Commit History

  1. Update README.md

    Verified signature
    3acf10b
  2. Update README.md

    Verified signature
    e3603dc
  3. Update README.md

    Verified signature
    cb6a4ca
  4. Update README.md

    Verified signature
    add766c
  5. Update train.py

    Verified signature
    f3fc038
  6. Update README.md

    Verified signature
    3c7a3a5
  7. Delete mock_worker.py

    Verified signature
    aa1d7f7
  8. Update train.py

    Verified signature
    6a2dd66
  9. Upload MODEL_CARD.md

    Verified signature
    5d8f1e9
  10. Update BLOG.md

    Verified signature
    1f65562
  11. Create BLOG.md

    Verified signature
    767ffe9
  12. Update README.md

    Verified signature
    904779b
  13. Update README.md

    Verified signature
    926997e
  14. Update train.py

    Verified signature
    f330c3f
  15. Fix: Use Level 1 scenarios only for training

    Verified signature
    7a19964
  16. Add MemoryLedger

    Verified signature
    9a90a52
  17. Add WorldModelSimulator

    Verified signature
    2327c5a
  18. Training script with WorldModel/Memory integration

    Verified signature
    48a7cf6
  19. Update README with all required links

    Verified signature
    1a5a502
  20. Add OpenEnv manifest

    Verified signature
    609a677
  21. More SFT warmup (40 steps) for better JSON format

    Verified signature
    aac0ab9
  22. Added friend laptop worker via ngrok

    Verified signature
    2688686
  23. Added friend worker + local worker dispatch

    Verified signature
    07656ee
  24. Updated: 250 steps, K=2, LR=1e-5, temp 1.0-0.7

    Verified signature
    a0297c3
  25. Add worker setup guide

    Verified signature
    7275c33
  26. Add mock worker for demo

    Verified signature
    7bffd13
  27. Add worker client with local ngrok URL

    Verified signature
    edc3562
  28. train: higher LR=1e-5, more SFT=20, lower temp=1.0->0.7

    23c3a1b
  29. chore: remove binary artifacts from git

    5e5d438
  30. faster training: lower temp, higher LR, more SFT

    Verified signature
    c84d93d
  31. Upload Dockerfile with huggingface_hub

    Verified signature
    31fe512
  32. Upload Dockerfile with huggingface_hub

    Verified signature
    524f673
  33. Upload Dockerfile with huggingface_hub

    Verified signature
    f5ca8fb
  34. Upload train.py with huggingface_hub

    Verified signature
    e5115bd
  35. Upload Dockerfile with huggingface_hub

    Verified signature
    da61617
  36. Upload folder using huggingface_hub

    Verified signature
    8b092ea
  37. fix: C-4 reward clamp, C-6 HF_TOKEN, W-2 citation floor, W-9 dup import

    Verified signature
    b022bda
  38. fix: force torch 2.5.1+cu121 after unsloth to prevent colab-new downgrade

    Verified signature
    9e1ad05
  39. fix: upgrade PyTorch to 2.5.1 to fix unsloth_zoo AttributeError on torch._inductor.config

    Verified signature
    ff9091d
  40. Upload Dockerfile with huggingface_hub

    Verified signature
    ce8daf0
  41. Upload hf_training/train.py with huggingface_hub

    Verified signature
    c51cef7
  42. Upload Dockerfile with huggingface_hub

    Verified signature
    4981837
  43. Upload README.md with huggingface_hub

    Verified signature
    85a478c
  44. Upload folder using huggingface_hub

    Verified signature
    206f794
  45. Upload README.md with huggingface_hub

    Verified signature
    acb482d
  46. Upload Dockerfile with huggingface_hub

    Verified signature
    319ef7e
  47. Upload folder using huggingface_hub

    Verified signature
    e945ec1
  48. Upload Dockerfile with huggingface_hub

    Verified signature
    854a3f5
  49. Upload train.py with huggingface_hub

    Verified signature
    466a284
  50. Upload folder using huggingface_hub

    Verified signature
    51db3e8