Kunumi is a team.
Cite
Notes
Only stored in your browser.
Culprit detection on kjgpta/WhoDunIt with Holmesian style reward.
Benchmark made to evaluate llms in the Brazilian Bar Examination, using a multi-judge system.
Single turn environment for guessing user's MBTI type based on tweets
Just GSM8K with the added reward based on how shakespearean the model is.