openai/prm800k

Issues

• number 24 GAME

  #16 opened 4 months ago by novohool
  0

• when rating is null, what the meaning and how to use it?

  #15 opened a year ago by LeopoldACC
  0

• Question about Q*

  #14 opened a year ago by samsara3978
  0

• Question about reward model evaluation metric

  #13 opened a year ago by waterhorse1
  0

• PRM model training details

  #11 opened a year ago by bdiy90
  2

• Question about the correctness of step-level rating

  #12 opened a year ago by MrZhengXin
  3

• Questions about implmentation detail.

  #7 opened a year ago by lxww302
  3

• Question about multiple alternative steps

  #10 opened a year ago by imoneoi
  1

• open AI is not available in your country

  #6 opened a year ago by mzeada
  1

• Incorrect trainning data?

  #9 opened a year ago by lychees
  3

• Questions about the solution-level score.

  #8 opened a year ago by lxww302
  1

• PRM800K prompt

  #5 opened a year ago by jieun9851
  1

• What's the training pipeline of PRM？

  #3 opened a year ago by LeopoldACC
  2

• MathMix

  #4 opened a year ago by congchan
  1

• What is the role of active learning?

  #2 opened a year ago by YingHH1
  1

• Could we use it with commercial models?

  #1 opened 2 years ago by gotzmann
  1