see our paper in https://arxiv.org/abs/2309.12284

View the project page: https://meta-math.github.io/

Note

All MetaMathQA data are augmented from the training sets of GSM8K and MATH. None of the augmented data is from the testing set.

You can check the original_question in meta-math/MetaMathQA, each item is from the GSM8K or MATH train set.

Model Details

MetaMath-Llemma-7B is fully fine-tuned on the MetaMathQA datasets and based on the powerful Llemma-7B model. It is glad to see using MetaMathQA datasets and change the base model from llama-2-7B to Llemma-7B can boost the MATH performance from 19.8 to 30.0.

Installation

pip install transformers==4.35.0
pip install torch==2.0.1
pip install sentencepiece==0.1.99
pip install tokenizers==0.13.3
pip install accelerate==0.21.0
pip install bitsandbytes==0.40.0
pip install vllm
pip install fraction
pip install protobuf

Model Usage

prompting template:

'''

"Below is an instruction that describes a task. " "Write a response that appropriately completes the request.\n\n" "### Instruction:\n{instruction}\n\n### Response: Let's think step by step."

'''

where you need to use your query question to replace the {instruction}

Experiments

Citation

@article{yu2023metamath,
  title={MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models},
  author={Yu, Longhui and Jiang, Weisen and Shi, Han and Yu, Jincheng and Liu, Zhengying and Zhang, Yu and Kwok, James T and Li, Zhenguo and Weller, Adrian and Liu, Weiyang},
  journal={arXiv preprint arXiv:2309.12284},
  year={2023}
}