Spaces:
AIR-Bench
/
Running on CPU Upgrade

leaderboard / src /benchmarks.py

Commit History

  1. feat-add-versions-to-benchmarks (#28)⁠

    nan
    Verified signature
    3478401

  1. feat-add-v2405 (#26)⁠

    nan +1: hanhainebula
    Verified signature
    0785fe4

  1. feat-switch-to-ndcg-for-qa-0607 (#19)⁠

    nan
    Verified signature
    973bd2a

  1. feat-use-recall-as-default-metric-0605 (#18)⁠

    nan
    Verified signature
    bbfe4c1

  1. fix a bug in METRIC_LIST

    443f557

  1. disable law-zh

    Verified signature
    8b7258f

  1. Fix bug in dataset_dict: "gpt-3" -> "gpt3"

    Verified signature
    8102fce
  2. Fix bug in dataset_dict: "health" -> "healthcare"

    Verified signature
    4a44211

  1. Add msmarco for qa task

    Verified signature
    43fbed5

  1. feat: improve the layout

    nan
    32ebf18

  1. feat: adapt to the latest data format

    nan
    1a2dba5

  1. chore: clean up

    nan
    a96f80a
  2. feat: fix the table updating

    nan
    f30cbcc

  1. feat: adapt UI in app.py

    nan
    e8879cc
  2. feat: adapt the utils in app.py

    nan
    9c49811
  3. feat: seperate the qa and longdoc tasks

    nan
    9134169
  4. feat: adapt the data loading part

    nan
    8b7a945