Instructions to use JaspinXu/KnowWhenToHandOff-Qwen3-4B-R2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use JaspinXu/KnowWhenToHandOff-Qwen3-4B-R2 with Transformers:

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

pipe = pipeline("text-generation", model="JaspinXu/KnowWhenToHandOff-Qwen3-4B-R2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("JaspinXu/KnowWhenToHandOff-Qwen3-4B-R2")
model = AutoModelForCausalLM.from_pretrained("JaspinXu/KnowWhenToHandOff-Qwen3-4B-R2", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use JaspinXu/KnowWhenToHandOff-Qwen3-4B-R2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "JaspinXu/KnowWhenToHandOff-Qwen3-4B-R2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "JaspinXu/KnowWhenToHandOff-Qwen3-4B-R2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/JaspinXu/KnowWhenToHandOff-Qwen3-4B-R2

SGLang

How to use JaspinXu/KnowWhenToHandOff-Qwen3-4B-R2 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 "JaspinXu/KnowWhenToHandOff-Qwen3-4B-R2" \
    --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": "JaspinXu/KnowWhenToHandOff-Qwen3-4B-R2",
		"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 "JaspinXu/KnowWhenToHandOff-Qwen3-4B-R2" \
        --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": "JaspinXu/KnowWhenToHandOff-Qwen3-4B-R2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use JaspinXu/KnowWhenToHandOff-Qwen3-4B-R2 with Docker Model Runner:
```
docker model run hf.co/JaspinXu/KnowWhenToHandOff-Qwen3-4B-R2
```

KnowWhenToHandOff-Qwen3-4B-R2 (GRPO, Responsible-AI reward)

Research artefact — not for deployment. Trained and evaluated only with simulated users on a public benchmark. It has not been tested with real customers, real data or real business systems.

Code github.com/JaspinXu/KnowWhenToHandOff · Data KnowWhenToHandOff-data · Family SFT · R1 · R2

R2 is Qwen3-4B-Instruct-2507 trained with SFT and then multi-turn GRPO on the τ²-bench airline and retail domains, with a reward that adds penalties for rule violations, unnecessary hand-offs and missed hand-offs. It has the best hand-off F1 of the study (0.812) with 10 % over-escalation, at the same task success as its SFT starting point.

Model family

Model	Training	Hand-off F1	Over-escalation	Use it for
SFT (B2)	LoRA SFT on 790 filtered teacher dialogues	0.768	0.016	starting point; precise but misses hand-offs
R1	GRPO from B2, task reward only	0.802	0.462	studying the outcome-reward loophole
R2	GRPO from B2, task reward + violation and hand-off penalties	0.812	0.103	the best-calibrated hand-off model

Task success on the official test tasks is the same for all three within noise (0.33–0.35).

Quick start

A standard Qwen3 chat model with tool calling. It was trained with the τ²-bench domain policy as the system prompt and the domain's tools, including transfer_to_human_agents; for faithful behaviour run it inside the evaluation harness of the code repository.

from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "JaspinXu/KnowWhenToHandOff-Qwen3-4B-R2"
tokenizer = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
    repo, torch_dtype="auto", device_map="auto"
)

transfer = {
    "type": "function",
    "function": {
        "name": "transfer_to_human_agents",
        "description": "Transfer the user to a human agent.",
        "parameters": {
            "type": "object",
            "properties": {"summary": {"type": "string"}},
            "required": ["summary"],
        },
    },
}
messages = [
    {"role": "system", "content": "<airline or retail policy>"},
    {"role": "user", "content": "I need the unaccompanied-minor service."},
]
inputs = tokenizer.apply_chat_template(
    messages, tools=[transfer], add_generation_prompt=True,
    return_tensors="pt",
).to(model.device)
output = model.generate(inputs, max_new_tokens=512)
print(tokenizer.decode(output[0][inputs.shape[-1]:], skip_special_tokens=True))

Serve it with vLLM (OpenAI-compatible API, tool calls parsed):

vllm serve JaspinXu/KnowWhenToHandOff-Qwen3-4B-R2 \
  --enable-auto-tool-choice --tool-call-parser hermes

Evaluation

Test split, protocol frozen in ADR-005; 95 % bootstrap intervals over tasks.

Metric	This model	B2 (SFT start)	Source
Success (pass^1), test_main	0.342 [0.245, 0.449]	0.327 [0.224, 0.434]	main table
Paired Δ success vs B2	+0.015 [−0.056, 0.082]	—	paired differences
pass^4	0.122 [0.041, 0.224]	0.102 [0.041, 0.204]	main table
Violation rate (incl. off-reference writes)	0.444	0.469	same
Hand-off F1 / precision / recall, test_handoff	0.812 / 0.886 / 0.750	0.768 / 0.976 / 0.633	`R2-final-test_handoff-s0-20261007`
Over-escalation, test_handoff	0.103	0.016	same
Worst-style success / style gap	0.316 / 0.112	0.327 / 0.112	styles

Known behaviour. R2 removes R1's over-escalation but sometimes makes the opposite error on out-of-scope requests: it refuses and tells the user to contact the company directly without calling the transfer tool, or substitutes an unrelated write (under-escalation 0.25). Once it justified a hand-off with a policy that does not exist.

Training details

Base model: Qwen/Qwen3-4B-Instruct-2507 (revision cdbee75f17c01a7cc42f958dc650907174af0554), Apache-2.0.
Training: GRPO from the SFT checkpoint B2 with the composite reward (configs/reward/r2.yaml: task reward − 0.25 × weighted violations − 0.5 × unneeded transfer − 1.0 × missed transfer − 0.1 × format errors); LoRA rank 64, alpha 128, lr 1e-5; 8 tasks × 8 rollouts per step, 60 steps, no KL term.
Training run R2-s1-20261006 (seed 1); exported step-60 checkpoint sha256:be6198a0c51773f52ba4f20c9605a5931f23b0206e92a9fe0521a93761348c96 (merged bf16, Hugging Face format).
Evaluation code at git 462b5d17b4e9add637a2ee7802974c720b625a5b; τ²-bench fc0055dc4e0a316c3f83133267fbd6faaa770992; all sources in reports/main/sources.json.

Intended use

Studying when a tool-using customer-service agent should hand off to a human, in the τ²-bench airline and retail domains. Out of scope: any production or customer-facing use, other domains, and decisions about real people.

Training data

Simulated conversations on τ²-bench v1.0.1 train-split tasks (a dev split was carved out for selection) and hand-off variants derived from them (explicit requests for a human, out-of-scope requests, hard negatives); the user simulator is Qwen3-30B-A3B-Instruct-2507. No real user data. Test tasks were never used for training or selection.

Limitations

One user simulator (Qwen3-30B-A3B-Instruct-2507, which also generated the SFT data) and one training seed; results may not transfer to real users or other simulators, and the intervals cover task sampling, not training variance.
Small test split (49 official tasks; retail uses the 74 tasks whose reward needs no LLM judge, so retail numbers are not comparable with leaderboards).
Communication styles describe how users write, not who they are; no claim is made about any demographic group.
Policy compliance is checked by five deterministic rules that cover only part of each domain policy; citation rate is a keyword rule (it counted one invented policy as a citation).
Observed reward-hacking behaviours: docs/rl-audit.md.

Licences

The weights are a LoRA fine-tune of Qwen/Qwen3-4B-Instruct-2507 and inherit its Apache-2.0 licence. τ²-bench code and data (pinned commit fc0055dc4e0a316c3f83133267fbd6faaa770992) are used under the licence in its LICENSE file; released dialogue samples are τ²-bench-derived synthetic conversations with no real user data.

Citation

Model DOI: 10.57967/hf/10823. Cite the model and the project:

@misc{knowwhentohandoff2026r2,
  title     = {KnowWhenToHandOff-Qwen3-4B-R2},
  author    = {{KnowWhenToHandOff contributors}},
  year      = {2026},
  publisher = {Hugging Face},
  doi       = {10.57967/hf/10823},
  url       = {https://huggingface.co/JaspinXu/KnowWhenToHandOff-Qwen3-4B-R2}
}

@misc{knowwhentohandoff2026,
  title  = {Know When to Hand Off: Multi-turn Reinforcement Learning for
            Trustworthy Customer-Service Agents},
  author = {{KnowWhenToHandOff contributors}},
  year   = {2026},
  howpublished = {\url{https://github.com/JaspinXu/KnowWhenToHandOff}}
}