zhentingqi/rStar

Issues

• How the `potential_score` work

  #12 opened 2 months ago by beishangeyu
  3

• Data

  #10 opened 2 months ago by repo-gardener
  1

• Could you provide the parameter configuration used to obtain the results in the paper?

  #11 opened 3 months ago by ChenYuhan00
  3

• Why can't I run the code? I followed all the steps in the readme.md exactly.

  #9 opened 3 months ago by isxychao
  3

• Why are the results of Llama-3-8B-Instruct on MATH500 so low?

  #8 opened 3 months ago by tongyx361
  0

• What does

  #6 opened 3 months ago by tongyx361
  0

• What does "the terminal node’s confidence score achieved from rollouts" mean in paper?

  #7 opened 3 months ago by tongyx361
  0

• could you recommend some classical self-play RL papers

  #4 opened 3 months ago by cmathx
  0

• Add open-source license (MIT)

  #2 opened 4 months ago by casper-hansen
  1

• I see you guide to run on local, can you give me an example running on API?

  #1 opened 4 months ago by dangyuuki123
  0