
    rh\                     6   d Z 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
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 ddlmZmZ ddlmZmZmZm Z m!Z!m"Z"m#Z#m$Z$m%Z%m&Z& ddl'm(Z(m)Z)  ejT                  e+      Z,dZ-dZ. G d de      Z/ G d de#      Z0 G d de$      Z1 G d dejd                        Z3 G d de)      Z4 G d de(      Z5 G d de"      Z6 G d  d!e6e!      Z7 G d" d#e      Z8 G d$ d%e      Z9 G d& d'e       Z: G d( d)e      Z;g d*Z<y)+zLG AI Research EXAONE Lab    )CallableOptionalUnionN)nn)check_model_inputs   )CacheDynamicCache)PretrainedConfiglayer_type_validation)create_causal_mask!create_sliding_window_causal_mask)BaseModelOutputWithPastCausalLMOutputWithPast)ALL_ATTENTION_FUNCTIONS)Unpack)TransformersKwargslogging   )
LlamaForCausalLMLlamaForQuestionAnsweringLlamaForSequenceClassificationLlamaForTokenClassification
LlamaModelLlamaPreTrainedModelLlamaRMSNormLlamaRotaryEmbeddingapply_rotary_pos_embeager_attention_forward)Olmo2DecoderLayerOlmo2MLPzLGAI-EXAONE/EXAONE-4.0-InstructExaone4Configc                        e Zd ZdZdZdgZddddddddZdgdgfd	d
gd	gfd	gd	gfdZ	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 d fd	Z xZ	S )r"   a  
    This is the configuration class to store the configuration of a [`Exaone4Model`]. It is used to
    instantiate a EXAONE 4.0 model according to the specified arguments, defining the model architecture. Instantiating a
    configuration with the defaults will yield a similar configuration to that of the EXAONE-4.0-Instruct [LGAI-EXAONE/EXAONE-4.0-Instruct](https://huggingface.co/LGAI-EXAONE/EXAONE-4.0-Instruct)
    NOTE: `EXAONE-4.0-Instruct` is a placeholder model ID. The exact model ID will be updated in the future.

    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model
    outputs. Read the documentation from [`PretrainedConfig`] for more information.

    Args:
        vocab_size (`int`, *optional*, defaults to 102400):
            Vocabulary size of the EXAONE 4.0 model. Defines the number of different tokens that can be represented by the
            `inputs_ids` passed when calling [`Exaone4Model`].
        hidden_size (`int`, *optional*, defaults to 4096):
            Dimension of the hidden representations.
        intermediate_size (`int`, *optional*, defaults to `hidden_size * 4`):
            Dimensionality of the MLP representations.
        num_hidden_layers (`int`, *optional*, defaults to 32):
            Number of hidden layers in the Transformer encoder.
        num_attention_heads (`int`, *optional*, defaults to 32):
            Number of attention heads for each attention layer in the Transformer decoder.
        num_key_value_heads (`int`, *optional*):
            This is the number of key_value heads that should be used to implement Grouped Query Attention. If
            `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
            `num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When
            converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
            by meanpooling all the original heads within that group. For more details checkout [this
            paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
            `num_attention_heads`.
        hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
            The non-linear activation function (function or string) in the decoder.
        max_position_embeddings (`int`, *optional*, defaults to 2048):
            The maximum sequence length that this model might ever be used with. Typically set this to something large
            just in case (e.g., 32768 for EXAONE 3.5).
        initializer_range (`float`, *optional*, defaults to 0.02):
            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
        rms_norm_eps (`float`, *optional*, defaults to 1e-05):
            The epsilon used by the layer normalization layers.
        use_cache (`bool`, *optional*, defaults to `True`):
            Whether or not the model should return the last key/values attentions (not used by all models). Only
            relevant if ``config.is_decoder=True``.
        bos_token_id (`int`, *optional*, defaults to 0):
            Beginning of stream token id.
        eos_token_id (`int`, *optional*, defaults to 2):
            End of stream token id.
        tie_word_embeddings (`bool`, *optional*, defaults to `False`):
            Whether to tie weight embeddings
        rope_theta (`float`, *optional*, defaults to 10000.0):
            The base period of the RoPE embeddings.
        rope_scaling (`Dict`, *optional*):
            Dictionary containing the scaling configuration for the RoPE embeddings. NOTE: if you apply new rope type
            and you expect the model to work on longer `max_position_embeddings`, we recommend you to update this value
            accordingly.
            Expected contents:
                `rope_type` (`str`):
                    The sub-variant of RoPE to use. Can be one of ['default', 'linear', 'dynamic', 'yarn', 'longrope',
                    'llama3'], with 'default' being the original RoPE implementation.
                `factor` (`float`, *optional*):
                    Used with all rope types except 'default'. The scaling factor to apply to the RoPE embeddings. In
                    most scaling types, a `factor` of x will enable the model to handle sequences of length x *
                    original maximum pre-trained length.
                `original_max_position_embeddings` (`int`, *optional*):
                    Used with 'dynamic', 'longrope' and 'llama3'. The original max position embeddings used during
                    pretraining.
                `attention_factor` (`float`, *optional*):
                    Used with 'yarn' and 'longrope'. The scaling factor to be applied on the attention
                    computation. If unspecified, it defaults to value recommended by the implementation, using the
                    `factor` field to infer the suggested value.
                `beta_fast` (`float`, *optional*):
                    Only used with 'yarn'. Parameter to set the boundary for extrapolation (only) in the linear
                    ramp function. If unspecified, it defaults to 32.
                `beta_slow` (`float`, *optional*):
                    Only used with 'yarn'. Parameter to set the boundary for interpolation (only) in the linear
                    ramp function. If unspecified, it defaults to 1.
                `short_factor` (`List[float]`, *optional*):
                    Only used with 'longrope'. The scaling factor to be applied to short contexts (<
                    `original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
                    size divided by the number of attention heads divided by 2
                `long_factor` (`List[float]`, *optional*):
                    Only used with 'longrope'. The scaling factor to be applied to long contexts (<
                    `original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
                    size divided by the number of attention heads divided by 2
                `low_freq_factor` (`float`, *optional*):
                    Only used with 'llama3'. Scaling factor applied to low frequency components of the RoPE
                `high_freq_factor` (`float`, *optional*):
                    Only used with 'llama3'. Scaling factor applied to high frequency components of the RoPE
        attention_dropout (`float`, *optional*, defaults to 0.0):
            The dropout ratio for the attention probabilities.
        sliding_window (`int`, *optional*):
            The size of the sliding window for the sliding window attention.
        sliding_window_pattern (`str`, *optional*):
            The pattern to use for sliding window attention. Can be one of:
                - `None`: No sliding window attention is used
                - `int`: Every `sliding_window` layers, use global attention, else use local attention.
                - `str`: A sequence of "L" (local attention) and "G" (global attention) characters that defines the
                  attention pattern. The pattern starts from layer 0 and repeats every `sliding_window` layers. The
                  final layer always uses global attention regardless of the pattern.
            For instance, sliding_window_pattern="LLLG" same as sliding_window=4, which means:
                - Layer 0, 1, 2: local attention,
                - Layer 3: global attention,
                ...(repeated)
        layer_types (`list`, *optional*):
            Attention pattern for each layer. Prioritized over `sliding_window_pattern`.

    Example:

    ```python
    >>> from transformers import Exaone4Model, Exaone4Config

    >>> # Initializing a EXAONE configuration
    >>> configuration = Exaone4Config()

    >>> # Initializing a model from configuration
    >>> model = Exaone4Model(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```exaone4past_key_valuescolwiserowwise)zlayers.*.self_attn.q_projzlayers.*.self_attn.k_projzlayers.*.self_attn.v_projzlayers.*.self_attn.o_projzlayers.*.mlp.gate_projzlayers.*.mlp.up_projzlayers.*.mlp.down_proj	input_idsinputs_embedshidden_statesattention_mask)embed_tokenslayersnormc                 4   || _         || _        || _        || _        || _        || _        || _        || _        |	| _        |
| _	        || _
        || _        || _        || _        || _        || _        || _        | j                  d}| j                   Dt#        | j                        D cg c]   }|dz   |z  dk7  r|| j                  k  rdnd" c}| _        d| j                   v rd| _        t'        | j                          t)        | T  d|||d| y c c}w )	Nr      sliding_attentionfull_attentionsliding_windowhybrid)bos_token_ideos_token_idtie_word_embeddings )
vocab_sizehidden_sizenum_hidden_layersnum_attention_headsnum_key_value_headsintermediate_size
hidden_actmax_position_embeddingsinitializer_rangerms_norm_eps	use_cacheattention_dropout
rope_thetarope_scalingr3   sliding_window_patternlayer_typesrangecache_implementationr   super__init__)selfr9   r:   r>   r;   r<   r=   r?   r@   rA   rB   rC   r5   r6   r7   rE   rF   rD   r3   rG   rH   kwargsi	__class__s                          ~/var/www/html/ai-insurance-compliance-backend/venv/lib/python3.12/site-packages/transformers/models/exaone4/modular_exaone4.pyrL   zExaone4Config.__init__   sG   0 %&!2#6 #6 !2$'>$!2("!2$(,&<#&&%&"#
 t556	   U56!;DDZDZ@Z $%& D t///(0D%d../ 	
%LVi	
ms	
 s   *%D)i     i @      rS   rS   silui   g{Gz?gh㈵>Tr   r   Fg     @N        rR      N)
__name__
__module____qualname____doc__
model_typekeys_to_ignore_at_inferencebase_model_tp_planbase_model_pp_planrL   __classcell__rP   s   @rQ   r"   r"   ;   s    un J#4"5 &/%.%.%."+ )"+ &(9:#%568IJ!"_$56  $! +9
 9
    c                       e Zd Zy)Exaone4RMSNormNrW   rX   rY   r8   ra   rQ   rc   rc         ra   rc   c                       e Zd Zy)Exaone4RotaryEmbeddingNrd   r8   ra   rQ   rg   rg     re   ra   rg   c                   4    e Zd Zdedef fdZ	 	 	 ddej                  deej                  ej                  f   de	ej                     de	e
   de	ej                     d	ee   d
eej                  e	ej                     e	eej                        f   fdZ xZS )Exaone4Attentionconfig	layer_idxc                    t         |           || _        || _        |j                  | _        |j
                  | _        |j                  | _        t        |d|j                  |j                  z        | _        |j                  |j
                  z  | _	        |j                  | _
        d| _        | j                  dz  | _        |j                  | _        |j                  | _        |j                  |   dk(  | _        t#        j$                  | 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 )Nhead_dimTg      r1   F)biaseps)rK   rL   rj   rk   r<   r=   r:   getattrrm   num_key_value_groupsrD   	is_causalscalingr3   rG   rH   
is_slidingr   Linearq_projk_projv_projo_projrc   rB   q_normk_normrM   rj   rk   rP   s      rQ   rL   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ra   r*   position_embeddingsr+   past_key_valuecache_positionrN   returnc                    |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$                  sdn| j&                  | j(                  | j                  r| j                  nd d|\  }} |j*                  g |d j-                         }| j/                  |      }||fS )Nr0   r   r   eagerrU   )dropoutrt   r3   )shaperm   rw   view	transposerx   ry   r{   r|   r3   ru   r   updaterk   r   rj   _attn_implementationr   trainingrD   rt   reshape
contiguousrz   )rM   r*   r~   r+   r   r   rN   input_shapehidden_shapequery_states
key_statesvalue_statescossincache_kwargsattention_interfaceattn_outputattn_weightss                     rQ   forwardzExaone4Attention.forward"  s    $))#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$2H2HLL26//4..t
%
 
%
!\ *k));;;;FFHkk+.L((ra   )NNN)rW   rX   rY   r"   intrL   torchTensortupler   r	   
LongTensorr   r   r   r_   r`   s   @rQ   ri   ri   	  s    M} M M8 26*.591)||1) #5<<#=>1) !.	1)
 !1) !!1!121) +,1) 
u||Xell3XeELL>Q5RR	S1)ra   ri   c                       e Zd Zy)
Exaone4MLPNrd   r8   ra   rQ   r   r   V  re   ra   r   c                       e Zd Zy)Exaone4DecoderLayerNrd   r8   ra   rQ   r   r   Z  re   ra   r   c                       e Zd ZeZdgZy)Exaone4PreTrainedModelr   N)rW   rX   rY   r"   config_class_no_split_modulesr8   ra   rQ   r   r   ^  s     L./ra   r   c                       e Zd Zdef fdZe	 	 	 	 	 	 	 ddej                  deej                     deej                     dee
   deej                     dee   d	eej                     d
ee   deeef   fd       Z xZS )Exaone4Modelrj   c           	      $   t         |   |       t        j                  t	        |j
                        D cg c]  }t        ||       c}      | _        t        |j                  |j                        | _        | j                          y c c}w )Nro   )rK   rL   r   
ModuleListrI   r;   r   r-   rc   r:   rB   r.   	post_initr}   s      rQ   rL   zExaone4Model.__init__d  so     mmEJ6KcKcEde	 3e
 #6#5#56;N;NO	 	 fs   Br(   r+   position_idsr%   r)   rC   r   rN   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   r0   )device)rj   input_embedsr+   r   r%   r   r2   r1   )r~   r+   r   r   rC   r   )last_hidden_stater%   r8   )
ValueErrorr,   r
   get_seq_lengthr   aranger   r   	unsqueeze
isinstancedictrj   r   rH   r   
rotary_emb	enumerater-   r.   r   )rM   r(   r+   r   r%   r)   rC   r   rN   past_seen_tokenscausal_mask_mappingmask_kwargsr*   r~   rO   decoder_layer
layer_types                    rQ   r   zExaone4Model.forwardn  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)	$72:>).#-	 	M	 		-0&+/8O
 	
>B
 	
ra   )NNNNNNN)rW   rX   rY   r"   rL   r   r   r   r   r   r	   FloatTensorboolr   r   r   r   r   r   r_   r`   s   @rQ   r   r   c  s    }   '+1537+/59$(59E
##E
 !.E
 u//0	E

 "%E
   1 12E
 D>E
 !!1!12E
 +,E
 
u--	.E
 E
ra   r   c                   ,    e Zd Z	 	 	 	 	 	 	 	 	 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 fdZ xZS )Exaone4ForCausalLMr(   r+   r   r%   r)   labelsrC   r   logits_to_keeprN   r   c
                 8    t        |   d|||||||||	d	|
 y)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+   r   r%   r)   r   rC   r   r   Nr8   )rK   r   )rM   r(   r+   r   r%   r)   r   rC   r   r   rN   rP   s              rQ   r   zExaone4ForCausalLM.forward  s<    Z 	 	
)%+'))	
 	
ra   )	NNNNNNNNr   )rW   rX   rY   r   r   r   r   r	   r   r   r   r   r   r   r   r   r_   r`   s   @rQ   r   r     s     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
ra   r   c                       e Zd Zy) Exaone4ForSequenceClassificationNrd   r8   ra   rQ   r   r     re   ra   r   c                       e Zd Zy)Exaone4ForTokenClassificationNrd   r8   ra   rQ   r   r     re   ra   r   c                       e Zd Zy)Exaone4ForQuestionAnsweringNrd   r8   ra   rQ   r   r     re   ra   r   )r"   r   r   r   r   r   r   )=rZ   typingr   r   r   r   r   transformers.utils.genericr   cache_utilsr	   r
   configuration_utilsr   r   masking_utilsr   r   modeling_outputsr   r   modeling_utilsr   processing_utilsr   utilsr   r   llama.modeling_llamar   r   r   r   r   r   r   r   r   r   olmo2.modeling_olmo2r    r!   
get_loggerrW   logger_CHECKPOINT_FOR_DOC_CONFIG_FOR_DOCr"   rc   rg   Moduleri   r   r   r   r   r   r   r   r   __all__r8   ra   rQ   <module>r      s      , ,   9 . J R 6 &   ? 
		H	%7 !C
$ C
L	\ 		1 	J)ryy J)Z	 		+ 	01 0
Q
): Q
h9
) 9
x	'E 		$? 		"; 	ra   