§
    ‚Štj¤T  ã                   óD  — d dl Z 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 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$m%Z%m&Z& ddl'm(Z(m)Z)m*Z* ddl+m,Z, ddl-m.Z.  G d„ dej        j/        ¦  «        Z0 G d„ dej/        ¦  «        Z1 ed¦  «        d7d„¦   «         Z2dej3        de4dej3        fd„Z5	 d8d ej/        d!ej3        d"ej3        d#ej3        d$ej3        dz  d%e6d&e6d'e#e%         fd(„Z7d)„ Z8 ee2¦  «         G d*„ d+ej/        ¦  «        ¦   «         Z9 G d,„ d-ej/        ¦  «        Z: G d.„ d/e¦  «        Z;e& G d0„ d1e!¦  «        ¦   «         Z<e& G d2„ d3e<¦  «        ¦   «         Z=e& G d4„ d5e<e¦  «        ¦   «         Z>g d6¢Z?dS )9é    N)ÚCallable)ÚOptionalé   )Úinitialization)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_docstring)Úcan_return_tupleÚmaybe_autocastÚmerge_with_config_defaults)Úcapture_outputsé   )ÚNanoChatConfigc                   ó8   ‡ — e Zd Zddefˆ fd„Zd„ Zd„ Zd„ Zˆ xZS )ÚNanoChatRMSNormç�íµ ÷Æ°>Úepsc                 óV   •— t          ¦   «                              ¦   «          || _        d S ©N)ÚsuperÚ__init__r!   )Úselfr!   Ú	__class__s     €úl/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/transformers/models/nanochat/modeling_nanochat.pyr%   zNanoChatRMSNorm.__init__.   s$   ø€ Ý‰Œ×ÒÑÔÐØˆŒˆˆó    c                 ó�   — |t          j        |                     d¦  «                             dd¬¦  «        | j        z   ¦  «        z  S )Né   éÿÿÿÿT)Úkeepdim)ÚtorchÚrsqrtÚpowÚmeanr!   ©r&   Úxs     r(   Ú_normzNanoChatRMSNorm._norm2   s8   € Ø•5”;˜qŸušu Q™xœxŸ}š}¨R¸˜}Ñ>Ô>ÀÄÑIÑJÔJÑJÐJr)   c                 óv   — |                       |                     ¦   «         ¦  «                             |¦  «        S r#   )r4   ÚfloatÚtype_asr2   s     r(   ÚforwardzNanoChatRMSNorm.forward5   s*   € Ø�zŠz˜!Ÿ'š'™)œ)Ñ$Ô$×,Ò,¨QÑ/Ô/Ð/r)   c                 ó   — d| j         › �S )Nzeps=©r!   )r&   s    r(   Ú
extra_reprzNanoChatRMSNorm.extra_repr8   s   € Ø �d”hÐ Ð Ð r)   )r    )	Ú__name__Ú
__module__Ú__qualname__r6   r%   r4   r8   r;   Ú__classcell__©r'   s   @r(   r   r   -   sy   ø€ € € € € ðð ˜Eð ð ð ð ð ð ðKð Kð Kð0ð 0ð 0ð!ð !ð !ð !ð !ð !ð !r)   r   c                   óÔ   ‡ — e Zd ZU ej        ed<   ddefˆ fd„Ze	 	 	 ddedz  de	d         de
dz  ded	ef         fd
„¦   «         Z ej        ¦   «         ed„ ¦   «         ¦   «         Zˆ xZS )ÚNanoChatRotaryEmbeddingÚinv_freqNÚconfigc                 ó²  •— t          ¦   «                              ¦   «          |j        | _        |j        | _        || _        | j        j        d         | _        | j        }| j        dk    rt          | j                 } || j        |¦  «        \  }| _
        |                      d|d¬¦  «         |                      d|                     ¦   «         d¬¦  «         d S )NÚ	rope_typeÚdefaultrC   F)Ú
persistentÚoriginal_inv_freq)r$   r%   Úmax_position_embeddingsÚmax_seq_len_cachedÚoriginal_max_seq_lenrD   Úrope_parametersrF   Úcompute_default_rope_parametersr   Úattention_scalingÚregister_bufferÚclone)r&   rD   ÚdeviceÚrope_init_fnrC   r'   s        €r(   r%   z NanoChatRotaryEmbedding.__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�$Ô(à×Ò˜Z¨¸eÐÑDÔDÐDØ×ÒÐ0°(·.².Ñ2BÔ2BÈuÐÑUÔUÐUÐUÐUr)   rR   ztorch.deviceÚseq_lenÚreturnztorch.Tensorc                 óü   — | j         d         }t          | dd¦  «        p| j        | j        z  }d}d|t	          j        d|dt          j        ¬¦  «                             |t          j        ¬¦  «        |z  z  z  }||fS )	a¨  
        Computes the inverse frequencies according to the original RoPE implementation
        Args:
            config ([`~transformers.PreTrainedConfig`]):
                The model configuration.
            device (`torch.device`):
                The device to use for initialization of the inverse frequencies.
            seq_len (`int`, *optional*):
                The current sequence length. Unused for this type of RoPE.
        Returns:
            Tuple of (`torch.Tensor`, `float`), containing the inverse frequencies for the RoPE embeddings and the
            post-processing scaling factor applied to the computed cos/sin (unused in this type of RoPE).
        Ú
rope_thetaÚhead_dimNg      ð?r   r+   ©Údtype)rR   rZ   )	rM   ÚgetattrÚhidden_sizeÚnum_attention_headsr.   ÚarangeÚint64Útor6   )rD   rR   rT   ÚbaseÚdimÚattention_factorrC   s          r(   rN   z7NanoChatRotaryEmbedding.compute_default_rope_parametersO   sŒ   € ð& Ô% lÔ3ˆÝ�f˜j¨$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)r)   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+   ©rb   rY   )rC   r6   ÚexpandÚshaper`   rR   Ú
isinstanceÚtypeÚstrr   Ú	transposer.   ÚcatÚcosrO   ÚsinrZ   )
r&   r3   Úposition_idsÚinv_freq_expandedÚposition_ids_expandedrg   ÚfreqsÚembrq   rr   s
             r(   r8   zNanoChatRotaryEmbedding.forwardm   s·  € ð !œM¨$°°°°4¨-Ô8×>Ò>Ñ@Ô@×GÒGÈÔHZÐ[\ÔH]Ð_aÐcdÑeÔe×hÒhÐijÔiqÑrÔrÐØ ,¨Q¨Q¨Q°°a°a°a¨ZÔ 8× >Ò >Ñ @Ô @Ðå'1°!´(´-ÅÑ'EÔ'EÐkÈ!Ì(Ì-Ð[`ÒJ`ÐJ`�a”h”m�mÐfkˆÝ¨¸UÐCÑCÔCð 	5ð 	5Ø&×,Ò,Ñ.Ô.Ð1F×1LÒ1LÑ1NÔ1NÑN×YÒYÐZ[Ð]^Ñ_Ô_ˆEÝ”)˜U E˜N°Ð3Ñ3Ô3ˆCØ—'’'‘)”)˜dÔ4Ñ4ˆCØ—'’'‘)”)˜dÔ4Ñ4ˆCð		5ð 	5ð 	5ñ 	5ô 	5ð 	5ð 	5ð 	5ð 	5ð 	5ð 	5øøøð 	5ð 	5ð 	5ð 	5ð �vŠv˜AœGˆvÑ$Ô$ c§f¢f°1´7 fÑ&;Ô&;Ð;Ð;s   ÃBE&Å&E*Å-E*r#   ©NNN)r<   r=   r>   r.   ÚTensorÚ__annotations__r   r%   Ústaticmethodr   ÚintÚtupler6   rN   Úno_gradr   r8   r?   r@   s   @r(   rB   rB   <   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 <r)   rB   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	unsqueezeÚrotate_half)ÚqÚkrq   rr   Úunsqueeze_dimÚq_embedÚk_embeds          r(   Úapply_rotary_pos_embrˆ   }   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r)   Úhidden_statesÚn_reprU   c                 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)rk   rj   Úreshape)r‰   rŠ   ÚbatchÚnum_key_value_headsÚslenrX   s         r(   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Tr)   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,   )rb   rZ   )ÚpÚtrainingr   )r�   Únum_key_value_groupsr.   Úmatmulro   ÚnnÚ
functionalÚsoftmaxÚfloat32r`   rZ   r˜   rœ   Ú
contiguous)r’   r“   r”   r•   r–   r—   r˜   r™   Ú
key_statesÚvalue_statesÚattn_weightsÚattn_outputs               r(   Úeager_attention_forwardr¨   £   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$Ð$r)   c                 óœ   — | dd| j         d         dz  …f         }| d| j         d         dz  d…f         }t          j        || fd¬¦  «        S )zJRotates half the hidden dims of the input with flipped signs for NanoChat..Nr,   r+   ri   )rk   r.   rp   )r3   Úx1Úx2s      r(   r‚   r‚   ¼   s]   € à	
ˆ3Ð"�!”'˜"”+ Ñ"Ð"Ð"Ô	#€BØ	
ˆ3�”˜”˜qÑ Ð"Ð"Ð"Ô	#€BÝŒ9�b˜2˜#�Y BÐ'Ñ'Ô'Ð'r)   c                   óÔ   ‡ — 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        dz  f         fd„Zˆ xZS )ÚNanoChatAttentionz=Multi-headed attention from 'Attention Is All You Need' paperrD   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        ¬¦  «        | _        t)          |j        ¬¦  «        | _        t)          |j        ¬¦  «        | _        d S )NrX   g      à¿T©Úbiasr:   )r$   r%   rD   r®   r[   r\   r]   rX   rŽ   r�   r—   Úattention_dropoutÚ	is_causalrŸ   ÚLinearÚattention_biasÚq_projÚk_projÚv_projÚo_projr   Úrms_norm_epsÚq_normÚk_norm©r&   rD   r®   r'   s      €r(   r%   zNanoChatAttention.__init__Ç   sn  ø€ Ý‰Œ×ÒÑÔÐØˆŒØ"ˆŒÝ ¨
°FÔ4FÈ&ÔJdÑ4dÑeÔeˆŒØ$*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õ &¨&Ô*=Ð>Ñ>Ô>ˆŒÝ%¨&Ô*=Ð>Ñ>Ô>ˆŒˆˆr)   Nr‰   Úposition_embeddingsr–   Úpast_key_valuesr™   rU   c                 óv  — |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‘   )r˜   r—   )rk   rX   r¶   Úviewro   r·   r¸   rˆ   r»   r¼   Úupdater®   r   Úget_interfacerD   Ú_attn_implementationr¨   rœ   r²   r—   rŒ   r£   r¹   )r&   r‰   r¾   r–   r¿   r™   Úinput_shapeÚhidden_shapeÚquery_statesr¤   r¥   rq   rr   Úattention_interfacer§   r¦   s                   r(   r8   zNanoChatAttention.forwardá   sä  € 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�jð —{’{ <Ñ0Ô0ˆØ—[’[ Ñ,Ô,ˆ
à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(r)   rx   )r<   r=   r>   Ú__doc__r   r|   r%   r.   ry   r}   r   r   r   r8   r?   r@   s   @r(   r­   r­   Ã   sê   ø€ € € € € àGÐGð?˜~ð ?¸#ð ?ð ?ð ?ð ?ð ?ð ?ð: 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\¨DÑ0Ð0Ô	1ð*)ð *)ð *)ð *)ð *)ð *)ð *)ð *)r)   r­   c                   óB   ‡ — e Zd Zˆ fd„Zdej        dej        fd„Zˆ xZS )ÚNanoChatMLPc                 ó  •— t          ¦   «                              ¦   «          || _        t          |j                 | _        t          j        |j        |j	        d¬¦  «        | _
        t          j        |j	        |j        d¬¦  «        | _        d S ©NFr°   )r$   r%   rD   r   Ú
hidden_actÚactivation_fnrŸ   r´   r\   Úintermediate_sizeÚfc1Úfc2©r&   rD   r'   s     €r(   r%   zNanoChatMLP.__init__  sr   ø€ Ý‰Œ×ÒÑÔÐØˆŒÝ# FÔ$5Ô6ˆÔÝ”9˜VÔ/°Ô1IÐPUÐVÑVÔVˆŒÝ”9˜VÔ5°vÔ7IÐPUÐVÑVÔVˆŒˆˆr)   r‰   rU   c                 ó„   — |                       |¦  «        }|                      |¦  «        }|                      |¦  «        }|S r#   )rÑ   rÏ   rÒ   )r&   r‰   s     r(   r8   zNanoChatMLP.forward  s=   € ØŸš Ñ/Ô/ˆØ×*Ò*¨=Ñ9Ô9ˆØŸš Ñ/Ô/ˆØÐr)   )r<   r=   r>   r%   r.   ry   r8   r?   r@   s   @r(   rË   rË     sc   ø€ € € € € ðWð Wð Wð Wð Wð U¤\ð °e´lð ð ð ð ð ð ð ð r)   rË   c                   óÒ   ‡ — e Zd Zdedefˆ fd„Z	 	 	 	 	 ddej        dej        dz  dej        dz  d	e	dz  d
e
dz  deej        ej        f         dz  dee         dej        fd„Zˆ xZS )ÚNanoChatDecoderLayerrD   r®   c                 ó  •— t          ¦   «                              ¦   «          |j        | _        t          ||¬¦  «        | _        t          |¦  «        | _        t          |j        ¬¦  «        | _	        t          |j        ¬¦  «        | _
        d S )N)rD   r®   r:   )r$   r%   r\   r­   Ú	self_attnrË   Úmlpr   rº   Úinput_layernormÚpost_attention_layernormr½   s      €r(   r%   zNanoChatDecoderLayer.__init__  sy   ø€ Ý‰Œ×ÒÑÔÐØ!Ô-ˆÔå*°&ÀIÐNÑNÔNˆŒå˜vÑ&Ô&ˆŒå.°6Ô3FÐGÑGÔGˆÔÝ(7¸FÔ<OÐ(PÑ(PÔ(PˆÔ%Ð%Ð%r)   NFr‰   r–   rs   r¿   Ú	use_cacher¾   r™   rU   c           
      óÎ   — |}|                       |¦  «        } | j        d||||||dœ|¤Ž\  }}	||z   }|}|                      |¦  «        }|                      |¦  «        }||z   }|S )N)r‰   r–   rs   r¿   rÜ   r¾   © )rÚ   rØ   rÛ   rÙ   )
r&   r‰   r–   rs   r¿   rÜ   r¾   r™   ÚresidualÚ_s
             r(   r8   zNanoChatDecoderLayer.forward)  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r)   )NNNFN)r<   r=   r>   r   r|   r%   r.   ry   Ú
LongTensorr   Úboolr}   r   r   r8   r?   r@   s   @r(   rÖ   rÖ     sÿ   ø€ € € € € ð	Q˜~ð 	Q¸#ð 	Qð 	Qð 	Qð 	Qð 	Qð 	Qð /3Ø04Ø(,Ø!&ØHLðð à”|ðð œ tÑ+ðð Ô&¨Ñ-ð	ð
  ™ðð ˜$‘;ðð # 5¤<°´Ð#=Ô>ÀÑEðð Ð+Ô,ðð 
Œðð ð ð ð ð ð ð r)   rÖ   c                   óp   ‡ — e Zd ZU eed<   dZdZdgZdgZdZ	dZ
dZdZdZeedœZdej        dd	fˆ fd
„Zˆ xZS )ÚNanoChatPreTrainedModelrD   ÚmodelTrÖ   r¿   )r‰   Ú
attentionsr’   rU   Nc           	      ó  •— t          ¦   «                              |¦  «         t          |t          ¦  «        rOt	          j        |j        j        d| j        j	        t          j        d| j        j        z  ¦  «        z  ¬¦  «         d S d S )Nr‘   r+   )r1   Ústd)r$   Ú_init_weightsrl   r­   ÚinitÚnormal_r¹   ÚweightrD   Úinitializer_rangeÚmathÚsqrtÚnum_hidden_layers)r&   r’   r'   s     €r(   ré   z%NanoChatPreTrainedModel._init_weights[  s‡   ø€ Ý‰Œ×Ò˜fÑ%Ô%Ð%Ý�fÕ/Ñ0Ô0ð 	ÝŒLØ”Ô$ØØ”KÔ1µD´I¸aÀ$Ä+ÔB_Ñ>_Ñ4`Ô4`Ñ`ðñ ô ð ð ð ð	ð 	r)   )r<   r=   r>   r   rz   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_backendrÖ   r­   Ú_can_record_outputsrŸ   ÚModuleré   r?   r@   s   @r(   rä   rä   I  s©   ø€ € € € € € àÐÐÑØÐØ&*Ð#Ø/Ð0ÐØ#4Ð"5ÐØÐØ€NØÐà!ÐØ"&Ðà-Ø'ðð Ðð
 B¤Ið °$ð ð ð ð ð ð ð ð ð ð r)   rä   c                   óâ   ‡ — e Zd Zdefˆ fd„Zeee	 	 	 	 	 	 ddej	        dz  dej
        dz  dej	        dz  dedz  dej        dz  d	edz  d
ee         defd„¦   «         ¦   «         ¦   «         Zˆ xZS )ÚNanoChatModelrD   c                 óÒ  •‡— t          ¦   «                              ‰¦  «         ‰j        | _        ‰j        | _        t          j        ‰j        ‰j        | j        ¦  «        | _        t          j	        ˆfd„t          ‰j        ¦  «        D ¦   «         ¦  «        | _        t          ‰j        ¬¦  «        | _        t!          ‰¬¦  «        | _        d| _        |                      ¦   «          d S )Nc                 ó0   •— g | ]}t          ‰|¦  «        ‘ŒS rÞ   )rÖ   )Ú.0r®   rD   s     €r(   ú
<listcomp>z*NanoChatModel.__init__.<locals>.<listcomp>n  s$   ø€ ÐfÐfÐf¸Õ! &¨)Ñ4Ô4ÐfÐfÐfr)   r:   ©rD   F)r$   r%   Úpad_token_idÚpadding_idxÚ
vocab_sizerŸ   Ú	Embeddingr\   Úembed_tokensÚ
ModuleListÚrangerð   Úlayersr   rº   ÚnormrB   Ú
rotary_embÚgradient_checkpointingÚ	post_initrÓ   s    `€r(   r%   zNanoChatModel.__init__g  sÏ   øø€ Ý‰Œ×Ò˜Ñ Ô Ð Ø!Ô.ˆÔØ Ô+ˆŒåœL¨Ô):¸FÔ<NÐPTÔP`ÑaÔaˆÔÝ”mØfÐfÐfÐfÅeÈFÔLdÑFeÔFeÐfÑfÔfñ
ô 
ˆŒõ $¨Ô(;Ð<Ñ<Ô<ˆŒ	Ý1¸Ð@Ñ@Ô@ˆŒØ&+ˆÔ#ð 	�ŠÑÔÐÐÐr)   NÚ	input_idsr–   rs   r¿   Úinputs_embedsrÜ   r™   rU   c           	      óp  — |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_embedsr  r   r   )rR   )rD   r  r–   r¿   rs   )rs   )r–   r¾   rs   r¿   )Úlast_hidden_stater¿   )Ú
ValueErrorr  r	   rD   Úget_seq_lengthr.   r^   rk   rR   r�   r   r  r  r
  rð   r   )r&   r  r–   rs   r¿   r  rÜ   r™   Úpast_seen_tokensÚcausal_maskr‰   r¾   Údecoder_layers                r(   r8   zNanoChatModel.forwardx  s˜  € 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Ÿ	š	 -Ñ0Ô0ˆØ!œ[Ð)H¨4¬;Ô+HÐ)HÔIð 	ð 	ˆMØ)˜MØðà*Ø$7Ø)Ø /ðð ð ðð ˆMˆMð Ÿ	š	 -Ñ0Ô0ˆÝ&Ø+Ø+ð
ñ 
ô 
ð 	
r)   )NNNNNN)r<   r=   r>   r   r%   r   r   r   r.   rá   ry   r   ÚFloatTensorrâ   r   r   r   r8   r?   r@   s   @r(   rý   rý   e  s  ø€ € € € € ð˜~ð ð ð ð ð ð ð"  ØØð .2Ø.2Ø04Ø(,Ø26Ø!%ð2
ð 2
àÔ# dÑ*ð2
ð œ tÑ+ð2
ð Ô&¨Ñ-ð	2
ð
  ™ð2
ð Ô(¨4Ñ/ð2
ð ˜$‘;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
r)   rý   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NanoChatForCausalLMzlm_head.weightzmodel.embed_tokens.weightÚlm_headÚcolwise_gather_outputr‰   Úlogitsc                 óþ   •— t          ¦   «                              |¦  «         t          |¦  «        | _        |j        | _        t          j        |j        |j        d¬¦  «        | _        |  	                    ¦   «          d S rÍ   )
r$   r%   rý   rå   r  rŸ   r´   r\   r  r  rÓ   s     €r(   r%   zNanoChatForCausalLM.__init__¶  sj   ø€ Ý‰Œ×Ò˜Ñ Ô Ð Ý" 6Ñ*Ô*ˆŒ
Ø Ô+ˆŒÝ”y Ô!3°VÔ5FÈUÐSÑSÔSˆŒð 	�ŠÑÔÐÐÐr)   Nr   r  r–   rs   r¿   r  ÚlabelsrÜ   Úlogits_to_keepr™   rU   c	           
      óÀ  —  | j         d||||||dœ|	¤Ž}
|
j        }t          |t          ¦  «        rt	          | d¦  «        n|}|                      |dd…|dd…f         ¦  «        }| j        j        �2|| j        j        z  }t          j	        |¦  «        }|| j        j        z  }d}|� | j
        ||| j        fi |	¤Ž}t          |||
j        |
j        |
j        ¬¦  «        S )ak  
        Example:

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

        >>> model = AutoModelForCausalLM.from_pretrained("karpathy/nanochat-d32")

        >>> tokenizer = AutoTokenizer.from_pretrained("karpathy/nanochat-d32")

        >>> conversation = [
                {"role": "user", "content": "What is the capital of France?"},
            ]

        >>> inputs = tokenizer.apply_chat_template(
                conversation, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt"
            ).to(device)

        >>> with torch.no_grad():
        >>>     outputs = model.generate(**inputs, max_new_tokens=64, do_sample=False)

        >>> generated_tokens = outputs[0, inputs["input_ids"].shape[1] :]
        >>> output = tokenizer.decode(generated_tokens, skip_special_tokens=True)
        ```)r  r–   rs   r¿   r  rÜ   N)Úlossr  r¿   r‰   ræ   rÞ   )rå   r  rl   r|   Úslicer  rD   Úfinal_logit_softcappingr.   ÚtanhÚloss_functionr  r   r¿   r‰   ræ   )r&   r  r–   rs   r¿   r  r  rÜ   r   r™   Úoutputsr‰   Úslice_indicesr  r"  s                  r(   r8   zNanoChatForCausalLM.forward¿  s&  € ðN ,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ØŒ;Ô.Ð:Ø˜dœkÔAÑAˆFÝ”Z Ñ'Ô'ˆFØ˜dœkÔAÑAˆFàˆØÐØ%�4Ô% f¨f°d´oÐPÐPÈÐPÐPˆDå%ØØØ#Ô3Ø!Ô/ØÔ)ð
ñ 
ô 
ð 	
r)   )NNNNNNNr   )r<   r=   r>   Ú_tied_weights_keysÚ_tp_planÚ_pp_planr%   r   r   r.   rá   ry   r   r  râ   r|   r   r   r   r8   r?   r@   s   @r(   r  r  °  s^  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B
ð B
àÔ# dÑ*ðB
ð œ tÑ+ðB
ð Ô&¨Ñ-ð	B
ð
  ™ðB
ð Ô(¨4Ñ/ðB
ð Ô  4Ñ'ðB
ð ˜$‘;ðB
ð ˜eœlÑ*ðB
ð Ð+Ô,ðB
ð 
 ðB
ð B
ð B
ñ „^ñ ÔðB
ð B
ð B
ð B
ð B
r)   r  )rä   rý   r  )r   )r‘   )@rî   Úcollections.abcr   Útypingr   r.   Útorch.nnrŸ   Ú r   rê   Úactivationsr   Úcache_utilsr   r	   Ú
generationr
   Úintegrationsr   r   Úmasking_utilsr   Úmodeling_layersr   Úmodeling_outputsr   r   Úmodeling_rope_utilsr   r   Úmodeling_utilsr   r   Úprocessing_utilsr   Úutilsr   r   Úutils.genericr   r   r   Úutils.output_capturingr   Úconfiguration_nanochatr   rû   r   rB   rˆ   ry   r|   r�   r6   r¨   r‚   r­   rË   rÖ   rä   rý   r  Ú__all__rÞ   r)   r(   ú<module>r?     sG  ðð* €€€Ø $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 !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 7Ð 7Ð 7Ð 7Ð 7Ð 7Ð 7Ð 7Ø YÐ YÐ YÐ YÐ YÐ YÐ YÐ YÐ YÐ YØ 5Ð 5Ð 5Ð 5Ð 5Ð 5Ø 2Ð 2Ð 2Ð 2Ð 2Ð 2ð!ð !ð !ð !ð !�e”h”oñ !ô !ð !ð><ð ><ð ><ð ><ð ><˜bœiñ ><ô ><ð ><ðB 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 (ð ÐÐ)Ñ*Ô*ðG)ð G)ð G)ð G)ð G)˜œ	ñ G)ô G)ñ +Ô*ðG)ðTð ð ð ð �"”)ñ ô ð ð)ð )ð )ð )ð )Ð5ñ )ô )ð )ðX ðð ð ð ð ˜oñ ô ñ „ðð6 ðG
ð G
ð G
ð G
ð G
Ð+ñ G
ô G
ñ „ðG
ðT ðR
ð R
ð R
ð R
ð R
Ð1°?ñ R
ô R
ñ „ðR
ðj NÐ
MÐ
M€€€r)   