ó
    ‡Ž¡j  ã                   óp   • S r SSKJr  SSKJr  SSKJr  SSKJr  \" SS9\ " S	 S
\5      5       5       r	S
/r
g)zDiffLlama model configurationé    )Ústricté   )ÚPreTrainedConfig)ÚRopeParameters)Úauto_docstringzkajuma/DiffLlama-0.3B-handcut)Ú
checkpointc                   ó˜  ^ • \ rS rSr% SrSrS/rSr\\	S'   Sr
\\	S'   S	r\\	S
'   Sr\\	S'   Sr\\	S'   Sr\S-  \	S'   Sr\\	S'   Sr\\	S'   Sr\\	S'   Sr\\	S'   Sr\\	S'   Sr\S-  \	S'   Sr\S-  \	S'   Sr\\\   -  S-  \	S'   Sr\\	S '   Sr\\-  S-  \	S!'   Sr\\	S"'   S#r \\-  S-  \	S$'   S%r!\S-  \	S&'   Sr"\S-  \	S''   U 4S( jr#S)r$U =r%$ )*ÚDiffLlamaConfigé   aû  
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                 óÐ   >• U R                   c  U R                  U l         U R                  b  U R                  OU R                  U R                  -  U l        [        TU ]  " S0 UD6  g )N© )r   r   r&   r   ÚsuperÚ__post_init__)ÚselfÚkwargsÚ	__class__s     €ÚÃC:\Users\johnn\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.13_qbz5n2kfra8p0\LocalCache\local-packages\Python313\site-packages\transformers/models/diffllama/configuration_diffllama.pyr*   ÚDiffLlamaConfig.__post_init__G   sU   ø€ à×#Ñ#Ñ+Ø'+×'?Ñ'?ˆDÔ$à)-¯©Ñ)B˜ŸšÈ×HXÑHXÐ\`×\tÑ\tÑHtˆŒÜ‰ÒÑ' Ó'ó    )r&   r   )&Ú__name__Ú
__module__Ú__qualname__Ú__firstlineno__Ú__doc__Ú
model_typeÚkeys_to_ignore_at_inferencer   ÚintÚ__annotations__r   r   r   r   r   r   Ústrr   r   Úfloatr   r   Úboolr   r   r    Úlistr!   r"   r   Údictr#   r$   r%   r&   r*   Ú__static_attributes__Ú__classcell__)r-   s   @r.   r
   r
      s&  ø‡ ñð$ €JØ#4Ð"5Ðà€J�ÓØ€K�ÓØ!Ð�sÓ!ØÐ�sÓØ!Ð˜Ó!Ø&*Ð˜˜t™Ó*Ø€J�ÓØ#'Ð˜SÓ'Ø#Ð�uÓ#Ø€L�%ÓØ€IˆtÓØ#€L�#˜‘*Ó#Ø €L�#˜‘*Ó Ø+,€L�#˜˜S™	‘/ DÑ(Ó,Ø %Ð˜Ó%Ø48€O�^ dÑ*¨TÑ1Ó8Ø €N�DÓ Ø,/Ð�u˜s‘{ TÑ)Ó/Ø#&€N�E˜D‘LÓ&Ø€Hˆc�D‰jÓ÷(ó (r0   r
   N)r5   Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úmodeling_rope_utilsr   Úutilsr   r
   Ú__all__r(   r0   r.   Ú<module>rF      sK   ðñ" $å .å 3Ý 1Ý #ñ Ð:Ñ;Øô1(Ð&ó 1(ó ó <ð1(ðh Ð
�r0   