Instructions to use Jarrodbarnes/Qwen3-4B-tau2-grpo-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Jarrodbarnes/Qwen3-4B-tau2-grpo-v1 with Transformers:

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

pipe = pipeline("text-generation", model="Jarrodbarnes/Qwen3-4B-tau2-grpo-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Jarrodbarnes/Qwen3-4B-tau2-grpo-v1")
model = AutoModelForCausalLM.from_pretrained("Jarrodbarnes/Qwen3-4B-tau2-grpo-v1")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Jarrodbarnes/Qwen3-4B-tau2-grpo-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Jarrodbarnes/Qwen3-4B-tau2-grpo-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jarrodbarnes/Qwen3-4B-tau2-grpo-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Jarrodbarnes/Qwen3-4B-tau2-grpo-v1

SGLang

How to use Jarrodbarnes/Qwen3-4B-tau2-grpo-v1 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 "Jarrodbarnes/Qwen3-4B-tau2-grpo-v1" \
    --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": "Jarrodbarnes/Qwen3-4B-tau2-grpo-v1",
		"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 "Jarrodbarnes/Qwen3-4B-tau2-grpo-v1" \
        --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": "Jarrodbarnes/Qwen3-4B-tau2-grpo-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Jarrodbarnes/Qwen3-4B-tau2-grpo-v1 with Docker Model Runner:
```
docker model run hf.co/Jarrodbarnes/Qwen3-4B-tau2-grpo-v1
```

Qwen3-4B-tau2-grpo-v1

A 4B parameter model fine-tuned for multi-turn tool-use tasks, achieving 59% Pass@4 on tau2-bench (test split). This represents a 4x improvement over the base model and demonstrates that progressive training (SFT -> RFT -> GRPO) works effectively for complex, multi-turn agent tasks.

Model Description

This model was trained using a three-stage pipeline:

SFT (Supervised Fine-Tuning): Learning protocol and tool schemas from successful trajectories
RFT (Rejection Fine-Tuning): Concentrating training on high-quality rollouts via rejection sampling
GRPO (Group Relative Policy Optimization): Reinforcement learning with turn-level reward shaping

The training process is documented in the tau2 training cookbook.

Performance

tau2-bench Test Split (Pass@4 evaluation)

Domain	Pass@1	Pass@4	Tasks
Overall	36.0%	59.0%	100
Airline	15.0%	45.0%	20
Retail	55.0%	85.0%	40
Telecom	27.5%	40.0%	40

Training Progression

Stage	Overall Pass@4
Baseline (Qwen3-4B-Instruct)	14.3%
SFT + RFT	27.0%
GRPO (this model)	59.0%

Eval config: temperature=0.8, top_p=1.0, top_k=20, num_samples=4, TAU2_USER_MODEL=gpt-4.1-mini, TAU2_USER_TEMPERATURE=0.7, TAU2_MAX_STEPS=100.

Usage

With SGLang (recommended for evaluation)

# Start the server (use --tp 1 for single GPU)
python -m sglang.launch_server \
  --model-path Jarrodbarnes/Qwen3-4B-tau2-grpo-v1 \
  --host 0.0.0.0 --port 30000 --tp 2 --mem-fraction-static 0.70

With Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Jarrodbarnes/Qwen3-4B-tau2-grpo-v1"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

Function Calling Format

This model uses Qwen3 native function calling format:

<tool_call>{"name": "tool_name", "arguments": {"arg": "value"}}</tool_call>

Include </tool_call> in stop sequences for proper parsing.

Training Details

Base model: Qwen/Qwen3-4B-Instruct-2507
Training framework: SLIME (Megatron-LM + SGLang)
SFT data: tau2-sft-seed-v3
GRPO steps: 21 optimizer steps
Reward shaping: Turn-level partial scores from tau2-bench reward_info
User simulator (training): Local Qwen3-4B-Instruct on port 30001
User simulator (eval): GPT-4.1-mini via OpenAI API

W&B Training Logs

SFT run: b7d80rfe
GRPO run: pkeu9kck

Resources

Training Cookbook - Full methodology and reproduction steps
SFT Checkpoint - Intermediate SFT+RFT checkpoint
Training Dataset - Filtered RFT trajectories
tau2-bench - Benchmark repository

Limitations

Telecom domain: Dual-control tasks (where the agent must instruct rather than execute) remain challenging (40% Pass@4)
User simulator sensitivity: Results vary with user simulator choice; GPT-4.1-mini recommended for reproducibility
Pass@k vs Pass^k: This model reports pass@k (any success in k attempts), not the pass^k metric used on the official tau2-bench leaderboard

Citation

@misc{qwen3-tau2-grpo,
  title={Qwen3-4B-tau2-grpo-v1: Multi-Turn Tool-Use Agent via Progressive RL Training},
  author={Jarrod Barnes},
  year={2025},
  url={https://huggingface.co/Jarrodbarnes/Qwen3-4B-tau2-grpo-v1}
}

Acknowledgments

Qwen Team for the base model
Sierra Research for tau2-bench
THUDM for the SLIME training framework

Downloads last month: 35

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for Jarrodbarnes/Qwen3-4B-tau2-grpo-v1

Base model

Qwen/Qwen3-4B-Instruct-2507

Finetuned

(1725)

this model

Dataset used to train Jarrodbarnes/Qwen3-4B-tau2-grpo-v1

Evaluation results

Pass@1 (Overall) on tau2-bench (test split)
self-reported

36.000
Pass@4 (Overall) on tau2-bench (test split)
self-reported

59.000