Ë
    ÛÓ^j9  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!swiss-ai/Apertus-8B-Instruct-2509)Ú
checkpointc            	       ó   ‡ — e Zd ZU dZdZdgZdZdddddddddœZd	gd
gfddgdgfdgdgf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d<   dZeed <   d!Zeed"<   d#Ze
dz  ed$<   d%Ze
dz  ed&<   d'Ze
ee
   z  dz  ed(<   d)Zeed*<   dZee z  dz  ed+<   d)Z!eed,<   d-Z"ee
z  ed.<   ˆ fd/„Z#ˆ xZ$S )0ÚApertusConfigaz  
    ```python
    >>> from transformers import ApertusModel, ApertusConfig

    >>> # Initializing a Apertus-8B style configuration
    >>> configuration = ApertusConfig()

    >>> # Initializing a model from the Apertus-8B style configuration
    >>> model = ApertusModel(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```ÚapertusÚpast_key_valuesç    `ãfAÚcolwiseÚreplicated_with_grad_allreduceÚrowwise)zlayers.*.self_attn.q_projzlayers.*.self_attn.k_projzlayers.*.self_attn.v_projzlayers.*.self_attn.q_normzlayers.*.self_attn.k_normzlayers.*.self_attn.o_projzlayers.*.mlp.up_projzlayers.*.mlp.down_projÚ	input_idsÚinputs_embedsÚhidden_statesÚattention_mask)Úembed_tokensÚlayersÚnormi   Ú
vocab_sizei   Úhidden_sizei 8  Úintermediate_sizeé    Únum_hidden_layersÚnum_attention_headsNÚnum_key_value_headsÚxieluÚ
hidden_acti   Úmax_position_embeddingsg{®Gáz”?Úinitializer_rangegñhãˆµøä>Úrms_norm_epsTÚ	use_cacher   Úpad_token_idé   Úbos_token_idé   Úeos_token_idFÚtie_word_embeddingsÚrope_parametersÚattention_biasg        Úattention_dropoutc                 ó’   •— | j                   €| j                  | _         | j                  €dddddddœ| _        t        ‰| �  di |¤Ž y )	NÚllama3r   g       @i    g      ð?g      @)Ú	rope_typeÚ
rope_thetaÚfactorÚ original_max_position_embeddingsÚlow_freq_factorÚhigh_freq_factor© )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/apertus/configuration_apertus.pyr8   zApertusConfig.__post_init__S   sW   ø€ Ø×#Ñ#Ð+Ø'+×'?Ñ'?ˆDÔ$à×ÑÐ'à%Ø(ØØ48Ø#&Ø$'ñ$ˆDÔ ô 	‰ÑÑ' Ó'ó    )%Ú__name__Ú
__module__Ú__qualname__Ú__doc__Ú
model_typeÚkeys_to_ignore_at_inferenceÚdefault_thetaÚbase_model_tp_planÚbase_model_pp_planr   ÚintÚ__annotations__r   r   r   r   r   r    Ústrr!   r"   Úfloatr#   r$   Úboolr%   r'   r)   Úlistr*   r+   r   Údictr,   r-   r8   Ú__classcell__)r;   s   @r<   r
   r
      sb  ø… ñð €JØ#4Ð"5ÐØ€Mà%.Ø%.Ø%.Ø%EØ%EØ%.Ø )Ø"+ñ	Ðð &˜¨Ð(9Ð:Ø#Ð%5Ð6¸Ð8IÐJØ!Ð" _Ð$5Ð6ñÐð €J�ÓØ€K�ÓØ"Ð�sÓ"ØÐ�sÓØ!Ð˜Ó!Ø&*Ð˜˜t™Ó*Ø€J�ÓØ#(Ð˜SÓ(Ø#Ð�uÓ#Ø€L�%ÓØ€IˆtÓØ €L�#˜‘*Ó Ø €L�#˜‘*Ó Ø+,€L�#˜˜S™	‘/ DÑ(Ó,Ø %Ð˜Ó%Ø48€O�^ dÑ*¨TÑ1Ó8Ø €N�DÓ Ø%(Ð�u˜s‘{Ó(÷(ð (r=   r
   N)
Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úmodeling_rope_utilsr   Úutilsr   r
   Ú__all__r6   r=   r<   ú<module>rT      sL   ðõ* /å 3Ý 1Ý #ñ Ð>Ô?ØôB(Ð$ó B(ó ó @ðB(ðJ Ð
�r=   