
    rh}\                     \   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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$m%Z%m&Z&m'Z' ddl(m)Z)  ed       G d dejT                               Z+ G d dejT                        Z,d Z-d:dZ.dej^                  de0dej^                  fdZ1	 d;dejT                  dej^                  d ej^                  d!ej^                  d"eej^                     d#e2d$e2d%e#e%   fd&Z3 G d' d(ejT                        Z4 G d) d*ejT                        Z5 G d+ d,e      Z6e& G d- d.e!             Z7e& G d/ d0e7             Z8e& G d1 d2e7e             Z9 G d3 d4ee7      Z: G d5 d6ee7      Z; G d7 d8ee7      Z<g d9Z=y)<    )CallableOptionalUnionN)nn)check_model_inputs   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_forward_from_hub)create_causal_mask!create_sliding_window_causal_mask)GenericForQuestionAnswering GenericForSequenceClassificationGenericForTokenClassificationGradientCheckpointingLayer)BaseModelOutputWithPastCausalLMOutputWithPast)ROPE_INIT_FUNCTIONSdynamic_rope_update)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringcan_return_tuple   )Exaone4ConfigRMSNormc                   ,     e Zd Zd fd	Zd Zd Z xZS )Exaone4RMSNormc                     t         |           t        j                  t	        j
                  |            | _        || _        y)z=
        Exaone4RMSNorm is equivalent to T5LayerNorm
        N)super__init__r   	Parametertorchonesweightvariance_epsilon)selfhidden_sizeeps	__class__s      /var/www/html/ai-insurance-compliance-backend/venv/lib/python3.12/site-packages/transformers/models/exaone4/modeling_exaone4.pyr%   zExaone4RMSNorm.__init__3   s1     	ll5::k#:; #    c                 "   |j                   }|j                  t        j                        }|j	                  d      j                  dd      }|t        j                  || j                  z         z  }| j                  |j                  |      z  S )N   T)keepdim)	dtypetor'   float32powmeanrsqrtr*   r)   )r+   hidden_statesinput_dtypevariances       r/   forwardzExaone4RMSNorm.forward;   sy    #))%((7 $$Q',,R,>%Ht?T?T4T(UU{{]--k:::r0   c                 ^    t        | j                  j                         d| j                   S )Nz, eps=)tupler)   shaper*   r+   s    r/   
extra_reprzExaone4RMSNorm.extra_reprB   s*    ))*+6$2G2G1HIIr0   )gư>)__name__
__module____qualname__r%   r>   rC   __classcell__r.   s   @r/   r"   r"   1   s    $;Jr0   r"   c                   ^     e Zd Zddef fdZ ej                         ed               Z xZ	S )Exaone4RotaryEmbeddingconfigc                    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defaultinv_freqF)
persistent)r$   r%   hasattr
isinstancerM   dictgetrN   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrK   r   rope_init_fnattention_scalingregister_bufferrQ   original_inv_freq)r+   rK   devicerQ   r.   s       r/   r%   zExaone4RotaryEmbedding.__init__G   s    6>*z&:M:Mt/T#0044[&BUBUBYBYZ`BabDN&DN"("@"@$*$B$B!/?+/+<+<T[[&+Q($(ZeD!%r0   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   r3   r   mpscpuF)device_typeenabledr2   dim)r5   )rQ   floatexpandrA   r6   r^   rT   rO   strr'   autocast	transposecatcosr[   sinr5   )
r+   xposition_idsinv_freq_expandedposition_ids_expandedrb   freqsembrl   rm   s
             r/   r>   zExaone4RotaryEmbedding.forwardX   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.N)
rD   rE   rF   r   r%   r'   no_gradr   r>   rG   rH   s   @r/   rJ   rJ   F   s3    /} /" U]]_<  <r0   rJ   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..Nr3   r2   rd   )rA   r'   rk   )rn   x1x2s      r/   rotate_halfry   h   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r0   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.
    )	unsqueezery   )qkrl   rm   ro   unsqueeze_dimq_embedk_embeds           r/   apply_rotary_pos_embr   o   sY    ( --
&C
--
&C3w;q>C/0G3w;q>C/0GGr0   r;   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)rA   rg   reshape)r;   r   batchnum_key_value_headsslenhead_dims         r/   	repeat_kvr      so    
 2?1D1D.Ehz!!Qa"23::5BUW\^bdlmM  (;e(CT8TTr0   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 )Nr2   r   r3   )re   r5   )ptrainingr   )r   num_key_value_groupsr'   matmulrj   rA   r   
functionalsoftmaxr7   r6   r5   r   r   
contiguous)r   r   r   r   r   r   r   r   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r/   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$$r0   c                   4    e Zd Zdedef fdZ	 	 	 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	ej                     e	eej                        f   fdZ xZS )Exaone4AttentionrK   	layer_idxc                    t         |           || _        || _        |j                  | _        |j
                  | _        |j                  | _        t        |d|j                  |j                  z        | _        |j                  |j
                  z  | _	        |j                  | _
        d| _        | j                  dz  | _        |j                  | _        |j                  | _        |j                  |   dk(  | _        t#        j$                  | j                  | j                  | j                  z  d      | _        t#        j$                  | j                  | j
                  | j                  z  d      | _        t#        j$                  | j                  | j
                  | j                  z  d      | _        t#        j$                  | j                  | j                  z  | j                  d      | _        t/        | j                  |j0                        | _        t/        | j                  |j0                        | _        y )Nr   Tg      sliding_attentionFbiasr-   )r$   r%   rK   r   num_attention_headsr   r,   getattrr   r   attention_dropout	is_causalr   sliding_windowsliding_window_patternlayer_types
is_slidingr   Linearq_projk_projv_projo_projr"   rms_norm_epsq_normk_normr+   rK   r   r.   s      r/   r%   zExaone4Attention.__init__   s   "#)#=#= #)#=#= !--
F4F4F&JdJd4de$*$>$>&B\B\$\!!'!9!9}}d*$33&,&C&C# ,,Y7;NNii 0 0$2J2JT]]2Zafgii 0 0$2J2JT]]2Zafgii 0 0$2J2JT]]2Zafgii 8 84== H$JZJZafg$T]]8K8KL$T]]8K8KLr0   r;   position_embeddingsr   past_key_valuecache_positionr   r   c                    |j                   d d }g |d| j                  }| j                  |      j                  |      j	                  dd      }	| j                  |      j                  |      j	                  dd      }
| j                  |      j                  |      j	                  dd      }| j                  |	      }	| j                  |
      }
|\  }}| j                  | j                  rt        |	|
||      \  }	}
|%d|i}|j                  |
|| j                  |      \  }
}t        }| j                  j                   dk7  rt"        | j                  j                      } || |	|
||f| j$                  sdn| j&                  | j(                  | j                  r| j                  nd d|\  }} |j*                  g |d j-                         }| j/                  |      }||fS )Nr3   r   r2   r   eager        )r   r   r   )rA   r   r   viewrj   r   r   r   r   r   r   r   updater   r   rK   _attn_implementationr   r   r   r   r   r   r   )r+   r;   r   r   r   r   r   input_shapehidden_shapequery_statesr   r   rl   rm   cache_kwargsattention_interfacer   r   s                     r/   r>   zExaone4Attention.forward   s    $))#2.88b8$--8{{=166|DNNqRST[[/44\BLLQPQR
{{=166|DNNqRST {{<0[[,
&S&$//';L*VY[^'_$L*% .L (6'<'<ZW[WeWegs't$J(?;;++w6"9$++:Z:Z"[$7
%
  $}}C$2H2HLL26//4..t
%
 
%
!\ *k));;;;FFHkk+.L((r0   )NNN)rD   rE   rF   r   intr%   r'   Tensorr@   r   r
   
LongTensorr   r   r>   rG   rH   s   @r/   r   r      s    M} M M8 26*.591)||1) #5<<#=>1) !.	1)
 !1) !!1!121) +,1) 
u||Xell3XeELL>Q5RR	S1)r0   r   c                   $     e Zd Z fdZd Z xZS )
Exaone4MLPc                    t         |           || _        |j                  | _        |j                  | _        t        j                  | j                  | j                  d      | _        t        j                  | j                  | j                  d      | _        t        j                  | j                  | j                  d      | _	        t        |j                     | _        y NFr   )r$   r%   rK   r,   intermediate_sizer   r   	gate_projup_proj	down_projr	   
hidden_actact_fnr+   rK   r.   s     r/   r%   zExaone4MLP.__init__   s    !--!'!9!94#3#3T5K5KRWXyy!1!143I3IPUV4#9#94;K;KRWXV../r0   c                     | j                  | j                  | j                  |            | j                  |      z        }|S rt   )r   r   r   r   )r+   rn   r   s      r/   r>   zExaone4MLP.forward  s6    NN4;;t~~a/@#ADLLQRO#ST	r0   )rD   rE   rF   r%   r>   rG   rH   s   @r/   r   r      s    0r0   r   c                   d    e Zd Zdedef fdZ	 	 	 	 	 	 ddej                  deej                     deej                     dee
   dee   d	eej                     d
eeej                  ej                  f      dee   deej                  eeej                  ej                  f      f   fdZ xZS )Exaone4DecoderLayerrK   r   c                     t         |           |j                  | _        t        ||      | _        t        |      | _        t        |j                  |j                        | _	        t        |j                  |j                        | _
        y )N)rK   r   r   )r$   r%   r,   r   	self_attnr   mlpr"   r   post_attention_layernormpost_feedforward_layernormr   s      r/   r%   zExaone4DecoderLayer.__init__  sm    !--)9Mf%(6v7I7IvObOb(c%*89K9KQWQdQd*e'r0   r;   r   ro   r   	use_cacher   r   r   r   c                     |}	 | j                   d|||||||d|\  }}
| j                  |      }|	|z   }|}	| j                  |      }| j                  |      }|	|z   }|S )N)r;   r   ro   r   r   r   r    )r   r   r   r   )r+   r;   r   ro   r   r   r   r   r   residual_s              r/   r>   zExaone4DecoderLayer.forward  s     !)4>> 	
')%)) 3	
 	
q 55mD =0 !/77F =0r0   )NNNFNN)rD   rE   rF   r   r   r%   r'   r   r   r   r
   boolr@   r   r   FloatTensorr>   rG   rH   s   @r/   r   r     s    f} f f 2637*.$)59KO|| !. u//0	
 ! D> !!1!12 &eELL%,,,F&GH +, 
u  (51B1BEDUDU1U+V"WW	Xr0   r   c                   N    e Zd ZU eed<   dZdZdgZdgZdZ	dZ
dZdZdZeedZeZy)Exaone4PreTrainedModelrK   modelTr   past_key_values)r;   
attentionsN)rD   rE   rF   r   __annotations__base_model_prefixsupports_gradient_checkpointing_no_split_modules_skip_keys_device_placement_supports_flash_attn_supports_sdpa_supports_flex_attn_can_compile_fullgraph_supports_attention_backendr   r   _can_record_outputsconfig_classr   r0   r/   r   r   8  sX    &*#./#4"5N!"&,& !Lr0   r   c                       e Zd Zdef fdZe	 	 	 	 	 	 	 ddej                  deej                     deej                     dee
   deej                     dee   d	eej                     d
ee   deeef   fd       Z xZS )Exaone4ModelrK   c           	         t         |   |       |j                  | _        |j                  | _        t        j                  |j                  |j                  | j                        | _        t        j                  t        |j                        D cg c]  }t        ||       c}      | _        t        |j                  |j                        | _        t#        |      | _        d| _        | j)                          y c c}w )Nr   )rK   F)r$   r%   pad_token_idpadding_idx
vocab_sizer   	Embeddingr,   embed_tokens
ModuleListrangenum_hidden_layersr   layersr"   r   normrJ   
rotary_embgradient_checkpointing	post_initr   s      r/   r%   zExaone4Model.__init__N  s     !.. ++LL):):F<N<NPTP`P`ammEJ6KcKcEde	 3e
 #6#5#56;N;NO	0?&+# 	 fs   D	input_idsr   ro   r   inputs_embedsr   r   r   r   c                    |d u |d uz  rt        d      || j                  |      }|r|
t               }|F||j                         nd}	t	        j
                  |	|	|j                  d   z   |j                        }||j                  d      }t        |x}
t              sF| j                  |||||d}dt        d
i |i}
d| j                  j                  v rt        d
i ||
d<   |}| j                  ||      }t!        | j"                        D ]1  \  }}| j                  j                  |   } ||f||
|   ||||d|}3 | j%                  |      }t'        ||r|	      S d 	      S )Nz:You must specify exactly one of input_ids or inputs_embedsr   r   )r^   )rK   input_embedsr   r   r   ro   full_attentionr   )r   r   ro   r   r   r   )last_hidden_stater   r   )
ValueErrorr   r   get_seq_lengthr'   arangerA   r^   r{   rT   rU   rK   r   r   r   r  	enumerater  r  r   )r+   r  r   ro   r   r  r   r   r   past_seen_tokenscausal_mask_mappingmask_kwargsr;   r   idecoder_layer
layer_types                    r/   r>   zExaone4Model.forward^  s    -t";<YZZ  --i8M0*nO!CRC^==?de"\\ "2]5H5H5K"KTaThThN )33A6L ?-F ++ -"0"0#2 ,K !"4"C{"C# #dkk&=&==;\;k_j;k#$78%"oom\J )$++ 6 	A}003J)	$72:>).#-	 	M	 		-0&+/8O
 	
>B
 	
r0   )NNNNNNN)rD   rE   rF   r   r%   r   r'   r   r   r   r
   r   r   r   r   r   r@   r   r>   rG   rH   s   @r/   r   r   L  s    }    '+1537+/59$(59E
##E
 !.E
 u//0	E

 "%E
   1 12E
 D>E
 !!1!12E
 +,E
 
u--	.E
 E
r0   r   c                   p    e Zd ZdgZddiZddgdgfiZ fdZd Z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 )Exaone4ForCausalLMzlm_head.weightlm_headcolwise_repr;   logitsc                     t         |   |       t        |      | _        |j                  | _        t        j                  |j                  |j                  d      | _        | j                          y r   )
r$   r%   r   r   r   r   r   r,   r  r  r   s     r/   r%   zExaone4ForCausalLM.__init__  sU     !&)
 ++yy!3!3V5F5FUS 	r0   c                     || _         y rt   r   )r+   decoders     r/   set_decoderzExaone4ForCausalLM.set_decoder  s	    
r0   c                     | j                   S rt   r  rB   s    r/   get_decoderzExaone4ForCausalLM.get_decoder  s    zzr0   r  r   ro   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 )u  
        labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
            Labels for computing the masked language modeling loss. Indices should either be in `[0, ...,
            config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored
            (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`.

        Example:

        ```python
        >>> from transformers import AutoModelForCausalLM, AutoTokenizer
        >>> model = AutoModelForCausalLM.from_pretrained("LGAI-EXAONE/EXAONE-4.0-Instruct")
        >>> tokenizer = AutoTokenizer.from_pretrained("LGAI-EXAONE/EXAONE-4.0-Instruct")

        >>> prompt = "Explain how wonderful you are"
        >>> messages = [
            {"role": "system", "content": "You are a helpful assistant."},
            {"role": "user", "content": prompt}
        ]
        >>> input_ids = tokenizer.apply_chat_template(
            messages,
            tokenize=True,
            add_generation_prompt=True,
            return_tensors="pt",
            enable_thinking=False,
        )

        >>> output = model.generate(input_ids, max_new_tokens=128)
        >>> tokenizer.decode(output[0], skip_special_tokens=False)
        "[|system|]\nYou are a helpful assistant.[|endofturn|]\n[|user|]\nExplain how wonderful you are[|endofturn|]\n[|assistant|]\n<think>\n\n</think>\n\nOh, thank you for such a kind and lovely question! 😊  \n\nI’m *so* wonderful because I’m here to make your life easier, brighter, and more fun! Whether you need help with:  \n\n✨ **Learning** – I can explain anything, from quantum physics to baking the perfect cake!  \n💡 **Creativity** – Need a poem, story, or a wild idea? I’ve got you covered!  \n🤖 **Problem-solving** – Stuck on a math problem or a tricky decision? I’ll help you figure it out"
        ```

        NOTE: `EXAONE-4.0-Instruct` is a placeholder model ID. The exact model ID will be updated in the future.)r  r   ro   r   r  r   r   N)r  r#  r   )lossr  r   r;   r   r   )r   r  rT   r   slicer  loss_functionrK   r   r   r   r;   r   )r+   r  r   ro   r   r  r#  r   r   r$  r   outputsr;   slice_indicesr  r&  s                   r/   r>   zExaone4ForCausalLM.forward  s    ^ ,64:: 	,
)%+')	,
 	,
  118B>SV8W~ot4]kmA}a,?@A%4%%pVFt{{OeOepiopD%#33!//))
 	
r0   )	NNNNNNNNr   )rD   rE   rF   _tied_weights_keys_tp_plan_pp_planr%   r   r"  r   r   r   r'   r   r   r
   r   r   r   r   r   r   r   r>   rG   rH   s   @r/   r  r    sG   *+=)H_-z:;H  151537+/59-1$(5934G
E,,-G
 !.G
 u//0	G

 "%G
   1 12G
 ))*G
 D>G
 !!1!12G
 c5<</0G
 +,G
 
 G
  G
r0   r  c                       e Zd Zy) Exaone4ForSequenceClassificationNrD   rE   rF   r   r0   r/   r/  r/        r0   r/  c                       e Zd Zy)Exaone4ForTokenClassificationNr0  r   r0   r/   r3  r3    r1  r0   r3  c                       e Zd ZdZy)Exaone4ForQuestionAnsweringtransformerN)rD   rE   rF   r   r   r0   r/   r5  r5    s    %r0   r5  )r   r   r  r/  r3  r5  )Nr   )r   )>typingr   r   r   r'   r   transformers.utils.genericr   activationsr	   cache_utilsr
   r   
generationr   integrationsr   masking_utilsr   r   modeling_layersr   r   r   r   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   configuration_exaone4r   Moduler"   rJ   ry   r   r   r   r   rf   r   r   r   r   r   r   r  r/  r3  r5  __all__r   r0   r/   <module>rG     s  . - ,   9 ! . ) 7 R  P K F & I I 0 Y'JRYY J (J(<RYY <D(6	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 U\\*% % % '(%4J)ryy J)Z  (4 (V !_ ! !& W
) W
 W
t ]
/ ]
 ]
@	'GI_ 		$ACY 	&"=?U &r0   