Effective Long-Context Scaling of Foundation Models.
Wenhan XiongJingyu LiuIgor MolybogHejia ZhangPrajjwal BhargavaRui HouLouis MartinRashi RungtaKarthik Abinav SankararamanBarlas OguzMadian KhabsaHan FangYashar MehdadSharan NarangKshitiz MalikAngela FanShruti BhosaleSergey EdunovMike LewisSinong WangHao MaPublished in: CoRR (2023)