Reproducabiliy of Evaluation

#1
by DRXD1000 - opened

Hey guys, great work as always!

I was wondering, is there a pipeline/ configuration you could share to enable the community to reproduce your evaluation?

VAGO solutions org

Hi @DRXD1000

for reproducibility we are using the this guide: https://huggingface.co/docs/leaderboards/open_llm_leaderboard/about and --apply_chattemplate

DRXD1000 changed discussion status to closed

Sign up or log in to comment