Spaces:

open-llm-leaderboard

/

open_llm_leaderboard

like 11.2k

Running on CPU Upgrade

Hello Open LLM LB Team,

Thanks for taking time to read this discussion, Could you please check why the Latest results from some of model eval runs are not updated on Leaderboard/Content repo?

The https://huggingface.co/datasets/open-llm-leaderboard/contents doesn't show any of below models eval runs which can be found below:

https://huggingface.co/datasets/open-llm-leaderboard/pankajmathur__orca_mini_v7_72b-details
https://huggingface.co/datasets/open-llm-leaderboard/pankajmathur__orca_mini_v2_7b-details
https://huggingface.co/datasets/open-llm-leaderboard/pankajmathur__orca_mini_v6_8b_dpo-details
https://huggingface.co/datasets/open-llm-leaderboard/pankajmathur__orca_mini_v5_8b_dpo-details
https://huggingface.co/datasets/open-llm-leaderboard/pankajmathur__Al_Dente_v1_8b-details

P.S.: They were all finished within 24 hour window, not sure if that's the reason.

Regards,
Pankaj