Commit History

  1. Update README.md

    Verified signature
    fae67c8
  2. Revert "Upload train_colab.ipynb"⁠

    Bhaskar
    d5cfc10
  3. final: official codebase and documentation

    Bhaskar
    ae26ca6
  4. Upload train_colab.ipynb

    Verified signature
    bec08c7
  5. Delete train_colab.ipynb

    Verified signature
    6184017
  6. Upload 8 files

    Verified signature
    891f1bd
  7. Create images/.gitkeep

    Verified signature
    5311253
  8. docs: technical write-up and readme

    Bhaskar
    6b36897
  9. added wandb in requirements

    Bhaskar
    a9f5ef8
  10. added wandb in train file

    Bhaskar
    a0e028b
  11. Update README with Judge Dashboard details

    Bhaskar
    2abec6a
  12. updated the index file

    Bhaskar
    1476327
  13. Created using Colab

    Bhaskar
    bccb381
  14. Created using Colab

    Bhaskar
    634c66e
  15. Created using Colab

    Bhaskar
    1d792bc

  1. fix ui serving route and include index.html in image

    Bhaskar
    8573ebf
  2. Fix Unsloth dtype mismatch by locking precision mode

    Bhaskar
    91ac1b6
  3. Fix grpo reward parser for list/dist completions

    Bhaskar
    8ca88e8
  4. fix triton compiler runtime and grpo batch config

    Bhaskar
    de62154
  5. docker update

    Bhaskar
    e11cac9
  6. removed uv from the last line in docker file

    Bhaskar
    8ee3bbf
  7. add colab notebook and updated the train and docker files and edited the requirements according to the codebase

    Bhaskar
    2b9c8cb
  8. updated the codebase for a10 24gb gpu

    Bhaskar
    a8a8219
  9. updated the codebase for a10 24gb gpu

    Bhaskar
    a24d3c8
  10. ui of the project

    Bhaskar
    66b85db
  11. train file updated for local training

    Bhaskar
    4714235
  12. update the readme file and added three updates to the main file

    Bhaskar
    d00513d

  1. fix: HF Space YAML metadata — colorTo blue, shorten short_description

    Bhaskar
    5a85fc9
  2. Round 2 Upgrade: Added GRPO train.py and vector-field reward shaping

    Bhaskar
    51bb0d4

  1. ResetRequest updated

    Bhaskar
    d29a040
  2. Final submission: Meta OpenEnv Hackathon

    Bhaskar
    b163d5f