Instructions to use ninacatcoin/nina-model-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use ninacatcoin/nina-model-8b with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="ninacatcoin/nina-model-8b", filename="nina-8b-nina-ft-Q4_K_M.gguf", )
llm.create_chat_completion( messages = "No input example has been defined for this model task." )
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use ninacatcoin/nina-model-8b with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf ninacatcoin/nina-model-8b:Q4_K_M # Run inference directly in the terminal: llama-cli -hf ninacatcoin/nina-model-8b:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf ninacatcoin/nina-model-8b:Q4_K_M # Run inference directly in the terminal: llama-cli -hf ninacatcoin/nina-model-8b: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 ninacatcoin/nina-model-8b:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf ninacatcoin/nina-model-8b: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 ninacatcoin/nina-model-8b:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf ninacatcoin/nina-model-8b:Q4_K_M
Use Docker
docker model run hf.co/ninacatcoin/nina-model-8b:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use ninacatcoin/nina-model-8b with Ollama:
ollama run hf.co/ninacatcoin/nina-model-8b:Q4_K_M
- Unsloth Studio new
How to use ninacatcoin/nina-model-8b 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 ninacatcoin/nina-model-8b 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 ninacatcoin/nina-model-8b to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for ninacatcoin/nina-model-8b to start chatting
- Pi new
How to use ninacatcoin/nina-model-8b with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf ninacatcoin/nina-model-8b:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "ninacatcoin/nina-model-8b:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use ninacatcoin/nina-model-8b with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf ninacatcoin/nina-model-8b:Q4_K_M
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default ninacatcoin/nina-model-8b:Q4_K_M
Run Hermes
hermes
- Docker Model Runner
How to use ninacatcoin/nina-model-8b with Docker Model Runner:
docker model run hf.co/ninacatcoin/nina-model-8b:Q4_K_M
- Lemonade
How to use ninacatcoin/nina-model-8b with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull ninacatcoin/nina-model-8b:Q4_K_M
Run and chat with the model
lemonade run user.nina-model-8b-Q4_K_M
List all available models
lemonade list
NINA 8B โ NinaCatCoin AI Model (VPS Edition)
Fine-tuned LLaMA 3.1 8B model for NinaCatCoin cryptocurrency AI assistant. Optimized for VPS deployment with CPU inference (24GB RAM).
Model Details
| Property | Value |
|---|---|
| Base Model | Meta LLaMA 3.1 8B Instruct |
| Method | QLoRA (r=16, alpha=32) |
| Dataset | 3,980 multilingual pairs (EN/ES/FR/DE/PT) |
| Epochs | 3 |
| Format | GGUF Q4_K_M |
| Size | 4.6 GB |
| SHA-256 | CF93DE6C27406C0C03958700498E6888F12C9BE94208148F4BE7587EE2CF542E |
Download
`ash
Direct download
wget https://huggingface.co/ninacatcoin/nina-model-8b/resolve/main/nina-8b-nina-ft-Q4_K_M.gguf `
Usage with llama.cpp
ash ./llama-server -m nina-8b-nina-ft-Q4_K_M.gguf -c 4096 --port 19021
What is NinaCatCoin?
NinaCatCoin is a Monero-based cryptocurrency with 34 embedded AI modules. NINA is the AI assistant that runs on every node โ no cloud, fully decentralized.
Related
- 3B Model (lightweight): ninacatcoin/nina-model
- GitHub: NinaCatCoin
- Downloads last month
- 18
4-bit
Model tree for ninacatcoin/nina-model-8b
Base model
meta-llama/Llama-3.1-8B