§
    ‚Štj'N  ã                   ó   — 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 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$m%Z%m&Z& ddl'm(Z( ddl)m*Z*  G d„ dej+        ¦  «        Z,d„ Z- ed¦  «        d4d„¦   «         Z.dej/        de0dej/        fd„Z1	 d5dej+        dej/        d ej/        d!ej/        d"ej/        dz  d#e2d$e2d%ee!         fd&„Z3 ee.¦  «         G d'„ d(ej+        ¦  «        ¦   «         Z4 G d)„ d*e¦  «        Z5e" G d+„ d,e¦  «        ¦   «         Z6 G d-„ d.ej+        ¦  «        Z7e" G d/„ d0e6¦  «        ¦   «         Z8e" G d1„ d2e6e¦  «        ¦   «         Z9g d3¢Z:dS )6é    )ÚCallable)ÚOptionalNé   )ÚACT2FN)ÚCacheÚDynamicCache)ÚGenerationMixin)Úuse_kernel_func_from_hubÚuse_kernelized_func)Úcreate_causal_mask)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Jais2Configc                   ó$   ‡ — e Zd Zˆ fd„Zd„ Zˆ xZS )ÚJais2MLPc                 ó`  •— t          ¦   «                              ¦   «          || _        |j        | _        |j        | _        t          j        | j        | j        |j        ¬¦  «        | _        t          j        | j        | j        |j        ¬¦  «        | _	        t          |j                 | _        d S )N©Úbias)ÚsuperÚ__init__ÚconfigÚhidden_sizeÚintermediate_sizeÚnnÚLinearÚmlp_biasÚup_projÚ	down_projr   Ú
hidden_actÚact_fn©Úselfr$   Ú	__class__s     €úf/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/transformers/models/jais2/modeling_jais2.pyr#   zJais2MLP.__init__-   s�   ø€ Ý‰Œ×ÒÑÔÐØˆŒØ!Ô-ˆÔØ!'Ô!9ˆÔÝ”y Ô!1°4Ô3IÐPVÔP_Ð`Ñ`Ô`ˆŒÝœ 4Ô#9¸4Ô;KÐRXÔRaÐbÑbÔbˆŒÝ˜VÔ.Ô/ˆŒˆˆó    c                 óx   — |                       |                      |                      |¦  «        ¦  «        ¦  «        S ©N)r+   r-   r*   )r/   Úxs     r1   ÚforwardzJais2MLP.forward6   s*   € Ø�~Š~˜dŸkšk¨$¯,ª,°q©/¬/Ñ:Ô:Ñ;Ô;Ð;r2   )Ú__name__Ú
__module__Ú__qualname__r#   r6   Ú__classcell__©r0   s   @r1   r   r   ,   sG   ø€ € € € € ð0ð 0ð 0ð 0ð 0ð<ð <ð <ð <ð <ð <ð <r2   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)r5   Úx1Úx2s      r1   Úrotate_halfrF   :   s]   € à	
ˆ3Ð"�!”'˜"”+ Ñ"Ð"Ð"Ô	#€BØ	
ˆ3�”˜”˜qÑ Ð"Ð"Ð"Ô	#€BÝŒ9�r�c˜2�Y BÐ'Ñ'Ô'Ð'r2   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	unsqueezerF   )ÚqÚkÚcosÚsinÚunsqueeze_dimÚq_embedÚk_embeds          r1   Úapply_rotary_pos_embrQ   A   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r2   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)rA   ÚexpandÚreshape)rR   rS   ÚbatchÚnum_key_value_headsÚslenÚhead_dims         r1   Ú	repeat_kvr\   [   s„   € ð
 2?Ô1DÑ.€EÐ  hØ�‚z€zØÐØ! ! ! ! Q Q Q¨¨a¨a¨a°°°Ð"2Ô3×:Ò:¸5ÐBUÐW\Ð^bÐdlÑmÔm€MØ× Ò  Ð(;¸eÑ(CÀTÈ8ÑTÔTÐTr2   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   )r\   Únum_key_value_groupsrB   ÚmatmulÚ	transposer'   Ú
functionalÚsoftmaxÚfloat32Útorg   rd   ri   Ú
contiguous)r^   r_   r`   ra   rb   rc   rd   re   Ú
key_statesÚvalue_statesÚattn_weightsÚattn_outputs               r1   Úeager_attention_forwardrv   g   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$Ð$r2   c                   óÎ   ‡ — 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Jais2Attentionz=Multi-headed attention from 'Attention Is All You Need' paperr$   Ú	layer_idxc                 ó®  •— t          ¦   «                              ¦   «          || _        || _        t	          |d|j        |j        z  ¦  «        | _        |j        |j        z  | _	        | j        dz  | _
        |j        | _        d| _        t          j        |j        |j        | j        z  |j        ¬¦  «        | _        t          j        |j        |j        | j        z  |j        ¬¦  «        | _        t          j        |j        |j        | j        z  |j        ¬¦  «        | _        t          j        |j        | j        z  |j        |j        ¬¦  «        | _        d S )Nr[   g      à¿Tr    )r"   r#   r$   ry   Úgetattrr%   Únum_attention_headsr[   rY   rj   rc   Úattention_dropoutÚ	is_causalr'   r(   Úattention_biasÚq_projÚk_projÚv_projÚo_proj©r/   r$   ry   r0   s      €r1   r#   zJais2Attention.__init__„   sB  ø€ Ý‰Œ×ÒÑÔÐØˆŒØ"ˆŒÝ ¨
°FÔ4FÈ&ÔJdÑ4dÑeÔeˆŒØ$*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ˆˆr2   NrR   Úposition_embeddingsrb   Úpast_key_valuesre   rT   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        dœ|¤Ž\  }} |j        g |¢d‘R Ž                      ¦   «         }|                      |¦  «        }||fS )Nr=   r   r>   r]   )rd   rc   )rA   r[   r€   Úviewrl   r�   r‚   rQ   Úupdatery   r   Úget_interfacer$   Ú_attn_implementationrv   ri   r}   rc   rW   rq   rƒ   )r/   rR   r…   rb   r†   re   Úinput_shapeÚhidden_shapeÚquery_statesrr   rs   rL   rM   Úattention_interfaceru   rt   s                   r1   r6   zJais2Attention.forward›   sÀ  € ð $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”Lð	%
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(r2   ©NNN)r7   r8   r9   Ú__doc__r   Úintr#   rB   ÚTensorÚtupler   r   r   r6   r:   r;   s   @r1   rx   rx   €   så   ø€ € € € € àGÐGð
˜{ð 
°sð 
ð 
ð 
ð 
ð 
ð 
ð4 IMØ.2Ø(,ð&)ð &)à”|ð&)ð # 5¤<°´Ð#=Ô>ÀÑEð&)ð œ tÑ+ð	&)ð
  ™ð&)ð Ð+Ô,ð&)ð 
ˆuŒ|˜Uœ\Ð)Ô	*ð&)ð &)ð &)ð &)ð &)ð &)ð &)ð &)r2   rx   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Jais2DecoderLayerr$   ry   c                 óH  •— t          ¦   «                              ¦   «          |j        | _        t          ||¬¦  «        | _        t          |¦  «        | _        t          j        |j        |j	        ¬¦  «        | _
        t          j        |j        |j	        ¬¦  «        | _        d S )N)r$   ry   ©Úeps)r"   r#   r%   rx   Ú	self_attnr   Úmlpr'   Ú	LayerNormÚlayer_norm_epsÚinput_layernormÚpost_attention_layernormr„   s      €r1   r#   zJais2DecoderLayer.__init__Å   s‡   ø€ Ý‰Œ×ÒÑÔÐØ!Ô-ˆÔå'¨vÀÐKÑKÔKˆŒå˜FÑ#Ô#ˆŒÝ!œ|¨FÔ,>ÀFÔDYÐZÑZÔZˆÔÝ(*¬°VÔ5GÈVÔMbÐ(cÑ(cÔ(cˆÔ%Ð%Ð%r2   NFrR   rb   Úposition_idsr†   Ú	use_cacher…   re   rT   c           
      óÎ   — |}|                       |¦  «        } | j        d||||||dœ|¤Ž\  }}	||z   }|}|                      |¦  «        }|                      |¦  «        }||z   }|S )N)rR   rb   r    r†   r¡   r…   © )rž   rš   rŸ   r›   )
r/   rR   rb   r    r†   r¡   r…   re   ÚresidualÚ_s
             r1   r6   zJais2DecoderLayer.forwardÏ   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r2   )NNNFN)r7   r8   r9   r   r’   r#   rB   r“   Ú
LongTensorr   Úboolr”   r   r   r6   r:   r;   s   @r1   r–   r–   Ä   sÿ   ø€ € € € € ðd˜{ð d°sð dð dð dð dð dð dð /3Ø04Ø(,Ø!&ØHLðð à”|ðð œ tÑ+ðð Ô&¨Ñ-ð	ð
  ™ðð ˜$‘;ðð # 5¤<°´Ð#=Ô>ÀÑEðð Ð+Ô,ðð 
Œðð ð ð ð ð ð ð r2   r–   c                   óL   — e Zd ZU eed<   dZdZdgZdgZdZ	dZ
dZdZdZeedœZdS )ÚJais2PreTrainedModelr$   ÚmodelTr–   r†   )rR   Ú
attentionsN)r7   r8   r9   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–   rx   Ú_can_record_outputsr£   r2   r1   r©   r©   ï   sl   € € € € € € àÐÐÑØÐØ&*Ð#Ø,Ð-ÐØ#4Ð"5ÐØÐØ€NØÐà!ÐØ"&Ðà*Ø$ðð ÐÐÐr2   r©   c                   óÔ   ‡ — e Zd ZU ej        ed<   ddefˆ fd„Ze	 	 	 ddedz  de	d         de
dz  ded	ef         fd
„¦   «         Z ej        ¦   «         ed„ ¦   «         ¦   «         Zˆ xZS )ÚJais2RotaryEmbeddingÚinv_freqNr$   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defaultr¹   F)Ú
persistentÚoriginal_inv_freq)r"   r#   Úmax_position_embeddingsÚmax_seq_len_cachedÚoriginal_max_seq_lenr$   Úrope_parametersr»   Úcompute_default_rope_parametersr   Úattention_scalingÚregister_bufferÚclone)r/   r$   ÚdeviceÚrope_init_fnr¹   r0   s        €r1   r#   zJais2RotaryEmbedding.__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�$Ô(à×Ò˜Z¨¸eÐÑDÔDÐDØ×ÒÐ0°(·.².Ñ2BÔ2BÈuÐÑUÔUÐUÐUÐUr2   rÇ   ztorch.deviceÚseq_lenrT   ztorch.Tensorc                 óü   — | j         d         }t          | dd¦  «        p| j        | j        z  }d}d|t	          j        d|dt          j        ¬¦  «                             |t          j        ¬¦  «        |z  z  z  }||fS )	a¨  
        Computes the inverse frequencies according to the original RoPE implementation
        Args:
            config ([`~transformers.PreTrainedConfig`]):
                The model configuration.
            device (`torch.device`):
                The device to use for initialization of the inverse frequencies.
            seq_len (`int`, *optional*):
                The current sequence length. Unused for this type of RoPE.
        Returns:
            Tuple of (`torch.Tensor`, `float`), containing the inverse frequencies for the RoPE embeddings and the
            post-processing scaling factor applied to the computed cos/sin (unused in this type of RoPE).
        Ú
rope_thetar[   Ng      ð?r   r>   ©rg   )rÇ   rg   )	rÂ   r{   r%   r|   rB   ÚarangeÚint64rp   Úfloat)r$   rÇ   rÉ   Úbaser@   Úattention_factorr¹   s          r1   rÃ   z4Jais2RotaryEmbedding.compute_default_rope_parameters  sŒ   € ð& Ô% lÔ3ˆÝ�f˜j¨$Ñ/Ô/Ðc°6Ô3EÈÔIcÑ3cˆàÐð Ø•U”\ ! S¨!µ5´;Ð?Ñ?Ô?×BÒBÈ&ÕX]ÔXcÐBÑdÔdÐgjÑjÑkñ
ˆð Ð)Ð)Ð)r2   c                 óN  — | j         d d d …d f                              ¦   «                              |j        d         dd¦  «                             |j        ¦  «        }|d d …d d d …f                              ¦   «         }t          |j        j        t          ¦  «        r|j        j        dk    r|j        j        nd}t          |d¬¦  «        5  |                     ¦   «         |                     ¦   «         z   
                    dd¦  «        }t          j        ||fd¬	¦  «        }|                     ¦   «         | j        z  }|                     ¦   «         | j        z  }	d d d ¦  «         n# 1 swxY w Y   |                     |j        ¬
¦  «        |	                     |j        ¬
¦  «        fS )Nr   r=   r   ÚmpsÚcpuF)Údevice_typeÚenabledr>   r?   rÌ   )r¹   rÏ   rV   rA   rp   rÇ   Ú
isinstanceÚtypeÚstrr   rl   rB   rC   rL   rÄ   rM   rg   )
r/   r5   r    Úinv_freq_expandedÚposition_ids_expandedrÕ   ÚfreqsÚembrL   rM   s
             r1   r6   zJais2RotaryEmbedding.forward3  s·  € ð !œM¨$°°°°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*r4   r�   )r7   r8   r9   rB   r“   r¬   r   r#   Ústaticmethodr   r’   r”   rÏ   rÃ   Úno_gradr   r6   r:   r;   s   @r1   r¸   r¸     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$Ô	%ð	*ð *ð *ñ „\ð*ð: €U„]�_„_Øð<ð <ñ Ôñ „_ð<ð <ð <ð <ð <r2   r¸   c                   óâ   ‡ — e Zd Zdefˆ fd„Zeee	 	 	 	 	 	 ddej	        dz  dej
        dz  dej	        dz  dedz  dej        dz  d	edz  d
ee         defd„¦   «         ¦   «         ¦   «         Zˆ xZS )Ú
Jais2Modelr$   c                 óè  •‡— t          ¦   «                              ‰¦  «         ‰j        | _        ‰j        | _        t          j        ‰j        ‰j        | j        ¦  «        | _        t          j	        ˆfd„t          ‰j        ¦  «        D ¦   «         ¦  «        | _        t          j        ‰j        ‰j        ¬¦  «        | _        t!          ‰¬¦  «        | _        d| _        |                      ¦   «          d S )Nc                 ó0   •— g | ]}t          ‰|¦  «        ‘ŒS r£   )r–   )Ú.0ry   r$   s     €r1   ú
<listcomp>z'Jais2Model.__init__.<locals>.<listcomp>L  s$   ø€ ÐcÐcÐc°iÕ˜v yÑ1Ô1ÐcÐcÐcr2   r˜   ©r$   F)r"   r#   Úpad_token_idÚpadding_idxÚ
vocab_sizer'   Ú	Embeddingr%   Úembed_tokensÚ
ModuleListÚrangeÚnum_hidden_layersÚlayersrœ   r�   Únormr¸   Ú
rotary_embÚgradient_checkpointingÚ	post_initr.   s    `€r1   r#   zJais2Model.__init__E  sÖ   øø€ Ý‰Œ×Ò˜Ñ Ô Ð Ø!Ô.ˆÔØ Ô+ˆŒåœL¨Ô):¸FÔ<NÐPTÔP`ÑaÔaˆÔÝ”mØcÐcÐcÐcÅ5ÈÔIaÑCbÔCbÐcÑcÔcñ
ô 
ˆŒõ ”L Ô!3¸Ô9NÐOÑOÔOˆŒ	Ý.°fÐ=Ñ=Ô=ˆŒØ&+ˆÔ#ð 	�ŠÑÔÐÐÐr2   NÚ	input_idsrb   r    r†   Úinputs_embedsr¡   re   rT   c           
      óH  — |d u |d uz  rt          d¦  «        ‚|€|                      |¦  «        }|r|€t          | j        ¬¦  «        }|€V|�|                     ¦   «         nd}t          j        |j        d         |j        ¬¦  «        |z   }| 	                    d¦  «        }t          | j        ||||¬¦  «        }	|}
|                      |
|¬¦  «        }| j        d | j        j        …         D ]} ||
f|	||||dœ|¤Ž}
Œ|                      |
¦  «        }
t          |
|¬	¦  «        S )
Nz:You must specify exactly one of input_ids or inputs_embedsræ   r   r   )rÇ   )r$   rõ   rb   r†   r    )r    )rb   r…   r    r†   r¡   )Úlast_hidden_stater†   )Ú
ValueErrorrë   r   r$   Úget_seq_lengthrB   rÍ   rA   rÇ   rI   r   rñ   rï   rî   rð   r   )r/   rô   rb   r    r†   rõ   r¡   re   Úpast_seen_tokensÚcausal_maskrR   r…   Údecoder_layers                r1   r6   zJais2Model.forwardU  sŠ  € ð ˜Ð -°tÐ";Ñ<ð 	[ÝÐYÑZÔZÐZàÐ Ø*.×*;Ò*;¸IÑ*FÔ*FˆMàð 	?˜Ð0Ý*°$´+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4ˆLå(Ø”;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$7Ø)Ø /Ø#ðð ð ðð ˆMˆMð Ÿ	š	 -Ñ0Ô0ˆÝ&Ø+Ø+ð
ñ 
ô 
ð 	
r2   )NNNNNN)r7   r8   r9   r   r#   r   r   r   rB   r¦   r“   r   ÚFloatTensorr§   r   r   r   r6   r:   r;   s   @r1   rá   rá   C  s  ø€ € € € € ð˜{ð ð ð ð ð ð ð   ØØð .2Ø.2Ø04Ø(,Ø26Ø!%ð2
ð 2
àÔ# dÑ*ð2
ð œ tÑ+ð2
ð Ô&¨Ñ-ð	2
ð
  ™ð2
ð Ô(¨4Ñ/ð2
ð ˜$‘;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
r2   rá   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Jais2ForCausalLMzlm_head.weightzmodel.embed_tokens.weightÚlm_headÚcolwise_gather_outputrR   Úlogitsc                 óþ   •— t          ¦   «                              |¦  «         t          |¦  «        | _        |j        | _        t          j        |j        |j        d¬¦  «        | _        |  	                    ¦   «          d S )NFr    )
r"   r#   rá   rª   ré   r'   r(   r%   r   ró   r.   s     €r1   r#   zJais2ForCausalLM.__init__“  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r2   Nr   rô   rb   r    r†   rõ   Úlabelsr¡   Úlogits_to_keepre   rT   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 )aÓ  
        Example:

        ```python
        >>> from transformers import AutoTokenizer, Jais2ForCausalLM

        >>> model = Jais2ForCausalLM.from_pretrained("inceptionai/Jais-2-8B-Chat")
        >>> tokenizer = AutoTokenizer.from_pretrained("inceptionai/Jais-2-8B-Chat")

        >>> 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."
        ```)rô   rb   r    r†   rõ   r¡   N)r  r  ré   )Úlossr  r†   rR   r«   r£   )rª   r÷   r×   r’   Úslicer   Úloss_functionr$   ré   r   r†   rR   r«   )r/   rô   rb   r    r†   rõ   r  r¡   r  re   ÚoutputsrR   Úslice_indicesr  r  s                  r1   r6   zJais2ForCausalLM.forwardœ  sô   € ð> ,6¨4¬:ð ,
ØØ)Ø%Ø+Ø'Øð,
ð ,
ð ð,
ð ,
ˆð  Ô1ˆå8BÀ>ÕSVÑ8WÔ8WÐk�˜~˜o¨tÑ4Ô4Ð4Ð]kˆØ—’˜m¨A¨A¨A¨}¸a¸a¸aÐ,?Ô@ÑAÔAˆàˆØÐØ%�4Ô%Ðp¨V¸FÈtÌ{ÔOeÐpÐpÐioÐpÐpˆDå%ØØØ#Ô3Ø!Ô/ØÔ)ð
ñ 
ô 
ð 	
r2   )NNNNNNNr   )r7   r8   r9   Ú_tied_weights_keysÚ_tp_planÚ_pp_planr#   r   r   rB   r¦   r“   r   rý   r§   r’   r   r   r   r6   r:   r;   s   @r1   rÿ   rÿ   �  sK  ø€ € € € € à*Ð,GÐHÐØÐ2Ð3€HØ˜_Ð-°¨zÐ:Ð;€Hðð ð ð ð ð Øð .2Ø.2Ø04Ø(,Ø26Ø*.Ø!%Ø-.ð6
ð 6
àÔ# dÑ*ð6
ð œ tÑ+ð6
ð Ô&¨Ñ-ð	6
ð
  ™ð6
ð Ô(¨4Ñ/ð6
ð Ô  4Ñ'ð6
ð ˜$‘;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
r2   rÿ   )rá   rÿ   r©   )r   )r]   );Úcollections.abcr   Útypingr   rB   Útorch.nnr'   Úactivationsr   Úcache_utilsr   r   Ú
generationr	   Úintegrationsr
   r   Úmasking_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_jais2r   ÚModuler   rF   rQ   r“   r’   r\   rÏ   rv   rx   r–   r©   r¸   rá   rÿ   Ú__all__r£   r2   r1   ú<module>r"     sþ  ðð, %Ð $Ð $Ð $Ð $Ð $Ø Ð Ð Ð Ð Ð à €€€Ø Ð Ð Ð Ð Ð à !Ð !Ð !Ð !Ð !Ð !Ø .Ð .Ð .Ð .Ð .Ð .Ð .Ð .Ø )Ð )Ð )Ð )Ð )Ð )Ø IÐ IÐ IÐ IÐ IÐ IÐ IÐ IØ /Ð /Ð /Ð /Ð /Ð /Ø 9Ð 9Ð 9Ð 9Ð 9Ð 9Ø OÐ OÐ OÐ OÐ OÐ OÐ OÐ OØ KÐ KÐ KÐ KÐ KÐ KÐ KÐ KØ FÐ FÐ FÐ FÐ FÐ FÐ FÐ FØ &Ð &Ð &Ð &Ð &Ð &Ø IÐ IÐ IÐ IÐ IÐ IÐ IÐ IÐ IÐ IØ GÐ GÐ GÐ GÐ GÐ GÐ GÐ GØ 5Ð 5Ð 5Ð 5Ð 5Ð 5Ø ,Ð ,Ð ,Ð ,Ð ,Ð ,ð<ð <ð <ð <ð <ˆrŒyñ <ô <ð <ð(ð (ð (ð ÐÐ*Ñ+Ô+ðð ð ñ ,Ô+ðð2	U˜Uœ\ð 	U°#ð 	U¸%¼,ð 	Uð 	Uð 	Uð 	Uð& ð%ð %ØŒIð%àŒ<ð%ð 
Œð%ð Œ<ð	%ð
 ”L 4Ñ'ð%ð ð%ð ð%ð Ð'Ô(ð%ð %ð %ð %ð2 ÐÐ)Ñ*Ô*ð@)ð @)ð @)ð @)ð @)�R”Yñ @)ô @)ñ +Ô*ð@)ðF(ð (ð (ð (ð (Ð2ñ (ô (ð (ðV ðð ð ð ð ˜?ñ ô ñ „ðð$><ð ><ð ><ð ><ð ><˜2œ9ñ ><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+¨_ñ F
ô F
ñ „ðF
ðR EÐ
DÐ
D€€€r2   