Instructions to use SiningZhou/Qwen3-8B-ReST-RL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SiningZhou/Qwen3-8B-ReST-RL with Transformers:

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

pipe = pipeline("text-generation", model="SiningZhou/Qwen3-8B-ReST-RL")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SiningZhou/Qwen3-8B-ReST-RL")
model = AutoModelForCausalLM.from_pretrained("SiningZhou/Qwen3-8B-ReST-RL")
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 SiningZhou/Qwen3-8B-ReST-RL with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SiningZhou/Qwen3-8B-ReST-RL"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SiningZhou/Qwen3-8B-ReST-RL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SiningZhou/Qwen3-8B-ReST-RL

SGLang

How to use SiningZhou/Qwen3-8B-ReST-RL 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 "SiningZhou/Qwen3-8B-ReST-RL" \
    --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": "SiningZhou/Qwen3-8B-ReST-RL",
		"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 "SiningZhou/Qwen3-8B-ReST-RL" \
        --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": "SiningZhou/Qwen3-8B-ReST-RL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SiningZhou/Qwen3-8B-ReST-RL with Docker Model Runner:
```
docker model run hf.co/SiningZhou/Qwen3-8B-ReST-RL
```

Model Card for Qwen3-8B-ReST-RL

This model is trained with the ReST-RL paradigm, based on the Qwen3-8B model. It is trained for 2 reinforce iterations.

Quick start

from transformers import pipeline

question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="None", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

Framework versions

TRL: 0.19.1
Transformers: 4.51.3
Pytorch: 2.6.0
Datasets: 3.2.0
Tokenizers: 0.21.1

Citations

Cite ReST-RL as:

@misc{zhoubian2025restrlachievingaccuratecode,
      title={ReST-RL: Achieving Accurate Code Reasoning of LLMs with Optimized Self-Training and Decoding}, 
      author={Sining Zhoubian and Dan Zhang and Jie Tang},
      year={2025},
      eprint={2508.19576},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/abs/2508.19576}, 
}