Smaller but Better: Self-Paced Knowledge Distillation for Lightweight yet Effective LCMs

TL;DR

This paper introduces SODA, a self-paced knowledge distillation framework that creates lightweight yet highly effective large code models, significantly improving performance and surpassing some existing models like ChatGPT.

Contribution

The paper proposes a novel self-paced knowledge distillation method for developing lightweight code models, with a new framework and a series of models outperforming larger counterparts.

Findings

SODA improves student models by 65.96% Pass@1.

SodaCoder models outperform 15 larger LCMs.

SodaCoder-DS-6.7B surpasses ChatGPT on average Pass@1.

Abstract

Large code models (LCMs) have remarkably advanced the field of code generation. Despite their impressive capabilities, they still face practical deployment issues, such as high inference costs, limited accessibility of proprietary LCMs, and adaptability issues of ultra-large LCMs. These issues highlight the critical need for more accessible, lightweight yet effective LCMs. Knowledge distillation (KD) offers a promising solution, which transfers the programming capabilities of larger, advanced LCMs to smaller, less powerful LCMs. In this paper, we propose a novel Self-Paced knOwledge DistillAtion framework, named SODA, aiming at developing lightweight yet effective student LCMs. SODA consists of three stages in one cycle: (1) Correct-and-Fault Knowledge Delivery stage aims at improving the student models capability to recognize errors while ensuring its basic programming skill during the knowledge transferring, which involves correctness-aware supervised learning and fault-aware contrastive learning methods. (2) Multi-View Feedback stage aims at measuring the quality of results generated by the student model from two views, including model-based and static tool-based measurement, for identifying the difficult questions. (3) Feedback-based Knowledge Update stage aims at updating the student model adaptively by generating new questions at different difficulty levels, in which the difficulty levels are categorized based on the feedback in the second stage. Experimental results show that SODA improves the student model by 65.96% in terms of average Pass@1, outperforming the best baseline by 29.85%. Based on the SODA framework, we develop SodaCoder, a series of lightweight yet effective LCMs, which outperform 15 LCMs with less than or equal to 16B parameters. Notably, SodaCoder-DS-6.7B, built on DeepseekCoder-6.7B, even surpasses the prominent ChatGPT on average Pass@1.