§
    ‚ŠtjýW  ã                   óÂ  — 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$m%Z% ddl&m'Z'm(Z(m)Z) ddl*m+Z+m,Z, ddl-m.Z. ddl/m0Z0  G d„ dej1        ¦  «        Z2d„ Z3 ed¦  «        d?d„¦   «         Z4dej5        de6dej5        fd„Z7	 d@d ej1        d!ej5        d"ej5        d#ej5        d$ej5        dz  d%e8d&e8d'e%e'         fd(„Z9 ee4¦  «         G d)„ d*ej1        ¦  «        ¦   «         Z: ed+¦  «         G d,„ d-ej1        ¦  «        ¦   «         Z; G d.„ d/e¦  «        Z<e( G d0„ d1e#¦  «        ¦   «         Z= G d2„ d3ej1        ¦  «        Z>e( G d4„ d5e=¦  «        ¦   «         Z?e( G d6„ d7e=e¦  «        ¦   «         Z@ G d8„ d9ee=¦  «        ZA G d:„ d;ee=¦  «        ZB G d<„ d=ee=¦  «        ZCg d>¢ZDdS )Aé    )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MinistralConfigc                   ó$   ‡ — e Zd Zˆ fd„Zd„ Zˆ xZS )ÚMinistralMLPc                 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)ÚsuperÚ__init__ÚconfigÚhidden_sizeÚintermediate_sizer   ÚLinearÚ	gate_projÚup_projÚ	down_projr   Ú
hidden_actÚact_fn©Úselfr,   Ú	__class__s     €ún/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/transformers/models/ministral/modeling_ministral.pyr+   zMinistralMLP.__init__3   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ó    c                 ó¨   — |                       |                      |                      |¦  «        ¦  «        |                      |¦  «        z  ¦  «        }|S ©N)r2   r4   r0   r1   )r6   Úxr2   s      r8   ÚforwardzMinistralMLP.forward=   sA   € Ø—N’N 4§;¢;¨t¯~ª~¸aÑ/@Ô/@Ñ#AÔ#AÀDÇLÂLÐQRÁOÄOÑ#SÑTÔTˆ	ØÐr9   )Ú__name__Ú
__module__Ú__qualname__r+   r=   Ú__classcell__©r7   s   @r8   r%   r%   2   sG   ø€ € € € € ð0ð 0ð 0ð 0ð 0ðð ð ð ð ð ð r9   r%   c                 óœ   — | dd| j         d         dz  …f         }| d| j         d         dz  d…f         }t          j        | |fd¬¦  «        S )z*Rotates half the hidden dims of the input..Néÿÿÿÿé   ©Údim)ÚshapeÚtorchÚcat)r<   Úx1Úx2s      r8   Úrotate_halfrM   B   s]   € à	
ˆ3Ð"�!”'˜"”+ Ñ"Ð"Ð"Ô	#€BØ	
ˆ3�”˜”˜qÑ Ð"Ð"Ð"Ô	#€BÝŒ9�r�c˜2�Y BÐ'Ñ'Ô'Ð'r9   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	unsqueezerM   )ÚqÚkÚcosÚsinÚunsqueeze_dimÚq_embedÚk_embeds          r8   Úapply_rotary_pos_embrX   I   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r9   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)rH   ÚexpandÚreshape)rY   rZ   ÚbatchÚnum_key_value_headsÚslenÚhead_dims         r8   Ú	repeat_kvrc   c   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Tr9   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 )NrE   r   rD   )rG   Údtype)ÚpÚtrainingr"   )rc   Únum_key_value_groupsrI   ÚmatmulÚ	transposer   Ú
functionalÚsoftmaxÚfloat32Útorn   rk   rp   Ú
contiguous)re   rf   rg   rh   ri   rj   rk   rl   Ú
key_statesÚvalue_statesÚattn_weightsÚattn_outputs               r8   Úeager_attention_forwardr}   o   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$Ð$r9   c                   óÆ   ‡ — e Zd ZdZ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MinistralAttentionz=Multi-headed attention from 'Attention Is All You Need' paperÚ	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  d¬¦  «        | _        t!          j        |j        |j        | j
        z  d¬¦  «        | _        t!          j        |j        |j        | j
        z  d¬¦  «        | _        t!          j        |j	        | j
        z  |j        d¬¦  «        | _        | j        dk    r|j        nd | _        d S )NÚlayer_typesrb   g      à¿TFr(   Úsliding_attention)r*   r+   Úhasattrr‚   Ú
layer_typer,   r€   Úgetattrr-   Únum_attention_headsrb   r`   rq   rj   Úattention_dropoutÚ	is_causalr   r/   Úq_projÚk_projÚv_projÚo_projÚsliding_window©r6   r,   r€   r7   s      €r8   r+   zMinistralAttention.__init__Œ   s^  ø€ Ý‰Œ×ÒÑÔÐÝ;BÀ6È=Ñ;YÔ;YÐc˜&Ô,¨YÔ7Ð7Ð_cˆŒØˆŒØ"ˆŒÝ ¨
°FÔ4FÈ&ÔJdÑ4dÑeÔeˆŒØ$*Ô$>À&ÔB\Ñ$\ˆÔ!Ø”} dÑ*ˆŒØ!'Ô!9ˆÔØˆŒå”i Ô 2°FÔ4NÐQUÔQ^Ñ4^ÐejÐkÑkÔkˆŒÝ”i Ô 2°FÔ4NÐQUÔQ^Ñ4^ÐejÐkÑkÔkˆŒÝ”i Ô 2°FÔ4NÐQUÔQ^Ñ4^ÐejÐkÑkÔkˆŒÝ”i Ô :¸T¼]Ñ JÈFÔL^ÐejÐkÑkÔkˆŒØ7;´ÐJ]Ò7]Ð7]˜fÔ3Ð3ÐcgˆÔÐÐr9   NrY   Úposition_embeddingsri   Úpast_key_valuesrl   r[   c                 ó.  — |j         d d…         }g |¢d‘| j        ‘R }|                      |¦  «                             |¦  «                             dd¦  «        }|                      |¦  «                             |¦  «                             dd¦  «        }	|                      |¦  «                             |¦  «                             dd¦  «        }
|\  }}t          ||	||¦  «        \  }}	|�|                     |	|
| j	        ¦  «        \  }	}
t          j        | j        j        t          ¦  «        } || ||	|
|f| j        sdn| j        | j        | j        dœ|¤Ž\  }} |j        g |¢d‘R Ž                      ¦   «         }|                      |¦  «        }||fS )NrD   r"   rE   rd   )rk   rj   rŽ   )rH   rb   rŠ   Úviewrs   r‹   rŒ   rX   Úupdater€   r   Úget_interfacer,   Ú_attn_implementationr}   rp   rˆ   rj   rŽ   r^   rx   r�   )r6   rY   r�   ri   r‘   rl   Úinput_shapeÚhidden_shapeÚquery_statesry   rz   rS   rT   Úattention_interfacer|   r{   s                   r8   r=   zMinistralAttention.forward�   sÆ  € ð $Ô)¨#¨2¨#Ô.ˆØ8˜Ð8 bÐ8¨$¬-Ð8Ð8ˆà—{’{ =Ñ1Ô1×6Ò6°|ÑDÔD×NÒNÈqÐRSÑTÔTˆØ—[’[ Ñ/Ô/×4Ò4°\ÑBÔB×LÒLÈQÐPQÑRÔRˆ
Ø—{’{ =Ñ1Ô1×6Ò6°|ÑDÔD×NÒNÈqÐRSÑTÔTˆà&‰ˆˆSÝ#7¸ÀjÐRUÐWZÑ#[Ô#[Ñ ˆ�jàÐ&Ø'6×'=Ò'=¸jÈ,ÐX\ÔXfÑ'gÔ'gÑ$ˆJ˜å(?Ô(MØŒKÔ,Õ.Eñ)
ô )
Ðð %8Ð$7ØØØØØð
%
ð  $œ}ÐH�C�C°$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(r9   r;   )r>   r?   r@   Ú__doc__Úintr+   rI   ÚTensorÚtupler   r   r   r=   rA   rB   s   @r8   r   r   ˆ   sÝ   ø€ € € € € àGÐGðh¨#ð 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 ')r9   r   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MinistralRMSNormç�íµ ÷Æ°>Úepsr[   Nc                 ó¬   •— t          ¦   «                              ¦   «          t          j        t	          j        |¦  «        ¦  «        | _        || _        dS )z?
        MinistralRMSNorm is equivalent to T5LayerNorm
        N)r*   r+   r   Ú	ParameterrI   ÚonesÚweightÚvariance_epsilon)r6   r-   r£   r7   s      €r8   r+   zMinistralRMSNorm.__init__É   sD   ø€ õ 	‰Œ×ÒÑÔÐÝ”l¥5¤:¨kÑ#:Ô#:Ñ;Ô;ˆŒØ #ˆÔÐÐr9   rY   c                 ó  — |j         }|                     t          j        ¦  «        }|                     d¦  «                             dd¬¦  «        }|t          j        || j        z   ¦  «        z  }| j        |                     |¦  «        z  S )NrE   rD   T)Úkeepdim)	rn   rw   rI   rv   ÚpowÚmeanÚrsqrtr¨   r§   )r6   rY   Úinput_dtypeÚvariances       r8   r=   zMinistralRMSNorm.forwardÑ   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:r9   c                 óH   — t          | j        j        ¦  «        › d| j        › �S )Nz, eps=)rž   r§   rH   r¨   )r6   s    r8   Ú
extra_reprzMinistralRMSNorm.extra_reprØ   s&   € Ý˜œÔ)Ñ*Ô*ÐIÐI°$Ô2GÐIÐIÐIr9   )r¢   )
r>   r?   r@   Úfloatr+   rI   r�   r=   r±   rA   rB   s   @r8   r¡   r¡   Ç   sŒ   ø€ € € € € ð$ð $¨ð $¸$ð $ð $ð $ð $ð $ð $ð; U¤\ð ;°e´lð ;ð ;ð ;ð ;ðJð Jð Jð Jð Jð Jð Jr9   r¡   c                   óÒ   ‡ — e Zd Zdedefˆ fd„Z	 	 	 	 	 ddej        dej        dz  dej        dz  d	e	dz  d
e
dz  deej        ej        f         dz  dee         dej        fd„Zˆ xZS )ÚMinistralDecoderLayerr,   r€   c                 ó4  •— t          ¦   «                              ¦   «          |j        | _        t          ||¬¦  «        | _        t          |¦  «        | _        t          |j        |j        ¬¦  «        | _	        t          |j        |j        ¬¦  «        | _
        d S )N)r,   r€   ©r£   )r*   r+   r-   r   Ú	self_attnr%   Úmlpr¡   Úrms_norm_epsÚinput_layernormÚpost_attention_layernormr�   s      €r8   r+   zMinistralDecoderLayer.__init__Ý   s„   ø€ Ý‰Œ×ÒÑÔÐØ!Ô-ˆÔå+°6ÀYÐOÑOÔOˆŒå Ñ'Ô'ˆŒÝ/°Ô0BÈÔH[Ð\Ñ\Ô\ˆÔÝ(8¸Ô9KÐQWÔQdÐ(eÑ(eÔ(eˆÔ%Ð%Ð%r9   NFrY   ri   Úposition_idsr‘   Ú	use_cacher�   rl   r[   c           
      óÎ   — |}|                       |¦  «        } | j        d||||||dœ|¤Ž\  }}	||z   }|}|                      |¦  «        }|                      |¦  «        }||z   }|S )N)rY   ri   r¼   r‘   r½   r�   © )rº   r·   r»   r¸   )
r6   rY   ri   r¼   r‘   r½   r�   rl   ÚresidualÚ_s
             r8   r=   zMinistralDecoderLayer.forwardç   s¡   € ð !ˆØ×,Ò,¨]Ñ;Ô;ˆà)˜4œ>ð 
Ø'Ø)Ø%Ø+ØØ 3ð
ð 
ð ð
ð 
Ñˆ�qð ! =Ñ0ˆð !ˆØ×5Ò5°mÑDÔDˆØŸš Ñ/Ô/ˆØ  =Ñ0ˆØÐr9   )NNNFN)r>   r?   r@   r#   rœ   r+   rI   r�   Ú
LongTensorr   Úboolrž   r   r   r=   rA   rB   s   @r8   r´   r´   Ü   sÿ   ø€ € € € € ðf˜ð f¸3ð fð fð fð fð fð fð /3Ø04Ø(,Ø!&ØHLðð à”|ðð œ tÑ+ðð Ô&¨Ñ-ð	ð
  ™ðð ˜$‘;ðð # 5¤<°´Ð#=Ô>ÀÑEðð Ð+Ô,ðð 
Œðð ð ð ð ð ð ð r9   r´   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MinistralPreTrainedModelr,   ÚmodelTr´   r‘   )rY   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_backendr´   r   Ú_can_record_outputsr¿   r9   r8   rÅ   rÅ     sl   € € € € € € àÐÐÑØÐØ&*Ð#Ø0Ð1ÐØ#4Ð"5ÐØÐØ€NØÐà!ÐØ"&Ðà.Ø(ðð ÐÐÐr9   rÅ   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MinistralRotaryEmbeddingÚinv_freqNr,   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defaultrÕ   F)Ú
persistentÚoriginal_inv_freq)r*   r+   Úmax_position_embeddingsÚmax_seq_len_cachedÚoriginal_max_seq_lenr,   Úrope_parametersr×   Úcompute_default_rope_parametersr   Úattention_scalingÚregister_bufferÚclone)r6   r,   ÚdeviceÚrope_init_fnrÕ   r7   s        €r8   r+   z!MinistralRotaryEmbedding.__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�$Ô(à×Ò˜Z¨¸eÐÑDÔDÐDØ×ÒÐ0°(·.².Ñ2BÔ2BÈuÐÑUÔUÐUÐUÐUr9   rã   ztorch.deviceÚseq_lenr[   ztorch.Tensorc                 óü   — | j         d         }t          | dd¦  «        p| j        | j        z  }d}d|t	          j        d|dt          j        ¬¦  «                             |t          j        ¬¦  «        |z  z  z  }||fS )	a¨  
        Computes the inverse frequencies according to the original RoPE implementation
        Args:
            config ([`~transformers.PreTrainedConfig`]):
                The model configuration.
            device (`torch.device`):
                The device to use for initialization of the inverse frequencies.
            seq_len (`int`, *optional*):
                The current sequence length. Unused for this type of RoPE.
        Returns:
            Tuple of (`torch.Tensor`, `float`), containing the inverse frequencies for the RoPE embeddings and the
            post-processing scaling factor applied to the computed cos/sin (unused in this type of RoPE).
        Ú
rope_thetarb   Ng      ð?r   rE   ©rn   )rã   rn   )	rÞ   r†   r-   r‡   rI   ÚarangeÚint64rw   r²   )r,   rã   rå   ÚbaserG   Úattention_factorrÕ   s          r8   rß   z8MinistralRotaryEmbedding.compute_default_rope_parameters-  sŒ   € ð& Ô% lÔ3ˆÝ�f˜j¨$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)r9   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   rD   r"   ÚmpsÚcpuF)Údevice_typeÚenabledrE   rF   rè   )rÕ   r²   r]   rH   rw   rã   Ú
isinstanceÚtypeÚstrr   rs   rI   rJ   rS   rà   rT   rn   )
r6   r<   r¼   Úinv_freq_expandedÚposition_ids_expandedrð   ÚfreqsÚembrS   rT   s
             r8   r=   z MinistralRotaryEmbedding.forwardK  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@   rI   r�   rÈ   r#   r+   Ústaticmethodr   rœ   rž   r²   rß   Úno_gradr   r=   rA   rB   s   @r8   rÔ   rÔ     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 $Ñ&ð*à˜Ô(ð*ð �t‘ð*ð 
ˆ~˜uÐ$Ô	%ð	*ð *ð *ñ „\ð*ð: €U„]�_„_Øð<ð <ñ Ôñ „_ð<ð <ð <ð <ð <r9   rÔ   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MinistralModelr,   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 r¿   )r´   )Ú.0r€   r,   s     €r8   ú
<listcomp>z+MinistralModel.__init__.<locals>.<listcomp>d  s$   ø€ ÐgÐgÐg¸)Õ" 6¨9Ñ5Ô5ÐgÐgÐgr9   r¶   ©r,   F)r*   r+   Úpad_token_idÚpadding_idxÚ
vocab_sizer   Ú	Embeddingr-   Úembed_tokensÚ
ModuleListÚrangeÚnum_hidden_layersÚlayersr¡   r¹   ÚnormrÔ   Ú
rotary_embÚgradient_checkpointingÚ	post_initr5   s    `€r8   r+   zMinistralModel.__init__]  sÔ   øø€ Ý‰Œ×Ò˜Ñ Ô Ð Ø!Ô.ˆÔØ Ô+ˆŒåœL¨Ô):¸FÔ<NÐPTÔP`ÑaÔaˆÔÝ”mØgÐgÐgÐgÅuÈVÔMeÑGfÔGfÐgÑgÔgñ
ô 
ˆŒõ % VÔ%7¸VÔ=PÐQÑQÔQˆŒ	Ý2¸&ÐAÑAÔAˆŒØ&+ˆÔ#ð 	�ŠÑÔÐÐÐr9   NÚ	input_idsri   r¼   r‘   Úinputs_embedsr½   rl   r[   c           
      óâ  — |d u |d uz  rt          d¦  «        ‚|€|                      |¦  «        }|r|€t          | j        ¬¦  «        }|€V|�|                     ¦   «         nd}t          j        |j        d         |j        ¬¦  «        |z   }| 	                    d¦  «        }t          |x}	t          ¦  «        s&| j        ||||dœ}
t          d
i |
¤Žt          d
i |
¤Ždœ}	|}|                      ||¦  «        }t          | j        d | j        j        …         ¦  «        D ]*\  }} ||f|	| j        j        |                  ||||dœ|¤Ž}Œ+|                      |¦  «        }t)          ||r|nd ¬	¦  «        S )Nz:You must specify exactly one of input_ids or inputs_embedsr  r   r"   )rã   )r,   r  ri   r‘   r¼   )Úfull_attentionrƒ   )ri   r¼   r‘   r½   r�   )Úlast_hidden_stater‘   r¿   )Ú
ValueErrorr  r	   r,   Úget_seq_lengthrI   ré   rH   rã   rP   rò   Údictr   r   r  Ú	enumerater
  r	  r‚   r  r   )r6   r  ri   r¼   r‘   r  r½   rl   Úpast_seen_tokensÚcausal_mask_mappingÚmask_kwargsrY   r�   ÚiÚdecoder_layers                  r8   r=   zMinistralModel.forwardm  sò  € ð ˜Ð -°tÐ";Ñ<ð 	[ÝÐYÑZÔZÐZàÐ Ø ×-Ò-¨iÑ8Ô8ˆMàð 	?˜Ð0Ý*°$´+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 	ð œ+Ø!.Ø"0Ø#2Ø ,ðð ˆKõ #5Ð"CÐ"C°{Ð"CÐ"CÝ%FÐ%UÐ%UÈÐ%UÐ%Uð#ð #Ðð
 &ˆØ"Ÿošo¨m¸\ÑJÔJÐå )¨$¬+Ð6U¸¼Ô8UÐ6UÔ*VÑ WÔ Wð 		ð 		ÑˆAˆ}Ø)˜MØðà2°4´;Ô3JÈ1Ô3MÔNØ)Ø /Ø#Ø$7ðð ð ðð ˆMˆMð Ÿ	š	 -Ñ0Ô0ˆÝ&Ø+Ø/8ÐB˜O˜O¸dð
ñ 
ô 
ð 	
r9   )NNNNNN)r>   r?   r@   r#   r+   r    r!   r   rI   rÂ   r�   r   ÚFloatTensorrÃ   r   r   r   r=   rA   rB   s   @r8   rü   rü   [  s  ø€ € € € € ð˜ð ð ð ð ð ð ð   ØØð .2Ø.2Ø04Ø(,Ø26Ø!%ð:
ð :
àÔ# dÑ*ð:
ð œ tÑ+ð:
ð Ô&¨Ñ-ð	:
ð
  ™ð:
ð Ô(¨4Ñ/ð:
ð ˜$‘;ð:
ð Ð+Ô,ð:
ð 
!ð:
ð :
ð :
ñ „^ñ „_ñ  Ôð:
ð :
ð :
ð :
ð :
r9   rü   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MinistralForCausalLMzlm_head.weightzmodel.embed_tokens.weightÚlm_headÚcolwise_gather_outputrY   Úlogitsc                 óþ   •— t          ¦   «                              |¦  «         t          |¦  «        | _        |j        | _        t          j        |j        |j        d¬¦  «        | _        |  	                    ¦   «          d S r'   )
r*   r+   rü   rÆ   r  r   r/   r-   r   r  r5   s     €r8   r+   zMinistralForCausalLM.__init__³  sj   ø€ Ý‰Œ×Ò˜Ñ Ô Ð Ý# FÑ+Ô+ˆŒ
Ø Ô+ˆŒÝ”y Ô!3°VÔ5FÈUÐSÑSÔSˆŒð 	�ŠÑÔÐÐÐr9   Nr   r  ri   r¼   r‘   r  Úlabelsr½   Úlogits_to_keeprl   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 )aç  
        Example:

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

        >>> model = MinistralForCausalLM.from_pretrained("meta-ministral/Ministral-2-7b-hf")
        >>> tokenizer = AutoTokenizer.from_pretrained("meta-ministral/Ministral-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  ri   r¼   r‘   r  r½   N)r"  r$  r  )Úlossr"  r‘   rY   rÇ   r¿   )rÆ   r  rò   rœ   Úslicer   Úloss_functionr,   r  r   r‘   rY   rÇ   )r6   r  ri   r¼   r‘   r  r$  r½   r%  rl   ÚoutputsrY   Úslice_indicesr"  r'  s                  r8   r=   zMinistralForCausalLM.forward¼  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 	
r9   )NNNNNNNr   )r>   r?   r@   Ú_tied_weights_keysÚ_tp_planÚ_pp_planr+   r   r   rI   rÂ   r�   r   r  rÃ   rœ   r   r   r   r=   rA   rB   s   @r8   r  r  ­  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 ˜$‘;ð6
ð ˜eœlÑ*ð6
ð Ð+Ô,ð6
ð 
 ð6
ð 6
ð 6
ñ „^ñ Ôð6
ð 6
ð 6
ð 6
ð 6
r9   r  c                   ó   — e Zd ZdS )Ú"MinistralForSequenceClassificationN©r>   r?   r@   r¿   r9   r8   r0  r0  ÷  ó   € € € € € Ø€Dr9   r0  c                   ó   — e Zd ZdS )ÚMinistralForTokenClassificationNr1  r¿   r9   r8   r4  r4  û  r2  r9   r4  c                   ó   — e Zd ZdZdS )ÚMinistralForQuestionAnsweringÚtransformerN)r>   r?   r@   rÉ   r¿   r9   r8   r6  r6  ÿ  s   € € € € € Ø%ÐÐÐr9   r6  )rÅ   rü   r  r0  r4  r6  )r"   )rd   )EÚcollections.abcr   Útypingr   rI   r   Úactivationsr   Úcache_utilsr   r	   Ú
generationr
   Úintegrationsr   r   r   Úmasking_utilsr   r   Úmodeling_flash_attention_utilsr   Úmodeling_layersr   r   r   r   Úmodeling_outputsr   r   Úmodeling_rope_utilsr   r   Úmodeling_utilsr   r   Úprocessing_utilsr   Úutilsr   r   r   Úutils.genericr   r    Úutils.output_capturingr!   Úconfiguration_ministralr#   ÚModuler%   rM   rX   r�   rœ   rc   r²   r}   r   r¡   r´   rÅ   rÔ   rü   r  r0  r4  r6  Ú__all__r¿   r9   r8   ú<module>rK     s  ðð, %Ð $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 4Ð 4Ð 4Ð 4Ð 4Ð 4ðð ð ð ð �2”9ñ ô ð ð (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;)ð ;)ð ;)ð ;)ð ;)˜œñ ;)ô ;)ñ +Ô*ð;)ð| Ð˜YÑ'Ô'ðJð Jð Jð Jð J�r”yñ Jô Jñ (Ô'ðJð((ð (ð (ð (ð (Ð6ñ (ô (ð (ðV ðð ð ð ð ˜ñ ô ñ „ðð$><ð ><ð ><ð ><ð ><˜rœyñ ><ô ><ð ><ðB ðN
ð N
ð N
ð N
ð N
Ð-ñ N
ô N
ñ „ðN
ðb ðF
ð F
ð F
ð F
ð F
Ð3°_ñ F
ô F
ñ „ðF
ðR	ð 	ð 	ð 	ð 	Ð)IÐKcñ 	ô 	ð 	ð	ð 	ð 	ð 	ð 	Ð&CÐE]ñ 	ô 	ð 	ð&ð &ð &ð &ð &Ð$?ÐAYñ &ô &ð &ðð ð €€€r9   