersr!   Únormr
   )
r<   r_   r`   ra   rb   r=   Úbidirectional_maskÚhidden_statesrf   Úencoder_layers
             r?   ÚforwardzEuroBertModel.forwardd   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 	
r@   )NNNN)rA   rB   rC   rj   Ú
LongTensorÚTensorÚFloatTensorr   r   Útupler
   rt   r9   r@   r?   r^   r^   c   sš   € € € € € 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 &
ð &
ð &
ð &
r@   r^   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_outputrr   ÚlogitsrW   c                 óî   •— t          ¦   «                              |¦  «         t          |¦  «        | _        t	          j        |j        |j        |j        ¦  «        | _	        |  
                    ¦   «          d S rR   )r:   rS   r^   Úmodelr   ÚLinearr   r   r4   r{   Ú	post_init©r<   rW   r>   s     €r?   rS   zEuroBertForMaskedLM.__init__“   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r@   Nr_   r`   ra   rb   Úlabelsr=   rc   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_   r`   ra   rb   N)r}   rƒ   r   ©Úlossr}   rr   Ú
attentionsr9   )	r   r{   rg   Úloss_functionrW   r   r   rr   r‡   )
r<   r_   r`   ra   rb   rƒ   r=   Úoutputsr}   r†   s
             r?   rt   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 	
r@   ©NNNNN)rA   rB   rC   Ú_tied_weights_keysÚ_tp_planÚ_pp_planr   rS   r   r   rj   ru   rv   rw   r   r   rx   r   rt   rM   rN   s   @r?   rz   rz   �   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 /
r@   rz   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!EuroBertForSequenceClassificationrW   c                 óŠ  •— t          ¦   «                              |¦  «         |j        | _        |j        | _        t	          |¦  «        | _        t          j        |j        |j        ¦  «        | _	        t          j
        ¦   «         | _        t          j        |j        | j        ¦  «        | _        |                      ¦   «          d S rR   )r:   rS   Ú
num_labelsr7   r^   r   r   r€   r   ÚdenseÚGELUÚ
activationÚ
classifierr�   r‚   s     €r?   rS   z*EuroBertForSequenceClassification.__init__Ñ   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r@   Nr_   r`   ra   rb   rƒ   r=   rc   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©r`   ra   rb   r   )ÚbosÚmeanr˜   r™   r.   )ÚdiméÿÿÿÿT)rš   Úkeepdimr6   Ú
regressionÚsingle_label_classificationÚmulti_label_classificationr…   )r   r7   r™   Útore   rm   Úsumr’   r”   r•   rW   Úproblem_typer‘   Údtyperj   ÚlongrF   r   Úsqueezer   Úviewr   r   rr   r‡   )r<   r_   r`   ra   rb   rƒ   r=   Úencoder_outputrg   Úpooled_outputr}   Úxr†   Úloss_fcts                 r?   rt   z)EuroBertForSequenceClassification.forwardÜ   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 	
r@   rŠ   )rA   rB   rC   r   rS   r   r   rj   ru   rv   rw   r   r   rx   r   rt   rM   rN   s   @r?   r�   r�   Ï   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
r@   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EuroBertForTokenClassificationrW   c                 óú   •— t          ¦   «                              |¦  «         |j        | _        t          |¦  «        | _        t          j        |j        |j        ¦  «        | _        |  	                    ¦   «          d S rR   )
r:   rS   r‘   r^   r   r   r€   r   r•   r�   r‚   s     €r?   rS   z'EuroBertForTokenClassification.__init__-  sc   ø€ Ý‰Œ×Ò˜Ñ Ô Ð Ø Ô+ˆŒÝ" 6Ñ*Ô*ˆŒ
åœ) FÔ$6¸Ô8IÑJÔJˆŒØ�ŠÑÔÐÐÐr@   c                 ó   — | j         j        S rR   ©r   ri   )r<   s    r?   Úget_input_embeddingsz3EuroBertForTokenClassification.get_input_embeddings5  s   € ØŒzÔ&Ð&r@   c                 ó   — || j         _        d S rR   r¯   )r<   Úvalues     r?   Úset_input_embeddingsz3EuroBertForTokenClassification.set_input_embeddings8  s   € Ø"'ˆŒ
ÔÐÐr@   Nr_   r`   ra   rb   rƒ   r=   rc   c                 ó.  —  | j         |f|||dœ|¤Ž}|d         }|                      |¦  «        }	d}
|�Ft          ¦   «         } ||	                     d| j        ¦  «        |                     d¦  «        ¦  «        }
t          |
|	|j        |j        ¬¦  «        S )a�  
        labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
            Labels for computing the sequence classification/regression loss. Indices should be in `[0, ...,
            config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If
            `config.num_labels > 1` a classification loss is computed (Cross-Entropy).
        r—   r   Nr›   r…   )r   r•   r   r¦   r‘   r   rr   r‡   )r<   r_   r`   ra   rb   rƒ   r=   r‰   Úsequence_outputr}   r†   rª   s               r?   rt   z&EuroBertForTokenClassification.forward;  s½   € ð" �$”*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 	
r@   rŠ   )rA   rB   rC   r   rS   r°   r³   r   r   rj   ru   rv   rw   r   r   rx   r   rt   rM   rN   s   @r?   r¬   r¬   +  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 #
r@   r¬   )r   r\   r^   rz   r�   r¬   )(rj   r   Útorch.nnr   r   r   Úconfiguration_utilsr   Úmasking_utilsr	   Úmodeling_outputsr
   r   r   r   Úmodeling_rope_utilsr   Úprocessing_utilsr   Úutilsr   Úutils.genericr   r   Úllama.configuration_llamar   Úllama.modeling_llamar   r   r   r   r   rP   rV   r\   r^   rz   r�   r¬   Ú__all__r9   r@   r?   ú<module>rÁ      sË  ðð  €€€Ø Ð Ð Ð Ð Ð Ø AÐ AÐ AÐ AÐ AÐ AÐ AÐ AÐ AÐ Aà )Ð )Ð )Ð )Ð )Ð )Ø 6Ð 6Ð 6Ð 6Ð 6Ð 6Ø pÐ pÐ pÐ pÐ pÐ pÐ pÐ pÐ pÐ pÐ pÐ pØ 1Ð 1Ð 1Ð 1Ð 1Ð 1Ø &Ð &Ð &Ð &Ð &Ð &Ø #Ð #Ð #Ð #Ð #Ð #Ø AÐ AÐ AÐ AÐ AÐ AÐ AÐ AØ 3Ð 3Ð 3Ð 3Ð 3Ð 3Ø aÐ aÐ aÐ aÐ aÐ aÐ aÐ aÐ aÐ aÐ aÐ að €Ð3Ð4Ñ4Ô4Øð0(ð 0(ð 0(ð 0(ð 0(�[ñ 0(ô 0(ñ „ñ 5Ô4ð0(ðf+ð +ð +ð +ð +�lñ +ô +ð +ð
ð ð ð ð ˜ñ ô ð ð	ð 	ð 	ð 	ð 	Ð2ñ 	ô 	ð 	ð'
ð '
ð '
ð '
ð '
�Jñ '
ô '
ð '
ðT 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 €€€r@   