Hugging Face's logo

hard007ik
/
shopmanager-train-code

openenv
Model card Files
xet
 Community
shopmanager-train-code

Commit History

  1. updated environment with multi-agent DB integration

    hard007ik
    c996cea

  2. complete almost

    hard007ik
    78e43a9

  3. complete almost

    hard007ik
    04b615f

  4. pin vllm<=0.18.0 to fix TRL importance-sampling ratio collapse

    hard007ik
    8464e70

  5. Drop max_prompt_length from GRPOConfig (removed in newer TRL)

    hard007ik
    1ecce94

  6. Add GRPO training scaffolding (Module 5 rollout_func pattern) + plot artifacts

    hard007ik
    caea08d

  7. Merge branch 'main' of https://github.com/Hard007ik/ShopManagerEng⁠

    hard007ik
    d11ffe8

  8. shop manage eng phase 2 first

    hard007ik
    048f186

  1. Add LICENSE file

    Hardik Makwana
    Unverified signature
    3b9e063

  2. Delete Apache License from LICENSE file⁠

    Hardik Makwana
    Unverified signature
    cb8199f

  3. Include Apache License 2.0⁠

    Hardik Makwana
    Unverified signature
    2348f11

  1. solve inference again 2

    hard007ik
    135f6f5

  2. solve inference again

    hard007ik
    8927ef0

  3. again inferecnce updated

    hard007ik
    2f31737

  4. resolving inference

    hard007ik
    78a47d4

  5. inference updated for 3 task

    hard007ik
    28cbbf9

  6. yaml updated

    hard007ik
    35bb9d3

  7. updated server/app.py as per submit validation

    hard007ik
    5c3c008

  8. updated url in inference.py

    hard007ik
    b4b27d7

  9. fix: resolve relative import error for Docker deployment

    hard007ik
    95a7814

  10. feat: jewelry shop RL environment with market, warehouse, and showroom phases

    hard007ik
    5c6ca01