+
    œ°³j  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tencent/Youtu-LLM-2B)Ú
checkpointc                   ó  a a€ ] tR t^"t oRtRtR.t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	/ t
RtRtRt^ t^t^tRtRt^@t^€t^€tRtRtRtRtR tRtR!tR"tR tRtR t R#t!R$t"Rt#V 3R% lt$V3R& lt%R't&Vt'V ;t(# )(ÚYoutuConfigaô  
rope_interleave (`bool`, *optional*, defaults to `True`):
    Whether to interleave the rotary position embeddings.
embedding_initializer_range (`float`, *optional*):
    The standard deviation of the truncated_normal_initializer for initializing all embedding matrices.

```python
>>> from transformers import YoutuModel, YoutuConfig
>>> # Initializing a Youtu-LLM-2B style configuration
>>> configuration = YoutuConfig()
>>> # Accessing the model configuration
>>> configuration = model.config
```ÚyoutuÚpast_key_valueszlayers.*.mlp.gate_projÚcolwisezlayers.*.mlp.up_projzlayers.*.mlp.down_projÚrowwiseÚembed_tokensÚ	input_idsÚinputs_embedsÚlayersÚhidden_statesÚattention_maskÚnormzlayers.*.mlp.gateÚ	ep_routerz!layers.*.mlp.experts.gate_up_projÚgrouped_gemmzlayers.*.mlp.experts.down_projzlayers.*.mlp.expertsÚmoe_tp_expertsi õ i   i   i   i   Úsilui   Ng�íµ ÷Æ°>Ti ô iô Fg        c                ó¾  <€ V P                   f@   V P                  ^ 8w  d(   RRV P                  ,          R,          ,          V n         MRV n         V P                  ;'       g    RV P                   ,          V n        V P                  f   V P                  V n        V P
                  V P                  ,           V n        V P                  V n        \        SV `(  ! R/ VB  R # )Ng       @g      @g      à?g{®Gáz”?© )Úinitializer_rangeÚhidden_sizeÚembedding_initializer_rangeÚnum_key_value_headsÚnum_attention_headsÚqk_nope_head_dimÚqk_rope_head_dimÚqk_head_dimÚhead_dimÚsuperÚ__post_init__)ÚselfÚkwargsÚ	__class__s   &,€Ún/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/youtu/configuration_youtu.pyr%   ÚYoutuConfig.__post_init__a   s´   ø€ Ø×!Ñ!Ò)Ø×Ñ 1Ô$Ø),°°d×6FÑ6FÕ0FÈ3Õ/NÕ)N�Õ&à)-�Ô&à+/×+KÑ+K×+kÐ+kÈsÐUY×UkÑUkÕOkˆÔ(Ø×#Ñ#Ò+Ø'+×'?Ñ'?ˆDÔ$à×0Ñ0°4×3HÑ3HÕHˆÔØ×-Ñ-ˆŒÜ‰ÒÑ' Ô'ó    c                ó  <€ V ^8„  d   Qh/ S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ R,          ;R	&   S[ ;R
&   S[ R,          ;R&   S[ ;R&   S[;R&   S[ ;R&   S[R,          ;R&   S[;R&   S[;R&   S[ R,          ;R&   S[ R,          ;R&   S[ S[S[ ,          ,          R,          ;R&   S[;R&   S[S[,          R,          ;R&   S[R,          ;R&   S[;R&   S[S[ ,          R,          ;R&   S[R,          ;R&   # )é   Ú
vocab_sizer   Úintermediate_sizeÚnum_hidden_layersr   r   Úkv_lora_rankNÚq_lora_rankr!   Ú
v_head_dimr    Ú
hidden_actÚmax_position_embeddingsr   Úrms_norm_epsÚ	use_cacheÚpad_token_idÚbos_token_idÚeos_token_idÚtie_word_embeddingsÚrope_parametersÚrope_interleaveÚattention_biasÚattention_dropoutr   )ÚintÚstrÚfloatÚboolÚlistr   Údict)ÚformatÚ__classdict__s   "€r)   Ú__annotate__ÚYoutuConfig.__annotate__"   s¸  ø‡ ‚ ñJ ÑñK ñL ÑñM ñN Ñ!ñO ñP ÑñQ ñR Ñ!ñS ñT Ñ!ñU ñV ÑñW ñX �t•Ñ"ñY ñZ Ññ[ ñ\ �d•
Ñ ñ] ñ^ Ññ_ ñ` Ñña ñb !Ñ)ñc ñd ˜t•|Ñ*ñe ñf Ññg ñh Ññi ñj ˜•*Ñ#ñk ñl ˜•*Ñ%ñm ñn ™™S�	•/ DÕ(Ñ1ño ñp Ñ$ñq ñr $¡dÕ*¨TÕ1Ñ8ñs ñt ˜D•[Ñ'ñu ñv Ñ ñw ñx ™s•{ TÕ)Ñ/ñy ñz "'¨¥Ñ4ò{ r+   )r   r#   r   r   r"   ))Ú__name__Ú
__module__Ú__qualname__Ú__firstlineno__Ú__doc__Ú
model_typeÚkeys_to_ignore_at_inferenceÚbase_model_tp_planÚbase_model_pp_planÚbase_model_ep_planÚattribute_mapr.   r   r/   r0   r   r   r1   r2   r!   r3   r    r4   r5   r   r6   r7   r8   r9   r:   r;   r<   r=   r>   r?   r   r%   Ú__annotate_func__Ú__static_attributes__Ú__classdictcell__Ú__classcell__)r(   rG   s   @@r)   r	   r	   "   s(  ù‡ € ñð €JØ#4Ð"5Ðà  )Ø 	Ø  )ðÐð 	˜+˜¨Ð(9Ð:Ø�OÐ%5Ð6¸Ð8IÐJØ�/Ð" _Ð$5Ð6ðÐð 	˜[Ø+¨^Ø(¨.ØÐ 0ð	Ðð €Mà€JØ€KØ!ÐØÐØ!ÐØ!ÐØ€LØ"€KØÐØ €JØÐØ€JØ#)ÐØ&*ÐØ€LØ€IØ#€LØ%€LØ+1€LØ $ÐØ48€OØ#'€OØ €NØ,/ÐØ04Ðõ(÷ … r+   r	   N)
Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úmodeling_rope_utilsr   Úutilsr   r	   Ú__all__r   r+   r)   Ú<module>r^      sJ   ðõ6 /å 3Ý 1Ý #ñ Ð1Ô2ØôJ(Ð"ó J(ó ó 3ðJ(ðZ ˆ/‚r+   