Instructions to use beyoru/Lunaa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use beyoru/Lunaa with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("beyoru/Lunaa")
model = AutoModelForCausalLM.from_pretrained("beyoru/Lunaa")
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 Settings

vLLM

How to use beyoru/Lunaa with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/beyoru/Lunaa

SGLang

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

Docker Model Runner
How to use beyoru/Lunaa with Docker Model Runner:
```
docker model run hf.co/beyoru/Lunaa
```

🌙 Lunaa – Roleplay Chat Model

Lunaa is a conversational AI model designed for immersive roleplay (RP) and natural chatting.
It is fine-tuned to respond in a more engaging, character-driven style compared to standard instruction-tuned models.

Notes:

Optimized for roleplay-style conversations
Flexible: can be used for creative writing, storytelling, or character interactions
You should describe the system prompt for your character.
Reasoning and non reasoning for fast interface as usage of Qwen3 (enable_thinking=True/False).

Cite:

@misc{Lunaa,
  title        = {Lunaa – Roleplay Chat Model},
  author       = {Beyoru},
  year         = {2025},
  howpublished = {\url{https://huggingface.co/beyoru/Lunaa}}
}

Downloads last month: 126

Safetensors

Model size

4B params

Tensor type

BF16

Collection including beyoru/Lunaa

RP/Storytelling - Luna-I

Collection

Roleplay • 7 items • Updated Apr 30 • 2