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
```

12 x H800 machines

by Armaan11 - opened Mar 17, 2025

Discussion

Armaan11

Mar 17, 2025

•

edited Mar 17, 2025

What are you referring to here? H800 GPU's or the DGX H800 machine (https://viperatech.com/shop/nvidia-dgx-h800-systems/?srsltid=AfmBOopC5v10W0UDH7GQo-wDkNdU4GCuTPJm2-blFUYWCFwOOq5URDvcXsw&gQT=2)?

How do you get to the 1000 dollar cost? A H100 chip is 3$/h. 6 hours on 12 chips is 216$ for the 32B model. Do you have estimates for the 14B model? Are any merges done for the -DS models to achieve the shown benchmark scores?

zhs12

北京奇虎科技有限公司 org Apr 18, 2025

H800 GPUs.
8 GPUs per machine
12 machines

zhs12 changed discussion status to closed Apr 18, 2025

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment