feidfoe's picture
Update README.md
9955b88
metadata
license: llama2
datasets:
  - meta-math/MetaMathQA
  - gsm8k
language:
  - en
pipeline_tag: text-generation

This model is a reproduction of Meta-Math. We follow the training instructions described in the original repo as much as possible with minimal modifications.

Prompt

Unlike the original Meta-math model, we do not use any instructions.

"""

Problem: {query_problem}\nSolution: {gt_solution}

"""

The {gt_solution} is provided in the training stage, whereas it is empty string in the evaluation stage.