waterhorse1/LLM_Tree_Search

Issues

• add code about using terminal_reward of env for the search algorithm in tree.rap

  #6 opened a year ago by ziyuwan
  0

• Where and how is the model in modeling_prm.py got trained?

  #8 opened a year ago by houghtonweihu
  0

• The trained model weights

  #2 opened a year ago by Bo396543018
  4

• Missing deps + torch install issue

  #3 opened a year ago by qrdlgit
  1