Instructions to use qihoo360/Light-R1-32B-DS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use qihoo360/Light-R1-32B-DS with Transformers:

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

pipe = pipeline("text-generation", model="qihoo360/Light-R1-32B-DS")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("qihoo360/Light-R1-32B-DS")
model = AutoModelForCausalLM.from_pretrained("qihoo360/Light-R1-32B-DS")
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 qihoo360/Light-R1-32B-DS with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "qihoo360/Light-R1-32B-DS"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "qihoo360/Light-R1-32B-DS",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/qihoo360/Light-R1-32B-DS

SGLang

How to use qihoo360/Light-R1-32B-DS 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 "qihoo360/Light-R1-32B-DS" \
    --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": "qihoo360/Light-R1-32B-DS",
		"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 "qihoo360/Light-R1-32B-DS" \
        --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": "qihoo360/Light-R1-32B-DS",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use qihoo360/Light-R1-32B-DS with Docker Model Runner:
```
docker model run hf.co/qihoo360/Light-R1-32B-DS
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Light-R1-32B-DS: near-SOTA 32B Math Model with Only 3K Data

Paper: https://huggingface.co/papers/2503.10460

Model	Trained From	Release Date	AIME24	AIME25	GPQA
DeepSeek-R1-Distill-Qwen-32B	Qwen2.5-32B	25.1.20	72.6	54.9	62.1
TinyR1-32B-Preview	DeepSeek-R1-Distill-Qwen-32B	25.2.25	77.1	65.9	65.0
Light-R1-32B-DS (ours) 🤗	DeepSeek-R1-Distill-Qwen-32B	25.3.12	78.1	65.9	68.0
Light-R1-32B (ours) 🤗	Qwen2.5-32B-Instruct	25.3.4	76.6	64.6	61.8
QwQ-32B	N/A	25.3.6	78.5	69.3	67.7

technical report

GitHub page

Light-R1-32B-DS is a near-SOTA 32B math model with AIME24 & 25 scores 78.1 & 65.9.

Originated from DeepSeek-R1-Distill-Qwen-32B, Light-R1-32B-DS is further trained with only 3K SFT data as we've open-sourced, demonstrating the strong applicability of the released data.

We are excited to release this model along with the technical report.

Usage

Same as DeepSeek-R1-Distill-Qwen-32B.

Data Decontamination

We carefully evaluated data contamination of several open-sourced datasets. While certain contamination may be inevitable during pre-training, it is unacceptable for post-training to compare on benchmarks. MATH-500 is somewhat compromised with tens of questions that are identical or only numbers changed. AIME 24 and 25 stay intact but we have to pay special attention when we incorporate AIME data up to 2023.

Light-R1 did thorough decontamination with exact matching (excluding digits) and N-gram (N=32) matching.

Citation

@misc{lightr1proj,
      title={Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond}, 
      author={Liang Wen, Yunke Cai, Fenrui Xiao, Xin He, Qi An, Zhenyu Duan, Yimin Du, Junchen Liu, Lifu Tang, Xiaowei Lv, Haosheng Zou, Yongchao Deng, Shousheng Jia, Xiangzheng Zhang},
      year={2025},
      eprint={},
      archivePrefix={},
      url={https://github.com/Qihoo360/Light-R1}, 
}