
    rhj                     z   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$m%Z%m&Z&m'Z' ddl(m)Z) ddl*m+Z+  ed       G d dejX                               Z- G d dejX                        Z.d Z/d9dZ0dejb                  de2dejb                  fdZ3	 d:dejX                  d ejb                  d!ejb                  d"ejb                  d#eejb                     d$e4d%e4d&e#e%   fd'Z5 G d( d)ejX                        Z6 G d* d+ejX                        Z7 G d, d-ejX                        Z8 G d. d/ejX                        Z9 G d0 d1e      Z:e& G d2 d3e!             Z;e& G d4 d5e;             Z<e& G d6 d7e;e             Z=g d8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)check_model_inputs   )Dots1ConfigRMSNormc                   ,     e Zd Zd fd	Zd Zd Z xZS )Dots1RMSNormc                     t         |           t        j                  t	        j
                  |            | _        || _        y)z;
        Dots1RMSNorm is equivalent to T5LayerNorm
        N)super__init__r   	Parametertorchonesweightvariance_epsilon)selfhidden_sizeeps	__class__s      {/var/www/html/ai-insurance-compliance-backend/venv/lib/python3.12/site-packages/transformers/models/dots1/modeling_dots1.pyr#   zDots1RMSNorm.__init__-   s1     	ll5::k#:; #    c                 "   |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)   hidden_statesinput_dtypevariances       r-   forwardzDots1RMSNorm.forward5   sy    #))%((7 $$Q',,R,>%Ht?T?T4T(UU{{]--k:::r.   c                 ^    t        | j                  j                         d| j                   S )Nz, eps=)tupler'   shaper(   r)   s    r-   
extra_reprzDots1RMSNorm.extra_repr<   s*    ))*+6$2G2G1HIIr.   )gư>)__name__
__module____qualname__r#   r<   rA   __classcell__r,   s   @r-   r    r    +   s    $;Jr.   r    c                   ^     e Zd Zddef fdZ ej                         ed               Z xZ	S )Dots1RotaryEmbedding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defaultinv_freqF)
persistent)r"   r#   hasattr
isinstancerK   dictgetrL   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrI   r   rope_init_fnattention_scalingregister_bufferrO   original_inv_freq)r)   rI   devicerO   r,   s       r-   r#   zDots1RotaryEmbedding.__init__A   s    6>*z&:M:Mt/T#0044[&BUBUBYBYZ`BabDN&DN"("@"@$*$B$B!/?+/+<+<T[[&+Q($(ZeD!%r.   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   r1   r   mpscpuF)device_typeenabledr0   dimr3   )rO   floatexpandr?   r4   r\   rR   rM   strr%   autocast	transposecatcosrY   sinr3   )
r)   xposition_idsinv_freq_expandedposition_ids_expandedr`   freqsembrk   rl   s
             r-   r<   zDots1RotaryEmbedding.forwardR   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)
rB   rC   rD   r   r#   r%   no_gradr   r<   rE   rF   s   @r-   rH   rH   @   s3    /{ /" U]]_<  <r.   rH   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..Nr1   r0   rb   )r?   r%   rj   )rm   x1x2s      r-   rotate_halfrx   b   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r.   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.
    )	unsqueezerx   )qkrk   rl   rn   unsqueeze_dimq_embedk_embeds           r-   apply_rotary_pos_embr   i   sY    ( --
&C
--
&C3w;q>C/0G3w;q>C/0GGr.   r9   n_repreturnc                     | 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)r?   rf   reshape)r9   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Tr.   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 )Nr0   r   r1   )rc   r3   )ptrainingr   )r   num_key_value_groupsr%   matmulri   r?   r   
functionalsoftmaxr5   r4   r3   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$$r.   c                   6    e Zd ZdZdedef fdZ	 	 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                     e
e	ej                        f   fdZ xZS )Dots1Attentionz=Multi-headed attention from 'Attention Is All You Need' paperrI   	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#   rI   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)   rI   r   r,   s      r-   r#   zDots1Attention.__init__   s   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
 #4==f6I6IJ"4==f6I6IJ7=7I7I)7TXk7kf33qur.   r9   position_embeddingsr   past_key_valuecache_positionr   r   c                    |j                   d d }g |d| j                  }| j                  | j                  |      j	                  |            j                  dd      }	| j                  | j                  |      j	                  |            j                  dd      }
| j                  |      j	                  |      j                  dd      }|\  }}t        |	|
||      \  }	}
|'|||d}|j                  |
|| j                  |      \  }
}t        }| j                  j                  dk7  rt        | j                  j                     } || |	|
||f| j                   sdn| j"                  | j$                  | j&                  d|\  }} |j(                  g |d j+                         }| j-                  |      }||fS )Nr1   r   r0   )rl   rk   r   eager        )r   r   r   )r?   r   r   r   viewri   r   r   r   r   updater   r   rI   _attn_implementationr   r   r   r   r   r   r   r   )r)   r9   r   r   r   r   r   input_shapehidden_shapequery_statesr   r   rk   rl   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'5'<'<ZW[WeWegs't$J(?;;++w6"9$++:Z:Z"[$7
%
  $}}C$2H2HLL..
%
 
%
!\ *k));;;;FFHkk+.L((r.   NN)rB   rC   rD   __doc__r   intr#   r%   Tensorr>   r   r	   
LongTensorr   r   r<   rE   rF   s   @r-   r   r      s    Gv{ vs v> +/59*)||*) #5<<#=>*) !.	*)
 !*) !!1!12*) -.*) 
u||Xell3XeELL>Q5RR	S*)r.   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#   rI   r*   intermediate_sizer   r   	gate_projup_proj	down_projr   
hidden_actact_fn)r)   rI   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../r.   c                     | j                  | j                  | j                  |            | j                  |      z        }|S rs   )r   r   r   r   )r)   rm   r   s      r-   r<   zDots1MLP.forward   s6    NN4;;t~~a/@#ADLLQRO#ST	r.   r   )rB   rC   rD   r#   r<   rE   rF   s   @r-   r   r      s    	0r.   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   )rI   r   )r"   r#   rI   r   
ModuleListrangen_routed_expertsr   moe_intermediate_sizeexpertsDots1TopkRoutergaten_shared_expertsshared_experts)r)   rI   _r,   s      r-   r#   zDots1MoE.__init__
  s    }}W\]c]t]tWuvRSXf0L0LMv
 $F+	&V-I-IFLcLc-c
 ws   B!r9   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).
        rd   )num_classesr0   r   r   r1   )r%   
zeros_liker3   r   r   one_hotlenr   permuter   wherenumelrz   
index_add_rM   )r)   r9   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>""$q(!-m^.K!L,]; &| 4"/.2J2J22N"N#..q-Q
	R #''(;(;<<r.   c                     |}|j                   }| j                  |      \  }}|j                  d|j                   d         } | j                  |||      j                  | }|| j	                  |      z   }|S )Nr1   )r?   r   r   r   r   )r)   r9   	residuals
orig_shaper   r   s         r-   r<   zDots1MoE.forward/  s}    !	"((
%)YY}%="l%**2}/B/B2/FGPlKPPR\]%(;(;I(FFr.   )
rB   rC   rD   r   r#   r%   r   r   r<   rE   rF   s   @r-   r   r     s;    	
= =U\\ =Y^YeYe =4r.   r   c                   R     e Zd Z fdZ ej
                         d        Zd Z xZS )r   c                    t         |           || _        |j                  | _        |j
                  | _        |j                  | _        |j                  | _        |j                  | _        |j                  | _	        t        j                  t        j                  | j
                  |j                  f            | _        | j!                  dt        j"                  | j
                               y )Ne_score_correction_bias)r"   r#   rI   num_experts_per_toktop_kr   routed_scaling_factorn_group
topk_groupnorm_topk_probr   r$   r%   emptyr*   r'   rZ   zerosr)   rI   r,   s     r-   r#   zDots1TopkRouter.__init__:  s    //
 & 7 7%+%A%A"~~ ++$33ll5;;0E0EvGYGY/Z#[\6DDYDY8Z[r.   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 )	Nr1   r   r0   rb   F)r|   rc   sortedr   r   )r   r   r   rz   r  topksumr%   r  r   scatter_rf   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_indicesG  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[r.   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 )Nr1   r   T)rc   r2   g#B;)r   rI   r*   FlinearrM   r%   r5   r'   sigmoidr  gatherr  r  r  )r)   r9   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&@&@@\))r.   )	rB   rC   rD   r#   r%   rt   r  r<   rE   rF   s   @r-   r   r   9  s*    \ U]]_ &
*r.   r   c                   (    e Zd Zdedef fdZ	 	 	 	 	 	 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ej                     fdZ xZS )Dots1DecoderLayerrI   r   c                    t         |           |j                  | _        t        ||      | _        ||j
                  k\  rt        |      | _        nt        |      | _        t        |j                  |j                        | _        t        |j                  |j                        | _        |j                  |   | _        y )N)rI   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__i  s    !--'vK444'DH'DH+F,>,>FDWDWX(4V5G5GVM`M`(a%$00;r.   r9   r   rn   r   	use_cacher   r   r   r   c                     |}	| j                  |      } | j                  d|||||||d|\  }}
|	|z   }|}	| j                  |      }| j                  |      }|	|z   }|S )N)r9   r   rn   r   r(  r   r    )r%  r"  r&  r$  )r)   r9   r   rn   r   r(  r   r   r   residualr   s              r-   r<   zDots1DecoderLayer.forwardx  s     !,,];)4>> 	
')%)) 3	
 	
q !=0 !55mD/ =0r.   )NNNFNN)rB   rC   rD   r   r   r#   r%   r   r   r   r	   r  r>   r   r   r<   rE   rF   s   @r-   r   r   h  s    <{ <s <$ 2637*.$)59KO|| !. u//0	
 ! D> !!1!12 &eELL%,,,F&GH +, 
u||	r.   r   c                   \     e Zd ZU eed<   dZdZdgZdgZdZ	dZ
dZdZdZeedZ fdZ xZS )Dots1PreTrainedModelrI   modelTr   past_key_values)r9   
attentionsc                     t         |   |       t        |t              r<|j                  j
                  j                  d| j                  j                         y y )Nr   )r7   std)	r"   _init_weightsrR   r   r'   datanormal_rI   initializer_range)r)   r   r,   s     r-   r3  z"Dots1PreTrainedModel._init_weights  sF    f%fo.MM&&CT[[5R5R&S /r.   )rB   rC   rD   r   __annotations__base_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_supports_sdpa_supports_flex_attn_can_compile_fullgraph_supports_attention_backendr   r   _can_record_outputsr3  rE   rF   s   @r-   r-  r-    s^    &*#,-#4"5N!"&*$
T Tr.   r-  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 )
Dots1ModelrI   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   )rI   Fr   )r"   r#   pad_token_idpadding_idx
vocab_sizer   	Embeddingr*   embed_tokensr   r   num_hidden_layersr   layersr    r   normrH   
rotary_embgradient_checkpointingrI   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   rn   r/  inputs_embedsr(  r   r   r   c                    |d u |d uz  rt        d      || j                  |      }|r|
t               }|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_embedsr   r   )r\   )rI   input_embedsr   r   r/  rn   full_attentionr   )r   rn   r   r(  r   r   )last_hidden_stater/  r*  )
ValueErrorrI  r
   get_seq_lengthr%   aranger?   r\   rz   rR   rS   rI   r   rO  r   rM  rK  rJ  r'  rL  r   )r)   rQ  r   rn   r/  rR  r(  r   r   past_seen_tokenscausal_mask_mappingmask_kwargsr9   r   decoder_layers                  r-   r<   zDots1Model.forward  s    -t";<YZZ  --i8M0*nO!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).#-$7	 	M
	 		-0&+/8O
 	
>B
 	
r.   )NNNNNNN)rB   rC   rD   r   r#   r   r   r   r%   r   r   r	   FloatTensorr  r   r   r   r<   rE   rF   s   @r-   rC  rC    s    { "  151537+/59$(59E
E,,-E
 !.E
 u//0	E

 "%E
   1 12E
 D>E
 !!1!12E
 +,E
 
!E
  E
r.   rC  c                   p    e Zd ZdgZddiZddgdgfiZ fdZd Z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_repr9   logitsc                     t         |   |       t        |      | _        |j                  | _        t        j                  |j                  |j                  d      | _        | j                          y r   )
r"   r#   rC  r.  rG  r   r   r*   ra  rP  r	  s     r-   r#   zDots1ForCausalLM.__init__  sU     '
 ++yy!3!3V5F5FUS 	r.   c                     || _         y rs   r.  )r)   decoders     r-   set_decoderzDots1ForCausalLM.set_decoder  s	    
r.   c                     | j                   S rs   rf  r@   s    r-   get_decoderzDots1ForCausalLM.get_decoder!  s    zzr.   rQ  r   rn   r/  rR  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."
        ```)rQ  r   rn   r/  rR  r(  r   N)rc  rk  rG  )lossrc  r/  r9   r0  r*  )r.  rV  rR   r   slicera  loss_functionrI   rG  r   r/  r9   r0  )r)   rQ  r   rn   r/  rR  rk  r(  r   rl  r   outputsr9   slice_indicesrc  rn  s                   r-   r<   zDots1ForCausalLM.forward$  s    J ,64:: 	,
)%+')	,
 	,
  118B>SV8W~ot4]kmA}a,?@A%4%%pVFt{{OeOepiopD%#33!//))
 	
r.   )	NNNNNNNNr   )rB   rC   rD   _tied_weights_keys_tp_plan_pp_planr#   rh  rj  r   r   r   r%   r   r   r	   r^  r  r   r   r   r   r   r<   rE   rF   s   @r-   r`  r`    s:   *+=)H_-z:;H  151537+/59-1$(5934=
E,,-=
 !.=
 u//0	=

 "%=
   1 12=
 ))*=
 D>=
 !!1!12=
 c5<</0=
 +,=
 
 =
  =
r.   r`  )r-  rC  r`  )Nr   )r   )?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.genericr   configuration_dots1r   Moduler    rH   rx   r   r   r   r   re   r   r   r   r   r   r   r-  rC  r`  __all__r*  r.   r-   <module>r     s  * - ,     ! . ) 7 R B 9 O K F & I I / , Y'J299 J (J(<299 <D(6	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 U\\*% % % '(%4G)RYY G)Tryy "1ryy 1h,*bii ,*^/2 /d T? T T. Y
% Y
 Y
x S
+_ S
 S
l Er.   