§
    9²¸jè]  ã                   óÞ  — 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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$m%Z% ddl&m'Z'm(Z(m)Z) ddl*m+Z+ ddl,m-Z-m.Z. ddl/m0Z0 ddl1m2Z2  G d„ dej3        ¦  «        Z4 G d„ dej3        ¦  «        Z5 G d„ dej3        ¦  «        Z6d„ Z7 ed¦  «        d>d„¦   «         Z8dej9        d e:d!ej9        fd"„Z;	 	 	 d?d$ej3        d%ej9        d&ej9        d'ej9        d(ej9        dz  d)e<e:z  d*e<dz  d+e<dz  d!e=ej9        ej9        f         fd,„Z> ee8¦  «         G d-„ d.ej3        ¦  «        ¦   «         Z? G d/„ d0e¦  «        Z@ G d1„ d2ejA        ¦  «        ZBe( G d3„ d4e#¦  «        ¦   «         ZCe( G d5„ d6eC¦  «        ¦   «         ZDe( G d7„ d8eCe¦  «        ¦   «         ZE G d9„ d:eeC¦  «        ZF G d;„ d<eeC¦  «        ZGg d=¢ZHdS )@é    )ÚCallableNé   )Úinitialization)ÚACT2FN)ÚCacheÚDynamicCache)ÚGenerationMixin)Úuse_kernel_forward_from_hubÚuse_kernelized_func)Úcreate_causal_maskÚ!create_sliding_window_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_tuple)Údeprecate_kwarg)Úmaybe_autocastÚmerge_with_config_defaults)Úcapture_outputsé   )ÚGemma2Configc                   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Gemma2RMSNormç�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      €úz/root/private/project/pallet_detection_v2/.venv/lib/python3.11/site-packages/transformers/models/gemma2/modeling_gemma2.pyr*   zGemma2RMSNorm.__init__2   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&   )r0   Úxs     r2   Ú_normzGemma2RMSNorm._norm7   s8   € Ø•5”;˜qŸušu Q™xœxŸ}š}¨R¸˜}Ñ>Ô>ÀÄÑIÑJÔJÑJÐJr3   c                 ó¸   — |                       |                     ¦   «         ¦  «        }|d| j                             ¦   «         z   z  }|                     |¦  «        S )Nç      ð?)r<   Úfloatr/   Útype_as)r0   r;   Úoutputs      r2   ÚforwardzGemma2RMSNorm.forward:   sL   € Ø—’˜AŸGšG™IœIÑ&Ô&ˆð ˜3 ¤×!2Ò!2Ñ!4Ô!4Ñ4Ñ5ˆØ�~Š~˜aÑ Ô Ð r3   c                 óH   — t          | j        j        ¦  «        › d| j        › �S )Nz, eps=)Útupler/   Úshaper&   )r0   s    r2   Ú
extra_reprzGemma2RMSNorm.extra_reprA   s%   € Ý˜œÔ)Ñ*Ô*Ð<Ð<°$´(Ð<Ð<Ð<r3   )r$   )
Ú__name__Ú
__module__Ú__qualname__Úintr?   r*   r<   rB   rF   Ú__classcell__©r1   s   @r2   r#   r#   1   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 =r3   r#   c                   ó$   ‡ — e Zd Zˆ fd„Zd„ Zˆ xZS )Ú	Gemma2MLPc                 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©r0   rS   r1   s     €r2   r*   zGemma2MLP.__init__F   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r3   c                 ó¨   — |                       |                      |                      |¦  «        ¦  «        |                      |¦  «        z  ¦  «        }|S r(   )rY   r[   rW   rX   )r0   r;   rY   s      r2   rB   zGemma2MLP.forwardP   sA   € Ø—N’N 4§;¢;¨t¯~ª~¸aÑ/@Ô/@Ñ#AÔ#AÀDÇLÂLÐQRÁOÄOÑ#SÑTÔTˆ	ØÐr3   )rG   rH   rI   r*   rB   rK   rL   s   @r2   rN   rN   E   sG   ø€ € € € € ð7ð 7ð 7ð 7ð 7ðð ð ð ð ð ð r3   rN   c            	       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Gemma2RotaryEmbeddingÚdevicez5.18)ÚversionNrS   c                 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)r)   r*   Úmax_position_embeddingsÚmax_seq_len_cachedÚoriginal_max_seq_lenrS   Úrope_parametersrc   Úcompute_default_rope_parametersr   Úattention_scalingr+   ÚBufferÚinv_freqÚcloneÚoriginal_inv_freq)r0   rS   r`   Úrope_init_fnrn   r1   s        €r2   r*   zGemma2RotaryEmbedding.__init__V   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r3   Úreturnc                 óä   — | j         d         }t          | dd¦  «        p| j        | j        z  }d}d|t	          j        d|dt          j        ¬¦  «        |z  z  z  }|                     |¦  «        |fS )a¾  
        Computes the inverse frequencies according to the original RoPE implementation
        Args:
            config ([`~transformers.PreTrainedConfig`]):
                The model configuration.
        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head_dimNr>   r   r5   ©Údtype)rj   ÚgetattrrT   Únum_attention_headsr-   Úaranger?   Úto)rS   r`   ÚkwargsÚbaser%   Úattention_factorrn   s          r2   rk   z5Gemma2RotaryEmbedding.compute_default_rope_parametersg   sz   € ð Ô% lÔ3ˆÝ�f˜j¨$Ñ/Ô/Ðc°6Ô3EÈÔIcÑ3cˆàÐà˜$¥5¤<°°3¸ÅÄÐ#MÑ#MÔ#MÐPSÑ#SÑTÑUˆØ�{Š{˜6Ñ"Ô"Ð$4Ð4Ð4r3   c                 óN  — | j         d d d …d f                              ¦   «                              |j        d         dd¦  «                             |j        ¦  «        }|d d …d d d …f                              ¦   «         }t          |j        j        t          ¦  «        r|j        j        dk    r|j        j        nd}t          |d¬¦  «        5  |                     ¦   «         |                     ¦   «         z   
                    dd¦  «        }t          j        ||fd¬	¦  «        }|                     ¦   «         | j        z  }|                     ¦   «         | j        z  }	d d d ¦  «         n# 1 swxY w Y   |                     |j        ¬
¦  «        |	                     |j        ¬
¦  «        fS )Nr   r6   r    ÚmpsÚcpuF)Údevice_typeÚenabledr5   ©r%   rv   )rn   r?   ÚexpandrE   r{   r`   Ú
isinstanceÚtypeÚstrr   Ú	transposer-   ÚcatÚcosrl   Úsinrw   )
r0   r;   Úposition_idsÚinv_freq_expandedÚposition_ids_expandedr‚   ÚfreqsÚembr‹   rŒ   s
             r2   rB   zGemma2RotaryEmbedding.forward{   s·  € ð !œM¨$°°°°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(   )rG   rH   rI   r   r!   r*   ÚstaticmethodrD   r-   ÚTensorr?   rk   Úno_gradr   rB   rK   rL   s   @r2   r_   r_   U   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  Ø€_�X vÐ.Ñ.Ô.ð5ð 5°ð 5ÐX]Ð^cÔ^jÐlqÐ^qÔXrð 5ð 5ð 5ñ /Ô.ñ „\ð5ð$ €U„]�_„_Øð<ð <ñ Ôñ „_ð<ð <ð <ð <ð <r3   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..Nr6   r5   r„   )rE   r-   rŠ   )r;   Úx1Úx2s      r2   Úrotate_halfr˜   ‹   s]   € à	
ˆ3Ð"�!”'˜"”+ Ñ"Ð"Ð"Ô	#€BØ	
ˆ3�”˜”˜qÑ Ð"Ð"Ð"Ô	#€BÝŒ9�r�c˜2�Y BÐ'Ñ'Ô'Ð'r3   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	unsqueezer˜   )ÚqÚkr‹   rŒ   Úunsqueeze_dimÚq_embedÚk_embeds          r2   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r3   Úhidden_statesÚn_reprr   c                 ó¸   — | j         \  }}}}|dk    r| S | dd…dd…ddd…dd…f                              |||||¦  «        } |                      |||z  ||¦  «        S )zÔ
    This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,
    num_key_value_heads, seqlen, head_dim) to (batch, num_attention_heads, seqlen, head_dim)
    r    N)rE   r…   Úreshape)r¢   r£   ÚbatchÚnum_key_value_headsÚslenru   s         r2   Ú	repeat_kvr©   ¬   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Tr3   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¿r5   r   r6   )r%   rw   )ÚpÚtrainingr    )ru   r©   Únum_key_value_groupsr-   Úmatmulr‰   Útanhr+   Ú
functionalÚsoftmaxÚfloat32r{   rw   r°   r¶   Ú
contiguous)r«   r¬   r­   r®   r¯   r°   r±   r²   r|   Ú
key_statesÚvalue_statesÚattn_weightsÚattn_outputs                r2   Úeager_attention_forwardrÂ   ¸   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$Ð$r3   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Gemma2Attentionz=Multi-headed attention from 'Attention Is All You Need' paperrS   Ú	layer_idxc                 ót  •— t          ¦   «                              ¦   «          t          |d¦  «        r|j        |         nd | _        || _        || _        t          |d|j        |j	        z  ¦  «        | _
        |j	        |j        z  | _        |j        dz  | _        | j        j        | _        t          |d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_typesru   r´   Úuse_bidirectional_attentionFrQ   Úsliding_attention)r)   r*   ÚhasattrrÇ   Ú
layer_typerS   rÅ   rx   rT   ry   ru   r§   r·   Úquery_pre_attn_scalarr±   Úattention_dropoutÚ	is_causalr+   rV   Úattention_biasÚq_projÚk_projÚv_projÚo_projÚattn_logit_softcappingÚsliding_window©r0   rS   rÅ   r1   s      €r2   r*   zGemma2Attention.__init__Þ   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Ý$ VÐ-JÈEÑRÔRÐRˆ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r3   Nr¢   Úposition_embeddingsr¯   Úpast_key_valuesr|   rr   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 )Nr6   r    r5   rª   )r°   r±   rÕ   r²   )rE   ru   rÐ   Úviewr‰   rÑ   rÒ   r¡   ÚupdaterÅ   r   Úget_interfacerS   Ú_attn_implementationrÂ   r¶   rÍ   r±   rÕ   rÔ   r¥   r½   rÓ   )r0   r¢   r×   r¯   rØ   r|   Úinput_shapeÚhidden_shapeÚquery_statesr¾   r¿   r‹   rŒ   Úattention_interfacerÁ   rÀ   s                   r2   rB   zGemma2Attention.forwardø   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$7ØØØØØð%
ð /3¬mÐD�DÔ*Ð*ÀØ”LØÔ.ØÔ/ð%
ð %
ð ð%
ð %
Ñ!ˆ�\ð *�kÔ)Ð;¨;Ð;¸Ð;Ð;Ð;×FÒFÑHÔHˆØ—k’k +Ñ.Ô.ˆØ˜LÐ(Ð(r3   )NNN)rG   rH   rI   Ú__doc__r!   rJ   r*   r-   r“   rD   r   r   r   rB   rK   rL   s   @r2   rÄ   rÄ   Ú   s   ø€ € € € € àGÐGðh˜|ð h¸ð hð hð hð hð hð hð: IMØ.2Ø(,ð()ð ()à”|ð()ð # 5¤<°´Ð#=Ô>ÀÑEð()ð œ tÑ+ð	()ð
  ™ð()ð Ð-Ô.ð()ð 
ˆuŒ|˜Uœ\¨DÑ0°%¸¼Ô2EÈÑ2LÐLÔ	Mð()ð ()ð ()ð ()ð ()ð ()ð ()ð ()r3   rÄ   c                   ó¶   ‡ — e Zd Zdedefˆ fd„Z	 	 	 	 ddej        deej        ej        f         dz  dej        dz  dej	        dz  d	e
dz  d
ej        fd„Zˆ xZS )ÚGemma2DecoderLayerrS   rÅ   c                 óÂ  •— t          ¦   «                              ¦   «          |j        | _        || _        t	          ||¬¦  «        | _        t          |¦  «        | _        t          |j        |j	        ¬¦  «        | _
        t          |j        |j	        ¬¦  «        | _        t          |j        |j	        ¬¦  «        | _        t          |j        |j	        ¬¦  «        | _        d S )N)rS   rÅ   ©r&   )r)   r*   rT   rS   rÄ   Ú	self_attnrN   Úmlpr#   Úrms_norm_epsÚinput_layernormÚpost_attention_layernormÚpre_feedforward_layernormÚpost_feedforward_layernormrÖ   s      €r2   r*   zGemma2DecoderLayer.__init__$  sÁ   ø€ Ý‰Œ×ÒÑÔÐØ!Ô-ˆÔØˆŒÝ(°À)ÐLÑLÔLˆŒÝ˜VÑ$Ô$ˆŒÝ,¨VÔ-?ÀVÔEXÐYÑYÔYˆÔÝ(5°fÔ6HÈfÔNaÐ(bÑ(bÔ(bˆÔ%å)6°vÔ7IÈvÔObÐ)cÑ)cÔ)cˆÔ&Ý*7¸Ô8JÐPVÔPcÐ*dÑ*dÔ*dˆÔ'Ð'Ð'r3   Nr¢   r×   r¯   r�   rØ   rr   c           	      ó   — |}|                       |¦  «        } | j        d|||||dœ|¤Ž\  }}|                      |¦  «        }||z   }|}|                      |¦  «        }|                      |¦  «        }|                      |¦  «        }||z   }|S )N)r¢   r×   r¯   r�   rØ   © )rê   rç   rë   rì   rè   rí   )	r0   r¢   r×   r¯   r�   rØ   r|   ÚresidualÚ_s	            r2   rB   zGemma2DecoderLayer.forward0  sÄ   € ð !ˆà×,Ò,¨]Ñ;Ô;ˆð *˜4œ>ð 
Ø'Ø 3Ø)Ø%Ø+ð
ð 
ð ð
ð 
Ñˆ�qð ×5Ò5°mÑDÔDˆØ  =Ñ0ˆà ˆØ×6Ò6°}ÑEÔEˆØŸš Ñ/Ô/ˆØ×7Ò7¸ÑFÔFˆØ  =Ñ0ˆàÐr3   )NNNN)rG   rH   rI   r!   rJ   r*   r-   r“   rD   Ú
LongTensorr   rB   rK   rL   s   @r2   rä   rä   #  sà   ø€ € € € € ð
e˜|ð 
e¸ð 
eð 
eð 
eð 
eð 
eð 
eð IMØ.2Ø04Ø(,ðð à”|ðð # 5¤<°´Ð#=Ô>ÀÑEðð œ tÑ+ð	ð
 Ô&¨Ñ-ðð  ™ðð 
Œðð ð ð ð ð ð ð r3   rä   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Gemma2TextScaledWordEmbeddingz\
    This module overrides nn.Embeddings' forward by multiplying with embeddings scale.
    r>   Únum_embeddingsÚembedding_dimÚpadding_idxÚembed_scalec                 ó¶   •— t          ¦   «                              |||¦  «         || _        t          j        t          j        |¦  «        d¬¦  «        | _        d S )NFre   )r)   r*   Úscalar_embed_scaler+   rm   r-   Útensorrø   )r0   rõ   rö   r÷   rø   r1   s        €r2   r*   z&Gemma2TextScaledWordEmbedding.__init__W  sN   ø€ Ý‰Œ×Ò˜¨¸ÑDÔDÐDØ"-ˆÔÝœ9¥U¤\°+Ñ%>Ô%>È5ÐQÑQÔQˆÔÐÐr3   Ú	input_idsc                 ó�   •— t          ¦   «                              |¦  «        | j                             | j        j        ¦  «        z  S r(   )r)   rB   rø   r{   r/   rw   )r0   rü   r1   s     €r2   rB   z%Gemma2TextScaledWordEmbedding.forward\  s4   ø€ Ý‰wŒw�Š˜yÑ)Ô)¨DÔ,<×,?Ò,?ÀÄÔ@QÑ,RÔ,RÑRÐRr3   )r>   )rG   rH   rI   râ   rJ   r?   r*   r-   r“   rB   rK   rL   s   @r2   rô   rô   R  s¦   ø€ € € € € ðð ðRð R sð R¸3ð RÈSð RÐ_dð Rð Rð Rð Rð Rð Rð
S ¤ð Sð Sð Sð Sð Sð Sð Sð Sð Sð Sr3   rô   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Gemma2PreTrainedModelrS   ÚmodelTrä   rØ   )r¢   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_weightsr1   rG   ÚinitÚzeros_r/   r†   rô   Ú	constant_rø   rú   )r0   r«   r1   s     €r2   r  z#Gemma2PreTrainedModel._init_weightsr  s‚   ø€ å‰Œ×Ò˜fÑ%Ô%Ð%à˜Ô(Ô1Ð1Ð1ÝŒK˜œÑ&Ô&Ð&Ð&Ð&Ý˜Õ =Ñ>Ô>ð 	JÝŒN˜6Ô-¨vÔ/HÑIÔIÐIÐIÐIð	Jð 	Jr3   )rG   rH   rI   r!   Ú__annotations__Úbase_model_prefixÚsupports_gradient_checkpointingÚ_no_split_modulesÚ_skip_keys_device_placementÚ_supports_flash_attnÚ_supports_sdpaÚ_supports_flex_attnÚ_can_compile_fullgraphÚ_supports_attention_backendrä   rÄ   Ú_can_record_outputsr-   r”   r  rK   rL   s   @r2   rÿ   rÿ   `  s±   ø€ € € € € € àÐÐÑØÐØ&*Ð#Ø-Ð.Ð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r3   rÿ   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Gemma2ModelrS   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?)rø   c                 ó0   •— g | ]}t          ‰|¦  «        ‘ŒS rï   )rä   )Ú.0rÅ   rS   s     €r2   ú
<listcomp>z(Gemma2Model.__init__.<locals>.<listcomp>‡  s$   ø€ ÐdÐdÐd°yÕ ¨	Ñ2Ô2ÐdÐdÐdr3   ræ   F)r)   r*   Úpad_token_idr÷   Ú
vocab_sizerô   rT   rS   Úembed_tokensr+   Ú
ModuleListÚrangeÚnum_hidden_layersÚlayersr#   ré   Únormr_   Ú
rotary_embÚgradient_checkpointingÚ	post_initr\   s    `€r2   r*   zGemma2Model.__init__~  sé   øø€ Ý‰Œ×Ò˜Ñ Ô Ð Ø!Ô.ˆÔØ Ô+ˆŒå9ØÔ˜vÔ1°4Ô3CÐQUÔQ\ÔQhÐjmÑQmð
ñ 
ô 
ˆÔõ ”mØdÐdÐdÐdÅEÈ&ÔJbÑDcÔDcÐdÑdÔdñ
ô 
ˆŒõ " &Ô"4¸&Ô:MÐNÑNÔNˆŒ	Ý/°Ñ7Ô7ˆŒØ&+ˆÔ#ð 	�ŠÑÔÐÐÐr3   Nrü   r¯   r�   rØ   Úinputs_embedsÚ	use_cacher|   rr   c           	      óØ  — |d u |d uz  rt          d¦  «        ‚|€|                      |¦  «        }|r|€t          | j        ¬¦  «        }|€V|�|                     ¦   «         nd}t          j        |j        d         |j        ¬¦  «        |z   }| 	                    d¦  «        }t          |x}	t          ¦  «        s&| j        ||||dœ}
t          d
i |
¤Žt          d
i |
¤Ždœ}	|}|                      ||¦  «        }t          | j        d | j        j        …         ¦  «        D ])\  }} ||f|	| j        j        |                  |||dœ|¤Ž}Œ*|                      |¦  «        }t)          ||¬	¦  «        S )Nz:You must specify exactly one of input_ids or inputs_embeds)rS   r   r    )r`   )rS   r$  r¯   rØ   r�   )Úfull_attentionrÉ   )r¯   r×   r�   rØ   )Úlast_hidden_staterØ   rï   )Ú
ValueErrorr  r   rS   Úget_seq_lengthr-   rz   rE   r`   r›   r†   Údictr   r   r!  Ú	enumerater  r  rÇ   r   r   )r0   rü   r¯   r�   rØ   r$  r%  r|   Úpast_seen_tokensÚcausal_mask_mappingÚmask_kwargsr¢   r×   ÚiÚdecoder_layers                  r2   rB   zGemma2Model.forward�  sæ  € ð ˜Ð -°tÐ";Ñ<ð 	[ÝÐYÑZÔZÐZàÐ Ø*.×*;Ò*;¸IÑ*FÔ*FˆMàð 	?˜Ð0Ý*°$´+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$7Ø)Ø /ðð ð ðð ˆMˆMð Ÿ	š	 -Ñ0Ô0ˆå&Ø+Ø+ð
ñ 
ô 
ð 	
r3   )NNNNNN)rG   rH   rI   r!   r*   r   r   r   r-   rò   r“   r   ÚFloatTensorÚboolr   r   r   rB   rK   rL   s   @r2   r  r  |  s  ø€ € € € € ð˜|ð ð ð ð ð ð ð$  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 ˜$‘;ð;
ð Ð+Ô,ð;
ð 
!ð;
ð ;
ð ;
ñ „^ñ „_ñ  Ôð;
ð ;
ð ;
ð ;
ð ;
r3   r  c                   ó   ‡ — e Zd ZddiZddiZddgdgfiZddiZˆ fd„Zee		 	 	 	 	 	 	 	 dde
j        d	z  de
j        d	z  de
j        d	z  ded	z  de
j        d	z  de
j        d	z  ded	z  dee
j        z  dee         defd„¦   «         ¦   «         Zˆ xZS )ÚGemma2ForCausalLMzlm_head.weightzmodel.embed_tokens.weightÚlm_headÚcolwise_gather_outputr¢   ÚlogitsÚkeep_full_weightc                 óþ   •— t          ¦   «                              |¦  «         t          |¦  «        | _        |j        | _        t          j        |j        |j        d¬¦  «        | _        |  	                    ¦   «          d S rP   )
r)   r*   r  r   r  r+   rV   rT   r6  r#  r\   s     €r2   r*   zGemma2ForCausalLM.__init__Ø  sj   ø€ Ý‰Œ×Ò˜Ñ Ô Ð Ý  Ñ(Ô(ˆŒ
Ø Ô+ˆŒÝ”y Ô!3°VÔ5FÈUÐSÑSÔSˆŒð 	�ŠÑÔÐÐÐr3   Nr   rü   r¯   r�   rØ   r$  Úlabelsr%  Úlogits_to_keepr|   rr   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 )a‚  
        Example:

        ```python
        >>> from transformers import AutoTokenizer, Gemma2ForCausalLM

        >>> model = Gemma2ForCausalLM.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?"
        ```)rü   r¯   r�   rØ   r$  r%  N)Úlossr8  rØ   r¢   r  rï   )r   r(  r†   rJ   Úslicer6  rS   Úfinal_logit_softcappingr-   r¹   Úloss_functionr  r   rØ   r¢   r  )r0   rü   r¯   r�   rØ   r$  r;  r%  r<  r|   Úoutputsr¢   Úslice_indicesr8  r>  s                  r2   rB   zGemma2ForCausalLM.forwardá  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 	
r3   )NNNNNNNr   )rG   rH   rI   Ú_tied_weights_keysÚ_tp_planÚ_pp_planÚ
_fsdp_planr*   r   r   r-   rò   r“   r   r2  r3  rJ   r   r   r   rB   rK   rL   s   @r2   r5  r5  Ñ  sV  ø€ € € € € à*Ð,GÐHÐØÐ2Ð3€HØ˜_Ð-°¨zÐ:Ð;€HØÐ/Ð0€Jð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 ˜$‘;ð;
ð ˜eœlÑ*ð;
ð Ð+Ô,ð;
ð 
 ð;
ð ;
ð ;
ñ „^ñ Ôð;
ð ;
ð ;
ð ;
ð ;
r3   r5  c                   ó   — e Zd ZdS )ÚGemma2ForSequenceClassificationN©rG   rH   rI   rï   r3   r2   rI  rI  !  ó   € € € € € Ø€Dr3   rI  c                   ó   — e Zd ZdS )ÚGemma2ForTokenClassificationNrJ  rï   r3   r2   rM  rM  %  rK  r3   rM  )r5  r  rÿ   rI  rM  )r    )rª   NN)IÚcollections.abcr   r-   Útorch.nnr+   Ú r   r  Úactivationsr   Úcache_utilsr   r   Ú
generationr	   Úintegrationsr
   r   Úmasking_utilsr   r   Úmodeling_flash_attention_utilsr   Úmodeling_layersr   r   r   Úmodeling_outputsr   r   Úmodeling_rope_utilsr   r   Úmodeling_utilsr   r   Úprocessing_utilsr   Úutilsr   r   r   Úutils.deprecationr   Úutils.genericr   r   Úutils.output_capturingr   Úconfiguration_gemma2r!   ÚModuler#   rN   r_   r˜   r¡   r“   rJ   r©   r?   rD   rÂ   rÄ   rä   Ú	Embeddingrô   rÿ   r  r5  rI  rM  Ú__all__rï   r3   r2   ú<module>rd     s7  ðð* %Ð $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 LÐ LÐ LÐ LÐ LÐ LÐ LÐ LØ RÐ RÐ RÐ RÐ RÐ RÐ RÐ RØ BÐ BÐ BÐ BÐ BÐ Bðð ð ð ð ð ð ð ð ð ð
 PÐ 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 0Ð 0Ð 0Ð 0Ð 0Ð 0Ø GÐ GÐ GÐ GÐ GÐ GÐ GÐ GØ 5Ð 5Ð 5Ð 5Ð 5Ð 5Ø .Ð .Ð .Ð .Ð .Ð .ð=ð =ð =ð =ð =�B”Iñ =ô =ð =ð(ð ð ð ð �”	ñ ô ð ð 3<ð 3<ð 3<ð 3<ð 3<˜BœIñ 3<ô 3<ð 3<ðl(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)�b”iñ E)ô E)ñ +Ô*ðE)ðP,ð ,ð ,ð ,ð ,Ð3ñ ,ô ,ð ,ð^Sð Sð Sð Sð S B¤Lñ Sô Sð Sð ðJð Jð Jð Jð J˜Oñ 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L
ð L
ð L
ð L
ð L
Ð-¨ñ L
ô L
ñ „ðL
ð^	ð 	ð 	ð 	ð 	Ð&FÐH]ñ 	ô 	ð 	ð	ð 	ð 	ð 	ð 	Ð#@ÐBWñ 	ô 	ð 	ðð ð €€€r3   