Commit History

  1. fix: conflicts in result loading Running

    booydar
    90b74f9
  2. fix: models from main repo; handle nan columns

    booydar
    701a854

  1. rename avg->avg(qa1-5) and pin model_name column

    43b9e03

  1. cleanup

    booydar
    4490eb8
  2. add 10M results & prettify naming & do not display models with few evals on the avg tab

    booydar
    4821c71

  1. Clarify naming

    Verified signature
    275a638
  2. Fill in missing result scores

    Verified signature
    3aac311

  1. remove duplicates and change colors

    4bec130
  2. adjuct table width

    d3e6b02
  3. group results by max eval length

    b54190c

  1. upd requirements

    7a82a99
  2. upd requirements

    6a1f9e9
  3. upd requirements

    f1a3bae
  4. upd requirements

    5a48266
  5. upd dockerfile

    ca585bc
  6. add leaderboard

    76050e6
  7. initial commit

    Verified signature
    467a0a0