Ë
    ÜÓ^j¡R  ã                   óÈ  — 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 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&m'Z' ddl(m)Z)m*Z* ddl+m,Z, ddl-m.Z.  e'j^                  e0«      Z1 ed«       G d„ dejd                  «      «       Z3 G d„ dejd                  «      Z4d„ Z5 ed«      d=d„«       Z6 G d„ dejd                  «      Z7dejp                  d e9d!ejp                  fd"„Z:	 d>d#ejd                  d$ejp                  d%ejp                  d&ejp                  d'ejp                  dz  d(e;d)e;d*e"e$   fd+„Z< ee6«       G d,„ d-ejd                  «      «       Z= G d.„ d/e«      Z>e% G d0„ d1e «      «       Z?e% G d2„ d3e?«      «       Z@e% G d4„ d5e?e«      «       ZA G d6„ d7ee?«      ZB G d8„ d9ee?«      ZC G d:„ d;ee?«      ZDg d<¢ZEy)?é    )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_mask)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_tupleÚlogging)Úmaybe_autocastÚmerge_with_config_defaults)Úcapture_outputsé   )ÚLlamaConfigÚRMSNormc                   óh   ‡ — 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LlamaRMSNormÚepsÚreturnNc                 óŠ   •— t         ‰| �  «        t        j                  t	        j
                  |«      «      | _        || _        y)z;
        LlamaRMSNorm is equivalent to T5LayerNorm
        N)ÚsuperÚ__init__r   Ú	ParameterÚtorchÚonesÚweightÚvariance_epsilon)ÚselfÚhidden_sizer&   Ú	__class__s      €ús/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/llama/modeling_llama.pyr*   zLlamaRMSNorm.__init__6   s1   ø€ ô 	‰ÑÔÜ—l‘l¤5§:¡:¨kÓ#:Ó;ˆŒØ #ˆÕó    Úhidden_statesc                 ó"  — |j                   }|j                  t        j                  «      }|j	                  d«      j                  dd¬«      }|t        j                  || j                  z   «      z  }| j                  |j                  |«      z  S )Né   éÿÿÿÿT)Úkeepdim)	ÚdtypeÚtor,   Úfloat32ÚpowÚmeanÚrsqrtr/   r.   )r0   r5   Úinput_dtypeÚvariances       r3   ÚforwardzLlamaRMSNorm.forward>   sy   € Ø#×)Ñ)ˆØ%×(Ñ(¬¯©Ó7ˆØ ×$Ñ$ QÓ'×,Ñ,¨R¸Ð,Ó>ˆØ%¬¯©°H¸t×?TÑ?TÑ4TÓ(UÑUˆØ�{‰{˜]×-Ñ-¨kÓ:Ñ:Ð:r4   c                 ó^   — t        | j                  j                  «      › d| j                  › �S )Nz, eps=)Útupler.   Úshaper/   )r0   s    r3   Ú
extra_reprzLlamaRMSNorm.extra_reprE   s*   € Ü˜Ÿ™×)Ñ)Ó*Ð+¨6°$×2GÑ2GÐ1HÐIÐIr4   )g�íµ ÷Æ°>)
Ú__name__Ú
__module__Ú__qualname__Úfloatr*   r,   ÚTensorrB   rF   Ú__classcell__©r2   s   @r3   r%   r%   4   s7   ø„ ñ$¨ð $¸$õ $ð; U§\¡\ð ;°e·l±ló ;öJr4   r%   c                   óÄ   ‡ — e Zd ZU ej                  ed<   ddefˆ fd„Ze	 	 	 ddedz  de	d   de
dz  ded	ef   fd
„«       Z ej                  «       ed„ «       «       Zˆ xZS )ÚLlamaRotaryEmbeddingÚinv_freqNÚconfigc                 ó®  •— t         ‰| �  «        |j                  | _        |j                  | _        || _        | j
                  j                  d   | _        | j                  }| j                  dk7  rt        | j                     } || j
                  |«      \  }| _
        | j                  d|d¬«       | j                  d|j                  «       d¬«       y )NÚ	rope_typeÚdefaultrP   F)Ú
persistentÚoriginal_inv_freq)r)   r*   Úmax_position_embeddingsÚmax_seq_len_cachedÚoriginal_max_seq_lenrQ   Úrope_parametersrS   Úcompute_default_rope_parametersr   Úattention_scalingÚregister_bufferÚclone)r0   rQ   ÚdeviceÚrope_init_fnrP   r2   s        €r3   r*   zLlamaRotaryEmbedding.__init__L   s¶   ø€ Ü‰ÑÔØ"(×"@Ñ"@ˆÔØ$*×$BÑ$BˆÔ!àˆŒàŸ™×4Ñ4°[ÑAˆŒØ!%×!EÑ!EˆØ�>‰>˜YÒ&Ü.¨t¯~©~Ñ>ˆLÙ+7¸¿¹ÀVÓ+LÑ(ˆ�$Ô(à×Ñ˜Z¨¸eÐÔDØ×ÑÐ0°(·.±.Ó2BÈuÐÕUr4   r_   ztorch.deviceÚseq_lenr'   ztorch.Tensorc                 ó  — | j                   d   }t        | dd«      xs | j                  | j                  z  }d}d|t	        j
                  d|dt        j                  ¬«      j                  |t        j                  ¬«      |z  z  z  }||fS )	a¨  
        Computes the inverse frequencies according to the original RoPE implementation
        Args:
            config ([`~transformers.PreTrainedConfig`]):
                The model configuration.
            device (`torch.device`):
                The device to use for initialization of the inverse frequencies.
            seq_len (`int`, *optional*):
                The current sequence length. Unused for this type of RoPE.
        Returns:
            Tuple of (`torch.Tensor`, `float`), containing the inverse frequencies for the RoPE embeddings and the
            post-processing scaling factor applied to the computed cos/sin (unused in this type of RoPE).
        Ú
rope_thetaÚhead_dimNg      ð?r   r7   ©r:   )r_   r:   )	rZ   Úgetattrr1   Únum_attention_headsr,   ÚarangeÚint64r;   rJ   )rQ   r_   ra   ÚbaseÚdimÚattention_factorrP   s          r3   r[   z4LlamaRotaryEmbedding.compute_default_rope_parameters\   s�   € ð& ×%Ñ% lÑ3ˆÜ�f˜j¨$Ó/Òc°6×3EÑ3EÈ×IcÑIcÑ3cˆàÐð Ø”U—\‘\ ! S¨!´5·;±;Ô?×BÑBÈ&ÔX]×XcÑXcÐBÓdÐgjÑjÑkñ
ˆð Ð)Ð)Ð)r4   c                 óN  — | j                   d d d …d f   j                  «       j                  |j                  d   dd«      j	                  |j
                  «      }|d d …d d d …f   j                  «       }t        |j
                  j                  t        «      r/|j
                  j                  dk7  r|j
                  j                  nd}t        |d¬«      5  |j                  «       |j                  «       z  j                  dd«      }t        j                  ||fd¬	«      }|j                  «       | j                  z  }|j                  «       | j                  z  }	d d d «       j	                  |j                   ¬
«      	j	                  |j                   ¬
«      fS # 1 sw Y   ŒAxY w)Nr   r8   r!   ÚmpsÚcpuF)Údevice_typeÚenabledr7   ©rk   re   )rP   rJ   ÚexpandrE   r;   r_   Ú
isinstanceÚtypeÚstrr   Ú	transposer,   ÚcatÚcosr\   Úsinr:   )
r0   ÚxÚposition_idsÚinv_freq_expandedÚposition_ids_expandedrp   ÚfreqsÚembry   rz   s
             r3   rB   zLlamaRotaryEmbedding.forwardz   sR  € ð !ŸM™M¨$²°4¨-Ñ8×>Ñ>Ó@×GÑGÈ×HZÑHZÐ[\ÑH]Ð_aÐcdÓe×hÑhÐij×iqÑiqÓrÐØ ,ªQ°²a¨ZÑ 8× >Ñ >Ó @Ðä'1°!·(±(·-±-ÄÔ'EÈ!Ï(É(Ï-É-Ð[`ÒJ`�a—h‘h—m’mÐfkˆÜ¨¸UÔCñ 	5Ø&×,Ñ,Ó.Ð1F×1LÑ1LÓ1NÑN×YÑYÐZ[Ð]^Ó_ˆEÜ—)‘)˜U E˜N°Ô3ˆCØ—'‘'“)˜d×4Ñ4Ñ4ˆCØ—'‘'“)˜d×4Ñ4Ñ4ˆC÷		5ð �v‰v˜AŸG™GˆvÓ$ c§f¡f°1·7±7 fÓ&;Ð;Ð;÷	5ð 	5ús   ÃBFÆF$©N©NNN)rG   rH   rI   r,   rK   Ú__annotations__r"   r*   Ústaticmethodr   ÚintrD   rJ   r[   Úno_gradr   rB   rL   rM   s   @r3   rO   rO   I   s˜   ø… Ø�l‰lÓñV˜{õ Vð  à%)Ø+/Ø"ñ*Ø˜dÑ"ð*à˜Ñ(ð*ð �t‘ð*ð 
ˆ~˜uÐ$Ñ	%ò	*ó ð*ð: €U‡]�]ƒ_Øñ<ó ó ô<r4   rO   c                 óš   — | 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..Nr8   r7   rr   )rE   r,   rx   )r{   Úx1Úx2s      r3   Úrotate_halfrŠ   Š   sZ   € à	
ˆ3Ð"�!—'‘'˜"‘+ Ñ"Ð"Ð"Ñ	#€BØ	
ˆ3�—‘˜‘˜qÑ Ñ"Ð"Ñ	#€BÜ�9‰9�r�c˜2�Y BÔ'Ð'r4   Úrotary_pos_embc                 óž   — |j                  |«      }|j                  |«      }| |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kry   rz   Úunsqueeze_dimÚq_embedÚk_embeds          r3   Úapply_rotary_pos_embr“   ‘   sY   € ð& �-‰-˜Ó
&€CØ
�-‰-˜Ó
&€CØ�3‰wœ; q›>¨CÑ/Ñ0€GØ�3‰wœ; q›>¨CÑ/Ñ0€GØ�GÐÐr4   c                   ó$   ‡ — e Zd Zˆ fd„Zd„ Zˆ xZS )ÚLlamaMLPc                 ó  •— t         ‰| �  «        || _        |j                  | _        |j                  | _        t        j                  | j                  | j                  |j                  ¬«      | _        t        j                  | j                  | j                  |j                  ¬«      | _	        t        j                  | j                  | j                  |j                  ¬«      | _
        t        |j                     | _        y )N©Úbias)r)   r*   rQ   r1   Úintermediate_sizer   ÚLinearÚmlp_biasÚ	gate_projÚup_projÚ	down_projr   Ú
hidden_actÚact_fn©r0   rQ   r2   s     €r3   r*   zLlamaMLP.__init__¬   s¸   ø€ Ü‰ÑÔØˆŒØ!×-Ñ-ˆÔØ!'×!9Ñ!9ˆÔÜŸ™ 4×#3Ñ#3°T×5KÑ5KÐRX×RaÑRaÔbˆŒÜ—y‘y ×!1Ñ!1°4×3IÑ3IÐPV×P_ÑP_Ô`ˆŒÜŸ™ 4×#9Ñ#9¸4×;KÑ;KÐRX×RaÑRaÔbˆŒÜ˜V×.Ñ.Ñ/ˆ�r4   c                 óˆ   — | j                  | j                  | j                  |«      «      | j                  |«      z  «      }|S r�   )rž   r    rœ   r�   )r0   r{   rž   s      r3   rB   zLlamaMLP.forward¶   s6   € Ø—N‘N 4§;¡;¨t¯~©~¸aÓ/@Ó#AÀDÇLÁLÐQRÃOÑ#SÓTˆ	ØÐr4   )rG   rH   rI   r*   rB   rL   rM   s   @r3   r•   r•   «   s   ø„ ô0ör4   r•   r5   Ún_repr'   c                 óª   — | j                   \  }}}}|dk(  r| S | dd…dd…ddd…dd…f   j                  |||||«      } | j                  |||z  ||«      S )zÔ
    This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,
    num_key_value_heads, seqlen, head_dim) to (batch, num_attention_heads, seqlen, head_dim)
    r!   N)rE   rs   Úreshape)r5   r£   ÚbatchÚnum_key_value_headsÚslenrd   s         r3   Ú	repeat_kvr©   »   so   € ð
 2?×1DÑ1DÑ.€EÐ  hØ�‚zØÐØ!¢!¢Q¨ªa²Ð"2Ñ3×:Ñ:¸5ÐBUÐW\Ð^bÐdlÓm€MØ× Ñ  Ð(;¸eÑ(CÀTÈ8ÓTÐTr4   ÚmoduleÚqueryÚkeyÚvalueÚattention_maskÚscalingÚdropoutÚkwargsc                 ó  — t        || j                  «      }t        || j                  «      }	t        j                  ||j	                  dd«      «      |z  }
|�|
|z   }
t
        j                  j                  |
dt        j                  ¬«      j                  |j                  «      }
t
        j                  j                  |
|| j                  ¬«      }
t        j                  |
|	«      }|j	                  dd«      j                  «       }||
fS )Nr7   r   r8   )rk   r:   )ÚpÚtrainingr!   )r©   Únum_key_value_groupsr,   Úmatmulrw   r   Ú
functionalÚsoftmaxr<   r;   r:   r°   r´   Ú
contiguous)rª   r«   r¬   r­   r®   r¯   r°   r±   Ú
key_statesÚvalue_statesÚattn_weightsÚattn_outputs               r3   Úeager_attention_forwardr¾   Ç   sà   € ô ˜3 × ;Ñ ;Ó<€JÜ˜U F×$?Ñ$?Ó@€Lä—<‘<  z×';Ñ';¸A¸qÓ'AÓBÀWÑL€LØÐ!Ø# nÑ4ˆä—=‘=×(Ñ(¨¸2ÄUÇ]Á]Ð(ÓS×VÑVÐW\×WbÑWbÓc€LÜ—=‘=×(Ñ(¨¸È6Ï?É?Ð(Ó[€LÜ—,‘,˜|¨\Ó:€KØ×'Ñ'¨¨1Ó-×8Ñ8Ó:€Kà˜Ð$Ð$r4   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z  dej                  dz  d	e
dz  d
ee   de	ej                  ej                  f   fd„Zˆ xZS )ÚLlamaAttentionz=Multi-headed attention from 'Attention Is All You Need' paperrQ   Ú	layer_idxc                 ód  •— t         ‰| �  «        || _        || _        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                  ¬«      | _        y )Nrd   g      à¿Tr—   )r)   r*   rQ   rÁ   rf   r1   rg   rd   r§   rµ   r¯   Úattention_dropoutÚ	is_causalr   rš   Úattention_biasÚq_projÚk_projÚv_projÚo_proj©r0   rQ   rÁ   r2   s      €r3   r*   zLlamaAttention.__init__ä   sM  ø€ Ü‰ÑÔØˆŒØ"ˆŒÜ ¨
°F×4FÑ4FÈ&×JdÑJdÑ4dÓeˆŒØ$*×$>Ñ$>À&×B\ÑB\Ñ$\ˆÔ!Ø—}‘} dÑ*ˆŒØ!'×!9Ñ!9ˆÔØˆŒä—i‘iØ×Ñ × :Ñ :¸T¿]¹]Ñ JÐQW×QfÑQfô
ˆŒô —i‘iØ×Ñ × :Ñ :¸T¿]¹]Ñ JÐQW×QfÑQfô
ˆŒô —i‘iØ×Ñ × :Ñ :¸T¿]¹]Ñ JÐQW×QfÑQfô
ˆŒô —i‘iØ×&Ñ&¨¯©Ñ6¸×8JÑ8JÐQW×QfÑQfô
ˆ�r4   Nr5   Úposition_embeddingsr®   Úpast_key_valuesr±   r'   c                 ó
  — |j                   d d }g |¢d‘| j                  ‘­}| j                  |«      j                  |«      j	                  dd«      }| j                  |«      j                  |«      j	                  dd«      }	| j                  |«      j                  |«      j	                  dd«      }
|\  }}t        ||	||«      \  }}	|� |j                  |	|
| j                  «      \  }	}
t        j                  | j                  j                  t        «      } || ||	|
|f| j                  sdn| j                   | j"                  dœ|¤Ž\  }} |j$                  g |¢d‘­Ž j'                  «       }| j)                  |«      }||fS )Nr8   r!   r7   ç        )r°   r¯   )rE   rd   rÆ   Úviewrw   rÇ   rÈ   r“   ÚupdaterÁ   r   Úget_interfacerQ   Ú_attn_implementationr¾   r´   rÃ   r¯   r¥   r¹   rÉ   )r0   r5   rË   r®   rÌ   r±   Úinput_shapeÚhidden_shapeÚquery_statesrº   r»   ry   rz   Úattention_interfacer½   r¼   s                   r3   rB   zLlamaAttention.forwardû   s‘  € ð $×)Ñ)¨#¨2Ð.ˆØ8˜Ð8 bÐ8¨$¯-©-Ñ8ˆà—{‘{ =Ó1×6Ñ6°|ÓD×NÑNÈqÐRSÓTˆØ—[‘[ Ó/×4Ñ4°\ÓB×LÑLÈQÐPQÓRˆ
Ø—{‘{ =Ó1×6Ñ6°|ÓD×NÑNÈqÐRSÓTˆà&‰ˆˆSÜ#7¸ÀjÐRUÐWZÓ#[Ñ ˆ�jàÐ&Ø'6×'=Ñ'=¸jÈ,ÐX\×XfÑXfÓ'gÑ$ˆJ˜ä(?×(MÑ(MØ�K‰K×,Ñ,Ô.Eó)
Ðñ %8ØØØØØð	%
ð  $Ÿ}š}‘C°$×2HÑ2HØ—L‘Lñ	%
ð ñ	%
Ñ!ˆ�\ð *�k×)Ñ)Ð;¨;Ð;¸Ò;×FÑFÓHˆØ—k‘k +Ó.ˆØ˜LÐ(Ð(r4   r‚   )rG   rH   rI   Ú__doc__r"   r…   r*   r,   rK   rD   r   r   r   rB   rL   rM   s   @r3   rÀ   rÀ   à   s¥   ø„ áGð
˜{ð 
°sõ 
ð4 IMØ.2Ø(,ñ&)à—|‘|ð&)ð # 5§<¡<°·±Ð#=Ñ>ÀÑEð&)ð Ÿ™ tÑ+ð	&)ð
  ™ð&)ð Ð+Ñ,ð&)ð 
ˆu�|‰|˜UŸ\™\Ð)Ñ	*÷&)r4   rÀ   c                   ó  ‡ — 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LlamaDecoderLayerrQ   rÁ   c                 ó   •— t         ‰| �  «        |j                  | _        t        ||¬«      | _        t        |«      | _        t        |j                  |j                  ¬«      | _	        t        |j                  |j                  ¬«      | _
        y )N)rQ   rÁ   ©r&   )r)   r*   r1   rÀ   Ú	self_attnr•   Úmlpr%   Úrms_norm_epsÚinput_layernormÚpost_attention_layernormrÊ   s      €r3   r*   zLlamaDecoderLayer.__init__%  sl   ø€ Ü‰ÑÔØ!×-Ñ-ˆÔä'¨vÀÔKˆŒä˜FÓ#ˆŒÜ+¨F×,>Ñ,>ÀF×DWÑDWÔXˆÔÜ(4°V×5GÑ5GÈV×M`ÑM`Ô(aˆÕ%r4   Nr5   r®   r|   rÌ   Ú	use_cacherË   r±   r'   c           
      óÀ   — |}| j                  |«      } | j                  d||||||dœ|¤Ž\  }}	||z   }|}| j                  |«      }| j                  |«      }||z   }|S )N)r5   r®   r|   rÌ   rá   rË   © )rß   rÜ   rà   rÝ   )
r0   r5   r®   r|   rÌ   rá   rË   r±   ÚresidualÚ_s
             r3   rB   zLlamaDecoderLayer.forward/  s�   € ð !ˆØ×,Ñ,¨]Ó;ˆà)˜4Ÿ>™>ð 
Ø'Ø)Ø%Ø+ØØ 3ñ
ð ñ
Ñˆ�qð ! =Ñ0ˆð !ˆØ×5Ñ5°mÓDˆØŸ™ Ó/ˆØ  =Ñ0ˆØÐr4   )NNNFN)rG   rH   rI   r"   r…   r*   r,   rK   Ú
LongTensorr   ÚboolrD   r   r   rB   rL   rM   s   @r3   rÙ   rÙ   $  s¾   ø„ ðb˜{ð b°sõ bð /3Ø04Ø(,Ø!&ØHLñà—|‘|ðð Ÿ™ tÑ+ðð ×&Ñ&¨Ñ-ð	ð
  ™ðð ˜$‘;ðð # 5§<¡<°·±Ð#=Ñ>ÀÑEðð Ð+Ñ,ðð 
�‰÷r4   rÙ   c                   óJ   — 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y)ÚLlamaPreTrainedModelrQ   ÚmodelTrÙ   rÌ   )r5   Ú
attentionsN)rG   rH   rI   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_backendrÙ   rÀ   Ú_can_record_outputsrã   r4   r3   ré   ré   O  sQ   … àÓØÐØ&*Ð#Ø,Ð-ÐØ#4Ð"5ÐØÐØ€NØÐà!ÐØ"&Ðà*Ø$ñÑr4   ré   c                   óò   ‡ — 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
LlamaModelrQ   c           	      ó  •— t         ‰| �  |«       |j                  | _        |j                  | _        t        j                  |j                  |j                  | j                  «      | _        t        j                  t        |j                  «      D �cg c]  }t        ||«      ‘Œ c}«      | _        t        |j                  |j                  ¬«      | _        t#        |¬«      | _        d| _        | j)                  «        y c c}w )NrÛ   ©rQ   F)r)   r*   Úpad_token_idÚpadding_idxÚ
vocab_sizer   Ú	Embeddingr1   Úembed_tokensÚ
ModuleListÚrangeÚnum_hidden_layersrÙ   Úlayersr%   rÞ   ÚnormrO   Ú
rotary_embÚgradient_checkpointingÚ	post_initrÊ   s      €r3   r*   zLlamaModel.__init__d  sÆ   ø€ Ü‰Ñ˜Ô Ø!×.Ñ.ˆÔØ ×+Ñ+ˆŒäŸL™L¨×):Ñ):¸F×<NÑ<NÐPT×P`ÑP`ÓaˆÔÜ—m‘mÜCHÈ×IaÑIaÓCbÖc°iÔ˜v yÕ1Òcó
ˆŒô ! ×!3Ñ!3¸×9LÑ9LÔMˆŒ	Ü.°fÔ=ˆŒØ&+ˆÔ#ð 	�‰Õùò ds   ÂDNÚ	input_idsr®   r|   rÌ   Úinputs_embedsrá   r±   r'   c           
      ó<  — |d u |d uz  rt        d«      ‚|€| j                  |«      }|r|€t        | j                  ¬«      }|€V|�|j	                  «       nd}t        j                  |j                  d   |j                  ¬«      |z   }|j                  d«      }t        | j                  ||||¬«      }	|}
| j                  |
|¬«      }| j                  d | j                  j                   D ]  } ||
f|	||||dœ|¤Ž}
Œ | j                  |
«      }
t        |
|¬	«      S )
Nz:You must specify exactly one of input_ids or inputs_embedsrù   r   r!   )r_   )rQ   r  r®   rÌ   r|   )r|   )r®   rË   r|   rÌ   rá   )Úlast_hidden_staterÌ   )Ú
ValueErrorrþ   r	   rQ   Úget_seq_lengthr,   rh   rE   r_   r�   r   r  r  r  r  r   )r0   r  r®   r|   rÌ   r  rá   r±   Úpast_seen_tokensÚcausal_maskr5   rË   Údecoder_layers                r3   rB   zLlamaModel.forwardt  sL  € ð ˜Ð -°tÐ";Ò<ÜÐYÓZÐZàÐ Ø*.×*;Ñ*;¸IÓ*FˆMá˜Ð0Ü*°$·+±+Ô>ˆOàÐØCRÐC^˜×=Ñ=Ô?ÐdeÐÜ Ÿ<™<¨×(;Ñ(;¸AÑ(>À}×G[ÑG[Ô\Ð_oÑoˆLØ'×1Ñ1°!Ó4ˆLä(Ø—;‘;Ø'Ø)Ø+Ø%ô
ˆð &ˆØ"Ÿo™o¨mÈ,˜oÓWÐà!Ÿ[™[Ð)H¨4¯;©;×+HÑ+HÐIò 		ˆMÙ)Øðà*Ø$7Ø)Ø /Ø#ñð ñ‰Mð		ð Ÿ	™	 -Ó0ˆÜ&Ø+Ø+ô
ð 	
r4   )NNNNNN)rG   rH   rI   r"   r*   r   r    r   r,   ræ   rK   r   ÚFloatTensorrç   r   r   r   rB   rL   rM   s   @r3   r÷   r÷   b  sÍ   ø„ ð˜{õ ð   ØØð .2Ø.2Ø04Ø(,Ø26Ø!%ñ2
à×#Ñ# dÑ*ð2
ð Ÿ™ tÑ+ð2
ð ×&Ñ&¨Ñ-ð	2
ð
  ™ð2
ð ×(Ñ(¨4Ñ/ð2
ð ˜$‘;ð2
ð Ð+Ñ,ð2
ð 
!ò2
ó ó ó  ô2
r4   r÷   c                   óB  ‡ — 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LlamaForCausalLMzlm_head.weightzmodel.embed_tokens.weightÚlm_headÚcolwise_gather_outputr5   Úlogitsc                 óè   •— t         ‰| �  |«       t        |«      | _        |j                  | _        t        j                  |j                  |j                  d¬«      | _        | j                  «        y )NFr—   )
r)   r*   r÷   rê   rü   r   rš   r1   r  r  r¡   s     €r3   r*   zLlamaForCausalLM.__init__²  sU   ø€ Ü‰Ñ˜Ô Ü Ó'ˆŒ
Ø ×+Ñ+ˆŒÜ—y‘y ×!3Ñ!3°V×5FÑ5FÈUÔSˆŒð 	�‰Õr4   Nr  r®   r|   rÌ   r  Úlabelsrá   Úlogits_to_keepr±   r'   c	           
      óx  —  | j                   d||||||dœ|	¤Ž}
|
j                  }t        |t        «      rt	        | d«      n|}| j                  |dd…|dd…f   «      }d}|�* | j                  d||| j                  j                  dœ|	¤Ž}t        |||
j                  |
j                  |
j                  ¬«      S )aÏ  
        Example:

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

        >>> model = LlamaForCausalLM.from_pretrained("meta-llama/Llama-2-7b-hf")
        >>> tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-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  r®   r|   rÌ   r  rá   N)r  r  rü   )Úlossr  rÌ   r5   rë   rã   )rê   r
  rt   r…   Úslicer  Úloss_functionrQ   rü   r   rÌ   r5   rë   )r0   r  r®   r|   rÌ   r  r  rá   r  r±   Úoutputsr5   Úslice_indicesr  r  s                  r3   rB   zLlamaForCausalLM.forward»  sÙ   € ð> ,6¨4¯:©:ð ,
ØØ)Ø%Ø+Ø'Øñ,
ð ñ,
ˆð  ×1Ñ1ˆä8BÀ>ÔSVÔ8Wœ˜~˜o¨tÔ4Ð]kˆØ—‘˜mªA¨}ºaÐ,?Ñ@ÓAˆàˆØÐØ%�4×%Ñ%Ðp¨V¸FÈtÏ{É{×OeÑOeÑpÐioÑpˆDä%ØØØ#×3Ñ3Ø!×/Ñ/Ø×)Ñ)ô
ð 	
r4   )NNNNNNNr   )rG   rH   rI   Ú_tied_weights_keysÚ_tp_planÚ_pp_planr*   r   r   r,   ræ   rK   r   r  rç   r…   r   r   r   rB   rL   rM   s   @r3   r  r  ¬  s  ø„ à*Ð,GÐHÐØÐ2Ð3€HØ˜_Ð-°¨zÐ:Ð;€Hôð Øð .2Ø.2Ø04Ø(,Ø26Ø*.Ø!%Ø-.ñ6
à×#Ñ# dÑ*ð6
ð Ÿ™ tÑ+ð6
ð ×&Ñ&¨Ñ-ð	6
ð
  ™ð6
ð ×(Ñ(¨4Ñ/ð6
ð × Ñ  4Ñ'ð6
ð ˜$‘;ð6
ð ˜eŸl™lÑ*ð6
ð Ð+Ñ,ð6
ð 
 ò6
ó ó ô6
r4   r  c                   ó   — e Zd Zy)ÚLlamaForSequenceClassificationN©rG   rH   rI   rã   r4   r3   r#  r#  ö  ó   … r4   r#  c                   ó   — e Zd ZdZy)ÚLlamaForQuestionAnsweringÚtransformerN)rG   rH   rI   rì   rã   r4   r3   r'  r'  ù  s   „ Ø%Ñr4   r'  c                   ó   — e Zd Zy)ÚLlamaForTokenClassificationNr$  rã   r4   r3   r*  r*  ý  r%  r4   r*  )r  r÷   ré   r#  r'  r*  )r!   )rÎ   )FÚcollections.abcr   Útypingr   r,   r   Úactivationsr   Úcache_utilsr   r	   Ú
generationr
   Úintegrationsr   r   r   Úmasking_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   r   Úutils.genericr   r   Úutils.output_capturingr    Úconfiguration_llamar"   Ú
get_loggerrG   ÚloggerÚModuler%   rO   rŠ   r“   r•   rK   r…   r©   rJ   r¾   rÀ   rÙ   ré   r÷   r  r#  r'  r*  Ú__all__rã   r4   r3   ú<module>r?     s.  ðõ& %Ý ã Ý å !ß .Ý )ß fÑ fÝ /÷ó ÷÷ Lß FÝ &ß RÓ Rß GÝ 5Ý ,ð 
ˆ×	Ñ	˜HÓ	%€ñ ˜YÓ'ôJ�2—9‘9ó Jó (ðJô(><˜2Ÿ9™9ô ><òB(ñ Ð*Ó+òó ,ðô2ˆr�y‰yô ð 	U˜UŸ\™\ð 	U°#ð 	U¸%¿,¹,ó 	Uð& ñ%Ø�I‰Ið%à�<‰<ð%ð 
�‰ð%ð �<‰<ð	%ð
 —L‘L 4Ñ'ð%ð ð%ð ð%ð Ð'Ñ(ó%ñ2 Ð)Ó*ô@)�R—Y‘Yó @)ó +ð@)ôF(Ð2ô (ðV ô˜?ó ó ðð$ ôF
Ð%ó F
ó ðF
ðR ôF
Ð+¨_ó F
ó ðF
ôR bÐ%EÐG[Ô aô&Ð ;Ð=Qô &ô \Ð"?ÐAUÔ [ò�r4   