CoolFace
Apppublic

Firemedic15/repro-single-rollout-hidden-state-dynamics-for-training-free-rlvr-data-selection

sourceHugging Faceupdated 2mo agoView on Hugging Face
0likes
2 commits on main
807abb32mo ago

Update logbook: Reproduction: Single-Rollout Hidden-State Dynamics for Training-Free RLVR Data Selection

Firemedic15
bc646ec2mo ago

initial commit

Firemedic15