§
    9²¸jÿY  ã                   ó¾  — d dl mZ d dlZd dlmZ ddlmZ ddlmZmZ ddl	m
Z
 ddlmZmZ dd	lmZmZ dd
lmZ ddlmZmZmZmZ ddlmZ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,m-Z- ddl.m/Z/  ed¦  «         G d„ dej0        ¦  «        ¦   «         Z1 G d„ dej0        ¦  «        Z2 G d„ dej0        ¦  «        Z3d„ Z4 ed¦  «        d?d„¦   «         Z5d ej6        d!e7d"ej6        fd#„Z8	 d@d%ej0        d&ej6        d'ej6        d(ej6        d)ej6        dz  d*e9d+e9d,e"e$         fd-„Z: ee5¦  «         G d.„ d/ej0        ¦  «        ¦   «         Z; G d0„ d1e¦  «        Z<e% G d2„ d3e ¦  «        ¦   «         Z=e% G d4„ d5e=¦  «        ¦   «         Z>e% G d6„ d7e=e
¦  «        ¦   «         Z? G d8„ d9ee=¦  «        Z@ G d:„ d;ee=¦  «        ZA G d<„ d=ee=¦  «        ZBg d>¢ZCdS )Aé    )ÚCallableN)Únné   )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GenericForQuestionAnsweringÚ 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Qwen3ConfigÚRMSNormc                   óT   ‡ — e Zd Zd	deddfˆ fd„Zdej        dej        fd„Zd„ Zˆ xZ	S )
ÚQwen3RMSNormç�íµ ÷Æ°>ÚepsÚreturnNc                 ó¬   •— t          ¦   «                              ¦   «          t          j        t	          j        |¦  «        ¦  «        | _        || _        dS )z;
        Qwen3RMSNorm is equivalent to T5LayerNorm
        N)ÚsuperÚ__init__r   Ú	ParameterÚtorchÚonesÚweightÚvariance_epsilon)ÚselfÚhidden_sizer'   Ú	__class__s      €úx/root/private/project/pallet_detection_v2/.venv/lib/python3.11/site-packages/transformers/models/qwen3/modeling_qwen3.pyr+   zQwen3RMSNorm.__init__3   sD   ø€ õ 	‰Œ×ÒÑÔÐÝ”l¥5¤:¨kÑ#:Ô#:Ñ;Ô;ˆŒØ #ˆÔÐÐó    Úhidden_statesc                 ó  — |j         }|                     t          j        ¦  «        }|                     d¦  «                             dd¬¦  «        }|t          j        || j        z   ¦  «        z  }| j        |                     |¦  «        z  S )Né   éÿÿÿÿT)Úkeepdim)	ÚdtypeÚtor-   Úfloat32ÚpowÚmeanÚrsqrtr0   r/   )r1   r6   Úinput_dtypeÚvariances       r4   ÚforwardzQwen3RMSNorm.forward;   s|   € Ø#Ô)ˆØ%×(Ò(­¬Ñ7Ô7ˆØ ×$Ò$ QÑ'Ô'×,Ò,¨R¸Ð,Ñ>Ô>ˆØ%­¬°H¸tÔ?TÑ4TÑ(UÔ(UÑUˆØŒ{˜]×-Ò-¨kÑ:Ô:Ñ:Ð:r5   c                 óH   — t          | j        j        ¦  «        › d| j        › �S )Nz, eps=)Útupler/   Úshaper0   )r1   s    r4   Ú
extra_reprzQwen3RMSNorm.extra_reprB   s&   € Ý˜œÔ)Ñ*Ô*ÐIÐI°$Ô2GÐIÐIÐIr5   )r&   )
Ú__name__Ú
__module__Ú__qualname__Úfloatr+   r-   ÚTensorrC   rG   Ú__classcell__©r3   s   @r4   r%   r%   1   sŒ   ø€ € € € € ð$ð $¨ð $¸$ð $ð $ð $ð $ð $ð $ð; U¤\ð ;°e´lð ;ð ;ð ;ð ;ðJð Jð Jð Jð Jð Jð Jr5   r%   c                   ó$   ‡ — e Zd Zˆ fd„Zd„ Zˆ xZS )ÚQwen3MLPc                 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configr2   Úintermediate_sizer   ÚLinearÚ	gate_projÚup_projÚ	down_projr   Ú
hidden_actÚact_fn©r1   rU   r3   s     €r4   r+   zQwen3MLP.__init__G   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.Ô/ˆŒˆˆr5   c                 ó¨   — |                       |                      |                      |¦  «        ¦  «        |                      |¦  «        z  ¦  «        }|S ©N)rZ   r\   rX   rY   )r1   ÚxrZ   s      r4   rC   zQwen3MLP.forwardQ   sA   € Ø—N’N 4§;¢;¨t¯~ª~¸aÑ/@Ô/@Ñ#AÔ#AÀDÇLÂLÐQRÁOÄOÑ#SÑTÔTˆ	ØÐr5   )rH   rI   rJ   r+   rC   rM   rN   s   @r4   rP   rP   F   sG   ø€ € € € € ð0ð 0ð 0ð 0ð 0ðð ð ð ð ð ð r5   rP   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Qwen3RotaryEmbeddingÚdevicez5.18)ÚversionNrU   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_lenrU   Úrope_parametersrf   Úcompute_default_rope_parametersr   Úattention_scalingr   ÚBufferÚinv_freqÚcloneÚoriginal_inv_freq)r1   rU   rc   Úrope_init_fnrp   r3   s        €r4   r+   zQwen3RotaryEmbedding.__init__W   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�$Ô(åœ	 (°uÐ=Ñ=Ô=ˆŒÝ!#¤¨8¯>ª>Ñ+;Ô+;ÈÐ!NÑ!NÔ!NˆÔÐÐr5   r(   c                 óä   — | j         d         }t          | dd¦  «        p| j        | j        z  }d}d|t	          j        d|dt          j        ¬¦  «        |z  z  z  }|                     |¦  «        |fS )a¾  
        Computes the inverse frequencies according to the original RoPE implementation
        Args:
            config ([`~transformers.PreTrainedConfig`]):
                The model configuration.
        Returns:
            Tuple of (`torch.Tensor`, `float`), containing the inverse frequencies for the RoPE embeddings and the
            post-processing scaling factor applied to the computed cos/sin (unused in this type of RoPE).
        Ú
rope_thetaÚhead_dimNg      ð?r   r8   ©r;   )rl   Úgetattrr2   Únum_attention_headsr-   ÚarangerK   r<   )rU   rc   ÚkwargsÚbaseÚdimÚattention_factorrp   s          r4   rm   z4Qwen3RotaryEmbedding.compute_default_rope_parametersh   sz   € ð Ô% lÔ3ˆÝ�f˜j¨$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$4Ð4Ð4r5   c                 óN  — | j         d d d …d f                              ¦   «                              |j        d         dd¦  «                             |j        ¦  «        }|d d …d d d …f                              ¦   «         }t          |j        j        t          ¦  «        r|j        j        dk    r|j        j        nd}t          |d¬¦  «        5  |                     ¦   «         |                     ¦   «         z   
                    dd¦  «        }t          j        ||fd¬	¦  «        }|                     ¦   «         | j        z  }|                     ¦   «         | j        z  }	d d d ¦  «         n# 1 swxY w Y   |                     |j        ¬
¦  «        |	                     |j        ¬
¦  «        fS )Nr   r9   r!   ÚmpsÚcpuF)Údevice_typeÚenabledr8   ©r}   rw   )rp   rK   ÚexpandrF   r<   rc   Ú
isinstanceÚtypeÚstrr   Ú	transposer-   ÚcatÚcosrn   Úsinr;   )
r1   r`   Úposition_idsÚinv_freq_expandedÚposition_ids_expandedr‚   ÚfreqsÚembr‹   rŒ   s
             r4   rC   zQwen3RotaryEmbedding.forward|   s·  € ð !œM¨$°°°°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_   )rH   rI   rJ   r   r"   r+   ÚstaticmethodrE   r-   rL   rK   rm   Úno_gradr   rC   rM   rN   s   @r4   rb   rb   V   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 5ÐW\Ð]bÔ]iÐkpÐ]pÔWqð 5ð 5ð 5ñ /Ô.ñ „\ð5ð$ €U„]�_„_Øð<ð <ñ Ôñ „_ð<ð <ð <ð <ð <r5   rb   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..Nr9   r8   r„   )rF   r-   rŠ   )r`   Úx1Úx2s      r4   Úrotate_halfr—   Œ   s]   € à	
ˆ3Ð"�!”'˜"”+ Ñ"Ð"Ð"Ô	#€BØ	
ˆ3�”˜”˜qÑ Ð"Ð"Ð"Ô	#€BÝŒ9�r�c˜2�Y BÐ'Ñ'Ô'Ð'r5   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          r4   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r5   r6   Ún_repr(   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)rF   r…   Úreshape)r6   r¡   ÚbatchÚnum_key_value_headsÚslenrv   s         r4   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Tr5   ç        ÚmoduleÚqueryÚkeyÚvalueÚattention_maskÚscalingÚdropoutr{   c                 ó  — t          || j        ¦  «        }t          || j        ¦  «        }	t          j        ||                     dd¦  «        ¦  «        |z  }
|�|
|z   }
t
          j                             |
dt          j        ¬¦  «         	                    |j
        ¦  «        }
t
          j                             |
|| j        ¬¦  «        }
t          j        |
|	¦  «        }|                     dd¦  «                             ¦   «         }||
fS )Nr8   r   r9   )r}   r;   )ÚpÚtrainingr!   )r§   Únum_key_value_groupsr-   Úmatmulr‰   r   Ú
functionalÚsoftmaxr=   r<   r;   r¯   r²   Ú
contiguous)r©   rª   r«   r¬   r­   r®   r¯   r{   Ú
key_statesÚvalue_statesÚattn_weightsÚattn_outputs               r4   Úeager_attention_forwardr¼   ¹   sé   € õ ˜3 Ô ;Ñ<Ô<€JÝ˜U FÔ$?Ñ@Ô@€Lå”<  z×';Ò';¸A¸qÑ'AÔ'AÑBÔBÀWÑL€LØÐ!Ø# nÑ4ˆå”=×(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:€Kà˜Ð$Ð$r5   c                   óÊ   ‡ — 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ej        dz  d	e
dz  d
ee         de	ej        ej        dz  f         fd„Zˆ xZS )ÚQwen3Attentionz=Multi-headed attention from 'Attention Is All You Need' paperrU   Ú	layer_idxc                 ó¨  •— t          ¦   «                              ¦   «          t          |d¦  «        r|j        |         nd | _        || _        || _        t          |d|j        |j	        z  ¦  «        | _
        |j	        |j        z  | _        | j
        dz  | _        |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        ¬¦  «        | _        t/          | j
        |j        ¬¦  «        | _        t/          | j
        |j        ¬¦  «        | _        | j        dk    r|j        nd | _        d S )NÚlayer_typesrv   g      à¿TrS   ©r'   Úsliding_attention)r*   r+   ÚhasattrrÁ   Ú
layer_typerU   r¿   rx   r2   ry   rv   r¥   r³   r®   Úattention_dropoutÚ	is_causalr   rW   Úattention_biasÚq_projÚk_projÚv_projÚo_projr%   Úrms_norm_epsÚq_normÚk_normÚsliding_window©r1   rU   r¿   r3   s      €r4   r+   zQwen3Attention.__init__Ö   sº  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$\ˆÔ!Ø”} dÑ*ˆŒØ!'Ô!9ˆÔØˆŒå”iØÔ Ô :¸T¼]Ñ JÐQWÔQfð
ñ 
ô 
ˆŒõ ”iØÔ Ô :¸T¼]Ñ JÐQWÔQfð
ñ 
ô 
ˆŒõ ”iØÔ Ô :¸T¼]Ñ JÐQWÔQfð
ñ 
ô 
ˆŒõ ”iØÔ&¨¬Ñ6¸Ô8JÐQWÔQfð
ñ 
ô 
ˆŒõ # 4¤=°fÔ6IÐJÑJÔJˆŒÝ" 4¤=°fÔ6IÐJÑJÔJˆŒØ7;´ÐJ]Ò7]Ð7]˜fÔ3Ð3ÐcgˆÔÐÐr5   Nr6   Úposition_embeddingsr­   Úpast_key_valuesr{   r(   c                 óz  — |j         d d…         }g |¢d‘| j        ‘R }|                      |                      |¦  «                             |¦  «        ¦  «                             dd¦  «        }|                      |                      |¦  «                             |¦  «        ¦  «                             dd¦  «        }	|                      |¦  «                             |¦  «                             dd¦  «        }
|\  }}t          ||	||¦  «        \  }}	|�| 
                    |	|
| j        ¦  «        \  }	}
t          j        | j        j        t           ¦  «        } || ||	|
|f| j        sdn| j        | j        | j        dœ|¤Ž\  }} |j        g |¢d‘R Ž                      ¦   «         }|                      |¦  «        }||fS )Nr9   r!   r8   r¨   )r¯   r®   rÐ   )rF   rv   rÎ   rÉ   Úviewr‰   rÏ   rÊ   rË   r    Úupdater¿   r   Úget_interfacerU   Ú_attn_implementationr¼   r²   rÆ   r®   rÐ   r£   r·   rÌ   )r1   r6   rÒ   r­   rÓ   r{   Úinput_shapeÚhidden_shapeÚquery_statesr¸   r¹   r‹   rŒ   Úattention_interfacer»   rº   s                   r4   rC   zQwen3Attention.forwardñ   sà  € ð $Ô)¨#¨2¨#Ô.ˆØ8˜Ð8 bÐ8¨$¬-Ð8Ð8ˆà—{’{ 4§;¢;¨}Ñ#=Ô#=×#BÒ#BÀ<Ñ#PÔ#PÑQÔQ×[Ò[Ð\]Ð_`ÑaÔaˆØ—[’[ §¢¨]Ñ!;Ô!;×!@Ò!@ÀÑ!NÔ!NÑOÔO×YÒYÐZ[Ð]^Ñ_Ô_ˆ
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  $œ}ÐH�C�C°$Ô2HØ”LØ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(r5   r_   )rH   rI   rJ   Ú__doc__r"   Úintr+   r-   rL   rE   r   r   r   rC   rM   rN   s   @r4   r¾   r¾   Ò   sæ   ø€ € € € € àGÐGðh˜{ð h°sð hð hð hð hð hð hð@ )-ð')ð ')à”|ð')ð # 5¤<°´Ð#=Ô>ð')ð œ tÑ+ð	')ð
  ™ð')ð Ð-Ô.ð')ð 
ˆuŒ|˜Uœ\¨DÑ0Ð0Ô	1ð')ð ')ð ')ð ')ð ')ð ')ð ')ð ')r5   r¾   c                   óÒ   ‡ — e Zd Zdedefˆ fd„Z	 	 	 	 	 ddej        dej        dz  dej        dz  d	e	dz  d
e
dz  deej        ej        f         dz  dee         dej        fd„Zˆ xZS )ÚQwen3DecoderLayerrU   r¿   c                 ó4  •— t          ¦   «                              ¦   «          |j        | _        t          ||¬¦  «        | _        t          |¦  «        | _        t          |j        |j        ¬¦  «        | _	        t          |j        |j        ¬¦  «        | _
        d S )N)rU   r¿   rÂ   )r*   r+   r2   r¾   Ú	self_attnrP   Úmlpr%   rÍ   Úinput_layernormÚpost_attention_layernormrÑ   s      €r4   r+   zQwen3DecoderLayer.__init__  sƒ   ø€ Ý‰Œ×ÒÑÔÐØ!Ô-ˆÔå'¨vÀÐKÑKÔKˆŒå˜FÑ#Ô#ˆŒÝ+¨FÔ,>ÀFÔDWÐXÑXÔXˆÔÝ(4°VÔ5GÈVÔM`Ð(aÑ(aÔ(aˆÔ%Ð%Ð%r5   NFr6   r­   r�   rÓ   Ú	use_cacherÒ   r{   r(   c           
      óÎ   — |}|                       |¦  «        } | j        d||||||dœ|¤Ž\  }}	||z   }|}|                      |¦  «        }|                      |¦  «        }||z   }|S )N)r6   r­   r�   rÓ   ræ   rÒ   © )rä   râ   rå   rã   )
r1   r6   r­   r�   rÓ   ræ   rÒ   r{   ÚresidualÚ_s
             r4   rC   zQwen3DecoderLayer.forward&  s¡   € ð !ˆØ×,Ò,¨]Ñ;Ô;ˆà)˜4œ>ð 
Ø'Ø)Ø%Ø+ØØ 3ð
ð 
ð ð
ð 
Ñˆ�qð ! =Ñ0ˆð !ˆØ×5Ò5°mÑDÔDˆØŸš Ñ/Ô/ˆØ  =Ñ0ˆØÐr5   )NNNFN)rH   rI   rJ   r"   rÞ   r+   r-   rL   Ú
LongTensorr   ÚboolrE   r   r   rC   rM   rN   s   @r4   rà   rà     sÿ   ø€ € € € € ðb˜{ð b°sð bð bð bð bð bð bð /3Ø04Ø(,Ø!&ØHLðð à”|ðð œ tÑ+ðð Ô&¨Ñ-ð	ð
  ™ðð ˜$‘;ðð # 5¤<°´Ð#=Ô>ÀÑEðð Ð+Ô,ðð 
Œðð ð ð ð ð ð ð r5   rà   c                   óL   — e Zd ZU eed<   dZdZdgZdgZdZ	dZ
dZdZdZeedœZdS )ÚQwen3PreTrainedModelrU   ÚmodelTrà   rÓ   )r6   Ú
attentionsN)rH   rI   rJ   r"   Ú__annotations__Úbase_model_prefixÚsupports_gradient_checkpointingÚ_no_split_modulesÚ_skip_keys_device_placementÚ_supports_flash_attnÚ_supports_sdpaÚ_supports_flex_attnÚ_can_compile_fullgraphÚ_supports_attention_backendrà   r¾   Ú_can_record_outputsrè   r5   r4   rî   rî   F  sl   € € € € € € àÐÐÑØÐØ&*Ð#Ø,Ð-ÐØ#4Ð"5ÐØÐØ€NØÐà!ÐØ"&Ðà*Ø$ðð ÐÐÐr5   rî   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
Qwen3ModelrU   c                 ó  •‡— t          ¦   «                              ‰¦  «         ‰j        | _        ‰j        | _        t          j        ‰j        ‰j        | j        ¦  «        | _        t          j	        ˆfd„t          ‰j        ¦  «        D ¦   «         ¦  «        | _        t          ‰j        ‰j        ¬¦  «        | _        t!          ‰¬¦  «        | _        d| _        d| j        j        v | _        |                      ¦   «          d S )Nc                 ó0   •— g | ]}t          ‰|¦  «        ‘ŒS rè   )rà   )Ú.0r¿   rU   s     €r4   ú
<listcomp>z'Qwen3Model.__init__.<locals>.<listcomp>b  s$   ø€ ÐcÐcÐc°iÕ˜v yÑ1Ô1ÐcÐcÐcr5   rÂ   ©rU   FrÃ   )r*   r+   Úpad_token_idÚpadding_idxÚ
vocab_sizer   Ú	Embeddingr2   Úembed_tokensÚ
ModuleListÚrangeÚnum_hidden_layersÚlayersr%   rÍ   Únormrb   Ú
rotary_embÚgradient_checkpointingrU   rÁ   Úhas_sliding_layersÚ	post_initr]   s    `€r4   r+   zQwen3Model.__init__[  sæ   øø€ Ý‰Œ×Ò˜Ñ Ô Ð Ø!Ô.ˆÔØ Ô+ˆŒåœL¨Ô):¸FÔ<NÐPTÔP`ÑaÔaˆÔÝ”mØcÐcÐcÐcÅ5ÈÔIaÑCbÔCbÐcÑcÔcñ
ô 
ˆŒõ ! Ô!3¸Ô9LÐMÑMÔMˆŒ	Ý.°fÐ=Ñ=Ô=ˆŒØ&+ˆÔ#Ø"5¸¼Ô9PÐ"PˆÔð 	�ŠÑÔÐÐÐr5   NÚ	input_idsr­   r�   rÓ   Úinputs_embedsræ   r{   r(   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          ¦  «        s1| j        ||||dœ}
dt          di |
¤Ži}	| j        rt          di |
¤Ž|	d<   |}|                      ||¦  «        }t!          | j        d | j        j        …         ¦  «        D ]*\  }} ||f|	| j        j        |                  ||||d	œ|¤Ž}Œ+|                      |¦  «        }t+          ||r|nd ¬
¦  «        S )Nz:You must specify exactly one of input_ids or inputs_embedsr  r   r!   )rc   )rU   r  r­   rÓ   r�   Úfull_attentionrÃ   )r­   rÒ   r�   rÓ   ræ   )Úlast_hidden_staterÓ   rè   )Ú
ValueErrorr  r   rU   Úget_seq_lengthr-   rz   rF   rc   rš   r†   Údictr   r  r   r  Ú	enumerater  r
  rÁ   r  r   )r1   r  r­   r�   rÓ   r  ræ   r{   Úpast_seen_tokensÚcausal_mask_mappingÚmask_kwargsr6   rÒ   ÚiÚdecoder_layers                  r4   rC   zQwen3Model.forwardl  s  € ð ˜Ð -°tÐ";Ñ<ð 	[ÝÐYÑZÔZÐZàÐ Ø ×-Ò-¨iÑ8Ô8ˆMà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 	lð œ+Ø!.Ø"0Ø#2Ø ,ðð ˆKð !Õ"4Ð"CÐ"C°{Ð"CÐ"Cð#Ðð Ô&ð lÝ;\Ð;kÐ;kÐ_jÐ;kÐ;kÐ#Ð$7Ñ8à%ˆØ"Ÿošo¨m¸\ÑJÔJÐå )¨$¬+Ð6U¸¼Ô8UÐ6UÔ*VÑ WÔ Wð 		ð 		ÑˆAˆ}Ø)˜MØðà2°4´;Ô3JÈ1Ô3MÔNØ$7Ø)Ø /Ø#ðð ð ðð ˆMˆMð Ÿ	š	 -Ñ0Ô0ˆÝ&Ø+Ø/8ÐB˜O˜O¸dð
ñ 
ô 
ð 	
r5   )NNNNNN)rH   rI   rJ   r"   r+   r   r    r   r-   rë   rL   r   ÚFloatTensorrì   r   r   r   rC   rM   rN   s   @r4   rý   rý   Y  s  ø€ € € € € ð˜{ð ð ð ð ð ð ð"  ØØð .2Ø.2Ø04Ø(,Ø26Ø!%ð<
ð <
àÔ# dÑ*ð<
ð œ tÑ+ð<
ð Ô&¨Ñ-ð	<
ð
  ™ð<
ð Ô(¨4Ñ/ð<
ð ˜$‘;ð<
ð Ð+Ô,ð<
ð 
!ð<
ð <
ð <
ñ „^ñ „_ñ  Ôð<
ð <
ð <
ð <
ð <
r5   rý   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Qwen3ForCausalLMzlm_head.weightzmodel.embed_tokens.weightÚlm_headÚcolwise_gather_outputr6   ÚlogitsÚkeep_full_weightc                 óþ   •— t          ¦   «                              |¦  «         t          |¦  «        | _        |j        | _        t          j        |j        |j        d¬¦  «        | _        |  	                    ¦   «          d S rR   )
r*   r+   rý   rï   r  r   rW   r2   r"  r  r]   s     €r4   r+   zQwen3ForCausalLM.__init__µ  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r5   Nr   r  r­   r�   rÓ   r  Úlabelsræ   Úlogits_to_keepr{   r(   c	           
      óP  —  | j         d||||||dœ|	¤Ž}
|
j        }t          |t          ¦  «        rt	          | d¦  «        n|}|                      |dd…|dd…f         ¦  «        }d}|� | j        d||| j        j        dœ|	¤Ž}t          |||
j
        |
j        |
j        ¬¦  «        S )a^  
        labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
            Labels for computing the masked language modeling loss. Indices should either be in `[0, ...,
            config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored
            (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`.

        Example:

        ```python
        >>> from transformers import AutoTokenizer, Qwen3ForCausalLM

        >>> model = Qwen3ForCausalLM.from_pretrained("Qwen/Qwen3-8B")
        >>> tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-8B")

        >>> prompt = "Hey, are you conscious? Can you talk to me?"
        >>> 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]
        "Hey, are you conscious? Can you talk to me?\nI'm not conscious, but I can talk to you."
        ```)r  r­   r�   rÓ   r  ræ   N)r$  r'  r  )Úlossr$  rÓ   r6   rð   rè   )rï   r  r†   rÞ   Úslicer"  Úloss_functionrU   r  r   rÓ   r6   rð   )r1   r  r­   r�   rÓ   r  r'  ræ   r(  r{   Úoutputsr6   Úslice_indicesr$  r*  s                  r4   rC   zQwen3ForCausalLM.forward¾  sõ   € ðH ,6¨4¬:ð ,
ØØ)Ø%Ø+Ø'Øð,
ð ,
ð ð,
ð ,
ˆð  Ô1ˆå8BÀ>ÕSVÑ8WÔ8WÐk�˜~˜o¨tÑ4Ô4Ð4Ð]kˆØ—’˜m¨A¨A¨A¨}¸a¸a¸aÐ,?Ô@ÑAÔAˆàˆØÐØ%�4Ô%Ðp¨V¸FÈtÌ{ÔOeÐpÐpÐioÐpÐpˆDå%ØØØ#Ô3Ø!Ô/ØÔ)ð
ñ 
ô 
ð 	
r5   )NNNNNNNr   )rH   rI   rJ   Ú_tied_weights_keysÚ_tp_planÚ_pp_planÚ
_fsdp_planr+   r   r   r-   rë   rL   r   r  rì   rÞ   r   r   r   rC   rM   rN   s   @r4   r!  r!  ®  sV  ø€ € € € € à*Ð,GÐHÐØÐ2Ð3€HØ˜_Ð-°¨zÐ:Ð;€HØÐ/Ð0€Jðð ð ð ð ð Øð .2Ø.2Ø04Ø(,Ø26Ø*.Ø!%Ø-.ð;
ð ;
àÔ# dÑ*ð;
ð œ tÑ+ð;
ð Ô&¨Ñ-ð	;
ð
  ™ð;
ð Ô(¨4Ñ/ð;
ð Ô  4Ñ'ð;
ð ˜$‘;ð;
ð ˜eœlÑ*ð;
ð Ð+Ô,ð;
ð 
 ð;
ð ;
ð ;
ñ „^ñ Ôð;
ð ;
ð ;
ð ;
ð ;
r5   r!  c                   ó   — e Zd ZdS )ÚQwen3ForSequenceClassificationN©rH   rI   rJ   rè   r5   r4   r4  r4  þ  ó   € € € € € Ø€Dr5   r4  c                   ó   — e Zd ZdS )ÚQwen3ForTokenClassificationNr5  rè   r5   r4   r8  r8    r6  r5   r8  c                   ó   — e Zd ZdZdS )ÚQwen3ForQuestionAnsweringÚtransformerN)rH   rI   rJ   rò   rè   r5   r4   r:  r:    s   € € € € € Ø%ÐÐÐr5   r:  )r!  r:  rî   rý   r4  r8  )r!   )r¨   )DÚcollections.abcr   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   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_qwen3r"   ÚModuler%   rP   rb   r—   r    rL   rÞ   r§   rK   r¼   r¾   rà   rî   rý   r!  r4  r8  r:  Ú__all__rè   r5   r4   ú<module>rO     s  ðð* %Ð $Ð $Ð $Ð $Ð $à €€€Ø Ð Ð Ð Ð Ð à !Ð !Ð !Ð !Ð !Ð !Ø .Ð .Ð .Ð .Ð .Ð .Ð .Ð .Ø )Ð )Ð )Ð )Ð )Ð )Ø LÐ LÐ LÐ LÐ LÐ LÐ LÐ LØ RÐ RÐ RÐ RÐ RÐ RÐ RÐ RØ BÐ BÐ BÐ BÐ BÐ Bðð ð ð ð ð ð ð ð ð ð ð ð PÐ OÐ OÐ OÐ OÐ OÐ OÐ OØ KÐ KÐ KÐ KÐ KÐ KÐ KÐ KØ FÐ FÐ FÐ FÐ FÐ FÐ FÐ FØ &Ð &Ð &Ð &Ð &Ð &Ø IÐ IÐ IÐ IÐ IÐ IÐ IÐ IÐ IÐ IØ 0Ð 0Ð 0Ð 0Ð 0Ð 0Ø GÐ GÐ GÐ GÐ GÐ GÐ GÐ GØ 5Ð 5Ð 5Ð 5Ð 5Ð 5Ø ,Ð ,Ð ,Ð ,Ð ,Ð ,ð Ð˜YÑ'Ô'ðJð Jð Jð Jð J�2”9ñ Jô Jñ (Ô'ðJð(ð ð ð ð ˆrŒyñ ô ð ð 3<ð 3<ð 3<ð 3<ð 3<˜2œ9ñ 3<ô 3<ð 3<ðl(ð (ð (ð ÐÐ-Ñ.Ô.ðð ð ñ /Ô.ðð2	U˜Uœ\ð 	U°#ð 	U¸%¼,ð 	Uð 	Uð 	Uð 	Uð& ð%ð %ØŒIð%àŒ<ð%ð 
Œð%ð Œ<ð	%ð
 ”L 4Ñ'ð%ð ð%ð ð%ð Ð'Ô(ð%ð %ð %ð %ð2 ÐÐ)Ñ*Ô*ðE)ð E)ð E)ð E)ð E)�R”Yñ E)ô E)ñ +Ô*ðE)ðP(ð (ð (ð (ð (Ð2ñ (ô (ð (ðV ðð ð ð ð ˜?ñ ô ñ „ðð$ 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%EÐG[ñ 	ô 	ð 	ð	ð 	ð 	ð 	ð 	Ð"?ÐAUñ 	ô 	ð 	ð&ð &ð &ð &ð &Ð ;Ð=Qñ &ô &ð &ðð ð €€€r5   