THUDM/ReST-MCTS

Issues

• What is VALUE_MODEL_STATE_DICT?

  #5 opened 19 days ago by dszpr
  3

• Hope for a more detailed README!

  #6 opened 19 days ago by PKUfreshman
  3

• distributed training of VM

  #8 opened 12 days ago by skepsun
  0

• how to run the code with the local model

  #7 opened 15 days ago by lambda7xx
  2

• Could you release the weights of PRM?

  #4 opened a month ago by cybisolated
  1

• Environment is missing

  #1 opened 4 months ago by XuweiyiChen
  4

• PRM "True" probability

  #3 opened a month ago by rawsh
  0

• Utilization of negative samples

  #2 opened 4 months ago by HillZhang1999
  1