Ë
    ÜÓ^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karpathy/nanochat-d32)Ú
checkpointc                   ó†  ‡ — e Zd ZU dZdZdgZdddddd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d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ez  dz  e	d<   dZe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dz  e	d(<   d"Z!ee	d)<   ˆ fd*„Z"ˆ xZ#S )+ÚNanoChatConfigaˆ  
    Example:

    ```python
    >>> from transformers import NanoChatModel, NanoChatConfig

    >>> # Initializing a NanoChat style configuration
    >>> configuration = NanoChatConfig()

    >>> # Initializing a model from the NanoChat style configuration
    >>> model = NanoChatModel(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```ÚnanochatÚpast_key_valuesÚcolwiseÚrowwise)zlayers.*.self_attn.q_projzlayers.*.self_attn.k_projzlayers.*.self_attn.v_projzlayers.*.self_attn.o_projzlayers.*.mlp.fc1zlayers.*.mlp.fc2i€Ä  Ú
vocab_sizei   Úhidden_sizei    Úintermediate_sizeé   Únum_hidden_layersé   Únum_attention_headsNÚnum_key_value_headsi   Úmax_position_embeddingsÚrelu2Ú
hidden_actg        Úattention_dropoutg�íµ ÷Æ°>Úrms_norm_epsg{®Gáz”?Úinitializer_rangeÚrope_parametersTÚ	use_cacheg      .@Úfinal_logit_softcappingFÚattention_biasr   Úbos_token_idé   Úeos_token_idÚpad_token_idÚtie_word_embeddingsc                 ó^   •— | j                   €| j                  | _         t        ‰| �  di |¤Ž y )N© )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/nanochat/configuration_nanochat.pyr)   zNanoChatConfig.__post_init__J   s-   ø€ Ø×#Ñ#Ð+Ø'+×'?Ñ'?ˆDÔ$ä‰ÑÑ' Ó'ó    )$Ú__name__Ú
__module__Ú__qualname__Ú__doc__Ú
model_typeÚkeys_to_ignore_at_inferenceÚbase_model_tp_planr   ÚintÚ__annotations__r   r   r   r   r   r   r   Ústrr   Úfloatr   r   r   r   Údictr   Úboolr   r    r!   r#   Úlistr$   r%   r)   Ú__classcell__)r,   s   @r-   r
   r
      s2  ø… ñð  €JØ#4Ð"5Ðð &/Ø%.Ø%.Ø%.Ø%Ø%ñÐð €J�ÓØ€K�ÓØ!Ð�sÓ!ØÐ�sÓØ Ð˜Ó Ø&*Ð˜˜t™Ó*Ø#'Ð˜SÓ'Ø€J�ÓØ%(Ð�u˜s‘{Ó(Ø€L�%ÓØ#Ð�uÓ#Ø48€O�^ dÑ*¨TÑ1Ó8Ø€IˆtÓØ,0Ð˜U T™\Ó0Ø €N�DÓ Ø €L�#˜‘*Ó Ø+,€L�#˜˜S™	‘/ DÑ(Ó,Ø €L�#˜‘*Ó Ø %Ð˜Ó%÷(ð (r.   r
   N)
Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úmodeling_rope_utilsr   Úutilsr   r
   Ú__all__r'   r.   r-   ú<module>rC      sH   ðõ  /å 3Ý 1Ý #ñ Ð2Ô3Øô5(Ð%ó 5(ó ó 4ð5(ðp Ð
�r.   