
    hk                        d dl mZmZmZ d dlZd dlmc 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 dd	lmZmZ dd
lmZ ddlmZ ddlmZmZ ddlmZmZ ddlm Z m!Z! ddl"m#Z# ddl$m%Z%m&Z&m'Z' ddl(m)Z) ddl*m+Z+ ddl,m-Z-  ed       G d dej\                               Z/ G d dej\                        Z0d Z1d:dZ2dejf                  de4dejf                  fdZ5	 d;d ej\                  d!ejf                  d"ejf                  d#ejf                  d$eejf                     d%e6d&e6d'e#e%   fd(Z7 G d) d*ej\                        Z8 G d+ d,ej\                        Z9 G d- d.ej\                        Z: G d/ d0ej\                        Z; G d1 d2e      Z<e& G d3 d4e!             Z=e& G d5 d6e=             Z>e& G d7 d8e=e             Z?g d9Z@y)<    )CallableOptionalUnionN)nn   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_forward_from_hub)create_causal_mask!create_sliding_window_causal_mask)FlashAttentionKwargs)GradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuple)deprecate_kwarg)check_model_inputs   )Dots1ConfigRMSNormc                   h     e Zd Zddeddf fdZdej                  dej                  fdZd Z xZ	S )	Dots1RMSNormepsreturnNc                     t         |           t        j                  t	        j
                  |            | _        || _        y)z;
        Dots1RMSNorm is equivalent to T5LayerNorm
        N)super__init__r   	Parametertorchonesweightvariance_epsilon)selfhidden_sizer"   	__class__s      f/var/www/html/eduruby.in/venv/lib/python3.12/site-packages/transformers/models/dots1/modeling_dots1.pyr&   zDots1RMSNorm.__init__.   s1     	ll5::k#:; #    hidden_statesc                 "   |j                   }|j                  t        j                        }|j	                  d      j                  dd      }|t        j                  || j                  z         z  }| j                  |j                  |      z  S )N   T)keepdim)	dtypetor(   float32powmeanrsqrtr+   r*   )r,   r1   input_dtypevariances       r/   forwardzDots1RMSNorm.forward6   sy    #))%((7 $$Q',,R,>%Ht?T?T4T(UU{{]--k:::r0   c                 ^    t        | j                  j                         d| j                   S )Nz, eps=)tupler*   shaper+   )r,   s    r/   
extra_reprzDots1RMSNorm.extra_repr=   s*    ))*+6$2G2G1HIIr0   )gư>)
__name__
__module____qualname__floatr&   r(   Tensorr>   rB   __classcell__r.   s   @r/   r!   r!   ,   s7    $ $$ $;U\\ ;ell ;Jr0   r!   c                   ~     e Zd ZU ej                  ed<   ddef fdZ ej                         e	d               Z
 xZS )Dots1RotaryEmbeddinginv_freqconfigc                    t         |           t        |d      rUt        |j                  t
              r;|j                  j                  d|j                  j                  d            | _        nd| _        |j                  | _	        |j                  | _
        || _        t        | j                     | _        | j                  | j                  |      \  }| _        | j                  d|d       | j                   | _        y )Nrope_scaling	rope_typetypedefaultrL   F)
persistent)r%   r&   hasattr
isinstancerO   dictgetrP   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrM   r   rope_init_fnattention_scalingregister_bufferrL   original_inv_freq)r,   rM   devicerL   r.   s       r/   r&   zDots1RotaryEmbedding.__init__D   s    6>*z&:M:Mt/T#0044[&BUBUBYBYZ`BabDN&DN"("@"@$*$B$B!/?+/+<+<T[[&+Q($(ZeD!%r0   c                 b   | 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        j                  |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   AxY w)Nr   r4   r   mpscpuF)device_typeenabledr3   dimr6   )rL   rF   expandrA   r7   r_   rU   rQ   strr(   autocast	transposecatcosr\   sinr6   )
r,   xposition_idsinv_freq_expandedposition_ids_expandedrc   freqsembrm   rn   s
             r/   r>   zDots1RotaryEmbedding.forwardU   sV    !MM$4-8>>@GGHZHZ[\H]_acdehhijiqiqr ,QaZ 8 > > @'1!((--'E!((--[`J`ahhmmfk^^UC 	5&,,.1F1L1L1NNYYZ[]^_E))UEN3C'')d444C'')d444C		5 vvAGGv$cff177f&;;;	5 	5s    BF%%F.N)rC   rD   rE   r(   rG   __annotations__r   r&   no_gradr   r>   rH   rI   s   @r/   rK   rK   A   s=    ll/{ /" U]]_<  <r0   rK   c                     | 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..Nr4   r3   re   )rA   r(   rl   )ro   x1x2s      r/   rotate_halfr{   e   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r0   c                     |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.
        position_ids (`torch.Tensor`, *optional*):
            Deprecated and unused.
        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.
    )	unsqueezer{   )qkrm   rn   rp   unsqueeze_dimq_embedk_embeds           r/   apply_rotary_pos_embr   l   sY    ( --
&C
--
&C3w;q>C/0G3w;q>C/0GGr0   r1   n_repr#   c                     | j                   \  }}}}|dk(  r| S | dddddddddf   j                  |||||      } | j                  |||z  ||      S )z
    This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,
    num_key_value_heads, seqlen, head_dim) to (batch, num_attention_heads, seqlen, head_dim)
    r   N)rA   rh   reshape)r1   r   batchnum_key_value_headsslenhead_dims         r/   	repeat_kvr      so    
 2?1D1D.Ehz!!Qa"23::5BUW\^bdlmM  (;e(CT8TTr0   modulequerykeyvalueattention_maskscalingdropoutkwargsc                 T   t        || j                        }t        || j                        }	t        j                  ||j	                  dd            |z  }
|#|d d d d d d d |j
                  d   f   }|
|z   }
t        j                  j                  |
dt        j                        j                  |j                        }
t        j                  j                  |
|| j                        }
t        j                  |
|	      }|j	                  dd      j                         }||
fS )Nr3   r   r4   )rf   r6   )ptrainingr   )r   num_key_value_groupsr(   matmulrk   rA   r   
functionalsoftmaxr8   r7   r6   r   r   
contiguous)r   r   r   r   r   r   r   r   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r/   eager_attention_forwardr      s    3 ; ;<JUF$?$?@L<<z';';Aq'ABWLL!$Q1.D
0@0@0D.D%DE#k1==((2U]](SVVW\WbWbcL==((6??([L,,|\:K''1-88:K$$r0   c                   0    e Zd ZdZdedef fdZ eddd      	 	 dd	ej                  d
e
ej                  ej                  f   deej                     dee   deej                     dee   de
ej                  eej                     f   fd       Z xZS )Dots1Attentionz=Multi-headed attention from 'Attention Is All You Need' paperrM   	layer_idxc                 R   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*                        | _        t)        | j                  |j*                        | _        |j0                  |   dk(  r|j2                  | _        y d | _        y )Nr   g      Tbiasr"   sliding_attention)r%   r&   rM   r   getattrr-   num_attention_headsr   r   r   r   attention_dropout	is_causalr   Linearattention_biasq_projk_projv_projo_projr!   rms_norm_epsq_normk_normlayer_typessliding_windowr,   rM   r   r.   s      r/   r&   zDots1Attention.__init__   s   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
 #4==f6I6IJ"4==f6I6IJ7=7I7I)7TXk7kf33qur0   past_key_valuepast_key_values4.58new_nameversionr1   position_embeddingsr   cache_positionr   r#   c                    |j                   d d }g |d| j                  }| j                  | j                  |      j	                  |            j                  dd      }	| j                  | j                  |      j	                  |            j                  dd      }
| j                  |      j	                  |      j                  dd      }|\  }}t        |	|
||      \  }	}
|'|||d}|j                  |
|| j                  |      \  }
}t        }| j                  j                  dk7  rt        | j                  j                     } || |	|
||f| j                   sdn| j"                  | j$                  | j&                  d|\  }} |j(                  g |d j+                         }| j-                  |      }||fS )Nr4   r   r3   )rn   rm   r   eager        )r   r   r   )rA   r   r   r   viewrk   r   r   r   r   updater   r   rM   _attn_implementationr   r   r   r   r   r   r   r   )r,   r1   r   r   r   r   r   input_shapehidden_shapequery_statesr   r   rm   rn   cache_kwargsattention_interfacer   r   s                     r/   r>   zDots1Attention.forward   s    $))#2.88b8$--8{{4;;}#=#B#B<#PQ[[\]_`a[[]!;!@!@!NOYYZ[]^_
{{=166|DNNqRST&S#7jRUWZ#[ j&#&snUL'6'='=j,X\XfXfht'u$J(?;;++w6"9$++:Z:Z"[$7
%
  $}}C$2H2HLL..
%
 
%
!\ *k));;;;FFHkk+.L((r0   NN)rC   rD   rE   __doc__r   intr&   r   r(   rG   r@   r   r	   
LongTensorr   r   r>   rH   rI   s   @r/   r   r      s    Gv{ vs v4 %0A6R ,059*)||*) #5<<#=>*) !.	*)
 "%*) !!1!12*) -.*) 
u||Xell33	4*) S*)r0   r   c                   &     e Zd Zd fd	Zd Z xZS )Dots1MLPc                    t         |           || _        ||j                  n|| _        ||j                  n|| _        t        j                  | j                  | j                  d      | _        t        j                  | j                  | j                  d      | _        t        j                  | j                  | j                  d      | _	        t        |j                     | _        y NFr   )r%   r&   rM   r-   intermediate_sizer   r   	gate_projup_proj	down_projr   
hidden_actact_fn)r,   rM   r-   r   r.   s       r/   r&   zDots1MLP.__init__   s    1<1D6--+=N=V!9!9\m4#3#3T5K5KRWXyy!1!143I3IPUV4#9#94;K;KRWXV../r0   c                     | j                  | j                  | j                  |            | j                  |      z        }|S ru   )r   r   r   r   )r,   ro   r   s      r/   r>   zDots1MLP.forward  s6    NN4;;t~~a/@#ADLLQRO#ST	r0   r   )rC   rD   rE   r&   r>   rH   rI   s   @r/   r   r      s    	0r0   r   c                   x     e Zd ZdZ fdZdej                  dej                  dej                  fdZd Z xZ	S )Dots1MoEz:
    A mixed expert module containing shared experts.
    c           	      L   t         |           || _        t        j                  t        |j                        D cg c]  }t        ||j                         c}      | _	        t        |      | _        t        ||j                  |j                  z        | _        y c c}w )N)r   )rM   r   )r%   r&   rM   r   
ModuleListrangen_routed_expertsr   moe_intermediate_sizeexpertsDots1TopkRoutergaten_shared_expertsshared_experts)r,   rM   _r.   s      r/   r&   zDots1MoE.__init__  s    }}W\]c]t]tWuvRSXf0L0LMv
 $F+	&V-I-IFLcLc-c
 ws   B!r1   topk_indicestopk_weightsc                 X   t        j                  ||j                        }t         j                  j                  j                  |t        | j                              }|j                  ddd      }t        t        | j                              D ]}  }| j                  |   }||   }t        j                  |      \  }	}
|	j                         dkD  sC||	|
f   }||	   } ||      }||j                  d      z  }|j                  d|	|        |j                  |j                        S )z
        CALL FOR CONTRIBUTION! I don't have time to optimise this right now, but expert weights need to be fused
        to not have to do a loop here (deepseek has 256 experts soooo yeah).
        rg   )num_classesr3   r   r   r4   )r(   
zeros_liker6   r   r   one_hotlenr   permuter   wherenumelr}   
index_add_rQ   )r,   r1   r   r   final_hidden_statesexpert_mask
expert_idxexpertmasktoken_indicesweight_indicesexpert_weightsexpert_inputexpert_outputweighted_outputs                  r/   moezDots1MoE.moe  s   
 $..}LDVDVWhh))11,CPTP\P\L]1^!))!Q2DLL 12 
	RJ\\*-Fz*D,1KK,=)M>""$q(!-m^.K!L,]; &| 4"/.2J2J22N"N#..q-Q
	R #''(;(;<<r0   c                     |}|j                   }| j                  |      \  }}|j                  d|j                   d         } | j                  |||      j                  | }|| j	                  |      z   }|S )Nr4   )rA   r   r   r   r   )r,   r1   	residuals
orig_shaper   r   s         r/   r>   zDots1MoE.forward3  s}    !	"((
%)YY}%="l%**2}/B/B2/FGPlKPPR\]%(;(;I(FFr0   )
rC   rD   rE   r   r&   r(   rG   r   r>   rH   rI   s   @r/   r   r   	  s;    	
= =U\\ =Y^YeYe =4r0   r   c                   R     e Zd Z fdZ ej
                         d        Zd Z xZS )r   c                    t         |           || _        |j                  | _        |j
                  | _        |j                  | _        |j                  | _        |j                  | _        |j                  | _	        t        j                  t        j                  | j
                  |j                  f            | _        | j!                  dt        j"                  | j
                               y )Ne_score_correction_bias)r%   r&   rM   num_experts_per_toktop_kr   routed_scaling_factorn_group
topk_groupnorm_topk_probr   r'   r(   emptyr-   r*   r]   zerosr,   rM   r.   s     r/   r&   zDots1TopkRouter.__init__>  s    //
 & 7 7%+%A%A"~~ ++$33ll5;;0E0EvGYGY/Z#[\6DDYDY8Z[r0   c                 
   |j                  d| j                        | j                  j                  d      z   }|j                  d| j                  | j                  | j                  z        j                  dd      d   j                  d      }t        j
                  || j                  dd      d   }t        j                  |      }|j                  d|d       |j                  d      j                  d| j                  | j                  | j                  z        j                  d| j                        }|j                  |j                          d      }t        j
                  || j                  dd      d   }|S )	Nr4   r   r3   re   F)r   rf   sortedr   r   )r   r   r  r}   r
  topksumr(   r  r   scatter_rh   r   masked_fillboolr  )r,   scoresscores_for_choicegroup_scores	group_idx
group_mask
score_maskr   s           r/   get_topk_indicesz Dots1TopkRouter.get_topk_indicesK  sF   "KKD,A,ABTEaEaEkEklmEnn""2t||T5J5Jdll5Z[T!T_Q SRS[ 	
 JJ|tBuUVWX	%%l3
Ay!,  $VBd&;&;t||&KLWR../ 	
 .99:??;L:LcRzz"3tzzrRWXYZ[r0   c                    |j                  d| j                  j                        }t        j                  |j                  t        j                        | j                  j                  t        j                              }|j                         }| j                  |      }|j                  d|      }| j                  r|j                  dd      dz   }||z  }|| j                  z  }||fS )Nr4   r   T)rf   r5   g#B;)r   rM   r-   FlinearrQ   r(   r8   r*   sigmoidr  gatherr  r  r	  )r,   r1   router_logitsr  r   r   denominators          r/   r>   zDots1TopkRouter.forward_  s    %**2t{{/F/FG!3!3EMM!BDKKDTDTUZUbUbDcd&&(,,V4}}Q5&**r4*@5HKK'L#d&@&@@\))r0   )	rC   rD   rE   r&   r(   rw   r  r>   rH   rI   s   @r/   r   r   =  s*    \ U]]_ &
*r0   r   c                   >    e Zd Zdedef fdZ eddd      	 	 	 	 	 	 ddej                  d	e	ej                     d
e	ej                     de	e   de	e   de	ej                     de	eej                  ej                  f      dee   dej                  fd       Z xZS )Dots1DecoderLayerrM   r   c                    t         |           |j                  | _        t        ||      | _        ||j
                  k\  rt        |      | _        nt        |      | _        t        |j                  |j                        | _        t        |j                  |j                        | _        |j                  |   | _        y )N)rM   r   r   )r%   r&   r-   r   	self_attnfirst_k_dense_replacer   mlpr   r!   r   input_layernormpost_attention_layernormr   attention_typer   s      r/   r&   zDots1DecoderLayer.__init__m  s    !--'vK444'DH'DH+F,>,>FDWDWX(4V5G5GVM`M`(a%$00;r0   r   r   r   r   r1   r   rp   	use_cacher   r   r   r#   c                     |}	| j                  |      } | j                  d|||||||d|\  }}
|	|z   }|}	| j                  |      }| j                  |      }|	|z   }|S )N)r1   r   rp   r   r.  r   r    )r+  r(  r,  r*  )r,   r1   r   rp   r   r.  r   r   r   residualr   s              r/   r>   zDots1DecoderLayer.forward|  s     !,,];)4>> 	
')%+) 3	
 	
q !=0 !55mD/ =0r0   )NNNFNN)rC   rD   rE   r   r   r&   r   r(   rG   r   r   r	   r  r@   r   r   r>   rH   rI   s   @r/   r&  r&  l  s    <{ <s < %0A6R 2637+/$)59KO|| !. u//0	
 "% D> !!1!12 &eELL%,,,F&GH +, 
 Sr0   r&  c                   \     e Zd ZU eed<   dZdZdgZdgZdZ	dZ
dZdZdZeedZ fdZ xZS )	Dots1PreTrainedModelrM   modelTr&  r   F)r1   
attentionsc                     t         |   |       t        |t              r<|j                  j
                  j                  d| j                  j                         y y )Nr   )r:   std)	r%   _init_weightsrU   r   r*   datanormal_rM   initializer_range)r,   r   r.   s     r/   r8  z"Dots1PreTrainedModel._init_weights  sF    f%fo.MM&&CT[[5R5R&S /r0   )rC   rD   rE   r   rv   base_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_supports_sdpa_supports_flex_attn_can_compile_fullgraph_supports_attention_backendr&  r   _can_record_outputsr8  rH   rI   s   @r/   r3  r3    s^    &*#,-#4"5N""&*$
T Tr0   r3  c                       e Zd Zdef fdZee	 	 	 	 	 	 	 ddeej                     deej                     deej                     dee   deej                     dee   d	eej                     d
ee   defd              Z xZS )
Dots1ModelrM   c           	      F   t         |   |       |j                  | _        |j                  | _        t        j                  |j                  |j                  | j                        | _        t        j                  t        |j                        D cg c]  }t        ||       c}      | _        t        |j                  |j                        | _        t#        |      | _        d| _        d| j(                  j*                  v | _        | j/                          y c c}w )Nr   rM   Fr   )r%   r&   pad_token_idpadding_idx
vocab_sizer   	Embeddingr-   embed_tokensr   r   num_hidden_layersr&  layersr!   r   normrK   
rotary_embgradient_checkpointingrM   r   has_sliding_layers	post_initr   s      r/   r&   zDots1Model.__init__  s     !.. ++LL):):F<N<NPTP`P`ammCHIaIaCbcivy1c
 !!3!39L9LM	.f=&+#"59P9P"P 	 ds   D	input_idsr   rp   r   inputs_embedsr.  r   r   r#   c                    |d u |d uz  rt        d      || j                  |      }|r|t        | j                        }|F||j	                         nd}	t        j                  |	|	|j                  d   z   |j                        }||j                  d      }t        |x}
t              s:| j                  |||||d}dt        di |i}
| j                  rt        di ||
d<   |}| j                  ||      }| j                   d | j                  j"                   D ]  } ||f|
|j$                     |||||d	|}! | j'                  |      }t)        ||r|
      S d 
      S )Nz:You must specify exactly one of input_ids or inputs_embedsrI  r   r   )r_   )rM   input_embedsr   r   r   rp   full_attentionr   )r   rp   r   r.  r   r   )last_hidden_stater   r0  )
ValueErrorrN  r
   rM   get_seq_lengthr(   arangerA   r_   r}   rU   rV   r   rT  r   rR  rP  rO  r-  rQ  r   )r,   rV  r   rp   r   rW  r.  r   r   past_seen_tokenscausal_mask_mappingmask_kwargsr1   r   decoder_layers                  r/   r>   zDots1Model.forward  s    -t";<YZZ  --i8M0*$++>O!CRC^==?de"\\ "2]5H5H5K"KTaThThN )33A6L ?-F ++ -"0"0#2 ,K !"4"C{"C# &&;\;k_j;k#$78% #oom\J![[)H4;;+H+HI 
	M)	2=3O3OP) /#-$7	 	M
	 		-0&+/8O
 	
>B
 	
r0   )NNNNNNN)rC   rD   rE   r   r&   r   r   r   r(   r   rG   r	   FloatTensorr  r   r   r   r>   rH   rI   s   @r/   rG  rG    s    { "  151537+/59$(59E
E,,-E
 !.E
 u//0	E

 "%E
   1 12E
 D>E
 !!1!12E
 +,E
 
!E
  E
r0   rG  c                   d    e Zd ZdgZddiZddgdgfiZ fdZee	 	 	 	 	 	 	 	 	 dde	e
j                     de	e
j                     d	e	e
j                     d
e	e   de	e
j                     de	e
j                     de	e   de	e
j                     deee
j                  f   dee   defd              Z xZS )Dots1ForCausalLMzlm_head.weightlm_headcolwise_repr1   logitsc                     t         |   |       t        |      | _        |j                  | _        t        j                  |j                  |j                  d      | _        | j                          y r   )
r%   r&   rG  r4  rL  r   r   r-   rf  rU  r  s     r/   r&   zDots1ForCausalLM.__init__  sU     '
 ++yy!3!3V5F5FUS 	r0   rV  r   rp   r   rW  labelsr.  r   logits_to_keepr   r#   c
                 z    | j                   d|||||||d|
}|j                  }t        |	t              rt	        |	 d      n|	}| j                  |dd|ddf         }d}|* | j                  d||| j                  j                  d|
}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, ...,
            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, ..., config.vocab_size]`.

        Example:

        ```python
        >>> from transformers import AutoTokenizer, Dots1ForCausalLM

        >>> model = Dots1ForCausalLM.from_pretrained("rednote-hilab/dots1.llm1.inst")
        >>> tokenizer = AutoTokenizer.from_pretrained("rednote-hilab/dots1.llm1.inst")

        >>> prompt = "Hey, are you conscious? Can you talk to me?"
        >>> inputs = tokenizer(prompt, return_tensors="pt")

        >>> # Generate
        >>> generate_ids = model.generate(inputs.input_ids, max_length=30)
        >>> tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
        "Hey, are you conscious? Can you talk to me?\nI'm not conscious, but I can talk to you."
        ```)rV  r   rp   r   rW  r.  r   N)rh  rj  rL  )lossrh  r   r1   r5  r0  )r4  r[  rU   r   slicerf  loss_functionrM   rL  r   r   r1   r5  )r,   rV  r   rp   r   rW  rj  r.  r   rk  r   outputsr1   slice_indicesrh  rm  s                   r/   r>   zDots1ForCausalLM.forward"  s    J ,64:: 	,
)%+')	,
 	,
  118B>SV8W~ot4]kmA}a,?@A%4%%pVFt{{OeOepiopD%#33!//))
 	
r0   )	NNNNNNNNr   )rC   rD   rE   _tied_weights_keys_tp_plan_pp_planr&   r   r   r   r(   r   rG   r	   rc  r  r   r   r   r   r   r>   rH   rI   s   @r/   re  re    s0   *+=)H_-z:;H  151537+/59-1$(5934=
E,,-=
 !.=
 u//0	=

 "%=
   1 12=
 ))*=
 D>=
 !!1!12=
 c5<</0=
 +,=
 
 =
  =
r0   re  )r3  rG  re  )Nr   )r   )Atypingr   r   r   r(   torch.nn.functionalr   r   r  activationsr   cache_utilsr	   r
   
generationr   integrationsr   masking_utilsr   r   modeling_flash_attention_utilsr   modeling_layersr   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.deprecationr   utils.genericr   configuration_dots1r   Moduler!   rK   r{   r   rG   r   r   rF   r   r   r   r   r   r&  r3  rG  re  __all__r0  r0   r/   <module>r     s  * - ,     ! . ) 7 R B 9 O K F & I I 0 / , Y'J299 J (J(!<299 !<H(6	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 U\\*% % % '(%4H)RYY H)Vryy "1ryy 1h,*bii ,*^02 0f T? T T, Y
% Y
 Y
x M
+_ M
 M
` Er0   