Spaces:
Sleeping
Sleeping
Commit History
Reframe 3B follow-up as trial run 0553162 verified
Add 3B GRPO follow-up evidence c89a7a9 verified
Align warehouse GRPO prompt with SFT 0ac1e98 verified
Fix adapter eval for 3B notebooks c66fcbe verified
Refresh 3B notebook eval path 83bf1ef verified
Refresh training notebook clone step ea9a79c verified
Expose generation batch size in 3B notebook 9592f16 verified
Expose GRPO generation batch size 87004db verified
Add 4bit SFT training knobs eee84e5 verified
Add 4bit GRPO training knobs bbb6307 verified
Tune 3B notebook for Colab GPU 491993a verified
Allow configurable SFT base model 6d2f03a verified
Allow configurable eval base model bfc3f5b verified
Allow configurable GRPO base model 130e9e4 verified
Add 3B GRPO Colab notebook 6f3e2d3 verified
make it more colab friendly c0a893e verified
Fix training notebook smoke test cbf66d6 verified
Remove Colab folder from Space 67adddd verified
Embed evidence plots in README 82d40c1 verified
Improve blog narrative opening 2114f64 verified
Embed evidence plots in blog a8cf751 verified
Upload blog evidence plots 56a3cf9 verified
Add playable demo links f39ab13
Rishav commited on
Refine SupplyMind blog evidence 4054708
Rishav commited on
Add SupplyMind blog draft cc7a029
Rishav commited on
Add runnable training notebook 00ebacd
Rishav commited on
Remove submission plots from HF package e069cc9
Rishav commited on
Clean SupplyMind submission for HF c186723
Rishav commited on
Pin latest OpenEnv runtime 32b510c
Rishav commited on
Add final eval set 0af60f8
Rishav commited on
Add conservative warehouse SFT evidence cb5e5bf
Rishav commited on
Bias center SFT toward action states 939eba0
Rishav commited on
Tighten role training scaffold a2144da
Rishav commited on
Add eval action diagnostics ff949e6
Rishav commited on
Add held-out improvement visuals d211fba
Rishav commited on
Split dashboard curves by training phase 7579e54
Rishav commited on
Add SFT warm start training pipeline be8d222
Rishav commited on
Add training dashboard UI 8258b94
Rishav commited on
Add HF adapter evaluation job 45cc878
Rishav commited on
Disable Trackio checkpoint sync aa7d416
Rishav commited on
Tune GRPO completion length cce2fba
Rishav commited on
Make GRPO config version tolerant 15084c8
Rishav commited on
Fix HF training config resolution d77a60c
Rishav commited on
Harden HF training startup 1cd6456
Rishav commited on
Add role-specific training scores 37049ad
Rishav commited on
Add training progress logs a7160ed
Rishav commited on
Fix training smoke task id 5ca7724
Rishav commited on
Add HF role GRPO training job 3f1eabc
Rishav commited on
Align center reward with service profit f058a59
Rishav commited on