stas
/

tr8b-104B-debug3

Model card Files Files and versions Metrics Training metrics Community

tr8b-104B-debug3 / cl /028-module.17.self_attention.scale_mask_softmax

1 contributor

History: 1 commit

stas's picture

debug3

59607a2 almost 3 years ago

events.out.tfevents.1637659594.r8i1n3.2542460.2

33.6 MB
LFS

debug3 almost 3 years ago