Ë
    ÜÓ^jÒ\  ã                   ó¾  — 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$m%Z% ddl&m'Z'm(Z(m)Z) ddl*m+Z+m,Z, ddl-m.Z. ddl/m0Z0  G d„ dejb                  «      Z2 G d„ dejb                  «      Z3d„ Z4 ed«      d9d„«       Z5dejl                  de7dejl                  fd „Z8	 	 	 d:d!ejb                  d"ejl                  d#ejl                  d$ejl                  d%ejl                  dz  d&e9e7z  d'e9dz  d(e9dz  de:ejl                  ejl                  f   fd)„Z; ee5«       G d*„ d+ejb                  «      «       Z< G d,„ d-e«      Z= G d.„ d/ejb                  «      Z> G d0„ d1ej~                  «      Z@e( G d2„ d3e#«      «       ZAe( G d4„ d5eA«      «       ZBe( G d6„ d7eAe«      «       ZCg d8¢ZDy);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VaultGemmaRMSNormÚdimÚepsc                 óŠ   •— t         ‰| �  «        || _        t        j                  t        j                  |«      «      | _        y ©N)ÚsuperÚ__init__r#   ÚnnÚ	ParameterÚtorchÚzerosÚweight)Úselfr"   r#   Ú	__class__s      €ú}/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/vaultgemma/modeling_vaultgemma.pyr'   zVaultGemmaRMSNorm.__init__/   s.   ø€ Ü‰ÑÔØˆŒÜ—l‘l¤5§;¡;¨sÓ#3Ó4ˆ�ó    c                 óŒ   — |t        j                  |j                  d«      j                  dd¬«      | j                  z   «      z  S )Né   éÿÿÿÿT)Úkeepdim)r*   ÚrsqrtÚpowÚmeanr#   )r-   Úxs     r/   Ú_normzVaultGemmaRMSNorm._norm4   s4   € Ø”5—;‘;˜qŸu™u Q›xŸ}™}¨R¸˜}Ó>ÀÇÁÑIÓJÑJÐJr0   c                 ó¢   — | j                  |j                  «       «      }|d| j                  j                  «       z   z  }|j                  |«      S )Nç      ð?)r9   Úfloatr,   Útype_as)r-   r8   Úoutputs      r/   ÚforwardzVaultGemmaRMSNorm.forward7   sC   € Ø—‘˜AŸG™G›IÓ&ˆð ˜3 §¡×!2Ñ!2Ó!4Ñ4Ñ5ˆØ�~‰~˜aÓ Ð r0   c                 ó^   — t        | j                  j                  «      › d| j                  › �S )Nz, eps=)Útupler,   Úshaper#   )r-   s    r/   Ú
extra_reprzVaultGemmaRMSNorm.extra_repr>   s'   € Ü˜Ÿ™×)Ñ)Ó*Ð+¨6°$·(±(°Ð<Ð<r0   )g�íµ ÷Æ°>)
Ú__name__Ú
__module__Ú__qualname__Úintr<   r'   r9   r?   rC   Ú__classcell__©r.   s   @r/   r!   r!   .   s&   ø„ ñ5˜Cð 5 eõ 5ò
Kò!ö=r0   r!   c                   ó$   ‡ — e Zd Zˆ fd„Zd„ Zˆ xZS )ÚVaultGemmaMLPc                 óÊ  •— t         ‰| �  «        || _        |j                  | _        |j                  | _        t        j                  | j                  | j                  d¬«      | _        t        j                  | j                  | j                  d¬«      | _        t        j                  | j                  | j                  d¬«      | _	        t        |j                     | _        y ©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-   rP   r.   s     €r/   r'   zVaultGemmaMLP.__init__C   s¦   ø€ Ü‰ÑÔØˆŒØ!×-Ñ-ˆÔØ!'×!9Ñ!9ˆÔÜŸ™ 4×#3Ñ#3°T×5KÑ5KÐRWÔXˆŒÜ—y‘y ×!1Ñ!1°4×3IÑ3IÐPUÔVˆŒÜŸ™ 4×#9Ñ#9¸4×;KÑ;KÐRWÔXˆŒÜ˜V×5Ñ5Ñ6ˆ�r0   c                 óˆ   — | j                  | j                  | j                  |«      «      | j                  |«      z  «      }|S r%   )rV   rX   rT   rU   )r-   r8   rV   s      r/   r?   zVaultGemmaMLP.forwardM   s6   € Ø—N‘N 4§;¡;¨t¯~©~¸aÓ/@Ó#AÀDÇLÁLÐQRÃOÑ#SÓTˆ	ØÐr0   )rD   rE   rF   r'   r?   rH   rI   s   @r/   rK   rK   B   s   ø„ ô7ör0   rK   c                 óš   — | 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..Nr3   r2   ©r"   )rB   r*   Úcat)r8   Úx1Úx2s      r/   Úrotate_halfr`   R   sZ   € à	
ˆ3Ð"�!—'‘'˜"‘+ Ñ"Ð"Ð"Ñ	#€BØ	
ˆ3�—‘˜‘˜qÑ Ñ"Ð"Ñ	#€BÜ�9‰9�r�c˜2�Y BÔ'Ð'r0   Úrotary_pos_embc                 óž   — |j                  |«      }|j                  |«      }| |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	unsqueezer`   )ÚqÚkÚcosÚsinÚunsqueeze_dimÚq_embedÚk_embeds          r/   Úapply_rotary_pos_embrk   Y   sY   € ð& �-‰-˜Ó
&€CØ
�-‰-˜Ó
&€CØ�3‰wœ; q›>¨CÑ/Ñ0€GØ�3‰wœ; q›>¨CÑ/Ñ0€GØ�GÐÐr0   Úhidden_statesÚn_repÚreturnc                 óª   — | j                   \  }}}}|dk(  r| S | dd…dd…ddd…dd…f   j                  |||||«      } | j                  |||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)rB   ÚexpandÚreshape)rl   rm   ÚbatchÚnum_key_value_headsÚslenÚhead_dims         r/   Ú	repeat_kvrv   s   so   € ð
 2?×1DÑ1DÑ.€EÐ  hØ�‚zØÐØ!¢!¢Q¨ªa²Ð"2Ñ3×:Ñ:¸5ÐBUÐW\Ð^bÐdlÓm€MØ× Ñ  Ð(;¸eÑ(CÀTÈ8ÓTÐTr0   ÚmoduleÚqueryÚkeyÚvalueÚattention_maskÚdropoutÚscalingÚsoftcapc                 ó|  — |€| j                   dz  }t        || j                  «      }	t        || j                  «      }
t        j                  ||	j                  dd«      «      |z  }|�||z  }t        j                  |«      }||z  }|�||z   }t        j                  j                  |dt        j                  ¬«      j                  |j                  «      }t        j                  j                  ||| j                  ¬«      }t        j                  ||
«      }|j                  dd«      j                  «       }||fS )Nç      à¿r2   r   r3   )r"   Údtype)ÚpÚtrainingr   )ru   rv   Únum_key_value_groupsr*   ÚmatmulÚ	transposeÚtanhr(   Ú
functionalÚsoftmaxÚfloat32Útor�   r|   rƒ   Ú
contiguous)rw   rx   ry   rz   r{   r|   r}   r~   ÚkwargsÚ
key_statesÚvalue_statesÚattn_weightsÚattn_outputs                r/   Úeager_attention_forwardr’      s  € ð €Ø—/‘/ 4Ñ'ˆä˜3 × ;Ñ ;Ó<€JÜ˜U F×$?Ñ$?Ó@€Lä—<‘<  z×';Ñ';¸A¸qÓ'AÓBÀWÑL€LàÐØ# gÑ-ˆÜ—z‘z ,Ó/ˆØ# gÑ-ˆØÐ!Ø# nÑ4ˆô —=‘=×(Ñ(¨¸2ÄUÇ]Á]Ð(ÓS×VÑVÐW\×WbÑWbÓc€LÜ—=‘=×(Ñ(¨¸È6Ï?É?Ð(Ó[€LÜ—,‘,˜|¨\Ó:€KØ×'Ñ'¨¨1Ó-×8Ñ8Ó:€KØ˜Ð$Ð$r0   c                   ó   ‡ — 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' paperrP   Ú	layer_idxc                 óB  •— 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
                  j0                  | _        | j                  dk(  r|j2                  | _        y d | _        y )NÚlayer_typesru   r€   TrN   Úsliding_attention)r&   r'   Úhasattrr—   Ú
layer_typerP   r•   ÚgetattrrQ   Únum_attention_headsru   rs   r„   Úquery_pre_attn_scalarr}   Úattention_dropoutÚ	is_causalr(   rS   Úattention_biasÚq_projÚk_projÚv_projÚo_projÚattn_logit_softcappingÚsliding_window©r-   rP   r•   r.   s      €r/   r'   zVaultGemmaAttention.__init__¥   s§  ø€ Ü‰ÑÔÜ;BÀ6È=Ô;Y˜&×,Ñ,¨YÒ7Ð_cˆŒØˆŒØ"ˆŒÜ ¨
°F×4FÑ4FÈ&×JdÑJdÑ4dÓeˆŒØ$*×$>Ñ$>À&×B\ÑB\Ñ$\ˆÔ!Ø×3Ñ3°TÑ9ˆŒØ!%§¡×!>Ñ!>ˆÔØˆŒä—i‘iØ×Ñ × :Ñ :¸T¿]¹]Ñ JÐQW×QfÑQfô
ˆŒô —i‘iØ×Ñ × :Ñ :¸T¿]¹]Ñ JÐQW×QfÑQfô
ˆŒô —i‘iØ×Ñ × :Ñ :¸T¿]¹]Ñ JÐQW×QfÑQfô
ˆŒô —i‘iØ×&Ñ&¨¯©Ñ6¸×8JÑ8JÐQW×QfÑQfô
ˆŒð '+§k¡k×&HÑ&HˆÔ#Ø7;·±ÐJ]Ò7]˜f×3Ñ3ˆÕÐcgˆÕr0   Nrl   Úposition_embeddingsr{   Úpast_key_valuesr�   rn   c                 ó6  — |j                   d d }g |¢d‘| j                  ‘­}| j                  |«      j                  |«      j	                  dd«      }| j                  |«      j                  |«      j	                  dd«      }	| j                  |«      j                  |«      j	                  dd«      }
|\  }}t        ||	||«      \  }}	|� |j                  |	|
| j                  «      \  }	}
t        j                  | j                  j                  t        «      } || ||	|
|f| j                  r| j                   nd| j"                  | j$                  | j&                  dœ|¤Ž\  }} |j(                  g |¢d‘­Ž j+                  «       }| j-                  |«      }||fS )Nr3   r   r2   ç        )r|   r}   r¦   r~   )rB   ru   r¡   Úviewr†   r¢   r£   rk   Úupdater•   r   Úget_interfacerP   Ú_attn_implementationr’   rƒ   rž   r}   r¦   r¥   rq   rŒ   r¤   )r-   rl   r¨   r{   r©   r�   Úinput_shapeÚhidden_shapeÚquery_statesrŽ   r�   rf   rg   Úattention_interfacer‘   r�   s                   r/   r?   zVaultGemmaAttention.forward¿   s£  € ð $×)Ñ)¨#¨2Ð.ˆØ8˜Ð8 bÐ8¨$¯-©-Ñ8ˆà—{‘{ =Ó1×6Ñ6°|ÓD×NÑNÈqÐRSÓTˆØ—[‘[ Ó/×4Ñ4°\ÓB×LÑLÈQÐPQÓRˆ
Ø—{‘{ =Ó1×6Ñ6°|ÓD×NÑNÈqÐRSÓTˆà&‰ˆˆSÜ#7¸ÀjÐRUÐWZÓ#[Ñ ˆ�jàÐ&Ø'6×'=Ñ'=¸jÈ,ÐX\×XfÑXfÓ'gÑ$ˆJ˜ä(?×(MÑ(MØ�K‰K×,Ñ,Ô.Eó)
Ðñ %8ØØØØØð%
ð /3¯mªm�D×*Ò*ÀØ—L‘LØ×.Ñ.Ø×/Ñ/ñ%
ð ñ%
Ñ!ˆ�\ð *�k×)Ñ)Ð;¨;Ð;¸Ò;×FÑFÓHˆØ—k‘k +Ó.ˆØ˜LÐ(Ð(r0   ©NNN)rD   rE   rF   Ú__doc__r   rG   r'   r*   ÚTensorrA   r   r   r   r?   rH   rI   s   @r/   r”   r”   ¡   s¾   ø„ áGðhÐ/ð h¸Cõ hð: IMØ.2Ø(,ñ()à—|‘|ð()ð # 5§<¡<°·±Ð#=Ñ>ÀÑEð()ð Ÿ™ tÑ+ð	()ð
  ™ð()ð Ð-Ñ.ð()ð 
ˆu�|‰|˜UŸ\™\¨DÑ0°%¸¿¹Ñ2EÈÑ2LÐLÑ	M÷()r0   r”   c                   ó&  ‡ — 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VaultGemmaDecoderLayerrP   r•   c                 ó.  •— t         ‰| �  «        |j                  | _        || _        t	        ||¬«      | _        t        |«      | _        t        |j                  |j                  ¬«      | _
        t        |j                  |j                  ¬«      | _        y )N)rP   r•   ©r#   )r&   r'   rQ   rP   r”   Ú	self_attnrK   Úmlpr!   Úrms_norm_epsÚinput_layernormÚpre_feedforward_layernormr§   s      €r/   r'   zVaultGemmaDecoderLayer.__init__ë   st   ø€ Ü‰ÑÔØ!×-Ñ-ˆÔØˆŒÜ,°FÀiÔPˆŒÜ  Ó(ˆŒÜ0°×1CÑ1CÈ×I\ÑI\Ô]ˆÔä):¸6×;MÑ;MÐSY×SfÑSfÔ)gˆÕ&r0   Nrl   r¨   r{   Úposition_idsr©   rn   c           	      ó¾   — |}| j                  |«      } | j                  d|||||dœ|¤Ž\  }}||z   }|}| j                  |«      }| j                  |«      }||z   }|S )N)rl   r¨   r{   rÀ   r©   © )r¾   r»   r¿   r¼   )	r-   rl   r¨   r{   rÀ   r©   r�   ÚresidualÚ_s	            r/   r?   zVaultGemmaDecoderLayer.forwardõ   s‹   € ð !ˆØ×,Ñ,¨]Ó;ˆà)˜4Ÿ>™>ð 
Ø'Ø 3Ø)Ø%Ø+ñ
ð ñ
Ñˆ�qð ! =Ñ0ˆà ˆØ×6Ñ6°}ÓEˆØŸ™ Ó/ˆØ  =Ñ0ˆàÐr0   r´   )rD   rE   rF   r   rG   r'   r*   r¶   rA   Ú
LongTensorr   ÚFloatTensorr?   rH   rI   s   @r/   r¸   r¸   ê   s¾   ø„ ðhÐ/ð h¸Cõ hð /3Ø04Ø(,ñà—|‘|ðð # 5§<¡<°·±Ð#=Ñ>ðð Ÿ™ tÑ+ð	ð
 ×&Ñ&¨Ñ-ðð  ™ðð 
ˆu× Ñ  %¨×(9Ñ(9¸5×;LÑ;LÐ(LÑ"MÐPTÑ"TÐTÑ	U÷r0   r¸   c                   óÄ   ‡ — 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_freqNrP   c                 ó®  •— t         ‰| �  «        |j                  | _        |j                  | _        || _        | j
                  j                  d   | _        | j                  }| j                  dk7  rt        | j                     } || j
                  |«      \  }| _
        | j                  d|d¬«       | j                  d|j                  «       d¬«       y )NÚ	rope_typeÚdefaultrÉ   F©Ú
persistentÚoriginal_inv_freq)r&   r'   Úmax_position_embeddingsÚmax_seq_len_cachedÚoriginal_max_seq_lenrP   Úrope_parametersrË   Úcompute_default_rope_parametersr   Úattention_scalingÚregister_bufferÚclone)r-   rP   ÚdeviceÚrope_init_fnrÉ   r.   s        €r/   r'   z"VaultGemmaRotaryEmbedding.__init__  s¶   ø€ Ü‰ÑÔØ"(×"@Ñ"@ˆÔØ$*×$BÑ$BˆÔ!àˆŒàŸ™×4Ñ4°[ÑAˆŒØ!%×!EÑ!EˆØ�>‰>˜YÒ&Ü.¨t¯~©~Ñ>ˆLÙ+7¸¿¹ÀVÓ+LÑ(ˆ�$Ô(à×Ñ˜Z¨¸eÐÔDØ×ÑÐ0°(·.±.Ó2BÈuÐÕUr0   rØ   ztorch.deviceÚseq_lenrn   ztorch.Tensorc                 ó  — | j                   d   }t        | dd«      xs | j                  | j                  z  }d}d|t	        j
                  d|dt        j                  ¬«      j                  |t        j                  ¬«      |z  z  z  }||fS )	a¨  
        Computes the inverse frequencies according to the original RoPE implementation
        Args:
            config ([`~transformers.PreTrainedConfig`]):
                The model configuration.
            device (`torch.device`):
                The device to use for initialization of the inverse frequencies.
            seq_len (`int`, *optional*):
                The current sequence length. Unused for this type of RoPE.
        Returns:
            Tuple of (`torch.Tensor`, `float`), containing the inverse frequencies for the RoPE embeddings and the
            post-processing scaling factor applied to the computed cos/sin (unused in this type of RoPE).
        Ú
rope_thetaru   Nr;   r   r2   ©r�   )rØ   r�   )	rÓ   r›   rQ   rœ   r*   ÚarangeÚint64r‹   r<   )rP   rØ   rÚ   Úbaser"   Úattention_factorrÉ   s          r/   rÔ   z9VaultGemmaRotaryEmbedding.compute_default_rope_parameters&  s�   € ð& ×%Ñ% lÑ3ˆÜ�f˜j¨$Ó/Òc°6×3EÑ3EÈ×IcÑIcÑ3cˆàÐð Ø”U—\‘\ ! S¨!´5·;±;Ô?×BÑBÈ&ÔX]×XcÑXcÐBÓdÐgjÑjÑkñ
ˆð Ð)Ð)Ð)r0   c                 óN  — | j                   d d d …d f   j                  «       j                  |j                  d   dd«      j	                  |j
                  «      }|d d …d d d …f   j                  «       }t        |j
                  j                  t        «      r/|j
                  j                  dk7  r|j
                  j                  nd}t        |d¬«      5  |j                  «       |j                  «       z  j                  dd«      }t        j                  ||fd¬	«      }|j                  «       | j                  z  }|j                  «       | j                  z  }	d d d «       j	                  |j                   ¬
«      	j	                  |j                   ¬
«      fS # 1 sw Y   ŒAxY w)Nr   r3   r   ÚmpsÚcpuF)Údevice_typeÚenabledr2   r\   rÝ   )rÉ   r<   rp   rB   r‹   rØ   Ú
isinstanceÚtypeÚstrr   r†   r*   r]   rf   rÕ   rg   r�   )
r-   r8   rÀ   Úinv_freq_expandedÚposition_ids_expandedrå   ÚfreqsÚembrf   rg   s
             r/   r?   z!VaultGemmaRotaryEmbedding.forwardD  sR  € ð !ŸM™M¨$²°4¨-Ñ8×>Ñ>Ó@×GÑGÈ×HZÑHZÐ[\ÑH]Ð_aÐcdÓe×hÑhÐij×iqÑiqÓrÐØ ,ªQ°²a¨ZÑ 8× >Ñ >Ó @Ðä'1°!·(±(·-±-ÄÔ'EÈ!Ï(É(Ï-É-Ð[`ÒJ`�a—h‘h—m’mÐfkˆÜ¨¸UÔCñ 	5Ø&×,Ñ,Ó.Ð1F×1LÑ1LÓ1NÑN×YÑYÐZ[Ð]^Ó_ˆEÜ—)‘)˜U E˜N°Ô3ˆCØ—'‘'“)˜d×4Ñ4Ñ4ˆCØ—'‘'“)˜d×4Ñ4Ñ4ˆC÷		5ð �v‰v˜AŸG™GˆvÓ$ c§f¡f°1·7±7 fÓ&;Ð;Ð;÷	5ð 	5ús   ÃBFÆF$r%   r´   )rD   rE   rF   r*   r¶   Ú__annotations__r   r'   Ústaticmethodr   rG   rA   r<   rÔ   Úno_gradr   r?   rH   rI   s   @r/   rÈ   rÈ     s™   ø… Ø�l‰lÓñVÐ/õ Vð  à*.Ø+/Ø"ñ*Ø  4Ñ'ð*à˜Ñ(ð*ð �t‘ð*ð 
ˆ~˜uÐ$Ñ	%ò	*ó ð*ð: €U‡]�]ƒ_Øñ<ó ó ô<r0   rÈ   c            	       óZ   ‡ — 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.
    Únum_embeddingsÚembedding_dimÚpadding_idxÚembed_scalec                 ó„   •— t         ‰| �  |||«       || _        | j                  dt	        j
                  |«      d¬«       y )Nrö   FrÍ   )r&   r'   Úscalar_embed_scalerÖ   r*   Útensor)r-   ró   rô   rõ   rö   r.   s        €r/   r'   z*VaultGemmaTextScaledWordEmbedding.__init__Y  s;   ø€ Ü‰Ñ˜¨¸ÔDØ"-ˆÔØ×Ñ˜]¬E¯L©L¸Ó,EÐRWÐÕXr0   Ú	input_idsc                 ó‚   •— t         ‰| �  |«      | j                  j                  | j                  j
                  «      z  S r%   )r&   r?   rö   r‹   r,   r�   )r-   rú   r.   s     €r/   r?   z)VaultGemmaTextScaledWordEmbedding.forward^  s2   ø€ Ü‰w‰˜yÓ)¨D×,<Ñ,<×,?Ñ,?ÀÇÁ×@QÑ@QÓ,RÑRÐRr0   )r;   )rD   rE   rF   rµ   rG   r<   r'   r*   r¶   r?   rH   rI   s   @r/   rò   rò   T  sG   ø„ ññY sð Y¸3ð YÈSð YÐ_dõ Yð
S §¡÷ Sñ Sr0   rò   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VaultGemmaPreTrainedModelrP   ÚmodelTr¸   r©   )rl   Ú
attentionsc                 ó
  •— t         ‰| �  |«       d|j                  j                  v r t	        j
                  |j                  «       y t        |t        «      r+t	        j                  |j                  |j                  «       y y )NÚRMSNorm)r&   Ú_init_weightsr.   rD   ÚinitÚzeros_r,   rç   rò   Ú	constant_rö   rø   )r-   rw   r.   s     €r/   r  z'VaultGemmaPreTrainedModel._init_weightst  s_   ø€ ä‰Ñ˜fÔ%à˜×(Ñ(×1Ñ1Ñ1Ü�K‰K˜Ÿ™Õ&Ü˜Ô AÔBÜ�N‰N˜6×-Ñ-¨v×/HÑ/HÕIð Cr0   )rD   rE   rF   r   rî   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_outputsr*   rð   r  rH   rI   s   @r/   rý   rý   b  sp   ø… àÓØÐØ&*Ð#Ø1Ð2ÐØ#4Ð"5ÐØÐØ€NØÐà!ÐØ"&Ðà/Ø)ñÐð
 €U‡]�]ƒ_óJó ôJr0   rý   c                   óò   ‡ — 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VaultGemmaModelrP   c           	      ó(  •— t         ‰| �  |«       |j                  | _        |j                  | _        t        |j                  |j                  | j                  | j                  j                  dz  ¬«      | _        t        j                  t        |j                  «      D �cg c]  }t        ||«      ‘Œ c}«      | _        t        |j                  |j                   ¬«      | _        t%        |«      | _        d| _        | j+                  «        y c c}w )Ng      à?)rö   rº   F)r&   r'   Úpad_token_idrõ   Ú
vocab_sizerò   rQ   rP   Úembed_tokensr(   Ú
ModuleListÚrangeÚnum_hidden_layersr¸   Úlayersr!   r½   ÚnormrÈ   Ú
rotary_embÚgradient_checkpointingÚ	post_initr§   s      €r/   r'   zVaultGemmaModel.__init__€  sÛ   ø€ Ü‰Ñ˜Ô Ø!×.Ñ.ˆÔØ ×+Ñ+ˆŒä=Ø×Ñ˜v×1Ñ1°4×3CÑ3CÐQU×Q\ÑQ\×QhÑQhÐjmÑQmô
ˆÔô —m‘mÜHMÈf×NfÑNfÓHgÖh¸9Ô# F¨IÕ6Òhó
ˆŒô & f×&8Ñ&8¸f×>QÑ>QÔRˆŒ	Ü3°FÓ;ˆŒØ&+ˆÔ#ð 	�‰Õùò is   Â"DNrú   r{   rÀ   r©   Úinputs_embedsÚ	use_cacher�   rn   c           	      óÆ  — |d u |d uz  rt        d«      ‚|€| j                  |«      }|r|€t        | j                  ¬«      }|€V|�|j	                  «       nd}t        j                  |j                  d   |j                  ¬«      |z   }|j                  d«      }t        |x}	t        «      s)| j                  ||||dœ}
t        d
i |
¤Žt        d
i |
¤Ždœ}	|}| j                  ||«      }t        | j                   d | j                  j"                   «      D ]-  \  }} ||f|	| j                  j$                  |      |||dœ|¤Ž}Œ/ | j'                  |«      }t)        ||¬	«      S )Nz:You must specify exactly one of input_ids or inputs_embeds)rP   r   r   )rØ   )rP   r  r{   r©   rÀ   )Úfull_attentionr˜   )r{   r¨   rÀ   r©   )Úlast_hidden_stater©   rÂ   )Ú
ValueErrorr  r	   rP   Úget_seq_lengthr*   rÞ   rB   rØ   rc   rç   Údictr   r   r  Ú	enumerater  r  r—   r  r   )r-   rú   r{   rÀ   r©   r  r  r�   Úpast_seen_tokensÚcausal_mask_mappingÚmask_kwargsrl   r¨   ÚiÚdecoder_layers                  r/   r?   zVaultGemmaModel.forward’  s–  € ð ˜Ð -°tÐ";Ò<ÜÐYÓZÐZàÐ Ø*.×*;Ñ*;¸IÓ*FˆMá˜Ð0Ü*°$·+±+Ô>ˆOàÐØCRÐC^˜×=Ñ=Ô?ÐdeÐÜ Ÿ<™<¨×(;Ñ(;¸AÑ(>À}×G[ÑG[Ô\Ð_oÑoˆLØ'×1Ñ1°!Ó4ˆLô °Ð?Ð-ÄÔFð Ÿ+™+Ø!.Ø"0Ø#2Ø ,ñˆKô #5Ñ"C°{Ñ"CÜ%FÑ%UÈÑ%Uñ#Ðð &ˆØ"Ÿo™o¨m¸\ÓJÐä )¨$¯+©+Ð6U¸¿¹×8UÑ8UÐ*VÓ Wò 	ÑˆAˆ}Ù)Øðà2°4·;±;×3JÑ3JÈ1Ñ3MÑNØ$7Ø)Ø /ñð ñ‰Mð	ð Ÿ	™	 -Ó0ˆä&Ø+Ø+ô
ð 	
r0   )NNNNNN)rD   rE   rF   r   r'   r   r   r   r*   rÅ   r¶   r   rÆ   Úboolr   r   r   r?   rH   rI   s   @r/   r  r  ~  sÎ   ø„ ðÐ/õ ð$  ØØð .2Ø.2Ø04Ø(,Ø26Ø!%ñ;
à×#Ñ# dÑ*ð;
ð Ÿ™ tÑ+ð;
ð ×&Ñ&¨Ñ-ð	;
ð
  ™ð;
ð ×(Ñ(¨4Ñ/ð;
ð ˜$‘;ð;
ð Ð+Ñ,ð;
ð 
!ò;
ó ó ó  ô;
r0   r  c                   óB  ‡ — e Zd ZddiZddiZddgdgfiZˆ fd„Zee	 	 	 	 	 	 	 	 dd	e	j                  dz  d
e	j                  dz  de	j                  dz  dedz  de	j                  dz  de	j                  dz  dedz  dee	j                  z  dee   defd„«       «       Zˆ xZS )ÚVaultGemmaForCausalLMzlm_head.weightzmodel.embed_tokens.weightÚlm_headÚcolwise_gather_outputrl   Úlogitsc                 óè   •— t         ‰| �  |«       t        |«      | _        |j                  | _        t        j                  |j                  |j                  d¬«      | _        | j                  «        y rM   )
r&   r'   r  rþ   r  r(   rS   rQ   r/  r  rY   s     €r/   r'   zVaultGemmaForCausalLM.__init__Ù  sU   ø€ Ü‰Ñ˜Ô Ü$ VÓ,ˆŒ
Ø ×+Ñ+ˆŒÜ—y‘y ×!3Ñ!3°V×5FÑ5FÈUÔSˆŒð 	�‰Õr0   Nrú   r{   rÀ   r©   r  Úlabelsr  Úlogits_to_keepr�   rn   c	           
      ó  —  | j                   d||||||dœ|	¤Ž}
|
j                  }t        |t        «      rt	        | d«      n|}| j                  |dd…|dd…f   «      }| j                  j                  �G|| 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?"
        ```)rú   r{   rÀ   r©   r  r  N)Úlossr1  r©   rl   rÿ   rÂ   )rþ   r"  rç   rG   Úslicer/  rP   Úfinal_logit_softcappingr*   r‡   Úloss_functionr  r   r©   rl   rÿ   )r-   rú   r{   rÀ   r©   r  r3  r  r4  r�   Úoutputsrl   Úslice_indicesr1  r6  s                  r/   r?   zVaultGemmaForCausalLM.forwardâ  s  € ð@ ,6¨4¯:©:ð ,
ØØ)Ø%Ø+Ø'Øñ,
ð ñ,
ˆð  ×1Ñ1ˆä8BÀ>ÔSVÔ8Wœ˜~˜o¨tÔ4Ð]kˆØ—‘˜mªA¨}ºaÐ,?Ñ@ÓAˆØ�;‰;×.Ñ.Ð:Ø˜dŸk™k×AÑAÑAˆFÜ—Z‘Z Ó'ˆFØ˜dŸk™k×AÑAÑAˆFàˆØÐØ%�4×%Ñ% f¨f°d·o±oÑPÈÑPˆDä%ØØØ#×3Ñ3Ø!×/Ñ/Ø×)Ñ)ô
ð 	
r0   )NNNNNNNr   )rD   rE   rF   Ú_tied_weights_keysÚ_tp_planÚ_pp_planr'   r   r   r*   rÅ   r¶   r   rÆ   r,  rG   r   r   r   r?   rH   rI   s   @r/   r.  r.  Ó  s  ø„ à*Ð,GÐHÐØÐ2Ð3€HØ˜_Ð-°¨zÐ:Ð;€Hôð Øð .2Ø.2Ø04Ø(,Ø26Ø*.Ø!%Ø-.ñ;
à×#Ñ# dÑ*ð;
ð Ÿ™ tÑ+ð;
ð ×&Ñ&¨Ñ-ð	;
ð
  ™ð;
ð ×(Ñ(¨4Ñ/ð;
ð × Ñ  4Ñ'ð;
ð ˜$‘;ð;
ð ˜eŸl™lÑ*ð;
ð Ð+Ñ,ð;
ð 
 ò;
ó ó ô;
r0   r.  )r.  r  rý   )r   )r«   NN)EÚcollections.abcr   Útypingr   r*   Útorch.nnr(   Ú r   r  Úactivationsr   Úcache_utilsr   r	   Ú
generationr
   Úintegrationsr   r   Úmasking_utilsr   r   Úmodeling_flash_attention_utilsr   Úmodeling_layersr   Úmodeling_outputsr   r   Úmodeling_rope_utilsr   r   Úmodeling_utilsr   r   Úprocessing_utilsr   Úutilsr   r   r   Úutils.genericr   r   Úutils.output_capturingr   Úconfiguration_vaultgemmar   ÚModuler!   rK   r`   rk   r¶   rG   rv   r<   rA   r’   r”   r¸   rÈ   Ú	Embeddingrò   rý   r  r.  Ú__all__rÂ   r0   r/   ú<module>rU     s  ðõ, %Ý ã Ý å &Ý !ß .Ý )ß Iß RÝ BÝ 9ß Oß Kß FÝ &ß IÑ Iß GÝ 5Ý 6ô=˜Ÿ	™	ô =ô(�B—I‘Iô ò (ñ Ð*Ó+òó ,ðð2	U˜UŸ\™\ð 	U°#ð 	U¸%¿,¹,ó 	Uð$ Ø Ø ñ%Ø�I‰Ið%à�<‰<ð%ð 
�‰ð%ð �<‰<ð	%ð
 —L‘L 4Ñ'ð%ð �S‰[ð%ð �T‰\ð%ð �T‰\ð%ð ˆ5�<‰<˜Ÿ™Ð%Ñ&ó%ñD Ð)Ó*ôE)˜"Ÿ)™)ó E)ó +ðE)ôP&Ð7ô &ôR>< §	¡	ô ><ôBS¨¯©ô Sð ôJ ó Jó ðJð6 ôQ
Ð/ó Q
ó ðQ
ðh ôK
Ð5°ó K
ó ðK
ò\ T�r0   