Text Generation
Transformers
Safetensors
Korean
English
qwen3_5
image-text-to-text
darwin
korean
reasoning
multimodal
qwen3.5
evolutionary-merge
vidraft
conversational
Instructions to use FINAL-Bench/Darwin-28B-KR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
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
| 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 출발점**이 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) | |
| ```bash | |
| 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 | |
| ```python | |
| 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](https://huggingface.co/FINAL-Bench/Darwin-28B-Opus) | |
| - Mother: [FINAL-Bench/Darwin-27B-KR](https://huggingface.co/FINAL-Bench/Darwin-27B-KR) | |
| - Merge methodology: Darwin V7 MRI-aware evolutionary merge | |
| ## 📜 License | |
| Apache 2.0 (inherited from base models). | |