Ë
    ÛÓ^jXU  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jZ                  «      «       Z. G d„ dejZ                  «      Z/d„ Z0 ed«      d8d„«       Z1dejd                  de3d ejd                  fd!„Z4	 d9d"ejZ                  d#ejd                  d$ejd                  d%ejd                  d&ejd                  dz  d'e5d(e5d)e!e#   fd*„Z6 ee1«       G d+„ d,ejZ                  «      «       Z7 G d-„ d.e«      Z8 G d/„ d0ejZ                  «      Z9e$ G d1„ d2e«      «       Z:e$ G d3„ d4e:«      «       Z;e$ G d5„ d6e:e«      «       Z<g d7¢Z=y):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                   óh   ‡ — 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BitNetRMSNormÚepsÚreturnNc                 óŠ   •— t         ‰| �  «        t        j                  t	        j
                  |«      «      | _        || _        y)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      €úu/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/bitnet/modeling_bitnet.pyr'   zBitNetRMSNorm.__init__-   s1   ø€ ô 	‰ÑÔÜ—l‘l¤5§:¡:¨kÓ#:Ó;ˆŒØ #ˆÕó    Úhidden_statesc                 ó"  — |j                   }|j                  t        j                  «      }|j	                  d«      j                  dd¬«      }|t        j                  || j                  z   «      z  }| j                  |j                  |«      z  S )Né   éÿÿÿÿT)Úkeepdim)	ÚdtypeÚtor)   Úfloat32ÚpowÚmeanÚrsqrtr,   r+   )r-   r2   Úinput_dtypeÚvariances       r0   ÚforwardzBitNetRMSNorm.forward5   sy   € Ø#×)Ñ)ˆØ%×(Ñ(¬¯©Ó7ˆØ ×$Ñ$ QÓ'×,Ñ,¨R¸Ð,Ó>ˆØ%¬¯©°H¸t×?TÑ?TÑ4TÓ(UÑUˆØ�{‰{˜]×-Ñ-¨kÓ:Ñ:Ð:r1   c                 ó^   — t        | j                  j                  «      › d| j                  › �S )Nz, eps=)Útupler+   Úshaper,   )r-   s    r0   Ú
extra_reprzBitNetRMSNorm.extra_repr<   s*   € Ü˜Ÿ™×)Ñ)Ó*Ð+¨6°$×2GÑ2GÐ1HÐIÐIr1   )g�íµ ÷Æ°>)
Ú__name__Ú
__module__Ú__qualname__Úfloatr'   r)   ÚTensorr?   rC   Ú__classcell__©r/   s   @r0   r"   r"   +   s7   ø„ ñ$¨ð $¸$õ $ð; U§\¡\ð ;°e·l±ló ;öJr1   r"   c                   ó*   ‡ — e Zd Zdefˆ fd„Zd„ Zˆ xZS )Ú	BitNetMLPÚconfigc                 ó  •— t         ‰| �  «        || _        |j                  | _        |j                  | _        t        j                  | j                  | j                  d¬«      | _        t        j                  | j                  | j                  d¬«      | _        t        j                  | j                  | j                  d¬«      | _	        t        |j                     | _        t        |j                  |j                  ¬«      | _        y )NF©Úbias©r#   )r&   r'   rM   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-   rM   r/   s     €r0   r'   zBitNetMLP.__init__A   sÁ   ø€ Ü‰ÑÔØˆŒØ!×-Ñ-ˆÔØ!'×!9Ñ!9ˆÔÜŸ™ 4×#3Ñ#3°T×5KÑ5KÐRWÔXˆŒÜ—y‘y ×!1Ñ!1°4×3IÑ3IÐPUÔVˆŒÜŸ™ 4×#9Ñ#9¸4×;KÑ;KÐRWÔXˆŒÜ˜V×.Ñ.Ñ/ˆŒÜ)¨&×*BÑ*BÈ×H[ÑH[Ô\ˆÕr1   c           	      ó¦   — | j                  | j                  | j                  | j                  |«      «      | j	                  |«      z  «      «      }|S ©N)rV   rZ   rX   rT   rU   )r-   ÚxrV   s      r0   r?   zBitNetMLP.forwardL   sF   € Ø—N‘N 4×#4Ñ#4°T·[±[ÀÇÁÐPQÓARÓ5SÐVZ×VbÑVbÐcdÓVeÑ5eÓ#fÓgˆ	ØÐr1   )rD   rE   rF   r   r'   r?   rI   rJ   s   @r0   rL   rL   @   s   ø„ ð	]˜|õ 	]ör1   rL   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..Nr5   r4   ©Údim)rB   r)   Úcat)r^   Úx1Úx2s      r0   Úrotate_halfre   Q   sZ   € à	
ˆ3Ð"�!—'‘'˜"‘+ Ñ"Ð"Ð"Ñ	#€BØ	
ˆ3�—‘˜‘˜qÑ Ñ"Ð"Ñ	#€BÜ�9‰9�r�c˜2�Y BÔ'Ð'r1   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	unsqueezere   )ÚqÚkÚcosÚsinÚunsqueeze_dimÚq_embedÚk_embeds          r0   Úapply_rotary_pos_embrp   X   sY   € ð& �-‰-˜Ó
&€CØ
�-‰-˜Ó
&€CØ�3‰wœ; q›>¨CÑ/Ñ0€GØ�3‰wœ; q›>¨CÑ/Ñ0€GØ�GÐÐr1   r2   Ún_repr$   c                 óª   — | j                   \  }}}}|dk(  r| S | dd…dd…ddd…dd…f   j                  |||||«      } | j                  |||z  ||«      S )zÔ
    This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,
    num_key_value_heads, seqlen, head_dim) to (batch, num_attention_heads, seqlen, head_dim)
    r   N)rB   ÚexpandÚreshape)r2   rq   ÚbatchÚnum_key_value_headsÚslenÚhead_dims         r0   Ú	repeat_kvry   r   so   € ð
 2?×1DÑ1DÑ.€EÐ  hØ�‚zØÐØ!¢!¢Q¨ªa²Ð"2Ñ3×:Ñ:¸5ÐBUÐW\Ð^bÐdlÓm€MØ× Ñ  Ð(;¸eÑ(CÀTÈ8ÓTÐTr1   ÚmoduleÚqueryÚkeyÚvalueÚattention_maskÚscalingÚdropoutÚkwargsc                 ó  — t        || j                  «      }t        || j                  «      }	t        j                  ||j	                  dd«      «      |z  }
|�|
|z   }
t
        j                  j                  |
dt        j                  ¬«      j                  |j                  «      }
t
        j                  j                  |
|| j                  ¬«      }
t        j                  |
|	«      }|j	                  dd«      j                  «       }||
fS )Nr4   r   r5   )ra   r7   )ÚpÚtrainingr   )ry   Únum_key_value_groupsr)   ÚmatmulÚ	transposer   Ú
functionalÚsoftmaxr9   r8   r7   r€   r„   Ú
contiguous)rz   r{   r|   r}   r~   r   r€   r�   Ú
key_statesÚvalue_statesÚattn_weightsÚattn_outputs               r0   Úeager_attention_forwardr�   ~   sà   € ô ˜3 × ;Ñ ;Ó<€JÜ˜U F×$?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$Ð$r1   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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' paperrM   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
                  |j*                  ¬«      | _        y )Nrx   g      à¿TrO   rQ   )r&   r'   rM   r’   Úgetattrr.   Únum_attention_headsrx   rv   r…   r   Úattention_dropoutÚ	is_causalr   rS   Úattention_biasÚq_projÚk_projÚv_projÚo_projr"   rY   Úattn_sub_norm©r-   rM   r’   r/   s      €r0   r'   zBitNetAttention.__init__›   sj  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Œô +¨6×+=Ñ+=À6×CVÑCVÔWˆÕr1   Nr2   Úposition_embeddingsr~   Úpast_key_valuesr�   r$   c                 ó,  — |j                   d d }g |¢d‘| j                  ‘­}| j                  |«      j                  |«      j	                  dd«      }| j                  |«      j                  |«      j	                  dd«      }	| j                  |«      j                  |«      j	                  dd«      }
|\  }}t        ||	||«      \  }}	|� |j                  |	|
| j                  «      \  }	}
t        j                  | j                  j                  t        «      } || ||	|
|f| j                  sdn| j                   | j"                  dœ|¤Ž\  }} |j$                  g |¢d‘­Ž j'                  «       }| j)                  |«      }| j+                  |«      }||fS )Nr5   r   r4   ç        )r€   r   )rB   rx   r™   Úviewr‡   rš   r›   rp   Úupdater’   r   Úget_interfacerM   Ú_attn_implementationr�   r„   r–   r   rt   rŠ   r�   rœ   )r-   r2   rŸ   r~   r    r�   Úinput_shapeÚhidden_shapeÚquery_statesr‹   rŒ   rk   rl   Úattention_interfacerŽ   r�   s                   r0   r?   zBitNetAttention.forward³   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×(Ñ(¨Ó5ˆØ—k‘k +Ó.ˆØ˜LÐ(Ð(r1   r]   )rD   rE   rF   Ú__doc__r   Úintr'   r)   rH   rA   r   r   r   r?   rI   rJ   s   @r0   r‘   r‘   —   s    ø„ áGðX˜|ð X¸õ Xð: )-ñ')à—|‘|ð')ð # 5§<¡<°·±Ð#=Ñ>ð')ð Ÿ™ tÑ+ð	')ð
  ™ð')ð Ð-Ñ.ð')ð 
ˆu�|‰|˜UŸ\™\¨DÑ0Ð0Ñ	1÷')r1   r‘   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BitNetDecoderLayerrM   r’   c                 ó   •— t         ‰| �  «        |j                  | _        t        ||¬«      | _        t        |«      | _        t        |j                  |j                  ¬«      | _	        t        |j                  |j                  ¬«      | _
        y )N)rM   r’   rQ   )r&   r'   r.   r‘   Ú	self_attnrL   Úmlpr"   rY   Úinput_layernormÚpost_attention_layernormrž   s      €r0   r'   zBitNetDecoderLayer.__init__Þ   sl   ø€ Ü‰ÑÔØ!×-Ñ-ˆÔä(°À)ÔLˆŒä˜VÓ$ˆŒÜ,¨V×-?Ñ-?ÀV×EXÑEXÔYˆÔÜ(5°f×6HÑ6HÈf×NaÑNaÔ(bˆÕ%r1   Nr2   r~   Úposition_idsr    Ú	use_cacherŸ   r�   r$   c           
      óÀ   — |}| j                  |«      } | j                  d||||||dœ|¤Ž\  }}	||z   }|}| j                  |«      }| j                  |«      }||z   }|S )N)r2   r~   r´   r    rµ   rŸ   © )r²   r°   r³   r±   )
r-   r2   r~   r´   r    rµ   rŸ   r�   ÚresidualÚ_s
             r0   r?   zBitNetDecoderLayer.forwardè   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r1   )NNNFN)rD   rE   rF   r   r¬   r'   r)   rH   Ú
LongTensorr   ÚboolrA   r   r   r?   rI   rJ   s   @r0   r®   r®   Ý   s¾   ø„ ðc˜|ð c¸õ cð /3Ø04Ø(,Ø!&ØHLñà—|‘|ðð Ÿ™ tÑ+ðð ×&Ñ&¨Ñ-ð	ð
  ™ðð ˜$‘;ðð # 5§<¡<°·±Ð#=Ñ>ÀÑEðð Ð+Ñ,ðð 
�‰÷r1   r®   c                   óÄ   ‡ — e Zd ZU ej                  ed<   ddefˆ fd„Ze	 	 	 ddedz  de	d   de
dz  ded	ef   fd
„«       Z ej                  «       ed„ «       «       Zˆ xZS )ÚBitNetRotaryEmbeddingÚinv_freqNrM   c                 ó®  •— t         ‰| �  «        |j                  | _        |j                  | _        || _        | j
                  j                  d   | _        | j                  }| j                  dk7  rt        | j                     } || j
                  |«      \  }| _
        | j                  d|d¬«       | j                  d|j                  «       d¬«       y )NÚ	rope_typeÚdefaultr¾   F)Ú
persistentÚoriginal_inv_freq)r&   r'   Úmax_position_embeddingsÚmax_seq_len_cachedÚoriginal_max_seq_lenrM   Úrope_parametersrÀ   Úcompute_default_rope_parametersr   Úattention_scalingÚregister_bufferÚclone)r-   rM   ÚdeviceÚrope_init_fnr¾   r/   s        €r0   r'   zBitNetRotaryEmbedding.__init__  s¶   ø€ Ü‰ÑÔØ"(×"@Ñ"@ˆÔØ$*×$BÑ$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�$Ô(à×Ñ˜Z¨¸eÐÔDØ×ÑÐ0°(·.±.Ó2BÈuÐÕUr1   rÌ   ztorch.deviceÚseq_lenr$   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_thetarx   Ng      ð?r   r4   ©r7   )rÌ   r7   )	rÇ   r”   r.   r•   r)   ÚarangeÚint64r8   rG   )rM   rÌ   rÎ   Úbasera   Úattention_factorr¾   s          r0   rÈ   z5BitNetRotaryEmbedding.compute_default_rope_parameters  s�   € ð& ×%Ñ% lÑ3ˆÜ�f˜j¨$Ó/Òc°6×3EÑ3EÈ×IcÑIcÑ3cˆàÐð Ø”U—\‘\ ! S¨!´5·;±;Ô?×BÑBÈ&ÔX]×XcÑXcÐBÓdÐgjÑjÑkñ
ˆð Ð)Ð)Ð)r1   c                 óN  — | j                   d d d …d f   j                  «       j                  |j                  d   dd«      j	                  |j
                  «      }|d d …d d d …f   j                  «       }t        |j
                  j                  t        «      r/|j
                  j                  dk7  r|j
                  j                  nd}t        |d¬«      5  |j                  «       |j                  «       z  j                  dd«      }t        j                  ||fd¬	«      }|j                  «       | j                  z  }|j                  «       | j                  z  }	d d d «       j	                  |j                   ¬
«      	j	                  |j                   ¬
«      fS # 1 sw Y   ŒAxY w)Nr   r5   r   ÚmpsÚcpuF)Údevice_typeÚenabledr4   r`   rÑ   )r¾   rG   rs   rB   r8   rÌ   Ú
isinstanceÚtypeÚstrr   r‡   r)   rb   rk   rÉ   rl   r7   )
r-   r^   r´   Úinv_freq_expandedÚposition_ids_expandedrÙ   ÚfreqsÚembrk   rl   s
             r0   r?   zBitNetRotaryEmbedding.forward9  sR  € ð !ŸM™M¨$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$r]   )NNN)rD   rE   rF   r)   rH   Ú__annotations__r   r'   Ústaticmethodr   r¬   rA   rG   rÈ   Úno_gradr   r?   rI   rJ   s   @r0   r½   r½     s˜   ø… Ø�l‰lÓñV˜|õ Vð  à&*Ø+/Ø"ñ*Ø˜tÑ#ð*à˜Ñ(ð*ð �t‘ð*ð 
ˆ~˜uÐ$Ñ	%ò	*ó ð*ð: €U‡]�]ƒ_Øñ<ó ó ô<r1   r½   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BitNetPreTrainedModelrM   ÚmodelTr®   r    )r2   Ú
attentionsN)rD   rE   rF   r   râ   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·   r1   r0   ræ   ræ   I  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r1   ræ   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BitNetModelrM   c           	      ó  •— t         ‰| �  |«       |j                  | _        |j                  | _        t        j                  |j                  |j                  | j                  «      | _        t        j                  t        |j                  «      D �cg c]  }t        ||«      ‘Œ c}«      | _        t        |j                  |j                  ¬«      | _        t#        |¬«      | _        d| _        | j)                  «        y c c}w )NrQ   ©rM   F)r&   r'   Úpad_token_idÚpadding_idxÚ
vocab_sizer   Ú	Embeddingr.   Úembed_tokensÚ
ModuleListÚrangeÚnum_hidden_layersr®   Úlayersr"   rY   Únormr½   Ú
rotary_embÚgradient_checkpointingÚ	post_initrž   s      €r0   r'   zBitNetModel.__init__^  sÆ   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‘mÜDIÈ&×JbÑJbÓDcÖd°yÔ ¨	Õ2Òdó
ˆŒô " &×"4Ñ"4¸&×:MÑ:MÔNˆŒ	Ü/°vÔ>ˆŒØ&+ˆÔ#ð 	�‰Õùò es   ÂDNÚ	input_idsr~   r´   r    Úinputs_embedsrµ   r�   r$   c           
      ó<  — |d u |d uz  rt        d«      ‚|€| j                  |«      }|r|€t        | j                  ¬«      }|€V|�|j	                  «       nd}t        j                  |j                  d   |j                  ¬«      |z   }|j                  d«      }t        | j                  ||||¬«      }	|}
| j                  |
|¬«      }| j                  d | j                  j                   D ]  } ||
f|	||||dœ|¤Ž}
Œ | j                  |
«      }
t        |
|¬	«      S )
Nz:You must specify exactly one of input_ids or inputs_embedsrö   r   r   )rÌ   )rM   r  r~   r    r´   )r´   )r~   rŸ   r´   r    rµ   )Úlast_hidden_stater    )Ú
ValueErrorrû   r	   rM   Úget_seq_lengthr)   rÒ   rB   rÌ   rh   r   r  rÿ   rþ   r   r   )r-   r  r~   r´   r    r  rµ   r�   Úpast_seen_tokensÚcausal_maskr2   rŸ   Údecoder_layers                r0   r?   zBitNetModel.forwardn  sL  € ð ˜Ð -°tÐ";Ò<ÜÐYÓZÐZàÐ Ø*.×*;Ñ*;¸IÓ*FˆMá˜Ð0Ü*°$·+±+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$7Ø)Ø /Ø#ñð ñ‰Mð		ð Ÿ	™	 -Ó0ˆÜ&Ø+Ø+ô
ð 	
r1   )NNNNNN)rD   rE   rF   r   r'   r   r   r   r)   rº   rH   r   ÚFloatTensorr»   r   r   r   r?   rI   rJ   s   @r0   rô   rô   \  sÍ   ø„ ð˜|õ ð   ØØð .2Ø.2Ø04Ø(,Ø26Ø!%ñ2
à×#Ñ# dÑ*ð2
ð Ÿ™ tÑ+ð2
ð ×&Ñ&¨Ñ-ð	2
ð
  ™ð2
ð ×(Ñ(¨4Ñ/ð2
ð ˜$‘;ð2
ð Ð+Ñ,ð2
ð 
!ò2
ó ó ó  ô2
r1   rô   c                   ó2  ‡ — 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                 óè   •— t         ‰| �  |«       t        |«      | _        |j                  | _        t        j                  |j                  |j                  d¬«      | _        | j                  «        y )NFrO   )
r&   r'   rô   rç   rù   r   rS   r.   Úlm_headr  r[   s     €r0   r'   zBitNetForCausalLM.__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r1   r  r~   r´   r    r  Úlabelsrµ   Úlogits_to_keepr�   r$   c	           
      óx  —  | j                   d||||||dœ|	¤Ž}
|
j                  }t        |t        «      rt	        | d«      n|}| j                  |dd…|dd…f   «      }d}|�* | j                  d||| j                  j                  dœ|	¤Ž}t        |||
j                  |
j                  |
j                  ¬«      S )a$  
        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~   r´   r    r  rµ   N)Úlogitsr  rù   )Úlossr  r    r2   rè   r·   )rç   r  rÛ   r¬   Úslicer  Úloss_functionrM   rù   r   r    r2   rè   )r-   r  r~   r´   r    r  r  rµ   r  r�   Úoutputsr2   Úslice_indicesr  r  s                  r0   r?   zBitNetForCausalLM.forwardµ  sÚ   € ðH ,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 	
r1   )NNNNNNNr   )rD   rE   rF   Ú_tied_weights_keysÚ_tp_planÚ_pp_planr'   r   r   r)   rº   rH   r   r  r»   r¬   r   r   r   r?   rI   rJ   s   @r0   r  r  ¦  s  ø„ à*Ð,GÐHÐØ€HØ€Hôð Øð .2Ø.2Ø04Ø(,Ø26Ø*.Ø!%Ø-.ñ;
à×#Ñ# dÑ*ð;
ð Ÿ™ tÑ+ð;
ð ×&Ñ&¨Ñ-ð	;
ð
  ™ð;
ð ×(Ñ(¨4Ñ/ð;
ð × Ñ  4Ñ'ð;
ð ˜$‘;ð;
ð ˜eŸl™lÑ*ð;
ð Ð+Ñ,ð;
ð 
 ò;
ó ó ô;
r1   r  )r  rô   ræ   )r   )r¢   )>Úcollections.abcr   Útypingr   r)   r   Úactivationsr   Úcache_utilsr   r	   Ú
generationr
   Úintegrationsr   r   r   Úmasking_utilsr   Úmodeling_flash_attention_utilsr   Úmodeling_layersr   Úmodeling_outputsr   r   Úmodeling_rope_utilsr   r   Úmodeling_utilsr   r   Úprocessing_utilsr   Úutilsr   r   r   Úutils.genericr   r   Úutils.output_capturingr   Úconfiguration_bitnetr   ÚModuler"   rL   re   rp   rH   r¬   ry   rG   r�   r‘   r®   r½   ræ   rô   r  Ú__all__r·   r1   r0   ú<module>r1     sä  ðõ( %Ý ã Ý å !ß .Ý )ß fÑ fÝ /Ý BÝ 9ß Oß Kß FÝ &ß IÑ Iß GÝ 5Ý .ñ ˜YÓ'ôJ�B—I‘Ió Jó (ðJô(�—	‘	ô ò"(ñ Ð*Ó+òó ,ðð2	U˜UŸ\™\ð 	U°#ð 	U¸%¿,¹,ó 	Uð& ñ%Ø�I‰Ið%à�<‰<ð%ð 
�‰ð%ð �<‰<ð	%ð
 —L‘L 4Ñ'ð%ð ð%ð ð%ð Ð'Ñ(ó%ñ2 Ð)Ó*ôB)�b—i‘ió B)ó +ðB)ôJ(Ð3ô (ôV><˜BŸI™Iô ><ðB ô˜Oó ó ðð$ ôF
Ð'ó F
ó ðF
ðR ôK
Ð-¨ó K
ó ðK
ò\ H�r1   