+
    œ°³jà  ã                   óx   € R t ^ 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	# )
zOLMoE model configuration)Ústrict)ÚPreTrainedConfig)ÚRopeParameters)Úauto_docstringzallenai/OLMoE-1B-7B-0924)Ú
checkpointc                   óè   a a€ ] tR t^t oRtRtR.tRR/tRRRRR	RR
RRRRRRR/tRRRRRRRR/t	Rt
RtRt^t^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^t^@tRtR t Rt!V 3R! lt"V3R" lt#R#t$Vt%V ;t&# )$ÚOlmoeConfiga  
clip_qkv (`float`, *optional*):
    If not `None`, elements of query, key and value attention states are clipped so that their
    absolute value does not exceed this value.

```python
>>> from transformers import OlmoeModel, OlmoeConfig

>>> # Initializing a OLMoE 7B A1B style configuration
>>> configuration = OlmoeConfig()

>>> # Initializing a model from the OLMoE 7B A1B style configuration
>>> model = OlmoeModel(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config
```
ÚolmoeÚpast_key_valuesÚnum_local_expertsÚnum_expertszlayers.*.self_attn.q_projÚcolwise_gather_outputzlayers.*.self_attn.k_projzlayers.*.self_attn.v_projzlayers.*.self_attn.o_projÚrowwise_split_inputz!layers.*.mlp.experts.gate_up_projÚpacked_colwisezlayers.*.mlp.experts.down_projÚrowwisezlayers.*.mlp.expertsÚmoe_tp_expertszlayers.*.mlp.gateÚ	ep_routerÚgrouped_gemmi€Ä  i   NÚsilui   g{®Gáz”?gñhãˆµøä>TigÄ  Fg        g{®Gáz„?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   &,€Ún/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/olmoe/configuration_olmoe.pyr   ÚOlmoeConfig.__post_init__Y   s-   ø€ Ø×#Ñ#Ò+Ø'+×'?Ñ'?ˆDÔ$Ü‰ÒÑ' Ô'ó    c                óÎ  <€ V ^8„  d   Qh/ S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ ;R&   S[ R,          ;R&   S[;R&   S[ ;R	&   S[;R
&   S[;R&   S[;R&   S[ R,          ;R&   S[ R,          ;R&   S[ S[S[ ,          ,          R,          ;R&   S[;R&   S[S[,          R,          ;R&   S[;R&   S[S[ ,          ;R&   S[R,          ;R&   S[ ;R&   S[ ;R&   S[;R&   S[;R&   S[;R&   # )é   Ú
vocab_sizeÚhidden_sizeÚintermediate_sizeÚnum_hidden_layersr   Nr   Ú
hidden_actÚmax_position_embeddingsÚinitializer_rangeÚrms_norm_epsÚ	use_cacheÚpad_token_idÚbos_token_idÚeos_token_idÚtie_word_embeddingsÚrope_parametersÚattention_biasÚattention_dropoutÚclip_qkvÚnum_experts_per_tokr   Úoutput_router_logitsÚrouter_aux_loss_coefÚnorm_topk_prob)ÚintÚstrÚfloatÚboolÚlistr   Údict)ÚformatÚ__classdict__s   "€r   Ú__annotate__ÚOlmoeConfig.__annotate__   s˜  ø‡ ‚ ñV ÑñW ñX ÑñY ñZ Ñ!ñ[ ñ\ Ññ] ñ^ Ñ!ñ_ ñ` ˜t�Ñ*ña ñb Ññc ñd !Ñ'ñe ñf Ñ#ñg ñh Ññi ñj Ññk ñl ˜•*Ñ ñm ñn ˜•*Ñ#ño ñp ™™S�	•/ DÕ(Ñ0ñq ñr Ñ%ñs ñt $¡dÕ*¨TÕ1Ñ8ñu ñv Ñ ñw ñx ™s•{Ñ(ñy ñz �d�lÑ!ñ{ ñ| Ñ ñ} ñ~ Ññ ñ@ Ñ&ñA ñB  Ñ&ñC ñD Ñ òE r    )r   )'Ú__name__Ú
__module__Ú__qualname__Ú__firstlineno__Ú__doc__Ú
model_typeÚkeys_to_ignore_at_inferenceÚattribute_mapÚbase_model_tp_planÚbase_model_ep_planr#   r$   r%   r&   r   r   r'   r(   r)   r*   r+   r,   r-   r.   r/   r0   r1   r2   r3   r4   r   r5   r6   r7   r   Ú__annotate_func__Ú__static_attributes__Ú__classdictcell__Ú__classcell__)r   r?   s   @@r   r   r      s  ù‡ € ñð& €JØ#4Ð"5ÐØ(¨-Ð8€Mð 	$Ð%<Ø#Ð%<Ø#Ð%<Ø#Ð%:Ø+Ð-=Ø(¨)ØÐ 0ðÐð 	˜[Ø+¨^Ø(¨.ØÐ 0ð	Ðð €JØ€KØ!ÐØÐØ!ÐØ&*ÐØ€JØ#'ÐØ#ÐØ€LØ€IØ €LØ#€LØ+0€LØ %ÐØ48€OØ €NØ%(ÐØ!€HØ ÐØ€KØ!&ÐØ"&ÐØ €Nõ(÷I … r    r   N)rF   Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úmodeling_rope_utilsr   Úutilsr   r   Ú__all__r   r    r   Ú<module>rU      sM   ðñ  å .å 3Ý 1Ý #ñ Ð5Ô6ØôE(Ð"ó E(ó ó 7ðE(ðP ˆ/‚r    