Instructions to use Warecube/Warecube-KO-27B-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Warecube/Warecube-KO-27B-v3 with Transformers:

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

pipe = pipeline("image-text-to-text", model="Warecube/Warecube-KO-27B-v3")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Warecube/Warecube-KO-27B-v3")
model = AutoModelForMultimodalLM.from_pretrained("Warecube/Warecube-KO-27B-v3", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Warecube/Warecube-KO-27B-v3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Warecube/Warecube-KO-27B-v3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Warecube/Warecube-KO-27B-v3",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/Warecube/Warecube-KO-27B-v3

SGLang

How to use Warecube/Warecube-KO-27B-v3 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 "Warecube/Warecube-KO-27B-v3" \
    --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": "Warecube/Warecube-KO-27B-v3",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "Warecube/Warecube-KO-27B-v3" \
        --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": "Warecube/Warecube-KO-27B-v3",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use Warecube/Warecube-KO-27B-v3 with Docker Model Runner:
```
docker model run hf.co/Warecube/Warecube-KO-27B-v3
```

Warecube-KO-27B-v2

한국어 reasoning 모델 — Darwin 진화 + 추가 SFT 정제 변종.

🧬 Darwin 진화 컨셉

본 모델은 Darwin V7 진화적 모델 머지 기반의 부모 모델에 한국어 K-AI 도메인 SFT를 추가 학습한 자식 모델입니다.

   자연 진화                    Darwin 머지 + SFT
   ─────────                    ───────────────────
   유전자 교차              →   가중치 모듈별 비율 결합 (부모)
   세대 진화                →   부모 모델에 추가 SFT 정제
   적자 생존                →   K-AI 도메인 우수 자손 보존

🏛️ 가문 계보

┌────────────────────────────────────────┐
│  베이스 (Base / Parent)                 │
│  ginigen-ai/Rogue-28B-MIX              │
│                                          │
│  - K-AI Leaderboard 2위 (avg 0.559)    │
│  - Darwin family + Quetta 진화 머지     │
│  - <think> reasoning trace              │
└────────────────────────────────────────┘
                  │
                  ▼ K-AI 도메인 추가 SFT 진화
╔════════════════════════════════════════╗
║  자식 (Child) — 본 모델                  ║
║  Warecube/Warecube-KO-27B-v2           ║
║                                          ║
║  ✦ 베이스의 모든 능력 계승               ║
║  ✦ Com2-main 도메인 강화                ║
║  ✦ K-AI Leaderboard Docker 호환 형식     ║
╚════════════════════════════════════════╝

🎓 학습 개요

Stage	개략
Base	ginigen-ai/Rogue-28B-MIX (Darwin family × Quetta family 진화 머지)
SFT	한국어 K-AI 도메인 instruction 데이터로 추가 정제
호환	K-AI Leaderboard Docker 호환 형식으로 정비

🎯 사용법

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "Warecube/Warecube-KO-27B-v2"
tokenizer = AutoTokenizer.from_pretrained(
    model_id, trust_remote_code=True
)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True,
)

prompt = "한국의 추석에 대해 설명해주세요."
messages = [{"role": "user", "content": prompt}]
inputs = tokenizer.apply_chat_template(
    messages, return_tensors="pt", add_generation_prompt=True
)
out = model.generate(
    inputs.to(model.device),
    max_new_tokens=512,
    do_sample=False,
)
print(tokenizer.decode(out[0], skip_special_tokens=False))