Instructions to use Chang-chih/leviathan-chat-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use Chang-chih/leviathan-chat-7b with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="Chang-chih/leviathan-chat-7b", filename="leviathan-chat-7b.gguf", )
llm.create_chat_completion( messages = "No input example has been defined for this model task." )
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Chang-chih/leviathan-chat-7b 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-7b # Run inference directly in the terminal: llama cli -hf Chang-chih/leviathan-chat-7b
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-7b # Run inference directly in the terminal: llama cli -hf Chang-chih/leviathan-chat-7b
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-7b # Run inference directly in the terminal: ./llama-cli -hf Chang-chih/leviathan-chat-7b
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-7b # Run inference directly in the terminal: ./build/bin/llama-cli -hf Chang-chih/leviathan-chat-7b
Use Docker
docker model run hf.co/Chang-chih/leviathan-chat-7b
- LM Studio
- Jan
- Ollama
How to use Chang-chih/leviathan-chat-7b with Ollama:
ollama run hf.co/Chang-chih/leviathan-chat-7b
- Unsloth Studio
How to use Chang-chih/leviathan-chat-7b 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 Chang-chih/leviathan-chat-7b 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 Chang-chih/leviathan-chat-7b to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Chang-chih/leviathan-chat-7b to start chatting
- Atomic Chat new
- Docker Model Runner
How to use Chang-chih/leviathan-chat-7b with Docker Model Runner:
docker model run hf.co/Chang-chih/leviathan-chat-7b
- Lemonade
How to use Chang-chih/leviathan-chat-7b with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Chang-chih/leviathan-chat-7b
Run and chat with the model
lemonade run user.leviathan-chat-7b-{{QUANT_TAG}}List all available models
lemonade list
🐋 利維坦軍團 · 輕量對話核心 (leviathan-chat-7b)
模型簡介
leviathan-chat-7b 為利維坦軍團的輕量化對話核心,基於 deepseek-ai/deepseek-llm-7b-chat 進行蒸餾與優化,專為高效率的戰略對話與決策支援而設計。
主要能力
- 戰略對話:擅長以「分析→判斷→建議」的結構進行回應。
- 輕量部署:GGUF Q4_K_M 量化版本,僅需約 4GB 顯存即可運行。
- 軍團風格:繼承利維坦軍團的參謀語氣與邏輯框架。
- 純正血統:源自 DeepSeek 家族,具備優秀的中文與邏輯推理能力。
快速部署 (Ollama)
- 下載 GGUF 檔案:
hf download Chang-chih/leviathan-chat-7b leviathan-chat-7b.gguf --local-dir ./ 載入 Ollama:
bash ollama create leviathan-chat-7b -f <(echo "FROM ./leviathan-chat-7b.gguf") 立即使用:
bash ollama run leviathan-chat-7b "你的問題" 血統與蒸餾歷程 階段 基底模型 說明 基底 deepseek-ai/deepseek-llm-7b-chat DeepSeek 家族的 7B 對話模型。 蒸餾 利維坦軍團內部數據 注入孫子兵法思維與軍團參謀風格。 評測結果 (Benchmark) 待補充 (建議執行 lm-eval 後填入)
授權 本模型採用 Apache-2.0 授權條款。
- Downloads last month
- 506
We're not able to determine the quantization variants.
Model tree for Chang-chih/leviathan-chat-7b
Base model
deepseek-ai/deepseek-llm-7b-chat