
    i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,  G d dejZ                        Z. ed       G d dejZ                               Z/ G d dejZ                        Z0d Z1 ed      d?d       Z2dejf                  d e4d!ejf                  fd"Z5	 d@d#ejZ                  d$ejf                  d%ejf                  d&ejf                  d'ejf                  dz  d(e6d)e6d*e$e&   fd+Z7 ee2       G d, d-ejZ                               Z8 G d. d/e      Z9e G d0 d1e"             Z:e G d2 d3e:             Z; ed45       G d6 d7e:e             Z< ed45       G d8 d9ee:             Z= ed45       G d: d;ee:             Z> ed45       G d< d=ee:             Z?g d>Z@y)A    )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)check_model_inputsmaybe_autocast   )ArceeConfigc                   $     e Zd Z fdZd Z xZS )ArceeMLPc                    t         |           || _        |j                  | _        |j                  | _        t        j                  | j                  | j                  |j                        | _        t        j                  | j                  | j                  |j                        | _	        t        |j                     | _        y )Nbias)super__init__confighidden_sizeintermediate_sizer   Linearmlp_biasup_proj	down_projr   
hidden_actact_fnselfr(   	__class__s     r/home/obispo/Crisostomo_bridge/mision_env/lib/python3.12/site-packages/transformers/models/arcee/modeling_arcee.pyr'   zArceeMLP.__init__2   s    !--!'!9!9yy!1!143I3IPVP_P_`4#9#94;K;KRXRaRabV../    c                 `    | j                  | j                  | j                  |                  S N)r.   r0   r-   )r2   xs     r4   forwardzArceeMLP.forward;   s"    ~~dkk$,,q/:;;r5   )__name__
__module____qualname__r'   r9   __classcell__r3   s   @r4   r"   r"   1   s    0<r5   r"   RMSNormc                   ,     e Zd Zd fd	Zd Zd Z xZS )ArceeRMSNormc                     t         |           t        j                  t	        j
                  |            | _        || _        y)z;
        ArceeRMSNorm is equivalent to T5LayerNorm
        N)r&   r'   r   	Parametertorchonesweightvariance_epsilon)r2   r)   epsr3   s      r4   r'   zArceeRMSNorm.__init__A   s1     	ll5::k#:; #r5   c                 "   |j                   }|j                  t        j                        }|j	                  d      j                  dd      }|t        j                  || j                  z         z  }| j                  |j                  |      z  S )N   T)keepdim)	dtypetorD   float32powmeanrsqrtrG   rF   )r2   hidden_statesinput_dtypevariances       r4   r9   zArceeRMSNorm.forwardI   sy    #))%((7 $$Q',,R,>%Ht?T?T4T(UU{{]--k:::r5   c                 ^    t        | j                  j                         d| j                   S )Nz, eps=)tuplerF   shaperG   )r2   s    r4   
extra_reprzArceeRMSNorm.extra_reprP   s*    ))*+6$2G2G1HIIr5   )gư>)r:   r;   r<   r'   r9   rY   r=   r>   s   @r4   rA   rA   ?   s    $;Jr5   rA   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_parametersr^   compute_default_rope_parametersr   attention_scalingregister_bufferclone)r2   r(   devicerope_init_fnr\   r3   s        r4   r'   zArceeRotaryEmbedding.__init__W   s    "("@"@$*$B$B!44[A!%!E!E>>Y&.t~~>L+7V+L($(ZeD0(..2BuUr5   rj   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   rJ   rM   )rj   rM   )	re   getattrr)   num_attention_headsrD   arangeint64rN   float)r(   rj   rl   basedimattention_factorr\   s          r4   rf   z4ArceeRotaryEmbedding.compute_default_rope_parametersg   s    & %%l3fj$/c63E3EIcIc3c U\\!S!5;;?BB&X]XcXcBdgjjk
 )))r5   c                 N   | j                   d d d d f   j                         j                  |j                  d   dd      j	                  |j
                        }|d d d d d f   j                         }t        |j
                  j                  t              r/|j
                  j                  dk7  r|j
                  j                  nd}t        |d      5  |j                         |j                         z  j                  dd      }t        j                  ||fd	      }|j                         | j                  z  }|j                         | j                  z  }	d d d        j	                  |j                   
      	j	                  |j                   
      fS # 1 sw Y   AxY w)Nr   rK   r   mpscpuF)device_typeenabledrJ   rx   rq   )r\   rv   expandrX   rN   rj   
isinstancetypestrr   	transposerD   catcosrg   sinrM   )
r2   r8   position_idsinv_freq_expandedposition_ids_expandedr}   freqsembr   r   s
             r4   r9   zArceeRotaryEmbedding.forward   sR    !MM$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$cff177f&;;;	5 	5s   BFF$r7   )NNN)r:   r;   r<   rD   Tensor__annotations__r    r'   staticmethodr   intrW   rv   rf   no_gradr   r9   r=   r>   s   @r4   r[   r[   T   s    llV{ V  %)+/"*d"*(* t* 
~u$	%	* *: U]]_<  <r5   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..NrK   rJ   r   )rX   rD   r   )r8   x1x2s      r4   rotate_halfr      sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r5   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          r4   apply_rotary_pos_embr      sY    & --
&C
--
&C3w;q>C/0G3w;q>C/0GGr5   rS   n_reprm   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)rX   r   reshape)rS   r   batchnum_key_value_headsslenrp   s         r4   	repeat_kvr      so    
 2?1D1D.Ehz!!Qa"23::5BUW\^bdlmM  (;e(CT8TTr5   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 )NrJ   r   rK   )rx   rM   )ptrainingr   )r   num_key_value_groupsrD   matmulr   rX   r   
functionalsoftmaxrO   rN   rM   r   r   
contiguous)r   r   r   r   r   r   r   r   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r4   eager_attention_forwardr      s    3 ; ;<JUF$?$?@L<<z';';Aq'ABWLL!$Q1.D
0@0@0D.D%DE#k1==((2U]](SVVW\WbWbcL==((6??([L,,|\:K''1-88:K$$r5   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 )Nrp   g      Tr$   )r&   r'   r(   r   rr   r)   rs   rp   r   r   r   attention_dropout	is_causalr   r+   attention_biasq_projk_projv_projo_projr2   r(   r   r3   s      r4   r'   zArceeAttention.__init__   sM   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
r5   NrS   position_embeddingsr   past_key_valuescache_positionr   rm   c                    |j                   d d }g |d| j                  }| j                  |      j                  |      j	                  dd      }	| j                  |      j                  |      j	                  dd      }
| j                  |      j                  |      j	                  dd      }|\  }}t        |	|
||      \  }	}
|'|||d}|j                  |
|| j                  |      \  }
}t        j                  | j                  j                  t              } || |	|
||f| j                  sdn| j                   | j"                  d|\  }} |j$                  g |d j'                         }| j)                  |      }||fS )NrK   r   rJ   )r   r   r           )r   r   )rX   rp   r   viewr   r   r   r   updater   r   get_interfacer(   _attn_implementationr   r   r   r   r   r   r   )r2   rS   r   r   r   r   r   input_shapehidden_shapequery_statesr   r   r   r   cache_kwargsattention_interfacer   r   s                     r4   r9   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$2H2HLL	%
 	%
!\ *k));;;;FFHkk+.L((r5   )NNNN)r:   r;   r<   __doc__r    r   r'   rD   r   rW   r	   
LongTensorr   r   r9   r=   r>   s   @r4   r   r      s    G
{ 
s 
4 IM.2(,26))||)) #5<<#=>E)) t+	))
 )) ((4/)) +,)) 
u||U\\)	*))r5   r   c                   "    e Zd Zdedef fdZ	 	 	 	 	 	 ddej                  dej                  dz  dej                  dz  de	dz  d	e
dz  d
ej                  dz  deej                  ej                  f   dz  dee   dej                  fdZ xZS )ArceeDecoderLayerr(   r   c                     t         |           |j                  | _        t        ||      | _        t        |      | _        t        |j                  |j                        | _	        t        |j                  |j                        | _
        y )N)r(   r   rH   )r&   r'   r)   r   	self_attnr"   mlprA   rms_norm_epsinput_layernormpost_attention_layernormr   s      r4   r'   zArceeDecoderLayer.__init__$  sl    !--'vKF#+F,>,>FDWDWX(4V5G5GVM`M`(a%r5   NrS   r   r   r   	use_cacher   r   r   rm   c                     |}	| j                  |      } | j                  d|||||||d|\  }}
|	|z   }|}	| j                  |      }| j                  |      }|	|z   }|S )N)rS   r   r   r   r   r   r    )r   r   r   r   )r2   rS   r   r   r   r   r   r   r   residual_s              r4   r9   zArceeDecoderLayer.forward.  s     !,,];)4>> 	
')%+) 3	
 	
q !=0 !55mD/ =0r5   )NNNFNN)r:   r;   r<   r    r   r'   rD   r   r   r	   boolrW   r   r   r9   r=   r>   s   @r4   r   r   #  s    b{ bs b /304(,!&26HL|| t+ &&-	
  $; ((4/ #5<<#=>E +, 
r5   r   c                   J    e Zd ZU eed<   dZdZdgZdgZdZ	dZ
dZdZdZeedZy)ArceePreTrainedModelr(   modelTr   r   )rS   
attentionsN)r:   r;   r<   r    r   base_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_supports_sdpa_supports_flex_attn_can_compile_fullgraph_supports_attention_backendr   r   _can_record_outputsr   r5   r4   r   r   P  sQ    &*#,-#4"5N!"&*$r5   r   c                       e 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
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   layersrA   r   normr[   
rotary_embgradient_checkpointing	post_initr   s      r4   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   rm   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   )rj   )r(   input_embedsr   r   r   r   )r   )r   r   r   r   r   r   )last_hidden_stater   )
ValueErrorr   r
   r(   get_seq_lengthrD   rt   rX   rj   r   r   r  r  r  r  r   )r2   r  r   r   r   r  r   r   r   past_seen_tokensr   rS   r   decoder_layers                 r4   r9   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&++
 	
r5   )NNNNNNN)r:   r;   r<   r    r'   r   r   rD   r   r   r	   FloatTensorr   r   r   r   r9   r=   r>   s   @r4   r   r   c  s    {    .2.204(,2626!%9
##d*9
 t+9
 &&-	9

 9
 ((4/9
 ((4/9
 $;9
 +,9
 
!9
  9
r5   r   zarcee-ai/AFM-4.5B)
checkpointc                   b    e Zd ZddiZddiZddgdgfiZ fdZee	 	 	 	 	 	 	 	 	 dd	e	j                  dz  d
e	j                  dz  de	j                  dz  dedz  de	j                  dz  de	j                  dz  dedz  de	j                  dz  dee	j                  z  dee   defd              Z xZS )ArceeForCausalLMzlm_head.weightzmodel.embed_tokens.weightlm_headcolwise_gather_outputrS   logitsc                     t         |   |       t        |      | _        |j                  | _        t        j                  |j                  |j                  d      | _        | j                          y )NFr$   )
r&   r'   r   r   r   r   r+   r)   r  r  r1   s     r4   r'   zArceeForCausalLM.__init__  sU     '
 ++yy!3!3V5F5FUS 	r5   Nr  r   r   r   r  labelsr   r   logits_to_keepr   rm   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   rS   r   r   )r   r  r   r   slicer  loss_functionr(   r   r   r   rS   r   )r2   r  r   r   r   r  r  r   r   r  r   outputsrS   slice_indicesr  r  s                   r4   r9   zArceeForCausalLM.forward  s    @ ,64:: 	,
)%+')	,
 	,
  118B>SV8W~ot4]kmA}a,?@A%4%%pVFt{{OeOepiopD%#33!//))
 	
r5   )	NNNNNNNNr   )r:   r;   r<   _tied_weights_keys_tp_plan_pp_planr'   r   r   rD   r   r   r	   r  r   r   r   r   r   r9   r=   r>   s   @r4   r  r    s/   *,GH23H_-z:;H  .2.204(,26*.!%26-.8
##d*8
 t+8
 &&-	8

 8
 ((4/8
   4'8
 $;8
 ((4/8
 ell*8
 +,8
 
 8
  8
r5   r  c                       e Zd Zy)ArceeForSequenceClassificationNr:   r;   r<   r   r5   r4   r$  r$        r5   r$  c                       e Zd ZdZy)ArceeForQuestionAnsweringtransformerN)r:   r;   r<   r   r   r5   r4   r(  r(    s    %r5   r(  c                       e Zd Zy)ArceeForTokenClassificationNr%  r   r5   r4   r+  r+  	  r&  r5   r+  )r  r(  r$  r+  r   r   )r   )r   )Acollections.abcr   typingr   rD   r   transformers.utilsr   activationsr   cache_utilsr	   r
   
generationr   integrationsr   r   r   masking_utilsr   modeling_layersr   r   r   r   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   utils.genericr   r   configuration_arceer    Moduler"   rA   r[   r   r   r   r   r   rv   r   r   r   r   r   r  r$  r(  r+  __all__r   r5   r4   <module>r>     s\  * %    - ! . ) f f /  P K F & 9 ? ,<ryy < Y'J299 J (J(><299 ><B( *+ ,2	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 LL4'% % % '(%4 )*C)RYY C) +C)L*2 *Z ?  $ L
% L
 L
^ ./H
+_ H
 0H
V ./	%EG[ 	 0	 ./& ;=Q & 0& ./	"?AU 	 0	r5   