Modelpublic

oro-ai/qwen3-4b-shoppingbench-rejection

sourceHugging Faceapache-2.0updated 4mo agoView on Hugging Face

0likes27downloads

Model Card

Qwen3-4B ShoppingBench Rejection-Sampled

Paper: arXiv:2606.10064 Code: https://github.com/ORO-AI/shoppingbench-trajectory-primitive

Reward-weighted rejection-sampled fine-tuning of Qwen3-4B, the second stage after base SFT in the ShoppingBench distillation pipeline.

Companion artifact for the paper Bittensor Agent Arenas as a Trajectory Primitive: Distilling a Shopping Agent from ShoppingBench Subnet Traces. The published Qwen3-4B base scores 18.0% ASR on ShoppingBench; the distilled SFT-family models in this collection lift that to 42.7% on a leak-cluster-guarded held-out partition scored production-strict.

This is a merged full model (Qwen3-4B weights with the trained delta merged in), ready to load directly with transformers or serve with vLLM. No adapter stacking required.

Training data

—Filtered corpus: `oro-ai/sn15-shoppingbench-sft-15k`
—Raw traces: `oro-ai/sn15-shoppingbench-traces-18k`

Usage

python

from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("oro-ai/qwen3-4b-shoppingbench-rejection")
model = AutoModelForCausalLM.from_pretrained("oro-ai/qwen3-4b-shoppingbench-rejection", torch_dtype="bfloat16", device_map="auto")

License

Apache-2.0, inherited from the Qwen3-4B base model.