Jin, Q., Song, X., Zhou, F., & Qin, Z. (2024). Align Attention Heads Before Merging Them: An Effective Way for Converting MHA to GQA.
Chicago Style (17th ed.) CitationJin, Qingyun, Xiaohui Song, Feng Zhou, and Zengchang Qin. Align Attention Heads Before Merging Them: An Effective Way for Converting MHA to GQA. 2024.
MLA (9th ed.) CitationJin, Qingyun, et al. Align Attention Heads Before Merging Them: An Effective Way for Converting MHA to GQA. 2024.
Warning: These citations may not always be 100% accurate.