Commit History

  1. Task 13: GRPO training notebook (Unsloth + TRL, 17 cells, base-vs-trained eval, plot cells, push-to-Hub)

    8e36acf

  1. Phase markers + restraint scoping: silent_witness/implicit_preference reward silence; secret_handling/multi_party expect engagement

    7c02f78
  2. Fix HF Space metadata: colorFrom yellow, shorter description

    4ddfaf4
  3. Merge HF Space init (keep our README + frontmatter)

    Bhargav
    fc3ec1a
  4. initial commit

    Verified signature
    317a044
  5. Initial KinChat env: models, personas, scenarios, rubrics, grader, env loop, FastAPI app, client, dashboard, baseline inference (377 tests passing)

    Bhargav
    2e8387b