Instructions to use knoveleng/Open-RS3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use knoveleng/Open-RS3 with Transformers:

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

pipe = pipeline("text-generation", model="knoveleng/Open-RS3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("knoveleng/Open-RS3")
model = AutoModelForCausalLM.from_pretrained("knoveleng/Open-RS3", device_map="auto")
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 Settings

vLLM

How to use knoveleng/Open-RS3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "knoveleng/Open-RS3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "knoveleng/Open-RS3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/knoveleng/Open-RS3

SGLang

How to use knoveleng/Open-RS3 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 "knoveleng/Open-RS3" \
    --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": "knoveleng/Open-RS3",
		"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 "knoveleng/Open-RS3" \
        --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": "knoveleng/Open-RS3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use knoveleng/Open-RS3 with Docker Model Runner:
```
docker model run hf.co/knoveleng/Open-RS3
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Summary

This model enhances the reasoning capabilities of the small 1.5B parameter DeepSeek-R1-Distill-Qwen-1.5B LLM using reinforcement learning (RL). Trained efficiently on 4 A40 GPUs in under 24 hours, it achieves significant gains in mathematical reasoning benchmarks (e.g., 80% accuracy on AMC23, 46.7% on AIME24, surpassing o1-preview). This cost-effective approach demonstrates the potential of RL for boosting reasoning in resource-constrained settings.

Evaluation

Performance Highlights

Open-RS1: 53.0% avg. score
Open-RS2: 55.7% avg. score, 80.0% on AMC23
Open-RS3: 56.3% avg. score, 46.7% on AIME24 (outperforms o1-preview at 44.6%)
Competitive MATH-500 scores; Minerva lags behind 7B models.

Cost Efficiency

Our approach uses 7,000 samples (42,000 total outputs) and costs ~$42 on 4x A40 GPUs in 24 hours, compared to thousands of dollars for baseline models.

Citation

If this project aids your work, please cite it as:

@inproceedings{
    dang2026reinforcement,
    title={Reinforcement Learning for Reasoning in Small {LLM}s: What Works and What Doesn{\textquoteright}t},
    author={Quy-Anh Dang and Chris Ngo},
    booktitle={Logical and Symbolic Reasoning in Language Models @ AAAI 2026},
    year={2026},
    url={https://openreview.net/forum?id=3pWL6Zxc4A}
}

For more details, including usage instructions and further evaluation results, please refer to our GitHub repository.