inclusionAI/Ring

inclusionAI/Ring

Description: Ring is a reasoning MoE LLM provided and open-sourced by InclusionAI, derived from Ling.

Language: Python

License: MIT

Stars: 110

Forks: 2

Open issues: 2

Created: 2025-03-28T12:44:30Z

Pushed: 2025-08-05T05:48:56Z

Default branch: main

Fork: no

Archived: no

README:

Ring

🤗 Hugging Face&nbsp&nbsp | &nbsp&nbsp🤖 ModelScope

News

• [2025-07]:🎉 Add Ring-lite-2507 Model
• [2025-06]:🎉 Add Ring-lite Model
• [2025-04]:🎉 Add [Ring-lite-linear-preview](hybrid_linear) Model

Introduction

Ring is a reasoning MoE LLM provided and open-sourced by InclusionAI, derived from Ling. We introduce Ring-lite-distill-preview, which has 16.8 billion parameters with 2.75 billion activated parameters. This model demonstrates impressive reasoning performance compared to existing models in the industry.

Model Downloads

You can download the following table to see the various parameters for your use case. If you are located in mainland China, we also provide the model on ModelScope.cn to speed up the download process.

Blog

https://inclusionai.github.io/blog/ring-lite-2507/

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"

model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype="auto",
device_map="auto",
trust_remote_code=True,
)
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]

🤖 ModelScope

If you're in mainland China, we strongly recommend you to use our model from 🤖 ModelScope.

Deployment

Please refer to Ling

Finetuning

Please refer to Ling

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},
}