Ring-lite-2506

Ring-lite-2506

<p align="center"> <img src="https://mdn.alipayobjects.com/huamei_qa8qxu/afts/img/A*4QxcQrBlTiAAAAAAQXAAAAgAemJ7AQ/original" width="100"/> <p> <p align="center"> 🤗 <a href="https://huggingface.co/inclusionAI">Hugging Face</a> <p>

Introduction

Ring-lite-2506 is a lightweight, fully open-sourced MoE (Mixture of Experts) LLM designed for complex reasoning tasks. It is built upon the publicly available Ling-lite-1.5 model, which has 16.8B parameters with 2.75B activated parameters. We use a joint training pipeline combining knowledge distillation with reinforcement learning, achieving performance comparable to state-of-the-art (SOTA) small-size reasoning models on challenging benchmarks (AIME, LiveCodeBench, and GPQA-Diamond) while activating only one-third of their parameters.

Model Downloads

<div align="center"> </div>

Evaluation

For a comprehensive evaluation of the quality of our reasoning models, we implemented automatic benchmarks to assess their performance including math, code and science.

<p align="center"> <img src="https://mdn.alipayobjects.com/huamei_qa8qxu/afts/img/A*iAXESaxrbDcAAAAATtAAAAgAemJ7AQ/original" width="1000"/> <p>

More details are reported in our technical report.

Quickstart

🤗 Hugging Face Transformers

Here is a code snippet to show you how to use the chat model with transformers:

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "inclusionAI/Ring-lite-2506"

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

prompt = "Give me a short introduction to large language models."
messages = [
    {"role": "system", "content": "You are Ring, an assistant created by inclusionAI"},
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.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]

Dataset

The training data of Ring-lite-2506 is release at Ring-lite-sft-data and Ring-lite-rl-data.

Deployment

Please refer to GitHub

License

This code repository is licensed under the MIT License.

Citation

@misc{ringteam2025ringlitescalablereasoningc3postabilized,
      title={Ring-lite: Scalable Reasoning via C3PO-Stabilized Reinforcement Learning for LLMs}, 
      author={Ling Team},
      year={2025},
      eprint={2506.14731},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2506.14731}, 
}