Ë
    ÜÓ^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Qwen3 model configurationé    )Ústricté   )ÚPreTrainedConfig)ÚRopeParameters)Úauto_docstringzQwen/Qwen3-8B)Ú
checkpointc            
       óö  ‡ — e Zd ZU dZdZdgZd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e
d#<   d$Zee
d%<   dZeez  dz  e
d&<   d$Zee
d'<   d$Zee
d(<   dZe	dz  e
d)<   d*Z e	e
d+<   dZ!e"e   dz  e
d,<   d-Z#ee	z  e
d.<   dZ$e	dz  e
d/<   dZ%e	dz  e
d0<   dZ&e	e"e	   z  dz  e
d1<   ˆ fd2„Z'ˆ xZ(S )3ÚQwen3Configap  
    ```python
    >>> from transformers import Qwen3Model, Qwen3Config

    >>> # Initializing a Qwen3 style configuration
    >>> configuration = Qwen3Config()

    >>> # Initializing a model from the Qwen3-8B style configuration
    >>> model = Qwen3Model(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```
    Úqwen3Úpast_key_valuesÚ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.gate_projzlayers.*.mlp.up_projzlayers.*.mlp.down_projÚ	input_idsÚinputs_embedsÚhidden_statesÚattention_mask)Úembed_tokensÚlayersÚnormi€Q Ú
vocab_sizei   Úhidden_sizei V  Úintermediate_sizeé    Únum_hidden_layersÚnum_attention_headsNÚnum_key_value_headsé€   Úhead_dimÚsiluÚ
hidden_acti €  Úmax_position_embeddingsg{®Gáz”?Úinitializer_rangeg�íµ ÷Æ°>Úrms_norm_epsTÚ	use_cacheFÚtie_word_embeddingsÚrope_parametersÚattention_biasÚuse_sliding_windowÚsliding_windowé   Úmax_window_layersÚlayer_typesg        Úattention_dropoutÚpad_token_idÚbos_token_idÚeos_token_idc                 óH  •— | j                   r| j                  nd | _        | j                  €| j                  | _        | j                  €Et        | j                  «      D �cg c]!  }| j                  �|| j                  k\  rdnd‘Œ# c}| _        t        ‰| �$  di |¤Ž y c c}w )NÚsliding_attentionÚfull_attention© )
r)   r*   r   r   r-   Úranger   r,   ÚsuperÚ__post_init__)ÚselfÚkwargsÚiÚ	__class__s      €úx/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/qwen3/configuration_qwen3.pyr8   zQwen3Config.__post_init__V   s¦   ø€ Ø59×5LÒ5L˜d×1Ò1ÐRVˆÔØ×#Ñ#Ð+Ø'+×'?Ñ'?ˆDÔ$à×ÑÐ#ô
 ˜t×5Ñ5Ó6ö	 ð ð ×&Ñ&Ð2°q¸D×<RÑ<RÒ7Rñ $à%ñ&ò ˆDÔô 	‰ÑÑ' Ó'ùò s   Á!&B))Ú__name__Ú
__module__Ú__qualname__Ú__doc__Ú
model_typeÚkeys_to_ignore_at_inferenceÚbase_model_tp_planÚbase_model_pp_planr   ÚintÚ__annotations__r   r   r   r   r   r   r!   Ústrr"   r#   Úfloatr$   r%   Úboolr&   r'   r   Údictr(   r)   r*   r,   r-   Úlistr.   r/   r0   r1   r8   Ú__classcell__)r<   s   @r=   r
   r
      s£  ø… ñð €JØ#4Ð"5Ðð &/Ø%.Ø%.Ø%EØ%EØ%.Ø"+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€HˆcÓØ€J�ÓØ#(Ð˜SÓ(Ø#Ð�uÓ#Ø€L�%ÓØ€IˆtÓØ %Ð˜Ó%Ø48€O�^ dÑ*¨TÑ1Ó8Ø €N�DÓ Ø$Ð˜Ó$Ø!%€N�C˜$‘JÓ%ØÐ�sÓØ$(€K��c‘˜TÑ!Ó(Ø%(Ð�u˜s‘{Ó(Ø#€L�#˜‘*Ó#Ø#€L�#˜‘*Ó#Ø+/€L�#˜˜S™	‘/ DÑ(Ó/÷(ð (ó    r
   N)rA   Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úmodeling_rope_utilsr   Úutilsr   r
   Ú__all__r5   rN   r=   ú<module>rT      sL   ðñ  å .å 3Ý 1Ý #ñ ˜?Ô+ØôI(Ð"ó I(ó ó ,ðI(ðX ˆ/�rN   