Instructions to use dnotitia/DNA-2.1-14B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dnotitia/DNA-2.1-14B with Transformers:

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

pipe = pipeline("text-generation", model="dnotitia/DNA-2.1-14B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dnotitia/DNA-2.1-14B")
model = AutoModelForCausalLM.from_pretrained("dnotitia/DNA-2.1-14B", 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 dnotitia/DNA-2.1-14B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dnotitia/DNA-2.1-14B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dnotitia/DNA-2.1-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dnotitia/DNA-2.1-14B

SGLang

How to use dnotitia/DNA-2.1-14B 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 "dnotitia/DNA-2.1-14B" \
    --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": "dnotitia/DNA-2.1-14B",
		"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 "dnotitia/DNA-2.1-14B" \
        --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": "dnotitia/DNA-2.1-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use dnotitia/DNA-2.1-14B with Docker Model Runner:
```
docker model run hf.co/dnotitia/DNA-2.1-14B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

DNA 2.1

DNA 2.1 is a fine-tuned Qwen3 14B model that thinks natively in Korean through a two-stage training approach. This model is released alongside the paper Making Qwen3 Think in Korean with Reinforcement Learning.

Key Features

Two-Stage Training Approach: Supervised fine-tuning (SFT) on high-quality Korean reasoning datasets followed by reinforcement learning with our proposed Oracle-Guided Dr. GRPO algorithm
Native Korean Thinking: Conducts internal chain-of-thought reasoning entirely in Korean
Stable RL Training: Addresses reward hacking and policy collapse through oracle judge model for reward signal calibration
Enhanced Reasoning Performance: Substantially improved results on advanced reasoning benchmarks, particularly in math and coding tasks
Preserved Knowledge & Language Proficiency: Maintains existing knowledge and language capabilities after reinforcement learning

Base Model

This model builds upon Smoothie Qwen3, which reduces Chinese token emission probabilities and enhances Korean reasoning capabilities.

Citation

If you use this model in your research, please cite our paper:

@misc{lee2025makingqwen3thinkkorean,
      title={Making Qwen3 Think in Korean with Reinforcement Learning}, 
      author={Jungyup Lee and Jemin Kim and Sang Park and SeungJae Lee},
      year={2025},
      eprint={2508.10355},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2508.10355}, 
}