Search results

The use of quality value and weighted reward.

Status: Open.

#28 In THUDM/ReST-MCTS;

· OneCoin123 opened on Mar 3, 2026

What dataset is D_G for policy SFT in 0-th iteration and further MCTS* ?

Status: Open.

#26 In THUDM/ReST-MCTS;

· RewindL opened on Feb 7, 2025

The training of policy model

Status: Open.

#25 In THUDM/ReST-MCTS;

· RewindL opened on Feb 5, 2025

Quality of VM

Status: Open.

#24 In THUDM/ReST-MCTS;

· RewindL opened on Jan 21, 2025

Some Problem about PRM model

Status: Open.

#22 In THUDM/ReST-MCTS;

· Alex-Dou123 opened on Jan 19, 2025

How to verify the string answer for MATH dataset?

Status: Open.

#21 In THUDM/ReST-MCTS;

· yuxiaooye opened on Jan 17, 2025

What is the difference between reward_model_type=='vm' and reward_model_type=='prm'?

Status: Open.

#20 In THUDM/ReST-MCTS;

· shawnye2000 opened on Jan 10, 2025

code for generate data for policy and PRM?

about datasetdatasets of PRM and policy modeldatasets of PRM and policy model

Status: Open.

#19 In THUDM/ReST-MCTS;

· Xccanxin opened on Dec 31, 2024

是否有实际使用的产品应用此算法？

Status: Open.

#18 In THUDM/ReST-MCTS;

· RyanOvO opened on Dec 28, 2024

sft training

about training

Status: Open.

#17 In THUDM/ReST-MCTS;

· wangxichi opened on Dec 26, 2024

Issue: FileNotFoundError when running self_train_dpo.py

about datasetdatasets of PRM and policy modeldatasets of PRM and policy model

Status: Open.

#15 In THUDM/ReST-MCTS;

· KaiyuHu2001 opened on Dec 18, 2024

About the synthetic data generation

about datasetdatasets of PRM and policy modeldatasets of PRM and policy model

Status: Open.

#14 In THUDM/ReST-MCTS;

· yeppp27 opened on Dec 8, 2024