§
    ‚ŠtjÒ\  ã                   óš  — d dl m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 ddlmZmZ ddl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 ddlmZm Z  ddl!m"Z"m#Z# ddl$m%Z% ddl&m'Z'm(Z(m)Z) ddl*m+Z+m,Z, ddl-m.Z. ddl/m0Z0  G d„ dej1        ¦  «        Z2 G d„ dej1        ¦  «        Z3d„ Z4 ed¦  «        d:d„¦   «         Z5dej6        de7dej6        fd „Z8	 	 	 d;d"ej1        d#ej6        d$ej6        d%ej6        d&ej6        dz  d'e9e7z  d(e9dz  d)e9dz  de:ej6        ej6        f         fd*„Z; ee5¦  «         G d+„ d,ej1        ¦  «        ¦   «         Z< G d-„ d.e¦  «        Z= G d/„ d0ej1        ¦  «        Z> G d1„ d2ej?        ¦  «        Z@e( G d3„ d4e#¦  «        ¦   «         ZAe( G d5„ d6eA¦  «        ¦   «         ZBe( G d7„ d8eAe¦  «        ¦   «         ZCg d9¢ZDdS )<é    )ÚCallable)ÚOptionalNé   )Úinitialization)ÚACT2FN)ÚCacheÚDynamicCache)ÚGenerationMixin)Úuse_kernel_func_from_hubÚuse_kernelized_func)Úcreate_causal_maskÚ!create_sliding_window_causal_mask)ÚFlashAttentionKwargs)ÚGradientCheckpointingLayer)ÚBaseModelOutputWithPastÚCausalLMOutputWithPast)ÚROPE_INIT_FUNCTIONSÚdynamic_rope_update)ÚALL_ATTENTION_FUNCTIONSÚPreTrainedModel)ÚUnpack)ÚTransformersKwargsÚauto_docstringÚcan_return_tuple)Úmaybe_autocastÚmerge_with_config_defaults)Úcapture_outputsé   )ÚVaultGemmaConfigc                   ó<   ‡ — e Zd Zddedefˆ fd„Zd„ Zd„ Zd„ Zˆ xZ	S )	ÚVaultGemmaRMSNormç�íµ ÷Æ°>ÚdimÚepsc                 ó¬   •— t          ¦   «                              ¦   «          || _        t          j        t          j        |¦  «        ¦  «        | _        d S ©N)ÚsuperÚ__init__r$   ÚnnÚ	ParameterÚtorchÚzerosÚweight)Úselfr#   r$   Ú	__class__s      €úp/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/transformers/models/vaultgemma/modeling_vaultgemma.pyr(   zVaultGemmaRMSNorm.__init__/   s?   ø€ Ý‰Œ×ÒÑÔÐØˆŒÝ”l¥5¤;¨sÑ#3Ô#3Ñ4Ô4ˆŒˆˆó    c                 ó�   — |t          j        |                     d¦  «                             dd¬¦  «        | j        z   ¦  «        z  S )Né   éÿÿÿÿT)Úkeepdim)r+   ÚrsqrtÚpowÚmeanr$   )r.   Úxs     r0   Ú_normzVaultGemmaRMSNorm._norm4   s8   € Ø•5”;˜qŸušu Q™xœxŸ}š}¨R¸˜}Ñ>Ô>ÀÄÑIÑJÔJÑJÐJr1   c                 ó¸   — |                       |                     ¦   «         ¦  «        }|d| j                             ¦   «         z   z  }|                     |¦  «        S )Nç      ð?)r:   Úfloatr-   Útype_as)r.   r9   Úoutputs      r0   ÚforwardzVaultGemmaRMSNorm.forward7   sL   € Ø—’˜AŸGšG™IœIÑ&Ô&ˆð ˜3 ¤×!2Ò!2Ñ!4Ô!4Ñ4Ñ5ˆØ�~Š~˜aÑ Ô Ð r1   c                 óH   — t          | j        j        ¦  «        › d| j        › �S )Nz, eps=)Útupler-   Úshaper$   )r.   s    r0   Ú
extra_reprzVaultGemmaRMSNorm.extra_repr>   s%   € Ý˜œÔ)Ñ*Ô*Ð<Ð<°$´(Ð<Ð<Ð<r1   )r"   )
Ú__name__Ú
__module__Ú__qualname__Úintr=   r(   r:   r@   rD   Ú__classcell__©r/   s   @r0   r!   r!   .   s€   ø€ € € € € ð5ð 5˜Cð 5 eð 5ð 5ð 5ð 5ð 5ð 5ð
Kð Kð Kð!ð !ð !ð=ð =ð =ð =ð =ð =ð =r1   r!   c                   ó$   ‡ — e Zd Zˆ fd„Zd„ Zˆ xZS )ÚVaultGemmaMLPc                 ó˜  •— t          ¦   «                              ¦   «          || _        |j        | _        |j        | _        t          j        | j        | j        d¬¦  «        | _        t          j        | j        | j        d¬¦  «        | _        t          j        | j        | j        d¬¦  «        | _	        t          |j                 | _        d S ©NF©Úbias)r'   r(   ÚconfigÚhidden_sizeÚintermediate_sizer)   ÚLinearÚ	gate_projÚup_projÚ	down_projr   Úhidden_activationÚact_fn©r.   rQ   r/   s     €r0   r(   zVaultGemmaMLP.__init__C   s¦   ø€ Ý‰Œ×ÒÑÔÐØˆŒØ!Ô-ˆÔØ!'Ô!9ˆÔÝœ 4Ô#3°TÔ5KÐRWÐXÑXÔXˆŒÝ”y Ô!1°4Ô3IÐPUÐVÑVÔVˆŒÝœ 4Ô#9¸4Ô;KÐRWÐXÑXÔXˆŒÝ˜VÔ5Ô6ˆŒˆˆr1   c                 ó¨   — |                       |                      |                      |¦  «        ¦  «        |                      |¦  «        z  ¦  «        }|S r&   )rW   rY   rU   rV   )r.   r9   rW   s      r0   r@   zVaultGemmaMLP.forwardM   sA   € Ø—N’N 4§;¢;¨t¯~ª~¸aÑ/@Ô/@Ñ#AÔ#AÀDÇLÂLÐQRÁOÄOÑ#SÑTÔTˆ	ØÐr1   )rE   rF   rG   r(   r@   rI   rJ   s   @r0   rL   rL   B   sG   ø€ € € € € ð7ð 7ð 7ð 7ð 7ðð ð ð ð ð ð r1   rL   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..Nr4   r3   ©r#   )rC   r+   Úcat)r9   Úx1Úx2s      r0   Úrotate_halfra   R   s]   € à	
ˆ3Ð"�!”'˜"”+ Ñ"Ð"Ð"Ô	#€BØ	
ˆ3�”˜”˜qÑ Ð"Ð"Ð"Ô	#€BÝŒ9�r�c˜2�Y BÐ'Ñ'Ô'Ð'r1   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	unsqueezera   )ÚqÚkÚcosÚsinÚunsqueeze_dimÚq_embedÚk_embeds          r0   Úapply_rotary_pos_embrl   Y   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r1   Úhidden_statesÚn_repÚreturnc                 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)rC   ÚexpandÚreshape)rm   rn   ÚbatchÚnum_key_value_headsÚslenÚhead_dims         r0   Ú	repeat_kvrw   s   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Tr1   ç        ÚmoduleÚqueryÚkeyÚvalueÚattention_maskÚdropoutÚscalingÚsoftcapc                 ól  — |€
| j         dz  }t          || j        ¦  «        }	t          || j        ¦  «        }
t          j        ||	                     dd¦  «        ¦  «        |z  }|�||z  }t          j        |¦  «        }||z  }|�||z   }t          j         	                    |dt          j
        ¬¦  «                             |j        ¦  «        }t          j                             ||| j        ¬¦  «        }t          j        ||
¦  «        }|                     dd¦  «                             ¦   «         }||fS )Nç      à¿r3   r   r4   )r#   Údtype)ÚpÚtrainingr   )rv   rw   Únum_key_value_groupsr+   ÚmatmulÚ	transposeÚtanhr)   Ú
functionalÚsoftmaxÚfloat32Útorƒ   r~   r…   Ú
contiguous)ry   rz   r{   r|   r}   r~   r   r€   ÚkwargsÚ
key_statesÚvalue_statesÚattn_weightsÚattn_outputs                r0   Úeager_attention_forwardr”      s%  € ð €Ø”/ 4Ñ'ˆå˜3 Ô ;Ñ<Ô<€JÝ˜U FÔ$?Ñ@Ô@€Lå”<  z×';Ò';¸A¸qÑ'AÔ'AÑBÔBÀWÑL€LàÐØ# gÑ-ˆÝ”z ,Ñ/Ô/ˆØ# gÑ-ˆØÐ!Ø# nÑ4ˆõ ”=×(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:€KØ˜Ð$Ð$r1   c                   óò   ‡ — 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        dz  e	ej                 dz  f         fd„Zˆ xZS )ÚVaultGemmaAttentionz=Multi-headed attention from 'Attention Is All You Need' paperrQ   Ú	layer_idxc                 óT  •— t          ¦   «                              ¦   «          t          |d¦  «        r|j        |         nd | _        || _        || _        t          |d|j        |j	        z  ¦  «        | _
        |j	        |j        z  | _        |j        dz  | _        | j        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        ¬¦  «        | _        | j        j        | _        | j        dk    r|j        nd | _        d S )NÚlayer_typesrv   r‚   TrO   Úsliding_attention)r'   r(   Úhasattrr™   Ú
layer_typerQ   r—   ÚgetattrrR   Únum_attention_headsrv   rt   r†   Úquery_pre_attn_scalarr   Úattention_dropoutÚ	is_causalr)   rT   Úattention_biasÚq_projÚk_projÚv_projÚo_projÚattn_logit_softcappingÚsliding_window©r.   rQ   r—   r/   s      €r0   r(   zVaultGemmaAttention.__init__¥   s˜  ø€ Ý‰Œ×ÒÑÔÐÝ;BÀ6È=Ñ;YÔ;YÐc˜&Ô,¨YÔ7Ð7Ð_cˆŒØˆŒØ"ˆŒÝ ¨
°FÔ4FÈ&ÔJdÑ4dÑeÔeˆŒØ$*Ô$>À&ÔB\Ñ$\ˆÔ!ØÔ3°TÑ9ˆŒØ!%¤Ô!>ˆÔØˆŒå”iØÔ Ô :¸T¼]Ñ JÐQWÔQfð
ñ 
ô 
ˆŒõ ”iØÔ Ô :¸T¼]Ñ JÐQWÔQfð
ñ 
ô 
ˆŒõ ”iØÔ Ô :¸T¼]Ñ JÐQWÔQfð
ñ 
ô 
ˆŒõ ”iØÔ&¨¬Ñ6¸Ô8JÐQWÔQfð
ñ 
ô 
ˆŒð '+¤kÔ&HˆÔ#Ø7;´ÐJ]Ò7]Ð7]˜fÔ3Ð3ÐcgˆÔÐÐr1   Nrm   Úposition_embeddingsr}   Úpast_key_valuesr�   ro   c                 ó:  — |j         d d…         }g |¢d‘| j        ‘R }|                      |¦  «                             |¦  «                             dd¦  «        }|                      |¦  «                             |¦  «                             dd¦  «        }	|                      |¦  «                             |¦  «                             dd¦  «        }
|\  }}t          ||	||¦  «        \  }}	|�|                     |	|
| j	        ¦  «        \  }	}
t          j        | j        j        t          ¦  «        } || ||	|
|f| j        r| j        nd| j        | j        | j        dœ|¤Ž\  }} |j        g |¢d‘R Ž                      ¦   «         }|                      |¦  «        }||fS )Nr4   r   r3   rx   )r~   r   r¨   r€   )rC   rv   r£   Úviewrˆ   r¤   r¥   rl   Úupdater—   r   Úget_interfacerQ   Ú_attn_implementationr”   r…   r    r   r¨   r§   rr   rŽ   r¦   )r.   rm   rª   r}   r«   r�   Úinput_shapeÚhidden_shapeÚquery_statesr�   r‘   rg   rh   Úattention_interfacer“   r’   s                   r0   r@   zVaultGemmaAttention.forward¿   sÍ  € ð $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$7ØØØØØð%
ð /3¬mÐD�DÔ*Ð*ÀØ”LØÔ.ØÔ/ð%
ð %
ð ð%
ð %
Ñ!ˆ�\ð *�kÔ)Ð;¨;Ð;¸Ð;Ð;Ð;×FÒFÑHÔHˆØ—k’k +Ñ.Ô.ˆØ˜LÐ(Ð(r1   ©NNN)rE   rF   rG   Ú__doc__r   rH   r(   r+   ÚTensorrB   r   r   r   r@   rI   rJ   s   @r0   r–   r–   ¡   s  ø€ € € € € àGÐGðhÐ/ð h¸Cð hð hð hð hð hð hð: IMØ.2Ø(,ð()ð ()à”|ð()ð # 5¤<°´Ð#=Ô>ÀÑEð()ð œ tÑ+ð	()ð
  ™ð()ð Ð-Ô.ð()ð 
ˆuŒ|˜Uœ\¨DÑ0°%¸¼Ô2EÈÑ2LÐLÔ	Mð()ð ()ð ()ð ()ð ()ð ()ð ()ð ()r1   r–   c                   óè   ‡ — e Zd Zdedefˆ fd„Z	 	 	 ddej        deej        ej        f         dej        dz  dej	        dz  d	e
dz  d
eej        eej        ej        f         dz  f         fd„Zˆ xZS )ÚVaultGemmaDecoderLayerrQ   r—   c                 óB  •— t          ¦   «                              ¦   «          |j        | _        || _        t	          ||¬¦  «        | _        t          |¦  «        | _        t          |j        |j	        ¬¦  «        | _
        t          |j        |j	        ¬¦  «        | _        d S )N)rQ   r—   ©r$   )r'   r(   rR   rQ   r–   Ú	self_attnrL   Úmlpr!   Úrms_norm_epsÚinput_layernormÚpre_feedforward_layernormr©   s      €r0   r(   zVaultGemmaDecoderLayer.__init__ë   s‹   ø€ Ý‰Œ×ÒÑÔÐØ!Ô-ˆÔØˆŒÝ,°FÀiÐPÑPÔPˆŒÝ  Ñ(Ô(ˆŒÝ0°Ô1CÈÔI\Ð]Ñ]Ô]ˆÔå):¸6Ô;MÐSYÔSfÐ)gÑ)gÔ)gˆÔ&Ð&Ð&r1   Nrm   rª   r}   Úposition_idsr«   ro   c           	      óÌ   — |}|                       |¦  «        } | j        d|||||dœ|¤Ž\  }}||z   }|}|                      |¦  «        }|                      |¦  «        }||z   }|S )N)rm   rª   r}   rÁ   r«   © )r¿   r¼   rÀ   r½   )	r.   rm   rª   r}   rÁ   r«   r�   ÚresidualÚ_s	            r0   r@   zVaultGemmaDecoderLayer.forwardõ   sœ   € ð !ˆØ×,Ò,¨]Ñ;Ô;ˆà)˜4œ>ð 
Ø'Ø 3Ø)Ø%Ø+ð
ð 
ð ð
ð 
Ñˆ�qð ! =Ñ0ˆà ˆØ×6Ò6°}ÑEÔEˆØŸš Ñ/Ô/ˆØ  =Ñ0ˆàÐr1   rµ   )rE   rF   rG   r   rH   r(   r+   r·   rB   Ú
LongTensorr   ÚFloatTensorr@   rI   rJ   s   @r0   r¹   r¹   ê   sø   ø€ € € € € ðhÐ/ð h¸Cð hð hð hð hð hð hð /3Ø04Ø(,ðð à”|ðð # 5¤<°´Ð#=Ô>ðð œ tÑ+ð	ð
 Ô&¨Ñ-ðð  ™ðð 
ˆuÔ  %¨Ô(9¸5Ô;LÐ(LÔ"MÐPTÑ"TÐTÔ	Uðð ð ð ð ð ð ð r1   r¹   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VaultGemmaRotaryEmbeddingÚinv_freqNrQ   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defaultrÊ   F©Ú
persistentÚoriginal_inv_freq)r'   r(   Úmax_position_embeddingsÚmax_seq_len_cachedÚoriginal_max_seq_lenrQ   Úrope_parametersrÌ   Úcompute_default_rope_parametersr   Úattention_scalingÚregister_bufferÚclone)r.   rQ   ÚdeviceÚrope_init_fnrÊ   r/   s        €r0   r(   z"VaultGemmaRotaryEmbedding.__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�$Ô(à×Ò˜Z¨¸eÐÑDÔDÐDØ×ÒÐ0°(·.².Ñ2BÔ2BÈuÐÑUÔUÐUÐUÐUr1   rÙ   ztorch.deviceÚseq_lenro   ztorch.Tensorc                 óü   — | j         d         }t          | dd¦  «        p| j        | j        z  }d}d|t	          j        d|dt          j        ¬¦  «                             |t          j        ¬¦  «        |z  z  z  }||fS )	a¨  
        Computes the inverse frequencies according to the original RoPE implementation
        Args:
            config ([`~transformers.PreTrainedConfig`]):
                The model configuration.
            device (`torch.device`):
                The device to use for initialization of the inverse frequencies.
            seq_len (`int`, *optional*):
                The current sequence length. Unused for this type of RoPE.
        Returns:
            Tuple of (`torch.Tensor`, `float`), containing the inverse frequencies for the RoPE embeddings and the
            post-processing scaling factor applied to the computed cos/sin (unused in this type of RoPE).
        Ú
rope_thetarv   Nr<   r   r3   ©rƒ   )rÙ   rƒ   )	rÔ   r�   rR   rž   r+   ÚarangeÚint64r�   r=   )rQ   rÙ   rÛ   Úbaser#   Úattention_factorrÊ   s          r0   rÕ   z9VaultGemmaRotaryEmbedding.compute_default_rope_parameters&  sŒ   € ð& Ô% lÔ3ˆÝ�f˜j¨$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)r1   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   r4   r   ÚmpsÚcpuF)Údevice_typeÚenabledr3   r]   rÞ   )rÊ   r=   rq   rC   r�   rÙ   Ú
isinstanceÚtypeÚstrr   rˆ   r+   r^   rg   rÖ   rh   rƒ   )
r.   r9   rÁ   Úinv_freq_expandedÚposition_ids_expandedræ   ÚfreqsÚembrg   rh   s
             r0   r@   z!VaultGemmaRotaryEmbedding.forwardD  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&   rµ   )rE   rF   rG   r+   r·   Ú__annotations__r   r(   Ústaticmethodr   rH   rB   r=   rÕ   Úno_gradr   r@   rI   rJ   s   @r0   rÉ   rÉ     sú   ø€ € € € € € ØŒlÐÐÑðVð VÐ/ð Vð Vð Vð Vð Vð Vð  à*.Ø+/Ø"ð*ð *Ø  4Ñ'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 <r1   rÉ   c            	       óP   ‡ — e Zd ZdZd
dedededefˆ fd„Zdej        fˆ fd	„Z	ˆ xZ
S )Ú!VaultGemmaTextScaledWordEmbeddingz\
    This module overrides nn.Embeddings' forward by multiplying with embeddings scale.
    r<   Únum_embeddingsÚembedding_dimÚpadding_idxÚembed_scalec                 ó°   •— t          ¦   «                              |||¦  «         || _        |                      dt	          j        |¦  «        d¬¦  «         d S )Nr÷   FrÎ   )r'   r(   Úscalar_embed_scaler×   r+   Útensor)r.   rô   rõ   rö   r÷   r/   s        €r0   r(   z*VaultGemmaTextScaledWordEmbedding.__init__Y  sS   ø€ Ý‰Œ×Ò˜¨¸ÑDÔDÐDØ"-ˆÔØ×Ò˜]­E¬L¸Ñ,EÔ,EÐRWÐÑXÔXÐXÐXÐXr1   Ú	input_idsc                 ó�   •— t          ¦   «                              |¦  «        | j                             | j        j        ¦  «        z  S r&   )r'   r@   r÷   r�   r-   rƒ   )r.   rû   r/   s     €r0   r@   z)VaultGemmaTextScaledWordEmbedding.forward^  s4   ø€ Ý‰wŒw�Š˜yÑ)Ô)¨DÔ,<×,?Ò,?ÀÄÔ@QÑ,RÔ,RÑRÐRr1   )r<   )rE   rF   rG   r¶   rH   r=   r(   r+   r·   r@   rI   rJ   s   @r0   ró   ró   T  s¦   ø€ € € € € ðð ðYð Y sð Y¸3ð YÈSð YÐ_dð Yð Yð Yð Yð Yð Yð
S ¤ð Sð Sð Sð Sð Sð Sð Sð Sð Sð Sr1   ró   c                   ó†   ‡ — 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 ej        ¦   «         ˆ fd„¦   «         Zˆ xZS )ÚVaultGemmaPreTrainedModelrQ   ÚmodelTr¹   r«   )rm   Ú
attentionsc                 ó  •— t          ¦   «                              |¦  «         d|j        j        v rt	          j        |j        ¦  «         d S t          |t          ¦  «        r!t	          j	        |j
        |j        ¦  «         d S d S )NÚRMSNorm)r'   Ú_init_weightsr/   rE   ÚinitÚzeros_r-   rè   ró   Ú	constant_r÷   rù   )r.   ry   r/   s     €r0   r  z'VaultGemmaPreTrainedModel._init_weightst  s‚   ø€ å‰Œ×Ò˜fÑ%Ô%Ð%à˜Ô(Ô1Ð1Ð1ÝŒK˜œÑ&Ô&Ð&Ð&Ð&Ý˜Õ AÑBÔBð 	JÝŒN˜6Ô-¨vÔ/HÑIÔIÐIÐIÐIð	Jð 	Jr1   )rE   rF   rG   r   rï   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_backendr¹   r–   Ú_can_record_outputsr+   rñ   r  rI   rJ   s   @r0   rþ   rþ   b  s±   ø€ € € € € € àÐÐÑØÐØ&*Ð#Ø1Ð2ÐØ#4Ð"5ÐØÐØ€NØÐà!ÐØ"&Ðà/Ø)ðð Ðð
 €U„]�_„_ðJð Jð Jð Jñ „_ðJð Jð Jð Jð Jr1   rþ   c                   óâ   ‡ — e 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VaultGemmaModelrQ   c                 óð  •‡— t          ¦   «                              ‰¦  «         ‰j        | _        ‰j        | _        t          ‰j        ‰j        | j        | j        j        dz  ¬¦  «        | _        t          j
        ˆfd„t          ‰j        ¦  «        D ¦   «         ¦  «        | _        t          ‰j        ‰j        ¬¦  «        | _        t#          ‰¦  «        | _        d| _        |                      ¦   «          d S )Ng      à?)r÷   c                 ó0   •— g | ]}t          ‰|¦  «        ‘ŒS rÃ   )r¹   )Ú.0r—   rQ   s     €r0   ú
<listcomp>z,VaultGemmaModel.__init__.<locals>.<listcomp>‰  s$   ø€ ÐhÐhÐh¸9Õ# F¨IÑ6Ô6ÐhÐhÐhr1   r»   F)r'   r(   Úpad_token_idrö   Ú
vocab_sizeró   rR   rQ   Úembed_tokensr)   Ú
ModuleListÚrangeÚnum_hidden_layersÚlayersr!   r¾   ÚnormrÉ   Ú
rotary_embÚgradient_checkpointingÚ	post_initrZ   s    `€r0   r(   zVaultGemmaModel.__init__€  sé   øø€ Ý‰Œ×Ò˜Ñ Ô Ð Ø!Ô.ˆÔØ Ô+ˆŒå=ØÔ˜vÔ1°4Ô3CÐQUÔQ\ÔQhÐjmÑQmð
ñ 
ô 
ˆÔõ ”mØhÐhÐhÐhÍÈfÔNfÑHgÔHgÐhÑhÔhñ
ô 
ˆŒõ & fÔ&8¸fÔ>QÐRÑRÔRˆŒ	Ý3°FÑ;Ô;ˆŒØ&+ˆÔ#ð 	�ŠÑÔÐÐÐr1   Nrû   r}   rÁ   r«   Úinputs_embedsÚ	use_cacher�   ro   c           	      óØ  — |d u |d uz  rt          d¦  «        ‚|€|                      |¦  «        }|r|€t          | j        ¬¦  «        }|€V|�|                     ¦   «         nd}t          j        |j        d         |j        ¬¦  «        |z   }| 	                    d¦  «        }t          |x}	t          ¦  «        s&| j        ||||dœ}
t          d
i |
¤Žt          d
i |
¤Ždœ}	|}|                      ||¦  «        }t          | j        d | j        j        …         ¦  «        D ])\  }} ||f|	| j        j        |                  |||dœ|¤Ž}Œ*|                      |¦  «        }t)          ||¬	¦  «        S )Nz:You must specify exactly one of input_ids or inputs_embeds)rQ   r   r   )rÙ   )rQ   r"  r}   r«   rÁ   )Úfull_attentionrš   )r}   rª   rÁ   r«   )Úlast_hidden_stater«   rÃ   )Ú
ValueErrorr  r	   rQ   Úget_seq_lengthr+   rß   rC   rÙ   rd   rè   Údictr   r   r  Ú	enumerater  r  r™   r  r   )r.   rû   r}   rÁ   r«   r"  r#  r�   Úpast_seen_tokensÚcausal_mask_mappingÚmask_kwargsrm   rª   ÚiÚdecoder_layers                  r0   r@   zVaultGemmaModel.forward’  sæ  € ð ˜Ð -°tÐ";Ñ<ð 	[ÝÐYÑZÔZÐZàÐ Ø*.×*;Ò*;¸IÑ*FÔ*FˆMàð 	?˜Ð0Ý*°$´+Ð>Ñ>Ô>ˆOàÐØCRÐC^˜×=Ò=Ñ?Ô?Ð?ÐdeÐÝ œ<¨Ô(;¸AÔ(>À}ÔG[Ð\Ñ\Ô\Ð_oÑoˆLØ'×1Ò1°!Ñ4Ô4ˆLõ °Ð?Ð-ÅÑFÔFð 	ð œ+Ø!.Ø"0Ø#2Ø ,ðð ˆKõ #5Ð"CÐ"C°{Ð"CÐ"CÝ%FÐ%UÐ%UÈÐ%UÐ%Uð#ð #Ðð &ˆØ"Ÿošo¨m¸\ÑJÔJÐå )¨$¬+Ð6U¸¼Ô8UÐ6UÔ*VÑ WÔ Wð 	ð 	ÑˆAˆ}Ø)˜MØðà2°4´;Ô3JÈ1Ô3MÔNØ$7Ø)Ø /ðð ð ðð ˆMˆMð Ÿ	š	 -Ñ0Ô0ˆå&Ø+Ø+ð
ñ 
ô 
ð 	
r1   )NNNNNN)rE   rF   rG   r   r(   r   r   r   r+   rÆ   r·   r   rÇ   Úboolr   r   r   r@   rI   rJ   s   @r0   r  r  ~  s  ø€ € € € € ðÐ/ð ð ð ð ð ð ð$  ØØð .2Ø.2Ø04Ø(,Ø26Ø!%ð;
ð ;
àÔ# dÑ*ð;
ð œ tÑ+ð;
ð Ô&¨Ñ-ð	;
ð
  ™ð;
ð Ô(¨4Ñ/ð;
ð ˜$‘;ð;
ð Ð+Ô,ð;
ð 
!ð;
ð ;
ð ;
ñ „^ñ „_ñ  Ôð;
ð ;
ð ;
ð ;
ð ;
r1   r  c                   ó  ‡ — e Zd ZddiZddiZddgdgfiZˆ fd„Zee	 	 	 	 	 	 	 	 dd
e	j
        dz  de	j        dz  de	j
        dz  dedz  de	j        dz  de	j
        dz  dedz  dee	j        z  dee         defd„¦   «         ¦   «         Zˆ xZS )ÚVaultGemmaForCausalLMzlm_head.weightzmodel.embed_tokens.weightÚlm_headÚcolwise_gather_outputrm   Úlogitsc                 óþ   •— t          ¦   «                              |¦  «         t          |¦  «        | _        |j        | _        t          j        |j        |j        d¬¦  «        | _        |  	                    ¦   «          d S rN   )
r'   r(   r  rÿ   r  r)   rT   rR   r3  r!  rZ   s     €r0   r(   zVaultGemmaForCausalLM.__init__Ù  sj   ø€ Ý‰Œ×Ò˜Ñ Ô Ð Ý$ VÑ,Ô,ˆŒ
Ø Ô+ˆŒÝ”y Ô!3°VÔ5FÈUÐSÑSÔSˆŒð 	�ŠÑÔÐÐÐr1   Nr   rû   r}   rÁ   r«   r"  Úlabelsr#  Úlogits_to_keepr�   ro   c	           
      óÀ  —  | j         d||||||dœ|	¤Ž}
|
j        }t          |t          ¦  «        rt	          | d¦  «        n|}|                      |dd…|dd…f         ¦  «        }| j        j        �2|| j        j        z  }t          j	        |¦  «        }|| j        j        z  }d}|� | j
        ||| j        fi |	¤Ž}t          |||
j        |
j        |
j        ¬¦  «        S )aŠ  
        Example:

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

        >>> model = VaultGemmaForCausalLM.from_pretrained("google/gemma-2-9b")
        >>> tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-9b")

        >>> prompt = "What is your favorite condiment?"
        >>> 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]
        "What is your favorite condiment?"
        ```)rû   r}   rÁ   r«   r"  r#  N)Úlossr5  r«   rm   r   rÃ   )rÿ   r&  rè   rH   Úslicer3  rQ   Úfinal_logit_softcappingr+   r‰   Úloss_functionr  r   r«   rm   r   )r.   rû   r}   rÁ   r«   r"  r7  r#  r8  r�   Úoutputsrm   Úslice_indicesr5  r:  s                  r0   r@   zVaultGemmaForCausalLM.forwardâ  s&  € ð@ ,6¨4¬:ð ,
ØØ)Ø%Ø+Ø'Øð,
ð ,
ð ð,
ð ,
ˆð  Ô1ˆå8BÀ>ÕSVÑ8WÔ8WÐk�˜~˜o¨tÑ4Ô4Ð4Ð]kˆØ—’˜m¨A¨A¨A¨}¸a¸a¸aÐ,?Ô@ÑAÔAˆØŒ;Ô.Ð:Ø˜dœkÔAÑAˆFÝ”Z Ñ'Ô'ˆFØ˜dœkÔAÑAˆFàˆØÐØ%�4Ô% f¨f°d´oÐPÐPÈÐPÐPˆDå%ØØØ#Ô3Ø!Ô/ØÔ)ð
ñ 
ô 
ð 	
r1   )NNNNNNNr   )rE   rF   rG   Ú_tied_weights_keysÚ_tp_planÚ_pp_planr(   r   r   r+   rÆ   r·   r   rÇ   r0  rH   r   r   r   r@   rI   rJ   s   @r0   r2  r2  Ó  sK  ø€ € € € € à*Ð,GÐHÐØÐ2Ð3€HØ˜_Ð-°¨zÐ:Ð;€Hð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 ˜$‘;ð;
ð ˜eœlÑ*ð;
ð Ð+Ô,ð;
ð 
 ð;
ð ;
ð ;
ñ „^ñ Ôð;
ð ;
ð ;
ð ;
ð ;
r1   r2  )r2  r  rþ   )r   )rx   NN)EÚcollections.abcr   Útypingr   r+   Útorch.nnr)   Ú r   r  Úactivationsr   Úcache_utilsr   r	   Ú
generationr
   Úintegrationsr   r   Úmasking_utilsr   r   Úmodeling_flash_attention_utilsr   Úmodeling_layersr   Úmodeling_outputsr   r   Úmodeling_rope_utilsr   r   Úmodeling_utilsr   r   Úprocessing_utilsr   Úutilsr   r   r   Úutils.genericr   r   Úutils.output_capturingr   Úconfiguration_vaultgemmar   ÚModuler!   rL   ra   rl   r·   rH   rw   r=   rB   r”   r–   r¹   rÉ   Ú	Embeddingró   rþ   r  r2  Ú__all__rÃ   r1   r0   ú<module>rY     sµ  ðð, %Ð $Ð $Ð $Ð $Ð $Ø Ð Ð Ð Ð Ð à €€€Ø Ð Ð Ð Ð Ð à &Ð &Ð &Ð &Ð &Ð &Ø !Ð !Ð !Ð !Ð !Ð !Ø .Ð .Ð .Ð .Ð .Ð .Ð .Ð .Ø )Ð )Ð )Ð )Ð )Ð )Ø IÐ IÐ IÐ IÐ IÐ IÐ IÐ IØ RÐ RÐ RÐ RÐ RÐ RÐ RÐ RØ BÐ BÐ BÐ BÐ BÐ BØ 9Ð 9Ð 9Ð 9Ð 9Ð 9Ø OÐ OÐ OÐ OÐ OÐ OÐ OÐ OØ KÐ KÐ KÐ KÐ KÐ KÐ KÐ KØ FÐ FÐ FÐ FÐ FÐ FÐ FÐ FØ &Ð &Ð &Ð &Ð &Ð &Ø IÐ IÐ IÐ IÐ IÐ IÐ IÐ IÐ IÐ IØ GÐ GÐ GÐ GÐ GÐ GÐ GÐ GØ 5Ð 5Ð 5Ð 5Ð 5Ð 5Ø 6Ð 6Ð 6Ð 6Ð 6Ð 6ð=ð =ð =ð =ð =˜œ	ñ =ô =ð =ð(ð ð ð ð �B”Iñ ô ð 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$ Ø Ø ð%ð %ØŒIð%àŒ<ð%ð 
Œð%ð Œ<ð	%ð
 ”L 4Ñ'ð%ð �S‰[ð%ð �T‰\ð%ð �T‰\ð%ð ˆ5Œ<˜œÐ%Ô&ð%ð %ð %ð %ðD ÐÐ)Ñ*Ô*ðE)ð E)ð E)ð E)ð E)˜"œ)ñ E)ô E)ñ +Ô*ðE)ðP&ð &ð &ð &ð &Ð7ñ &ô &ð &ðR><ð ><ð ><ð ><ð >< ¤	ñ ><ô ><ð ><ðBSð Sð Sð Sð S¨¬ñ Sô Sð Sð ðJð Jð Jð Jð J ñ Jô Jñ „ðJð6 ðQ
ð Q
ð Q
ð Q
ð Q
Ð/ñ Q
ô Q
ñ „ðQ
ðh ðK
ð K
ð K
ð K
ð K
Ð5°ñ K
ô K
ñ „ðK
ð\ TÐ
SÐ
S€€€r1   