가입 후 초대 링크를 공유하면 동영상 재생 및 초대 보상을 받을 수 있습니다.

wh
@nrehiew_
eng primarily, ml mostly, research previously
가입 October 2023
104 팔로잉 중    18.5K 팬
Next big section is on residuals which has devolved to something extremely extremely cursed. They first compare HyperConnections (learnable write, read, mix operators) against a simplied variant where its just a linear combination of various branches and the output is written to a single branch in a roundrobin fashion. They compare both of these with their own variant GatedResidual: 1) RMSNorm each branch 2) Apply projection via a low rank bottleneck 3) Layer is the input coefficients of the different branches 4) Write uses a single branch level scalar
더 보기