48 lines
1.8 KiB
Markdown
48 lines
1.8 KiB
Markdown
---
|
|
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 + KTO
|
|
|
|
**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)
|
|
|
|
KTO preference refinement (v3) applied on top of the merged opd_renderers SFT champion. Reaches 42.7% ASR on the 75-problem leak-cluster-guarded held-out partition (production-strict, temp 0), matching the SFT champion.
|
|
|
|
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-kto")
|
|
model = AutoModelForCausalLM.from_pretrained("oro-ai/qwen3-4b-shoppingbench-kto", torch_dtype="bfloat16", device_map="auto")
|
|
```
|
|
|
|
## License
|
|
|
|
Apache-2.0, inherited from the Qwen3-4B base model.
|