Paper · arXiv 2408.15496
ReMamba: Equip Mamba with Effective Long-Sequence Modeling
Danlong Yuan, Jiahao Liu, Bei Li, Huishuai Zhang, Jingang Wang, Xunliang Cai, Dongyan Zhao
ReMamba addresses Mamba's long-context efficiency limitations through selective compression and adaptation, narrowing the performance gap with transformer models on long contexts.
Abstract
While the Mamba architecture demonstrates superior inference efficiency and competitive performance on short-context natural language processing (NLP) tasks, empirical evidence suggests its capacity to comprehend long contexts is limited compared to transformer-based models. In this study, we investigate the long-context efficiency issues of the Mamba models and propose ReMamba, which enhances Mamba's ability to comprehend long contexts. ReMamba incorporates selective compression and adaptation techniques within a two-stage re-forward process, incurring minimal additional inference costs overhead. Experimental results on the LongBench and L-Eval benchmarks demonstrate ReMamba's efficacy, improving over the baselines by 3.2 and 1.6 points, respectively, and attaining performance almost on par with same-size transformer models.