---
license: apache-2.0
base_model: Qwen/Qwen3-4B
library_name: transformers
pipeline_tag: text-generation
tags:
- agentic
- tool-use
- shopping
- bittensor
- shoppingbench
- qwen3
---

# Qwen3-4B ShoppingBench SFT

**Paper:** [arXiv:2606.10064](https://arxiv.org/abs/2606.10064)  
**Code:** [https://github.com/ORO-AI/shoppingbench-trajectory-primitive](https://github.com/ORO-AI/shoppingbench-trajectory-primitive)

Supervised fine-tuning (SFT) of Qwen3-4B on the leak-cluster-guarded ShoppingBench SN15 corpus. This is the base SFT stage of the 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`](https://huggingface.co/datasets/oro-ai/sn15-shoppingbench-sft-15k)
- Raw traces: [`oro-ai/sn15-shoppingbench-traces-18k`](https://huggingface.co/datasets/oro-ai/sn15-shoppingbench-traces-18k)

## Usage

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

## License

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