MuPT: A Generative Symbolic Music Pretrained Transformer

Xingwei Qu, Yuelin Bai, Yinghao Ma, Ziya Zhou, Ka Man Lo, Jiaheng Liu, Ruibin Yuan, Lejun Min, Xueling Liu, Tianyu Zhang, du, Shuyue Guo, yimingliang, Yizhi Li, Shangda Wu, Junting Zhou, TY.Zheng, Ziyang Ma, Fengze Han, HKUST Audio, Gus Xia, Emmanouil Benetos, Xiang Yue, Chenghua Lin, Xu Tan, Wenhao Huang, Wenhu Chen, Jie Fu, Ge Zhang

MuPT: A Generative Symbolic Music Pretrained Transformer: 16 upvotes on Hugging Face Daily Papers, #5 of 13 papers on 2024-04-10. Day-by-day upvote history.

In this paper, we explore the application of Large Language Models (LLMs) to the pre-training of music. While the prevalent use of MIDI in music modeling is well-established, our findings suggest that LLMs are inherently more compatible with ABC Notation, which aligns more closely with their design and strengths, thereby enhancing the model's performance in musical composition. To address the challenges associated with misaligned measures from different tracks during generation, we propose the development of a Synchronized Multi-Track ABC Notation (SMT-ABC Notation), which aims to preserve coherence across multiple musical tracks. Our contributions include a series of models capable of handling up to 8192 tokens, covering 90\% of the symbolic music data in our training set. Furthermore, we explore the implications of the Symbolic Music Scaling Law (SMS Law) on model performance. The results indicate a promising direction for future research in music generation, offering extensive resources for community-led research through our open-source contributions.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.