import vllm


def apply_qwen_math_template(question: str):
    return (
        "<|im_start|>system\nPlease reason step by step, and put your final answer within \\boxed{}.<|im_end|>\n<|im_start|>user\n"
        + question
        + "<|im_end|>\n<|im_start|>assistant\n"
    )

def apply_r1_template(question: str):
    return (
        "A conversation between User and Assistant. The User asks a question, and the Assistant solves it. The Assistant first thinks about the reasoning process in the mind and then provides the User with the answer. "
        "The reasoning process is enclosed within <think> </think> and answer is enclosed within <answer> </answer> tags, respectively, i.e., <think> reasoning process here </think> <answer> answer here </answer>.\nUser: "
        + question
        + "\nAssistant: <think>"
    )

model_name = "sail/Qwen2.5-Math-1.5B-Oat-Zero"

sampling_params = vllm.SamplingParams(
    n=1,
    temperature=0,
    top_p=1,
    max_tokens=3000,
)

model = vllm.LLM(
    model_name,
    max_model_len=4096,
    dtype="bfloat16",
    enable_prefix_caching=True,
)

if "Llama-3.2-3B-Oat-Zero" in model_name:
    apply_template = apply_r1_template
else:
    apply_template = apply_qwen_math_template

prompts = [
    "How many positive whole-number divisors does 196 have?"
]
prompts = list(map(apply_template, prompts))
outputs = model.generate(prompts, sampling_params)

print(outputs)

Citation

latex

@article{liu2025understanding,
  title={Understanding r1-zero-like training: A critical perspective},
  author={Liu, Zichen and Chen, Changyu and Li, Wenjun and Qi, Penghui and Pang, Tianyu and Du, Chao and Lee, Wee Sun and Lin, Min},
  journal={arXiv preprint arXiv:2503.20783},
  year={2025}
}

sail/Qwen2.5-Math-1.5B-Oat-Zero

Qwen2.5-Math-1.5B-Oat-Zero

Links

Introduction

Usage

Citation

sail/
Qwen2.5-Math-1.5B-Oat-Zero