§
    9²¸jX  ã                   óÜ  — d Z ddlmZ ddl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 dd
lmZ ddl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mZ ddlmZ ddlm Z m!Z!m"Z"m#Z# ddl$m%Z% ddl&m'Z'm(Z( ddl)m*Z* ddl+m,Z,  e#j-        e.¦  «        Z/ G d„ dej0        ¦  «        Z1d„ Z2d4d„Z3 G d„ dej0        ¦  «        Z4	 d5dej0        dej5        dej5        d ej5        d!ej5        dz  d"e6d#e6fd$„Z7 G d%„ d&ej0        ¦  «        Z8 G d'„ d(e¦  «        Z9e! G d)„ d*e¦  «        ¦   «         Z:e! G d+„ d,e:¦  «        ¦   «         Z; G d-„ d.e:e¦  «        Z< G d/„ d0ee:¦  «        Z= G d1„ d2ee:¦  «        Z>g d3¢Z?dS )6zPyTorch Persimmon model.é    )ÚCallableN)Únné   )ÚACT2FN)ÚCacheÚDynamicCache)ÚGenerationMixin)Úcreate_causal_mask)ÚFlashAttentionKwargs)Ú GenericForSequenceClassificationÚGenericForTokenClassificationÚGradientCheckpointingLayer)ÚBaseModelOutputWithPastÚCausalLMOutputWithPast)ÚROPE_INIT_FUNCTIONSÚdynamic_rope_update)ÚALL_ATTENTION_FUNCTIONSÚPreTrainedModel)ÚUnpack)ÚTransformersKwargsÚauto_docstringÚcan_return_tupleÚlogging)Údeprecate_kwarg)Úmaybe_autocastÚmerge_with_config_defaults)Úcapture_outputsé   )ÚPersimmonConfigc            	       óî   ‡ — e Zd Z edd¬¦  «        d
defˆ fd„¦   «         Ze edd¬¦  «        d
dedeej	        e
f         fd„¦   «         ¦   «         Z ej        ¦   «         ed	„ ¦   «         ¦   «         Zˆ xZS )ÚPersimmonRotaryEmbeddingÚdevicez5.18)ÚversionNÚconfigc                 ó¾  •— t          ¦   «                              ¦   «          |j        | _        |j        | _        || _        | j        j        d         | _        | j        }| j        dk    rt          | j                 } || j        |¦  «        \  }| _
        t          j        |d¬¦  «        | _        t          j        |                     ¦   «         d¬¦  «        | _        d S )NÚ	rope_typeÚdefaultF)Ú
persistent)ÚsuperÚ__init__Úmax_position_embeddingsÚmax_seq_len_cachedÚoriginal_max_seq_lenr$   Úrope_parametersr&   Úcompute_default_rope_parametersr   Úattention_scalingr   ÚBufferÚinv_freqÚcloneÚoriginal_inv_freq)Úselfr$   r"   Úrope_init_fnr2   Ú	__class__s        €ú€/root/private/project/pallet_detection_v2/.venv/lib/python3.11/site-packages/transformers/models/persimmon/modeling_persimmon.pyr*   z!PersimmonRotaryEmbedding.__init__:   sÀ   ø€ å‰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�$Ô(åœ	 (°uÐ=Ñ=Ô=ˆŒÝ!#¤¨8¯>ª>Ñ+;Ô+;ÈÐ!NÑ!NÔ!NˆÔÐÐó    Úreturnc                 ó>  — | j         d         }| j                              dd¦  «        }t          | dd¦  «        p| j        | j        z  }t          ||z  ¦  «        }d}d|t          j        d|dt          j        ¬¦  «        |z  z  z  }| 	                    |¦  «        |fS )	a•  
        Computes the inverse frequencies according to the original RoPE implementation
        Args:
            config ([`~transformers.PreTrainedConfig`]):
        Returns:
            Tuple of (`torch.Tensor`, `float`), containing the inverse frequencies for the RoPE embeddings and the
            post-processing scaling factor applied to the computed cos/sin (unused in this type of RoPE).
        Ú
rope_thetaÚpartial_rotary_factorg      ð?Úhead_dimNr   é   ©Údtype)
r.   ÚgetÚgetattrÚhidden_sizeÚnum_attention_headsÚintÚtorchÚarangeÚfloatÚto)	r$   r"   ÚkwargsÚbaser=   r>   ÚdimÚattention_factorr2   s	            r8   r/   z8PersimmonRotaryEmbedding.compute_default_rope_parametersK   s¨   € ð Ô% lÔ3ˆØ &Ô 6× :Ò :Ð;RÐTWÑ XÔ XÐÝ˜6 :¨tÑ4Ô4Ðh¸Ô8JÈfÔNhÑ8hˆÝ�(Ð2Ñ2Ñ3Ô3ˆàÐà˜$¥5¤<°°3¸ÅÄÐ#MÑ#MÔ#MÐPSÑ#SÑTÑUˆØ�{Š{˜6Ñ"Ô"Ð$4Ð4Ð4r9   c                 óú  — | j         d d d …d f                              |j        d         dd¦  «                             t          j        |j        ¬¦  «        }|d d …d d d …f                              ¦   «         }t          |j        j        t          ¦  «        r|j        j        dk    r|j        j        nd}t          |d¬¦  «        5  ||z                       dd	¦  «        }t	          j        ||fd¬
¦  «        }|                     ¦   «         | j        z  }|                     ¦   «         | j        z  }	d d d ¦  «         n# 1 swxY w Y   |                     |j        ¬¦  «        |	                     |j        ¬¦  «        fS )Nr   éÿÿÿÿr   )rA   r"   ÚmpsÚcpuF)Údevice_typeÚenabledr?   ©rM   r@   )r2   ÚexpandÚshaperJ   rG   rI   r"   Ú
isinstanceÚtypeÚstrr   Ú	transposeÚcatÚcosr0   ÚsinrA   )
r5   ÚxÚposition_idsÚinv_freq_expandedÚposition_ids_expandedrS   ÚfreqsÚembr]   r^   s
             r8   Úforwardz PersimmonRotaryEmbedding.forwarda   s›  € ð ŒM˜$    4˜-Ô(×/Ò/°Ô0BÀ1Ô0EÀrÈ1ÑMÔM×PÒPÕW\ÔWbÐklÔksÐPÑtÔtð 	ð !-¨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å¨¸UÐCÑCÔCð 	5ð 	5Ø&Ð)>Ñ>×IÒIÈ!ÈQÑOÔOˆEÝ”)˜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A*D<Ä<E ÅE ©N)Ú__name__Ú
__module__Ú__qualname__r   r   r*   ÚstaticmethodÚtuplerG   ÚTensorrI   r/   Úno_gradr   re   Ú__classcell__©r7   s   @r8   r!   r!   9   sö   ø€ € € € € Ø€_�X vÐ.Ñ.Ô.ðOð O˜ð Oð Oð Oð Oð Oñ /Ô.ðOð  à€_�X vÐ.Ñ.Ô.ð5ð 5°ð 5Ð[`ÐafÔamÐotÐatÔ[uð 5ð 5ð 5ñ /Ô.ñ „\ð5ð& €U„]�_„_Øð<ð <ñ Ôñ „_ð<ð <ð <ð <ð <r9   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..NrP   r?   rU   )rW   rG   r\   )r_   Úx1Úx2s      r8   Úrotate_halfrs   u   s]   € à	
ˆ3Ð"�!”'˜"”+ Ñ"Ð"Ð"Ô	#€BØ	
ˆ3�”˜”˜qÑ Ð"Ð"Ð"Ô	#€BÝŒ9�r�c˜2�Y BÐ'Ñ'Ô'Ð'r9   c                 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	unsqueezers   )ÚqÚkr]   r^   Úunsqueeze_dimÚq_embedÚk_embeds          r8   Úapply_rotary_pos_embr{   }   sc   € ð$ �-Š-˜Ñ
&Ô
&€CØ
�-Š-˜Ñ
&Ô
&€CØ�3‰w�; q™>œ>¨CÑ/Ñ0€GØ�3‰w�; q™>œ>¨CÑ/Ñ0€GØ�GÐÐr9   c                   ó$   ‡ — e Zd Zˆ fd„Zd„ Zˆ xZS )ÚPersimmonMLPc                 ó  •— t          ¦   «                              ¦   «          t          j        |j        |j        ¦  «        | _        t          j        |j        |j        ¦  «        | _        t          |j	                 | _
        d S rf   )r)   r*   r   ÚLinearrD   Úintermediate_sizeÚdense_h_to_4hÚdense_4h_to_hr   Ú
hidden_actÚact©r5   r$   r7   s     €r8   r*   zPersimmonMLP.__init__˜   s`   ø€ Ý‰Œ×ÒÑÔÐÝœY vÔ'9¸6Ô;SÑTÔTˆÔÝœY vÔ'?ÀÔASÑTÔTˆÔÝ˜&Ô+Ô,ˆŒˆˆr9   c                 ó„   — |                       |¦  «        }|                      |¦  «        }|                      |¦  «        }|S rf   )r�   r„   r‚   )r5   Úhidden_statess     r8   re   zPersimmonMLP.forwardž   s?   € Ø×*Ò*¨=Ñ9Ô9ˆØŸš Ñ/Ô/ˆØ×*Ò*¨=Ñ9Ô9ˆØÐr9   )rg   rh   ri   r*   re   rn   ro   s   @r8   r}   r}   —   sG   ø€ € € € € ð-ð -ð -ð -ð -ðð ð ð ð ð ð r9   r}   ç        ÚmoduleÚqueryÚkeyÚvalueÚattention_maskÚscalingÚdropoutc                 óÀ  — t          j        ||                     dd¦  «        ¦  «        |z  }|�||z   }t          j                             |dt           j        ¬¦  «                             |j        ¦  «        }t          j         	                    ||| j
        ¬¦  «        }t          j        ||¦  «        }	|	                     dd¦  «                             ¦   «         }	|	|fS )Nr?   r   rP   )rM   rA   )ÚpÚtrainingr   )rG   Úmatmulr[   r   Ú
functionalÚsoftmaxÚfloat32rJ   rA   r�   r’   Ú
contiguous)
r‰   rŠ   r‹   rŒ   r�   rŽ   r�   rK   Úattn_weightsÚattn_outputs
             r8   Úeager_attention_forwardrš   ¥   sÃ   € õ ”<  s§}¢}°Q¸Ñ':Ô':Ñ;Ô;¸gÑE€LØÐ!Ø# nÑ4ˆå”=×(Ò(¨¸2ÅUÄ]Ð(ÑSÔS×VÒVÐW\ÔWbÑcÔc€LÝ”=×(Ò(¨¸È6Ì?Ð(Ñ[Ô[€LÝ”,˜|¨UÑ3Ô3€KØ×'Ò'¨¨1Ñ-Ô-×8Ò8Ñ:Ô:€Kà˜Ð$Ð$r9   c                   óf  ‡ — e Zd ZdZddededz  fˆ fd„Zdej        de	ej        ej        ej        f         fd„Z
	 	 	 	 	 	 dd
ej        dej        dz  dej        dz  dedz  dedede	ej        ej        f         dz  dee         de	ej        ej        dz  e	ej                 dz  f         fd„Zˆ xZS )ÚPersimmonAttentionz=Multi-headed attention from 'Attention Is All You Need' paperNr$   Ú	layer_idxc                 óÂ  •— t          ¦   «                              ¦   «          || _        || _        |€(t                               d| j        j        › d�¦  «         |j        | _        |j	        | _
        | j        | j
        z  | _        t          | j        |j        d         z  ¦  «        | _        d| _        | j        | j
        z  | j        k    r t!          d| j        › d| j
        › d�¦  «        ‚t#          j        | j        d| j        z  d¬	¦  «        | _        t#          j        | j
        | j        z  | j        d¬	¦  «        | _        |j        | _        | j        d
z  | _        | j        r\t#          j        |j        | j
        z  |j        d¬¦  «        | _        t#          j        |j        | j
        z  |j        d¬¦  «        | _        t#          j        |j        ¦  «        | _        d S )NzInstantiating z¹ without passing a `layer_idx` is not recommended and will lead to errors during the forward call if caching is used. Please make sure to provide a `layer_idx` when creating this class.r=   Tz?hidden_size must be divisible by num_heads (got `hidden_size`: z and `num_heads`: z).r   ©Úbiasg      à¿)ÚepsÚelementwise_affine)r)   r*   r$   r�   ÚloggerÚwarning_oncer7   rg   rD   rE   Ú	num_headsr>   rF   r.   Úrotary_ndimsÚ	is_causalÚ
ValueErrorr   r   Úquery_key_valueÚdenseÚqk_layernormrŽ   Ú	LayerNormÚlayer_norm_epsÚq_layernormÚk_layernormÚDropoutÚattention_dropout©r5   r$   r�   r7   s      €r8   r*   zPersimmonAttention.__init__¾   sì  ø€ Ý‰Œ×ÒÑÔÐØˆŒØ"ˆŒØÐÝ×Òð, ¤Ô!8ð ,ð ,ð ,ñô ð ð "Ô-ˆÔØÔ3ˆŒØÔ(¨D¬NÑ:ˆŒå ¤°Ô0FÐG^Ô0_Ñ _Ñ`Ô`ˆÔØˆŒàŒM˜DœNÑ*¨tÔ/?Ò?Ð?Ýð8ÐRVÔRbð 8ð 8Ø%)¤^ð8ð 8ð 8ñô ð õ  "œy¨Ô)9¸1¸tÔ?OÑ;OÐVZÐ[Ñ[Ô[ˆÔÝ”Y˜tœ~°´Ñ=¸tÔ?OÐVZÐ[Ñ[Ô[ˆŒ
Ø"Ô/ˆÔØ”} dÑ*ˆŒàÔð 	Ý!œ|ØÔ" d¤nÑ4¸&Ô:OÐdhð ñ  ô  ˆDÔõ  "œ|ØÔ" d¤nÑ4¸&Ô:OÐdhð ñ  ô  ˆDÔõ "$¤¨FÔ,DÑ!EÔ!EˆÔÐÐr9   Ú	fused_qkvr:   c                 óª   — |j         \  }}}|                     ||| j        d| j        ¦  «        }|dddd…f         |dddd…f         |dddd…f         fS )aÊ  
        Split the last dimension into (num_heads, head_dim) without making any copies, results share same memory
        storage as `fused_qkv`

        Args:
            fused_qkv (`torch.tensor`): [batch_size, seq_length, num_heads * 3 * head_dim]

        Returns:
            query: [batch_size, seq_length, num_heads, head_dim] key: [batch_size, seq_length, num_heads, head_dim]
            value: [batch_size, seq_length, num_heads, head_dim]
        r   .r   Nr   r?   )rW   Úviewr¥   r>   )r5   r³   Ú
batch_sizeÚ
seq_lengthÚthree_times_hidden_sizes        r8   Ú_split_headszPersimmonAttention._split_headsã   sk   € ð ;D¼/Ñ7ˆ
�JÐ 7Ø—N’N :¨z¸4¼>È1ÈdÌmÑ\Ô\ˆ	Ø˜˜a   ˜Ô# Y¨s°A°q°q°q¨yÔ%9¸9ÀSÈ!ÈQÈQÈQÀYÔ;OÐOÐOr9   Fr‡   r�   r`   Úpast_key_valuesÚoutput_attentionsÚ	use_cacheÚposition_embeddingsrK   c                 óÐ  — |                      ¦   «         \  }	}
}|                      |¦  «        }|                      |¦  «        \  }}}| j        r*|                      |¦  «        }|                      |¦  «        }|                     dd¦  «        }|                     dd¦  «        }|                     dd¦  «        }|\  }}|dd | j        …f         |d| j        d …f         }}|dd | j        …f         |d| j        d …f         }}t          ||||¦  «        \  }}t          j
        ||fd¬¦  «        }t          j
        ||fd¬¦  «        }|�|                     ||| j        ¦  «        \  }}t          j        | j        j        t"          ¦  «        } || ||||f| j        sdn| j        j        | j        dœ|¤Ž\  }}|                     |	|
d¦  «        }|                      |¦  «        }||fS )Nr   r?   .rP   rU   rˆ   )r�   rŽ   )Úsizer©   r¹   r«   r®   r¯   r[   r¦   r{   rG   r\   Úupdater�   r   Úget_interfacer$   Ú_attn_implementationrš   r’   r±   rŽ   Úreshaperª   )r5   r‡   r�   r`   rº   r»   r¼   r½   rK   ÚbszÚq_lenÚ_r³   Úquery_statesÚ
key_statesÚvalue_statesr]   r^   Ú	query_rotÚ
query_passÚkey_rotÚkey_passÚattention_interfacer™   r˜   s                            r8   re   zPersimmonAttention.forwardó   sL  € ð &×*Ò*Ñ,Ô,‰ˆˆU�Að ×(Ò(¨Ñ7Ô7ˆ	ð 48×3DÒ3DÀYÑ3OÔ3OÑ0ˆ�z <àÔð 	6Ø×+Ò+¨LÑ9Ô9ˆLØ×)Ò)¨*Ñ5Ô5ˆJð $×-Ò-¨a°Ñ3Ô3ˆØ#×-Ò-¨a°Ñ3Ô3ˆØ×)Ò)¨!¨QÑ/Ô/ˆ
à&‰ˆˆSà˜Ð1 Ô 1Ð1Ð1Ô2Ø˜˜dÔ/Ð1Ð1Ð1Ô2ð ˆ	ð
 �sÐ/˜dÔ/Ð/Ð/Ô0Ø�s˜DÔ-Ð/Ð/Ð/Ô0ð ˆõ
 2°)¸WÀcÈ3ÑOÔOÑˆ	�7õ ”y )¨ZÐ!8¸bÐAÑAÔAˆÝ”Y ¨Ð2¸Ð;Ñ;Ô;ˆ
à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  $œ}ÐO�C�C°$´+Ô2OØ”Lð	%
ð 	%
ð ð	%
ð 	%
Ñ!ˆ�\ð "×)Ò)¨#¨u°bÑ9Ô9ˆØ—j’j Ñ-Ô-ˆà˜LÐ(Ð(r9   rf   )NNNFFN)rg   rh   ri   Ú__doc__r   rF   r*   rG   rl   rk   r¹   Ú
LongTensorr   Úboolr   r   re   rn   ro   s   @r8   rœ   rœ   »   sˆ  ø€ € € € € ØGÐGð#Fð #F˜ð #F¸3À¹:ð #Fð #Fð #Fð #Fð #Fð #FðJP e¤lð P°u¸U¼\È5Ì<ÐY^ÔYeÐ=eÔ7fð Pð Pð Pð Pð& /3Ø04Ø(,Ø"'ØØHLðA)ð A)à”|ðA)ð œ tÑ+ðA)ð Ô&¨Ñ-ð	A)ð
  ™ðA)ð  ðA)ð ðA)ð # 5¤<°´Ð#=Ô>ÀÑEðA)ð Ð-Ô.ðA)ð 
ˆuŒ|˜Uœ\¨DÑ0°%¸¼Ô2EÈÑ2LÐLÔ	MðA)ð A)ð A)ð A)ð A)ð A)ð A)ð A)r9   rœ   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PersimmonDecoderLayerr$   r�   c                 ó„  •— t          ¦   «                              ¦   «          |j        | _        t          ||¬¦  «        | _        t          |¦  «        | _        t          j        |j        |j	        ¬¦  «        | _
        t          j        |j        |j	        ¬¦  «        | _        t          j        |j        ¦  «        | _        d S )N)r$   r�   ©r¡   )r)   r*   rD   rœ   Ú	self_attnr}   Úmlpr   r¬   r­   Úinput_layernormÚpost_attention_layernormr°   Úhidden_dropoutr�   r²   s      €r8   r*   zPersimmonDecoderLayer.__init__8  s™   ø€ Ý‰Œ×ÒÑÔÐØ!Ô-ˆÔÝ+°6ÀYÐOÑOÔOˆŒÝ Ñ'Ô'ˆŒÝ!œ|¨FÔ,>ÀFÔDYÐZÑZÔZˆÔÝ(*¬°VÔ5GÈVÔMbÐ(cÑ(cÔ(cˆÔ%Ý”z &Ô"7Ñ8Ô8ˆŒˆˆr9   NFr‡   r�   r`   rº   r¼   r½   rK   r:   c           
      óø   — |}|                       |¦  «        } | j        d||||||dœ|¤Ž\  }}	||z   }|}|                      |¦  «        }|                      |¦  «        }|                      |¦  «        }||z   }|S )N)r‡   r�   r`   rº   r¼   r½   © )rØ   rÖ   rÙ   r×   r�   )
r5   r‡   r�   r`   rº   r¼   r½   rK   ÚresidualrÆ   s
             r8   re   zPersimmonDecoderLayer.forwardA  s´   € ð !ˆà×,Ò,¨]Ñ;Ô;ˆð *˜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àŸš ]Ñ3Ô3ˆØ%¨Ñ0ˆàÐr9   )NNNFN)rg   rh   ri   r   rF   r*   rG   rl   rÐ   r   rÑ   rk   r   r   re   rn   ro   s   @r8   rÓ   rÓ   7  s÷   ø€ € € € € ð9˜ð 9¸3ð 9ð 9ð 9ð 9ð 9ð 9ð /3Ø04Ø(,Ø!&ØHLð"ð "à”|ð"ð œ tÑ+ð"ð Ô&¨Ñ-ð	"ð
  ™ð"ð ˜$‘;ð"ð # 5¤<°´Ð#=Ô>ÀÑEð"ð Ð-Ô.ð"ð 
Œð"ð "ð "ð "ð "ð "ð "ð "r9   rÓ   c                   óH   — e Zd ZU eed<   dZdZdgZdgZdZ	dZ
dZdZeedœZdS )ÚPersimmonPreTrainedModelr$   ÚmodelTrÓ   rº   )r‡   Ú
attentionsN)rg   rh   ri   r   Ú__annotations__Úbase_model_prefixÚsupports_gradient_checkpointingÚ_no_split_modulesÚ_skip_keys_device_placementÚ_can_compile_fullgraphÚ_supports_sdpaÚ_supports_flash_attnÚ_supports_attention_backendrÓ   rœ   Ú_can_record_outputsrÜ   r9   r8   rß   rß   f  sf   € € € € € € àÐÐÑØÐØ&*Ð#Ø0Ð1ÐØ#4Ð"5ÐØ!ÐØ€NØÐØ"&Ðà.Ø(ðð ÐÐÐr9   rß   c                   óæ   ‡ — e Zd ZdZdefˆ fd„Zeee	 	 	 	 	 	 dde	j
        dz  de	j        dz  de	j
        dz  dedz  d	e	j        dz  d
edz  dee         defd„¦   «         ¦   «         ¦   «         Zˆ xZS )ÚPersimmonModelz£
    Transformer decoder consisting of *config.num_hidden_layers* layers. Each layer is a [`PersimmonDecoderLayer`]

    Args:
        config: PersimmonConfig
    r$   c                 óò  •‡— t          ¦   «                              ‰¦  «         ‰j        | _        ‰j        | _        t          j        ‰j        ‰j        | j        ¦  «        | _        t          j	        ˆfd„t          ‰j        ¦  «        D ¦   «         ¦  «        | _        t          j        ‰j        ‰j        ¬¦  «        | _        t!          | j        ¬¦  «        | _        d| _        |                      ¦   «          d S )Nc                 ó0   •— g | ]}t          ‰|¦  «        ‘ŒS rÜ   )rÓ   )Ú.0r�   r$   s     €r8   ú
<listcomp>z+PersimmonModel.__init__.<locals>.<listcomp>‡  s$   ø€ ÐgÐgÐg¸)Õ" 6¨9Ñ5Ô5ÐgÐgÐgr9   rÕ   ©r$   F)r)   r*   Úpad_token_idÚpadding_idxÚ
vocab_sizer   Ú	EmbeddingrD   Úembed_tokensÚ
ModuleListÚrangeÚnum_hidden_layersÚlayersr¬   r­   Úfinal_layernormr!   r$   Ú
rotary_embÚgradient_checkpointingÚ	post_initr…   s    `€r8   r*   zPersimmonModel.__init__€  s×   øø€ Ý‰Œ×Ò˜Ñ Ô Ð Ø!Ô.ˆÔØ Ô+ˆŒåœL¨Ô):¸FÔ<NÐPTÔP`ÑaÔaˆÔÝ”mØgÐgÐgÐgÅuÈVÔMeÑGfÔGfÐgÑgÔgñ
ô 
ˆŒõ  "œ|¨FÔ,>ÀFÔDYÐZÑZÔZˆÔÝ2¸$¼+ÐFÑFÔFˆŒØ&+ˆÔ#à�ŠÑÔÐÐÐr9   NÚ	input_idsr�   r`   rº   Úinputs_embedsr¼   rK   r:   c           
      ó$  — |d u |d uz  rt          d¦  «        ‚|r|€t          | j        ¬¦  «        }|€|                      |¦  «        }|€V|�|                     ¦   «         nd}t          j        |j        d         |j        ¬¦  «        |z   }| 	                    d¦  «        }t          | j        ||||¬¦  «        }	|}
|                      |
|¬¦  «        }| j        D ]} ||
f|	||||dœ|¤Ž}
Œ|                      |
¦  «        }
t          |
|¬	¦  «        S )
Nz:You must specify exactly one of input_ids or inputs_embedsrò   r   r   )r"   )r$   r  r�   rº   r`   )r`   )r�   r`   rº   r¼   r½   )Úlast_hidden_staterº   )r¨   r   r$   r÷   Úget_seq_lengthrG   rH   rW   r"   ru   r
   rý   rû   rü   r   )r5   r   r�   r`   rº   r  r¼   rK   Úpast_seen_tokensÚcausal_maskr‡   r½   Údecoder_layers                r8   re   zPersimmonModel.forward�  s|  € ð ˜Ð -°tÐ";Ñ<ð 	[ÝÐYÑZÔZÐZàð 	?˜Ð0Ý*°$´+Ð>Ñ>Ô>ˆOàÐ Ø ×-Ò-¨iÑ8Ô8ˆMàÐØCRÐC^˜×=Ò=Ñ?Ô?Ð?ÐdeÐÝ œ<¨Ô(;¸AÔ(>À}ÔG[Ð\Ñ\Ô\Ð_oÑoˆLØ'×1Ò1°!Ñ4Ô4ˆLå(Ø”;Ø'Ø)Ø+Ø%ð
ñ 
ô 
ˆð &ˆØ"Ÿošo¨mÈ,˜oÑWÔWÐà!œ[ð 		ð 		ˆMØ)˜MØðà*Ø)Ø /Ø#Ø$7ðð ð ðð ˆMˆMð ×,Ò,¨]Ñ;Ô;ˆå&Ø+Ø+ð
ñ 
ô 
ð 	
r9   )NNNNNN)rg   rh   ri   rÏ   r   r*   r   r   r   rG   rÐ   rl   r   ÚFloatTensorrÑ   r   r   r   re   rn   ro   s   @r8   rí   rí   w  s  ø€ € € € € ðð ð˜ð ð ð ð ð ð ð  ØØð .2Ø.2Ø04Ø(,Ø26Ø!%ð3
ð 3
àÔ# dÑ*ð3
ð œ tÑ+ð3
ð Ô&¨Ñ-ð	3
ð
  ™ð3
ð Ô(¨4Ñ/ð3
ð ˜$‘;ð3
ð Ð+Ô,ð3
ð 
!ð3
ð 3
ð 3
ñ „^ñ „_ñ  Ôð3
ð 3
ð 3
ð 3
ð 3
r9   rí   c                   ó   ‡ — e Zd ZddiZˆ fd„Zee	 	 	 	 	 	 	 	 ddej        dz  dej	        dz  dej        dz  d	e
dz  d
ej        dz  dej        dz  dedz  deej	        z  dee         defd„¦   «         ¦   «         Zˆ xZS )ÚPersimmonForCausalLMzlm_head.weightzmodel.embed_tokens.weightc                 óþ   •— t          ¦   «                              |¦  «         t          |¦  «        | _        |j        | _        t          j        |j        |j        d¬¦  «        | _        |  	                    ¦   «          d S )NFrŸ   )
r)   r*   rí   rà   rõ   r   r   rD   Úlm_headrÿ   r…   s     €r8   r*   zPersimmonForCausalLM.__init__Ì  sj   ø€ Ý‰Œ×Ò˜Ñ Ô Ð Ý# FÑ+Ô+ˆŒ
Ø Ô+ˆŒÝ”y Ô!3°VÔ5FÈUÐSÑSÔSˆŒð 	�ŠÑÔÐÐÐr9   Nr   r   r�   r`   rº   r  Úlabelsr¼   Úlogits_to_keeprK   r:   c	           
      óP  —  | j         d||||||dœ|	¤Ž}
|
j        }t          |t          ¦  «        rt	          | d¦  «        n|}|                      |dd…|dd…f         ¦  «        }d}|� | j        ||fd| j        j        i|	¤Ž}t          |||
j
        |
j        |
j        ¬¦  «        S )uk  
        labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
            Labels for computing the masked language modeling loss. Indices should either be in `[0, ...,
            config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored
            (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`.

        Example:

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

        >>> model = PersimmonForCausalLM.from_pretrained("adept/persimmon-8b-base")
        >>> tokenizer = AutoTokenizer.from_pretrained("adept/persimmon-8b-base")

        >>> prompt = "human: Hey, what should I eat for dinner?"
        >>> inputs = tokenizer(prompt, return_tensors="pt")

        >>> # Generate
        >>> generate_ids = model.generate(inputs.input_ids, max_length=30)
        >>> tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
        'human: Hey, what should I eat for dinner?\n\ncat: ðŸ�±\n\nhuman: ðŸ˜�\n\n'
        ```)r   r�   r`   rº   r  r¼   Nrõ   )ÚlossÚlogitsrº   r‡   rá   rÜ   )rà   r  rX   rF   Úslicer  Úloss_functionr$   rõ   r   rº   r‡   rá   )r5   r   r�   r`   rº   r  r  r¼   r  rK   Úoutputsr‡   Úslice_indicesr  r  s                  r8   re   zPersimmonForCausalLM.forwardÕ  sõ   € ðH ,6¨4¬:ð ,
ØØ)Ø%Ø+Ø'Øð,
ð ,
ð ð,
ð ,
ˆð  Ô1ˆÝ8BÀ>ÕSVÑ8WÔ8WÐk�˜~˜o¨tÑ4Ô4Ð4Ð]kˆØ—’˜m¨A¨A¨A¨}¸a¸a¸aÐ,?Ô@ÑAÔAˆàˆØÐØ%�4Ô% f¨fÐbÐbÀÄÔAWÐbÐ[aÐbÐbˆDå%ØØØ#Ô3Ø!Ô/ØÔ)ð
ñ 
ô 
ð 	
r9   )NNNNNNNr   )rg   rh   ri   Ú_tied_weights_keysr*   r   r   rG   rÐ   rl   r   r  rÑ   rF   r   r   r   re   rn   ro   s   @r8   r
  r
  È  s,  ø€ € € € € Ø*Ð,GÐHÐðð ð ð ð ð Øð .2Ø.2Ø04Ø(,Ø26Ø*.Ø!%Ø-.ð:
ð :
àÔ# dÑ*ð:
ð œ tÑ+ð:
ð Ô&¨Ñ-ð	:
ð
  ™ð:
ð Ô(¨4Ñ/ð:
ð Ô  4Ñ'ð:
ð ˜$‘;ð:
ð ˜eœlÑ*ð:
ð Ð+Ô,ð:
ð 
 ð:
ð :
ð :
ñ „^ñ Ôð:
ð :
ð :
ð :
ð :
r9   r
  c                   ó   — e Zd ZdS )Ú"PersimmonForSequenceClassificationN©rg   rh   ri   rÜ   r9   r8   r  r    ó   € € € € € € € r9   r  c                   ó   — e Zd ZdS )ÚPersimmonForTokenClassificationNr  rÜ   r9   r8   r  r    r  r9   r  )r
  rí   rß   r  r  )r   )rˆ   )@rÏ   Úcollections.abcr   rG   r   Úactivationsr   Úcache_utilsr   r   Ú
generationr	   Úmasking_utilsr
   Úmodeling_flash_attention_utilsr   Úmodeling_layersr   r   r   Úmodeling_outputsr   r   Úmodeling_rope_utilsr   r   Úmodeling_utilsr   r   Úprocessing_utilsr   Úutilsr   r   r   r   Úutils.deprecationr   Úutils.genericr   r   Úutils.output_capturingr   Úconfiguration_persimmonr   Ú
get_loggerrg   r£   ÚModuler!   rs   r{   r}   rl   rI   rš   rœ   rÓ   rß   rí   r
  r  r  Ú__all__rÜ   r9   r8   ú<module>r0     s  ðð& Ð à $Ð $Ð $Ð $Ð $Ð $à €€€Ø Ð Ð Ð Ð Ð à !Ð !Ð !Ð !Ð !Ð !Ø .Ð .Ð .Ð .Ð .Ð .Ð .Ð .Ø )Ð )Ð )Ð )Ð )Ð )Ø /Ð /Ð /Ð /Ð /Ð /Ø BÐ BÐ BÐ BÐ BÐ Bðð ð ð ð ð ð ð ð ð ð
ð ð ð ð ð ð ð ðð ð ð ð ð ð ð ð GÐ FÐ FÐ FÐ FÐ FÐ FÐ FØ &Ð &Ð &Ð &Ð &Ð &Ø RÐ RÐ RÐ RÐ RÐ RÐ RÐ RÐ RÐ RÐ RÐ RØ 0Ð 0Ð 0Ð 0Ð 0Ð 0Ø GÐ GÐ GÐ GÐ GÐ GÐ GÐ GØ 5Ð 5Ð 5Ð 5Ð 5Ð 5Ø 4Ð 4Ð 4Ð 4Ð 4Ð 4ð 
ˆÔ	˜HÑ	%Ô	%€ð8<ð 8<ð 8<ð 8<ð 8<˜rœyñ 8<ô 8<ð 8<ðx(ð (ð (ðð ð ð ð4ð ð ð ð �2”9ñ ô ð ð* ð%ð %ØŒIð%àŒ<ð%ð 
Œð%ð Œ<ð	%ð
 ”L 4Ñ'ð%ð ð%ð ð%ð %ð %ð %ð,y)ð y)ð y)ð y)ð y)˜œñ y)ô y)ð y)ðx,ð ,ð ,ð ,ð ,Ð6ñ ,ô ,ð ,ð^ ðð ð ð ð ˜ñ ô ñ „ðð  ðM
ð M
ð M
ð M
ð M
Ð-ñ M
ô M
ñ „ðM
ð`I
ð I
ð I
ð I
ð I
Ð3°_ñ I
ô I
ð I
ðX jÐ iÐ iÐ iÐ iÐ)IÐKcÑ iÔ iÐ ið dÐ cÐ cÐ cÐ cÐ&CÐE]Ñ cÔ cÐ cðð ð €€€r9   