primeai7460/hackmentor-instruction

---
license: apache-2.0
language:
- en
---
# HackMentor: Fine-Tuning Large Language Models for Cybersecurity

HackMentor is a cybersecurity LLMs (Large Language Models) focused on domain-specific data fine-tuning. This project consists of three main parts: data construction, model training, and model evaluation.

### Features
- Data construction: Methods and tools for creating domain-specific datasets (instructions & conversations) for fine-tuning LLMs.
- Model training: Techniques and processes for training LLMs on the constructed datasets.
- Model evaluation: Metrics and evaluation methodologies to assess the performance of the fine-tuned models.

### Acknowledgements
This project refers to the following open source projects, and I would like to express my gratitude to the relevant projects and research and development personnel.

- Llama by Meta
- FastChat by @im-sys
- Stanford_alpaca by @tatsu-lab

# Citation

The dataset belongs to these fellows, it only posted here for educational purposes.
```
@inproceedings{hackmentor2023,
title={HackMentor: Fine-tuning Large Language Models for Cybersecurity},
author={Jie Zhang, Hui Wen*, Liting Deng, Mingfeng Xin, Zhi Li, Lun Li, Hongsong Zhu, and Limin Sun},
booktitle={2023 IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)},
year={2023},
organization={IEEE}
}
```