Instructions to use Chang-chih/leviathan-pure with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use Chang-chih/leviathan-pure with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="Chang-chih/leviathan-pure", filename="leviathan-pure.gguf", )
output = llm( "Once upon a time,", max_tokens=512, echo=True ) print(output)
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Chang-chih/leviathan-pure 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-pure # Run inference directly in the terminal: llama cli -hf Chang-chih/leviathan-pure
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Chang-chih/leviathan-pure # Run inference directly in the terminal: llama cli -hf Chang-chih/leviathan-pure
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-pure # Run inference directly in the terminal: ./llama-cli -hf Chang-chih/leviathan-pure
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-pure # Run inference directly in the terminal: ./build/bin/llama-cli -hf Chang-chih/leviathan-pure
Use Docker
docker model run hf.co/Chang-chih/leviathan-pure
- LM Studio
- Jan
- vLLM
How to use Chang-chih/leviathan-pure with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Chang-chih/leviathan-pure" # 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-pure", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Chang-chih/leviathan-pure
- Ollama
How to use Chang-chih/leviathan-pure with Ollama:
ollama run hf.co/Chang-chih/leviathan-pure
- Unsloth Studio
How to use Chang-chih/leviathan-pure 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-pure 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-pure 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-pure to start chatting
- Atomic Chat new
- Docker Model Runner
How to use Chang-chih/leviathan-pure with Docker Model Runner:
docker model run hf.co/Chang-chih/leviathan-pure
- Lemonade
How to use Chang-chih/leviathan-pure with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Chang-chih/leviathan-pure
Run and chat with the model
lemonade run user.leviathan-pure-{{QUANT_TAG}}List all available models
lemonade list
language: - en - zh tags: - leviathan - pure - code - python - ollama - gguf - deepseek-coder license: apache-2.0 base_model: - deepseek-ai/deepseek-coder-6.7b-base - deepseek-ai/deepseek-llm-7b-chat
🐋 利維坦軍團 · 純血工匠 (leviathan-pure)
模型簡介
leviathan-pure 為利維坦軍團之純血工匠,歷經兩次蒸餾而成,專責程式碼產出、自動化任務與日誌盤點。回應僅包含純 Python 程式碼,無教學、無填充、無冗餘。
血統與蒸餾歷程
| 階段 | 基底模型 | 說明 |
|---|---|---|
| 第一次蒸餾 | deepseek-ai/deepseek-coder-6.7b-base |
以原始程式碼模型為基底,進行技術能力蒸餾。 |
| 第二次蒸餾 | deepseek-ai/deepseek-llm-7b-chat |
以聊天模型進行二次蒸餾,強化對話邏輯與指令遵循能力。 |
| 最終產物 | leviathan-pure |
結合技術與對話邏輯,固化為純代碼輸出風格的純血工匠。 |
主要能力
- 純代碼產出:僅輸出 Python 程式碼,無任何解釋或教學內容。
- 路徑鎖定:自動對齊
~/leviathan_core/路徑。 - 憲法內化:無須 System Prompt,已固化於權重中。
快速部署 (Ollama)
- 下載 GGUF 檔案:
hf download Chang-chih/leviathan-pure leviathan-pure.gguf --local-dir ./ 載入 Ollama:
bash ollama create leviathan-pure -f <(echo "FROM ./leviathan-pure.gguf") 立即使用:
bash ollama run leviathan-pure "你的 Python 請求" 使用範例 輸入:
text 請寫一個 Python 函數,計算費波那契數列。 輸出:
python def fibonacci(n): if n <= 0: return [] elif n == 1: return [0] elif n == 2: return [0, 1] else: fib = [0, 1] for i in range(2, n): fib.append(fib[-1] + fib[-2]) return fib 授權 本模型採用 Apache-2.0 授權條款。
- Downloads last month
- 108
We're not able to determine the quantization variants.
Model tree for Chang-chih/leviathan-pure
Base model
deepseek-ai/deepseek-coder-6.7b-base