§
    9²¸jÝS  ã                   óD  — d dl 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& 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Callableé   )Úinitialization)ÚACT2FN)ÚCacheÚDynamicCache)ÚGenerationMixin)Úuse_kernel_forward_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deprecate_kwarg)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     €ú~/root/private/project/pallet_detection_v2/.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$×,Ò,¨QÑ/Ô/Ð/r)   c                 ó   — d| j         › �S )Nzeps=©r!   )r&   s    r(   Ú
extra_reprzNanoChatRMSNorm.extra_repr8   s   € Ø �d”hÐ Ð Ð r)   )r    )	Ú__name__Ú
__module__Ú__qualname__r6   r%   r4   r8   r;   Ú__classcell__©r'   s   @r(   r   r   -   sy   ø€ € € € € ðð ˜Eð ð ð ð ð ð ðKð Kð Kð0ð 0ð 0ð!ð !ð !ð !ð !ð !ð !r)   r   c            	       óî   ‡ — e Zd Z edd¬¦  «        d
defˆ fd„¦   «         Ze edd¬¦  «        d
dedeej	        e
f         fd„¦   «         ¦   «         Z ej        ¦   «         ed	„ ¦   «         ¦   «         Zˆ xZS )ÚNanoChatRotaryEmbeddingÚdevicez5.18)ÚversionNÚconfigc                 ó¾  •— t          ¦   «                              ¦   «          |j        | _        |j        | _        || _        | j        j        d         | _        | j        }| j        dk    rt          | j                 } || j        |¦  «        \  }| _
        t          j        |d¬¦  «        | _        t          j        |                     ¦   «         d¬¦  «        | _        d S )NÚ	rope_typeÚdefaultF)Ú
persistent)r$   r%   Úmax_position_embeddingsÚmax_seq_len_cachedÚoriginal_max_seq_lenrE   Úrope_parametersrG   Úcompute_default_rope_parametersr   Úattention_scalingÚnnÚBufferÚinv_freqÚcloneÚoriginal_inv_freq)r&   rE   rC   Úrope_init_fnrR   r'   s        €r(   r%   z NanoChatRotaryEmbedding.__init__=   sÀ   ø€ å‰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�$Ô(åœ	 (°uÐ=Ñ=Ô=ˆŒÝ!#¤¨8¯>ª>Ñ+;Ô+;ÈÐ!NÑ!NÔ!NˆÔÐÐr)   Úreturnc                 óä   — | j         d         }t          | dd¦  «        p| j        | j        z  }d}d|t	          j        d|dt          j        ¬¦  «        |z  z  z  }|                     |¦  «        |fS )a¾  
        Computes the inverse frequencies according to the original RoPE implementation
        Args:
            config ([`~transformers.PreTrainedConfig`]):
                The model configuration.
        Returns:
            Tuple of (`torch.Tensor`, `float`), containing the inverse frequencies for the RoPE embeddings and the
            post-processing scaling factor applied to the computed cos/sin (unused in this type of RoPE).
        Ú
rope_thetaÚhead_dimNg      ð?r   r+   ©Údtype)rM   ÚgetattrÚhidden_sizeÚnum_attention_headsr.   Úaranger6   Úto)rE   rC   ÚkwargsÚbaseÚdimÚattention_factorrR   s          r(   rN   z7NanoChatRotaryEmbedding.compute_default_rope_parametersN   sz   € ð Ô% lÔ3ˆÝ�f˜j¨$Ñ/Ô/Ðc°6Ô3EÈÔIcÑ3cˆàÐà˜$¥5¤<°°3¸ÅÄÐ#MÑ#MÔ#MÐPSÑ#SÑTÑUˆØ�{Š{˜6Ñ"Ô"Ð$4Ð4Ð4r)   c                 óú  — | j         d d d …d f                              |j        d         dd¦  «                             t          j        |j        ¬¦  «        }|d d …d d d …f                              ¦   «         }t          |j        j        t          ¦  «        r|j        j        dk    r|j        j        nd}t          |d¬¦  «        5  ||z                       dd	¦  «        }t	          j        ||fd¬
¦  «        }|                     ¦   «         | j        z  }|                     ¦   «         | j        z  }	d d d ¦  «         n# 1 swxY w Y   |                     |j        ¬¦  «        |	                     |j        ¬¦  «        fS )Nr   r,   r   )r[   rC   ÚmpsÚcpuF)Údevice_typeÚenabledr+   ©rc   rZ   )rR   ÚexpandÚshaper`   r.   r6   rC   Ú
isinstanceÚtypeÚstrr   Ú	transposeÚcatÚcosrO   Úsinr[   )
r&   r3   Úposition_idsÚinv_freq_expandedÚposition_ids_expandedrh   ÚfreqsÚembrr   rs   s
             r(   r8   zNanoChatRotaryEmbedding.forwardb   s›  € ð ŒM˜$    4˜-Ô(×/Ò/°Ô0BÀ1Ô0EÀrÈ1ÑMÔM×PÒPÕW\ÔWbÐklÔksÐPÑtÔtð 	ð !-¨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å¨¸UÐCÑCÔCð 	5ð 	5Ø&Ð)>Ñ>×IÒIÈ!ÈQÑOÔOˆEÝ”)˜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A*D<Ä<E ÅE r#   )r<   r=   r>   r   r   r%   ÚstaticmethodÚtupler.   ÚTensorr6   rN   Úno_gradr   r8   r?   r@   s   @r(   rB   rB   <   sö   ø€ € € € € Ø€_�X vÐ.Ñ.Ô.ðOð O˜~ð Oð Oð Oð Oð Oñ /Ô.ðOð  Ø€_�X vÐ.Ñ.Ô.ð5ð 5°ð 5ÐZ_Ð`eÔ`lÐnsÐ`sÔZtð 5ð 5ð 5ñ /Ô.ñ „\ð5ð$ €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krr   rs   Úunsqueeze_dimÚq_embedÚk_embeds          r(   Úapply_rotary_pos_embr†   u   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_reprV   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)rl   rk   Úreshape)r‡   rˆ   ÚbatchÚnum_key_value_headsÚslenrY   s         r(   Ú	repeat_kvrŽ   �   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dropoutra   c                 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,   )rc   r[   )ÚpÚtrainingr   )rŽ   Únum_key_value_groupsr.   Úmatmulrp   rP   Ú
functionalÚsoftmaxÚfloat32r`   r[   r–   r™   Ú
contiguous)r�   r‘   r’   r“   r”   r•   r–   ra   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+   rj   )rl   r.   rq   )r3   Úx1Úx2s      r(   r€   r€   ´   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' paperrE   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 )NrY   g      à¿T©Úbiasr:   )r$   r%   rE   rª   r\   r]   r^   rY   rŒ   rš   r•   Úattention_dropoutÚ	is_causalrP   ÚLinearÚattention_biasÚq_projÚk_projÚv_projÚo_projr   Úrms_norm_epsÚq_normÚk_norm©r&   rE   rª   r'   s      €r(   r%   zNanoChatAttention.__init__¿   sn  ø€ Ý‰Œ×ÒÑÔÐØˆŒØ"ˆŒÝ ¨
°FÔ4FÈ&ÔJdÑ4dÑeÔeˆŒØ$*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_valuesra   rV   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•   )rl   rY   r²   Úviewrp   r³   r´   r†   r·   r¸   Úupdaterª   r   Úget_interfacerE   Ú_attn_implementationr¤   r™   r®   r•   rŠ   rŸ   rµ   )r&   r‡   rº   r”   r»   ra   Úinput_shapeÚhidden_shapeÚquery_statesr    r¡   rr   rs   Úattention_interfacer£   r¢   s                   r(   r8   zNanoChatAttention.forwardÙ   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)   )NNN)r<   r=   r>   Ú__doc__r   Úintr%   r.   r{   rz   r   r   r   r8   r?   r@   s   @r(   r©   r©   »   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%   rE   r   Ú
hidden_actÚactivation_fnrP   r°   r]   Úintermediate_sizeÚfc1Úfc2©r&   rE   r'   s     €r(   r%   zNanoChatMLP.__init__  sr   ø€ Ý‰Œ×ÒÑÔÐØˆŒÝ# FÔ$5Ô6ˆÔÝ”9˜VÔ/°Ô1IÐPUÐVÑVÔVˆŒÝ”9˜VÔ5°vÔ7IÐPUÐVÑVÔVˆŒˆˆr)   r‡   rV   c                 ó„   — |                       |¦  «        }|                      |¦  «        }|                      |¦  «        }|S r#   )rÎ   rÌ   rÏ   )r&   r‡   s     r(   r8   zNanoChatMLP.forward  s=   € ØŸš Ñ/Ô/ˆØ×*Ò*¨=Ñ9Ô9ˆØŸš Ñ/Ô/ˆØÐr)   )r<   r=   r>   r%   r.   r{   r8   r?   r@   s   @r(   rÈ   rÈ     sc   ø€ € € € € ðWð Wð Wð Wð Wð U¤\ð °e´lð ð ð ð ð ð ð ð r)   rÈ   c                   óÒ   ‡ — e Zd Zdedefˆ fd„Z	 	 	 	 	 ddej        dej        dz  dej        dz  d	e	dz  d
e
dz  deej        ej        f         dz  dee         dej        fd„Zˆ xZS )ÚNanoChatDecoderLayerrE   rª   c                 ó  •— t          ¦   «                              ¦   «          |j        | _        t          ||¬¦  «        | _        t          |¦  «        | _        t          |j        ¬¦  «        | _	        t          |j        ¬¦  «        | _
        d S )N)rE   rª   r:   )r$   r%   r]   r©   Ú	self_attnrÈ   Úmlpr   r¶   Úinput_layernormÚpost_attention_layernormr¹   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”   rt   r»   Ú	use_cacherº   ra   rV   c           
      óÎ   — |}|                       |¦  «        } | j        d||||||dœ|¤Ž\  }}	||z   }|}|                      |¦  «        }|                      |¦  «        }||z   }|S )N)r‡   r”   rt   r»   rÙ   rº   © )r×   rÕ   rØ   rÖ   )
r&   r‡   r”   rt   r»   rÙ   rº   ra   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   rÆ   r%   r.   r{   Ú
LongTensorr   Úboolrz   r   r   r8   r?   r@   s   @r(   rÓ   rÓ     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 ˜$‘;ðð # 5¤<°´Ð#=Ô>ÀÑEðð Ð+Ô,ðð 
Œðð ð ð ð ð ð ð r)   rÓ   c                   óp   ‡ — e Zd ZU eed<   dZdZdgZdgZdZ	dZ
dZdZdZeedœZdej        dd	fˆ fd
„Zˆ xZS )ÚNanoChatPreTrainedModelrE   ÚmodelTrÓ   r»   )r‡   Ú
attentionsr�   rV   Nc           	      ó  •— t          ¦   «                              |¦  «         t          |t          ¦  «        rOt	          j        |j        j        d| j        j	        t          j        d| j        j        z  ¦  «        z  ¬¦  «         d S d S )Nr�   r+   )r1   Ústd)r$   Ú_init_weightsrm   r©   ÚinitÚnormal_rµ   ÚweightrE   Úinitializer_rangeÚmathÚsqrtÚnum_hidden_layers)r&   r�   r'   s     €r(   ræ   z%NanoChatPreTrainedModel._init_weightsS  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   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_backendrÓ   r©   Ú_can_record_outputsrP   ÚModuleræ   r?   r@   s   @r(   rá   rá   A  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 °$ð ð ð ð ð ð ð ð ð ð r)   rá   c                   óâ   ‡ — e Zd Zdefˆ fd„Zeee	 	 	 	 	 	 ddej	        dz  dej
        dz  dej	        dz  dedz  dej        dz  d	edz  d
ee         defd„¦   «         ¦   «         ¦   «         Zˆ xZS )ÚNanoChatModelrE   c                 óÒ  •‡— t          ¦   «                              ‰¦  «         ‰j        | _        ‰j        | _        t          j        ‰j        ‰j        | j        ¦  «        | _        t          j	        ˆfd„t          ‰j        ¦  «        D ¦   «         ¦  «        | _        t          ‰j        ¬¦  «        | _        t!          ‰¬¦  «        | _        d| _        |                      ¦   «          d S )Nc                 ó0   •— g | ]}t          ‰|¦  «        ‘ŒS rÛ   )rÓ   )Ú.0rª   rE   s     €r(   ú
<listcomp>z*NanoChatModel.__init__.<locals>.<listcomp>f  s$   ø€ ÐfÐfÐf¸Õ! &¨)Ñ4Ô4ÐfÐfÐfr)   r:   ©rE   F)r$   r%   Úpad_token_idÚpadding_idxÚ
vocab_sizerP   Ú	Embeddingr]   Úembed_tokensÚ
ModuleListÚrangerí   Úlayersr   r¶   ÚnormrB   Ú
rotary_embÚgradient_checkpointingÚ	post_initrÐ   s    `€r(   r%   zNanoChatModel.__init___  sÏ   øø€ Ý‰Œ×Ò˜Ñ Ô Ð Ø!Ô.ˆÔØ Ô+ˆŒåœL¨Ô):¸FÔ<NÐPTÔP`ÑaÔaˆÔÝ”mØfÐfÐfÐfÅeÈFÔLdÑFeÔFeÐfÑfÔfñ
ô 
ˆŒõ $¨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”   rt   r»   Úinputs_embedsrÙ   ra   rV   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   )rC   )rE   r  r”   r»   rt   )rt   )r”   rº   rt   r»   )Úlast_hidden_stater»   )Ú
ValueErrorr  r   rE   Úget_seq_lengthr.   r_   rl   rC   r   r   r
  r	  r  rí   r   )r&   r  r”   rt   r»   r  rÙ   ra   Úpast_seen_tokensÚcausal_maskr‡   rº   Údecoder_layers                r(   r8   zNanoChatModel.forwardp  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$7Ø)Ø /ðð ð ðð ˆMˆMð Ÿ	š	 -Ñ0Ô0ˆÝ&Ø+Ø+ð
ñ 
ô 
ð 	
r)   )NNNNNN)r<   r=   r>   r   r%   r   r   r   r.   rÞ   r{   r   ÚFloatTensorrß   r   r   r   r8   r?   r@   s   @r(   rû   rû   ]  s  ø€ € € € € ð˜~ð ð ð ð ð ð ð"  ØØð .2Ø.2Ø04Ø(,Ø26Ø!%ð2
ð 2
àÔ# dÑ*ð2
ð œ tÑ+ð2
ð Ô&¨Ñ-ð	2
ð
  ™ð2
ð Ô(¨4Ñ/ð2
ð ˜$‘;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)   rû   c                   ó   ‡ — e Zd ZddiZddiZddgdgfiZdd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logitsÚkeep_full_weightc                 óþ   •— t          ¦   «                              |¦  «         t          |¦  «        | _        |j        | _        t          j        |j        |j        d¬¦  «        | _        |  	                    ¦   «          d S rÊ   )
r$   r%   rû   râ   r  rP   r°   r]   r  r  rÐ   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”   rt   r»   r  ÚlabelsrÙ   Úlogits_to_keepra   rV   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”   rt   r»   r  rÙ   N)Úlossr  r»   r‡   rã   rÛ   )râ   r  rm   rÆ   Úslicer  rE   Úfinal_logit_softcappingr.   ÚtanhÚloss_functionr  r   r»   r‡   rã   )r&   r  r”   rt   r»   r  r  rÙ   r  ra   Úoutputsr‡   Úslice_indicesr  r!  s                  r(   r8   zNanoChatForCausalLM.forward¹  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_planÚ
_fsdp_planr%   r   r   r.   rÞ   r{   r   r  rß   rÆ   r   r   r   r8   r?   r@   s   @r(   r  r  ¨  si  ø€ € € € € à*Ð,GÐHÐØÐ2Ð3€HØ˜_Ð-°¨zÐ:Ð;€HàÐ/Ð0€Jð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 ˜$‘;ðB
ð ˜eœlÑ*ðB
ð Ð+Ô,ðB
ð 
 ðB
ð B
ð B
ñ „^ñ ÔðB
ð B
ð B
ð B
ð B
r)   r  )rá   rû   r  )r   )r�   )@rë   Úcollections.abcr   r.   Útorch.nnrP   Ú r   rç   Úactivationsr   Úcache_utilsr   r   Ú
generationr	   Úintegrationsr
   r   Úmasking_utilsr   Úmodeling_layersr   Úmodeling_outputsr   r   Úmodeling_rope_utilsr   r   Úmodeling_utilsr   r   Úprocessing_utilsr   Úutilsr   r   Úutils.deprecationr   Úutils.genericr   r   r   Úutils.output_capturingr   Úconfiguration_nanochatr   rù   r   rB   r†   r{   rÆ   rŽ   r6   r¤   r€   r©   rÈ   rÓ   rá   rû   r  Ú__all__rÛ   r)   r(   ú<module>r?     sG  ðð* €€€Ø $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 LÐ LÐ LÐ LÐ LÐ LÐ LÐ LØ /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 0Ð 0Ð 0Ð 0Ð 0Ð 0Ø 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6<ð 6<ð 6<ð 6<ð 6<˜bœiñ 6<ô 6<ð 6<ðr 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T
ð T
ð T
ð T
ð T
Ð1°?ñ T
ô T
ñ „ðT
ðn NÐ
MÐ
M€€€r)   