YuLan: An Open-source Large Language Model

TL;DR

YuLan is an open-source 12-billion-parameter language model trained on diverse multilingual data, employing a three-stage curriculum learning approach, achieving state-of-the-art performance in English and Chinese benchmarks.

Contribution

This paper introduces YuLan, a large open-source multilingual LLM with a detailed training methodology including curriculum learning and instruction tuning, advancing transparency and reproducibility.

Findings

YuLan achieves performance comparable to state-of-the-art LLMs.

The three-stage training enhances multilingual and complex knowledge learning.

Open-source code and models promote further research.

Abstract

Large language models (LLMs) have become the foundation of many applications, leveraging their extensive capabilities in processing and understanding natural language. While many open-source LLMs have been released with technical reports, the lack of training details hinders further research and development. This paper presents the development of YuLan, a series of open-source LLMs with $12$ billion parameters. The base model of YuLan is pre-trained on approximately $1.7$T tokens derived from a diverse corpus, including massive English, Chinese, and multilingual texts. We design a three-stage pre-training method to enhance YuLan's overall capabilities. Subsequent phases of training incorporate instruction-tuning and human alignment, employing a substantial volume of high-quality synthesized data. To facilitate the learning of complex and long-tail knowledge, we devise a curriculum-learning framework throughout across these stages, which helps LLMs learn knowledge in an easy-to-hard manner. YuLan's training is finished on Jan, 2024 and has achieved performance on par with state-of-the-art LLMs across various English and Chinese benchmarks. This paper outlines a comprehensive technical roadmap for developing LLMs from scratch. Our model and codes are available at https://github.com/RUC-GSAI/YuLan-Chat.