
    i`                        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 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jZ                               Z. G d dejZ                        Z/d Z0 ed      d=d       Z1dejd                  de3dejd                  fd Z4	 d>d!ejZ                  d"ejd                  d#ejd                  d$ejd                  d%ejd                  dz  d&e5d'e5d(e$e&   fd)Z6 G d* d+ejZ                        Z7 G d, d-ejZ                        Z8 G d. d/e      Z9e' G d0 d1e"             Z:e' G d2 d3e:             Z;e' G d4 d5e:e             Z< G d6 d7ee:      Z= G d8 d9ee:      Z> G d: d;ee:      Z?g d<Z@y)?    )Callable)OptionalN)nn)check_model_inputs   )ACT2FN)CacheDynamicCache)GenerationMixin)use_kernel_forward_from_hubuse_kernel_func_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)maybe_autocast   )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      v/home/obispo/Crisostomo_bridge/mision_env/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	 	 	 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 )Exaone4RotaryEmbeddinginv_freqNconfigc                    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defaultrK   F)
persistentoriginal_inv_freq)r%   r&   max_position_embeddingsmax_seq_len_cachedoriginal_max_seq_lenrL   rope_parametersrN   compute_default_rope_parametersr   attention_scalingregister_bufferclone)r,   rL   devicerope_init_fnrK   r/   s        r0   r&   zExaone4RotaryEmbedding.__init__J   s    "("@"@$*$B$B!44[A!%!E!E>>Y&.t~~>L+7V+L($(ZeD0(..2BuUr1   rZ   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   r3   r6   )rZ   r6   )	rU   getattrr-   num_attention_headsr(   arangeint64r7   float)rL   rZ   r\   basedimattention_factorrK   s          r0   rV   z6Exaone4RotaryEmbedding.compute_default_rope_parametersZ   s    & %%l3fj$/c63E3EIcIc3c U\\!S!5;;?BB&X]XcXcBdgjjk
 )))r1   c                 N   | j                   d d d d f   j                         j                  |j                  d   dd      j	                  |j
                        }|d d d d d f   j                         }t        |j
                  j                  t              r/|j
                  j                  dk7  r|j
                  j                  nd}t        |d      5  |j                         |j                         z  j                  dd      }t        j                  ||fd	      }|j                         | j                  z  }|j                         | j                  z  }	d d d        j	                  |j                   
      	j	                  |j                   
      fS # 1 sw Y   AxY w)Nr   r4   r   mpscpuF)device_typeenabledr3   rh   ra   )rK   rf   expandrB   r7   rZ   
isinstancetypestrr   	transposer(   catcosrW   sinr6   )
r,   xposition_idsinv_freq_expandedposition_ids_expandedrm   freqsembrv   rw   s
             r0   r?   zExaone4RotaryEmbedding.forwardx   sR    !MM$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$cff177f&;;;	5 	5s   BFF$NNNN)rD   rE   rF   r(   Tensor__annotations__r    r&   staticmethodr   intrA   rf   rV   no_gradr   r?   rG   rH   s   @r0   rJ   rJ   G   s    llV} V  '++/"*$*(* t* 
~u$	%	* *: 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   ro   )rB   r(   ru   )rx   x1x2s      r0   rotate_halfr      sZ    	
3"!''"+"""	#B	
3q ""	#B99rc2YB''r1   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krv   rw   unsqueeze_dimq_embedk_embeds          r0   apply_rotary_pos_embr      sY    & --
&C
--
&C3w;q>C/0G3w;q>C/0GGr1   r<   n_repr]   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)rB   rp   reshape)r<   r   batchnum_key_value_headsslenr`   s         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   )rh   r6   )ptrainingr   )r   num_key_value_groupsr(   matmulrt   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                   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j                  dz  de	dz  d	ej                  dz  d
ee   deej                  ej                  dz  eej                     dz  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                  | _        t        |d      r|j                   |   nd }|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      | _        t1        | j                  |j2                        | _        t1        | j                  |j2                        | _        y )	Nr`   Tg      layer_typessliding_attentionFbiasr.   )r%   r&   rL   r   rc   r   r-   rb   r`   r   attention_dropout	is_causalr   sliding_windowsliding_window_patternhasattrr   
is_slidingr   Linearq_projk_projv_projo_projr#   rms_norm_epsq_normk_norm)r,   rL   r   
layer_typer/   s       r0   r&   zExaone4Attention.__init__   s   "#)#=#= #)#=#= !--
F4F4F&JdJd4de$*$>$>&B\B\$\!!'!9!9}}d*$33&,&C&C#6=fm6TV''	2Z^
$(;;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   Nr<   position_embeddingsr   past_key_values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                   j"                  t$              } || |	|
||f| j&                  sdn| j(                  | j*                  | j                  r| j                  nd d|\  }} |j,                  g |d j/                         }| j1                  |      }||fS )Nr4   r   r3   r           )r   r   r   )rB   r`   r   viewrt   r   r   r   r   r   r   r   updater   r   get_interfacerL   _attn_implementationr   r   r   r   r   r   r   )r,   r<   r   r   r   r   r   input_shapehidden_shapequery_statesr   r   rv   rw   cache_kwargsattention_interfacer   r   s                     r0   r?   zExaone4Attention.forward   s    $))#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(?(M(MKK,,.E)
 %8
%
  $}}C$2H2HLL26//4..t
%
 
%
!\ *k));;;;FFHkk+.L((r1   r   )rD   rE   rF   r    r   r&   r(   r   rA   r	   
LongTensorr   r   r?   rG   rH   s   @r0   r   r      s    M} M M: /3(,261)||1) #5<<#=>1) t+	1)
 1) ((4/1) +,1) 
u||U\\D0%2E2LL	M1)r1   r   c                   $     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 r~   )r   r   r   r   )r,   rx   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	 	 	 	 	 	 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 )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_layernormr,   rL   r   r/   s      r0   r&   zExaone4DecoderLayer.__init__.  sm    !--)9Mf%(6v7I7IvObOb(c%*89K9KQWQdQd*e'r1   Nr<   r   ry   r   	use_cacher   r   r   r]   c                     |}	 | j                   d|||||||d|\  }}
| j                  |      }|	|z   }|}	| j                  |      }| j                  |      }|	|z   }|S )N)r<   r   ry   r   r   r   r    )r   r   r   r   )r,   r<   r   ry   r   r   r   r   r   residual_s              r0   r?   zExaone4DecoderLayer.forward7  s     !)4>> 	
')%+) 3	
 	
q 55mD =0 !/77F =0r1   )NNNFNN)rD   rE   rF   r    r   r&   r(   r   r   r	   boolrA   r   r   r?   rG   rH   s   @r0   r   r   -  s    f} f f /304(,!&26HL|| t+ &&-	
  $; ((4/ #5<<#=>E +, 
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    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_outputsconfig_classr   r1   r0   r   r   X  sX    &*#./#4"5N!"&,& !Lr1   r   c                       e Zd Zdef fdZ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dz  d
ej                  dz  dee   deez  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__n  s     !.. ++LL):):F<N<NPTP`P`ammEJ6KcKcEde	 3e
 #6#5#56;N;NO	0?&+# 	 fs   DN	input_idsr   ry   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   )rZ   )rL   input_embedsr   r   r   ry   full_attentionr   )r   ry   r   r   r   r   )last_hidden_stater   r   )
ValueErrorr  r
   rL   get_seq_lengthr(   rd   rB   rZ   r   rq   dictr   r   r   r  	enumerater  r  r   )r,   r  r   ry   r   r  r   r   r   past_seen_tokenscausal_mask_mappingmask_kwargsr<   r   idecoder_layerr   s                    r0   r?   zExaone4Model.forward~  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)	2:>) /#-$7	 	M	 		-0&+/8O
 	
>B
 	
r1   )NNNNNNN)rD   rE   rF   r    r&   r   r(   r   r   r	   FloatTensorr   r   r   rA   r   r?   rG   rH   s   @r0   r  r  l  s    }    .2.204(,26!%26D
##d*D
 t+D
 &&-	D

 D
 ((4/D
 $;D
 ((4/D
 +,D
 
(	(D
 D
r1   r  c                   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 )Exaone4ForCausalLMzlm_head.weightzmodel.embed_tokens.weightlm_headcolwise_gather_outputr<   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   Nr  r   ry   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-4.0-32B")
        >>> tokenizer = AutoTokenizer.from_pretrained("LGAI-EXAONE/EXAONE-4.0-32B")

        >>> 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"
        ```
        )r  r   ry   r   r  r   r   N)r%  r'  r  )lossr%  r   r<   r   r   )r   r  rq   r   slicer#  loss_functionrL   r  r   r   r<   r   )r,   r  r   ry   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   r	   r   r   r   r   r   r   r?   rG   rH   s   @r0   r"  r"    s<   *,GH23H_-z:;H  .2.204(,26*.!%26-.F
##d*F
 t+F
 &&-	F

 F
 ((4/F
   4'F
 $;F
 ((4/F
 ell*F
 +,F
 
 F
  F
r1   r"  c                       e Zd Zy) Exaone4ForSequenceClassificationNrD   rE   rF   r   r1   r0   r3  r3         r1   r3  c                       e Zd Zy)Exaone4ForTokenClassificationNr4  r   r1   r0   r7  r7  $  r5  r1   r7  c                       e Zd ZdZy)Exaone4ForQuestionAnsweringtransformerN)rD   rE   rF   r   r   r1   r0   r9  r9  (  s    %r1   r9  )r   r  r"  r3  r7  r9  )r   )r   )Acollections.abcr   typingr   r(   r   transformers.utils.genericr   activationsr   cache_utilsr	   r
   
generationr   integrationsr   r   masking_utilsr   r   modeling_layersr   r   r   r   modeling_outputsr   r   modeling_rope_utilsr   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   utils.genericr   configuration_exaone4r    Moduler#   rJ   r   r   r   r   r   rf   r   r   r   r   r   r  r"  r3  r7  r9  __all__r   r1   r0   <module>rM     s  , %    9 ! . ) Q R  P K F & I I + 0 Y'JRYY J (J(><RYY ><B( *+ ,2	UU\\ 	U# 	U%,, 	U& %II%<<% 
% <<	%
 LL4'% % % '(%4K)ryy K)\  (4 (V !_ ! !& V
) V
 V
r V
/ V
 V
r	'GI_ 		$ACY 	&"=?U &r1   