FlagOpen/TACO

Issues

• Problem Regarding Evaluation

  #15 opened 3 months ago by chrisliu298
  1

• Taco数据集能够用于其他模型微调，比如qwen，或者是和llama factory框架适配

  #14 opened 3 months ago by zhenzhenzhizhi
  0

• 更新后的评测框架似乎存在重大bug?

  #12 opened 7 months ago by Iiji
  2

• compute_metric.py 好像有问题

  #11 opened 7 months ago by Iiji
  3

• specific performance of gpt-4

  #4 opened 7 months ago by SueJane
  1

• 数据污染问题

  #6 opened 7 months ago by Ezra-Yu
  1

• AttributeError: module 'inspect' has no attribute 'getargspec'. Did you mean: 'getargs'?

  #3 opened 7 months ago by zhangxii
  1

• 请问TACO数据集中是否包含了APPS和code_contest中的所有题目？

  #8 opened 7 months ago by Connor-Shen
  1

• 题目的难度是如何确定的？/ How is the difficulty level obtained?

  #7 opened 7 months ago by likaixin2000
  2

• Finetuned Models

  #9 opened 7 months ago by abwilf
  3

• 请问是否有在test数据集上的测试结果？

  #10 opened 7 months ago by ccccj
  4

• code-llama-7b-python精度对不上

  #5 opened 10 months ago by Connor-Shen
  3

• How to construct the appropriate output?

  #2 opened a year ago by QuaY316
  1