
    rhQ                     |   d dl Z d dlmZ d dlmZmZ d dlZd dlmZ d dl	mc m
Z d dlZddlmZ ddlmZ ddlmZ ddlmZ dd	lmZ dd
lmZmZmZ ddlmZmZ ddlmZm Z m!Z!m"Z"m#Z# ddl$m%Z% ddl&m'Z'm(Z(m)Z)  ejT                  e+      Z, G d de      Z- G d de       Z. G d dej^                        Z0 G d de      Z1 G d dej^                        Z2 G d dej^                        Z3 G d dej^                        Z4 G d d ej^                        Z5 G d! d"ej^                        Z6 G d# d$ej^                        Z7 G d% d&ej^                        Z8 G d' d(e%      Z9 G d) d*ejt                        Z; G d+ d,ej^                        Z< G d- d.ej^                        Z= G d/ d0ej^                        Z> G d1 d2ej^                        Z? G d3 d4ej^                        Z@ ed56       G d7 d8e             ZA G d9 d:      ZB G d; d<eeA      ZC G d= d>e"eC      ZD G d? d@e!eCe      ZE G dA dBeC      ZF G dC dDeCe      ZGg dEZHy)F    N)cached_property)OptionalUnion   )Cache)GenerationMixin)CausalLMOutputWithPast)PreTrainedModel)Unpack)auto_docstringcan_return_tuplelogging   )ChameleonPreTrainedModel#ChameleonVQVAEEncoderConvDownsample)LlamaAttentionLlamaDecoderLayerLlamaForCausalLM
LlamaModelTransformersKwargs)SiglipAttention   )
Emu3ConfigEmu3TextConfigEmu3VQVAEConfigc                       e Zd Zy)Emu3AttentionN__name__
__module____qualname__     x/var/www/html/ai-insurance-compliance-backend/venv/lib/python3.12/site-packages/transformers/models/emu3/modular_emu3.pyr   r   ,       r#   r   c                   d    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                  eeej                  ej                  f      f   fdZ xZS )Emu3DecoderLayerconfig	layer_idxc                 n    t         |   ||       t        j                  |j                        | _        y N)super__init__nnDropoutattention_dropoutdropoutselfr(   r)   	__class__s      r$   r-   zEmu3DecoderLayer.__init__2   s(    +zz&":":;r#   hidden_statesattention_maskposition_idspast_key_value	use_cachecache_positionposition_embeddingskwargsreturnc                     |}	| j                  |      } | j                  d|||||||d|\  }}
|	| j                  |      z   }|}	| j                  |      }| j	                  |      }|	| j                  |      z   }|S )N)r5   r6   r7   r8   r9   r:   r;   r"   )input_layernorm	self_attnr1   post_attention_layernormmlp)r3   r5   r6   r7   r8   r9   r:   r;   r<   residual_s              r$   forwardzEmu3DecoderLayer.forward6   s     !,,];)4>> 	
')%)) 3	
 	
q !4<<#>> 55mD/ 4<<#>>r#   )NNNFNN)r   r    r!   r   intr-   torchTensorr   
LongTensorr   booltupler   r   FloatTensorrE   __classcell__r4   s   @r$   r'   r'   1   s    <z <c < 2637*.$)59KO|| !. u//0	
 ! D> !!1!12 &eELL%,,,F&GH +, 
u  (51B1BEDUDU1U+V"WW	Xr#   r'   c                   H     e Zd ZdZdef fdZdej                  fdZ xZ	S )Emu3VQVAEVectorQuantizera  
    A module for vector quantization using learned embedding vectors.

    This module implements the quantization process similar to te one described in
    the VQ-VAE (Vector Quantized Variational AutoEncoder) paper. It quantizes continuous
    input vectors into discrete codebook vectors, which are learned during training.
    Current implementation improves over previous ones by avoiding costly matrix multiplications
    and allowing for post-hoc remapping of indices.
    r(   c                    t         |           t        j                  |j                  |j
                        | _        | j                  j                  j                  j                  d|j                  z  d|j                  z         y )Ng            ?)
r,   r-   r.   	Embeddingcodebook_size	embed_dim	embeddingweightdatauniform_r3   r(   r4   s     r$   r-   z!Emu3VQVAEVectorQuantizer.__init__b   sb    f&:&:F<L<LM""++D63G3G,GvOcOcIcdr#   hidden_statec                    |j                   \  }}}}}|j                  ddddd      j                         }|j                  d|      }t	        j
                  |dz  dd      }t	        j
                  | j                  j                  dz  d	      }	dt	        j                  || j                  j                  j                  dd            z  }
||	z   |
z
  }
t	        j                  |
d	      }|j                  ||||      }|S )
Nr   r   r      r   T)dimkeepdimr_   )shapepermute
contiguousviewrG   sumrV   rW   matmul	transposeargmin)r3   r[   
batch_sizetemporalchannelsheightwidthhidden_state_flattenedhidden_state_sumembedding_sum	distancesmin_encoding_indicess               r$   rE   z Emu3VQVAEVectorQuantizer.forwardg   s    8D8J8J5
Hh#++Aq!Q:EEG!-!2!22x!@ !99%;Q%>AtT		$.."7"7":B %;T^^=R=R=\=\]^`a=bcc	$}4y@	$||I1=388XvW\]##r#   )
r   r    r!   __doc__r   r-   rG   rH   rE   rM   rN   s   @r$   rP   rP   W   s&    e e
$ELL $r#   rP   c                       e Zd Zy)Emu3VQVAEEncoderConvDownsampleNr   r"   r#   r$   rv   rv   y   r%   r#   rv   c                   $     e Zd Z fdZd Z xZS )Emu3VQVAEEncoderConvUpsamplec                 `    t         |           t        j                  ||ddd      | _        y )Nr   r   kernel_sizestridepadding)r,   r-   r.   Conv2dconv)r3   in_channelsr4   s     r$   r-   z%Emu3VQVAEEncoderConvUpsample.__init__~   s'    IIk;AaYZ[	r#   c                 X    t        j                  |dd      }| j                  |      }|S )N       @nearestscale_factormode)Finterpolater   r3   r5   s     r$   rE   z$Emu3VQVAEEncoderConvUpsample.forward   s(    m#IV		-0r#   r   r    r!   r-   rE   rM   rN   s   @r$   rx   rx   }   s    \r#   rx   c            	       \     e Zd Zdededee   dee   f fdZdej                  fdZ xZ	S )Emu3VQVAEConv3d
in_channelout_channelr{   r|   c                 P   t         	|           t        |dd  |dd        D cg c]
  \  }}||z
   }}}d| _        |d d d   D ]%  }| xj                  |dz  |dz  z   |dz  fz  c_        ' | xj                  dz  c_        t	        j
                  ||||      | _        y c c}}w )Nr   r"   r^   r   )r   r   )r|   )r,   r-   zipr}   r.   Conv3dr   )
r3   r   r   r{   r|   
one_kernel
one_stridepadding_sizespad_sizer4   s
            r$   r-   zEmu3VQVAEConv3d.__init__   s     	ORS^_`_aSbdjklkmdnOop5KZj0pp%dd+ 	JHLLX]X\98q=IIL	JII	
	 qs   B"r5   c                 h    t        j                  || j                        }| j                  |      }|S r+   )r   padr}   r   r   s     r$   rE   zEmu3VQVAEConv3d.forward   s*    mT\\:		-0r#   )
r   r    r!   rF   rK   r-   rG   rH   rE   rM   rN   s   @r$   r   r      sF    

 
 3Z	

 c

,U\\ r#   r   c                   `     e Zd Zdedef fdZdej                  dej                  fdZ xZS )Emu3VQVAESpatialNormr   out_channelsc                     t         |           t        j                  |ddd      | _        t        j
                  ||ddd      | _        t        j
                  ||ddd      | _        y )N    ư>Tnum_channels
num_groupsepsaffiner   r   rz   )r,   r-   r.   	GroupNorm
norm_layerr~   conv_yconv_br3   r   r   r4   s      r$   r-   zEmu3VQVAESpatialNorm.__init__   sn    
 	,,%	
 ii
 ii
r#   r5   quant_statesc                     t        j                  ||j                  dd  d      }| j                  |      }|| j	                  |      z  | j                  |      z   }|S )Nr   )sizer   )r   r   rb   r   r   r   )r3   r5   r   s      r$   rE   zEmu3VQVAESpatialNorm.forward   sX    }}\8K8KBC8PW`a6%L(AADKKP\D]]r#   	r   r    r!   rF   r-   rG   rH   rE   rM   rN   s   @r$   r   r      s5    

 
8U\\  r#   r   c                   H     e Zd Zdedef fdZdej                  fdZ xZS )Emu3VQVAETemporalUpsampler   r   c                 J    t         |           t        ||dd      | _        y )Nr   r   r   r   r   r   r{   r|   r,   r-   r   r   r3   r   r   r4   s      r$   r-   z"Emu3VQVAETemporalUpsample.__init__   (    
 	#!	
	r#   r5   c                 P   |j                   \  }}}}}|j                  ddddd      j                         j                  |d|      }t	        j
                  |dd	      }|j                  ||||d      j                  ddddd      j                         }| j                  |      }|S )
Nr   r   r   r]   r   r^   r   r   r   )rb   rc   rd   re   r   r   r   )r3   r5   rj   rl   rk   rm   rn   s          r$   rE   z!Emu3VQVAETemporalUpsample.forward   s    8E8K8K5
Hh%--aAq!<GGINNz[]_ghm#IV%**:xPRS[[\]_`bcefhijuuw		-0r#   r   rN   s   @r$   r   r      s*    

 
U\\ r#   r   c                   H     e Zd Zdedef fdZdej                  fdZ xZS )Emu3VQVAETemporalDownsampler   r   c                 J    t         |           t        ||dd      | _        y )N)r]   r   r   )r   r   r   r   r   r   s      r$   r-   z$Emu3VQVAETemporalDownsample.__init__   r   r#   r5   c                 (    | j                  |      }|S r+   )r   r   s     r$   rE   z#Emu3VQVAETemporalDownsample.forward   s    		-0r#   r   rN   s   @r$   r   r      s*    

 
U\\ r#   r   c                   (     e Zd Z	 d fd	Zd Z xZS )Emu3VQVAETemporalResnetBlockc                 p   t         |           || _        ||n|| _        t	        j
                  |      | _        t        ||dd      | _        t	        j
                  |      | _	        t        ||dd      | _
        | j                  | j                  k7  r t	        j                  ||ddd      | _        y y )Nr   r   r   r   r   rz   )r,   r-   r   r   r.   BatchNorm3dnorm1r   conv1norm2conv2r   nin_shortcutr   s      r$   r-   z%Emu3VQVAETemporalResnetBlock.__init__   s    
 	&+7+?K\^^K0
$!	

 ^^L1
$!	

 t000 "		!D 1r#   c                 L   |}| j                  |      }|t        j                  |      z  }| j                  |      }| j	                  |      }|t        j                  |      z  }| j                  |      }| j                  | j                  k7  r| j                  |      }||z   S r+   )	r   rG   sigmoidr   r   r   r   r   r   )r3   r5   rC   s      r$   rE   z$Emu3VQVAETemporalResnetBlock.forward  s     

=1}55

=1

=1}55

=1t000((2H-''r#   r+   r   rN   s   @r$   r   r      s     @(r#   r   c                   ~     e Zd Z	 	 ddedee   dee   f fdZddej                  deej                     fdZ xZ	S )	Emu3VQVAEResnetBlockr   r   quant_channelsc                    t         |           || _        ||n|}|| _        || _        |=t        j                  |ddd      | _        t        j                  |ddd      | _        n"t        ||      | _        t        ||      | _        t        j                  ||ddd      | _        t        j                  ||ddd      | _        | j                  | j                  k7  r t        j                  ||ddd      | _        y y )	Nr   r   Tr   r   r   rz   r   )r,   r-   r   r   r   r.   r   r   r   r   r~   r   r   r   )r3   r   r   r   r4   s       r$   r-   zEmu3VQVAEResnetBlock.__init__%  s    	&&2&:{(,!;2SW`deDJ<BTXaefDJ-nkJDJ-nlKDJYY

 YY

 t000 "		!D 1r#   r5   c                 v   | j                   dn|f}|} | j                  |g| }|t        j                  |      z  }| j	                  |      } | j
                  |g| }|t        j                  |      z  }| j                  |      }| j                  | j                  k7  r| j                  |      }||z   S Nr"   )
r   r   rG   r   r   r   r   r   r   r   )r3   r5   r   	norm_argsrC   s        r$   rE   zEmu3VQVAEResnetBlock.forwardQ  s    --5BN;L	 "

==9=}55

=1"

==9=}55

=1t000((2H-''r#   )NNr+   )
r   r    r!   rF   r   r-   rG   rH   rE   rM   rN   s   @r$   r   r   $  sU     '+(,	** sm* !	*X(U\\ (8ELLCY (r#   r   c                   $     e Zd Zdef fdZ xZS )Emu3VQVAEAttentionBlockr(   c                 2    t         |   |       d| _        y )Nr   )r,   r-   num_key_value_groupsrZ   s     r$   r-   z Emu3VQVAEAttentionBlock.__init__d  s      %&!r#   )r   r    r!   r   r-   rM   rN   s   @r$   r   r   c  s    & & &r#   r   c                   *     e Zd ZdZ fdZddZ xZS )Emu3VQVAEGroupNormz
    Same as the torch GroupNorm with the only difference that this ones accepts
    an optional kwarg `quant_states` which is not used. This class makes it easier to
    use SpatialNorm or GroupNorm without conditionals
    c                 $    t        |   di | y r   )r,   r-   )r3   r<   r4   s     r$   r-   zEmu3VQVAEGroupNorm.__init__r  s    "6"r#   c                     t        j                  || j                  | j                  | j                  | j
                        S r+   )r   
group_normr   rW   biasr   )r3   inputr   s      r$   rE   zEmu3VQVAEGroupNorm.forwardu  s)    ||E4??DKKDHHUUr#   r+   )r   r    r!   rt   r-   rE   rM   rN   s   @r$   r   r   k  s    #Vr#   r   c                   `     e Zd Zd fd	Zddej
                  deej
                     fdZ xZS )Emu3VQVAEMiddleBlockc                     t         |           t        |||      | _        t	        |      | _        |t        |ddd      | _        nt        ||      | _        t        |||      | _	        y )Nr   r   r   r   r   Tr   )
r,   r-   r   block_1r   attn_1r   	attn_normr   block_2)r3   r(   r   r   r4   s       r$   r-   zEmu3VQVAEMiddleBlock.__init__z  so    +#$)

 .f5!/[UW]ajnoDN1.+NDN+#$)
r#   r5   r   c                 b   | j                  ||      }|}| j                  ||      }|j                  \  }}}}|j                  ||||z        j	                  dd      }| j                  |      d   }|j                  ||||      j                  dddd      }||z   }| j                  ||      }|S )Nr   r   r   r   )	r   r   rb   re   rh   r   reshaperc   r   )r3   r5   r   rC   rj   rl   rm   rn   s           r$   rE   zEmu3VQVAEMiddleBlock.forward  s    ]LA }lC.;.A.A+
Hfe%**:x%PZZ[\^_`M215%--j&%RZZ[\^_abdef =0]LAr#   r+   )	r   r    r!   r-   rG   rL   r   rE   rM   rN   s   @r$   r   r   y  s,    
(
U%6%6 
huO`O`Fa 
r#   r   c                   >     e Zd Z fdZdej
                  fdZ xZS )Emu3VQVAEDownBlockc           
         t         |           t        |j                        | _        |j
                  | _        |j                  }|j                  }dt        |      z   }|| _        t        j                         | _        t        | j                        D ]K  }t        j                         }t        j                         }t        j                         }|||   z  }	|||   z  }
t        | j
                        D ]~  }|j                  t        |	|
             |
}	|j                  .||j                  v s=|j                  t!        |             |j                  t        j"                  |	ddd              t        j$                         }||_        ||_        ||_        || j                  dz
  k7  rt-        |	      |_        | j                  j                  |       N y )N)r   r   r   r   r   Tr   r   )r,   r-   lenchannel_multipliernum_resolutionsnum_res_blocksbase_channelsrK   in_channel_multiplierr.   
ModuleListdownrangeappendr   attn_resolutionsr   r   Moduleblockattn
attn_normsrv   
downsample)r3   r(   r   r   r   i_levelr   r   r   block_in	block_outi_blockr   r4   s                r$   r-   zEmu3VQVAEDownBlock.__init__  s   "6#<#<=$33,,#66 $u-?'@ @%:"MMO	T112 	#GMMOE==?DJ$'<W'EEH%(:7(CCI !4!45 
q($,%. %**67fF]F];]KK 7 ?@%%bllUW]ajn&op
q 99;DDJDI(DO$..22"@"JIIT"1	#r#   r5   c                 >   t        | j                        D ]  \  }}t        | j                        D ]  } |j                  |   |      }t        |j                        dkD  s1|} |j                  |   |      }|j                  \  }}}}	|j                  ||||	z        j                  dd      } |j                  |   |      d   }|j                  |||	|      j                  dddd      }||z   } || j                  dz
  k7  s|j                  |      } |S )Nr   r   r   r   )	enumerater   r   r   r   r   r   r   rb   re   rh   r   rc   r   r   )
r3   r5   r   blocksr   rC   rj   rl   rm   rn   s
             r$   rE   zEmu3VQVAEDownBlock.forward  s5   (3 	AOGV !4!45 = 5W 5m Dv{{#a',H$>F$5$5g$>}$MM:G:M:M7J&%$1$6$6z8VV[^$\$f$fghjk$lM$8FKK$8$G$JM$1$9$9*feU]$^$f$fghjkmnpq$rM$,}$<M= $..22 & 1 1- @	A" r#   r   r    r!   r-   rG   rL   rE   rM   rN   s   @r$   r   r     s    ##JU%6%6 r#   r   c                   V     e Zd Z fdZdej
                  dej
                  fdZ xZS )Emu3VQVAEUpBlockc           	         t         |           t        |j                        | _        |j
                  | _        |j                  }|j                  |j                  d   z  }t        j                         | _
        t        t        | j                              D ]5  }t        j                         }t        j                         }t        j                         }|j                  |j                  |   z  }t        | j
                  dz         D ]e  }	|j                  t        |||             |}||j                  v s1|j                  t!        |             |j                  t#        ||             g t        j$                         }
||
_        ||
_        ||
_        |dk7  rt-        |      |
_        | j                  j1                  d|
       8 y )Nr^   r   r   r   )r,   r-   r   r   r   r   rU   r   r.   r   upreversedr   r   r   r   r   r   r   r   r   r   rx   upsampleinsert)r3   r(   r   r   r   r   r   r   r   r   r  r4   s              r$   r-   zEmu3VQVAEUpBlock.__init__  s   "6#<#<=$33))''&*C*CB*GG--/d&:&: ;< 	"GMMOE==?DJ,,v/H/H/QQI !4!4q!89 V($,%.'5 %f555KK 7 ?@%%&:>8&TUV BBHBG&BM!|:8DGGNN1b!3	"r#   r5   r   c                 h   t        | j                  d d d         D ]  \  }}t        | j                  dz         D ]  } |j                  |   ||      }t        |j                        dkD  s2|} |j                  |   ||      }|j                  \  }}}	}
|j                  |||	|
z        j                  dd      } |j                  |   |      d   }|j                  ||	|
|      j                  dddd      }||z   } |t        | j                        dz
  k7  s|j                  |      } |S )Nr^   r   r   r   r   )r   r  r   r   r   r   r   r   rb   re   rh   r   rc   r  )r3   r5   r   r   r   r   rC   rj   rl   rm   rn   s              r$   rE   zEmu3VQVAEUpBlock.forward  sD   (27 	?OGV !4!4q!89 = 5W 5m\ Rv{{#a',H$>F$5$5g$>}l$[M:G:M:M7J&%$1$6$6z8VV[^$\$f$fghjk$lM$8FKK$8$G$JM$1$9$9*feU]$^$f$fghjkmnpq$rM$,}$<M= #dgg,** & >	?  r#   r   rN   s   @r$   r   r     s(    #"JU%6%6 eFWFW r#   r   c                   >     e Zd Z fdZdej
                  fdZ xZS )Emu3VQVAEEncoderc                    t         |           |j                  }|j                  }|j                  }|j
                  }|j                  }|rd|z  n|}||d   z  }t        j                  j                  ||ddd      | _
        t        |      | _        t        ||      | _        t        j                  j                  d|dd	      | _        t        j                  j                  ||ddd      | _        t%        t'        j(                  |j*                              }	t        j,                         | _        t        j,                         | _        t3        |	      D ])  }
t5        ||      }| j.                  j7                  |       + t3        |j8                        D ]*  }t;        ||
      }| j0                  j7                  |       , y )Nr   r^   r   r   rz   r   r   T)r   r   r   r   r   )r,   r-   r   r   double_latentlatent_channelsr   rG   r.   r~   conv_inr   
down_blockr   middle_blockr   norm_outconv_outrF   mathlog2temporal_downsample_factorr   	time_convtime_res_stackr   r   r   r   r   )r3   r(   r   r   r	  r
  r   r   r   temporal_down_blocksir   rD   time_res_convr4   s                 r$   r-   zEmu3VQVAEEncoder.__init__  s   ,,((,, 00#66.;q?* #5b#99xx{MqYZdef,V40B**bxUYbf*g ( 
  #499V-N-N#OP mmo+, 	(A.|\JDNN!!$'	( v,,- 	6A8()M &&}5	6r#   pixel_valuesc                 h   |j                   d   } |j                  dg|j                   dd   }| j                  |      }| j                  |      }| j	                  |      }| j                  |      }|t        j                  |      z  }| j                  |      } |j                  d|g|j                   dd   }|j                  ddddd      }| j                  D ]"  } ||      }|t        j                  |      z  }$ | j                  D ]
  } ||      } |j                  ddddd      }|S )Nr   r^   r   r   r   r]   )rb   r   r  r  r  r  rG   r   r  rc   r  r  )r3   r  temporal_dimr5   r   layers         r$   rE   zEmu3VQVAEEncoder.forward8  sH   #))!,+|++BH1C1CAB1GH \26))-8 m4}55m4---b,YATATUVUWAXY%--aAq!< NN 	:D /MU]]=99M	: (( 	1E!-0M	1 &--aAq!<r#   )r   r    r!   r-   rG   rI   rE   rM   rN   s   @r$   r  r    s    %6NE$4$4 r#   r  c                   \     e Zd Zdef fdZdej                  dej                  fdZ xZS )Emu3VQVAEDecoderr(   c                    t         	|           |j                  }|j                  |j                  d   z  }t        j                         | _        t        |j                        D ]>  }t        |j                  |j                        }| j                  j                  |       @ t        t        j                  |j                               }t        j                         | _        t        |      D ]=  }t%        |j                  |j                        }| j"                  j                  |       ? t        j&                  |j                  |ddd      | _        t+        |||      | _        t/        |      | _        |j                  |j                  d   z  }t3        ||      | _        t        j&                  ||j6                  ddd      | _        y )Nr^   r   r   r   rz   )r   r   )r,   r-   rU   r   r   r.   r   r  r   r   r   r
  r   rF   r  r  r  r  r   r~   r  r   r  r   up_blockr   r  r   r  )
r3   r(   r   r   rD   r  temp_upsample_block_numr  r   r4   s
            r$   r-   zEmu3VQVAEDecoder.__init__W  s   ))''&*C*CB*GG mmov,,- 	6A8"22AWAWM &&}5		6 #&dii0Q0Q&R"S./ 	(A,V-C-CVE[E[\DNN!!$'	( yy""
 1R`a(0''&*C*CA*FF,^XF		
r#   r5   r   c                    t        j                  ||fd      }|j                  ddddd      }| j                  D ]
  } ||      } | j                  D ]"  } ||      }|t        j
                  |      z  }$ |j                  ddddd      }t        j                  |dd      \  }} |j                  dg|j                  dd   } |j                  dg|j                  dd   }| j                  |      }| j                  ||      }| j                  ||      }| j                  ||      }|t        j
                  |      z  }| j                  |      }|S )Nr   ra   r   r   r   r]   r^   )rG   catrc   r  r  r   chunkr   rb   r  r  r  r  r  )r3   r5   r   hidden_quant_statesr  s        r$   rE   zEmu3VQVAEDecoder.forward~  sp   #ii(E1M199!Q1aH (( 	=E"'(;"<	= ^^ 	FE"'(;"<5==1D#EE	F 299!Q1aH&+kk2Eqa&P#|---bK=3F3Fqr3JK+|++BH1C1CAB1GH]3 ))-Fm\Bm\B}55m4r#   )	r   r    r!   r   r-   rG   rH   rE   rM   rN   s   @r$   r  r  V  s+    %
 %
NU\\  r#   r  aR  
    The VQ-VAE model used in Emu3 for encoding/decoding images into discrete tokens.
    This model follows the "Make-a-scene: Scene-based text-to-image generation with human priors" paper from
    [ Oran Gafni, Adam Polyak, Oron Ashual, Shelly Sheynin, Devi Parikh, and Yaniv
    Taigman](https://huggingface.co/papers/2203.13131).
    )custom_introc                        e Zd ZU eed<   dZdZdZdZdZ	dZ
g dZd Zdef fdZdej                  dej                  fd	Zd
ej                  fdZ xZS )	Emu3VQVAEr(   
emuvideovqr  T)r   r   r   rP   c                 |   t        |t        j                  t        j                  f      rt        j                  j                  |j                  dd       |j                  qt        j                  j                  |j                        \  }}dt        j                  |      z  }t        j                  j                  |j                  | |       y y t        |t        j                        rt        j                  j                  |j                  t        j                  d             |j                  xt        j                  j                  |j                        \  }}|dkD  rdt        j                  |      z  nd}t        j                  j                  |j                  | |       y y t        |t        j                  t        j                  t        j                   f      rUt        j                  j#                  |j                  d       t        j                  j#                  |j                  d	       y t        |t        j$                        rc|j                  j&                  j)                          |j*                  2|j                  j&                  |j*                     j-                          y y y )
Nfan_outrelu)r   nonlinearityr      )ar   rR   g        )
isinstancer.   r~   r   initkaiming_normal_rW   r   _calculate_fan_in_and_fan_outr  sqrtrY   Linearkaiming_uniform_BatchNorm2dr   r   	constant_rS   rX   normal_padding_idxzero_)r3   modulefan_inrD   bounds        r$   _init_weightszEmu3VQVAE._init_weights  s   fryy"))45GG##FMM	PV#W{{&GGAA&--P	DIIf--  ufe< ' 		*GG$$V]]diil$C{{&GGAA&--P	17!DIIf--  ufe< '  NOGGfmmS1GGfkk3/-MM&&(!!-""6#5#56<<> . .r#   c                    t         |   |       || _        t        |      | _        t        |      | _        t        |      | _        dt        |j                        dz
  z  | _        t        |j                  |j                  dd      | _        t        |j                  |j                  dd      | _        dt        |j                        dz
  z  | _        | j%                          | j'                          y )Nr   r   )r   r   r   r   r   )r,   r-   r(   r  encoderr  decoderrP   quantizer   r   vision_spatial_factorr   r
  rU   
quant_convpost_quant_convspatial_scale_factoreval	post_initrZ   s     r$   r-   zEmu3VQVAE.__init__  s     '/'/08%&3v/H/H+IA+M%N")""F$4$4)T]
  /f44)T] 
 %&#f.G.G*H1*L$M!		r#   image_sizesc                    |j                   dk(  }|rL| j                  j                  }|j                  \  }}}}|j	                  d      j                  d|ddd      }n|j                  \  }}}}}| j                  |      }	|	j                  ddddd      }	| j                  |	      }	|	j                  ddddd      }	| j                  |	      }
|r|
j                  d      n|
}t        ||      D cg c]B  \  }}|d t        |d   | j                  z        d t        |d   | j                  z        f   D }}}|S c c}}w )Nr]   r   r   r   r   )ndimr(   r  rb   	unsqueezerepeatr@  rc   rD  rB  squeezer   rF   rC  )r3   r  rI  is_imagerk   rj   rl   rm   rn   r5   codesimage_tokenssingle_imager   s                 r$   encodezEmu3VQVAE.encode  sX   $$){{==H2>2D2D/J&%'11!4;;AxAqQL<H<N<N9J(FE\2 &--aAq!<6 &--aAq!<m,+3u}}Q' '*,&D
"d D3tAw)C)CCDDFqDQRGVZVpVpLpHqFqqr
 

 
s   1AD=r5   c                    |j                   dk(  }|r|j                  d      }|j                  \  }}}}| j                  j	                  |j                               }|j                  d   }|j                  |||||      j                  ddddd      j                         }| j                  |      }	|j                  ddddd      }|	j                  ddddd      }	| j                  |	|      }
|
j                  ||| j                  j                  z  | j                  j                  || j                  z  || j                  z        }
|r	|
d d df   S |
S )Nr   r   r^   r   r]   r   )rK  rL  rb   rB  rV   flattenre   rc   rd   rE  rA  r   r(   r  r   rF  )r3   r5   rO  rj   rk   rm   rn   quantrl   
post_quantvideos              r$   decodezEmu3VQVAE.decode  sK    %%*)33A6M.;.A.A+
Hfe''(=(=(?@;;r?

:xIQQRSUVXY[\^_`kkm))%0
aAq!,''1aA6
Z/t{{===KK$$T...D---
 'uQT{1E1r#   )r   r    r!   r   __annotations__base_model_prefixmain_input_name_supports_sdpa_supports_flash_attn_supports_flex_attn_supports_attention_backend_no_split_modulesr>  r-   rG   rH   rS  rY  rM   rN   s   @r$   r'  r'    sq     $$ON"&?* *5<< ell 82ELL 2r#   r'  c                       e Zd ZdZd Zed        Zed        Zed        Zed        Z	ed        Z
ed        Zd	eej                     d
ej                  fdZd	ej                  d
ej                  fdZy)Emu3ImageVocabularyMappingzM
    A class for mapping discrete image tokens from VQGAN to BPE tokens.
    c                 j    || _         |j                  d      | _        |j                  d      | _        y )Nz<|extra_200|>z<image>)	vocab_mapgeteol_token_idimage_token_id)r3   re  s     r$   r-   z#Emu3ImageVocabularyMapping.__init__  s+    "%MM/:'mmI6r#   c           	          t        | j                  j                         D cg c]  \  }}|j                  d      s| c}}      S c c}}w Nz<|visual tokensortedre  items
startswithr3   namevals      r$   rQ  z'Emu3ImageVocabularyMapping.image_tokens  s8    DNN,@,@,BhytSdooVfFgshiih
   A	
A	
c           	          t        | j                  j                         D cg c]  \  }}|j                  d      s| c}}      S c c}}w rj  rk  ro  s      r$   image_tokens_strz+Emu3ImageVocabularyMapping.image_tokens_str!  s8    T^^-A-A-Ci	ctWgGhtijjirr  c                 t    | j                   D ci c]  }t        |dd       | j                  |     c}S c c}w )Nir   )rt  rF   re  )r3   tokens     r$   img2bpez"Emu3ImageVocabularyMapping.img2bpe%  s5    FJF[F[\UE"RL!4>>%#88\\\s   #5c                 j    | j                   j                         D ci c]  \  }}||
 c}}S c c}}w r+   )rw  rm  )r3   kvs      r$   bpe2imgz"Emu3ImageVocabularyMapping.bpe2img)  s+    !%!3!3!56A1666s   /c                     t        j                  t        | j                  j	                               dz   t         j
                        }| j                  j                         D ]
  \  }}|||<    |S Nr   dtype)rG   zerosmaxr{  keysrF   rm  r3   mappingry  rz  s       r$   bpe2img_mapping_tensorz1Emu3ImageVocabularyMapping.bpe2img_mapping_tensor-  [    ++c$,,"3"3"56:%))LLL&&( 	DAqGAJ	r#   c                     t        j                  t        | j                  j	                               dz   t         j
                        }| j                  j                         D ]
  \  }}|||<    |S r}  )rG   r  r  rw  r  rF   rm  r  s       r$   img2bpe_mapping_tensorz1Emu3ImageVocabularyMapping.img2bpe_mapping_tensor4  r  r#   	img_batchr=   c                 ,   |j                   }t        j                  |j                  d   dft        j                        | j
                  z  }| j                  |j                  d         }t        j                  ||gd      }|j                  |      S )Nr   r   r~  cpur^   ra   )	devicerG   onesrb   rF   rg  r  tor"  )r3   r  r  eol_row
img_tokenss        r$   convert_img2bpez*Emu3ImageVocabularyMapping.convert_img2bpe;  sw    !!**iooa0!4EIIFIZIZZ00e1DE
YY
G4"=
}}V$$r#   c                     |j                   }|dd df   }| j                  |j                  d         }|j                  |      S )N.r^   r  )r  r  r  )r3   r  r  r  s       r$   convert_bpe2imgz*Emu3ImageVocabularyMapping.convert_bpe2imgB  sG    !!c3B3h'	00e1DE
}}V$$r#   N)r   r    r!   rt   r-   r   rQ  rt  rw  r{  r  r  listrG   rH   r  r  r"   r#   r$   rc  rc    s    7
 j j k k ] ] 7 7    %ell); % %% %%,, %r#   rc  c                       e Zd ZdgZdZdZy)Emu3PreTrainedModelr'   TN)r   r    r!   ra  r_  r`  r"   r#   r$   r  r  I  s     "&r#   r  c                   .     e Zd ZeedZdef fdZ xZS )Emu3TextModel)r5   
attentionsr(   c           	          t         |   |       t        j                  t	        |j
                        D cg c]  }t        ||       c}      | _        y c c}w r+   )r,   r-   r.   r   r   num_hidden_layersr'   layersr2   s      r$   r-   zEmu3TextModel.__init__W  sD     mmBGH`H`BabYfi0b
bs   A)	r   r    r!   r'   r   _can_record_outputsr   r-   rM   rN   s   @r$   r  r  Q  s"    )#

z 
 
r#   r  c                   4     e Zd ZU eed<    fdZ fdZ xZS )Emu3ForCausalLMr(   c                 D    t         |   |       t        |      | _        y r+   )r,   r-   r  modelrZ   s     r$   r-   zEmu3ForCausalLM.__init__a  s     "6*
r#   c                  6    t               j                          y)a  
        Example:

        ```python
        >>> from transformers import Emu3Processor, Emu3ForConditionalGeneration
        >>> import torch
        >>> import requests
        >>> from PIL import Image

        >>> model = Emu3ForCausalLM.from_pretrained("BAAI/Emu3-Chat-hf", torch_dtype=torch.bfloat16)
        >>> processor = Emu3Processor.from_pretrained("BAAI/Emu3-Chat-hf")

        >>> inputs = processor(text=["Can you write me a poem about winter."], return_tensors="pt").to(model.device)

        >>> generated_ids = model.generate(**inputs, max_new_tokens=100, do_sample=False)
        >>> processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
        ```N)r,   rE   )super_kwargsr4   s    r$   rE   zEmu3ForCausalLM.forwarde  s    $ 	r#   )r   r    r!   r   rZ  r-   rE   rM   rN   s   @r$   r  r  ^  s    + r#   r  c                   `    e Zd ZddiZ fdZd Zd Zd Zd Zde	j                  d	e	j                  fd
Zde	j                  d	e	j                  fdZe	j                  de	j                  dedefd       Zde	j                  de	j                  de	j                  fdZee	 	 	 	 	 	 	 	 	 dde	j                  de	j                  d	e	j(                  dee	j(                     dee	j                     dee   dee	j                     dee   dee	j                     dee   deeef   fd              Z xZS )	Emu3Modelztext_model.model
text_modelc                     t         |   |       t        j                  |j                        | _        t        |j                        | _        t        |j                        | _        | j                          y r+   )r,   r-   r  _from_configtext_configr  r'  	vq_configvqmodelrc  vocabulary_mapvocabulary_mappingrH  rZ   s     r$   r-   zEmu3Model.__init__}  sY     '44V5G5GH !1!12"<V=R=R"S 	r#   c                 6    | j                   j                         S r+   )r  get_input_embeddingsr3   s    r$   r  zEmu3Model.get_input_embeddings  s    3355r#   c                 :    | j                   j                  |       y r+   )r  set_input_embeddingsr3   values     r$   r  zEmu3Model.set_input_embeddings  s    ,,U3r#   c                     || _         y r+   r  r3   rA  s     r$   set_decoderzEmu3Model.set_decoder  s	    !r#   c                     | j                   S r+   r  r  s    r$   get_decoderzEmu3Model.get_decoder  s    r#   r  rI  c                     | j                   j                  ||      }|D cg c]+  }| j                  j                  |      j	                         - }}t        j                  |      }|S c c}w )a  
        Tokenizes images into discrete tokens with VQGAN module. Converts
        obtained image tokens into BPE tokens and wraps with "boi" and "eoi"
        special tokens.

        Args:
            pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, image_size, image_size)`):
                The tensors corresponding to the input images.
            image_sizes (`torch.LongTensor` of shape `(batch_size, 2)`):
                The sizes of the images in the batch, being (height, width) for each image.
        )r  rS  r  r  rU  rG   r"  )r3   r  rI  image_tokens_listtokensbpe_tokens_list
bpe_tokenss          r$   get_image_tokenszEmu3Model.get_image_tokens  sc     !LL//kJctuY_422BB6JRRTuuYY/
 vs   0A*c                    | j                  ||      }|D cg c];  \  }}|| j                  j                  z  || j                  j                  z  dz   z  = }}} | j                         |      }t	        j
                  ||      }|S c c}}w )a7  
        Tokenizes images into discrete tokens with VQGAN module and embeds
        them with text embeddings layer

        Args:
            pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, image_size, image_size)):
                The tensors corresponding to the input images.
        r   )r  r  rC  r  rG   split)r3   r  rI  rQ  rm   rn   split_sizesimage_featuress           r$   get_image_featureszEmu3Model.get_image_features  s     ,,\;G "-
 t||999et||GiGi>ilm>mn
 
 5224\B^[A
s   A B	rQ  rm   rn   c                     |ddddf   j                  d||dz         }| j                  j                  |      }| j                  j	                  |      }|S )a  
        Decodes generated image tokens from language model to continuous pixel values
        with VQGAN module via upsampling.

        Args:
            image_tokens (`torch.LongTensor` of shape `(batch_size, num_of_tokens)`):
                The tensors corresponding to the input images.
            height (`int`):
                Height of the generated image before upsampling.
            width (`int`):
                Width of the generated image before upsampling.
        Nr^   r   )re   r  r  r  rY  )r3   rQ  rm   rn   	sequencesimages         r$   decode_image_tokenszEmu3Model.decode_image_tokens  sX     !CRC(--b&%!)D	..>>yI##L1r#   	input_idsinputs_embedsr  c                 P   |m| | j                         t        j                  | j                  j                  t        j
                  |j                              k(  }|j                  d      }n|| j                  j                  k(  }|j                         }|j                  d      j                  |      j                  |j                        }|j                  d   |j                  d   z  }||   j                         |j                         k7  rt        d| d|       |S )z
        Obtains multimodal placeholdr mask from `input_ids` or `inputs_embeds`, and checks that the placeholder token count is
        equal to the length of multimodal features. If the lengths are different, an error is raised.
        )r  r  r^   r   r   z6Image features and image tokens do not match: tokens: z, features )r  rG   tensorr  rh  longr  allrf   rL  	expand_asr  rb   numel
ValueError)r3   r  r  r  special_image_maskn_image_tokensn_image_featuress          r$   get_placeholder_maskzEmu3Model.get_placeholder_mask  s    !.2M$2K2K2MT44CC5::^k^r^rs3 " "4!7!7!;!*d.E.E.T.T!T+//1/99"=GGVYYZgZnZno)//2^5I5I!5LL+,2248L8L8NNHHXXcdtcuv  "!r#   r6   r7   past_key_valuesr9   r:   r<   r=   c
           
      2   |du |duz  rt        d      | | j                         |      }|O| j                  ||      }t        j                  |d      }| j                  |||      }|j                  ||      } | j                  d||||||	d|
}|S )ap  
        image_sizes (`torch.LongTensor` of shape `(batch_size, 2)`):
            The sizes of the images in the batch, being (height, width) for each image. Image sizes can be obtained using
            [`AutoImageProcessor`]. See [`Emu3ImageProcessor.__call__`] for details ([]`Emu3Processor`] uses
            [`Emu3ImageProcessor`] for processing images).
        NzaYou cannot specify both input_ids and inputs_embeds at the same time, and must specify either oner   ra   )r  r  )r6   r7   r  r  r9   r:   r"   )r  r  r  rG   r"  r  masked_scatterr  )r3   r  r  rI  r6   r7   r  r  r9   r:   r<   image_embedsr  outputss                 r$   rE   zEmu3Model.forward  s    * -t";<s   7D557	BM#22<ML 99\q9L!%!:!:| "; " *889K\ZM "$// 
)%+')
 
 r#   )	NNNNNNNNN)r   r    r!   _checkpoint_conversion_mappingr-   r  r  r  r  rG   rL   rI   r  r  no_gradrF   r  r  r   r   rH   r   r   rJ   r   r   r   rK   r	   rE   rM   rN   s   @r$   r  r  z  s   &8,%G"64"U->-> UM]M] "u/@/@ uO_O_ $ ]]0@0@ # VY  $"))":?:K:K"]b]n]n"0  '+*.$(1537+/59$(59.##. ''. \\	.
 !.. u//0. "%.   1 12. D>. !!1!12. +,. 
u,,	-.  .r#   r  c                       e Zd ZdZdgZddddZ fdZd Zd	 Zd
e	j                  fdZd Zd Zed        Zed        Zed        Zd Zee	 	 	 	 	 	 	 	 	 	 	 d dej,                  dej.                  dej0                  deej0                     deej,                     dee   deej.                     dee   deej,                     deej,                     deeej0                  f   dee   d
ee e!f   fd              Z"	 	 	 	 	 	 	 d! fd	Z# xZ$S )"Emu3ForConditionalGeneration zlm_head.weightzmodel.text_modelzmodel.vqmodellm_head)z^text_model.modelz^vqmodelz^text_model.lm_headc                     t         |   |       t        |      | _        t	        j
                  |j                  j                  |j                  j                  d      | _	        | j                          y )NF)r   )r,   r-   r  r  r.   r4  r  hidden_size
vocab_sizer  rH  rZ   s     r$   r-   z%Emu3ForConditionalGeneration.__init__  sS     v&
yy!3!3!?!?ASASA^A^ejkr#   c                 6    | j                   j                         S r+   )r  r  r  s    r$   r  z1Emu3ForConditionalGeneration.get_input_embeddings#  s    zz..00r#   c                 :    | j                   j                  |       y r+   )r  r  r  s     r$   r  z1Emu3ForConditionalGeneration.set_input_embeddings&  s    

''.r#   r=   c                     | j                   S r+   )r  r  s    r$   get_output_embeddingsz2Emu3ForConditionalGeneration.get_output_embeddings)  s    ||r#   c                 :    | j                   j                  |       y r+   )r  r  r  s     r$   r  z(Emu3ForConditionalGeneration.set_decoder,  s    

w'r#   c                 6    | j                   j                         S r+   )r  r  r  s    r$   r  z(Emu3ForConditionalGeneration.get_decoder/  s    zz%%''r#   c                 .    | j                   j                  S r+   )r  r  r  s    r$   r  z'Emu3ForConditionalGeneration.text_model3  s    zz$$$r#   c                 .    | j                   j                  S r+   )r  r  r  s    r$   r  z$Emu3ForConditionalGeneration.vqmodel7  s    zz!!!r#   c                 .    | j                   j                  S r+   )r  r  r  s    r$   r  z/Emu3ForConditionalGeneration.vocabulary_mapping;  s    zz,,,r#   c                 :     | j                   j                  di |S r   )r  r  )r3   r<   s     r$   r  z0Emu3ForConditionalGeneration.decode_image_tokens?  s    -tzz--777r#   r  r  rI  r6   r7   r  r  r9   r:   labelslogits_to_keepr<   c                     | j                   d|||||||	d|}|d   }t        |t              rt        | d      n|}| j	                  |dd|ddf         }d}|
4 | j
                  d||
| j                  j                  j                  d|}t        |||j                  |j                  |j                        S )at  
        image_sizes (`torch.LongTensor` of shape `(batch_size, 2)`):
            The sizes of the images in the batch, being (height, width) for each image. Image sizes can be obtained using
            [`AutoImageProcessor`]. See [`Emu3ImageProcessor.__call__`] for details ([]`Emu3Processor`] uses
            [`Emu3ImageProcessor`] for processing images).
        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 Emu3Processor, Emu3ForConditionalGeneration
        >>> import torch
        >>> import requests
        >>> from PIL import Image

        >>> model = Emu3ForConditionalGeneration.from_pretrained("BAAI/Emu3-Chat-hf", torch_dtype=torch.bfloat16)
        >>> processor = Emu3Processor.from_pretrained("BAAI/Emu3-Chat-hf")

        >>> conversation = [
        ...     {
        ...     "role": "system",
        ...     "content": [
        ...         {"type": "text", "text": "You are a helpful assistant."},
        ...         ],
        ...     },
        ...     {
        ...     "role": "user",
        ...     "content": [
        ...         {"type": "image"},
        ...         {"type": "text", "text": "Please describe the image."},
        ...         ],
        ...     },
        ... ]

        >>> prompt = processor.apply_chat_template(conversation, add_generation_prompt=True)
        >>> image = Image.open(requests.get("https://www.ilankelman.org/stopsigns/australia.jpg", stream=True).raw)

        >>> inputs = processor(images=[image], text=[prompt], return_tensors="pt").to(model.device, torch.bfloat16)

        >>> generated_ids = model.generate(**inputs, max_new_tokens=100, do_sample=False)
        >>> processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
        ```)r  r6   r7   r  r  r9   r:   r   N)logitsr  r  )lossr  r  r5   r  r"   )r  r/  rF   slicer  loss_functionr(   r  r  r	   r  r5   r  )r3   r  r  rI  r6   r7   r  r  r9   r:   r  r  r<   r  r5   slice_indicesr  r  s                     r$   rE   z$Emu3ForConditionalGeneration.forwardB  s    | $** 	
)%+')	
 	
  
8B>SV8W~ot4]kmA}a,?@A%4%% f9P9P9[9[_eD &#33!//))
 	
r#   c	                 R    t        |   |f|||||||d|	}
|d   dk7  rd |
d<   |
S )N)r  r6   r  r:   r7   r  r9   r   r  )r,   prepare_inputs_for_generation)r3   r  r  r6   r  r:   r7   r9   r  r<   model_inputsr4   s              r$   r  z:Emu3ForConditionalGeneration.prepare_inputs_for_generation  sZ     w<

+)')%%

 

 !!+/L(r#   )NNNNNNNNNNr   )NNNNNTN)%r   r    r!   r[  _tied_weights_keysr  r-   r  r  r.   r   r  r  r  propertyr  r  r  r  r   r   rG   rI   rL   rH   r   r   rJ   r   rF   r   r   rK   r	   rE   r  rM   rN   s   @r$   r  r    s   *+/#(&"1/ryy (( % % " " - -8  '+*.$(1537+/59$(59-134X
##X
 ''X
 \\	X

 !.X
 u//0X
 "%X
   1 12X
 D>X
 !!1!12X
 ))*X
 c5<</0X
 +,X
 
u,,	-X
  X
z  r#   r  )r  r  r  r  r'  r  )Ir  	functoolsr   typingr   r   rG   torch.nnr.   torch.nn.functional
functionalr   torch.utils.checkpointcache_utilsr   
generationr   modeling_outputsr	   modeling_utilsr
   processing_utilsr   utilsr   r   r   chameleon.modeling_chameleonr   r   llama.modeling_llamar   r   r   r   r   siglip.modeling_siglipr   configuration_emu3r   r   r   
get_loggerr   loggerr   r'   r   rP   rv   rx   r   r   r   r   r   r   r   r   r   r   r   r   r  r  r'  rc  r  r  r  r  r  __all__r"   r#   r$   <module>r     s  "  % "        ) 6 - & > > w v 4 K K 
		H	%	N 	
#( #L$ryy $D	%H 	299 bii :!299 !H		 .")) &.(299 .(b<(299 <(~&o &V V299 D8 8v7ryy 7tCryy CLCryy CL l2 l2l2^3% 3%l'2I '

J 3 

&(;_ 8V# Vrh#6 hVr#   