Instructions to use RLHFlow/Qwen2.5-Math-7B-Zero-Reinforce-Rej with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RLHFlow/Qwen2.5-Math-7B-Zero-Reinforce-Rej with Transformers:

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

pipe = pipeline("text-generation", model="RLHFlow/Qwen2.5-Math-7B-Zero-Reinforce-Rej")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RLHFlow/Qwen2.5-Math-7B-Zero-Reinforce-Rej")
model = AutoModelForCausalLM.from_pretrained("RLHFlow/Qwen2.5-Math-7B-Zero-Reinforce-Rej")
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

vLLM

How to use RLHFlow/Qwen2.5-Math-7B-Zero-Reinforce-Rej with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RLHFlow/Qwen2.5-Math-7B-Zero-Reinforce-Rej"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RLHFlow/Qwen2.5-Math-7B-Zero-Reinforce-Rej",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RLHFlow/Qwen2.5-Math-7B-Zero-Reinforce-Rej

SGLang

How to use RLHFlow/Qwen2.5-Math-7B-Zero-Reinforce-Rej 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 "RLHFlow/Qwen2.5-Math-7B-Zero-Reinforce-Rej" \
    --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": "RLHFlow/Qwen2.5-Math-7B-Zero-Reinforce-Rej",
		"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 "RLHFlow/Qwen2.5-Math-7B-Zero-Reinforce-Rej" \
        --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": "RLHFlow/Qwen2.5-Math-7B-Zero-Reinforce-Rej",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RLHFlow/Qwen2.5-Math-7B-Zero-Reinforce-Rej with Docker Model Runner:
```
docker model run hf.co/RLHFlow/Qwen2.5-Math-7B-Zero-Reinforce-Rej
```

Reinforce-Rej baseline from `Qwen-Math-7B-base`.

If you found useful, please consider cite,

@inproceedings{Xiong2025AMA,
  title={A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforce},
  author={Wei Xiong and Jiarui Yao and Yuhui Xu and Bo Pang and Lei Wang and Doyen Sahoo and Junnan Li and Nan Jiang and Tong Zhang and Caiming Xiong and Hanze Dong},
  journal={arXiv preprint arXiv:2504.11343},
  year={2025},
}