---
license: apache-2.0
datasets:
- zd21/SciInstruct
language:
- en
---
# SciGLM: Training Scientific Language Models with Self-Reflective Instruction Annotation and Tuning

<p align="center">
📃 <a href="https://arxiv.org/abs/2401.07950" target="_blank">[SciGLM]</a> <a href="https://github.com/THUDM/SciGLM" target="_blank">[GitHub]</a> <br>
</p>

**SciGLM** is a suite of scientific language models able to conduct college-level scientific reasoning. Central to our approach is a novel self-reflective instruction annotation framework to address the data scarcity challenge in the science domain. This framework leverages existing LLMs to generate step-by-step reasoning for unlabelled scientific questions, followed by a process of self-reflective critic-and-revise. Applying this framework, we curated SciInstruct, a diverse and high-quality dataset encompassing physics, chemistry, math, and formal proofs.

## **SciInstruct**

We construct the SciInstruct as follows:

| Subject  |  Math  | Physics\& Chemistry | Formal Proofs (Lean) | Total   |
| --- | ---- | --------- | ------- | --- |
| # Number | 89,934 |       123,869       |        40,248        | 254,051 |

We release our data and model for public use. If you wish to use SciInstruct or SciGLM, you can download them from the following links.

Download data:
[[Google Drive](https://drive.google.com/file/d/1UlvMEau9659BoBxbMG6sk-oKaiIIO-hJ/view?usp=sharing)]
[[Tsinghua Cloud](https://cloud.tsinghua.edu.cn/d/da691b9466544d55be8e/)]

Download model:
[[Hugging Face](https://huggingface.co/zd21/SciGLM-6B)]

## **Training & Inference**

### **Fine-tuning**
You can use the SciGLM model through Huggingface's Transformers library. 

```
git clone https://github.com/THUDM/SciGLM.git
cd SciGLM
pip install -r requirements.txt
```

To train the 6B model, run:
```
bash /path/training/finetune.sh
```

### Inference
```
cd /path/to/inference
python cli_demo.py
```

## **Citation**

If you find our work helpful, please kindly cite our paper:

```
@article{zhang2024sciglm,
  title={Sciglm: Training scientific language models with self-reflective instruction annotation and tuning},
  author={Zhang, Dan and Hu, Ziniu and Zhoubian, Sining and Du, Zhengxiao and Yang, Kaiyu and Wang, Zihan and Yue, Yisong and Dong, Yuxiao and Tang, Jie},
  journal={arXiv preprint arXiv:2401.07950},
  year={2024}
}
```