Request for rerun: nlpguy/Hermes-low-tune-4

#549
by nlpguy - opened

It appears that the inital run has failed, but running the evaluation harness myself on the mmlu benchmark worked, so I would like to request a rerun.

Nevermind: I was looking at my submission with the false precision, the one with the correct one is still running: https://huggingface.co/datasets/open-llm-leaderboard/requests/blob/main/nlpguy/Hermes-low-tune-4_eval_request_False_bfloat16_Original.json

nlpguy changed discussion status to closed

Sign up or log in to comment