Instructions to use qihoo360/Light-R1-7B-DS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use qihoo360/Light-R1-7B-DS with Transformers:

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

pipe = pipeline("text-generation", model="qihoo360/Light-R1-7B-DS")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("qihoo360/Light-R1-7B-DS")
model = AutoModelForCausalLM.from_pretrained("qihoo360/Light-R1-7B-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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use qihoo360/Light-R1-7B-DS with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "qihoo360/Light-R1-7B-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-R1-7B-DS",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/qihoo360/Light-R1-7B-DS

SGLang

How to use qihoo360/Light-R1-7B-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-R1-7B-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-R1-7B-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-R1-7B-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-R1-7B-DS",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use qihoo360/Light-R1-7B-DS with Docker Model Runner:
```
docker model run hf.co/qihoo360/Light-R1-7B-DS
```

zhs12 commited on Mar 14, 2025

Commit

44e3134

verified ·

1 Parent(s): b5726e1

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -1

README.md CHANGED Viewed

@@ -13,6 +13,8 @@ base_model:
 | [**Light-R1-7B-DS (ours)** 🤗](https://huggingface.co/qihoo360/Light-R1-7B-DS) |DeepSeek-R1-Distill-Qwen-7B|25.3.12|**59.1**|**44.3**|**49.4**|
 | [Light-R1-32B (ours) 🤗](https://huggingface.co/qihoo360/Light-R1-32B) |Qwen2.5-32B-Instruct|25.3.4|76.6|64.6|61.8|
 [GitHub page](https://github.com/Qihoo360/Light-R1)
@@ -21,7 +23,7 @@ Light-R1-7B-DS also performed well on GPQA *without* any specific training.
 Originated from DeepSeek-R1-Distill-Qwen-7B, Light-R1-7B-DS is further trained with only [3K SFT data](https://huggingface.co/datasets/qihoo360/Light-R1-SFTData) 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](https://github.com/Qihoo360/Light-R1/blob/main/Light-R1.pdf).
 ## Usage
 Same as DeepSeek-R1-Distill-Qwen-7B.

 | [**Light-R1-7B-DS (ours)** 🤗](https://huggingface.co/qihoo360/Light-R1-7B-DS) |DeepSeek-R1-Distill-Qwen-7B|25.3.12|**59.1**|**44.3**|**49.4**|
 | [Light-R1-32B (ours) 🤗](https://huggingface.co/qihoo360/Light-R1-32B) |Qwen2.5-32B-Instruct|25.3.4|76.6|64.6|61.8|
+[technical report](https://arxiv.org/abs/2503.10460)
 [GitHub page](https://github.com/Qihoo360/Light-R1)
 Originated from DeepSeek-R1-Distill-Qwen-7B, Light-R1-7B-DS is further trained with only [3K SFT data](https://huggingface.co/datasets/qihoo360/Light-R1-SFTData) 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](https://arxiv.org/abs/2503.10460).
 ## Usage
 Same as DeepSeek-R1-Distill-Qwen-7B.