Ë
    ÛÓ^j—  ã                   ór   — d dl mZ ddlmZ ddlmZ ddlmZ  ed¬«      e G d„ d	e«      «       «       Zd	gZ	y
)é    )Ústricté   )ÚPreTrainedConfig)ÚRopeParameters)Úauto_docstringzLGAI-EXAONE/EXAONE-4.0-32B)Ú
checkpointc            
       óÒ  ‡ — e Zd ZU dZdZdgZddddddddddœ	Zdgd	gfd
dgd
gfd
gd
gfdœZdZe	e
d<   dZe	e
d<   dZe	e
d<   dZe	e
d<   dZe	e
d<   dZe	e
d<   dZee
d<   dZe	e
d<   dZee
d<   dZee
d<   dZee
d <   d!Ze	d"z  e
d#<   d$Ze	ee	   z  d"z  e
d%<   d"Ze	d"z  e
d&<   d'Zee
d(<   d"Zeez  d"z  e
d)<   d*Z ee	z  e
d+<   dZ!e	d"z  e
d,<   d-Z"ee	z  d"z  e
d.<   d"Z#ee   d"z  e
d/<   ˆ fd0„Z$ˆ xZ%S )1ÚExaone4Configa~  
    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)

    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
    ```Úexaone4Úpast_key_valuesÚcolwiseÚreplicated_with_grad_allreduceÚrowwise)	zlayers.*.self_attn.q_projzlayers.*.self_attn.k_projzlayers.*.self_attn.v_projzlayers.*.self_attn.q_normzlayers.*.self_attn.k_normzlayers.*.self_attn.o_projzlayers.*.mlp.gate_projzlayers.*.mlp.up_projzlayers.*.mlp.down_projÚ	input_idsÚinputs_embedsÚhidden_statesÚattention_mask)Úembed_tokensÚlayersÚnormi � Ú
vocab_sizei   Úhidden_sizei @  Úintermediate_sizeé    Únum_hidden_layersÚnum_attention_headsÚnum_key_value_headsÚsiluÚ
hidden_acti   Úmax_position_embeddingsg{®Gáz”?Úinitializer_rangegñhãˆµøä>Úrms_norm_epsTÚ	use_cacher   NÚbos_token_idé   Úeos_token_idÚpad_token_idFÚtie_word_embeddingsÚrope_parametersg        Úattention_dropoutÚsliding_windowé   Úsliding_window_patternÚlayer_typesc                 ó  •— | j                   €d| _        | j                  €Nt        | j                  «      D �cg c]*  }|dz   | j                  z  dk7  r|| j                  k  rdnd‘Œ, c}| _        t        ‰| �  di |¤Ž y c c}w )Nr   é   Úsliding_attentionÚfull_attention© )r+   r-   r.   Úranger   ÚsuperÚ__post_init__)ÚselfÚkwargsÚiÚ	__class__s      €ú|/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/exaone4/configuration_exaone4.pyr6   zExaone4Config.__post_init__d   s’   ø€ Ø×ÑÐ&Ø*+ˆDÔ'Ø×ÑÐ#ô
 ˜t×5Ñ5Ó6ö	 ð ð ˜‘U˜t×:Ñ:Ñ;¸qÒ@ÀQÈ×I_ÑI_ÒE_ñ $à%ñ&ò ˆDÔô 	‰ÑÑ' Ó'ùò s   ¸/A?)&Ú__name__Ú
__module__Ú__qualname__Ú__doc__Ú
model_typeÚkeys_to_ignore_at_inferenceÚbase_model_tp_planÚbase_model_pp_planr   ÚintÚ__annotations__r   r   r   r   r   r   Ústrr    r!   Úfloatr"   r#   Úboolr$   r&   Úlistr'   r(   r)   r   Údictr*   r+   r-   r.   r6   Ú__classcell__)r:   s   @r;   r
   r
      s‰  ø… ñð8 €JØ#4Ð"5Ðð &/Ø%.Ø%.Ø%EØ%EØ%.Ø"+Ø )Ø"+ñ
Ðð &˜¨Ð(9Ð:Ø#Ð%5Ð6¸Ð8IÐJØ!Ð" _Ð$5Ð6ñÐð €J�ÓØ€K�ÓØ"Ð�sÓ"ØÐ�sÓØ!Ð˜Ó!Ø!Ð˜Ó!Ø€J�ÓØ#'Ð˜SÓ'Ø#Ð�uÓ#Ø€L�%ÓØ€IˆtÓØ €L�#˜‘*Ó Ø+,€L�#˜˜S™	‘/ DÑ(Ó,Ø#€L�#˜‘*Ó#Ø %Ð˜Ó%Ø48€O�^ dÑ*¨TÑ1Ó8Ø%(Ð�u˜s‘{Ó(Ø!%€N�C˜$‘JÓ%Ø/0Ð˜C #™I¨Ñ,Ó0Ø$(€K��c‘˜TÑ!Ó(÷(ð (ó    r
   N)
Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úmodeling_rope_utilsr   Úutilsr   r
   Ú__all__r3   rL   r;   ú<module>rR      sK   ðõ* /å 3Ý 1Ý #ñ Ð7Ô8ØôQ(Ð$ó Q(ó ó 9ðQ(ðh Ð
�rL   