Instructions to use qihoo360/Light-R1-14B-DS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use qihoo360/Light-R1-14B-DS with Transformers:

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

pipe = pipeline("text-generation", model="qihoo360/Light-R1-14B-DS")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("qihoo360/Light-R1-14B-DS")
model = AutoModelForCausalLM.from_pretrained("qihoo360/Light-R1-14B-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-R1-14B-DS with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "qihoo360/Light-R1-14B-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-R1-14B-DS",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/qihoo360/Light-R1-14B-DS

SGLang

How to use qihoo360/Light-R1-14B-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-R1-14B-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-R1-14B-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-R1-14B-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-R1-14B-DS",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use qihoo360/Light-R1-14B-DS with Docker Model Runner:
```
docker model run hf.co/qihoo360/Light-R1-14B-DS
```

Update README.md

by dyc-sh - opened Mar 14, 2025

base: refs/heads/main

←

from: refs/pr/3

Discussion Files changed

-4

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -16,11 +16,11 @@ base_model:
   <img width="80%" src="14b-rl.png">
 </p>
-[technical report](https://github.com/Qihoo360/Light-R1/blob/main/Light-R1.pdf)
-[GitHub page](https://github.com/Qihoo360/Light-R1)
-[wandb log](https://api.wandb.ai/links/seek4-nus/4klmwpqs)
 We introduce Light-R1-14B-DS, the first open-source successful RL attempt on already long-COT finetuned models of simialr sizes under **light** budget.
 Light-R1-14B-DS is also the State-Of-The-Art 14B math model with AIME24 & 25 scores 74.0 & 60.2, outperforming many 32B models.
@@ -32,7 +32,7 @@ We have finally seen expected behavior during RL training: simultaneous increase
 Originated from DeepSeek-R1-Distill-Qwen-14B, Light-R1-14B-DS underwent our long-COT RL Post-Training and achieved a new State-Of-The-Art across 14B-Math models: 74.0 & 60.2 on AIME 24 & 25 respectively.
 Light-R1-14B-DS also performed well on GPQA *without* any specific training.
-We are excited to release this model along with the [technical report](https://github.com/Qihoo360/Light-R1/blob/main/Light-R1.pdf), and will continue to perfect our long-COT RL Post-Training.
 ## Usage
 Same as DeepSeek-R1-Distill-Qwen-14B.

   <img width="80%" src="14b-rl.png">
 </p>
+[Technical Report](https://arxiv.org/pdf/2503.10460)
+[GitHub Page](https://github.com/Qihoo360/Light-R1)
+[Wandb Log](https://api.wandb.ai/links/seek4-nus/4klmwpqs)
 We introduce Light-R1-14B-DS, the first open-source successful RL attempt on already long-COT finetuned models of simialr sizes under **light** budget.
 Light-R1-14B-DS is also the State-Of-The-Art 14B math model with AIME24 & 25 scores 74.0 & 60.2, outperforming many 32B models.
 Originated from DeepSeek-R1-Distill-Qwen-14B, Light-R1-14B-DS underwent our long-COT RL Post-Training and achieved a new State-Of-The-Art across 14B-Math models: 74.0 & 60.2 on AIME 24 & 25 respectively.
 Light-R1-14B-DS also performed well on GPQA *without* any specific training.
+We are excited to release this model along with the [technical report](https://arxiv.org/pdf/2503.10460), and will continue to perfect our long-COT RL Post-Training.
 ## Usage
 Same as DeepSeek-R1-Distill-Qwen-14B.