tlem / utils.py

Commit History

  1. ADD: BoolQ, TurthfulQA (#5)⁠

    7e92c24

  1. fix math cornercase

    32ae64f

  1. update MATH

    4e1024e
  2. !ref suite

    3a8c0d0
  3. refactor

    9827786

  1. fix math

    6d6787f
  2. update math

    58f14b3

  1. Add new benchmark (#2)⁠

    facat +1: Cookize
    141ccb9

  1. update

    33a6f85

  1. add mmlu and cmmlu

    be1543a

  1. upd

    8af54b8