10T Mixed RLVR Collection Selected Snowball 67B-A2B checkpoints from mixed-task RLVR training. • 1 item • Updated about 12 hours ago
2.7T Math RL Collection Snowball 67B-A2B models (2.7T cooldown) math RL campaign tracked in marin-community/marin#7786. • 15 items • Updated about 13 hours ago