+
    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SmallDoge/Doge-320M)Ú
checkpointc                   ó  a a€ ] tR t^t oRtRtR.tRRRRRRRR	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t	Rt
Rt^ tRtRtRtR tR!tR"tRtR#t^tR#tR"tRtR"tR#tRtR"tR$t^@tR"tR"t R%t!R#t"R#t#R#t$V 3R& lt%V3R' lt&R(t'Vt(V ;t)# ))Ú
DogeConfiga´  
keep_window_size (`int`, *optional*, defaults to 2048):
    The window size of tokens that are not dynamically masked, and dynamic masking is only performed when the sequence length exceeds this value.
is_moe (`bool`, *optional*, defaults to `False`):
    Whether to use the Cross Domain Mixture of Experts, if `True`, the MoE will inherit the MLP to initialize.

```python
>>> from transformers import DogeConfig, DogeModel

>>> # Initializing a Doge-320M style configuration
>>> configuration = DogeConfig()

>>> # Initializing a model from the Doge-320M style configuration
>>> model = DogeModel(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config
```ÚdogeÚpast_key_valueszlayers.*.self_attn.q_projÚcolwisezlayers.*.self_attn.k_projzlayers.*.self_attn.v_projzlayers.*.self_attn.dt_projÚrowwisezlayers.*.self_attn.o_projzlayers.*.mlp.gate_projzlayers.*.mlp.up_projzlayers.*.mlp.down_projzlayers.*.mlp.router_gateÚcolwise_gather_outputzlayers.*.mlp.down_embedÚrowwise_split_inputzlayers.*.mlp.up_embedÚembed_tokensÚ	input_idsÚinputs_embedsÚlayersÚhidden_statesÚattention_maskÚnormi €  i   i   g        Úsilug{®Gáz”?g�íµ ÷Æ°>TFNi @  gü©ñÒMbP?c                óf   <€ V P                   f   V P                  V n         \        SV `  ! R/ VB  R # )N© )Únum_key_value_headsÚnum_attention_headsÚsuperÚ__post_init__)ÚselfÚkwargsÚ	__class__s   &,€Úl/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/doge/configuration_doge.pyr   ÚDogeConfig.__post_init__f   s-   ø€ à×#Ñ#Ò+Ø'+×'?Ñ'?ˆDÔ$ä‰ÒÑ' Ô'ó    c                ó  <€ V ^8„  d   Qh/ S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[S[ ,          ;R&   S[;R&   S[;R&   S[;R&   S[;R	&   S[;R
&   S[ ;R&   S[S[,          R,          ;R&   S[ ;R&   S[ R,          ;R&   S[;R&   S[R,          ;R&   S[;R&   S[ R,          ;R&   S[ ;R&   S[;R&   S[ ;R&   S[ ;R&   S[;R&   S[;R&   S[;R&   S[ R,          ;R&   S[ R,          ;R&   S[ S[S[ ,          ,          R,          ;R&   # )é   Ú
vocab_sizeÚhidden_sizeÚintermediate_sizeÚnum_hidden_layersÚhidden_dropoutÚ
hidden_actÚinitializer_rangeÚrms_norm_epsÚ	use_cacheÚtie_word_embeddingsÚmax_position_embeddingsNÚrope_parametersr   r   Úattention_biasÚattention_dropoutÚmlp_biasÚsliding_windowÚkeep_window_sizeÚis_moeÚnum_expertsÚnum_experts_per_tokÚnorm_topk_probÚoutput_router_logitsÚrouter_aux_loss_coefÚpad_token_idÚbos_token_idÚeos_token_id)ÚintÚfloatÚstrÚboolr   ÚdictÚlist)ÚformatÚ__classdict__s   "€r!   Ú__annotate__ÚDogeConfig.__annotate__   sØ  ø‡ ‚ ñX ÑñY ñZ Ññ[ ñ\ Ñ!ñ] ñ^ Ññ_ ñ` ™C•KÑ%ña ñb Ññc ñd Ñ#ñe ñf Ññg ñh Ññi ñj Ñ%ñk ñl !Ñ'ñm ñn $¡dÕ*¨TÕ1Ñ8ño ñp Ñ ñq ñr ˜t�Ñ*ñs ñt Ñ ñu ñv ˜t•|Ñ)ñw ñx Ññy ñz ˜$•JÑ%ñ{ ñ| Ñ ñ} ñ~ Ññ ñ@ ÑñA ñB Ñ!ñC ñD Ñ ñE ñF Ñ&ñG ñH  Ñ'ñI ñJ ˜•*Ñ#ñK ñL ˜•*Ñ#ñM ñN ™™S�	•/ DÕ(Ñ/òO 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_planr&   r'   r(   r)   r*   r+   r,   r-   r.   r/   r0   r1   r   r   r2   r3   r4   r5   r6   r7   r8   r9   r:   r;   r<   r=   r>   r?   r   Ú__annotate_func__Ú__static_attributes__Ú__classdictcell__Ú__classcell__)r    rG   s   @@r!   r	   r	      sA  ù‡ € ñð& €JØ#4Ð"5Ðð 	$ YØ# YØ# YØ$ iØ# YØ  )Ø 	Ø  )Ø"Ð$;Ø!Ð#8ØÐ!6ðÐð 	˜+˜¨Ð(9Ð:Ø�OÐ%5Ð6¸Ð8IÐJØ�/Ð" _Ð$5Ð6ðÐð €JØ€KØ!ÐØÐØ"%€NØ€JØ#ÐØ€LØ€IØ %ÐØ#'ÐØ48€OØ ÐØ&*ÐØ €NØ&)ÐØ€HØ!%€NØ ÐØ€FØ€KØ!ÐØ €NØ!&ÐØ"'ÐØ#€LØ#€LØ+/€Lõ(÷S … 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õ, /å 3Ý 1Ý #ñ Ð0Ô1ØôL(Ð!ó L(ó ó 2ðL(ð^ ˆ.‚r#   