SenseTime Open-Sources SenseNova-Loop-9B-Preview, a Looped Model That Runs Its Middle Layers Twice

T2Covered by 1 source · first reported by China: SCMP Tech / TechNode / Pandaily / KrASIA / Sixth Tone at 01 Nov, 01:52 UTC

SenseTime's open-source SenseNova-Loop-9B-Preview runs a shared 24-layer block twice, giving 56 layer passes from 32 layers, and adds two-stream mHC. Weights are Apache 2.0.

dev

Sources

• T2SenseTime Open-Sources SenseNova-Loop-9B-Preview, a Looped Model That Runs Its Middle Layers TwiceChina: SCMP Tech / TechNode / Pandaily / KrASIA / Sixth Tone01 Nov, 01:52