JiuZhang3.0-8x7B

<h1 align="center"> JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models </h1> <p align="center"> <a href="https://arxiv.org/abs/2405.14365"><b>[Paper]</b></a> • <a href="https://github.com/RUCAIBox/JiuZhang3.0"><b>[GitHub]</b></a> • <a href="https://huggingface.co/collections/ToheartZhang/jiuzhang30-66508be8be5a61de47101655#/"><b>[Models]</b></a> • <a href="https://huggingface.co/collections/ToheartZhang/jiuzhang30-corpus-665092209525389ad7a2289a"><b>[Data]</b></a> </p>

Introduction

JiuZhang3.0 is a series of fine-tuned models for math reasoning continually pre-trained on corpus synthesized by our carefully trained small LLM.

Experimental Results

For more evaluation results, please refer to the Paper

Evaluation

Natural Language Reasoning

## Question
{question}

## Solution
{solution}

Tool Manipulation

## Question
{question}

## Code Solution
{solution}

Citation

If you find this repository helpful, please consider citing our paper:

@article{zhou2024jiuzhang30,
      title={JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models}, 
      author={Kun Zhou and Beichen Zhang and Jiapeng Wang and Zhipeng Chen and Wayne Xin Zhao and Jing Sha and Zhichao Sheng and Shijin Wang and Ji-Rong Wen},
      year={2024},
}