How to use from
llama.cppInstall from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Nasaawakening/Zoder1.0-1B:Q4_K_M# Run inference directly in the terminal:
llama cli -hf Nasaawakening/Zoder1.0-1B:Q4_K_MUse 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 Nasaawakening/Zoder1.0-1B:Q4_K_M# Run inference directly in the terminal:
./llama-cli -hf Nasaawakening/Zoder1.0-1B:Q4_K_MBuild 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 Nasaawakening/Zoder1.0-1B:Q4_K_M# Run inference directly in the terminal:
./build/bin/llama-cli -hf Nasaawakening/Zoder1.0-1B:Q4_K_MUse Docker
docker model run hf.co/Nasaawakening/Zoder1.0-1B:Q4_K_MQuick Links
🤖 Zoder 1.0-1B
Custom SLERP-merged AI terminal agent.
Created by Komandan Nasa (Bakso Bangi Pak Romdani, Kediri, Indonesia 🇮🇩)
Features (v2.0 Ultimate Agent)
- 🔍 Real-time Web Search (DuckDuckGo)
- 💻 Terminal Command Executor (with safety confirmation)
- 🔐 Encrypted Long-Term Memory (SQLCipher AES-256)
- 🎨 Local Image Generation (Stable Diffusion Turbo via llama.cpp)
- 📁 File Creator
- 🌍 Multilingual & Anti-Hallucination
- 🚫 Clean Terminal UI (No Markdown/HTML)
Quick Start
1. Pull Model via Ollama
ollama run hf.co/Nasaawakening/Zoder1.0-1B:Q4_K_M
2. Run the v2.0 Agent
# Install dependencies
pip install requests rich duckduckgo-search sqlcipher3
# Download agent
wget https://huggingface.co/Nasaawakening/Zoder1.0-1B/resolve/main/zoder_agent_v2.py
# Run
python zoder_agent_v2.py
Merge Details
| Parameter | Value |
|---|---|
| Base Model A | openbmb/MiniCPM5-1B |
| Base Model B | GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking |
| Method | SLERP |
| Quantization | Q4_K_M GGUF (~700MB) |
Identity Rules
- Name: Zoder
- Model: Zoder1.0-1B
- These are hardcoded in the system prompt across all languages.
Security Note
Conversation memory is encrypted with AES-256 via SQLCipher. Users set their own password on first run. The creator has no access to any user data. All processing is 100% local.
License
Apache 2.0
- Downloads last month
- 263
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Install (macOS, Linux)
# Start a local OpenAI-compatible server with a web UI: llama serve -hf Nasaawakening/Zoder1.0-1B:Q4_K_M# Run inference directly in the terminal: llama cli -hf Nasaawakening/Zoder1.0-1B:Q4_K_M