Jungwhan Kim

Hello, @haileyschoelkopf, thank you for the review. I can add the a unit test related to prompt rendering. Could you please clarify if by MMLU-style unit test means that simply...

Hi! I just wanted to clarify before making corrections. You mean that removing the whitespace of all the subtasks of [leaderboard/bbh_mc](https://github.com/EleutherAI/lm-evaluation-harness/blob/main/lm_eval/tasks/leaderboard/bbh_mc/boolean_expressions.yaml#L2-L4), like this: `description: 'Evaluate the result of a random...

@haileyschoelkopf Could you please check this PR? Is there anything else that needs to be updated?