
    iu                        d dl mZ d dlmZ d dlZd dlmZ ddlmZ ddl	m
Z
 ddlmZmZ dd	lmZ dd
lmZmZmZ ddlmZmZ ddlmZ ddlmZmZmZ ddlmZmZ ddl m!Z!m"Z" ddl#m$Z$ ddl%m&Z&m'Z'm(Z( ddl)m*Z*m+Z+ ddl,m-Z-  G d dej\                        Z/ ed       G d dej\                               Z0 G d dej\                        Z1 G d dej\                        Z2 G d dejf                        Z4 G d  d!ej\                        Z5d" Z6 ed#      d=d$       Z7d%ejp                  d&e9d'ejp                  fd(Z:	 d>d)ej\                  d*ejp                  d+ejp                  d,ejp                  d-ejp                  dz  d.e;d/e;d0e$e&   fd1Z< ee7       G d2 d3ej\                               Z= G d4 d5e      Z> G d6 d7e"      Z?e' G d8 d9e?             Z@e' G d: d;e?e             ZAg d<ZBy)?    )Callable)OptionalN)nn   )initialization)ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_forward_from_hubuse_kernel_func_from_hubuse_kernelized_func)create_causal_mask!create_sliding_window_causal_mask)GradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPastMoeModelOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuple)check_model_inputsmaybe_autocast   )AfmoeConfigc                        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 )AfmoeRotaryEmbedding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defaultr#   F)
persistentoriginal_inv_freq)super__init__max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenr$   rope_parametersr&   compute_default_rope_parametersr   attention_scalingregister_bufferclone)selfr$   devicerope_init_fnr#   	__class__s        r/home/obispo/Crisostomo_bridge/mision_env/lib/python3.12/site-packages/transformers/models/afmoe/modeling_afmoe.pyr+   zAfmoeRotaryEmbedding.__init__.   s    "("@"@$*$B$B!44[A!%!E!E>>Y&.t~~>L+7V+L($(ZeD0(..2BuU    r5   ztorch.deviceseq_lenreturnz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      dtyper5   rA   )	r/   getattrhidden_sizenum_attention_headstorcharangeint64tofloat)r$   r5   r:   basedimattention_factorr#   s          r8   r0   z4AfmoeRotaryEmbedding.compute_default_rope_parameters>   s    & %%l3fj$/c63E3EIcIc3c U\\!S!5;;?BB&X]XcXcBdgjjk
 )))r9   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   r   mpscpuF)device_typeenabledr?   rL   r@   )r#   rJ   expandshaperI   r5   
isinstancetypestrr   	transposerF   catcosr1   sinrA   )
r4   xposition_idsinv_freq_expandedposition_ids_expandedrR   freqsembr\   r]   s
             r8   forwardzAfmoeRotaryEmbedding.forward\   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$N)NNN)__name__
__module____qualname__rF   Tensor__annotations__r    r+   staticmethodr   inttuplerJ   r0   no_gradr   rd   __classcell__r7   s   @r8   r"   r"   +   s    llV{ V  %)+/"*d"*(* t* 
~u$	%	* *: U]]_<  <r9   r"   RMSNormc                   ,     e Zd Zd fd	Zd Zd Z xZS )AfmoeRMSNormc                     t         |           t        j                  t	        j
                  |            | _        || _        y)z;
        AfmoeRMSNorm is equivalent to T5LayerNorm
        N)r*   r+   r   	ParameterrF   onesweightvariance_epsilon)r4   rD   epsr7   s      r8   r+   zAfmoeRMSNorm.__init__n   s1     	ll5::k#:; #r9   c                 "   |j                   }|j                  t        j                        }|j	                  d      j                  dd      }|t        j                  || j                  z         z  }| j                  |z  j                  |      S )Nr?   rO   T)keepdim)	rA   rI   rF   float32powmeanrsqrtrx   rw   )r4   hidden_statesinput_dtypevariances       r8   rd   zAfmoeRMSNorm.forwardv   sy    #))%((7 $$Q',,R,>%Ht?T?T4T(UUm+//<<r9   c                 ^    t        | j                  j                         d| j                   S )Nz, eps=)rm   rw   rV   rx   )r4   s    r8   
extra_reprzAfmoeRMSNorm.extra_repr}   s*    ))*+6$2G2G1HIIr9   )gư>)rf   rg   rh   r+   rd   r   ro   rp   s   @r8   rs   rs   l   s    $=Jr9   rs   c                   &     e Zd Zd fd	Zd Z xZS )AfmoeMLPc                    t         |           || _        |j                  | _        ||j                  n|| _        t        j                  | j                  | j                  d      | _        t        j                  | j                  | j                  d      | _        t        j                  | j                  | j                  d      | _	        t        |j                     | _        y NFbias)r*   r+   r$   rD   intermediate_sizer   Linear	gate_projup_proj	down_projr   
hidden_actact_fn)r4   r$   r   r7   s      r8   r+   zAfmoeMLP.__init__   s    !--=N=V!9!9\m4#3#3T5K5KRWXyy!1!143I3IPUV4#9#94;K;KRWXV../r9   c                     | j                  | j                  | j                  |            | j                  |      z        }|S re   )r   r   r   r   )r4   r^   r   s      r8   rd   zAfmoeMLP.forward   s6    NN4;;t~~a/@#ADLLQRO#ST	r9   re   )rf   rg   rh   r+   rd   ro   rp   s   @r8   r   r      s    0r9   r   c                   Z     e Zd ZdZ fdZdej                  dej                  fdZ xZS )AfmoeTokenChoiceRouterz
    Token-choice top-K router for MoE routing.

    This router assigns each token to the top-K experts based on sigmoid scores, matching the released checkpoints.
    c                     t         |           || _        |j                  | _        |j
                  | _        |j                  | _        t        j                  |j                  |j
                  d      | _
        y r   )r*   r+   r$   num_experts_per_toktop_knum_expertsroute_scaler   r   rD   gater4   r$   r7   s     r8   r+   zAfmoeTokenChoiceRouter.__init__   s^    //
!--!--IIf00&2D2D5Q	r9   r   expert_biasc                    |j                   \  }}}|j                  d|      }t        j                  | j	                  |      j                  t        j                              }t        j                  ||z   | j                  d      \  }}|j                  d|      }|j                  dd      dz   }||z  }|| j                  z  }||fS )NrO   r   )krL   )rL   indexT)rL   r{   g#B;)rV   viewrF   sigmoidr   rI   r|   topkr   gathersumr   )	r4   r   r   _
hidden_dimscoresselected_experts
top_scoresdenominators	            r8   rd   zAfmoeTokenChoiceRouter.forward   s    (..1j%**2z:tyy7::5==IJ#jj+)=QRS]]q0@]A
 nnTn:UB+-
$"2"22
+++r9   )	rf   rg   rh   __doc__r+   rF   ri   rd   ro   rp   s   @r8   r   r      s)    R,U\\ , ,r9   r   c                        e Zd ZdZdef fdZdej                  dej                  dej                  dej                  fdZ xZ	S )	AfmoeExpertsz
    Container holding the routed experts.

    This mirrors the Experts pattern used across other MoE models to ease checkpoint conversion.
    r$   c                     t         |           |j                  | _        |j                  | _        t        | j                        D ](  }| j                  t        ||j                               * y )N)r   )	r*   r+   r   r   r   rangeappendr   moe_intermediate_size)r4   r$   r   r7   s      r8   r+   zAfmoeExperts.__init__   s^    //
!--t''( 	ZAKK6;W;WXY	Zr9   r   r   routing_weightsr;   c                 0   |j                   \  }}}|dk(  r|j                  |d|      S |j                  d|      }|j                   d   }t        j                  |j                   d   |j
                  t        j                        j                  |      }	|j                  d      }
|j                  d      }t        j                  |
d      }|	|   }	|
|   }
||   }|j                  d|	      }t        j                  |      }t        j                  |
d      \  }}d}t        |j                         |j                               D ]'  \  }}|dk(  r||z   }||| } | |   |      }|||| |}) |j                  t        j                         |j#                  d      z  j                  |j$                        }t        j                  |      }|	j#                  d      j'                  |      }|j)                  d||       |j                  |||      S )z
        Args:
            hidden_states: (batch, seq, hidden)
            selected_experts: (batch, seq, top_k)
            routing_weights: (batch, seq, top_k)
        r   rO   rB   T)stable)return_counts)rV   	new_zerosr   rF   rG   r5   longrepeat_interleavereshapeargsortindex_select
zeros_likeunique_consecutiveziptolistrI   r|   	unsqueezerA   	expand_asscatter_add_)r4   r   r   r   
batch_sizer:   r   hidden_states_flatr   token_indicesexpert_indicessortingdispatched_tokensexpert_outputsunique_expertscountsstart	expert_idcountendexpert_inputexpert_outputweighted_outputs
aggregatedscatter_indicess                            r8   rd   zAfmoeExperts.forward   s    +8*=*='
GZa< **:q*EE*//J? &&r* $$Q'0D0DEJJ


E
" 	 *11"5)11"5--t<%g.'0)'2.;;A}M))*;<!&!9!9.X\!] #N$9$9$;V]]_ M 	Iuz%-C,U37L+DOL9M(5N5%E	 +--emm<?X?XY[?\\``anatatu%%&89
'11"5??@PQ?4DEz7J??r9   )
rf   rg   rh   r   r    r+   rF   ri   rd   ro   rp   s   @r8   r   r      sR    Z{ Z-@"\\-@=B\\-@\a\h\h-@	-@r9   r   c                   (     e Zd ZdZ fdZd Z xZS )AfmoeMoEz
    Mixture of Experts (MoE) module for AFMoE.

    This module implements a sparse MoE layer with both shared experts (always active) and
    routed experts (activated based on token-choice routing).
    c                 2   t         |           || _        t        |      | _        t        ||j                  |j                  z        | _        t        |      | _
        t        j                  t        j                  |j                        d      | _        y )NF)requires_grad)r*   r+   r$   r   routerr   r   num_shared_expertsshared_expertsr   expertsr   ru   rF   zerosr   r   r   s     r8   r+   zAfmoeMoE.__init__   sp    ,V4&vv/K/KfNgNg/gh#F+<<F4F4F(GW\]r9   c                    |j                   \  }}}|j                  d|      }| j                  || j                        \  }}|j                  ||| j                  j
                        }|j                  ||| j                  j
                        }| j                  |      j                  |||      }| j                  |||      }	||	z   S )NrO   )rV   r   r   r   r$   r   r   r   )
r4   r   r   r:   r   r   r   r   shared_outputrouted_outputs
             r8   rd   zAfmoeMoE.forward   s    *7*=*='
GZ*//J? (,{{=$BRBR'S$
$__Z$++:Y:YZ
+00WdkkFeFef ++,>?DDZQXZde]4DjQ},,r9   )rf   rg   rh   r   r+   rd   ro   rp   s   @r8   r   r      s    ^-r9   r   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..NrO   r?   rT   )rV   rF   r[   )r^   x1x2s      r8   rotate_halfr     sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r9   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.
    )r   r   )qr   r\   r]   unsqueeze_dimq_embedk_embeds          r8   apply_rotary_pos_embr     sY    & --
&C
--
&C3w;q>C/0G3w;q>C/0GGr9   r   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)rV   rU   r   )r   r   batchnum_key_value_headsslenr>   s         r8   	repeat_kvr   ,  so    
 2?1D1D.Ehz!!Qa"23::5BUW\^bdlmM  (;e(CT8TTr9   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 )Nr?   r   rO   )rL   rA   )ptrainingr   )r   num_key_value_groupsrF   matmulrZ   rV   r   
functionalsoftmaxr|   rI   rA   r   r   
contiguous)r   r   r   r   r   r   r   r   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r8   eager_attention_forwardr  8  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$$r9   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                  f   fdZ xZS )AfmoeAttentionaJ  
    Multi-headed attention module with optional sliding window and gating.

    This attention mechanism supports both full attention and sliding window attention,
    and includes Q/K normalization and gating of the output. It inherits from [`LlamaAttention`] to minimize the amount
    of custom logic we need to maintain.
    r$   	layer_idxc                    t         |           || _        || _        t	        |d|j
                  |j                  z        | _        |j                  |j                  z  | _	        | j                  dz  | _
        |j                  | _        d| _        t        j                  |j
                  |j                  | j                  z  |j                        | _        t        j                  |j
                  |j                  | j                  z  |j                        | _        t        j                  |j
                  |j                  | j                  z  |j                        | _        t        j                  |j                  | j                  z  |j
                  |j                        | _        |j(                  |   dk(  | _        | j*                  r|j,                  nd | _        t/        | j                  |j0                        | _        t/        | j                  |j0                        | _        t        j                  |j
                  |j                  | j                  z  d      | _        y )Nr>   g      Tr   sliding_attentionry   F)r*   r+   r$   r  rC   rD   rE   r>   r   r   r   attention_dropout	is_causalr   r   attention_biasq_projk_projv_projo_projlayer_typesis_local_attentionsliding_windowrs   rms_norm_epsq_normk_normr   r4   r$   r  r7   s      r8   r+   zAfmoeAttention.__init__\  s   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf

 #)"4"4Y"?CV"V7;7N7Nf33TX"4==f6I6IJ"4==f6I6IJ6#5#5v7Q7QTXTaTa7ahmnr9   Nr   position_embeddingsr   past_key_valuecache_positionr   r;   c                    |j                   d d }g |d| j                  }| j                  |      j                  |      }	| j	                  |      j                  |      }
| j                  |      j                  |      }| j                  |      }| j                  |	      j                  dd      }	| j                  |
      j                  dd      }
|j                  dd      }| j                  r|\  }}t        |	|
||      \  }	}
|%d|i}|j                  |
|| j                  |      \  }
}t        j                  | j                   j"                  t$              } || |	|
|f|| j&                  sdn| j(                  | j*                  | j,                  d|\  }} |j                  g |d j/                         }|t1        j2                  |      z  }| j5                  |      }||fS )NrO   r   r?   r          )r   r   r   r  )rV   r>   r  r   r  r  r   r  rZ   r  r  r   updater  r   get_interfacer$   _attn_implementationr  r   r  r   r  r  rF   r   r  )r4   r   r  r   r  r  r   input_shapehidden_shapequery_statesr  r  gate_statesr\   r]   cache_kwargsattention_interfaceoutputr  r  s                       r8   rd   zAfmoeAttention.forward{  s    $))#2.88b8$--8{{=166|D[[/44\B
{{=166|Dnn]3{{<0::1a@[[,66q!<
#--a3""*HC';L*VY[^'_$L*%,n=L'5'<'<ZW[WeWegs't$J(?(M(MKK,,.E)
  3	
 

 *#}}C$2H2HLL..
 
 
 
 .k.2.99;%--44kk&)L((r9   )NN)rf   rg   rh   r   r    rl   r+   rF   ri   rm   r	   
LongTensorr   r   rd   ro   rp   s   @r8   r
  r
  R  s    o{ os oH (,260)||0) #5<<#=>0) t+	0)
 0) ((4/0) +,0) 
u||U\\)	*0)r9   r
  c                   &    e Zd 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 )AfmoeDecoderLayerz
    AFMoE decoder layer with dual normalization.

    This layer applies self-attention followed by either a dense MLP or MoE block,
    with dual normalization (pre and post) around each component.
    r$   r  c                 P   t         |           |j                  | _        || _        t	        ||      | _        |j                  |   | _        t        |j                  |j                        | _
        t        |j                  |j                        | _        t        |j                  |j                        | _        t        |j                  |j                        | _        ||j                  k\  | _        | j                  rt!        |      | _        y t%        |      | _        y )N)r$   r  r  )r*   r+   rD   r  r
  	self_attnr  attention_typers   r  input_layernormpost_attention_layernormpre_mlp_layernormpost_mlp_layernormnum_dense_layersmoe_enabledr   mlpr   r  s      r8   r+   zAfmoeDecoderLayer.__init__  s    !--"'vK$00;  ,F,>,>FDWDWX(4V5G5GVM`M`(a% ".f.@.@fFYFY!Z".v/A/AvGZGZ"[ %(?(??'DH'DHr9   Nr   r   r_   r  	use_cacher  r  r   r;   c                    |}	| j                  |      } | j                  d|||||||d|\  }}
| j                  |      }|	|z   }|}	| j                  |      }| j	                  |      }| j                  |      }|	|z   }|S )N)r   r   r_   r  r9  r  r   )r2  r0  r3  r4  r8  r5  )r4   r   r   r_   r  r9  r  r  r   residualr   s              r8   rd   zAfmoeDecoderLayer.forward  s     ! ,,];)4>> 	
')%)) 3	
 	
q 55mD =0 !..}=///> =0r9   )NNNNNN)rf   rg   rh   r   r    rl   r+   rF   ri   r,  r	   boolrm   r   r   FloatTensorrd   ro   rp   s   @r8   r.  r.    s    ({ (s (4 /304'+!%26HL#||# t+# &&-	#
 # $;# ((4/# #5<<#=>E# +,# 
		#r9   r.  c                   d     e Zd ZU dZeed<   dZdgZdgZe	e
dZg dZdZdZdZdZdZ fd	Z xZS )
AfmoePreTrainedModelz
    An abstract class to handle weights initialization and a simple interface for downloading and loading pretrained
    models.
    r$   modelr.  past_key_values)r   
attentions)r2  r3  r4  r5  r  r  normr   Tc                     t         |   |       t        |t              r*t	        j
                  |j                  j                         yt        |t              r t	        j
                  |j                         yy)zInitialize the weightsN)
r*   _init_weightsrW   r   initzeros_r   rw   r   r   )r4   r   r7   s     r8   rF  z"AfmoePreTrainedModel._init_weights  sR    f%f45KK**+)KK**+ *r9   )rf   rg   rh   r   r    rj   base_model_prefix_no_split_modules_skip_keys_device_placementr.  r
  _can_record_outputs_keep_in_fp32_modules_supports_sdpa_supports_flash_attn_supports_flex_attn_supports_attention_backendsupports_gradient_checkpointingrF  ro   rp   s   @r8   r@  r@    sg    
 ,-#4"5*$	 N"&&*#, ,r9   r@  c                       e Zd ZdZdef fdZee	 	 	 	 	 	 	 ddej                  dz  dej                  dz  dej                  dz  dej                  dz  d	edz  d
ej                  dz  dedz  dee   deez  fd              Z xZS )
AfmoeModelz
    Transformer decoder consisting of *config.num_hidden_layers* layers. Each layer is a [`AfmoeDecoderLayer`]

    Args:
        config: AfmoeConfig
    r$   c           	         t         |   |       |j                  | _        |j                  | _        t        j                  |j                  |j                  | j                        | _        t        j                  t        |j                        D cg c]  }t        ||       c}      | _        t        |j                  |j                        | _        t#        |      | _        d| _        | j)                          y c c}w )Nr  r$   F)r*   r+   pad_token_idpadding_idx
vocab_sizer   	EmbeddingrD   embed_tokens
ModuleListr   num_hidden_layersr.  layersrs   r  rD  r"   
rotary_embgradient_checkpointing	post_initr  s      r8   r+   zAfmoeModel.__init__#  s     !.. ++LL):):F<N<NPTP`P`ammCHIaIaCbcivy1c
 !!3!39L9LM	.f=&+# ds   DN	input_idsr   inputs_embedsr_   rB  r  r9  r   r;   c                    |d u |d uz  rt        d      |r|t        | j                        }|| j                  |      }|F||j	                         nd}	t        j                  |	|	|j                  d   z   |j                        }||j                  d      }t        |x}
t              s)| j                  ||||d}t        di |t        di |d}
|}| j                  j                  r|| j                  j                  dz  z  }| j!                  ||      }| j"                  D ]  } ||f|
|j$                     |||||d	|}! | j'                  |      }t)        ||r|
      S d 
      S )Nz:You must specify exactly one of input_ids or inputs_embedsrV  r   r   )r5   )r$   input_embedsr   r  rB  )full_attentionr  g      ?)r   r_   r  r9  r  r  )last_hidden_staterB  r;  )
ValueErrorr
   r$   r[  get_seq_lengthrF   rG   rV   r5   r   rW   dictr   r   mup_enabledrD   r_  r^  r1  rD  r   )r4   rb  r   rc  r_   rB  r  r9  r   past_seen_tokenscausal_mask_mappingmask_kwargsr   r  decoder_layers                  r8   rd   zAfmoeModel.forward2  s    -t";<YZZ0*$++>O  --i8M!CRC^==?de"\\  =#6#6q#99$++N
 )33A6L ?-F++ -"0"0#2K #5"C{"C%F%U%U#
 & ;;"")T[[-D-Dc-IJM"oom\J![[ 
	M)	2=3O3OP).#-$7	 	M
	 		-0%+/8O
 	
>B
 	
r9   )NNNNNNN)rf   rg   rh   r   r    r+   r   r   rF   r,  ri   r>  r	   r=  r   r   rm   r   rd   ro   rp   s   @r8   rT  rT    s    {   .2.22604(,26!%D
##d*D
 t+D
 ((4/	D

 &&-D
 D
 ((4/D
 $;D
 +,D
 
'	'D
  D
r9   rT  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 )AfmoeForCausalLMzlm_head.weightzmodel.embed_tokens.weightlm_headcolwise_gather_outputr   logitsc                     t         |   |       t        |      | _        |j                  | _        t        j                  |j                  |j                  d      | _        | j                          y r   )
r*   r+   rT  rA  rY  r   r   rD   rr  ra  r   s     r8   r+   zAfmoeForCausalLM.__init__  sS     '
 ++yy!3!3V5F5FUSr9   Nrb  r   r_   rB  rc  labelsr9  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  
        Example:

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

        >>> model = AfmoeForCausalLM.from_pretrained("meta-afmoe/Afmoe-2-7b-hf")
        >>> tokenizer = AutoTokenizer.from_pretrained("meta-afmoe/Afmoe-2-7b-hf")

        >>> 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."
        ```)rb  r   r_   rB  rc  r9  r  N)rt  rv  rY  )lossrt  rB  r   rC  r;  )rA  rg  rW   rl   slicerr  loss_functionr$   rY  r   rB  r   rC  )r4   rb  r   r_   rB  rc  rv  r9  r  rw  r   outputsr   slice_indicesrt  ry  s                   r8   rd   zAfmoeForCausalLM.forward  s    @ ,64:: 	,
)%+')	,
 	,
  118B>SV8W~ot4]kmA}a,?@A%4%%pVFt{{OeOepiopD%#33!//))
 	
r9   )	NNNNNNNNr   )rf   rg   rh   _tied_weights_keys_tp_plan_pp_planr+   r   r   rF   r,  ri   r	   r>  r=  rl   r   r   r   rd   ro   rp   s   @r8   rq  rq  {  s/   *,GH23H_-z:;H  .2.204(,26*.!%26-.8
##d*8
 t+8
 &&-	8

 8
 ((4/8
   4'8
 $;8
 ((4/8
 ell*8
 +,8
 
 8
  8
r9   rq  )rq  rT  r@  )r   )r!  )Ccollections.abcr   typingr   rF   r    r   rG  activationsr   cache_utilsr	   r
   
generationr   integrationsr   r   r   masking_utilsr   r   modeling_layersr   modeling_outputsr   r   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.genericr   r   configuration_afmoer    Moduler"   rs   r   r   r\  r   r   r   r   ri   rl   r   rJ   r  r
  r.  r@  rT  rq  __all__r;  r9   r8   <module>r     s  * %    & ! . ) f f R 9 g g K F & I I ? ,><299 ><B Y'J299 J (J(ryy  ,RYY ,:;@2== ;@|-ryy ->( *+ ,2	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 LL4'% % % '(%4 )*X)RYY X) +X)vB2 BJ$,? $,N ]
% ]
 ]
@ F
+_ F
 F
R Er9   