SWIFT:一种可扩展的轻量级基础设施用于微调
https://arxiv.org/abs/2408.05517
Yuze Zhao, Jintao Huang, Jinghan Hu, Daoze Zhang, Zeyinzi Jiang, Zhikai Wu, Baole Ai, Ang Wang, Wenmeng Zhou 和 Yingda Chen
ModelScope团队,阿里巴巴集团
摘要
最近在大型语言模型(LLMs)和多模态大型语言模型(MLLMs)方面的发展,利用基于注意力的T
2024-10-31