
    qis                        d dl mZ d dl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 ddlmZmZ dd	lmZ dd
lmZmZmZ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/m0Z0 ddl1m2Z2 ddl3m4Z4  ed       G d dejj                               Z6 G d dejj                        Z7d Z8 ed      d?d       Z9dejt                  d e;d!ejt                  fd"Z<	 d@d#ejj                  d$ejt                  d%ejt                  d&ejt                  d'ejt                  dz  d(e=d)e=d*e)e+   fd+Z> ee9       G d, d-ejj                               Z? G d. d/ejj                        Z@ G d0 d1ejj                        ZAe G d2 d3ejj                               ZB G d4 d5ejj                        ZC G d6 d7e      ZDe, G d8 d9e'             ZEe, G d: d;eE             ZFe, G d< d=eEe             ZGg d>ZHy)A    )Callable)OptionalN)nn   )initialization)ACT2FN)CacheDynamicCache)GenerationMixin)use_experts_implementationuse_kernel_forward_from_hubuse_kernel_func_from_hubuse_kernelized_func)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)maybe_autocastmerge_with_config_defaults)capture_outputs   )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      Z/opt/pipecat/venv/lib/python3.12/site-packages/transformers/models/dots1/modeling_dots1.pyr*   zDots1RMSNorm.__init__4   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.   )r0   r5   input_dtypevariances       r3   forwardzDots1RMSNorm.forward<   sy    #))%((7 $$Q',,R,>%Ht?T?T4T(UU{{]--k:::r4   c                 ^    t        | j                  j                         d| j                   S )Nz, eps=)tupler.   shaper/   )r0   s    r3   
extra_reprzDots1RMSNorm.extra_reprC   s*    ))*+6$2G2G1HIIr4   )gư>)
__name__
__module____qualname__floatr*   r,   TensorrB   rF   __classcell__r2   s   @r3   r%   r%   2   s7    $ $$ $;U\\ ;ell ;Jr4   r%   c                        e Zd ZU ej                  ed<   ddef 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 xZS )Dots1RotaryEmbeddinginv_freqNconfigc                    t         |           |j                  | _        |j                  | _        || _        | j
                  j                  d   | _        | j                  }| j                  dk7  rt        | j                     } || j
                  |      \  }| _
        | j                  d|d       | j                  d|j                         d       y )N	rope_typedefaultrP   F)
persistentoriginal_inv_freq)r)   r*   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrQ   rope_parametersrS   compute_default_rope_parametersr   attention_scalingregister_bufferclone)r0   rQ   devicerope_init_fnrP   r2   s        r3   r*   zDots1RotaryEmbedding.__init__J   s    "("@"@$*$B$B!44[A!%!E!E>>Y&.t~~>L+7V+L($(ZeD0(..2BuUr4   r_   ztorch.deviceseq_lenr'   ztorch.Tensorc                    | 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).
        
rope_thetahead_dimNg      ?r   r7   r:   )r_   r:   )	rZ   getattrr1   num_attention_headsr,   arangeint64r;   rJ   )rQ   r_   ra   basedimattention_factorrP   s          r3   r[   z4Dots1RotaryEmbedding.compute_default_rope_parametersZ   s    & %%l3fj$/c63E3EIcIc3c U\\!S!5;;?BB&X]XcXcBdgjjk
 )))r4   c                 N   | j                   d d d d f   j                         j                  |j                  d   dd      j	                  |j
                        }|d d d d d f   j                         }t        |j
                  j                  t              r/|j
                  j                  dk7  r|j
                  j                  nd}t        |d      5  |j                         |j                         z  j                  dd      }t        j                  ||fd	      }|j                         | j                  z  }|j                         | j                  z  }	d d d        j	                  |j                   
      	j	                  |j                   
      fS # 1 sw Y   AxY w)Nr   r8   r!   mpscpuF)device_typeenabledr7   rk   re   )rP   rJ   expandrE   r;   r_   
isinstancetypestrr   	transposer,   catcosr\   sinr:   )
r0   xposition_idsinv_freq_expandedposition_ids_expandedrp   freqsembry   rz   s
             r3   rB   zDots1RotaryEmbedding.forwardx   sR    !MM$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)NNN)rG   rH   rI   r,   rK   __annotations__r"   r*   staticmethodr   intrD   rJ   r[   no_gradr   rB   rL   rM   s   @r3   rO   rO   G   s    llV{ V  %)+/"*d"*(* t* 
~u$	%	* *: U]]_<  <r4   rO   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..Nr8   r7   rr   )rE   r,   rx   )r{   x1x2s      r3   rotate_halfr      sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r4   rotary_pos_embc                     |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.
    )	unsqueezer   )qkry   rz   unsqueeze_dimq_embedk_embeds          r3   apply_rotary_pos_embr      sY    & --
&C
--
&C3w;q>C/0G3w;q>C/0GGr4   r5   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)rE   rs   reshape)r5   r   batchnum_key_value_headsslenrd   s         r3   	repeat_kvr      so    
 2?1D1D.Ehz!!Qa"23::5BUW\^bdlmM  (;e(CT8TTr4   modulequerykeyvalueattention_maskscalingdropoutkwargsc                    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 )Nr7   r   r8   )rk   r:   )ptrainingr!   )r   num_key_value_groupsr,   matmulrw   r   
functionalsoftmaxr<   r;   r:   r   r   
contiguous)r   r   r   r   r   r   r   r   
key_statesvalue_statesattn_weightsattn_outputs               r3   eager_attention_forwardr      s     3 ; ;<JUF$?$?@L<<z';';Aq'ABWLL!#n4==((2U]](SVVW\WbWbcL==((6??([L,,|\:K''1-88:K$$r4   c                       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j                  dz  d	e
dz  d
ej                  dz  dee   de	ej                  ej                  dz  f   fdZ xZS )Dots1Attentionz=Multi-headed attention from 'Attention Is All You Need' paperrQ   	layer_idxc                    t         |           t        |d      r|j                  |   nd | _        || _        || _        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                  |j0                        | _        t/        | j                  |j0                        | _        | j                  dk(  r|j6                  | _        y d | _        y )Nlayer_typesrd   g      Tbiasr&   sliding_attention)r)   r*   hasattrr   
layer_typerQ   r   rf   r1   rg   rd   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sliding_windowr0   rQ   r   r2   s      r3   r*   zDots1Attention.__init__   s   ;B6=;Y&,,Y7_c"
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
 #4==f6I6IJ"4==f6I6IJ7;J]7]f33cgr4   Nr5   position_embeddingsr   past_key_valuescache_positionr   r'   c                 j   |j                   d d }g |d| j                  }| j                  | j                  |      j	                  |            j                  dd      }	| j                  | j                  |      j	                  |            j                  dd      }
| j                  |      j	                  |      j                  dd      }|\  }}t        |	|
||      \  }	}
|'|||d}|j                  |
|| j                  |      \  }
}t        j                  | j                  j                  t               } || |	|
||f| j"                  sdn| j$                  | j&                  | j(                  d|\  }} |j*                  g |d j-                         }| j/                  |      }||fS )Nr8   r!   r7   )rz   ry   r           )r   r   r   )rE   rd   r   r   viewrw   r   r   r   r   updater   r   get_interfacerQ   _attn_implementationr   r   r   r   r   r   r   r   )r0   r5   r   r   r   r   r   input_shapehidden_shapequery_statesr   r   ry   rz   cache_kwargsattention_interfacer   r   s                     r3   rB   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(?(M(MKK,,.E)
 %8
%
  $}}C$2H2HLL..
%
 
%
!\ *k));;;;FFHkk+.L((r4   )NN)rG   rH   rI   __doc__r"   r   r*   r,   rK   rD   r	   
LongTensorr   r   rB   rL   rM   s   @r3   r   r      s    Gh{ hs h@ )-26*)||*) #5<<#=>*) t+	*)
 *) ((4/*) -.*) 
u||U\\D00	1*)r4   r   c                   &     e Zd Zd fd	Zd Z xZS )Dots1MLPc                    t         |           || _        |j                  | _        ||j                  n|| _        t        j                  | j                  | j                  d      | _        t        j                  | j                  | j                  d      | _        t        j                  | j                  | j                  d      | _	        t        |j                     | _        y NFr   )r)   r*   rQ   r1   intermediate_sizer   r   	gate_projup_proj	down_projr   
hidden_actact_fn)r0   rQ   r   r2   s      r3   r*   zDots1MLP.__init__  s    !--=N=V!9!9\m4#3#3T5K5KRWXyy!1!143I3IPUV4#9#94;K;KRWXV../r4   c                     | j                  | j                  | j                  |            | j                  |      z        }|S r   )r   r   r   r   )r0   r{   r   s      r3   rB   zDots1MLP.forward%  s6    NN4;;t~~a/@#ADLLQRO#ST	r4   r   rG   rH   rI   r*   rB   rL   rM   s   @r3   r   r     s    0r4   r   c                   $     e Zd Z fdZd Z xZS )Dots1TopkRouterc                 6   t         |           || _        |j                  | _        t	        j
                  t        j                  | j                  |j                  f            | _	        | j                  dt        j                  | j                               y )Ne_score_correction_bias)r)   r*   rQ   n_routed_expertsr   r+   r,   emptyr1   r.   r]   zerosr0   rQ   r2   s     r3   r*   zDots1TopkRouter.__init__+  sm     & 7 7ll5;;0E0EvGYGY/Z#[\6DDYDY8Z[r4   c                    |j                  d| j                  j                        }t        j                  |j                  t        j                        | j                  j                  t        j                              }|S Nr8   )	r   rQ   r1   Flinearru   r,   r<   r.   )r0   r5   router_logitss      r3   rB   zDots1TopkRouter.forward3  sY    %**2t{{/F/FG!3!3EMM!BDKKDTDTUZUbUbDcdr4   r   rM   s   @r3   r   r   *  s    \r4   r   c                        e Zd ZdZ fdZdej                  dej                  dej                  dej                  fdZ xZS )Dots1NaiveMoez2Collection of expert weights stored as 3D tensors.c                    t         |           |j                  | _        |j                  | _        |j                  | _        t        j                  t        j                  | j                  d| j                  z  | j
                              | _        t        j                  t        j                  | j                  | j
                  | j                              | _        t        |j                     | _        y )Nr7   )r)   r*   num_local_expertsnum_expertsr1   
hidden_dimmoe_intermediate_sizeintermediate_dimr   r+   r,   r   gate_up_projr   r   r   r   r   s     r3   r*   zDots1NaiveMoe.__init__=  s    !33 ,, & < <LLT5E5Eq4K`K`G`bfbqbq)rsekk$2B2BDOOUYUjUj&klV../r4   r5   top_k_indextop_k_weightsr'   c                 f   t        j                  |      }t        j                         5  t         j                  j                  j                  || j                        }|j                  ddd      }t        j                  |j                  d      d      j                         }d d d        D ]  }|d   }|| j                  k(  rt        j                  |         \  }}	||	   }
t        j                  j                  |
| j                  |         j                  dd      \  }}| j                  |      |z  }t        j                  j                  || j                   |         }|||	|d f   z  }|j#                  d|	|j%                  |j&                                |S # 1 sw Y   xY w)N)num_classesr7   r!   r   )r8   rr   r8   )r,   
zeros_liker   r   r   one_hotr   permutegreatersumnonzerowherer   r   chunkr   r   
index_add_r;   r:   )r0   r5   r   r   final_hidden_statesexpert_mask
expert_hit
expert_idx	top_k_pos	token_idxcurrent_stategateupcurrent_hidden_statess                 r3   rB   zDots1NaiveMoe.forwardF  s    $..}=]]_ 	S((--55ktO_O_5`K%--aA6K{8'DaHPPRJ	S
 % 
	nJ#AJT---#(;;{:/F#G Iy))4M}}++M4;L;LZ;XY__`agi_jHD"$(KK$5$:!$&MM$8$89NPTP^P^_iPj$k!$9M)U^`dJd<e$e!**1i9N9Q9QReRkRk9lm
	n #"#	S 	Ss   A=F&&F0)	rG   rH   rI   r   r*   r,   rK   rB   rL   rM   s   @r3   r   r   9  sF    <0#||# \\# ||	#
 
#r4   r   c                   .     e Zd ZdZ fdZd Zd Z xZS )Dots1MoEz:
    A mixed expert module containing shared experts.
    c                    t         |           || _        t        |      | _        t        |      | _        t        ||j                  |j                  z        | _
        |j                  | _        |j                  | _        |j                  | _        |j                  | _        |j                  | _        |j                   | _        y )N)rQ   r   )r)   r*   rQ   r   expertsr   r  r   r   n_shared_expertsshared_expertsr   n_group
topk_groupnorm_topk_probrouted_scaling_factornum_experts_per_toktop_kr   s     r3   r*   zDots1MoE.__init__f  s    $V,#F+	&V-I-IFLcLc-c
 !' 7 7~~ ++$33%+%A%A"//
r4   c                    |j                         }|| j                  j                  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   }|j%                  d|      }	| j&                  r|	j                  dd	
      dz   }
|	|
z  }	|	| j(                  z  }	||	fS )Nr8   r7   rr   r   F)r   rk   sortedr!   r   T)rk   r9   g#B;)sigmoidr  r   r   r  r   topkr  r,   r  r   scatter_r   rs   r   masked_fillboolr  gatherr  r  )r0   r   router_logits_for_choicegroup_scores	group_idx
group_mask
score_maskscores_for_choicetopk_indicestopk_weightsdenominators              r3   route_tokens_to_expertsz Dots1MoE.route_tokens_to_expertsu  s   %--/#04993T3T#T $))"dllD<Q<QUYUaUa<abT!T_Q SRS[ 	
 JJ|tBuUVWX	%%l3
Ay!,  $VBd&;&;t||&KLWR../ 	
 5@@*//BSASUXYzz"3tzzrRWXYZ[$++A|<&**r4*@5HKK'L#d&@&@@\))r4   c                    |}|j                   }| j                  |      }| j                  |      \  }}|j                  d|j                   d         } | j	                  |||      j                  | }|| j                  |      z   }|S r   )rE   r  r.  r   r  r  )r0   r5   	residuals
orig_shaper   r+  r,  s          r3   rB   zDots1MoE.forward  s    !	"((
		-0%)%A%A-%P"l%**2}/B/B2/FGT]L,OTTV`a%(;(;I(FFr4   )rG   rH   rI   r   r*   r.  rB   rL   rM   s   @r3   r  r  a  s    0*2r4   r  c                   "    e Zd Zdedef 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j                  dz  deej                  ej                  f   dz  dee   dej                  fdZ xZS )Dots1DecoderLayerrQ   r   c                    t         |           |j                  | _        t        ||      | _        ||j
                  k\  rt        |      | _        nt        |      | _        t        |j                  |j                        | _        t        |j                  |j                        | _        |j                  |   | _        y )N)rQ   r   r   )r)   r*   r1   r   	self_attnfirst_k_dense_replacer  mlpr   r%   r   input_layernormpost_attention_layernormr   attention_typer   s      r3   r*   zDots1DecoderLayer.__init__  s    !--'vK444'DH'DH+F,>,>FDWDWX(4V5G5GVM`M`(a%$00;r4   Nr5   r   r|   r   	use_cacher   r   r   r'   c                     |}	| j                  |      } | j                  d|||||||d|\  }}
|	|z   }|}	| j                  |      }| j                  |      }|	|z   }|S )N)r5   r   r|   r   r;  r   r    )r8  r5  r9  r7  )r0   r5   r   r|   r   r;  r   r   r   residual_s              r3   rB   zDots1DecoderLayer.forward  s     !,,];)4>> 	
')%+) 3	
 	
q !=0 !55mD/ =0r4   )NNNFNN)rG   rH   rI   r"   r   r*   r,   rK   r   r	   r#  rD   r   r   rB   rL   rM   s   @r3   r3  r3    s    <{ <s <$ /304(,!&26HL|| t+ &&-	
  $; ((4/ #5<<#=>E +, 
r4   r3  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dgZdZ ej(                          fd	       Z xZS )
Dots1PreTrainedModelrQ   modelTr3  r   )r5   
attentionsr   Nc                    t         |   |       t        |t              rVt	        j
                  |j                  d| j                  j                         t	        j                  |j                         y t        |t              rmt	        j
                  |j                  d| j                  j                         t	        j
                  |j                  d| j                  j                         y y )Nr   )r>   std)r)   _init_weightsrt   r   initnormal_r.   rQ   initializer_rangezeros_r   r   r   r   )r0   r   r2   s     r3   rF  z"Dots1PreTrainedModel._init_weights  s    f%fo.LLSdkk6S6STKK667.LL,,3DKK<Y<YZLL))9V9VW /r4   )rG   rH   rI   r"   r   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_backendr3  r   _can_record_outputs_keep_in_fp32_modules_strict"_keys_to_ignore_on_load_unexpectedr,   r   rF  rL   rM   s   @r3   rA  rA    s    &*#,-#4"5N!"&*$ %>#> )-&U]]_X Xr4   rA  c                       e Zd Zdef 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j                  dz  dee   defd                     Z xZS )
Dots1ModelrQ   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   rQ   Fr   )r)   r*   pad_token_idpadding_idx
vocab_sizer   	Embeddingr1   embed_tokens
ModuleListrangenum_hidden_layersr3  layersr%   r   normrO   
rotary_embgradient_checkpointingrQ   r   has_sliding_layers	post_initr   s      r3   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N	input_idsr   r|   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_embedsrZ  r   r!   )r_   )rQ   rj  r   r   r   r|   full_attentionr   )r   r   r|   r   r;  r   )last_hidden_stater   r=  )
ValueErrorr_  r
   rQ   get_seq_lengthr,   rh   rE   r_   r   rt   dictr   rg  r   re  rc  rb  r:  rd  r   )r0   ri  r   r|   r   rj  r;  r   r   past_seen_tokenscausal_mask_mappingmask_kwargsr5   r   decoder_layers                  r3   rB   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
 	
r4   )NNNNNNN)rG   rH   rI   r"   r*   r   r    r   r,   r   rK   r	   FloatTensorr#  r   r   r   rB   rL   rM   s   @r3   rX  rX    s    { "   .2.204(,26!%26C
##d*C
 t+C
 &&-	C

 C
 ((4/C
 $;C
 ((4/C
 +,C
 
!C
    C
r4   rX  c                   b    e Zd ZddiZddiZddgdgfiZ 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	j                  dz  dee	j                  z  dee   defd              Z xZS )Dots1ForCausalLMzlm_head.weightzmodel.embed_tokens.weightlm_headcolwise_gather_outputr5   logitsc                     t         |   |       t        |      | _        |j                  | _        t        j                  |j                  |j                  d      | _        | j                          y r   )
r)   r*   rX  rB  r]  r   r   r1   rx  rh  r   s     r3   r*   zDots1ForCausalLM.__init__L  sU     '
 ++yy!3!3V5F5FUS 	r4   Nri  r   r|   r   rj  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."
        ```)ri  r   r|   r   rj  r;  r   N)rz  r|  r]  )lossrz  r   r5   rC  r=  )rB  rm  rt   r   slicerx  loss_functionrQ   r]  r   r   r5   rC  )r0   ri  r   r|   r   rj  r|  r;  r   r}  r   outputsr5   slice_indicesrz  r  s                   r3   rB   zDots1ForCausalLM.forwardU  s    J ,64:: 	,
)%+')	,
 	,
  118B>SV8W~ot4]kmA}a,?@A%4%%pVFt{{OeOepiopD%#33!//))
 	
r4   )	NNNNNNNNr   )rG   rH   rI   _tied_weights_keys_tp_plan_pp_planr*   r   r   r,   r   rK   r	   ru  r#  r   r   r   r   rB   rL   rM   s   @r3   rw  rw  F  s/   *,GH23H_-z:;H  .2.204(,26*.!%26-.=
##d*=
 t+=
 &&-	=

 =
 ((4/=
   4'=
 $;=
 ((4/=
 ell*=
 +,=
 
 =
  =
r4   rw  )rA  rX  rw  )r!   )r   )Icollections.abcr   typingr   r,   torch.nn.functionalr   r   r    r   rG  activationsr   cache_utilsr	   r
   
generationr   integrationsr   r   r   r   masking_utilsr   r   modeling_flash_attention_utilsr   modeling_layersr   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.genericr   r   utils.output_capturingr    configuration_dots1r"   Moduler%   rO   r   r   rK   r   r   rJ   r   r   r   r   r   r  r3  rA  rX  rw  __all__r=  r4   r3   <module>r     s8  ( %      & ! . )  S B 9 O K F & I I G 5 , Y'J299 J (J(><299 ><B( *+ ,2	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 LL4'% % % '(%2 )*H)RYY H) +H)Vryy  bii  $#BII $# $#N5ryy 5p/2 /d X? X X< X
% X
 X
v M
+_ M
 M
` Er4   