Instructions to use sooh098/midmb-kculture-qa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sooh098/midmb-kculture-qa with Transformers:

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

pipe = pipeline("text-generation", model="sooh098/midmb-kculture-qa")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sooh098/midmb-kculture-qa")
model = AutoModelForCausalLM.from_pretrained("sooh098/midmb-kculture-qa")
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 sooh098/midmb-kculture-qa with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sooh098/midmb-kculture-qa"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sooh098/midmb-kculture-qa",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sooh098/midmb-kculture-qa

SGLang

How to use sooh098/midmb-kculture-qa 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 "sooh098/midmb-kculture-qa" \
    --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": "sooh098/midmb-kculture-qa",
		"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 "sooh098/midmb-kculture-qa" \
        --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": "sooh098/midmb-kculture-qa",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use sooh098/midmb-kculture-qa with Docker Model Runner:
```
docker model run hf.co/sooh098/midmb-kculture-qa
```

🏛️ 과제 개요

본 모델은 국립국어원 ‘AI 말평 경진대회’의
「[2025]한국문화 질의응답」 과제를 위해 개발되었습니다.

🧑‍💻 팀명: 다마고치

🔤 Korean Culture QA Model (한국 문화 QA)

본 모델은 위 과제 수행을 위해 설계된 한국 문화 QA 모델입니다.

📌 모델 개요

베이스 모델: K-intelligence/Midm-2.0-Base-Instruct
파인튜닝 방식: QLoRA(4bit) 기반 LoRA 어댑터 미세조정(PEFT)
사용 목적: 한국 문화 기반의 QA 태스크 (선다형, 단답형, 서술형)

📎 참고

데이터 출처: [2025]한국문화 질의응답(가 유형)

Downloads last month: 1

Safetensors

Model size

12B params

Tensor type

F16

Model tree for sooh098/midmb-kculture-qa

Base model

K-intelligence/Midm-2.0-Base-Instruct

Finetuned

(4)

this model