SvS-LLama-8B

Model Card for SvS-8B (from LLaMA3.1-8B-Instruct)

<p align="left"> <a href="https://mastervito.github.io/SvS.github.io/"><b>[🌐 Website]</b></a> • <a href="https://huggingface.co/datasets/RLVR-SvS/Variational-DAPO"><b>[🤗 Dataset]</b></a> • <a href="https://huggingface.co/RLVR-SvS"><b>[🤖 Models]</b></a> • <a href="https://arxiv.org/abs/2508.14029"><b>[📜 Paper]</b></a> • <a href="https://github.com/MasterVito/SvS"><b>[🐱 GitHub]</b></a> • <a href="https://huggingface.co/datasets/RLVR-SvS/Variational-DAPO"><b>[🐦 Twitter]</b></a> • <a href="https://huggingface.co/datasets/RLVR-SvS/Variational-DAPO"><b>[📕 Rednote]</b></a> </p>

The official model checkpoints for <a href="https://arxiv.org/abs/2508.14029"><b>SvS</b></a>. The SvS model is trained on the MATH-12k dataset (included in this repository as <code>MATH_12k.parquet</code>).

Inference

We recommend using our official inference template, which is inspired by the chat template of the Qwen2.5-Math series.

model_name = "RLVR-SvS/SvS-LLama-8B"
device = "cuda" # the device to load the model onto

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "Find the value of $x$ that satisfies the equation $4x+5 = 6x+7$."

messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": prompt}
]

text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=8192
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]

Cite Us

If you find the model helpful, please consider citing our paper:

@misc{liang2025pass1selfplayvariationalproblem,
      title={Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR}, 
      author={Xiao Liang and Zhongzhi Li and Yeyun Gong and Yelong Shen and Ying Nian Wu and Zhijiang Guo and Weizhu Chen},
      year={2025},
      eprint={2508.14029},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2508.14029}, 
}