Spaces:
Running
on
CPU Upgrade
Is `HuggingFaceH4/human_eval_llm_leaderboard` abandoned?
Is https://huggingface.co/spaces/HuggingFaceH4/human_eval_llm_leaderboard abandoned? I saw it malfunctioning for a while. I also left a message to the maintainer but nobody replies.
I know that there have been some changes in the team working on this leaderboard, so I'm unsure.
@lewtun
@edbeeching
might know?
The new models are not being mentioned in the leaderboard. New models I would like to see appear are Zephyr beta, airoboros (mistral2.2 something like that) and dolphin2.2 and hermes (mistral).
To avoid confusion for other users, and since this issue is unrelated with the OpenLLMLeaderboard, I'll close it.
I trust Lewis or Ed will come by and answer it once they are on.
Hello @zhiminy @supercharge19 ! For human evaluation we recommend checking out LMSYS's Chatbot Arena(https://chat.lmsys.org) which is actively maintained and the community standard in this domain. Our human eval leaderboard is now archived, but kept public for reference :)