Ë
    ÜÓ^jù
  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RWKV configurationé    )Ústricté   )ÚPreTrainedConfig)Úauto_docstringzRWKV/rwkv-4-169m-pile)Ú
checkpointc                   óü   ‡ — e Zd ZU dZdZddiZ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dz  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ed<   dZeed<   dZeed<   ˆ fd„Zˆ xZS )Ú
RwkvConfigaÏ  
    context_length (`int`, *optional*, defaults to 1024):
        The maximum sequence length that this model can be used with in a single forward (using it in RNN mode
        lets use any sequence length).
    attention_hidden_size (`int`, *optional*):
        Dimensionality of the attention hidden states. Will default to `hidden_size` if unset.
    rescale_every (`int`, *optional*, defaults to 6):
        At inference, the hidden states (and weights of the corresponding output layers) are divided by 2 every
        `rescale_every` layer. If set to 0 or a negative number, no rescale is done.

    Example:

    ```python
    >>> from transformers import RwkvConfig, RwkvModel

    >>> # Initializing a Rwkv configuration
    >>> configuration = RwkvConfig()

    >>> # Initializing a model (with random weights) from the configuration
    >>> model = RwkvModel(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```ÚrwkvÚmax_position_embeddingsÚcontext_lengthieÄ  Ú
vocab_sizei   i   Úhidden_sizeé    Únum_hidden_layersNÚattention_hidden_sizeÚintermediate_sizegñhãˆµøä>Úlayer_norm_epsilonr   Úbos_token_idÚeos_token_idé   Úrescale_everyFÚtie_word_embeddingsTÚ	use_cachec                 óÎ   •— | j                   �| j                   n| j                  | _         | j                  �| j                  nd| j                  z  | _        t        ‰| �  di |¤Ž y )Né   © )r   r   r   ÚsuperÚ__post_init__)ÚselfÚkwargsÚ	__class__s     €úv/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/rwkv/configuration_rwkv.pyr   zRwkvConfig.__post_init__C   sc   ø€ à*.×*DÑ*DÐ*PˆD×&Ò&ÐVZ×VfÑVfð 	Ô"ð <@×;QÑ;QÐ;] ×!7Ò!7ÐcdÐgk×gwÑgwÑcwˆÔä‰ÑÑ' Ó'ó    )Ú__name__Ú
__module__Ú__qualname__Ú__doc__Ú
model_typeÚattribute_mapr   ÚintÚ__annotations__r   r   r   r   r   r   Úfloatr   r   Úlistr   r   Úboolr   r   Ú__classcell__)r!   s   @r"   r	   r	      sº   ø… ñð2 €JØ.Ð0@ÐA€Mà€J�ÓØ€N�CÓØ€K�ÓØÐ�sÓØ(,Ð˜3 ™:Ó,Ø$(Ð�s˜T‘zÓ(Ø $Ð˜Ó$Ø €L�#˜‘*Ó Ø+,€L�#˜˜S™	‘/ DÑ(Ó,Ø€M�3ÓØ %Ð˜Ó%Ø€IˆtÓ÷(ð (r#   r	   N)	r'   Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úutilsr   r	   Ú__all__r   r#   r"   ú<module>r4      sG   ðñ å .å 3Ý #ñ Ð2Ô3Øô0(Ð!ó 0(ó ó 4ð0(ðf ˆ.�r#   