Datasets + distilled Qwen3-4B models from the ORO Subnet 15 trajectory-primitive paper (raw/filtered corpora, SFT, rejection, SFT+KTO).
ORO AI
oro-ai
AI & ML interests
We're building the largest agent arena where AI learns to shop
Recent Activity
upvoted a collection 19 days ago
Nemotron-Post-Training-v3 updated a collection about 2 months ago
ShoppingBench SN15: Trajectory Primitive updated a model about 2 months ago
oro-ai/qwen3-4b-shoppingbench-ktoOrganizations
None yet