---
license: mit
language:
- en
metrics:
- accuracy
pipeline_tag: text-generation
---
# MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning

Paper: [https://arxiv.org/pdf/2310.03731.pdf](https://arxiv.org/pdf/2310.03731.pdf)

Repo: [https://github.com/mathllm/MathCoder](https://github.com/mathllm/MathCoder)


## Introduction
We introduce MathCoder, a series of open-source large language models (LLMs) specifically tailored for general math problem-solving.

| Base Model: Llama-2                                           	| Base Model: Code Llama                                                |
|-------------------------------------------------------------------|-----------------------------------------------------------------------|
|  [MathCoder-L-7B](https://huggingface.co./MathLLM/MathCoder-L-7B)  |  [MathCoder-CL-7B](https://huggingface.co./MathLLM/MathCoder-CL-7B)   	|
|  [MathCoder-L-13B](https://huggingface.co./MathLLM/MathCoder-L-13B)  |  [MathCoder-CL-34B](https://huggingface.co./MathLLM/MathCoder-CL-34B)   	|


## Training Data
The models are trained on the [MathCodeInstruct](https://huggingface.co./MathLLM/MathCodeInstruct) Dataset.


## Training Procedure
The models are fine-tuned with the MathCodeInstruct dataset using the original Llama-2 and CodeLlama models as base models. Check out our paper and repo for more details.

## Evaluation

<br>
<div align="center">
  <img src="result.png" width="100%" title="Result Figure">
</div>



## Usage
You can use the models through Huggingface's Transformers library. Use the pipeline function to create a text-generation pipeline with the model of your choice, then feed in a math problem to get the solution.
Check our Github repo for datails.


## Citation
Please cite the paper if you use our data, model or code.

```
@misc{wang2023mathcoder,
      title={MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning}, 
      author={Ke Wang and Houxing Ren and Aojun Zhou and Zimu Lu and Sichun Luo and Weikang Shi and Renrui Zhang and Linqi Song and Mingjie Zhan and Hongsheng Li},
      year={2023},
      eprint={2310.03731},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}
```