Ë
    ÜÓ^j¾  ã                   ój   — d 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
)zOPT model configurationé    )Ústricté   )ÚPreTrainedConfig)Úauto_docstringzfacebook/opt-350m)Ú
checkpointc                   óŠ  ‡ — e Zd ZU dZdZdg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dz  ed<   dZeez  ed<   dZeez  ed<   dZeed<   dZeed<   dZeez  ed<   dZeed<   dZeed<   dZedz  ed <   d!Zedz  ed"<   d!Zeee   z  dz  ed#<   dZeed$<   dZeed%<   dZ eed&<   ˆ fd'„Z!ˆ xZ"S )(Ú	OPTConfiga  
    do_layer_norm_before (`bool`, *optional*, defaults to `True`):
        Whether to perform layer normalization before the attention block.
    word_embed_proj_dim (`int`, *optional*):
        `word_embed_proj_dim` can be set to down-project word embeddings, *e.g.* `opt-350m`. Defaults to
        `hidden_size`.
    enable_bias (`bool`, *optional*, defaults to `True`):
        Whether or not if the linear layers in the attention blocks should use the bias term.
    layer_norm_elementwise_affine (`bool`, *optional*, defaults to `True`):
        Whether or not if the layer norms should have learnable parameters.

    Example:

    ```python
    >>> from transformers import OPTConfig, OPTModel

    >>> # Initializing a OPT facebook/opt-large style configuration
    >>> configuration = OPTConfig()

    >>> # Initializing a model (with random weights) from the facebook/opt-large style configuration
    >>> model = OPTModel(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```ÚoptÚpast_key_valuesi`Ä  Ú
vocab_sizei   Úhidden_sizeé   Únum_hidden_layersi   Úffn_dimi   Úmax_position_embeddingsTÚdo_layer_norm_beforeFÚ_remove_final_layer_normNÚword_embed_proj_dimgš™™™™™¹?Údropoutg        Úattention_dropoutÚnum_attention_headsÚreluÚactivation_functionÚ	layerdropg{®Gáz”?Úinit_stdÚ	use_cacheé   Úpad_token_idé   Úbos_token_idÚeos_token_idÚenable_biasÚlayer_norm_elementwise_affineÚtie_word_embeddingsc                 óv   •— | j                   �| j                   n| j                  | _         t        ‰| �  di |¤Ž y )N© )r   r   ÚsuperÚ__post_init__)ÚselfÚkwargsÚ	__class__s     €út/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/opt/configuration_opt.pyr(   zOPTConfig.__post_init__L   s:   ø€ à(,×(@Ñ(@Ð(LˆD×$Ò$ÐRV×RbÑRbð 	Ô ô 	‰ÑÑ' Ó'ó    )#Ú__name__Ú
__module__Ú__qualname__Ú__doc__Ú
model_typeÚkeys_to_ignore_at_inferencer   ÚintÚ__annotations__r   r   r   r   r   Úboolr   r   r   Úfloatr   r   r   Ústrr   r   r   r   r    r!   Úlistr"   r#   r$   r(   Ú__classcell__)r+   s   @r,   r	   r	      s#  ø… ñð4 €JØ#4Ð"5Ðà€J�ÓØ€K�ÓØÐ�sÓØ€GˆSÓØ#'Ð˜SÓ'Ø!%Ð˜$Ó%Ø%*Ð˜dÓ*Ø&*Ð˜˜t™Ó*Ø€GˆU�S‰[ÓØ%(Ð�u˜s‘{Ó(Ø!Ð˜Ó!Ø%Ð˜Ó%Ø €Iˆu�s‰{Ó Ø€HˆeÓØ€IˆtÓØ €L�#˜‘*Ó Ø €L�#˜‘*Ó Ø+,€L�#˜˜S™	‘/ DÑ(Ó,Ø€K�ÓØ*.Ð! 4Ó.Ø $Ð˜Ó$÷(ð (r-   r	   N)	r1   Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úutilsr   r	   Ú__all__r&   r-   r,   ú<module>r?      sG   ðñ å .å 3Ý #ñ Ð.Ô/Øô8(Ð ó 8(ó ó 0ð8(ðv ˆ-�r-   