Instructions to use Saxo/Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Saxo/Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B with Transformers:

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

pipe = pipeline("text-generation", model="Saxo/Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Saxo/Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B")
model = AutoModelForCausalLM.from_pretrained("Saxo/Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B", device_map="auto")
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

llama.cpp

How to use Saxo/Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Saxo/Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Saxo/Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Saxo/Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Saxo/Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Saxo/Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Saxo/Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Saxo/Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Saxo/Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B:Q4_K_M

Use Docker

docker model run hf.co/Saxo/Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B:Q4_K_M

LM Studio
Jan

vLLM

How to use Saxo/Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Saxo/Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Saxo/Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Saxo/Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B:Q4_K_M

SGLang

How to use Saxo/Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B 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 "Saxo/Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B" \
    --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": "Saxo/Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B",
		"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 "Saxo/Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B" \
        --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": "Saxo/Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Saxo/Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B with Ollama:
```
ollama run hf.co/Saxo/Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use Saxo/Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B with Docker Model Runner:
```
docker model run hf.co/Saxo/Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B:Q4_K_M
```

Lemonade

How to use Saxo/Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Saxo/Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B:Q4_K_M

Run and chat with the model

lemonade run user.Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B-Q4_K_M

List all available models

lemonade list

Atomic Chat

Model Card for Model ID

Open Ko LLM Leaderboard Season 2 🏆 Rank-1 2024/11/01~2024/12/28

AI 와 빅데이터 분석 전문 기업인 Linkbricks Horizon-AI의 데이터사이언티스트인 지윤성(Saxo) 대표가 gemma-2-27b-it 베이스모델을 H100-80G 8개를 통해 SFT->DPO 파인 튜닝을 한 한글 언어 모델로 한국어-중국어-영어-일본어 교차 학습 데이터와 로지컬 데이터를 통하여 한중일영 언어 교차 증강 처리와 복잡한 한글 논리 문제 역시 대응 가능하도록 훈련한 모델이며 토크나이저는 단어 확장 없이 베이스 모델 그대로 사용. 특히 고객 리뷰나 소셜 포스팅 고차원 분석 및 코딩과 욕설, 비방, 음란물, 성적으로 노골적인 콘텐츠, 인종차별 또는 기타 유해 콘텐츠 탐지 개인정보 및 민감정보 패턴 탐지, 차단 또는 사용자 경고가 필요할 수 있는 기타 고위험 요청 탐지 강화된 모델
-Deepspeed Stage=3, rslora 및 BAdam Layer Mode 사용
Linkbricks Horizon-AI CEO and data scientist Yunsung Ji (Saxo) developed a Korean-specialized large language model based on Gemma-2-27B-IT, fine-tuned through a two-stage SFT → DPO pipeline using eight NVIDIA H100 80GB GPUs. The model was trained on cross-lingual datasets spanning Korean, Chinese, English, and Japanese, together with logical reasoning datasets. This enables cross-lingual knowledge augmentation and reasoning across all four languages, while significantly improving its ability to handle complex Korean-language logical reasoning tasks. The model retains the original Gemma-2-27B-IT tokenizer without additional vocabulary expansion, preserving compatibility with the base model architecture. It is particularly optimized for high-dimensional analysis of customer reviews and social media posts, as well as coding and content-safety applications. Its safety capabilities have been strengthened to detect potentially harmful content, including profanity, harassment and defamation, sexually explicit or obscene material, racist or discriminatory content, and other forms of harmful content. The model also provides enhanced detection of personally identifiable information (PII) and sensitive-information patterns, along with improved identification of high-risk requests that may require blocking, additional safeguards, or user warnings. -ollama run benedict/linkbricks-gemma2-korean:27b
Benchmark (Open Ko LLM Leader Board Season 2 : No. 1)
Model : Saxo/Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B
Average : 51.37
Ko-GPQA : 25.25
Ko-Winogrande : 68.27
Ko-GSM8k : 70.96
Ko-EQ Bench : 50.25
Ko-IFEval : 49.84
KorNAT-CKA : 34.59
KorNAT-SVA : 48.42
Ko-Harmlessness : 65.66
Ko-Helpfulness : 49.12

CEO Yunsung Ji (Saxo), a data scientist at Linkbricks Horizon-AI, a company specializing in AI and big data analytics, fine-tuned the gemma-2-27b-it base model with SFT->DPO using four H100-80Gs. It is a Korean language model trained to handle complex Korean logic problems through Korean-Chinese-English-Japanese cross-training data and logical data, and Tokenizer uses the base model without word expansion.

www.horizonai.ai, www.linkbricks.com, www.linkbricks.vc

Downloads last month: 899

Safetensors

Model size

27B params

Tensor type

BF16

Model tree for Saxo/Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B

Base model

google/gemma-2-27b

Finetuned

google/gemma-2-27b-it

Quantized

(60)

this model

Saxo
/

Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B

Model Card for Model ID

Model tree for Saxo/Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B

Datasets used to train Saxo/Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B

Space using Saxo/Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B 1