gavinlaw
/

setground-question-policy

Model card Files Files and versions

setground-question-policy

469 MB

Ctrl+K

Ctrl+K

1 contributor

History: 101 commits

gavinlaw's picture

Preserve six paired RL students from a preselected distilled initialization

b59e9f6 verified 19 minutes ago

snapshots
Preserve six paired RL students from a preselected distilled initialization 19 minutes ago
.gitattributes

2 kB
Preserve four task readouts and eight matched action heads 4 days ago
README.md

2.21 kB
Preserve first conditional learned question policies and complete recovery evidence 7 days ago