Instructions to use oro-ai/qwen3-4b-shoppingbench-rejection with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use oro-ai/qwen3-4b-shoppingbench-rejection with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="oro-ai/qwen3-4b-shoppingbench-rejection")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("oro-ai/qwen3-4b-shoppingbench-rejection")
model = AutoModelForCausalLM.from_pretrained("oro-ai/qwen3-4b-shoppingbench-rejection", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use oro-ai/qwen3-4b-shoppingbench-rejection with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "oro-ai/qwen3-4b-shoppingbench-rejection"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "oro-ai/qwen3-4b-shoppingbench-rejection",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/oro-ai/qwen3-4b-shoppingbench-rejection

SGLang

How to use oro-ai/qwen3-4b-shoppingbench-rejection with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "oro-ai/qwen3-4b-shoppingbench-rejection" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "oro-ai/qwen3-4b-shoppingbench-rejection",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "oro-ai/qwen3-4b-shoppingbench-rejection" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "oro-ai/qwen3-4b-shoppingbench-rejection",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use oro-ai/qwen3-4b-shoppingbench-rejection with Docker Model Runner:
```
docker model run hf.co/oro-ai/qwen3-4b-shoppingbench-rejection
```

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")