[ flag ] udkai/Garrulus

#525
by HDiffusion - opened

This model is self reported as contaminated with Winogrande so it should be flagged. This model shows some very interesting insights about how contamination effects other benchmarks, but obviously it needs to be flagged so that it doesn't get used or merged mistakenly.

Open LLM Leaderboard org
clefourrier changed discussion status to closed
Open LLM Leaderboard org

Thanks for the report!

Sign up or log in to comment