
    h\                     h   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$m%Z%m&Z&m'Z' ddl(m)Z) ddl*m+Z+  ed       G d dejX                               Z- G d dejX                        Z.d Z/d;dZ0dejb                  de2dejb                  fdZ3	 d<dejX                  d ejb                  d!ejb                  d"ejb                  d#eejb                     d$e4d%e4d&e#e%   fd'Z5 G d( d)ejX                        Z6 G d* d+ejX                        Z7 G d, d-e      Z8e& G d. d/e!             Z9e& G d0 d1e9             Z:e& G d2 d3e9e             Z; G d4 d5ee9      Z< G d6 d7ee9      Z= G d8 d9ee9      Z>g d: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)deprecate_kwarg   )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      j/var/www/html/eduruby.in/venv/lib/python3.12/site-packages/transformers/models/exaone4/modeling_exaone4.pyr&   zExaone4RMSNorm.__init__4   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       r0   forwardzExaone4RMSNorm.forward<   sy    #))%((7 $$Q',,R,>%Ht?T?T4T(UU{{]--k:::r1   c                 ^    t        | j                  j                         d| j                   S )Nz, eps=)tupler*   shaper+   )r,   s    r0   
extra_reprzExaone4RMSNorm.extra_reprC   s*    ))*+6$2G2G1HIIr1   )gư>)__name__
__module____qualname__r&   r?   rC   __classcell__r/   s   @r0   r#   r#   2   s    $;Jr1   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 )Exaone4RotaryEmbeddinginv_freq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defaultrK   F)
persistent)r%   r&   hasattr
isinstancerN   dictgetrO   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrL   r   rope_init_fnattention_scalingregister_bufferrK   original_inv_freq)r,   rL   devicerK   r/   s       r0   r&   zExaone4RotaryEmbedding.__init__J   s    6>*z&:M:Mt/T#0044[&BUBUBYBYZ`BabDN&DN"("@"@$*$B$B!/?+/+<+<T[[&+Q($(ZeD!%r1   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   r4   r   mpscpuF)device_typeenabledr3   dim)r6   )rK   floatexpandrB   r7   r^   rT   rP   strr(   autocast	transposecatcosr[   sinr6   )
r,   xposition_idsinv_freq_expandedposition_ids_expandedrb   freqsembrl   rm   s
             r0   r?   zExaone4RotaryEmbedding.forward[   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(   Tensor__annotations__r    r&   no_gradr   r?   rG   rH   s   @r0   rJ   rJ   G   s=    ll/} /" U]]_<  <r1   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..Nr4   r3   rd   )rB   r(   rk   )rn   x1x2s      r0   rotate_halfr{   k   sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r1   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krl   rm   ro   unsqueeze_dimq_embedk_embeds           r0   apply_rotary_pos_embr   r   sY    ( --
&C
--
&C3w;q>C/0G3w;q>C/0GGr1   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)rB   rg   reshape)r<   r   batchnum_key_value_headsslenhead_dims         r0   	repeat_kvr      so    
 2?1D1D.Ehz!!Qa"23::5BUW\^bdlmM  (;e(CT8TTr1   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 )Nr3   r   r4   )re   r6   )ptrainingr   )r   num_key_value_groupsr(   matmulrj   rB   r   
functionalsoftmaxr8   r7   r6   r   r   
contiguous)r   r   r   r   r   r   r   r   
key_statesvalue_statesattn_weightscausal_maskattn_outputs                r0   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$$r1   c                   P    e 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
ej                     e
e	ej                        f   fd       Z xZS )Exaone4AttentionrL   	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&   rL   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,   rL   r   r/   s      r0   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r1   past_key_valuepast_key_values4.58new_nameversionr<   position_embeddingsr   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$                  sdn| j&                  | j(                  | j                  r| j                  nd d|\  }} |j*                  g |d j-                         }| j/                  |      }||fS )Nr4   r   r3   r   eager        )r   r   r   )rB   r   r   viewrj   r   r   r   r   r   r   r   updater   r   rL   _attn_implementationr   r   r   r   r   r   r   )r,   r<   r   r   r   r   r   input_shapehidden_shapequery_statesr   r   rl   rm   cache_kwargsattention_interfacer   r   s                     r0   r?   zExaone4Attention.forward   s    $))#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 (7'='=j,X\XfXfht'u$J(?;;++w6"9$++:Z:Z"[$7
%
  $}}C$2H2HLL26//4..t
%
 
%
!\ *k));;;;FFHkk+.L((r1   )NNN)rD   rE   rF   r    intr&   r   r(   ru   rA   r   r
   
LongTensorr   r   r?   rG   rH   s   @r0   r   r      s    M} M M0 %0A6R
 26+/591)||1) #5<<#=>1) !.	1)
 "%1) !!1!121) +,1) 
u||Xell3XeELL>Q5RR	S1) S1)r1   r   c                   $     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&   rL   r-   intermediate_sizer   r   	gate_projup_proj	down_projr	   
hidden_actact_fnr,   rL   r/   s     r0   r&   zExaone4MLP.__init__  s    !--!'!9!94#3#3T5K5KRWXyy!1!143I3IPUV4#9#94;K;KRWXV../r1   c                     | j                  | j                  | j                  |            | j                  |      z        }|S rt   )r   r   r   r   )r,   rn   r   s      r0   r?   zExaone4MLP.forward  s6    NN4;;t~~a/@#ADLLQRO#ST	r1   )rD   rE   rF   r&   r?   rG   rH   s   @r0   r   r     s    0r1   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 )Exaone4DecoderLayerrL   r   c                     t         |           |j                  | _        t        ||      | _        t        |      | _        t        |j                  |j                        | _	        t        |j                  |j                        | _
        y )N)rL   r   r   )r%   r&   r-   r   	self_attnr   mlpr#   r   post_attention_layernormpost_feedforward_layernormr   s      r0   r&   zExaone4DecoderLayer.__init__  sm    !--)9Mf%(6v7I7IvObOb(c%*89K9KQWQdQd*e'r1   r   r   r   r   r<   r   ro   	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              r0   r?   zExaone4DecoderLayer.forward  s     !)4>> 	
')%+) 3	
 	
q 55mD =0 !/77F =0r1   )NNNFNN)rD   rE   rF   r    r   r&   r   r(   ru   r   r   r
   boolrA   r   r   r?   rG   rH   s   @r0   r   r     s    f} f f %0A6R 2637+/$)59KO|| !. u//0	
 "% D> !!1!12 &eELL%,,,F&GH +, 
 Sr1   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)Exaone4PreTrainedModelrL   modelTr   r   )r<   
attentionsN)rD   rE   rF   r    rv   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   r1   r0   r   r   =  sX    &*#./#4"5N!"&,& !Lr1   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 )Exaone4ModelrL   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   rL   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      r0   r&   zExaone4Model.__init__S  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        | j                        }|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   )r^   )rL   input_embedsr   r   r   ro   full_attentionr   )r   r   ro   r   r   r   )last_hidden_stater   r   )
ValueErrorr  r   rL   get_seq_lengthr(   arangerB   r^   r}   rT   rU   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                    r0   r?   zExaone4Model.forwardc  s    -t";<YZZ  --i8M0*$++>O!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)	$72:>) /#-	 	M	 		-0&+/8O
 	
>B
 	
r1   )NNNNNNN)rD   rE   rF   r    r&   r   r(   r   r   ru   r
   FloatTensorr   r   r   r   rA   r   r?   rG   rH   s   @r0   r   r   Q  s    }    '+1537+/59$(59E
##E
 !.E
 u//0	E

 "%E
   1 12E
 D>E
 !!1!12E
 +,E
 
u--	.E
 E
r1   r   c                   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 )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     r0   r&   zExaone4ForCausalLM.__init__  sU     !&)
 ++yy!3!3V5F5FUS 	r1   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_functionrL   r   r   r   r<   r   )r,   r  r   ro   r   r  r"  r   r   r#  r   outputsr<   slice_indicesr   r%  s                   r0   r?   zExaone4ForCausalLM.forward  s    ^ ,64:: 	,
)%+')	,
 	,
  118B>SV8W~ot4]kmA}a,?@A%4%%pVFt{{OeOepiopD%#33!//))
 	
r1   )	NNNNNNNNr   )rD   rE   rF   _tied_weights_keys_tp_plan_pp_planr&   r   r   r   r(   r   ru   r
   r  r   r   r   r   r   r   r?   rG   rH   s   @r0   r  r    s=   *+=)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
r1   r  c                       e Zd Zy) Exaone4ForSequenceClassificationNrD   rE   rF   r   r1   r0   r.  r.        r1   r.  c                       e Zd Zy)Exaone4ForTokenClassificationNr/  r   r1   r0   r2  r2    r0  r1   r2  c                       e Zd ZdZy)Exaone4ForQuestionAnsweringtransformerN)rD   rE   rF   r   r   r1   r0   r4  r4    s    %r1   r4  )r   r   r  r.  r2  r4  )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   utils.deprecationr   configuration_exaone4r    Moduler#   rJ   r{   r   ru   r   r   rf   r   r   r   r   r   r   r  r.  r2  r4  __all__r   r1   r0   <module>rG     s  . - ,   9 ! . ) 7 R  P K F & I I 0 0 Y'JRYY J (J(!<RYY !<H(6	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 U\\*% % % '(%4K)ryy K)\  )4 )X !_ ! !& W
) W
 W
t W
/ W
 W
t	'GI_ 		$ACY 	&"=?U &r1   