
    hR                        d dl mZmZ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 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' ddl(m)Z) ddl*m+Z+  G d dejX                        Z- ed       G d dejX                               Z. G d dejX                        Z/d Z0d>dZ1dejd                  de3d ejd                  fd!Z4	 d?d"ejX                  d#ejd                  d$ejd                  d%ejd                  d&eejd                     d'e5d(e5d)e"e$   fd*Z6 G d+ d,ejX                        Z7 G d- d.e      Z8e G d/ d0e              Z9e G d1 d2e9             Z: ed34       G d5 d6e9e             Z; ed34       G d7 d8ee9             Z< ed34       G d9 d:ee9             Z= ed34       G d; d<ee9             Z>g d=Z?y)@    )CallableOptionalUnionN)nn)auto_docstring   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_forward_from_hub)create_causal_mask)GenericForQuestionAnswering GenericForSequenceClassificationGenericForTokenClassificationGradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargscan_return_tuple)deprecate_kwarg)check_model_inputs   )ArceeConfigc                   $     e Zd Z fdZd Z xZS )ArceeMLPc                    t         |           || _        |j                  | _        |j                  | _        t        j                  | j                  | j                  |j                        | _        t        j                  | j                  | j                  |j                        | _	        t        |j                     | _        y )Nbias)super__init__confighidden_sizeintermediate_sizer   Linearmlp_biasup_proj	down_projr	   
hidden_actact_fnselfr'   	__class__s     f/var/www/html/eduruby.in/venv/lib/python3.12/site-packages/transformers/models/arcee/modeling_arcee.pyr&   zArceeMLP.__init__3   s    !--!'!9!9yy!1!143I3IPVP_P_`4#9#94;K;KRXRaRabV../    c                 `    | j                  | j                  | j                  |                  S N)r-   r/   r,   )r1   xs     r3   forwardzArceeMLP.forward<   s"    ~~dkk$,,q/:;;r4   )__name__
__module____qualname__r&   r8   __classcell__r2   s   @r3   r!   r!   2   s    0<r4   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)r1   r(   epsr2   s      r3   r&   zArceeRMSNorm.__init__B   s1     	ll5::k#:; #r4   c                 "   |j                   }|j                  t        j                        }|j	                  d      j                  dd      }|t        j                  || j                  z         z  }| j                  |j                  |      z  S )N   T)keepdim)	dtypetorC   float32powmeanrsqrtrF   rE   )r1   hidden_statesinput_dtypevariances       r3   r8   zArceeRMSNorm.forwardJ   sy    #))%((7 $$Q',,R,>%Ht?T?T4T(UU{{]--k:::r4   c                 ^    t        | j                  j                         d| j                   S )Nz, eps=)tuplerE   shaperF   )r1   s    r3   
extra_reprzArceeRMSNorm.extra_reprQ   s*    ))*+6$2G2G1HIIr4   )gư>)r9   r:   r;   r&   r8   rX   r<   r=   s   @r3   r@   r@   @   s    $;Jr4   r@   c                   ~     e Zd ZU ej                  ed<   ddef fdZ ej                         e	d               Z
 xZS )ArceeRotaryEmbeddinginv_freqr'   c                    t         |           t        |d      rUt        |j                  t
              r;|j                  j                  d|j                  j                  d            | _        nd| _        |j                  | _	        |j                  | _
        || _        t        | j                     | _        | j                  | j                  |      \  }| _        | j                  d|d       | j                   | _        y )Nrope_scaling	rope_typetypedefaultr[   F)
persistent)r%   r&   hasattr
isinstancer]   dictgetr^   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenr'   r   rope_init_fnattention_scalingregister_bufferr[   original_inv_freq)r1   r'   devicer[   r2   s       r3   r&   zArceeRotaryEmbedding.__init__X   s    6>*z&:M:Mt/T#0044[&BUBUBYBYZ`BabDN&DN"("@"@$*$B$B!/?+/+<+<T[[&+Q($(ZeD!%r4   c                 b   | 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        j                  |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   rJ   r   mpscpuF)device_typeenabledrI   dim)rL   )r[   floatexpandrW   rM   rm   rc   r_   strrC   autocast	transposecatcosrj   sinrL   )
r1   r7   position_idsinv_freq_expandedposition_ids_expandedrq   freqsembr{   r|   s
             r3   r8   zArceeRotaryEmbedding.forwardi   sV    !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.r6   )r9   r:   r;   rC   Tensor__annotations__r   r&   no_gradr   r8   r<   r=   s   @r3   rZ   rZ   U   s=    ll/{ /" U]]_<  <r4   rZ   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..NrJ   rI   rs   )rW   rC   rz   )r7   x1x2s      r3   rotate_halfr   y   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r4   c                     |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.
        position_ids (`torch.Tensor`, *optional*):
            Deprecated and unused.
        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|   r}   unsqueeze_dimq_embedk_embeds           r3   apply_rotary_pos_embr      sY    ( --
&C
--
&C3w;q>C/0G3w;q>C/0GGr4   rR   n_repreturnc                     | 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)rW   rv   reshape)rR   r   batchnum_key_value_headsslenhead_dims         r3   	repeat_kvr      so    
 2?1D1D.Ehz!!Qa"23::5BUW\^bdlmM  (;e(CT8TTr4   modulequerykeyvalueattention_maskscalingdropoutkwargsc                 T   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 )NrI   r   rJ   )rt   rL   )ptrainingr   )r   num_key_value_groupsrC   matmulry   rW   r   
functionalsoftmaxrN   rM   rL   r   r   
contiguous)r   r   r   r   r   r   r   r   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r3   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$$r4   c                   *    e Zd ZdZdedef fdZ eddd      	 	 dd	ej                  d
e
ej                  ej                  f   deej                     dee   deej                     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 )Nr   g      Tr#   )r%   r&   r'   r   getattrr(   num_attention_headsr   r   r   r   attention_dropout	is_causalr   r*   attention_biasq_projk_projv_projo_projr1   r'   r   r2   s      r3   r&   zArceeAttention.__init__   sM   "
F4F4F&JdJd4de$*$>$>&B\B\$\!}}d*!'!9!9ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii : :T]] JQWQfQf
 ii&&68J8JQWQfQf
r4   past_key_valuepast_key_values4.58new_nameversionrR   position_embeddingsr   cache_positionr   r   c                 4   |j                   d d }g |d| j                  }| j                  |      j                  |      j	                  dd      }	| j                  |      j                  |      j	                  dd      }
| j                  |      j                  |      j	                  dd      }|\  }}t        |	|
||      \  }	}
|'|||d}|j                  |
|| j                  |      \  }
}t        }| j                  j                  dk7  rt        | j                  j                     } || |	|
||f| j                  sdn| j                  | j                   d|\  }} |j"                  g |d j%                         }| j'                  |      }||fS )NrJ   r   rI   )r|   r{   r   eager        )r   r   )rW   r   r   viewry   r   r   r   updater   r   r'   _attn_implementationr   r   r   r   r   r   r   )r1   rR   r   r   r   r   r   input_shapehidden_shapequery_statesr   r   r{   r|   cache_kwargsattention_interfacer   r   s                     r3   r8   zArceeAttention.forward   s    $))#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$J(?;;++w6"9$++:Z:Z"[$7	%
  $}}C$2H2HLL	%
 	%
!\ *k));;;;FFHkk+.L((r4   )NN)r9   r:   r;   __doc__r   intr&   r   rC   r   rV   r   r
   
LongTensorr   r   r8   r<   r=   s   @r3   r   r      s    G
{ 
s 
. %0A6R ,059))||)) #5<<#=>)) !.	))
 "%)) !!1!12)) +,)) 
u||U\\)	*)) S))r4   r   c                   >    e Zd Zdedef fdZ eddd      	 	 	 	 	 	 ddej                  d	e	ej                     d
e	ej                     de	e   de	e   de	ej                     de	eej                  ej                  f      dee   dej                  fd       Z xZS )ArceeDecoderLayerr'   r   c                     t         |           |j                  | _        t        ||      | _        t        |      | _        t        |j                  |j                        | _	        t        |j                  |j                        | _
        y )N)r'   r   rG   )r%   r&   r(   r   	self_attnr!   mlpr@   rms_norm_epsinput_layernormpost_attention_layernormr   s      r3   r&   zArceeDecoderLayer.__init__	  sl    !--'vKF#+F,>,>FDWDWX(4V5G5GVM`M`(a%r4   r   r   r   r   rR   r   r}   	use_cacher   r   r   r   c                     |}	| j                  |      } | j                  d|||||||d|\  }}
|	|z   }|}	| j                  |      }| j                  |      }|	|z   }|S )N)rR   r   r}   r   r   r   r    )r   r   r   r   )r1   rR   r   r}   r   r   r   r   r   residual_s              r3   r8   zArceeDecoderLayer.forward  s     !,,];)4>> 	
')%+) 3	
 	
q !=0 !55mD/ =0r4   )NNNFNN)r9   r:   r;   r   r   r&   r   rC   r   r   r   r
   boolrV   r   r   r8   r<   r=   s   @r3   r   r     s    b{ bs b %0A6R 2637+/$)59KO|| !. u//0	
 "% D> !!1!12 &eELL%,,,F&GH +, 
 Sr4   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   )rR   
attentionsN)r9   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   r4   r3   r   r   6  sQ    &*#,-#4"5N!"&*$r4   r   c                       e Zd Zdef fdZee	 	 	 	 	 	 	 ddeej                     deej                     deej                     dee   deej                     deej                     d	ee   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   layersr@   r   normrZ   
rotary_embgradient_checkpointing	post_initr   s      r3   r&   zArceeModel.__init__K  s     !.. ++LL):):F<N<NPTP`P`ammCHIaIaCbcivy1c
 !!3!39L9LM	.f=&+# 	 ds   D	input_idsr   r}   r   inputs_embedsr   r   r   r   c           
      B   |d u |d uz  rt        d      || j                  |      }|r|t        | j                        }|F||j	                         nd}	t        j                  |	|	|j                  d   z   |j                        }||j                  d      }t        | 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   )rm   )r'   input_embedsr   r   r   r}   )r   r}   r   r   r   )last_hidden_stater   )
ValueErrorr   r   r'   get_seq_lengthrC   arangerW   rm   r   r   r   r   r   r   r   )r1   r  r   r}   r   r  r   r   r   past_seen_tokensr   rR   r   decoder_layers                 r3   r8   zArceeModel.forward[  s[    -t";<YZZ *.*;*;I*FM0*$++>O!CRC^==?de+0<< "2]5H5H5K"KTaThTh,N )33A6L(;;&))+%
 &"oom\J![[)H4;;+H+HI 		M)*) /-$7 M		 		-0&++
 	
r4   )NNNNNNN)r9   r:   r;   r   r&   r   r   r   rC   r   r   r
   FloatTensorr   r   r   r   r8   r<   r=   s   @r3   r   r   I  s    {    151537+/5959$(8
E,,-8
 !.8
 u//0	8

 "%8
   1 128
 !!1!128
 D>8
 +,8
 
!8
  8
r4   r   zarcee-ai/AFM-4.5B)
checkpointc                   d    e Zd ZdgZddiZddgdgfiZ fdZee	 	 	 	 	 	 	 	 	 dde	e
j                     de	e
j                     d	e	e
j                     d
e	e   de	e
j                     de	e
j                     de	e   de	e
j                     deee
j                  f   dee   defd              Z xZS )ArceeForCausalLMzlm_head.weightlm_headcolwise_reprR   logitsc                     t         |   |       t        |      | _        |j                  | _        t        j                  |j                  |j                  d      | _        | j                          y )NFr#   )
r%   r&   r   r   r   r   r*   r(   r  r  r0   s     r3   r&   zArceeForCausalLM.__init__  sU     '
 ++yy!3!3V5F5FUS 	r4   r  r   r}   r   r  labelsr   r   logits_to_keepr   r   c
                 z    | j                   d|||||||d|
}|j                  }t        |	t              rt	        |	 d      n|	}| j                  |dd|ddf         }d}|* | j                  d||| j                  j                  d|
}t        |||j                  |j                  |j                        S )a  
        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   rR   r   r   )r   r  rc   r   slicer  loss_functionr'   r   r   r   rR   r   )r1   r  r   r}   r   r  r  r   r   r  r   outputsrR   slice_indicesr  r  s                   r3   r8   zArceeForCausalLM.forward  s    @ ,64:: 	,
)%+')	,
 	,
  118B>SV8W~ot4]kmA}a,?@A%4%%pVFt{{OeOepiopD%#33!//))
 	
r4   )	NNNNNNNNr   )r9   r:   r;   _tied_weights_keys_tp_plan_pp_planr&   r   r   r   rC   r   r   r
   r  r   r   r   r   r   r   r8   r<   r=   s   @r3   r  r    s0   *+=)H_-z:;H  151537+/59-1$(59348
E,,-8
 !.8
 u//0	8

 "%8
   1 128
 ))*8
 D>8
 !!1!128
 c5<</08
 +,8
 
 8
  8
r4   r  c                       e Zd Zy)ArceeForSequenceClassificationNr9   r:   r;   r   r4   r3   r!  r!        r4   r!  c                       e Zd ZdZy)ArceeForQuestionAnsweringtransformerN)r9   r:   r;   r   r   r4   r3   r%  r%    s    %r4   r%  c                       e Zd Zy)ArceeForTokenClassificationNr"  r   r4   r3   r(  r(    r#  r4   r(  )r  r%  r!  r(  r   r   )Nr   )r   )@typingr   r   r   rC   r   transformers.utilsr   activationsr	   cache_utilsr
   r   
generationr   integrationsr   masking_utilsr   modeling_layersr   r   r   r   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   utils.deprecationr   utils.genericr   configuration_arceer   Moduler!   r@   rZ   r   r   r   r   r   ru   r   r   r   r   r   r  r!  r%  r(  __all__r   r4   r3   <module>r;     s1  , - ,   - ! . ) 7 /  P K F & 9 0 / ,<ryy < Y'J299 J (J(!<299 !<H(6	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 U\\*% % % '(%4D)RYY D)N+2 +\ ?  $ K
% K
 K
\ ./H
+_ H
 0H
V ./	%EG[ 	 0	 ./& ;=Q & 0& ./	"?AU 	 0	r4   