chad / experiments

Commit History

  1. add dpo iteration snapshots

    Verified signature
    75b1b87
  2. add experiments/dpo-rdiff1.12.pt

    Verified signature
    e333bdf
  3. add experiments/sft-v1-to-v3.pt

    Verified signature
    9c2924b
  4. add experiments/sft-v1-to-v2.pt

    Verified signature
    7081761