no code implementations • 13 May 2024 • Shuo Yin, Weihao You, Zhilong Ji, Guoqiang Zhong, Jinfeng Bai
To fully leverage the advantages of our augmented data, we propose a two-stage training strategy: In Stage-1, we finetune Llama-2 on pure CoT data to get an intermediate model, which then is trained on the code-nested data in Stage-2 to get the resulting MuMath-Code.