Year: 2025
Type: preprint
Abstract: The challenge of reducing the size of Large Language Models (LLMs) while maintaining their performance has gained significant attention. However, existing methods, such as model distillation and transfer learning, often fail to achieve high accuracy. To address this limitation, we introduce the Branch-Merge distillation approach, which enhances model compression through two phases: (1) the Branch Phase, where knowledge from a large teacher model is \textit{selectively distilled} into specialized student models via domain-specific supervised fine-tuning (SFT); And (2) the Merge Phase, where these student models are merged to enable cross-domain knowledge transfer and improve generalization. We validate our distillation approach using DeepSeek-R1 as the teacher and DeepSeek-R1-Distill-Qwen-32B as the student. The resulting merged model, TinyR1-32B-Preview, outperforms its counterpart DeepSeek-R1-Distill-Qwen-32B across multiple benchmarks, including Mathematics (+5.5 points), Coding (+4.4 points) and Science (+2.9 points), while achieving near-equal performance to DeepSeek-R1 on AIME 2024. The Branch-Merge distillation approach provides a scalable solution for creating smaller, high-performing LLMs with reduced computational cost and time.
Source: arXiv (Cornell University)
Authors: Sun, Lin, Zhao, Guangxiang, Jian, Xiaoqi, Wu, Yuhan, Lin, Weihong, Zhu, Yongfu, Shi, Qilong, Jia, Change, Yuan, Aomufei, Tian, Yuxuan, Zhang, Linglin, Wu, Jinzhu, Ran, Junfeng, Hu, Sai-er, Jiang, Zihan, Zhou, Junting, Liu, Wenrui, Xiao, Xusen, Cui, Bin, Yang, Tong, Zhang, Xiangzheng
Institution: Peking University
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6966841588