Instructions to use Chang-chih/leviathan-chat-9b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Chang-chih/leviathan-chat-9b 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 Chang-chih/leviathan-chat-9b
# Run inference directly in the terminal:
llama cli -hf Chang-chih/leviathan-chat-9b

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Chang-chih/leviathan-chat-9b
# Run inference directly in the terminal:
llama cli -hf Chang-chih/leviathan-chat-9b

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 Chang-chih/leviathan-chat-9b
# Run inference directly in the terminal:
./llama-cli -hf Chang-chih/leviathan-chat-9b

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 Chang-chih/leviathan-chat-9b
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Chang-chih/leviathan-chat-9b

Use Docker

docker model run hf.co/Chang-chih/leviathan-chat-9b

LM Studio
Jan

vLLM

How to use Chang-chih/leviathan-chat-9b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Chang-chih/leviathan-chat-9b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Chang-chih/leviathan-chat-9b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Chang-chih/leviathan-chat-9b

Ollama
How to use Chang-chih/leviathan-chat-9b with Ollama:
```
ollama run hf.co/Chang-chih/leviathan-chat-9b
```
Unsloth Desktop
Docker Model Runner
How to use Chang-chih/leviathan-chat-9b with Docker Model Runner:
```
docker model run hf.co/Chang-chih/leviathan-chat-9b
```

Lemonade

How to use Chang-chih/leviathan-chat-9b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Chang-chih/leviathan-chat-9b

Run and chat with the model

lemonade run user.leviathan-chat-9b-{{QUANT_TAG}}

List all available models

lemonade list

Atomic Chat

🐋 Leviathan-Chat-9B

This is a GGUF version of the Leviathan Legion's strategic advisor model.

Model Details

Base Model: Google Gemma-2-9B
Format: GGUF
Size: 18 GB
Purpose: Strategic analysis using Sun Tzu's "The Art of War"

Usage

ollama run leviathan-chat-9b "你的問題"
Gemma Terms of Use
# Leviathan-Chat-9B (利維坦參謀模型)

本模型是「利維坦軍團」的核心參謀 AI，基於高效率參謀架構打造。它專注於戰術分析、防禦部署及複雜決策支援。

## 戰術定位 (Model Overview)
* **架構**：高效率緊湊型架構 (Dense Optimized)，繼承利維坦軍團的參謀思維邏輯。
* **戰略職責**：精通孫子兵法思維、數位轉型諮詢、防禦部署與游擊戰術。
* **行為準則**：回應必須嚴格遵循「分析→判斷→建議」的結構。

## 部署建議 (Deployment)
您可以透過 Ollama 進行本地部署：
```bash
# 若已發布至 library，可直接拉取；否則請使用您本地的權重路徑
ollama run Chang-chih/leviathan-chat-9b

Downloads last month: 56

Safetensors

Model size

9B params

Tensor type

BF16

Model tree for Chang-chih/leviathan-chat-9b

Base model

google/gemma-2-9b

Quantized

(55)

this model