1.7 KiB
license, base_model, library_name, pipeline_tag, tags
| license | base_model | library_name | pipeline_tag | tags | ||||||
|---|---|---|---|---|---|---|---|---|---|---|
| apache-2.0 | Qwen/Qwen3-4B | transformers | text-generation |
|
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
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.