§
    ‚ŠtjJo  ã                   ó   — d dl mZ d dlmZ d dlZd dlmc m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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/m0Z0 ddl1m2Z2 ddl3m4Z4  ed¦  «         G d„ dej5        ¦  «        ¦   «         Z6 G d„ dej5        ¦  «        Z7d„ Z8 ed¦  «        d@d„¦   «         Z9dej:        d e;d!ej:        fd"„Z<	 dAd$ej5        d%ej:        d&ej:        d'ej:        d(ej:        dz  d)e=d*e=d+e)e+         fd,„Z> ee9¦  «         G d-„ d.ej5        ¦  «        ¦   «         Z? G d/„ d0ej5        ¦  «        Z@ G d1„ d2ej5        ¦  «        ZAe G d3„ d4ej5        ¦  «        ¦   «         ZB G d5„ d6ej5        ¦  «        ZC G d7„ d8e¦  «        ZDe, G d9„ d:e'¦  «        ¦   «         ZEe, G d;„ d<eE¦  «        ¦   «         ZFe, G d=„ d>eEe¦  «        ¦   «         ZGg d?¢ZHdS )Bé    )ÚCallable)ÚOptionalN)Únné   )Úinitialization)ÚACT2FN)ÚCacheÚDynamicCache)ÚGenerationMixin)Úuse_experts_implementationÚuse_kernel_forward_from_hubÚ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Dots1ConfigÚ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Dots1RMSNormç�íµ ÷Æ°>ÚepsÚreturnNc                 ó¬   •— t          ¦   «                              ¦   «          t          j        t	          j        |¦  «        ¦  «        | _        || _        dS )z;
        Dots1RMSNorm is equivalent to T5LayerNorm
        N)ÚsuperÚ__init__r   Ú	ParameterÚtorchÚonesÚweightÚvariance_epsilon)ÚselfÚhidden_sizer'   Ú	__class__s      €úf/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/transformers/models/dots1/modeling_dots1.pyr+   zDots1RMSNorm.__init__4   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Dots1RMSNorm.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Dots1RMSNorm.extra_reprC   s&   € Ý˜œÔ)Ñ*Ô*ÐIÐI°$Ô2GÐIÐIÐIr5   )r&   )
Ú__name__Ú
__module__Ú__qualname__Úfloatr+   r-   ÚTensorrC   rG   Ú__classcell__©r3   s   @r4   r%   r%   2   sŒ   ø€ € € € € ð$ð $¨ð $¸$ð $ð $ð $ð $ð $ð $ð; U¤\ð ;°e´lð ;ð ;ð ;ð ;ðJð Jð Jð Jð Jð Jð Jr5   r%   c                   óÔ   ‡ — e Zd ZU ej        ed<   ddefˆ fd„Ze	 	 	 ddedz  de	d         de
dz  ded	ef         fd
„¦   «         Z ej        ¦   «         ed„ ¦   «         ¦   «         Zˆ xZS )ÚDots1RotaryEmbeddingÚinv_freqNÚconfigc                 ó²  •— t          ¦   «                              ¦   «          |j        | _        |j        | _        || _        | j        j        d         | _        | j        }| j        dk    rt          | j                 } || j        |¦  «        \  }| _
        |                      d|d¬¦  «         |                      d|                     ¦   «         d¬¦  «         d S )NÚ	rope_typeÚdefaultrQ   F)Ú
persistentÚoriginal_inv_freq)r*   r+   Úmax_position_embeddingsÚmax_seq_len_cachedÚoriginal_max_seq_lenrR   Úrope_parametersrT   Úcompute_default_rope_parametersr   Úattention_scalingÚregister_bufferÚclone)r1   rR   ÚdeviceÚrope_init_fnrQ   r3   s        €r4   r+   zDots1RotaryEmbedding.__init__J   sÊ   ø€ Ý‰Œ×ÒÑÔÐØ"(Ô"@ˆÔØ$*Ô$BˆÔ!àˆŒàœÔ4°[ÔAˆŒØ!%Ô!EˆØŒ>˜YÒ&Ð&Ý.¨t¬~Ô>ˆLØ+7¨<¸¼ÀVÑ+LÔ+LÑ(ˆ�$Ô(à×Ò˜Z¨¸eÐÑDÔDÐDØ×ÒÐ0°(·.².Ñ2BÔ2BÈuÐÑUÔUÐUÐUÐUr5   r`   ztorch.deviceÚseq_lenr(   ztorch.Tensorc                 óü   — | j         d         }t          | dd¦  «        p| j        | j        z  }d}d|t	          j        d|dt          j        ¬¦  «                             |t          j        ¬¦  «        |z  z  z  }||fS )	a¨  
        Computes the inverse frequencies according to the original RoPE implementation
        Args:
            config ([`~transformers.PreTrainedConfig`]):
                The model configuration.
            device (`torch.device`):
                The device to use for initialization of the inverse frequencies.
            seq_len (`int`, *optional*):
                The current sequence length. Unused for this type of RoPE.
        Returns:
            Tuple of (`torch.Tensor`, `float`), containing the inverse frequencies for the RoPE embeddings and the
            post-processing scaling factor applied to the computed cos/sin (unused in this type of RoPE).
        Ú
rope_thetaÚhead_dimNg      ð?r   r8   ©r;   )r`   r;   )	r[   Úgetattrr2   Únum_attention_headsr-   ÚarangeÚint64r<   rK   )rR   r`   rb   ÚbaseÚdimÚattention_factorrQ   s          r4   r\   z4Dots1RotaryEmbedding.compute_default_rope_parametersZ   sŒ   € ð& Ô% lÔ3ˆÝ�f˜j¨$Ñ/Ô/Ðc°6Ô3EÈÔIcÑ3cˆàÐð Ø•U”\ ! S¨!µ5´;Ð?Ñ?Ô?×BÒBÈ&ÕX]ÔXcÐBÑdÔdÐgjÑjÑkñ
ˆð Ð)Ð)Ð)r5   c                 óN  — | j         d d d …d f                              ¦   «                              |j        d         dd¦  «                             |j        ¦  «        }|d d …d d d …f                              ¦   «         }t          |j        j        t          ¦  «        r|j        j        dk    r|j        j        nd}t          |d¬¦  «        5  |                     ¦   «         |                     ¦   «         z   
                    dd¦  «        }t          j        ||fd¬	¦  «        }|                     ¦   «         | j        z  }|                     ¦   «         | j        z  }	d d d ¦  «         n# 1 swxY w Y   |                     |j        ¬
¦  «        |	                     |j        ¬
¦  «        fS )Nr   r9   r!   ÚmpsÚcpuF)Údevice_typeÚenabledr8   ©rl   rf   )rQ   rK   ÚexpandrF   r<   r`   Ú
isinstanceÚtypeÚstrr   Ú	transposer-   ÚcatÚcosr]   Úsinr;   )
r1   ÚxÚposition_idsÚinv_freq_expandedÚposition_ids_expandedrq   ÚfreqsÚembrz   r{   s
             r4   rC   zDots1RotaryEmbedding.forwardx   s·  € ð !œM¨$°°°°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*©N)NNN)rH   rI   rJ   r-   rL   Ú__annotations__r"   r+   Ústaticmethodr   ÚintrE   rK   r\   Úno_gradr   rC   rM   rN   s   @r4   rP   rP   G   sù   ø€ € € € € € ØŒlÐÐÑðVð V˜{ð Vð Vð Vð Vð Vð Vð  à%)Ø+/Ø"ð*ð *Ø˜dÑ"ð*à˜Ô(ð*ð �t‘ð*ð 
ˆ~˜uÐ$Ô	%ð	*ð *ð *ñ „\ð*ð: €U„]�_„_Øð<ð <ñ Ôñ „_ð<ð <ð <ð <ð <r5   rP   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   rs   )rF   r-   ry   )r|   Úx1Úx2s      r4   Úrotate_halfrŠ   ˆ   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	unsqueezerŠ   )ÚqÚkrz   r{   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   rt   Úreshape)r6   r”   ÚbatchÚnum_key_value_headsÚslenre   s         r4   Ú	repeat_kvrš   ©   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dropoutÚkwargsc                 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   )rl   r;   )ÚpÚtrainingr!   )rš   Únum_key_value_groupsr-   Úmatmulrx   r   Ú
functionalÚsoftmaxr=   r<   r;   r¢   r¦   Ú
contiguous)rœ   r�   rž   rŸ   r    r¡   r¢   r£   Ú
key_statesÚvalue_statesÚattn_weightsÚattn_outputs               r4   Úeager_attention_forwardr°   µ   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Dots1Attentionz=Multi-headed attention from 'Attention Is All You Need' paperrR   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_typesre   g      à¿T©Úbias©r'   Úsliding_attention)r*   r+   Úhasattrrµ   Ú
layer_typerR   r³   rg   r2   rh   re   r˜   r§   r¡   Úattention_dropoutÚ	is_causalr   ÚLinearÚattention_biasÚq_projÚk_projÚv_projÚo_projr%   Úrms_norm_epsÚq_normÚk_normÚsliding_window©r1   rR   r³   r3   s      €r4   r+   zDots1Attention.__init__Ò   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$\ˆÔ!Ø”} dÑ*ˆŒØ!'Ô!9ˆÔØˆŒå”iØÔ Ô :¸T¼]Ñ JÐQWÔQfð
ñ 
ô 
ˆŒõ ”iØÔ Ô :¸T¼]Ñ JÐQWÔQfð
ñ 
ô 
ˆŒõ ”iØÔ Ô :¸T¼]Ñ JÐQWÔQfð
ñ 
ô 
ˆŒõ ”iØÔ&¨¬Ñ6¸Ô8JÐQWÔQfð
ñ 
ô 
ˆŒõ # 4¤=°fÔ6IÐJÑJÔJˆŒÝ" 4¤=°fÔ6IÐJÑJÔJˆŒØ7;´ÐJ]Ò7]Ð7]˜fÔ3Ð3ÐcgˆÔÐÐr5   Nr6   Úposition_embeddingsr    Úpast_key_valuesr£   r(   c                 óz  — |j         d d…         }g |¢d‘| j        ‘R }|                      |                      |¦  «                             |¦  «        ¦  «                             dd¦  «        }|                      |                      |¦  «                             |¦  «        ¦  «                             dd¦  «        }	|                      |¦  «                             |¦  «                             dd¦  «        }
|\  }}t          ||	||¦  «        \  }}	|�| 
                    |	|
| j        ¦  «        \  }	}
t          j        | j        j        t           ¦  «        } || ||	|
|f| j        sdn| j        | j        | j        dœ|¤Ž\  }} |j        g |¢d‘R Ž                      ¦   «         }|                      |¦  «        }||fS )Nr9   r!   r8   r›   )r¢   r¡   rÇ   )rF   re   rÅ   rÀ   Úviewrx   rÆ   rÁ   rÂ   r“   Úupdater³   r   Úget_interfacerR   Ú_attn_implementationr°   r¦   r¼   r¡   rÇ   r–   r«   rÃ   )r1   r6   rÉ   r    rÊ   r£   Úinput_shapeÚhidden_shapeÚquery_statesr¬   r­   rz   r{   Úattention_interfacer¯   r®   s                   r4   rC   zDots1Attention.forwardí   sà  € ð $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"   r…   r+   r-   rL   rE   r	   r   r   rC   rM   rN   s   @r4   r²   r²   Î   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   r²   c                   ó&   ‡ — e Zd Zdˆ fd„	Zd„ Zˆ xZS )ÚDots1MLPNc                 ó   •— t          ¦   «                              ¦   «          || _        |j        | _        |€|j        n|| _        t          j        | j        | j        d¬¦  «        | _        t          j        | j        | j        d¬¦  «        | _        t          j        | j        | j        d¬¦  «        | _	        t          |j                 | _        d S ©NFr¶   )r*   r+   rR   r2   Úintermediate_sizer   r¾   Ú	gate_projÚup_projÚ	down_projr   Ú
hidden_actÚact_fn)r1   rR   rÙ   r3   s      €r4   r+   zDots1MLP.__init__  s±   ø€ Ý‰Œ×ÒÑÔÐØˆŒØ!Ô-ˆÔØ=NÐ=V Ô!9Ð!9Ð\mˆ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 r‚   )rÜ   rÞ   rÚ   rÛ   )r1   r|   rÜ   s      r4   rC   zDots1MLP.forward"  sA   € Ø—N’N 4§;¢;¨t¯~ª~¸aÑ/@Ô/@Ñ#AÔ#AÀDÇLÂLÐQRÁOÄOÑ#SÑTÔTˆ	ØÐr5   r‚   ©rH   rI   rJ   r+   rC   rM   rN   s   @r4   rÖ   rÖ     sL   ø€ € € € € ð0ð 0ð 0ð 0ð 0ð 0ðð ð ð ð ð ð r5   rÖ   c                   ó$   ‡ — e Zd Zˆ fd„Zd„ Zˆ xZS )ÚDots1TopkRouterc                 ó¶  •— t          ¦   «                              ¦   «          |j        | _        |j        | _        |j        | _        t          j	        t          j        | j        | j        ¦  «        ¦  «        | _        |j        | _        |j        | _        |j        | _        |j        | _        |                      dt          j        | j        ¦  «        ¦  «         d S )NÚe_score_correction_bias)r*   r+   Únum_experts_per_tokÚtop_kÚnum_local_expertsÚnum_expertsr2   Ú
hidden_dimr   r,   r-   Úzerosr/   Úrouted_scaling_factorÚn_groupÚ	num_groupÚ
topk_groupÚnorm_topk_probr^   ©r1   rR   r3   s     €r4   r+   zDots1TopkRouter.__init__(  s­   ø€ Ý‰Œ×ÒÑÔÐØÔ/ˆŒ
Ø!Ô3ˆÔØ Ô,ˆŒÝ”l¥5¤;¨tÔ/?ÀÄÑ#QÔ#QÑRÔRˆŒØ%+Ô%AˆÔ"ØœˆŒØ Ô+ˆŒØ$Ô3ˆÔØ×ÒÐ6½¼ÀDÔDTÑ8UÔ8UÑVÔVÐVÐVÐVr5   c                 óZ  — |                      d| j        ¦  «        }t          j        |                     t
          j        ¦  «        | j                             t
          j        ¦  «        ¦  «        }|                     ¦   «         }|| j	        z   }|                      d| j
        | j        | j
        z  ¦  «                             dd¬¦  «        d                              d¬¦  «        }t          j        || j        dd¬¦  «        d         }t          j        |¦  «        }|                     d|d¦  «         |                     d¦  «                             d| j
        | j        | j
        z  ¦  «                             d| j        ¦  «        }|                     |                     ¦   «          t-          d¦  «        ¦  «        }t          j        || j        dd¬¦  «        d         }	|                     d|	¦  «        }
| j        r|
                     dd	¬
¦  «        dz   }|
|z  }
|
| j        z  }
||
|	fS )Nr9   r8   rs   r   F)r�   rl   Úsortedr!   z-infT)rl   r:   g#B’¡œÇ;)rÌ   ré   ÚFÚlinearrv   r-   r=   r/   Úsigmoidrä   rí   rè   ÚtopkÚsumrî   Ú
zeros_likeÚscatter_r�   rt   r–   Úmasked_fillÚboolrK   ræ   Úgatherrï   rë   )r1   r6   Úrouter_logitsÚscoresÚscores_for_choiceÚgroup_scoresÚ	group_idxÚ
group_maskÚ
score_maskÚtopk_indicesÚtopk_weightsÚdenominators               r4   rC   zDots1TopkRouter.forward4  sò  € Ø%×*Ò*¨2¨t¬Ñ?Ô?ˆÝœ ×!3Ò!3µE´MÑ!BÔ!BÀDÄK×DTÒDTÕUZÔUbÑDcÔDcÑdÔdˆØ×&Ò&Ñ(Ô(ˆØ" TÔ%AÑAÐà×"Ò" 2 t¤~°tÔ7GÈ4Ì>Ñ7YÑZÔZßŠT�!˜ˆT‰_Œ_˜Qô çŠS�RˆS‰[Œ[ð 	õ
 ”J˜|¨t¬ÀBÈuÐUÑUÔUÐVWÔXˆ	ÝÔ% lÑ3Ô3ˆ
Ø×Ò˜A˜y¨!Ñ,Ô,Ð,à× Ò  Ñ$Ô$ßŠV�B˜œ¨Ô(8¸D¼NÑ(JÑKÔKßŠW�R˜Ô)Ñ*Ô*ð 	ð
 .×9Ò9¸:¿?º?Ñ;LÔ;LÐ:LÍeÐTZÉmÌmÑ\Ô\ÐÝ”zÐ"3°t´zÀrÐRWÐXÑXÔXÐYZÔ[ˆØ—}’} Q¨Ñ5Ô5ˆØÔð 	(Ø&×*Ò*¨r¸4Ð*Ñ@Ô@À5ÑHˆKØ˜KÑ'ˆLØ# dÔ&@Ñ@ˆØ˜l¨LÐ8Ð8r5   rà   rN   s   @r4   râ   râ   '  sL   ø€ € € € € ð
Wð 
Wð 
Wð 
Wð 
Wð9ð 9ð 9ð 9ð 9ð 9ð 9r5   râ   c                   ób   ‡ — e Zd ZdZˆ fd„Zdej        dej        dej        dej        fd„Zˆ xZS )ÚDots1Expertsz2Collection of expert weights stored as 3D tensors.c                 ó´  •— t          ¦   «                              ¦   «          |j        | _        |j        | _        |j        | _        t          j	        t          j        | j        d| j        z  | j        ¦  «        ¦  «        | _        t          j	        t          j        | j        | j        | j        ¦  «        ¦  «        | _        t          |j                 | _        d S )Nr8   )r*   r+   rç   rè   r2   ré   Úmoe_intermediate_sizeÚintermediate_dimr   r,   r-   ÚemptyÚgate_up_projrÜ   r   rÝ   rÞ   rð   s     €r4   r+   zDots1Experts.__init__T  s£   ø€ Ý‰Œ×ÒÑÔÐØ!Ô3ˆÔØ Ô,ˆŒØ &Ô <ˆÔÝœL­¬°TÔ5EÀqÈ4ÔK`ÑG`ÐbfÔbqÑ)rÔ)rÑsÔsˆÔÝœ¥e¤k°$Ô2BÀDÄOÐUYÔUjÑ&kÔ&kÑlÔlˆŒÝ˜VÔ.Ô/ˆŒˆˆr5   r6   Útop_k_indexÚtop_k_weightsr(   c                 ó€  — t          j        |¦  «        }t          j        ¦   «         5  t           j        j                             || j        ¬¦  «        }|                     ddd¦  «        }t          j        | 	                    d¬¦  «        d¦  «         
                    ¦   «         }d d d ¦  «         n# 1 swxY w Y   |D ]þ}|d         }|| j        k    rŒt          j        ||         ¦  «        \  }}	||	         }
t          j                             |
| j        |         ¦  «                             dd¬¦  «        \  }}|                      |¦  «        |z  }t          j                             || j        |         ¦  «        }|||	|d f         z  }|                     d|	|                     |j        ¦  «        ¦  «         Œÿ|S )N)Únum_classesr8   r!   r   )r9   éþÿÿÿrs   r9   )r-   rø   r†   r   r©   Úone_hotrè   ÚpermuteÚgreaterr÷   ÚnonzeroÚwhererô   r  ÚchunkrÞ   rÜ   Ú
index_add_r<   r;   )r1   r6   r  r  Úfinal_hidden_statesÚexpert_maskÚ
expert_hitÚ
expert_idxÚ	top_k_posÚ	token_idxÚcurrent_stateÚgateÚupÚcurrent_hidden_statess                 r4   rC   zDots1Experts.forward]  sø  € õ $Ô.¨}Ñ=Ô=ÐÝŒ]‰_Œ_ð 	Sð 	SÝœ(Ô-×5Ò5°kÈtÔO_Ð5Ñ`Ô`ˆKØ%×-Ò-¨a°°AÑ6Ô6ˆKÝœ {§¢¸8 Ñ'DÔ'DÀaÑHÔH×PÒPÑRÔRˆJð	Sð 	Sð 	Sñ 	Sô 	Sð 	Sð 	Sð 	Sð 	Sð 	Sð 	Søøøð 	Sð 	Sð 	Sð 	Sð
 %ð 
	nð 
	nˆJØ# AœˆJØ˜TÔ-Ò-Ð-ØÝ#(¤;¨{¸:Ô/FÑ#GÔ#GÑ ˆI�yØ)¨)Ô4ˆMÝ”}×+Ò+¨M¸4Ô;LÈZÔ;XÑYÔY×_Ò_Ð`aÐgiÐ_ÑjÔj‰HˆD�"Ø$(§K¢K°Ñ$5Ô$5¸Ñ$:Ð!Ý$&¤M×$8Ò$8Ð9NÐPTÔP^Ð_iÔPjÑ$kÔ$kÐ!Ø$9¸MÈ)ÐU^Ð`dÐJdÔ<eÑ$eÐ!Ø×*Ò*¨1¨iÐ9N×9QÒ9QÐReÔRkÑ9lÔ9lÑmÔmÐmÐmà"Ð"s   ¨A>B2Â2B6Â9B6)	rH   rI   rJ   rÔ   r+   r-   rL   rC   rM   rN   s   @r4   r  r  P  s€   ø€ € € € € à<Ð<ð0ð 0ð 0ð 0ð 0ð#à”|ð#ð ”\ð#ð ”|ð	#ð
 
Œð#ð #ð #ð #ð #ð #ð #ð #r5   r  c                   óL   ‡ — e Zd ZdZdefˆ fd„Zdej        dej        fd„Zˆ xZ	S )ÚDots1MoEz:
    A mixed expert module containing shared experts.
    rR   c                 óì   •— t          ¦   «                              ¦   «          || _        t          |¦  «        | _        t          |¦  «        | _        t          ||j        |j	        z  ¬¦  «        | _
        d S )N)rR   rÙ   )r*   r+   rR   r  Úexpertsrâ   r!  rÖ   r
  Ún_shared_expertsÚshared_expertsrð   s     €r4   r+   zDots1MoE.__init__}  sk   ø€ Ý‰Œ×ÒÑÔÐØˆŒÝ# FÑ+Ô+ˆŒÝ# FÑ+Ô+ˆŒ	Ý&Ø¨VÔ-IÈFÔLcÑ-cð
ñ 
ô 
ˆÔÐÐr5   r6   r(   c                 óú   — |}|j         }|                      |¦  «        \  }}}|                     d|j         d         ¦  «        } |                      |||¦  «        j        |Ž }||                      |¦  «        z   }|S )Nr9   )rF   r!  rÌ   r'  r)  )r1   r6   Ú	residualsÚ
orig_shapeÚ_r  r  s          r4   rC   zDots1MoE.forward†  s‚   € Ø!ˆ	Ø"Ô(ˆ
Ø(,¯	ª	°-Ñ(@Ô(@Ñ%ˆˆ<˜Ø%×*Ò*¨2¨}Ô/BÀ2Ô/FÑGÔGˆØT˜Ÿš ]°LÀ,ÑOÔOÔTÐV`ÐaˆØ%¨×(;Ò(;¸IÑ(FÔ(FÑFˆØÐr5   )
rH   rI   rJ   rÔ   r"   r+   r-   rL   rC   rM   rN   s   @r4   r%  r%  x  st   ø€ € € € € ðð ð
˜{ð 
ð 
ð 
ð 
ð 
ð 
ð U¤\ð °e´lð ð ð ð ð ð ð ð r5   r%  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Dots1DecoderLayerrR   r³   c                 ót  •— t          ¦   «                              ¦   «          |j        | _        t          ||¬¦  «        | _        ||j        k    rt          |¦  «        | _        nt          |¦  «        | _        t          |j        |j
        ¬¦  «        | _        t          |j        |j
        ¬¦  «        | _        d S )N)rR   r³   r¸   )r*   r+   r2   r²   Ú	self_attnÚfirst_k_dense_replacer%  ÚmlprÖ   r%   rÄ   Úinput_layernormÚpost_attention_layernormrÈ   s      €r4   r+   zDots1DecoderLayer.__init__‘  s¢   ø€ Ý‰Œ×ÒÑÔÐØ!Ô-ˆÔå'¨vÀÐKÑKÔKˆŒà˜Ô4Ò4Ð4Ý Ñ'Ô'ˆDŒHˆHå Ñ'Ô'ˆDŒHå+¨FÔ,>ÀFÔDWÐXÑXÔXˆÔÝ(4°VÔ5GÈVÔM`Ð(aÑ(aÔ(aˆÔ%Ð%Ð%r5   NFr6   r    r}   rÊ   Ú	use_cacherÉ   r£   r(   c           
      óÎ   — |}|                       |¦  «        } | j        d||||||dœ|¤Ž\  }}	||z   }|}|                      |¦  «        }|                      |¦  «        }||z   }|S )N)r6   r    r}   rÊ   r6  rÉ   © )r4  r1  r5  r3  )
r1   r6   r    r}   rÊ   r6  rÉ   r£   Úresidualr-  s
             r4   rC   zDots1DecoderLayer.forwardŸ  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"   r…   r+   r-   rL   Ú
LongTensorr	   rû   rE   r   r   rC   rM   rN   s   @r4   r/  r/  �  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 ˜$‘;ðð # 5¤<°´Ð#=Ô>ÀÑEðð Ð+Ô,ðð 
Œðð ð ð ð ð ð ð r5   r/  c                   ó�   ‡ — e Zd ZU eed<   dZdZdgZdgZdZ	dZ
dZdZdZeedœZdgZdZ ej        ¦   «         ˆ fd	„¦   «         Zˆ xZS )
ÚDots1PreTrainedModelrR   ÚmodelTr/  rÊ   )r6   Ú
attentionsrä   Nc                 ó¼  •— t          ¦   «                              |¦  «         t          |t          ¦  «        rAt	          j        |j        d| j        j        ¬¦  «         t	          j	        |j
        ¦  «         d S t          |t          ¦  «        rNt	          j        |j        d| j        j        ¬¦  «         t	          j        |j        d| j        j        ¬¦  «         d S d S )Nr›   )r?   Ústd)r*   Ú_init_weightsru   râ   ÚinitÚnormal_r/   rR   Úinitializer_rangeÚzeros_rä   r  r  rÜ   )r1   rœ   r3   s     €r4   rA  z"Dots1PreTrainedModel._init_weightsÓ  sÈ   ø€ å‰Œ×Ò˜fÑ%Ô%Ð%Ý�f�oÑ.Ô.ð 	XÝŒL˜œ¨S°d´kÔ6SÐTÑTÔTÐTÝŒK˜Ô6Ñ7Ô7Ð7Ð7Ð7Ý˜¥Ñ-Ô-ð 	XÝŒL˜Ô,°3¸D¼KÔ<YÐZÑZÔZÐZÝŒL˜Ô)°¸¼Ô9VÐWÑWÔWÐWÐWÐWð	Xð 	Xr5   )rH   rI   rJ   r"   rƒ   Úbase_model_prefixÚsupports_gradient_checkpointingÚ_no_split_modulesÚ_skip_keys_device_placementÚ_supports_flash_attnÚ_supports_sdpaÚ_supports_flex_attnÚ_can_compile_fullgraphÚ_supports_attention_backendr/  r²   Ú_can_record_outputsÚ_keep_in_fp32_modules_strictÚ"_keys_to_ignore_on_load_unexpectedr-   r†   rA  rM   rN   s   @r4   r<  r<  ¿  sÀ   ø€ € € € € € àÐÐÑØÐØ&*Ð#Ø,Ð-ÐØ#4Ð"5ÐØÐØ€NØÐà!ÐØ"&Ðà*Ø$ðð Ðð %>Ð#>Ð Ø)-Ð&à€U„]�_„_ðXð Xð Xð Xñ „_ðXð Xð Xð Xð Xr5   r<  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
Dots1ModelrR   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 r8  )r/  )Ú.0r³   rR   s     €r4   ú
<listcomp>z'Dots1Model.__init__.<locals>.<listcomp>ç  s$   ø€ ÐcÐcÐc°iÕ˜v yÑ1Ô1ÐcÐcÐcr5   r¸   ©rR   Fr¹   )r*   r+   Úpad_token_idÚpadding_idxÚ
vocab_sizer   Ú	Embeddingr2   Úembed_tokensÚ
ModuleListÚrangeÚnum_hidden_layersÚlayersr%   rÄ   ÚnormrP   Ú
rotary_embÚgradient_checkpointingrR   rµ   Úhas_sliding_layersÚ	post_initrð   s    `€r4   r+   zDots1Model.__init__à  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}   rÊ   Úinputs_embedsr6  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_embedsrX  r   r!   )r`   )rR   rh  r    rÊ   r}   Úfull_attentionr¹   )r    rÉ   r}   rÊ   r6  )Úlast_hidden_staterÊ   r8  )Ú
ValueErrorr]  r
   rR   Úget_seq_lengthr-   ri   rF   r`   r�   ru   Údictr   re  r   rc  Ú	enumeratera  r`  rµ   rb  r   )r1   rg  r    r}   rÊ   rh  r6  r£   Úpast_seen_tokensÚcausal_mask_mappingÚmask_kwargsr6   rÉ   ÚiÚdecoder_layers                  r4   rC   zDots1Model.forwardñ  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$7Ø)Ø /Ø#ðð ð ðð ˆMˆMð Ÿ	š	 -Ñ0Ô0ˆÝ&Ø+Ø/8ÐB˜O˜O¸dð
ñ 
ô 
ð 	
r5   )NNNNNN)rH   rI   rJ   r"   r+   r   r    r   r-   r:  rL   r	   ÚFloatTensorrû   r   r   r   rC   rM   rN   s   @r4   rS  rS  Þ  s  ø€ € € € € ð˜{ð ð ð ð ð ð ð"  ØØð .2Ø.2Ø04Ø(,Ø26Ø!%ð<
ð <
àÔ# dÑ*ð<
ð œ tÑ+ð<
ð Ô&¨Ñ-ð	<
ð
  ™ð<
ð Ô(¨4Ñ/ð<
ð ˜$‘;ð<
ð Ð+Ô,ð<
ð 
!ð<
ð <
ð <
ñ „^ñ „_ñ  Ôð<
ð <
ð <
ð <
ð <
r5   rS  c                   ó  ‡ — e Zd ZddiZddiZddgdgfiZˆ fd„Zee	 	 	 	 	 	 	 	 dd
e	j
        dz  de	j        dz  de	j
        dz  dedz  de	j        dz  de	j
        dz  dedz  dee	j        z  dee         defd„¦   «         ¦   «         Zˆ xZS )ÚDots1ForCausalLMzlm_head.weightzmodel.embed_tokens.weightÚlm_headÚcolwise_gather_outputr6   Úlogitsc                 óþ   •— t          ¦   «                              |¦  «         t          |¦  «        | _        |j        | _        t          j        |j        |j        d¬¦  «        | _        |  	                    ¦   «          d S rØ   )
r*   r+   rS  r=  r[  r   r¾   r2   rx  rf  rð   s     €r4   r+   zDots1ForCausalLM.__init__9  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   rg  r    r}   rÊ   rh  Úlabelsr6  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, Dots1ForCausalLM

        >>> model = Dots1ForCausalLM.from_pretrained("rednote-hilab/dots1.llm1.inst")
        >>> tokenizer = AutoTokenizer.from_pretrained("rednote-hilab/dots1.llm1.inst")

        >>> 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."
        ```)rg  r    r}   rÊ   rh  r6  N)rz  r|  r[  )Úlossrz  rÊ   r6   r>  r8  )r=  rk  ru   r…   Úslicerx  Úloss_functionrR   r[  r   rÊ   r6   r>  )r1   rg  r    r}   rÊ   rh  r|  r6  r}  r£   Úoutputsr6   Úslice_indicesrz  r  s                  r4   rC   zDots1ForCausalLM.forwardB  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_planr+   r   r   r-   r:  rL   r	   ru  rû   r…   r   r   r   rC   rM   rN   s   @r4   rw  rw  3  sK  ø€ € € € € à*Ð,GÐHÐØÐ2Ð3€HØ˜_Ð-°¨zÐ:Ð;€Hðð ð ð ð ð Øð .2Ø.2Ø04Ø(,Ø26Ø*.Ø!%Ø-.ð;
ð ;
àÔ# dÑ*ð;
ð œ tÑ+ð;
ð Ô&¨Ñ-ð	;
ð
  ™ð;
ð Ô(¨4Ñ/ð;
ð Ô  4Ñ'ð;
ð ˜$‘;ð;
ð ˜eœlÑ*ð;
ð Ð+Ô,ð;
ð 
 ð;
ð ;
ð ;
ñ „^ñ Ôð;
ð ;
ð ;
ð ;
ð ;
r5   rw  )r<  rS  rw  )r!   )r›   )IÚcollections.abcr   Útypingr   r-   Útorch.nn.functionalr   r©   ró   Ú r   rB  Úactivationsr   Úcache_utilsr	   r
   Ú
generationr   Úintegrationsr   r   r   r   Úmasking_utilsr   r   Úmodeling_flash_attention_utilsr   Úmodeling_layersr   Úmodeling_outputsr   r   Úmodeling_rope_utilsr   r   Úmodeling_utilsr   r   Úprocessing_utilsr   Úutilsr   r   r   Úutils.genericr   r   Úutils.output_capturingr    Úconfiguration_dots1r"   ÚModuler%   rP   rŠ   r“   rL   r…   rš   rK   r°   r²   rÖ   râ   r  r%  r/  r<  rS  rw  Ú__all__r8  r5   r4   ú<module>rœ     sQ  ðð( %Ð $Ð $Ð $Ð $Ð $Ø Ð Ð Ð Ð Ð à €€€Ø Ð Ð Ð Ð Ð Ð Ð Ð 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 )ðð ð ð ð ð ð ð ð ð ð ð ð SÐ RÐ RÐ RÐ RÐ RÐ RÐ RØ BÐ BÐ BÐ BÐ BÐ BØ 9Ð 9Ð 9Ð 9Ð 9Ð 9Ø OÐ OÐ OÐ OÐ OÐ OÐ OÐ OØ KÐ KÐ KÐ KÐ KÐ KÐ KÐ KØ FÐ FÐ FÐ FÐ FÐ FÐ FÐ FØ &Ð &Ð &Ð &Ð &Ð &Ø IÐ IÐ IÐ IÐ IÐ IÐ IÐ IÐ IÐ IØ GÐ GÐ GÐ GÐ GÐ GÐ GÐ GØ 5Ð 5Ð 5Ð 5Ð 5Ð 5Ø ,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 ><˜2œ9ñ ><ô ><ð ><ðB(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 ˆrŒyñ ô ð ð &9ð &9ð &9ð &9ð &9�b”iñ &9ô &9ð &9ðR ð$#ð $#ð $#ð $#ð $#�2”9ñ $#ô $#ñ Ôð$#ðNð ð ð ð ˆrŒyñ ô ð ð0,ð ,ð ,ð ,ð ,Ð2ñ ,ô ,ð ,ð^ ðXð Xð Xð Xð X˜?ñ Xô Xñ „ðXð< ðQ
ð Q
ð Q
ð Q
ð Q
Ð%ñ Q
ô Q
ñ „ðQ
ðh ðK
ð K
ð K
ð K
ð K
Ð+¨_ñ K
ô K
ñ „ðK
ð\ EÐ
DÐ
D€€€r5   