Instructions to use FINAL-Bench/Darwin-28B-KR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FINAL-Bench/Darwin-28B-KR with Transformers:

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

pipe = pipeline("text-generation", model="FINAL-Bench/Darwin-28B-KR")
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)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("FINAL-Bench/Darwin-28B-KR")
model = AutoModelForImageTextToText.from_pretrained("FINAL-Bench/Darwin-28B-KR")
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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use FINAL-Bench/Darwin-28B-KR with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FINAL-Bench/Darwin-28B-KR"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FINAL-Bench/Darwin-28B-KR",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FINAL-Bench/Darwin-28B-KR

SGLang

How to use FINAL-Bench/Darwin-28B-KR 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 "FINAL-Bench/Darwin-28B-KR" \
    --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": "FINAL-Bench/Darwin-28B-KR",
		"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 "FINAL-Bench/Darwin-28B-KR" \
        --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": "FINAL-Bench/Darwin-28B-KR",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use FINAL-Bench/Darwin-28B-KR with Docker Model Runner:
```
docker model run hf.co/FINAL-Bench/Darwin-28B-KR
```

Darwin-28B-KR / README.md

SeaWolf-AI

Initial release: Darwin-28B-KR — Korean-specialized 2nd-gen mother model

492de6f verified 22 days ago

3.85 kB

license: apache-2.0
language:
  - en
  - ko
base_model:
  - FINAL-Bench/Darwin-28B-Opus
  - FINAL-Bench/Darwin-27B-KR
pipeline_tag: text-generation
tags:
  - darwin
  - korean
  - reasoning
  - multimodal
  - qwen3.5
  - evolutionary-merge
library_name: transformers

Darwin-28B-KR

Darwin family 한국어 특화 2세대 모체 모델 28B 영어 추론력과 27B 한국어 능력을 통합한 Darwin V7 진화 머지 결과물.

🎯 모델 포지셔닝

Darwin-28B-KR은 Darwin family에서 한국어 특화 2세대 모델 개발의 모체(母體) 로 설계되었습니다.

이 모델 자체로 사용 가능하며, 향후 다양한 한국어 도메인 특화 모델(법률·의료·금융·학술 등)의 공통 출발점이 됩니다.

🧬 Lineage

Qwen3.5-27B (Alibaba Qwen team)
       │
       ▼
Darwin-27B-Opus (FINAL-Bench)
       │   Darwin V7 evolutionary merge
       │
   ┌───┴────────────────────────┐
   ▼                            ▼
Darwin-28B-Opus            Darwin-27B-KR
(English/reasoning         (Korean-specialized
 + multimodal)              champion)
   │                            │
   └────────┬───────────────────┘
            │ Darwin V7 MRI-aware merge
            ▼
       Darwin-28B-KR  ← this model (2nd-gen mother)

⚙️ 구성 능력

능력	출처	강도
한국어 이해/생성	Darwin-27B-KR 계열	⭐⭐⭐⭐⭐
영어 추론	Darwin-28B-Opus 계열	⭐⭐⭐⭐
멀티모달 (이미지/비디오)	Darwin-28B-Opus 보존	⭐⭐⭐⭐
한국어 추론 (CSAT/PSAT)	통합 효과	⭐⭐⭐⭐⭐
영한 코드스위칭	통합 효과	⭐⭐⭐⭐

📊 Specs


Architecture	Qwen3_5ForConditionalGeneration (hybrid full + linear attention)
Parameters	~28B
Hidden size	5120
Layers	64
Vocab size	248,320
Format	bfloat16 (52 GB on disk)
Context	8K~32K (deployment dependent)

🚀 Usage

vLLM (recommended)

vllm serve FINAL-Bench/Darwin-28B-KR \
    --trust-remote-code \
    --port 8000 \
    --enforce-eager \
    --max-model-len 8192 \
    --gpu-memory-utilization 0.85

OpenAI-compatible client

from openai import OpenAI

client = OpenAI(base_url="http://localhost:8000/v1", api_key="EMPTY")
response = client.chat.completions.create(
    model="FINAL-Bench/Darwin-28B-KR",
    messages=[{"role": "user", "content": "한국의 광복절은 무엇을 기념하는 날인가요?"}],
    max_tokens=2048,
    temperature=0.0,
)

🖥️ Hardware

GPU family	Status
NVIDIA Blackwell (B200)	✅ Best
NVIDIA Hopper (H100/H200)	✅ Recommended
NVIDIA Ada (L40S)	⚠️ Marginal (52 GB BF16)
Older Ampere	❌ Insufficient VRAM

Minimum VRAM: ~55 GB for inference at BF16.

🌳 2세대 도메인 특화 모델 개발 (예정)

이 모체에서 파생될 예정인 한국어 특화 변종들:

Darwin-28B-KR-Legal — 법률 도메인 SFT
Darwin-28B-KR-Medical — 의료 도메인 SFT
Darwin-28B-KR-Finance — 금융 도메인 SFT
Darwin-28B-KR-Code — 한국어 주석 코드 생성
Darwin-28B-KR-MFP4 — 메모리 효율 양자화 버전

각 변종은 이 모델을 base로 하여 도메인 데이터로 미세조정/머지됩니다.

🙏 Credits

Architecture lineage: Qwen3.5 (Alibaba Qwen team)
Father: FINAL-Bench/Darwin-28B-Opus
Mother: FINAL-Bench/Darwin-27B-KR
Merge methodology: Darwin V7 MRI-aware evolutionary merge

📜 License

Apache 2.0 (inherited from base models).