+
    œ°³j¾  ã                   ót   € ^ RI Ht ^RIHt ^RIHt ^RIHt ]! RR7      ] ! R R]4      4       4       tR.t	R	# )
é    )Ústrict)ÚPreTrainedConfig)ÚRopeParameters)Úauto_docstringzMiniMaxAI/MiniMax-Text-01-hf)Ú
checkpointc                   ó6  a a€ ] tR t^t oRtRtR.tRtRRRRRRR	R
RRRR
RR/tRR.R.3RRR.R.3RR.R.3/t	RRRRRRRR/t
RR/tRtRtRt^ t^ t^tRtR tR+tR!tR"tR#tRt^t^tR$tRtR%t^t^tR$t R&t!R%t"Rt#Rt$R't%^t&^t'^t(^t)^t*^t+V 3R( lt,V3R) lt-R*t.Vt/V ;t0# ),ÚMiniMaxConfigaA  
block_size (`int`, *optional*, defaults to 256):
    The length of each attention block, determining how queries, keys, and values
    are grouped and processed for intra- and inter-block attention.
full_attn_alpha_factor (`float`, *optional*, defaults to 1):
    Weight for residual value in residual connection after normal attention.
full_attn_beta_factor (`float`, *optional*, defaults to 1):
    Weight for hidden state value in residual connection after normal attention.
linear_attn_alpha_factor (`float`, *optional*, defaults to 1):
    Weight for residual value in residual connection after lightning attention.
linear_attn_beta_factor (`float`, *optional*, defaults to 1):
    Weight for hidden state value in residual connection after lightning attention.
mlp_alpha_factor (`float`, *optional*, defaults to 1):
    Weight for residual value in residual connection after MLP.
mlp_beta_factor (`float`, *optional*, defaults to 1):
    Weight for hidden state value in residual connection after MLP.

```python
>>> from transformers import MiniMaxModel, MiniMaxConfig

>>> # Initializing a MiniMax style configuration
>>> configuration = MiniMaxConfig()

>>> # Initializing a model from the MiniMax style configuration
>>> model = MiniMaxModel(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config
```ÚminimaxÚpast_key_valuesg    €„.Azlayers.*.self_attn.q_projÚcolwisezlayers.*.self_attn.k_projzlayers.*.self_attn.v_projzlayers.*.self_attn.o_projÚrowwisez!layers.*.mlp.experts.gate_up_projÚpacked_colwisezlayers.*.mlp.experts.down_projzlayers.*.mlp.expertsÚmoe_tp_expertsÚembed_tokensÚ	input_idsÚinputs_embedsÚlayersÚhidden_statesÚattention_maskÚnormzlayers.*.mlp.gateÚ	ep_routerÚgrouped_gemmÚnum_expertsÚnum_local_expertsi }  i   i 8  NÚsilug{®Gáz”?gñhãˆµøä>TFg        gü©ñÒMbP?é   c                ó"  <€ V P                   f   V P                  V n         V P                  fL   \        V P                  4       Uu. uF&  p\        V^,           ^,          4      '       d   RMRNK(  	  upV n        \        SV `  ! R/ VB  R # u upi )NÚfull_attentionÚlinear_attention© )Únum_key_value_headsÚnum_attention_headsÚlayer_typesÚrangeÚnum_hidden_layersÚboolÚsuperÚ__post_init__)ÚselfÚkwargsÚiÚ	__class__s   &, €Úr/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/minimax/configuration_minimax.pyr(   ÚMiniMaxConfig.__post_init__x   sƒ   ø€ Ø×#Ñ#Ò+Ø'+×'?Ñ'?ˆDÔ$à×ÑÒ#äW\Ð]a×]sÑ]sÔWtó ÙWtÐRS¤D¨!¨a­%°1­×$5Ò$5Ñ Ð;MÒMÑWtñ ˆDÔô 	‰ÒÑ' Ô'ùò	 s   Á,Bc                ó¬  <€ V ^8„  d   Qh/ S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ R,          ;R&   S[;R	&   S[ ;R
&   S[;R&   S[;R&   S[;R&   S[ R,          ;R&   S[ R,          ;R&   S[ S[S[ ,          ,          R,          ;R&   S[;R&   S[ R,          ;R&   S[S[ ,          ;R&   S[ ;R&   S[ ;R&   S[;R&   S[;R&   S[;R&   S[S[,          R,          ;R&   S[S[,          R,          ;R&   S[ ;R&   S[ S[,          ;R&   S[ S[,          ;R&   S[ S[,          ;R&   S[ S[,          ;R&   S[ S[,          ;R &   S[ S[,          ;R!&   # )"é   Ú
vocab_sizeÚhidden_sizeÚintermediate_sizer%   r"   r!   NÚhead_dimÚ
hidden_actÚmax_position_embeddingsÚinitializer_rangeÚrms_norm_epsÚ	use_cacheÚpad_token_idÚbos_token_idÚeos_token_idÚtie_word_embeddingsÚsliding_windowÚattention_dropoutÚnum_experts_per_tokr   Úoutput_router_logitsÚrouter_aux_loss_coefÚrouter_jitter_noiseÚrope_parametersr#   Ú
block_sizeÚfull_attn_alpha_factorÚfull_attn_beta_factorÚlinear_attn_alpha_factorÚlinear_attn_beta_factorÚmlp_alpha_factorÚmlp_beta_factor)ÚintÚstrÚfloatr&   Úlistr   Údict)ÚformatÚ__classdict__s   "€r-   Ú__annotate__ÚMiniMaxConfig.__annotate__   s1  ø‡ ‚ ñv Ññw ñx Ññy ñz Ñ"ñ{ ñ| Ññ} ñ~ Ñ!ñ ñ@ Ñ ñA ñB �D�jÑñC ñD ÑñE ñF !Ñ,ñG ñH Ñ#ñI ñJ ÑñK ñL ÑñM ñN ˜•*Ñ#ñO ñP ˜•*Ñ ñQ ñR ™™S�	•/ DÕ(Ñ,ñS ñT Ñ%ñU ñV ˜$•JÑ%ñW ñX ™s•{Ñ(ñY ñZ Ñ ñ[ ñ\ Ññ] ñ^ Ñ&ñ_ ñ`  Ñ'ña ñb Ñ$ñc ñd $¡dÕ*¨TÕ1Ñ8ñe ñf ‘c•˜TÕ!Ñ(ñg ñh Ññi ñj  ¡%�KÑ+ñk ñl ¡�;Ñ*ñm ñn "¡E�kÑ-ño ñp !¡5�[Ñ,ñq ñr ™E•kÑ%ñs ñt ™5•[Ñ$òu ó    )r#   r!   i   )1Ú__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_mapr1   r2   r3   r%   r"   r!   r4   r5   r6   r7   r8   r9   r:   r;   r<   r=   r>   r?   r@   r   rA   rB   rC   rD   r#   rE   rF   rG   rH   rI   rJ   rK   r(   Ú__annotate_func__Ú__static_attributes__Ú__classdictcell__Ú__classcell__)r,   rR   s   @@r-   r	   r	      ss  ù‡ € ñð< €JØ#4Ð"5ÐØ€Mà# YØ# YØ# YØ# YØ+Ð-=Ø(¨)ØÐ 0ðÐð 	˜+˜¨Ð(9Ð:Ø�OÐ%5Ð6¸Ð8IÐJØ�/Ð" _Ð$5Ð6ðÐð 	˜[Ø+¨^Ø(¨.ØÐ 0ð	Ðð #Ð$7Ð8€Mà€JØ€KØ"ÐØÐØ!ÐØ ÐØ€HØ€JØ#,ÐØ#ÐØ€LØ€IØ#€LØ €LØ+,€LØ %ÐØ!%€NØ%(ÐØ ÐØÐØ!&ÐØ"'ÐØ!$ÐØ48€OØ$(€KØ€JØ*+ÐØ)*ÐØ,-ÐØ+,ÐØ$%ÐØ#$€Oõ	(÷y … rU   r	   N)
Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úmodeling_rope_utilsr   Úutilsr   r	   Ú__all__r    rU   r-   Ú<module>rk      sK   ðõ* /å 3Ý 1Ý #ñ Ð9Ô:Øôc(Ð$ó c(ó ó ;ðc(ðL Ð
‚rU   