Instructions to use Saxo/Linkbricks-Horizon-AI-Korean-llama3.1-sft-dpo-70B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Saxo/Linkbricks-Horizon-AI-Korean-llama3.1-sft-dpo-70B with Transformers:

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

pipe = pipeline("text-generation", model="Saxo/Linkbricks-Horizon-AI-Korean-llama3.1-sft-dpo-70B")
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-llama3.1-sft-dpo-70B")
model = AutoModelForCausalLM.from_pretrained("Saxo/Linkbricks-Horizon-AI-Korean-llama3.1-sft-dpo-70B")
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]:]))

llama-cpp-python

How to use Saxo/Linkbricks-Horizon-AI-Korean-llama3.1-sft-dpo-70B with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Saxo/Linkbricks-Horizon-AI-Korean-llama3.1-sft-dpo-70B",
	filename="ggml-model-q4_k_m.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Inference
Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Saxo/Linkbricks-Horizon-AI-Korean-llama3.1-sft-dpo-70B with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Saxo/Linkbricks-Horizon-AI-Korean-llama3.1-sft-dpo-70B:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Saxo/Linkbricks-Horizon-AI-Korean-llama3.1-sft-dpo-70B:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Saxo/Linkbricks-Horizon-AI-Korean-llama3.1-sft-dpo-70B:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Saxo/Linkbricks-Horizon-AI-Korean-llama3.1-sft-dpo-70B: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-llama3.1-sft-dpo-70B:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Saxo/Linkbricks-Horizon-AI-Korean-llama3.1-sft-dpo-70B: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-llama3.1-sft-dpo-70B:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Saxo/Linkbricks-Horizon-AI-Korean-llama3.1-sft-dpo-70B:Q4_K_M

Use Docker

docker model run hf.co/Saxo/Linkbricks-Horizon-AI-Korean-llama3.1-sft-dpo-70B:Q4_K_M

LM Studio
Jan

vLLM

How to use Saxo/Linkbricks-Horizon-AI-Korean-llama3.1-sft-dpo-70B 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-llama3.1-sft-dpo-70B"
# 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-llama3.1-sft-dpo-70B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Saxo/Linkbricks-Horizon-AI-Korean-llama3.1-sft-dpo-70B:Q4_K_M

SGLang

How to use Saxo/Linkbricks-Horizon-AI-Korean-llama3.1-sft-dpo-70B 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-llama3.1-sft-dpo-70B" \
    --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-llama3.1-sft-dpo-70B",
		"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-llama3.1-sft-dpo-70B" \
        --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-llama3.1-sft-dpo-70B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Saxo/Linkbricks-Horizon-AI-Korean-llama3.1-sft-dpo-70B with Ollama:
```
ollama run hf.co/Saxo/Linkbricks-Horizon-AI-Korean-llama3.1-sft-dpo-70B:Q4_K_M
```

Unsloth Studio new

How to use Saxo/Linkbricks-Horizon-AI-Korean-llama3.1-sft-dpo-70B with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Saxo/Linkbricks-Horizon-AI-Korean-llama3.1-sft-dpo-70B to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Saxo/Linkbricks-Horizon-AI-Korean-llama3.1-sft-dpo-70B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Saxo/Linkbricks-Horizon-AI-Korean-llama3.1-sft-dpo-70B to start chatting

Docker Model Runner
How to use Saxo/Linkbricks-Horizon-AI-Korean-llama3.1-sft-dpo-70B with Docker Model Runner:
```
docker model run hf.co/Saxo/Linkbricks-Horizon-AI-Korean-llama3.1-sft-dpo-70B:Q4_K_M
```

Lemonade

How to use Saxo/Linkbricks-Horizon-AI-Korean-llama3.1-sft-dpo-70B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Saxo/Linkbricks-Horizon-AI-Korean-llama3.1-sft-dpo-70B:Q4_K_M

Run and chat with the model

lemonade run user.Linkbricks-Horizon-AI-Korean-llama3.1-sft-dpo-70B-Q4_K_M

List all available models

lemonade list

Model Card for Model ID

AI 전문 기업인 Linkbricks Horizon-AI 의 데이터사이언티스트인 지윤성(Saxo) 대표가
NousResearch/Meta-Llama-3.1-70B-Instruct 베이스모델을 KT-CLOUD상의 H100-80G 4개를 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 코딩등이 강화된 모델, 128k-Context Window, Tool Calling 지원, 애국가 가사를 정확히 아는 모델 입니다 ^^ Deepspeed Stage=3, rslora 를 사용
ollama run benedict/linkbricks-llama3.1-korean:70b

CEO Yunsung Ji (Saxo), a data scientist at Linkbricks Horizon-AI, a company specializing in AI and big data analytics, fine-tuned the NousResearch/Meta-Llama-3.1-70B-Instruct base model with SFT->DPO using four H100-80Gs on KT-CLOUD. 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.linkbricks.com, www.linkbricks.vc