Qwen2.5-72B-Instruct results?

#1
by yellowtown - opened

The evaluation of Qwen2.5-72B-Instruct model is FAILED, is there any chance to rerun it?

Hello @yellowtown

Thank you for your request. For the Open Japanese LLM Leaderboard, we are using GPU clusters from MDX (with a grant from the Japanese government). Unfortunately, Qwen 72B created a bug, due to computing limitation. We will try our best to restart the evaluation of Qwen 2.5 at 72B. : )

We appreciate your patience!

Your need to confirm your account before you can post a new comment.

Sign up or log in to comment