put the dataset under data/
Set the hyperparameters in train.slurm
and execute bash train.slurm
Set the hyperparameters in train_verifier.slurm
and execute bash train_verifier.slurm
After fine-tuning, specify the model path in mcts.slurm
, execute bash mcts.slurm
. Note that the provided script will not produce reasonable outputs unless the generator and verifiers are properly fine-tuned.
pytorch-lightning==1.6.4
torch==1.10.0
python==3.8
cuda==11.1
Please consider citing our paper and starring this repo if you find them helpful. Thank you!
@article{zhu2022core,
title={Solving Math Word Problem via Cooperative Reasoning induced Language Models},
author={Zhu, Xinyu and Wang, Junjie and Zhang, Lin and Zhang, Yuxiang and Gan, Ruyi and Zhang, Jiaxing and Yang, Yujiu},
journal={arXiv preprint arXiv:2210.16257},
year={2022}
}
Feel free to open an issue if you have any questions.