Commit History
8 days ago
-
Strip internal training metadata from reward checkpoints
Verified signature5d72be9 -
Strip internal training metadata from reward checkpoints
Verified signature6cd1dc5 -
Release eVTA0 reward-model and GRPO policy checkpoints
Verified signature1eee29b -
Add model card
Verified signature7a73bd4 -
initial commit
Verified signature9813deb