§
    ‚ŠtjXU  ã                   óX  — d dl mZ d dlmZ d dlZd dlmZ ddlmZ ddlm	Z	m
Z
 ddlmZ dd	lmZmZmZ dd
lmZ ddlmZ 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,  ed¦  «         G d„ dej-        ¦  «        ¦   «         Z. G d„ dej-        ¦  «        Z/d„ Z0 ed¦  «        d9d„¦   «         Z1dej2        de3d ej2        fd!„Z4	 d:d#ej-        d$ej2        d%ej2        d&ej2        d'ej2        dz  d(e5d)e5d*e!e#         fd+„Z6 ee1¦  «         G d,„ d-ej-        ¦  «        ¦   «         Z7 G d.„ d/e¦  «        Z8 G d0„ d1ej-        ¦  «        Z9e$ G d2„ d3e¦  «        ¦   «         Z:e$ G d4„ d5e:¦  «        ¦   «         Z;e$ G d6„ d7e:e¦  «        ¦   «         Z<g d8¢Z=dS );é    )ÚCallable)ÚOptionalN)Únné   )ÚACT2FN)ÚCacheÚDynamicCache)ÚGenerationMixin)Úuse_kernel_forward_from_hubÚuse_kernel_func_from_hubÚuse_kernelized_func)Úcreate_causal_mask)ÚFlashAttentionKwargs)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BitNetConfigÚRMSNormc                   óT   ‡ — e Zd Zd	deddfˆ fd„Zdej        dej        fd„Zd„ Zˆ xZ	S )
ÚBitNetRMSNormç�íµ ÷Æ°>ÚepsÚreturnNc                 ó¬   •— t          ¦   «                              ¦   «          t          j        t	          j        |¦  «        ¦  «        | _        || _        dS )z<
        BitNetRMSNorm is equivalent to T5LayerNorm
        N)ÚsuperÚ__init__r   Ú	ParameterÚtorchÚonesÚweightÚvariance_epsilon)ÚselfÚhidden_sizer$   Ú	__class__s      €úh/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/transformers/models/bitnet/modeling_bitnet.pyr(   zBitNetRMSNorm.__init__-   sD   ø€ õ 	‰Œ×ÒÑÔÐÝ”l¥5¤:¨kÑ#:Ô#:Ñ;Ô;ˆŒØ #ˆÔÐÐó    Úhidden_statesc                 ó  — |j         }|                     t          j        ¦  «        }|                     d¦  «                             dd¬¦  «        }|t          j        || j        z   ¦  «        z  }| j        |                     |¦  «        z  S )Né   éÿÿÿÿT)Úkeepdim)	ÚdtypeÚtor*   Úfloat32ÚpowÚmeanÚrsqrtr-   r,   )r.   r3   Úinput_dtypeÚvariances       r1   ÚforwardzBitNetRMSNorm.forward5   s|   € Ø#Ô)ˆØ%×(Ò(­¬Ñ7Ô7ˆØ ×$Ò$ QÑ'Ô'×,Ò,¨R¸Ð,Ñ>Ô>ˆØ%­¬°H¸tÔ?TÑ4TÑ(UÔ(UÑUˆØŒ{˜]×-Ò-¨kÑ:Ô:Ñ:Ð:r2   c                 óH   — t          | j        j        ¦  «        › d| j        › �S )Nz, eps=)Útupler,   Úshaper-   )r.   s    r1   Ú
extra_reprzBitNetRMSNorm.extra_repr<   s&   € Ý˜œÔ)Ñ*Ô*ÐIÐI°$Ô2GÐIÐIÐIr2   )r#   )
Ú__name__Ú
__module__Ú__qualname__Úfloatr(   r*   ÚTensorr@   rD   Ú__classcell__©r0   s   @r1   r"   r"   +   sŒ   ø€ € € € € ð$ð $¨ð $¸$ð $ð $ð $ð $ð $ð $ð; U¤\ð ;°e´lð ;ð ;ð ;ð ;ðJð Jð Jð Jð Jð Jð Jr2   r"   c                   ó*   ‡ — e Zd Zdefˆ fd„Zd„ Zˆ xZS )Ú	BitNetMLPÚconfigc                 óØ  •— t          ¦   «                              ¦   «          || _        |j        | _        |j        | _        t          j        | j        | j        d¬¦  «        | _        t          j        | j        | j        d¬¦  «        | _        t          j        | j        | j        d¬¦  «        | _	        t          |j                 | _        t          |j        |j        ¬¦  «        | _        d S )NF©Úbias©r$   )r'   r(   rN   r/   Úintermediate_sizer   ÚLinearÚ	gate_projÚup_projÚ	down_projr   Ú
hidden_actÚact_fnr"   Úrms_norm_epsÚffn_sub_norm©r.   rN   r0   s     €r1   r(   zBitNetMLP.__init__A   sÃ   ø€ Ý‰Œ×ÒÑÔÐØˆŒØ!Ô-ˆÔØ!'Ô!9ˆÔÝœ 4Ô#3°TÔ5KÐRWÐXÑXÔXˆŒÝ”y Ô!1°4Ô3IÐPUÐVÑVÔVˆŒÝœ 4Ô#9¸4Ô;KÐRWÐXÑXÔXˆŒÝ˜VÔ.Ô/ˆŒÝ)¨&Ô*BÈÔH[Ð\Ñ\Ô\ˆÔÐÐr2   c           	      óÎ   — |                       |                      |                      |                      |¦  «        ¦  «        |                      |¦  «        z  ¦  «        ¦  «        }|S ©N)rW   r[   rY   rU   rV   )r.   ÚxrW   s      r1   r@   zBitNetMLP.forwardL   sU   € Ø—N’N 4×#4Ò#4°T·[²[ÀÇÂÐPQÑARÔARÑ5SÔ5SÐVZ×VbÒVbÐcdÑVeÔVeÑ5eÑ#fÔ#fÑgÔgˆ	ØÐr2   )rE   rF   rG   r   r(   r@   rJ   rK   s   @r1   rM   rM   @   sZ   ø€ € € € € ð	]˜|ð 	]ð 	]ð 	]ð 	]ð 	]ð 	]ðð ð ð ð ð ð r2   rM   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..Nr6   r5   ©Údim)rC   r*   Úcat)r_   Úx1Úx2s      r1   Úrotate_halfrf   Q   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   X   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   r3   Ún_repr%   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)rC   ÚexpandÚreshape)r3   rr   ÚbatchÚnum_key_value_headsÚslenÚhead_dims         r1   Ú	repeat_kvrz   r   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 )Nr5   r   r6   )rb   r8   )ÚpÚtrainingr   )rz   Únum_key_value_groupsr*   ÚmatmulÚ	transposer   Ú
functionalÚsoftmaxr:   r9   r8   r‚   r†   Ú
contiguous)r|   r}   r~   r   r€   r�   r‚   rƒ   Ú
key_statesÚvalue_statesÚattn_weightsÚattn_outputs               r1   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$Ð$r2   c                   óÊ   ‡ — 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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BitNetAttentionz=Multi-headed attention from 'Attention Is All You Need' paperrN   Ú	layer_idxc                 óî  •— 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        |j        ¬¦  «        | _        d S )Nry   g      à¿TrP   rR   )r'   r(   rN   r”   Úgetattrr/   Únum_attention_headsry   rw   r‡   r�   Úattention_dropoutÚ	is_causalr   rT   Úattention_biasÚq_projÚk_projÚv_projÚo_projr"   rZ   Úattn_sub_norm©r.   rN   r”   r0   s      €r1   r(   zBitNetAttention.__init__›   sa  ø€ Ý‰Œ×ÒÑÔÐØˆŒØ"ˆŒÝ ¨
°FÔ4FÈ&ÔJdÑ4dÑeÔeˆŒØ$*Ô$>À&ÔB\Ñ$\ˆÔ!Ø”} dÑ*ˆŒØ!'Ô!9ˆÔØˆŒå”iØÔ Ô :¸T¼]Ñ JÐQWÔQfð
ñ 
ô 
ˆŒõ ”iØÔ Ô :¸T¼]Ñ JÐQWÔQfð
ñ 
ô 
ˆŒõ ”iØÔ Ô :¸T¼]Ñ JÐQWÔQfð
ñ 
ô 
ˆŒõ ”iØÔ&¨¬Ñ6¸Ô8JÐQWÔQfð
ñ 
ô 
ˆŒõ +¨6Ô+=À6ÔCVÐWÑWÔWˆÔÐÐr2   Nr3   Úposition_embeddingsr€   Úpast_key_valuesrƒ   r%   c                 óL  — |j         d d…         }g |¢d‘| j        ‘R }|                      |¦  «                             |¦  «                             dd¦  «        }|                      |¦  «                             |¦  «                             dd¦  «        }	|                      |¦  «                             |¦  «                             dd¦  «        }
|\  }}t          ||	||¦  «        \  }}	|�|                     |	|
| j	        ¦  «        \  }	}
t          j        | j        j        t          ¦  «        } || ||	|
|f| j        sdn| j        | j        dœ|¤Ž\  }} |j        g |¢d‘R Ž                      ¦   «         }|                      |¦  «        }|                      |¦  «        }||fS )Nr6   r   r5   r{   )r‚   r�   )rC   ry   r›   Úviewr‰   rœ   r�   rq   Úupdater”   r   Úget_interfacerN   Ú_attn_implementationr‘   r†   r˜   r�   ru   rŒ   rŸ   rž   )r.   r3   r¡   r€   r¢   rƒ   Úinput_shapeÚhidden_shapeÚquery_statesr�   rŽ   rl   rm   Úattention_interfacer�   r�   s                   r1   r@   zBitNetAttention.forward³   sÓ  € ð $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×(Ò(¨Ñ5Ô5ˆØ—k’k +Ñ.Ô.ˆØ˜LÐ(Ð(r2   r^   )rE   rF   rG   Ú__doc__r   Úintr(   r*   rI   rB   r   r   r   r@   rJ   rK   s   @r1   r“   r“   —   så   ø€ € € € € àGÐGðX˜|ð X¸ð Xð Xð Xð Xð Xð Xð: )-ð')ð ')à”|ð')ð # 5¤<°´Ð#=Ô>ð')ð œ tÑ+ð	')ð
  ™ð')ð Ð-Ô.ð')ð 
ˆuŒ|˜Uœ\¨DÑ0Ð0Ô	1ð')ð ')ð ')ð ')ð ')ð ')ð ')ð ')r2   r“   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BitNetDecoderLayerrN   r”   c                 ó4  •— t          ¦   «                              ¦   «          |j        | _        t          ||¬¦  «        | _        t          |¦  «        | _        t          |j        |j        ¬¦  «        | _	        t          |j        |j        ¬¦  «        | _
        d S )N)rN   r”   rR   )r'   r(   r/   r“   Ú	self_attnrM   Úmlpr"   rZ   Úinput_layernormÚpost_attention_layernormr    s      €r1   r(   zBitNetDecoderLayer.__init__Þ   sƒ   ø€ Ý‰Œ×ÒÑÔÐØ!Ô-ˆÔå(°À)ÐLÑLÔLˆŒå˜VÑ$Ô$ˆŒÝ,¨VÔ-?ÀVÔEXÐYÑYÔYˆÔÝ(5°fÔ6HÈfÔNaÐ(bÑ(bÔ(bˆÔ%Ð%Ð%r2   NFr3   r€   Úposition_idsr¢   Ú	use_cacher¡   rƒ   r%   c           
      óÎ   — |}|                       |¦  «        } | j        d||||||dœ|¤Ž\  }}	||z   }|}|                      |¦  «        }|                      |¦  «        }||z   }|S )N)r3   r€   rµ   r¢   r¶   r¡   © )r³   r±   r´   r²   )
r.   r3   r€   rµ   r¢   r¶   r¡   rƒ   ÚresidualÚ_s
             r1   r@   zBitNetDecoderLayer.forwardè   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)rE   rF   rG   r   r­   r(   r*   rI   Ú
LongTensorr   ÚboolrB   r   r   r@   rJ   rK   s   @r1   r¯   r¯   Ý   sÿ   ø€ € € € € ðc˜|ð c¸ð cð cð cð cð cð cð /3Ø04Ø(,Ø!&ØHLðð à”|ðð œ tÑ+ðð Ô&¨Ñ-ð	ð
  ™ðð ˜$‘;ðð # 5¤<°´Ð#=Ô>ÀÑEðð Ð+Ô,ðð 
Œðð ð ð ð ð ð ð r2   r¯   c                   óÔ   ‡ — e Zd ZU ej        ed<   ddefˆ fd„Ze	 	 	 ddedz  de	d         de
dz  ded	ef         fd
„¦   «         Z ej        ¦   «         ed„ ¦   «         ¦   «         Zˆ xZS )ÚBitNetRotaryEmbeddingÚinv_freqNrN   c                 ó²  •— t          ¦   «                              ¦   «          |j        | _        |j        | _        || _        | j        j        d         | _        | j        }| j        dk    rt          | j                 } || j        |¦  «        \  }| _
        |                      d|d¬¦  «         |                      d|                     ¦   «         d¬¦  «         d S )NÚ	rope_typeÚdefaultr¿   F)Ú
persistentÚoriginal_inv_freq)r'   r(   Úmax_position_embeddingsÚmax_seq_len_cachedÚoriginal_max_seq_lenrN   Úrope_parametersrÁ   Úcompute_default_rope_parametersr   Úattention_scalingÚregister_bufferÚclone)r.   rN   ÚdeviceÚrope_init_fnr¿   r0   s        €r1   r(   zBitNetRotaryEmbedding.__init__  sÊ   ø€ Ý‰Œ×ÒÑÔÐØ"(Ô"@ˆÔØ$*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   rÍ   ztorch.deviceÚseq_lenr%   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_thetary   Ng      ð?r   r5   ©r8   )rÍ   r8   )	rÈ   r–   r/   r—   r*   ÚarangeÚint64r9   rH   )rN   rÍ   rÏ   Úbaserb   Úattention_factorr¿   s          r1   rÉ   z5BitNetRotaryEmbedding.compute_default_rope_parameters  sŒ   € ð& Ô% lÔ3ˆÝ�f˜j¨$Ñ/Ô/Ðc°6Ô3EÈÔIcÑ3cˆàÐð Ø•U”\ ! S¨!µ5´;Ð?Ñ?Ô?×BÒBÈ&ÕX]ÔXcÐBÑdÔdÐgjÑjÑkñ
ˆð Ð)Ð)Ð)r2   c                 óN  — | j         d d d …d f                              ¦   «                              |j        d         dd¦  «                             |j        ¦  «        }|d d …d d d …f                              ¦   «         }t          |j        j        t          ¦  «        r|j        j        dk    r|j        j        nd}t          |d¬¦  «        5  |                     ¦   «         |                     ¦   «         z   
                    dd¦  «        }t          j        ||fd¬	¦  «        }|                     ¦   «         | j        z  }|                     ¦   «         | j        z  }	d d d ¦  «         n# 1 swxY w Y   |                     |j        ¬
¦  «        |	                     |j        ¬
¦  «        fS )Nr   r6   r   ÚmpsÚcpuF)Údevice_typeÚenabledr5   ra   rÒ   )r¿   rH   rt   rC   r9   rÍ   Ú
isinstanceÚtypeÚstrr   r‰   r*   rc   rl   rÊ   rm   r8   )
r.   r_   rµ   Úinv_freq_expandedÚposition_ids_expandedrÚ   ÚfreqsÚembrl   rm   s
             r1   r@   zBitNetRotaryEmbedding.forward9  s·  € ð !œM¨$°°°°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)rE   rF   rG   r*   rI   Ú__annotations__r   r(   Ústaticmethodr   r­   rB   rH   rÉ   Úno_gradr   r@   rJ   rK   s   @r1   r¾   r¾     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˜tÑ#ð*à˜Ô(ð*ð �t‘ð*ð 
ˆ~˜uÐ$Ô	%ð	*ð *ð *ñ „\ð*ð: €U„]�_„_Øð<ð <ñ Ôñ „_ð<ð <ð <ð <ð <r2   r¾   c                   óL   — e Zd ZU eed<   dZdZdgZdgZdZ	dZ
dZdZdZeedœZdS )ÚBitNetPreTrainedModelrN   ÚmodelTr¯   r¢   )r3   Ú
attentionsN)rE   rF   rG   r   rã   Úbase_model_prefixÚsupports_gradient_checkpointingÚ_no_split_modulesÚ_skip_keys_device_placementÚ_supports_flash_attnÚ_supports_sdpaÚ_supports_flex_attnÚ_can_compile_fullgraphÚ_supports_attention_backendr¯   r“   Ú_can_record_outputsr¸   r2   r1   rç   rç   I  sl   € € € € € € àÐÐÑØÐØ&*Ð#Ø-Ð.ÐØ#4Ð"5ÐØÐØ€NØÐà!ÐØ"&Ðà+Ø%ðð ÐÐÐr2   rç   c                   óâ   ‡ — e Zd Zdefˆ fd„Zeee	 	 	 	 	 	 ddej	        dz  dej
        dz  dej	        dz  dedz  dej        dz  d	edz  d
ee         defd„¦   «         ¦   «         ¦   «         Zˆ xZS )ÚBitNetModelrN   c                 óÞ  •‡— t          ¦   «                              ‰¦  «         ‰j        | _        ‰j        | _        t          j        ‰j        ‰j        | j        ¦  «        | _        t          j	        ˆfd„t          ‰j        ¦  «        D ¦   «         ¦  «        | _        t          ‰j        ‰j        ¬¦  «        | _        t!          ‰¬¦  «        | _        d| _        |                      ¦   «          d S )Nc                 ó0   •— g | ]}t          ‰|¦  «        ‘ŒS r¸   )r¯   )Ú.0r”   rN   s     €r1   ú
<listcomp>z(BitNetModel.__init__.<locals>.<listcomp>e  s$   ø€ ÐdÐdÐd°yÕ ¨	Ñ2Ô2ÐdÐdÐdr2   rR   ©rN   F)r'   r(   Úpad_token_idÚpadding_idxÚ
vocab_sizer   Ú	Embeddingr/   Úembed_tokensÚ
ModuleListÚrangeÚnum_hidden_layersÚlayersr"   rZ   Únormr¾   Ú
rotary_embÚgradient_checkpointingÚ	post_initr\   s    `€r1   r(   zBitNetModel.__init__^  sÔ   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dÐdÐdÐdÅEÈ&ÔJbÑDcÔDcÐdÑdÔdñ
ô 
ˆŒõ " &Ô"4¸&Ô:MÐNÑNÔNˆŒ	Ý/°vÐ>Ñ>Ô>ˆŒØ&+ˆÔ#ð 	�ŠÑÔÐÐÐr2   NÚ	input_idsr€   rµ   r¢   Úinputs_embedsr¶   rƒ   r%   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_embedsrú   r   r   )rÍ   )rN   r	  r€   r¢   rµ   )rµ   )r€   r¡   rµ   r¢   r¶   )Úlast_hidden_stater¢   )Ú
ValueErrorrÿ   r	   rN   Úget_seq_lengthr*   rÓ   rC   rÍ   ri   r   r  r  r  r  r   )r.   r  r€   rµ   r¢   r	  r¶   rƒ   Úpast_seen_tokensÚcausal_maskr3   r¡   Údecoder_layers                r1   r@   zBitNetModel.forwardn  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$7Ø)Ø /Ø#ðð ð ðð ˆMˆMð Ÿ	š	 -Ñ0Ô0ˆÝ&Ø+Ø+ð
ñ 
ô 
ð 	
r2   )NNNNNN)rE   rF   rG   r   r(   r   r   r   r*   r»   rI   r   ÚFloatTensorr¼   r   r   r   r@   rJ   rK   s   @r1   rõ   rõ   \  s  ø€ € € € € ð˜|ð ð ð ð ð ð ð   ØØð .2Ø.2Ø04Ø(,Ø26Ø!%ð2
ð 2
àÔ# dÑ*ð2
ð œ tÑ+ð2
ð Ô&¨Ñ-ð	2
ð
  ™ð2
ð Ô(¨4Ñ/ð2
ð ˜$‘;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   rõ   c                   ó  ‡ — e Zd ZddiZdZd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BitNetForCausalLMzlm_head.weightzmodel.embed_tokens.weightNc                 óþ   •— t          ¦   «                              |¦  «         t          |¦  «        | _        |j        | _        t          j        |j        |j        d¬¦  «        | _        |  	                    ¦   «          d S )NFrP   )
r'   r(   rõ   rè   rý   r   rT   r/   Úlm_headr  r\   s     €r1   r(   zBitNetForCausalLM.__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   r   r  r€   rµ   r¢   r	  Úlabelsr¶   Úlogits_to_keeprƒ   r%   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 )a$  
        labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
            Labels for computing the masked language modeling loss. Indices should either be in `[0, transformers.,
            config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored
            (masked), the loss is only computed for the tokens with labels in `[0, transformers., config.vocab_size]`.

        Example:

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

        >>> model = BitNetForCausalLM.from_pretrained("microsoft/bitnet-b1.58-2B-4T")
        >>> tokenizer = AutoTokenizer.from_pretrained("microsoft/bitnet-b1.58-2B-4T")

        >>> prompt = f'<|begin_of_text|>User: Hey, are you conscious? Can you talk to me?<|eot_id|>Assistant: '
        >>> inputs = tokenizer(prompt, return_tensors="pt")

        >>> # Generate
        >>> generate_ids = model.generate(inputs.input_ids, max_length=100)
        >>> tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
        "User: Hey, are you conscious? Can you talk to me?Assistant: No, I'm not conscious. I'm an artificial intelligence designed to assist with information and tasks. How can I help you today?"
        ```)r  r€   rµ   r¢   r	  r¶   N)Úlogitsr  rý   )Úlossr  r¢   r3   ré   r¸   )rè   r  rÜ   r­   Úslicer  Úloss_functionrN   rý   r   r¢   r3   ré   )r.   r  r€   rµ   r¢   r	  r  r¶   r  rƒ   Úoutputsr3   Úslice_indicesr  r  s                  r1   r@   zBitNetForCausalLM.forwardµ  sõ   € ðH ,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   )rE   rF   rG   Ú_tied_weights_keysÚ_tp_planÚ_pp_planr(   r   r   r*   r»   rI   r   r  r¼   r­   r   r   r   r@   rJ   rK   s   @r1   r  r  ¦  s6  ø€ € € € € à*Ð,GÐHÐØ€HØ€Hðð ð ð ð ð Øð .2Ø.2Ø04Ø(,Ø26Ø*.Ø!%Ø-.ð;
ð ;
àÔ# dÑ*ð;
ð œ tÑ+ð;
ð Ô&¨Ñ-ð	;
ð
  ™ð;
ð Ô(¨4Ñ/ð;
ð Ô  4Ñ'ð;
ð ˜$‘;ð;
ð ˜eœlÑ*ð;
ð Ð+Ô,ð;
ð 
 ð;
ð ;
ð ;
ñ „^ñ Ôð;
ð ;
ð ;
ð ;
ð ;
r2   r  )r  rõ   rç   )r   )r{   )>Úcollections.abcr   Útypingr   r*   r   Úactivationsr   Úcache_utilsr   r	   Ú
generationr
   Úintegrationsr   r   r   Úmasking_utilsr   Úmodeling_flash_attention_utilsr   Úmodeling_layersr   Úmodeling_outputsr   r   Úmodeling_rope_utilsr   r   Úmodeling_utilsr   r   Úprocessing_utilsr   Úutilsr   r   r   Úutils.genericr   r   Úutils.output_capturingr   Úconfiguration_bitnetr   ÚModuler"   rM   rf   rq   rI   r­   rz   rH   r‘   r“   r¯   r¾   rç   rõ   r  Ú__all__r¸   r2   r1   ú<module>r5     sb  ðð( %Ð $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 fÐ fÐ fÐ fÐ fÐ fÐ fÐ fÐ fÐ fØ /Ð /Ð /Ð /Ð /Ð /Ø BÐ BÐ BÐ BÐ BÐ BØ 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˜YÑ'Ô'ðJð Jð Jð Jð J�B”Iñ Jô Jñ (Ô'ðJð(ð ð ð ð �”	ñ 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B)ð B)ð B)ð B)ð B)�b”iñ B)ô B)ñ +Ô*ðB)ðJ(ð (ð (ð (ð (Ð3ñ (ô (ð (ðV><ð ><ð ><ð ><ð ><˜BœIñ ><ô ><ð ><ðB ðð ð ð ð ˜Oñ ô ñ „ðð$ ðF
ð F
ð F
ð F
ð F
Ð'ñ F
ô F
ñ „ðF
ðR ðK
ð K
ð K
ð K
ð K
Ð-¨ñ K
ô K
ñ „ðK
ð\ HÐ
GÐ
G€€€r2   