Commit History

  1. Update model card with paper-aligned evaluation

    Verified signature
    2b4952d
  2. Add reproducible paper-aligned evaluation script

    Verified signature
    20b14d7
  3. Add paper-aligned constitutional classifier evaluation results

    Verified signature
    00aadf0

  1. Update README.md

    Verified signature
    0ae551a

  1. Add evaluation script v2

    Verified signature
    808c7ed
  2. Add evaluation script

    Verified signature
    67bdb02
  3. Add constitution definition

    Verified signature
    9de2b9a
  4. Final constitutional safety classifier

    Verified signature
    257a0c1
  5. Training in progress, step 3690

    Verified signature
    3b1b381
  6. Training in progress, step 3600

    Verified signature
    a49efbd
  7. Training in progress, step 3400

    Verified signature
    954fc52
  8. Training in progress, step 3200

    Verified signature
    b5a831b
  9. Training in progress, step 3000

    Verified signature
    80ab68c
  10. Training in progress, step 2800

    Verified signature
    4db8f2e
  11. Training in progress, step 2600

    Verified signature
    bc48ab4
  12. Training in progress, step 2400

    Verified signature
    22ec762
  13. Training in progress, step 2200

    Verified signature
    220c0c7
  14. Training in progress, step 2000

    Verified signature
    c1e14fb
  15. Training in progress, step 1800

    Verified signature
    be8b1f5
  16. Training in progress, step 1600

    Verified signature
    a5ed105
  17. Training in progress, step 1400

    Verified signature
    dc75217

  1. Training in progress, step 1200

    Verified signature
    a56614b
  2. Training in progress, step 1000

    Verified signature
    650297e
  3. Training in progress, step 800

    Verified signature
    8e9bf6d
  4. Training in progress, step 600

    Verified signature
    782eb6e
  5. Upload README.md

    Verified signature
    cec6607
  6. Training in progress, step 400

    Verified signature
    30a0319
  7. Training in progress, step 200

    Verified signature
    7501d45
  8. Add comprehensive model README

    Verified signature
    075b734
  9. initial commit

    Verified signature
    398ff01