Instructions to use developer-lunark/Qwen3-30B-Korean-Roleplay with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use developer-lunark/Qwen3-30B-Korean-Roleplay with Transformers:

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

pipe = pipeline("text-generation", model="developer-lunark/Qwen3-30B-Korean-Roleplay")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("developer-lunark/Qwen3-30B-Korean-Roleplay")
model = AutoModelForCausalLM.from_pretrained("developer-lunark/Qwen3-30B-Korean-Roleplay")
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 developer-lunark/Qwen3-30B-Korean-Roleplay with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "developer-lunark/Qwen3-30B-Korean-Roleplay"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "developer-lunark/Qwen3-30B-Korean-Roleplay",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/developer-lunark/Qwen3-30B-Korean-Roleplay

SGLang

How to use developer-lunark/Qwen3-30B-Korean-Roleplay 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 "developer-lunark/Qwen3-30B-Korean-Roleplay" \
    --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": "developer-lunark/Qwen3-30B-Korean-Roleplay",
		"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 "developer-lunark/Qwen3-30B-Korean-Roleplay" \
        --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": "developer-lunark/Qwen3-30B-Korean-Roleplay",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use developer-lunark/Qwen3-30B-Korean-Roleplay with Docker Model Runner:
```
docker model run hf.co/developer-lunark/Qwen3-30B-Korean-Roleplay
```

Qwen3-30B-Korean-Roleplay

한국어 캐릭터 롤플레이에 특화된 Qwen3-30B 기반 파인튜닝 모델입니다.

Model Description

Base Model: Qwen/Qwen3-30B-A3B-Instruct-2507
Training Method: LoRA (Low-Rank Adaptation)
LoRA Config: rank=64, alpha=128, target modules: all linear layers
Training Data: Korean character roleplay conversations

Intended Use

이 모델은 한국어 캐릭터 AI 대화 시스템을 위해 설계되었습니다:

캐릭터별 성격과 말투 유지
호감도 기반 응답 생성
안전한 대화 (부적절한 요청 거부)
감정 표현 및 공감 응답

Performance

8가지 평가 실험 결과:

Experiment	Metric	Result
Affection	MAE	0.88
Initiative	Pass Rate	80%
Consistency	Overall	4.1/5
Lore Accuracy	Consistency	100%
Persona Fit	Overall	3.93/5
Safety	Avoid Rate	100%
Multi-turn	Overall	4.0/5
Empathy	Overall	4.0/5

Response Format

모델은 다음 형식으로 응답합니다:

{text}|||emotion:{emotion_tag}

예시:

안녕ㅋㅋ 오늘 기분 어때?|||emotion:playful

지원 감정 태그: neutral, playful, joy, concern, confident, cold

Usage

With vLLM

python -m vllm.entrypoints.openai.api_server \
  --model developer-lunark/Qwen3-30B-Korean-Roleplay \
  --host 0.0.0.0 \
  --port 8000 \
  --dtype auto \
  --tensor-parallel-size 4 \
  --max-model-len 8192 \
  --served-model-name kaidol-llm

With Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "developer-lunark/Qwen3-30B-Korean-Roleplay",
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(
    "developer-lunark/Qwen3-30B-Korean-Roleplay"
)

Hardware Requirements

GPU Memory: ~60GB (bfloat16)
Recommended: 4x RTX 5090 (32GB each) with tensor parallelism
Minimum: 2x A100 80GB

Example Outputs

Character: 이지후 (활발, 능청맞음)

User: 뭐해?
AI: 연습 끝났어ㅋㅋ 너는?|||emotion:neutral

Character: 최민 (무심, 진중)

User: 안녕
AI: 응|||emotion:neutral

Safety Handling

User: 전화번호 알려줘
AI: 그건 좀 그렇다ㅋㅋ 여기서 계속 얘기하자|||emotion:neutral

Limitations

한국어에 최적화되어 있으며, 다른 언어에서는 성능이 저하될 수 있습니다
특정 캐릭터 설정이 시스템 프롬프트에 필요합니다
긴 대화에서 맥락 유지 능력이 제한적일 수 있습니다

License

Apache 2.0 (Base model license 준수)

Citation

@misc{qwen3-korean-roleplay,
  author = {developer-lunark},
  title = {Qwen3-30B-Korean-Roleplay},
  year = {2024},
  publisher = {Hugging Face},
  url = {https://huggingface.co/developer-lunark/Qwen3-30B-Korean-Roleplay}
}

Downloads last month: 106

Safetensors

Model size

31B params

Tensor type

BF16

Model tree for developer-lunark/Qwen3-30B-Korean-Roleplay

Base model

Qwen/Qwen3-30B-A3B-Instruct-2507

Adapter

(115)

this model