Ë
    ÛÓ^j'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$m%Z%m&Z& ddl'm(Z( ddl)m*Z*  G d„ dejV                  «      Z,d„ Z- ed«      d3d„«       Z.dej^                  de0dej^                  fd„Z1	 d4dejV                  dej^                  dej^                  d ej^                  d!ej^                  dz  d"e2d#e2d$ee!   fd%„Z3 ee.«       G d&„ d'ejV                  «      «       Z4 G d(„ d)e«      Z5e" G d*„ d+e«      «       Z6 G d,„ d-ejV                  «      Z7e" G d.„ d/e6«      «       Z8e" G d0„ d1e6e«      «       Z9g d2¢Z:y)5é    )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$   ‡ — e Zd Zˆ fd„Zd„ Zˆ xZS )ÚJais2MLPc                 ó�  •— t         ‰| �  «        || _        |j                  | _        |j                  | _        t        j                  | j                  | j                  |j                  ¬«      | _        t        j                  | j                  | j                  |j                  ¬«      | _	        t        |j                     | _        y )N©Úbias)ÚsuperÚ__init__ÚconfigÚhidden_sizeÚintermediate_sizeÚnnÚLinearÚmlp_biasÚup_projÚ	down_projr   Ú
hidden_actÚact_fn©Úselfr$   Ú	__class__s     €ús/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/jais2/modeling_jais2.pyr#   zJais2MLP.__init__-   s‘   ø€ Ü‰ÑÔØˆŒØ!×-Ñ-ˆÔØ!'×!9Ñ!9ˆÔ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�ó    c                 ó`   — | j                  | j                  | j                  |«      «      «      S ©N)r+   r-   r*   )r/   Úxs     r1   ÚforwardzJais2MLP.forward6   s"   € Ø�~‰~˜dŸk™k¨$¯,©,°q«/Ó:Ó;Ð;r2   )Ú__name__Ú
__module__Ú__qualname__r#   r6   Ú__classcell__©r0   s   @r1   r   r   ,   s   ø„ ô0ö<r2   r   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..Néÿÿÿÿé   ©Údim)ÚshapeÚtorchÚcat)r5   Úx1Úx2s      r1   Úrotate_halfrF   :   sZ   € à	
ˆ3Ð"�!—'‘'˜"‘+ Ñ"Ð"Ð"Ñ	#€BØ	
ˆ3�—‘˜‘˜qÑ Ñ"Ð"Ñ	#€BÜ�9‰9�r�c˜2�Y BÔ'Ð'r2   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	unsqueezerF   )ÚqÚkÚcosÚsinÚunsqueeze_dimÚq_embedÚk_embeds          r1   Úapply_rotary_pos_embrQ   A   sY   € ð& �-‰-˜Ó
&€CØ
�-‰-˜Ó
&€CØ�3‰wœ; q›>¨CÑ/Ñ0€GØ�3‰wœ; q›>¨CÑ/Ñ0€GØ�GÐÐr2   Úhidden_statesÚn_repÚreturnc                 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)rA   ÚexpandÚreshape)rR   rS   ÚbatchÚnum_key_value_headsÚslenÚhead_dims         r1   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Tr2   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 )Nr>   r   r=   )r@   Údtype)ÚpÚtrainingr   )r\   Únum_key_value_groupsrB   ÚmatmulÚ	transposer'   Ú
functionalÚsoftmaxÚfloat32Útorf   rc   rh   Ú
contiguous)r]   r^   r_   r`   ra   rb   rc   rd   Ú
key_statesÚvalue_statesÚattn_weightsÚattn_outputs               r1   Úeager_attention_forwardru   g   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$Ð$r2   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Jais2Attentionz=Multi-headed attention from 'Attention Is All You Need' paperr$   Ú	layer_idxc                 ód  •— t         ‰| �  «        || _        || _        t	        |d|j
                  |j                  z  «      | _        |j                  |j                  z  | _	        | j                  dz  | _
        |j                  | _        d| _        t        j                  |j
                  |j                  | j                  z  |j                  ¬«      | _        t        j                  |j
                  |j                  | j                  z  |j                  ¬«      | _        t        j                  |j
                  |j                  | j                  z  |j                  ¬«      | _        t        j                  |j                  | j                  z  |j
                  |j                  ¬«      | _        y )Nr[   g      à¿Tr    )r"   r#   r$   rx   Úgetattrr%   Únum_attention_headsr[   rY   ri   rb   Úattention_dropoutÚ	is_causalr'   r(   Úattention_biasÚq_projÚk_projÚv_projÚo_proj©r/   r$   rx   r0   s      €r1   r#   zJais2Attention.__init__„   sM  ø€ Ü‰ÑÔØˆŒØ"ˆŒÜ ¨
°F×4FÑ4FÈ&×JdÑJdÑ4dÓeˆŒØ$*×$>Ñ$>À&×B\ÑB\Ñ$\ˆÔ!Ø—}‘} dÑ*ˆŒØ!'×!9Ñ!9ˆÔØˆŒä—i‘iØ×Ñ × :Ñ :¸T¿]¹]Ñ JÐQW×QfÑQfô
ˆŒô —i‘iØ×Ñ × :Ñ :¸T¿]¹]Ñ JÐQW×QfÑQfô
ˆŒô —i‘iØ×Ñ × :Ñ :¸T¿]¹]Ñ JÐQW×QfÑQfô
ˆŒô —i‘iØ×&Ñ&¨¯©Ñ6¸×8JÑ8JÐQW×QfÑQfô
ˆ�r2   NrR   Úposition_embeddingsra   Úpast_key_valuesrd   rT   c                 ó
  — |j                   d d }g |¢d‘| j                  ‘­}| j                  |«      j                  |«      j	                  dd«      }| j                  |«      j                  |«      j	                  dd«      }	| j                  |«      j                  |«      j	                  dd«      }
|\  }}t        ||	||«      \  }}	|� |j                  |	|
| j                  «      \  }	}
t        j                  | j                  j                  t        «      } || ||	|
|f| j                  sdn| j                   | j"                  dœ|¤Ž\  }} |j$                  g |¢d‘­Ž j'                  «       }| j)                  |«      }||fS )Nr=   r   r>   ç        )rc   rb   )rA   r[   r   Úviewrk   r€   r�   rQ   Úupdaterx   r   Úget_interfacer$   Ú_attn_implementationru   rh   r|   rb   rW   rp   r‚   )r/   rR   r„   ra   r…   rd   Úinput_shapeÚhidden_shapeÚquery_statesrq   rr   rL   rM   Úattention_interfacert   rs   s                   r1   r6   zJais2Attention.forward›   s‘  € ð $×)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(r2   ©NNN)r7   r8   r9   Ú__doc__r   Úintr#   rB   ÚTensorÚtupler   r   r   r6   r:   r;   s   @r1   rw   rw   €   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	*÷&)r2   rw   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Jais2DecoderLayerr$   rx   c                 óH  •— t         ‰| �  «        |j                  | _        t        ||¬«      | _        t        |«      | _        t        j                  |j                  |j                  ¬«      | _
        t        j                  |j                  |j                  ¬«      | _        y )N)r$   rx   ©Úeps)r"   r#   r%   rw   Ú	self_attnr   Úmlpr'   Ú	LayerNormÚlayer_norm_epsÚinput_layernormÚpost_attention_layernormrƒ   s      €r1   r#   zJais2DecoderLayer.__init__Å   st   ø€ Ü‰ÑÔØ!×-Ñ-ˆÔä'¨vÀÔKˆŒä˜FÓ#ˆŒÜ!Ÿ|™|¨F×,>Ñ,>ÀF×DYÑDYÔZˆÔÜ(*¯©°V×5GÑ5GÈV×MbÑMbÔ(cˆÕ%r2   NrR   ra   Úposition_idsr…   Ú	use_cacher„   rd   rT   c           
      óÀ   — |}| j                  |«      } | j                  d||||||dœ|¤Ž\  }}	||z   }|}| j                  |«      }| j                  |«      }||z   }|S )N)rR   ra   r    r…   r¡   r„   © )rž   rš   rŸ   r›   )
r/   rR   ra   r    r…   r¡   r„   rd   ÚresidualÚ_s
             r1   r6   zJais2DecoderLayer.forwardÏ   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r2   )NNNFN)r7   r8   r9   r   r’   r#   rB   r“   Ú
LongTensorr   Úboolr”   r   r   r6   r:   r;   s   @r1   r–   r–   Ä   s¾   ø„ ðd˜{ð d°sõ dð /3Ø04Ø(,Ø!&ØHLñà—|‘|ðð Ÿ™ tÑ+ðð ×&Ñ&¨Ñ-ð	ð
  ™ðð ˜$‘;ðð # 5§<¡<°·±Ð#=Ñ>ÀÑEðð Ð+Ñ,ðð 
�‰÷r2   r–   c                   óJ   — e Zd ZU eed<   dZdZdgZdgZdZ	dZ
dZdZdZeedœZy)ÚJais2PreTrainedModelr$   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–   rw   Ú_can_record_outputsr£   r2   r1   r©   r©   ï   sQ   … àÓØÐØ&*Ð#Ø,Ð-ÐØ#4Ð"5ÐØÐØ€NØÐà!ÐØ"&Ðà*Ø$ñÑr2   r©   c                   óÄ   ‡ — e Zd ZU ej                  ed<   ddefˆ fd„Ze	 	 	 ddedz  de	d   de
dz  ded	ef   fd
„«       Z ej                  «       ed„ «       «       Zˆ xZS )ÚJais2RotaryEmbeddingÚinv_freqNr$   c                 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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__  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Ur2   rÇ   ztorch.deviceÚseq_lenrT   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_thetar[   Ng      ð?r   r>   ©rf   )rÇ   rf   )	rÂ   rz   r%   r{   rB   ÚarangeÚint64ro   Úfloat)r$   rÇ   rÉ   Úbaser@   Úattention_factorr¹   s          r1   rÃ   z4Jais2RotaryEmbedding.compute_default_rope_parameters  s�   € ð& ×%Ñ% lÑ3ˆÜ�f˜j¨$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)r2   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   r=   r   ÚmpsÚcpuF)Údevice_typeÚenabledr>   r?   rÌ   )r¹   rÏ   rV   rA   ro   rÇ   Ú
isinstanceÚtypeÚstrr   rk   rB   rC   rL   rÄ   rM   rf   )
r/   r5   r    Úinv_freq_expandedÚposition_ids_expandedrÕ   ÚfreqsÚembrL   rM   s
             r1   r6   zJais2RotaryEmbedding.forward3  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$r4   r�   )r7   r8   r9   rB   r“   r¬   r   r#   Ústaticmethodr   r’   r”   rÏ   rÃ   Úno_gradr   r6   r:   r;   s   @r1   r¸   r¸     s˜   ø… Ø�l‰lÓñV˜{õ Vð  à%)Ø+/Ø"ñ*Ø˜dÑ"ð*à˜Ñ(ð*ð �t‘ð*ð 
ˆ~˜uÐ$Ñ	%ò	*ó ð*ð: €U‡]�]ƒ_Øñ<ó ó ô<r2   r¸   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
Jais2Modelr$   c           	      ó   •— t         ‰| �  |«       |j                  | _        |j                  | _        t        j                  |j                  |j                  | j                  «      | _        t        j                  t        |j                  «      D �cg c]  }t        ||«      ‘Œ c}«      | _        t        j                  |j                  |j                  ¬«      | _        t#        |¬«      | _        d| _        | j)                  «        y c c}w )Nr˜   ©r$   F)r"   r#   Úpad_token_idÚpadding_idxÚ
vocab_sizer'   Ú	Embeddingr%   Úembed_tokensÚ
ModuleListÚrangeÚnum_hidden_layersr–   Úlayersrœ   r�   Únormr¸   Ú
rotary_embÚgradient_checkpointingÚ	post_initrƒ   s      €r1   r#   zJais2Model.__init__E  sÊ   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 —L‘L ×!3Ñ!3¸×9NÑ9NÔOˆŒ	Ü.°fÔ=ˆŒØ&+ˆÔ#ð 	�‰Õùò ds   ÂDNÚ	input_idsra   r    r…   Úinputs_embedsr¡   rd   rT   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_embedsrã   r   r   )rÇ   )r$   rò   ra   r…   r    )r    )ra   r„   r    r…   r¡   )Úlast_hidden_stater…   )Ú
ValueErrorrè   r   r$   Úget_seq_lengthrB   rÍ   rA   rÇ   rI   r   rî   rì   rë   rí   r   )r/   rñ   ra   r    r…   rò   r¡   rd   Úpast_seen_tokensÚcausal_maskrR   r„   Údecoder_layers                r1   r6   zJais2Model.forwardU  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$7Ø)Ø /Ø#ñð ñ‰Mð		ð Ÿ	™	 -Ó0ˆÜ&Ø+Ø+ô
ð 	
r2   )NNNNNN)r7   r8   r9   r   r#   r   r   r   rB   r¦   r“   r   ÚFloatTensorr§   r   r   r   r6   r:   r;   s   @r1   rá   rá   C  sÍ   ø„ ð˜{õ ð   ØØð .2Ø.2Ø04Ø(,Ø26Ø!%ñ2
à×#Ñ# dÑ*ð2
ð Ÿ™ tÑ+ð2
ð ×&Ñ&¨Ñ-ð	2
ð
  ™ð2
ð ×(Ñ(¨4Ñ/ð2
ð ˜$‘;ð2
ð Ð+Ñ,ð2
ð 
!ò2
ó ó ó  ô2
r2   rá   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Jais2ForCausalLMzlm_head.weightzmodel.embed_tokens.weightÚlm_headÚcolwise_gather_outputrR   Úlogitsc                 óè   •— t         ‰| �  |«       t        |«      | _        |j                  | _        t        j                  |j                  |j                  d¬«      | _        | j                  «        y )NFr    )
r"   r#   rá   rª   ræ   r'   r(   r%   rý   rð   r.   s     €r1   r#   zJais2ForCausalLM.__init__“  sU   ø€ Ü‰Ñ˜Ô Ü Ó'ˆŒ
Ø ×+Ñ+ˆŒÜ—y‘y ×!3Ñ!3°V×5FÑ5FÈUÔSˆŒð 	�‰Õr2   Nrñ   ra   r    r…   rò   Úlabelsr¡   Úlogits_to_keeprd   rT   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 )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."
        ```)rñ   ra   r    r…   rò   r¡   N)rÿ   r  ræ   )Úlossrÿ   r…   rR   r«   r£   )rª   rô   r×   r’   Úslicerý   Úloss_functionr$   ræ   r   r…   rR   r«   )r/   rñ   ra   r    r…   rò   r  r¡   r  rd   ÚoutputsrR   Úslice_indicesrÿ   r  s                  r1   r6   zJais2ForCausalLM.forwardœ  sÙ   € ð> ,6¨4¯:©:ð ,
ØØ)Ø%Ø+Ø'Øñ,
ð ñ,
ˆð  ×1Ñ1ˆä8BÀ>ÔSVÔ8Wœ˜~˜o¨tÔ4Ð]kˆØ—‘˜mªA¨}ºaÐ,?Ñ@ÓAˆàˆØÐØ%�4×%Ñ%Ðp¨V¸FÈtÏ{É{×OeÑOeÑpÐioÑpˆDä%ØØØ#×3Ñ3Ø!×/Ñ/Ø×)Ñ)ô
ð 	
r2   )NNNNNNNr   )r7   r8   r9   Ú_tied_weights_keysÚ_tp_planÚ_pp_planr#   r   r   rB   r¦   r“   r   rú   r§   r’   r   r   r   r6   r:   r;   s   @r1   rü   rü   �  s  ø„ à*Ð,GÐHÐØÐ2Ð3€HØ˜_Ð-°¨zÐ:Ð;€Hôð Øð .2Ø.2Ø04Ø(,Ø26Ø*.Ø!%Ø-.ñ6
à×#Ñ# dÑ*ð6
ð Ÿ™ tÑ+ð6
ð ×&Ñ&¨Ñ-ð	6
ð
  ™ð6
ð ×(Ñ(¨4Ñ/ð6
ð × Ñ  4Ñ'ð6
ð ˜$‘;ð6
ð ˜eŸl™lÑ*ð6
ð Ð+Ñ,ð6
ð 
 ò6
ó ó ô6
r2   rü   )rá   rü   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   ru   rw   r–   r©   r¸   rá   rü   Ú__all__r£   r2   r1   ú<module>r     s·  ðõ, %Ý ã Ý å !ß .Ý )ß IÝ /Ý 9ß Oß Kß FÝ &ß IÑ Iß GÝ 5Ý ,ô<ˆr�y‰yô <ò(ñ Ð*Ó+òó ,ðð2	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ô$><˜2Ÿ9™9ô ><ðB ôF
Ð%ó F
ó ðF
ðR ôF
Ð+¨_ó F
ó ðF
òR E�r2   