Commit History

  1. fix DPOConfig: drop max_prompt_length

    Verified signature
    2ac14b9
  2. DPO: merge SFT LoRA then train

    Verified signature
    5fb8489
  3. fix Trackio crash: push at end only

    Verified signature
    927b117
  4. fix Trackio crash: push at end only

    Verified signature
    95f1e85
  5. DPO script

    Verified signature
    332a987
  6. SFT script

    Verified signature
    17a6842
  7. initial commit

    Verified signature
    a41fb61