open-llm-leaderboard/open_llm_leaderboard · Missing evaluations on the leaderboard

Apr 7

Hi,

I got a message that my model had finished evaluation almost a week ago:
https://huggingface.co/datasets/open-llm-leaderboard/results/blob/main/Infinimol/miiqu-f16/results_2024-04-01T10-40-55.195466.json

But I see its still not on the leaderboard. I went back and checked for another well know model, Miqu:
https://huggingface.co/datasets/open-llm-leaderboard/results/blob/main/152334H/miqu-1-70b-sf/results_2024-02-02T02-50-47.877017.json

On the model card for Miqu, I can see the results, but not on the leaderboard. Is there a reason for this?

alozowski

Open LLM Leaderboard org Apr 8

Hi dnhkng!

I've checked the leaderboard, you can find 'Infinimol/miiqu-f16' model by unchecking the "contains a merge/moerge". You can also find '152334H/miqu-1-70b-sf' model by unchecking "private or deleted"

I'll close this issue now, please reopen it in case of other questions :)

alozowski changed discussion status to closed Apr 8