eVTA0_models / reward_model

Commit History

16 days ago

  1. Strip internal training metadata from reward checkpoints

    Verified signature
    5d72be9
  2. Strip internal training metadata from reward checkpoints

    Verified signature
    6cd1dc5
  3. Release eVTA0 reward-model and GRPO policy checkpoints

    Verified signature
    1eee29b