ó
    ˆŽ¡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Mixtral model configurationé    )Ústricté   )ÚPreTrainedConfig)ÚRopeParameters)Úauto_docstringzmistralai/Mixtral-8x7B-v0.1)Ú
checkpointc                   ó  ^ • \ rS rSr% SrSrS/rSrSSSSSSS	S
.rS/S/4SS/S/4S/S/4S.r	SSSS	S.r
SS0rSr\\S'   Sr\\S'   Sr\\S'   Sr\\S'   Sr\\S'   Sr\\S'   S r\S -  \S!'   S"r\\S#'   S$r\\S%'   S&r\\S''   S(r\\S)'   S*r\\S+'   S r\S -  \S,'   S-r\S -  \S.'   S/r\\ \   -  S -  \S0'   S1r!\\S2'   S r"\S -  \S3'   S4r#\\-  \S5'   S/r$\\S6'   Sr%\\S'   S1r&\\S7'   S8r'\\S9'   S4r(\\S:'   S r)\*\+-  S -  \S;'   U 4S< jr,S=r-U =r.$ )>ÚMixtralConfigé   a`  
Example:

```python
>>> from transformers import MixtralModel, MixtralConfig

>>> # Initializing a Mixtral 7B style configuration
>>> configuration = MixtralConfig()

>>> # Initializing a model from the Mixtral 7B style configuration
>>> model = MixtralModel(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config
```ÚmixtralÚpast_key_valuesg    €„.AÚcolwiseÚrowwiseÚpacked_colwiseÚmoe_tp_experts)zlayers.*.self_attn.q_projzlayers.*.self_attn.k_projzlayers.*.self_attn.v_projzlayers.*.self_attn.o_projú!layers.*.mlp.experts.gate_up_projúlayers.*.mlp.experts.down_projúlayers.*.mlp.expertsÚ	input_idsÚinputs_embedsÚhidden_statesÚattention_mask)Úembed_tokensÚlayersÚnormÚ	ep_routerÚgrouped_gemm)zlayers.*.mlp.gater   r   r   Únum_expertsÚnum_local_expertsi }  Ú
vocab_sizei   Úhidden_sizei 8  Úintermediate_sizeé    Únum_hidden_layersÚnum_attention_headsé   Únum_key_value_headsNÚhead_dimÚsiluÚ
hidden_acti   Ú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sliding_windowg        Úattention_dropoutÚnum_experts_per_tokÚoutput_router_logitsgü©ñÒMbP?Úrouter_aux_loss_coefÚrouter_jitter_noiseÚrope_parametersc                 ób   >• U R                   c  U R                  U l         [        TU ]  " S0 UD6  g )N© )r'   r%   ÚsuperÚ__post_init__)ÚselfÚkwargsÚ	__class__s     €Ú¿C:\Users\johnn\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.13_qbz5n2kfra8p0\LocalCache\local-packages\Python313\site-packages\transformers/models/mixtral/configuration_mixtral.pyr?   ÚMixtralConfig.__post_init__]   s-   ø€ Ø×#Ñ#Ñ+Ø'+×'?Ñ'?ˆDÔ$ä‰ÒÑ' Ó'ó    )r'   )/Ú__name__Ú
__module__Ú__qualname__Ú__firstlineno__Ú__doc__Ú
model_typeÚkeys_to_ignore_at_inferenceÚdefault_thetaÚbase_model_tp_planÚbase_model_pp_planÚbase_model_ep_planÚattribute_mapr    ÚintÚ__annotations__r!   r"   r$   r%   r'   r(   r*   Ústrr+   r,   Úfloatr-   r.   Úboolr/   r1   r3   Úlistr4   r5   r6   r7   r   r8   r9   r:   r;   r   Údictr?   Ú__static_attributes__Ú__classcell__)rB   s   @rC   r
   r
      sÅ  ø‡ ñð  €JØ#4Ð"5ÐØ€Mà%.Ø%.Ø%.Ø%.Ø-=Ø*3Ø 0ñÐð &˜¨Ð(9Ð:Ø#Ð%5Ð6¸Ð8IÐJØ!Ð" _Ð$5Ð6ñÐð )Ø-;Ø*8Ø 0ñ	Ðð #Ð$7Ð8€Mà€J�ÓØ€K�ÓØ"Ð�sÓ"ØÐ�sÓØ!Ð˜Ó!Ø Ð˜Ó Ø€Hˆc�D‰jÓØ€J�ÓØ#,Ð˜SÓ,Ø#Ð�uÓ#Ø€L�%ÓØ€IˆtÓØ#€L�#˜‘*Ó#Ø €L�#˜‘*Ó Ø+,€L�#˜˜S™	‘/ DÑ(Ó,Ø %Ð˜Ó%Ø!%€N�C˜$‘JÓ%Ø%(Ð�u˜s‘{Ó(Ø Ð˜Ó ØÐ�sÓØ!&Ð˜$Ó&Ø"'Ð˜%Ó'Ø!$Ð˜Ó$Ø48€O�^ dÑ*¨TÑ1Ó8÷(ó (rE   r
   N)rJ   Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úmodeling_rope_utilsr   Úutilsr   r
   Ú__all__r=   rE   rC   Ú<module>r`      sN   ðñ "å .å 3Ý 1Ý #ñ Ð8Ñ9ØôH(Ð$ó H(ó ó :ðH(ðV Ð
�rE   