§
    ‚Štj^U  ã                   óî  — d dl mZ d dlmZ d dlZd dlmZ ddlmZ ddlm	Z	m
Z
 ddlmZ dd	lmZmZmZ dd
lmZmZ ddlmZ ddl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$m%Z% ddl&m'Z'm(Z(m)Z) ddl*m+Z+m,Z, ddl-m.Z. ddl/m0Z0 d„ Z1 ed¦  «        dCd„¦   «         Z2dej3        de4dej3        fd„Z5	 dDdej6        dej3        d ej3        d!ej3        d"ej3        dz  d#e7d$e7d%e%e'         fd&„Z8d'ej3        d(e7d)e4dej3        fd*„Z9 ee2¦  «         G d+„ d,ej6        ¦  «        ¦   «         Z: G d-„ d.ej6        ¦  «        Z; ed/¦  «         G d0„ d1ej6        ¦  «        ¦   «         Z< G d2„ d3e¦  «        Z=e( G d4„ d5e#¦  «        ¦   «         Z> G d6„ d7ej6        ¦  «        Z?e( G d8„ d9e>¦  «        ¦   «         Z@e( G d:„ d;e>e¦  «        ¦   «         ZA G d<„ d=ee>¦  «        ZB G d>„ d?ee>¦  «        ZC G d@„ dAee>¦  «        ZDg dB¢ZEdS )Eé    )ÚCallable)ÚOptionalN)Únné   )ÚACT2FN)ÚCacheÚDynamicCache)ÚGenerationMixin)Ú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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maybe_autocastÚmerge_with_config_defaults)Úcapture_outputsé   )ÚMinistral3Configc                 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..Néÿÿÿÿé   ©Údim)ÚshapeÚtorchÚcat)ÚxÚx1Úx2s      úp/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/transformers/models/ministral3/modeling_ministral3.pyÚrotate_halfr0   #   s]   € à	
ˆ3Ð"�!”'˜"”+ Ñ"Ð"Ð"Ô	#€BØ	
ˆ3�”˜”˜qÑ Ð"Ð"Ð"Ô	#€BÝŒ9�r�c˜2�Y BÐ'Ñ'Ô'Ð'ó    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	unsqueezer0   )ÚqÚkÚcosÚsinÚunsqueeze_dimÚq_embedÚk_embeds          r/   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r1   Úhidden_statesÚn_repÚreturnc                 ó¸   — | j         \  }}}}|dk    r| S | dd…dd…ddd…dd…f                              |||||¦  «        } |                      |||z  ||¦  «        S )zÔ
    This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,
    num_key_value_heads, seqlen, head_dim) to (batch, num_attention_heads, seqlen, head_dim)
    r"   N)r)   ÚexpandÚreshape)r=   r>   ÚbatchÚnum_key_value_headsÚslenÚhead_dims         r/   Ú	repeat_kvrG   D   s„   € ð
 2?Ô1DÑ.€EÐ  hØ�‚z€zØÐØ! ! ! ! Q Q Q¨¨a¨a¨a°°°Ð"2Ô3×:Ò:¸5ÐBUÐW\Ð^bÐdlÑmÔm€MØ× Ò  Ð(;¸eÑ(CÀTÈ8ÑTÔTÐTr1   ç        ÚmoduleÚqueryÚkeyÚvalueÚattention_maskÚ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 )Nr&   r   r%   )r(   Údtype)ÚpÚtrainingr"   )rG   Únum_key_value_groupsr*   ÚmatmulÚ	transposer   Ú
functionalÚsoftmaxÚfloat32ÚtorR   rO   rT   Ú
contiguous)rI   rJ   rK   rL   rM   rN   rO   rP   Ú
key_statesÚvalue_statesÚattn_weightsÚattn_outputs               r/   Úeager_attention_forwardra   P   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$Ð$r1   Úpositions_idsÚbetaÚmax_position_embeddingsc           	      ó†   — d|t          j        dt          j        | |z  ¦  «        z   ¦  «        z  z   }|d d …d d d …d f         S )Nr"   )r*   ÚlogÚfloor)rb   rc   rd   rN   s       r/   Úget_llama_4_attn_scalerh   i   sL   € Ø�$�œ 1¥u¤{°=ÐCZÑ3ZÑ'[Ô'[Ñ#[Ñ\Ô\Ñ\Ñ\€GØ�1�1�1�d˜A˜A˜A˜tÐ#Ô$Ð$r1   c                   óØ   ‡ — 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j        d
e
dz  dee         de	ej        ej        dz  f         fd„Zˆ xZS )ÚMinistral3Attentionz=Multi-headed attention from 'Attention Is All You Need' paperÚconfigÚ	layer_idxc                 óŠ  •— t          ¦   «                              ¦   «          || _        || _        t	          |dd ¦  «        p|j        |j        z  | _        |j        |j        z  | _	        | j        dz  | _
        |j        | _        d| _        t          j        |j        |j        | j        z  d¬¦  «        | _        t          j        |j        |j        | j        z  d¬¦  «        | _        t          j        |j        |j        | j        z  d¬¦  «        | _        t          j        |j        | j        z  |j        d¬¦  «        | _        d S )NrF   g      à¿TF©Úbias)ÚsuperÚ__init__rk   rl   ÚgetattrÚhidden_sizeÚnum_attention_headsrF   rD   rU   rN   Úattention_dropoutÚ	is_causalr   ÚLinearÚq_projÚk_projÚv_projÚo_proj©Úselfrk   rl   Ú	__class__s      €r/   rq   zMinistral3Attention.__init__r   s   ø€ Ý‰Œ×ÒÑÔÐØˆŒØ"ˆŒÝ ¨
°DÑ9Ô9Ðm¸VÔ=OÐSYÔSmÑ=mˆŒØ$*Ô$>À&ÔB\Ñ$\ˆÔ!Ø”} dÑ*ˆŒØ!'Ô!9ˆÔØˆŒÝ”i Ô 2°FÔ4NÐQUÔQ^Ñ4^ÐejÐkÑkÔkˆŒÝ”i Ô 2°FÔ4NÐQUÔQ^Ñ4^ÐejÐkÑkÔkˆŒÝ”i Ô 2°FÔ4NÐQUÔQ^Ñ4^ÐejÐkÑkÔkˆŒÝ”i Ô :¸T¼]Ñ JÈFÔL^ÐejÐkÑkÔkˆŒˆˆr1   Nr=   Úposition_embeddingsrM   Úposition_idsÚpast_key_valuesrP   r?   c           
      ó  — |j         d d…         }g |¢d‘| j        ‘R }|                      |¦  «                             |¦  «                             dd¦  «        }	|                      |¦  «                             |¦  «                             dd¦  «        }
|                      |¦  «                             |¦  «                             dd¦  «        }|\  }}t          |	|
||¦  «        \  }	}
|	t          || j	        j
                             d¦  «        | j	        j
                             d¦  «        ¦  «                             |	j        ¦  «        z  }	|�|                     |
|| j        ¦  «        \  }
}t!          j        | j	        j        t&          ¦  «        } || |	|
||f| j        sdn| j        | j        t/          | j	        dd ¦  «        dœ|¤Ž\  }} |j        g |¢d‘R Ž                      ¦   «         }|                      |¦  «        }||fS )	Nr%   r"   r&   Úllama_4_scaling_betaÚ original_max_position_embeddingsrH   Úsliding_window)rO   rN   r…   )r)   rF   rx   ÚviewrW   ry   rz   r<   rh   rk   Úrope_parametersÚgetr[   rR   Úupdaterl   r   Úget_interfaceÚ_attn_implementationra   rT   ru   rN   rr   rB   r\   r{   )r}   r=   r   rM   r€   r�   rP   Úinput_shapeÚhidden_shapeÚquery_statesr]   r^   r7   r8   Úattention_interfacer`   r_   s                    r/   ÚforwardzMinistral3Attention.forward€   s.  € ð $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�jØ#Õ&<ØØŒKÔ'×+Ò+Ð,BÑCÔCØŒKÔ'×+Ò+Ð,NÑOÔOñ'
ô '
÷ Š"ˆ\ÔÑ
 Ô
 ñ	!ˆð 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”LÝ" 4¤;Ð0@À$ÑGÔGð
%
ð 
%
ð ð
%
ð 
%
Ñ!ˆ�\ð *�kÔ)Ð;¨;Ð;¸Ð;Ð;Ð;×FÒFÑHÔHˆØ—k’k +Ñ.Ô.ˆØ˜LÐ(Ð(r1   ©N)Ú__name__Ú
__module__Ú__qualname__Ú__doc__r#   Úintrq   r*   ÚTensorÚtupler   r   r   r�   Ú__classcell__©r~   s   @r/   rj   rj   n   sò   ø€ € € € € àGÐGðlÐ/ð l¸Cð lð lð lð lð lð lð( )-ð-)ð -)à”|ð-)ð # 5¤<°´Ð#=Ô>ð-)ð œ tÑ+ð	-)ð
 ”lð-)ð  ™ð-)ð Ð-Ô.ð-)ð 
ˆuŒ|˜Uœ\¨DÑ0Ð0Ô	1ð-)ð -)ð -)ð -)ð -)ð -)ð -)ð -)r1   rj   c                   ó$   ‡ — e Zd Zˆ fd„Zd„ Zˆ xZS )ÚMinistral3MLPc                 ó˜  •— t          ¦   «                              ¦   «          || _        |j        | _        |j        | _        t          j        | j        | j        d¬¦  «        | _        t          j        | j        | j        d¬¦  «        | _        t          j        | j        | j        d¬¦  «        | _	        t          |j                 | _        d S ©NFrn   )rp   rq   rk   rs   Úintermediate_sizer   rw   Ú	gate_projÚup_projÚ	down_projr   Ú
hidden_actÚact_fn©r}   rk   r~   s     €r/   rq   zMinistral3MLP.__init__±   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r1   c                 ó¨   — |                       |                      |                      |¦  «        ¦  «        |                      |¦  «        z  ¦  «        }|S r‘   )r¢   r¤   r    r¡   )r}   r,   r¢   s      r/   r�   zMinistral3MLP.forward»   sA   € Ø—N’N 4§;¢;¨t¯~ª~¸aÑ/@Ô/@Ñ#AÔ#AÀDÇLÂLÐQRÁOÄOÑ#SÑTÔTˆ	ØÐr1   )r’   r“   r”   rq   r�   r™   rš   s   @r/   rœ   rœ   °   sG   ø€ € € € € ð0ð 0ð 0ð 0ð 0ðð ð ð ð ð ð r1   rœ   Ú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Ministral3RMSNormç�íµ ÷Æ°>Úepsr?   Nc                 ó¬   •— t          ¦   «                              ¦   «          t          j        t	          j        |¦  «        ¦  «        | _        || _        dS )z@
        Ministral3RMSNorm is equivalent to T5LayerNorm
        N)rp   rq   r   Ú	Parameterr*   ÚonesÚweightÚvariance_epsilon)r}   rs   r«   r~   s      €r/   rq   zMinistral3RMSNorm.__init__Â   sD   ø€ õ 	‰Œ×ÒÑÔÐÝ”l¥5¤:¨kÑ#:Ô#:Ñ;Ô;ˆŒØ #ˆÔÐÐr1   r=   c                 ó  — |j         }|                     t          j        ¦  «        }|                     d¦  «                             dd¬¦  «        }|t          j        || j        z   ¦  «        z  }| j        |                     |¦  «        z  S )Nr&   r%   T)Úkeepdim)	rR   r[   r*   rZ   ÚpowÚmeanÚrsqrtr°   r¯   )r}   r=   Úinput_dtypeÚvariances       r/   r�   zMinistral3RMSNorm.forwardÊ   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:r1   c                 óH   — t          | j        j        ¦  «        › d| j        › �S )Nz, eps=)r˜   r¯   r)   r°   )r}   s    r/   Ú
extra_reprzMinistral3RMSNorm.extra_reprÑ   s&   € Ý˜œÔ)Ñ*Ô*ÐIÐI°$Ô2GÐIÐIÐIr1   )rª   )
r’   r“   r”   Úfloatrq   r*   r—   r�   r¹   r™   rš   s   @r/   r©   r©   À   sŒ   ø€ € € € € ð$ð $¨ð $¸$ð $ð $ð $ð $ð $ð $ð; U¤\ð ;°e´lð ;ð ;ð ;ð ;ðJð Jð Jð Jð Jð Jð Jr1   r©   c                   óÒ   ‡ — e Zd Zdedefˆ fd„Z	 	 	 	 	 ddej        dej        dz  dej        dz  d	e	dz  d
e
dz  deej        ej        f         dz  dee         dej        fd„Zˆ xZS )ÚMinistral3DecoderLayerrk   rl   c                 ó4  •— t          ¦   «                              ¦   «          |j        | _        t          ||¬¦  «        | _        t          |¦  «        | _        t          |j        |j        ¬¦  «        | _	        t          |j        |j        ¬¦  «        | _
        d S )N)rk   rl   ©r«   )rp   rq   rs   rj   Ú	self_attnrœ   Úmlpr©   Úrms_norm_epsÚinput_layernormÚpost_attention_layernormr|   s      €r/   rq   zMinistral3DecoderLayer.__init__Ö   s„   ø€ Ý‰Œ×ÒÑÔÐØ!Ô-ˆÔÝ,°FÀiÐPÑPÔPˆŒÝ  Ñ(Ô(ˆŒÝ0°Ô1CÈÔI\Ð]Ñ]Ô]ˆÔÝ(9¸&Ô:LÐRXÔReÐ(fÑ(fÔ(fˆÔ%Ð%Ð%r1   NFr=   rM   r€   r�   Ú	use_cacher   rP   r?   c           
      óÎ   — |}|                       |¦  «        } | j        d||||||dœ|¤Ž\  }}	||z   }|}|                      |¦  «        }|                      |¦  «        }||z   }|S )N)r=   rM   r€   r�   rÄ   r   © )rÂ   r¿   rÃ   rÀ   )
r}   r=   rM   r€   r�   rÄ   r   rP   ÚresidualÚ_s
             r/   r�   zMinistral3DecoderLayer.forwardÞ   s¡   € ð !ˆØ×,Ò,¨]Ñ;Ô;ˆà)˜4œ>ð 
Ø'Ø)Ø%Ø+ØØ 3ð
ð 
ð ð
ð 
Ñˆ�qð ! =Ñ0ˆð !ˆØ×5Ò5°mÑDÔDˆØŸš Ñ/Ô/ˆØ  =Ñ0ˆØÐr1   )NNNFN)r’   r“   r”   r#   r–   rq   r*   r—   Ú
LongTensorr   Úboolr˜   r   r   r�   r™   rš   s   @r/   r¼   r¼   Õ   s   ø€ € € € € ðgÐ/ð g¸Cð gð gð gð gð gð gð /3Ø04Ø(,Ø!&ØHLðð à”|ðð œ tÑ+ðð Ô&¨Ñ-ð	ð
  ™ðð ˜$‘;ðð # 5¤<°´Ð#=Ô>ÀÑEðð Ð+Ô,ðð 
Œðð ð ð ð ð ð ð r1   r¼   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Ministral3PreTrainedModelrk   ÚmodelTr¼   r�   )r=   Ú
attentionsN)r’   r“   r”   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_backendr¼   rj   Ú_can_record_outputsrÆ   r1   r/   rÌ   rÌ   þ   sl   € € € € € € àÐÐÑØÐØ&*Ð#Ø1Ð2ÐØ#4Ð"5ÐØÐØ€NØÐà!ÐØ"&Ðà/Ø)ðð ÐÐÐr1   rÌ   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Ministral3RotaryEmbeddingÚinv_freqNrk   c                 ó²  •— t          ¦   «                              ¦   «          |j        | _        |j        | _        || _        | j        j        d         | _        | j        }| j        dk    rt          | j                 } || j        |¦  «        \  }| _
        |                      d|d¬¦  «         |                      d|                     ¦   «         d¬¦  «         d S )NÚ	rope_typeÚdefaultrÜ   F)Ú
persistentÚoriginal_inv_freq)rp   rq   rd   Úmax_seq_len_cachedÚoriginal_max_seq_lenrk   r‡   rÞ   Úcompute_default_rope_parametersr   Úattention_scalingÚregister_bufferÚclone)r}   rk   ÚdeviceÚrope_init_fnrÜ   r~   s        €r/   rq   z"Ministral3RotaryEmbedding.__init__  sÊ   ø€ Ý‰Œ×ÒÑÔÐØ"(Ô"@ˆÔØ$*Ô$BˆÔ!àˆŒàœÔ4°[ÔAˆŒØ!%Ô!EˆØŒ>˜YÒ&Ð&Ý.¨t¬~Ô>ˆLØ+7¨<¸¼ÀVÑ+LÔ+LÑ(ˆ�$Ô(à×Ò˜Z¨¸eÐÑDÔDÐDØ×ÒÐ0°(·.².Ñ2BÔ2BÈuÐÑUÔUÐUÐUÐUr1   rè   ztorch.deviceÚseq_lenr?   ztorch.Tensorc                 óü   — | j         d         }t          | dd¦  «        p| j        | j        z  }d}d|t	          j        d|dt          j        ¬¦  «                             |t          j        ¬¦  «        |z  z  z  }||fS )	a¨  
        Computes the inverse frequencies according to the original RoPE implementation
        Args:
            config ([`~transformers.PreTrainedConfig`]):
                The model configuration.
            device (`torch.device`):
                The device to use for initialization of the inverse frequencies.
            seq_len (`int`, *optional*):
                The current sequence length. Unused for this type of RoPE.
        Returns:
            Tuple of (`torch.Tensor`, `float`), containing the inverse frequencies for the RoPE embeddings and the
            post-processing scaling factor applied to the computed cos/sin (unused in this type of RoPE).
        Ú
rope_thetarF   Ng      ð?r   r&   ©rR   )rè   rR   )	r‡   rr   rs   rt   r*   ÚarangeÚint64r[   rº   )rk   rè   rê   Úbaser(   Úattention_factorrÜ   s          r/   rä   z9Ministral3RotaryEmbedding.compute_default_rope_parameters$  sŒ   € ð& Ô% lÔ3ˆÝ�f˜j¨$Ñ/Ô/Ðc°6Ô3EÈÔIcÑ3cˆàÐð Ø•U”\ ! S¨!µ5´;Ð?Ñ?Ô?×BÒBÈ&ÕX]ÔXcÐBÑdÔdÐgjÑjÑkñ
ˆð Ð)Ð)Ð)r1   c                 óN  — | j         d d d …d f                              ¦   «                              |j        d         dd¦  «                             |j        ¦  «        }|d d …d d d …f                              ¦   «         }t          |j        j        t          ¦  «        r|j        j        dk    r|j        j        nd}t          |d¬¦  «        5  |                     ¦   «         |                     ¦   «         z   
                    dd¦  «        }t          j        ||fd¬	¦  «        }|                     ¦   «         | j        z  }|                     ¦   «         | j        z  }	d d d ¦  «         n# 1 swxY w Y   |                     |j        ¬
¦  «        |	                     |j        ¬
¦  «        fS )Nr   r%   r"   ÚmpsÚcpuF)Údevice_typeÚenabledr&   r'   rí   )rÜ   rº   rA   r)   r[   rè   Ú
isinstanceÚtypeÚstrr   rW   r*   r+   r7   rå   r8   rR   )
r}   r,   r€   Úinv_freq_expandedÚposition_ids_expandedrõ   ÚfreqsÚembr7   r8   s
             r/   r�   z!Ministral3RotaryEmbedding.forwardB  s·  € ð !œM¨$°°°°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‘   )NNN)r’   r“   r”   r*   r—   rÏ   r#   rq   Ústaticmethodr   r–   r˜   rº   rä   Úno_gradr   r�   r™   rš   s   @r/   rÛ   rÛ     sú   ø€ € € € € € ØŒlÐÐÑðVð VÐ/ð Vð Vð Vð Vð Vð Vð  à*.Ø+/Ø"ð*ð *Ø  4Ñ'ð*à˜Ô(ð*ð �t‘ð*ð 
ˆ~˜uÐ$Ô	%ð	*ð *ð *ñ „\ð*ð: €U„]�_„_Øð<ð <ñ Ôñ „_ð<ð <ð <ð <ð <r1   rÛ   c                   óâ   ‡ — e Zd Zdefˆ fd„Zeee	 	 	 	 	 	 ddej	        dz  dej
        dz  dej	        dz  dedz  dej        dz  d	edz  d
ee         defd„¦   «         ¦   «         ¦   «         Zˆ xZS )ÚMinistral3Modelrk   c                 óÞ  •‡— t          ¦   «                              ‰¦  «         ‰j        | _        ‰j        | _        t          j        ‰j        ‰j        | j        ¦  «        | _        t          j	        ˆfd„t          ‰j        ¦  «        D ¦   «         ¦  «        | _        t          ‰j        ‰j        ¬¦  «        | _        t!          ‰¬¦  «        | _        d| _        |                      ¦   «          d S )Nc                 ó0   •— g | ]}t          ‰|¦  «        ‘ŒS rÆ   )r¼   )Ú.0rl   rk   s     €r/   ú
<listcomp>z,Ministral3Model.__init__.<locals>.<listcomp>[  s$   ø€ ÐhÐhÐh¸9Õ# F¨IÑ6Ô6ÐhÐhÐhr1   r¾   ©rk   F)rp   rq   Úpad_token_idÚpadding_idxÚ
vocab_sizer   Ú	Embeddingrs   Úembed_tokensÚ
ModuleListÚrangeÚnum_hidden_layersÚlayersr©   rÁ   ÚnormrÛ   Ú
rotary_embÚgradient_checkpointingÚ	post_initr¥   s    `€r/   rq   zMinistral3Model.__init__T  sÔ   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hÐhÐhÐhÍÈfÔNfÑHgÔHgÐhÑhÔhñ
ô 
ˆŒõ & fÔ&8¸fÔ>QÐRÑRÔRˆŒ	Ý3¸6ÐBÑBÔBˆŒØ&+ˆÔ#ð 	�ŠÑÔÐÐÐr1   NÚ	input_idsrM   r€   r�   Úinputs_embedsrÄ   rP   r?   c           
      ó|  — |d u |d uz  rt          d¦  «        ‚|€|                      |¦  «        }|r|€t          | j        ¬¦  «        }|€V|�|                     ¦   «         nd}t          j        |j        d         |j        ¬¦  «        |z   }| 	                    d¦  «        }| j        j
        €t          nt          }	 |	| j        ||||¬¦  «        }
|}|                      ||¬¦  «        }| j        d | j        j        …         D ]} ||f|
||||dœ|¤Ž}Œ|                      |¦  «        }t#          ||r|nd ¬	¦  «        S )
Nz:You must specify exactly one of input_ids or inputs_embedsr  r   r"   )rè   )rk   r  rM   r�   r€   )r€   )rM   r€   r�   rÄ   r   )Úlast_hidden_stater�   )Ú
ValueErrorr  r	   rk   Úget_seq_lengthr*   rî   r)   rè   r4   r…   r   r   r  r  r  r  r   )r}   r  rM   r€   r�   r  rÄ   rP   Úpast_seen_tokensÚmask_functionÚcausal_maskr=   r   Údecoder_layers                 r/   r�   zMinistral3Model.forwardd  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4ˆLà.2¬kÔ.HÐ.PÕ*Ð*ÕVwˆØ#�mØ”;Ø'Ø)Ø+Ø%ð
ñ 
ô 
ˆð &ˆØ"Ÿošo¨mÈ,˜oÑWÔWÐà!œ[Ð)H¨4¬;Ô+HÐ)HÔIð 		ð 		ˆMØ)˜MØðà*Ø)Ø /Ø#Ø$7ðð ð ðð ˆMˆMð Ÿ	š	 -Ñ0Ô0ˆÝ&Ø+Ø/8ÐB˜O˜O¸dð
ñ 
ô 
ð 	
r1   )NNNNNN)r’   r“   r”   r#   rq   r    r!   r   r*   rÉ   r—   r   ÚFloatTensorrÊ   r   r   r   r�   r™   rš   s   @r/   r  r  R  s  ø€ € € € € ðÐ/ð ð ð ð ð ð ð   ØØð .2Ø.2Ø04Ø(,Ø26Ø!%ð2
ð 2
àÔ# dÑ*ð2
ð œ tÑ+ð2
ð Ô&¨Ñ-ð	2
ð
  ™ð2
ð Ô(¨4Ñ/ð2
ð ˜$‘;ð2
ð Ð+Ô,ð2
ð 
!ð2
ð 2
ð 2
ñ „^ñ „_ñ  Ôð2
ð 2
ð 2
ð 2
ð 2
r1   r  c                   ó  ‡ — e Zd ZddiZddiZddgdgfiZˆ fd„Zee	 	 	 	 	 	 	 	 dd
e	j
        dz  de	j        dz  de	j
        dz  dedz  de	j        dz  de	j
        dz  dedz  dee	j        z  dee         defd„¦   «         ¦   «         Zˆ xZS )ÚMinistral3ForCausalLMzlm_head.weightzmodel.embed_tokens.weightÚlm_headÚcolwise_gather_outputr=   Úlogitsc                 óþ   •— t          ¦   «                              |¦  «         t          |¦  «        | _        |j        | _        t          j        |j        |j        d¬¦  «        | _        |  	                    ¦   «          d S rž   )
rp   rq   r  rÍ   r	  r   rw   rs   r!  r  r¥   s     €r/   rq   zMinistral3ForCausalLM.__init__¢  sj   ø€ Ý‰Œ×Ò˜Ñ Ô Ð Ý$ VÑ,Ô,ˆŒ
Ø Ô+ˆŒÝ”y Ô!3°VÔ5FÈUÐSÑSÔSˆŒð 	�ŠÑÔÐÐÐr1   Nr   r  rM   r€   r�   r  ÚlabelsrÄ   Úlogits_to_keeprP   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 )aí  
        Example:

        ```python
        >>> from transformers import AutoTokenizer, Ministral3ForCausalLM

        >>> model = Ministral3ForCausalLM.from_pretrained("meta-ministral3/Ministral3-2-7b-hf")
        >>> tokenizer = AutoTokenizer.from_pretrained("meta-ministral3/Ministral3-2-7b-hf")

        >>> 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  rM   r€   r�   r  rÄ   N)r#  r%  r	  )Úlossr#  r�   r=   rÎ   rÆ   )rÍ   r  r÷   r–   Úslicer!  Úloss_functionrk   r	  r   r�   r=   rÎ   )r}   r  rM   r€   r�   r  r%  rÄ   r&  rP   Úoutputsr=   Úslice_indicesr#  r(  s                  r/   r�   zMinistral3ForCausalLM.forward«  sô   € 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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 	
r1   )NNNNNNNr   )r’   r“   r”   Ú_tied_weights_keysÚ_tp_planÚ_pp_planrq   r   r   r*   rÉ   r—   r   r  rÊ   r–   r   r   r   r�   r™   rš   s   @r/   r   r   œ  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6
ð 6
àÔ# dÑ*ð6
ð œ tÑ+ð6
ð Ô&¨Ñ-ð	6
ð
  ™ð6
ð Ô(¨4Ñ/ð6
ð Ô  4Ñ'ð6
ð ˜$‘;ð6
ð ˜eœlÑ*ð6
ð Ð+Ô,ð6
ð 
 ð6
ð 6
ð 6
ñ „^ñ Ôð6
ð 6
ð 6
ð 6
ð 6
r1   r   c                   ó   — e Zd ZdS )Ú Ministral3ForTokenClassificationN©r’   r“   r”   rÆ   r1   r/   r1  r1  æ  ó   € € € € € Ø€Dr1   r1  c                   ó   — e Zd ZdS )Ú#Ministral3ForSequenceClassificationNr2  rÆ   r1   r/   r5  r5  ê  r3  r1   r5  c                   ó   — e Zd ZdS )ÚMinistral3ForQuestionAnsweringNr2  rÆ   r1   r/   r7  r7  î  r3  r1   r7  )r   r7  r  rÌ   r5  r1  )r"   )rH   )FÚcollections.abcr   Útypingr   r*   r   Úactivationsr   Úcache_utilsr   r	   Ú
generationr
   Úintegrationsr   r   r   Úmasking_utilsr   r   Úmodeling_flash_attention_utilsr   Úmodeling_layersr   r   r   r   Úmodeling_outputsr   r   Úmodeling_rope_utilsr   r   Úmodeling_utilsr   r   Úprocessing_utilsr   Úutilsr   r   r   Úutils.genericr   r    Úutils.output_capturingr!   Úconfiguration_ministral3r#   r0   r<   r—   r–   rG   ÚModulerº   ra   rh   rj   rœ   r©   r¼   rÌ   rÛ   r  r   r1  r5  r7  Ú__all__rÆ   r1   r/   ú<module>rK     sQ  ðð %Ð $Ð $Ð $Ð $Ð $Ø Ð Ð Ð Ð Ð à €€€Ø Ð Ð Ð Ð Ð à !Ð !Ð !Ð !Ð !Ð !Ø .Ð .Ð .Ð .Ð .Ð .Ð .Ð .Ø )Ð )Ð )Ð )Ð )Ð )Ø fÐ fÐ fÐ fÐ fÐ fÐ fÐ fÐ fÐ fØ 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 GÐ GÐ GÐ GÐ GÐ GÐ GÐ GØ 5Ð 5Ð 5Ð 5Ð 5Ð 5Ø 6Ð 6Ð 6Ð 6Ð 6Ð 6ð(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 %¸eð %Ð^að %ÐfkÔfrð %ð %ð %ð %ð
 ÐÐ)Ñ*Ô*ð>)ð >)ð >)ð >)ð >)˜"œ)ñ >)ô >)ñ +Ô*ð>)ðBð ð ð ð �B”Iñ ô ð ð  Ð˜YÑ'Ô'ðJð Jð Jð Jð J˜œ	ñ Jô Jñ (Ô'ðJð(&ð &ð &ð &ð &Ð7ñ &ô &ð &ðR ðð ð ð ð  ñ ô ñ „ðð$><ð ><ð ><ð ><ð >< ¤	ñ ><ô ><ð ><ðB ðF
ð F
ð F
ð F
ð F
Ð/ñ F
ô F
ñ „ðF
ðR ðF
ð F
ð F
ð F
ð F
Ð5°ñ F
ô F
ñ „ðF
ðR	ð 	ð 	ð 	ð 	Ð'DÐF_ñ 	ô 	ð 	ð	ð 	ð 	ð 	ð 	Ð*JÐLeñ 	ô 	ð 	ð	ð 	ð 	ð 	ð 	Ð%@ÐB[ñ 	ô 	ð 	ðð ð €€€r1   