
    qi^W                        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 ddlmZ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!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, ddl-m.Z.  G d dej^                        Z0 ed       G d dej^                               Z1 G d dej^                        Z2d Z3 ed      d@d       Z4d ejj                  d!e6d"ejj                  fd#Z7	 dAd$ej^                  d%ejj                  d&ejj                  d'ejj                  d(ejj                  dz  d)e8d*e8d+e$e&   fd,Z9 ee4       G d- d.ej^                               Z: G d/ d0e      Z;e G d1 d2e"             Z<e G d3 d4e<             Z= ed56       G d7 d8e<e             Z> ed56       G d9 d:ee<             Z? ed56       G d; d<ee<             Z@ ed56       G d= d>ee<             ZAg d?ZBy)B    )Callable)OptionalN)nn)auto_docstring   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_forward_from_hubuse_kernel_func_from_hubuse_kernelized_func)create_causal_mask)GenericForQuestionAnswering GenericForSequenceClassificationGenericForTokenClassificationGradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargscan_return_tuple)maybe_autocastmerge_with_config_defaults)capture_outputs   )ArceeConfigc                   $     e Zd Z fdZd Z xZS )ArceeMLPc                    t         |           || _        |j                  | _        |j                  | _        t        j                  | j                  | j                  |j                        | _        t        j                  | j                  | j                  |j                        | _	        t        |j                     | _        y )Nbias)super__init__confighidden_sizeintermediate_sizer   Linearmlp_biasup_proj	down_projr   
hidden_actact_fnselfr)   	__class__s     Z/opt/pipecat/venv/lib/python3.12/site-packages/transformers/models/arcee/modeling_arcee.pyr(   zArceeMLP.__init__3   s    !--!'!9!9yy!1!143I3IPVP_P_`4#9#94;K;KRXRaRabV../    c                 `    | j                  | j                  | j                  |                  S N)r/   r1   r.   )r3   xs     r5   forwardzArceeMLP.forward<   s"    ~~dkk$,,q/:;;r6   )__name__
__module____qualname__r(   r:   __classcell__r4   s   @r5   r#   r#   2   s    0<r6   r#   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 )	ArceeRMSNormepsreturnNc                     t         |           t        j                  t	        j
                  |            | _        || _        y)z;
        ArceeRMSNorm is equivalent to T5LayerNorm
        N)r'   r(   r   	Parametertorchonesweightvariance_epsilon)r3   r*   rC   r4   s      r5   r(   zArceeRMSNorm.__init__B   s1     	ll5::k#:; #r6   hidden_statesc                 "   |j                   }|j                  t        j                        }|j	                  d      j                  dd      }|t        j                  || j                  z         z  }| j                  |j                  |      z  S )N   T)keepdim)	dtypetorG   float32powmeanrsqrtrJ   rI   )r3   rK   input_dtypevariances       r5   r:   zArceeRMSNorm.forwardJ   sy    #))%((7 $$Q',,R,>%Ht?T?T4T(UU{{]--k:::r6   c                 ^    t        | j                  j                         d| j                   S )Nz, eps=)tuplerI   shaperJ   )r3   s    r5   
extra_reprzArceeRMSNorm.extra_reprQ   s*    ))*+6$2G2G1HIIr6   )gư>)
r;   r<   r=   floatr(   rG   Tensorr:   r[   r>   r?   s   @r5   rB   rB   @   s7    $ $$ $;U\\ ;ell ;Jr6   rB   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 )ArceeRotaryEmbeddinginv_freqNr)   c                    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)r'   r(   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenr)   rope_parametersrb   compute_default_rope_parametersr   attention_scalingregister_bufferclone)r3   r)   devicerope_init_fnr`   r4   s        r5   r(   zArceeRotaryEmbedding.__init__X   s    "("@"@$*$B$B!44[A!%!E!E>>Y&.t~~>L+7V+L($(ZeD0(..2BuUr6   rn   ztorch.deviceseq_lenrD   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   rM   rP   )rn   rP   )	ri   getattrr*   num_attention_headsrG   arangeint64rQ   r\   )r)   rn   rp   basedimattention_factorr`   s          r5   rj   z4ArceeRotaryEmbedding.compute_default_rope_parametersh   s    & %%l3fj$/c63E3EIcIc3c U\\!S!5;;?BB&X]XcXcBdgjjk
 )))r6   c                 N   | j                   d d d d f   j                         j                  |j                  d   dd      j	                  |j
                        }|d d d d d f   j                         }t        |j
                  j                  t              r/|j
                  j                  dk7  r|j
                  j                  nd}t        |d      5  |j                         |j                         z  j                  dd      }t        j                  ||fd	      }|j                         | j                  z  }|j                         | j                  z  }	d d d        j	                  |j                   
      	j	                  |j                   
      fS # 1 sw Y   AxY w)Nr   rN   r    mpscpuF)device_typeenabledrM   rz   rt   )r`   r\   expandrZ   rQ   rn   
isinstancetypestrr   	transposerG   catcosrk   sinrP   )
r3   r9   position_idsinv_freq_expandedposition_ids_expandedr   freqsembr   r   s
             r5   r:   zArceeRotaryEmbedding.forward   sR    !MM$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$cff177f&;;;	5 	5s   BFF$r8   )NNN)r;   r<   r=   rG   r]   __annotations__r!   r(   staticmethodr   intrY   r\   rj   no_gradr   r:   r>   r?   s   @r5   r_   r_   U   s    llV{ V  %)+/"*d"*(* t* 
~u$	%	* *: U]]_<  <r6   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..NrN   rM   r   )rZ   rG   r   )r9   x1x2s      r5   rotate_halfr      sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r6   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kr   r   unsqueeze_dimq_embedk_embeds          r5   apply_rotary_pos_embr      sY    & --
&C
--
&C3w;q>C/0G3w;q>C/0GGr6   rK   n_reprD   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)rZ   r   reshape)rK   r   batchnum_key_value_headsslenrs   s         r5   	repeat_kvr      so    
 2?1D1D.Ehz!!Qa"23::5BUW\^bdlmM  (;e(CT8TTr6   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 )NrM   r   rN   )rz   rP   )ptrainingr    )r   num_key_value_groupsrG   matmulr   r   
functionalsoftmaxrR   rQ   rP   r   r   
contiguous)r   r   r   r   r   r   r   r   
key_statesvalue_statesattn_weightsattn_outputs               r5   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$$r6   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z  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 )ArceeAttentionz=Multi-headed attention from 'Attention Is All You Need' paperr)   	layer_idxc                 d   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                        | _        y )Nrs   g      Tr%   )r'   r(   r)   r   ru   r*   rv   rs   r   r   r   attention_dropout	is_causalr   r,   attention_biasq_projk_projv_projo_projr3   r)   r   r4   s      r5   r(   zArceeAttention.__init__   sM   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
r6   NrK   position_embeddingsr   past_key_valuescache_positionr   rD   c                    |j                   d d }g |d| j                  }| j                  |      j                  |      j	                  dd      }	| j                  |      j                  |      j	                  dd      }
| j                  |      j                  |      j	                  dd      }|\  }}t        |	|
||      \  }	}
|'|||d}|j                  |
|| j                  |      \  }
}t        j                  | j                  j                  t              } || |	|
||f| j                  sdn| j                   | j"                  d|\  }} |j$                  g |d j'                         }| j)                  |      }||fS )NrN   r    rM   )r   r   r           )r   r   )rZ   rs   r   viewr   r   r   r   updater   r   get_interfacer)   _attn_implementationr   r   r   r   r   r   r   )r3   rK   r   r   r   r   r   input_shapehidden_shapequery_statesr   r   r   r   cache_kwargsattention_interfacer   r   s                     r5   r:   zArceeAttention.forward   s    $))#2.88b8$--8{{=166|DNNqRST[[/44\BLLQPQR
{{=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$2H2HLL	%
 	%
!\ *k));;;;FFHkk+.L((r6   )NNNN)r;   r<   r=   __doc__r!   r   r(   rG   r]   rY   r	   
LongTensorr   r   r:   r>   r?   s   @r5   r   r      s    G
{ 
s 
4 IM.2(,26))||)) #5<<#=>E)) t+	))
 )) ((4/)) +,)) 
u||U\\)	*))r6   r   c                   "    e Zd Zdedef fdZ	 	 	 	 	 	 ddej                  dej                  dz  dej                  dz  de	dz  d	e
dz  d
ej                  dz  deej                  ej                  f   dz  dee   dej                  fdZ xZS )ArceeDecoderLayerr)   r   c                     t         |           |j                  | _        t        ||      | _        t        |      | _        t        |j                  |j                        | _	        t        |j                  |j                        | _
        y )N)r)   r   rC   )r'   r(   r*   r   	self_attnr#   mlprB   rms_norm_epsinput_layernormpost_attention_layernormr   s      r5   r(   zArceeDecoderLayer.__init__$  sl    !--'vKF#+F,>,>FDWDWX(4V5G5GVM`M`(a%r6   NrK   r   r   r   	use_cacher   r   r   rD   c                     |}	| j                  |      } | j                  d|||||||d|\  }}
|	|z   }|}	| j                  |      }| j                  |      }|	|z   }|S )N)rK   r   r   r   r   r   r    )r   r   r   r   )r3   rK   r   r   r   r   r   r   r   residual_s              r5   r:   zArceeDecoderLayer.forward.  s     !,,];)4>> 	
')%+) 3	
 	
q !=0 !55mD/ =0r6   )NNNFNN)r;   r<   r=   r!   r   r(   rG   r]   r   r	   boolrY   r   r   r:   r>   r?   s   @r5   r   r   #  s    b{ bs b /304(,!&26HL|| t+ &&-	
  $; ((4/ #5<<#=>E +, 
r6   r   c                   J    e Zd ZU eed<   dZdZdgZdgZdZ	dZ
dZdZdZeedZy)ArceePreTrainedModelr)   modelTr   r   )rK   
attentionsN)r;   r<   r=   r!   r   base_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_supports_sdpa_supports_flex_attn_can_compile_fullgraph_supports_attention_backendr   r   _can_record_outputsr   r6   r5   r   r   P  sQ    &*#,-#4"5N!"&*$r6   r   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j                  dz  d
edz  dee   defd                     Z xZS )
ArceeModelr)   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   	Embeddingr*   embed_tokens
ModuleListrangenum_hidden_layersr   layersrB   r   normr_   
rotary_embgradient_checkpointing	post_initr   s      r5   r(   zArceeModel.__init__e  s     !.. ++LL):):F<N<NPTP`P`ammCHIaIaCbcivy1c
 !!3!39L9LM	.f=&+# 	 ds   DN	input_idsr   r   r   inputs_embedsr   r   r   rD   c                 D   |d u |d uz  rt        d      || j                  |      }|r|t        | j                        }|E||j	                         nd}	t        j                  |j                  d   |j                        |	z   }||j                  d      }t        | j                  |||||      }
|}| j                  ||      }| j                  d | j                  j                   D ]  } ||f|
|||||d|} | j                  |      }t        ||	      S )
Nz:You must specify exactly one of input_ids or inputs_embedsr   r   r    )rn   )r)   r  r   r   r   r   )r   )r   r   r   r   r   r   )last_hidden_stater   )
ValueErrorr   r
   r)   get_seq_lengthrG   rw   rZ   rn   r   r   r  r  r   r  r   )r3   r  r   r   r   r  r   r   r   past_seen_tokenscausal_maskrK   r   decoder_layers                 r5   r:   zArceeModel.forwardu  s]    -t";<YZZ *.*;*;I*FM0*$++>O!CRC^==?de]003M<P<PQTdd  )33A6L(;;'))+%
 &"oom,oW![[)H4;;+H+HI 
	M)	*$7) /#-	 	M
	 		-0&++
 	
r6   )NNNNNNN)r;   r<   r=   r!   r(   r   r   r   rG   r   r]   r	   FloatTensorr   r   r   r   r:   r>   r?   s   @r5   r   r   c  s    {     .2.204(,2626!%9
##d*9
 t+9
 &&-	9

 9
 ((4/9
 ((4/9
 $;9
 +,9
 
!9
    9
r6   r   zarcee-ai/AFM-4.5B)
checkpointc                   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 )ArceeForCausalLMzlm_head.weightzmodel.embed_tokens.weightlm_headcolwise_gather_outputrK   logitsc                     t         |   |       t        |      | _        |j                  | _        t        j                  |j                  |j                  d      | _        | j                          y )NFr%   )
r'   r(   r   r   r   r   r,   r*   r  r  r2   s     r5   r(   zArceeForCausalLM.__init__  sU     '
 ++yy!3!3V5F5FUS 	r6   Nr  r   r   r   r  labelsr   r   logits_to_keepr   rD   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, ArceeForCausalLM

        >>> model = ArceeForCausalLM.from_pretrained("meta-arcee/Arcee-2-7b-hf")
        >>> tokenizer = AutoTokenizer.from_pretrained("meta-arcee/Arcee-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."
        ```)r  r   r   r   r  r   r   N)r  r  r   )lossr  r   rK   r   r   )r   r	  r   r   slicer  loss_functionr)   r   r   r   rK   r   )r3   r  r   r   r   r  r  r   r   r  r   outputsrK   slice_indicesr  r  s                   r5   r:   zArceeForCausalLM.forward  s    @ ,64:: 	,
)%+')	,
 	,
  118B>SV8W~ot4]kmA}a,?@A%4%%pVFt{{OeOepiopD%#33!//))
 	
r6   )	NNNNNNNNr   )r;   r<   r=   _tied_weights_keys_tp_plan_pp_planr(   r   r   rG   r   r]   r	   r  r   r   r   r   r   r:   r>   r?   s   @r5   r  r    s/   *,GH23H_-z:;H  .2.204(,26*.!%26-.8
##d*8
 t+8
 &&-	8

 8
 ((4/8
   4'8
 $;8
 ((4/8
 ell*8
 +,8
 
 8
  8
r6   r  c                       e Zd Zy)ArceeForSequenceClassificationNr;   r<   r=   r   r6   r5   r#  r#         r6   r#  c                       e Zd ZdZy)ArceeForQuestionAnsweringtransformerN)r;   r<   r=   r   r   r6   r5   r'  r'    s    %r6   r'  c                       e Zd Zy)ArceeForTokenClassificationNr$  r   r6   r5   r*  r*  
  r%  r6   r*  )r  r'  r#  r*  r   r   )r    )r   )Ccollections.abcr   typingr   rG   r   transformers.utilsr   activationsr   cache_utilsr	   r
   
generationr   integrationsr   r   r   masking_utilsr   modeling_layersr   r   r   r   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   utils.genericr   r   utils.output_capturingr   configuration_arceer!   Moduler#   rB   r_   r   r   r]   r   r   r\   r   r   r   r   r   r  r#  r'  r*  __all__r   r6   r5   <module>r>     s_  * %    - ! . ) f f /  P K F & 9 G 5 ,<ryy < Y'J299 J (J(><299 ><B( *+ ,2	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 LL4'% % % '(%2 )*C)RYY C) +C)L*2 *Z ?  $ M
% M
 M
` ./H
+_ H
 0H
V ./	%EG[ 	 0	 ./& ;=Q & 0& ./	"?AU 	 0	r6   