Ë
    ÛÓ^j  ã                   óv   — d Z 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)zDiffLlama model configurationé    )Ústricté   )ÚPreTrainedConfig)ÚRopeParameters)Úauto_docstringzkajuma/DiffLlama-0.3B-handcut)Ú
checkpointc                   óŽ  ‡ — 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dz  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dz  ed<   dZeee   z  dz  ed<   dZeed<   dZeez  dz  ed <   dZeed!<   d"Zeez  dz  ed#<   d$Z edz  ed%<   dZ!edz  ed&<   ˆ fd'„Z"ˆ xZ#S )(ÚDiffLlamaConfiga+  
    lambda_std_dev (`float`, *optional*, defaults to 0.1):
        The standard deviation for initialization of parameter lambda in attention layer.

    ```python
    >>> from transformers import DiffLlamaModel, DiffLlamaConfig

    >>> # Initializing a DiffLlama diffllama-7b style configuration
    >>> configuration = DiffLlamaConfig()

    >>> # Initializing a model from the diffllama-7b style configuration
    >>> model = DiffLlamaModel(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```
    Ú	diffllamaÚpast_key_valuesi }  Ú
vocab_sizei   Úhidden_sizei    Úintermediate_sizeé   Únum_hidden_layersé    Únum_attention_headsNÚnum_key_value_headsÚsiluÚ
hidden_actÚmax_position_embeddingsg{®Gáz”?Úinitializer_rangegñhãˆµøä>Úrms_norm_epsTÚ	use_cacheÚpad_token_idé   Úbos_token_idé   Úeos_token_idFÚtie_word_embeddingsÚrope_parametersÚattention_biasg        Úattention_dropoutgš™™™™™¹?Úlambda_std_devÚhead_dimc                 óÊ   •— | j                   €| j                  | _         | j                  �| j                  n| j                  | j                  z  | _        t	        ‰| �  di |¤Ž y )N© )r   r   r%   r   ÚsuperÚ__post_init__)ÚselfÚkwargsÚ	__class__s     €ú€/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/diffllama/configuration_diffllama.pyr)   zDiffLlamaConfig.__post_init__G   sU   ø€ à×#Ñ#Ð+Ø'+×'?Ñ'?ˆDÔ$à)-¯©Ð)B˜ŸšÈ×HXÑHXÐ\`×\tÑ\tÑHtˆŒÜ‰ÑÑ' Ó'ó    )$Ú__name__Ú
__module__Ú__qualname__Ú__doc__Ú
model_typeÚkeys_to_ignore_at_inferencer   ÚintÚ__annotations__r   r   r   r   r   r   Ústrr   r   Úfloatr   r   Úboolr   r   r   Úlistr    r!   r   Údictr"   r#   r$   r%   r)   Ú__classcell__)r,   s   @r-   r
   r
      s&  ø… ñð$ €JØ#4Ð"5Ðà€J�ÓØ€K�ÓØ!Ð�sÓ!ØÐ�sÓØ!Ð˜Ó!Ø&*Ð˜˜t™Ó*Ø€J�ÓØ#'Ð˜SÓ'Ø#Ð�uÓ#Ø€L�%ÓØ€IˆtÓØ#€L�#˜‘*Ó#Ø €L�#˜‘*Ó Ø+,€L�#˜˜S™	‘/ DÑ(Ó,Ø %Ð˜Ó%Ø48€O�^ dÑ*¨TÑ1Ó8Ø €N�DÓ Ø,/Ð�u˜s‘{ TÑ)Ó/Ø#&€N�E˜D‘LÓ&Ø€Hˆc�D‰jÓ÷(ð (r.   r
   N)r2   Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úmodeling_rope_utilsr   Úutilsr   r
   Ú__all__r'   r.   r-   ú<module>rB      sK   ðñ" $å .å 3Ý 1Ý #ñ Ð:Ô;Øô1(Ð&ó 1(ó ó <ð1(ðh Ð
�r.   