To facilitate the research on large language models (LLMs), this paper presents a comprehensive and unified library, LLMBox, to ease the development, use, and evaluation of LLMs. This library is featured with three main merits: (1) a unified data interface that supports the flexible implementation of various training strategies, (2) a comprehensive evaluation that covers extensive tasks, datasets, and models, and (3) more practical consideration, especially on user-friendliness and efficiency. With our library, users can easily reproduce existing methods, train new models, and conduct comprehensive performance comparisons. To rigorously test LLMBox, we conduct extensive experiments in a diverse coverage of evaluation settings, and experimental results demonstrate the effectiveness and efficiency of our library in supporting various implementations related to LLMs. The detailed introduction and usage guidance can be found at https://github.com/RUCAIBox/LLMBox.
@article{arxiv.2407.05563,
title = {LLMBox: A Comprehensive Library for Large Language Models},
author = {Tianyi Tang and Yiwen Hu and Bingqian Li and Wenyang Luo and Zijing Qin and Haoxiang Sun and Jiapeng Wang and Shiyi Xu and Xiaoxue Cheng and Geyang Guo and Han Peng and Bowen Zheng and Yiru Tang and Yingqian Min and Yushuo Chen and Jie Chen and Yuanqian Zhao and Luran Ding and Yuhao Wang and Zican Dong and Chunxuan Xia and Junyi Li and Kun Zhou and Wayne Xin Zhao and Ji-Rong Wen},
journal= {arXiv preprint arXiv:2407.05563},
year = {2024}
}