dvlab-research / MGM

Official repo for "Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models"

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

计划加入DPO训练来缓解模型幻觉问题吗

jiezhangGt opened this issue · comments

如题,请问有计划引入DPO强化学习,来进一步提升模型效果,降低模型幻觉等问题吗?谢谢