
    i                     j    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 configuration    )strict   )PreTrainedConfig)auto_docstringzfacebook/opt-350m)
checkpointc                       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&<    fd'Z! xZ"S )(	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
    ```optpast_key_valuesi`  
vocab_sizei   hidden_size   num_hidden_layersi   ffn_dimi   max_position_embeddingsTdo_layer_norm_beforeF_remove_final_layer_normNword_embed_proj_dimg?dropoutg        attention_dropoutnum_attention_headsreluactivation_function	layerdropg{Gz?init_std	use_cache   pad_token_id   bos_token_ideos_token_idenable_biaslayer_norm_elementwise_affinetie_word_embeddingsc                 v    | j                   | j                   n| j                  | _         t        |   di | y )N )r   r   super__post_init__)selfkwargs	__class__s     z/var/www/vps2.regionflexible.com/Desarrollo/venv/lib/python3.12/site-packages/transformers/models/opt/configuration_opt.pyr(   zOPTConfig.__post_init__L   s:    (,(@(@(LD$$RVRbRb 	  	''    )#__name__
__module____qualname____doc__
model_typekeys_to_ignore_at_inferencer   int__annotations__r   r   r   r   r   boolr   r   r   floatr   r   r   strr   r   r   r   r    r!   listr"   r#   r$   r(   __classcell__)r+   s   @r,   r	   r	      s#   4 J#4"5JKsGS#'S'!%$%%*d*&*t*GUS[%(us{(!!%% Ius{ HeIt L#*  L#* +,L#S	/D(,K*.!4. $$( (r-   r	   N)	r1   huggingface_hub.dataclassesr   configuration_utilsr   utilsr   r	   __all__r&   r-   r,   <module>r?      sG     . 3 # ./8(  8(  08(v -r-   