Instructions to use wgruner/xork-i-assets with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use wgruner/xork-i-assets 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 wgruner/xork-i-assets:Q4_K_M # Run inference directly in the terminal: llama cli -hf wgruner/xork-i-assets:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf wgruner/xork-i-assets:Q4_K_M # Run inference directly in the terminal: llama cli -hf wgruner/xork-i-assets:Q4_K_M
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf wgruner/xork-i-assets:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf wgruner/xork-i-assets:Q4_K_M
Use Docker
docker model run hf.co/wgruner/xork-i-assets:Q4_K_M
- Llama new
- LM Studio
- Jan
- Ollama
How to use wgruner/xork-i-assets with Ollama:
ollama run hf.co/wgruner/xork-i-assets:Q4_K_M
- Unsloth Desktop
- Pi
How to use wgruner/xork-i-assets with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf wgruner/xork-i-assets:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "wgruner/xork-i-assets:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use wgruner/xork-i-assets with Docker Model Runner:
docker model run hf.co/wgruner/xork-i-assets:Q4_K_M
- Lemonade
How to use wgruner/xork-i-assets with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull wgruner/xork-i-assets:Q4_K_M
Run and chat with the model
lemonade run user.xork-i-assets-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use wgruner/xork-i-assets with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf wgruner/xork-i-assets: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://127.0.0.1:9931/v1 hermes config set model.default wgruner/xork-i-assets:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use wgruner/xork-i-assets with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf wgruner/xork-i-assets:Q4_K_M
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:9931/v1 \ --custom-model-id "wgruner/xork-i-assets:Q4_K_M" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Xork I assets
Files for Xork I, a non-commercial project that plays the original Zork I with room pictures and a companion character's lines, all on your own computer. The "Play Xork I" installer downloads these; you don't need to fetch them yourself. The installer: github.com/wgruner/xork-i.
This project is not affiliated with or endorsed by the owners of the "Zork" trademark.
Files
| File | What it is | Base model and license |
|---|---|---|
models/sybylla-4b-lora/sybylla-4b-lora-Q4_K_M.gguf |
Sybylla's lines: NVIDIA Nemotron 3 Nano 4B fine-tuned with a LoRA, merged and quantized to Q4_K_M for llama.cpp | NVIDIA Nemotron 3 Nano 4B, under the NVIDIA Open Model License Agreement |
loras/trapdoor-style-klein4b-v1.safetensors, loras/trapdoor.json |
A picture-style LoRA for the best picture setting; the JSON file gives its label, trigger and strength |
FLUX.2 klein 4B, under the Apache License 2.0 |
Licensed by NVIDIA Corporation under the NVIDIA Open Model License. The Sybylla model is a derivative of NVIDIA Nemotron 3 Nano 4B and is distributed under the same agreement.
Checksums (SHA-256)
3bfeff8a33768df8e415b6c8b45ad53aadce67ef354b5d592e55491206e957a4 models/sybylla-4b-lora/sybylla-4b-lora-Q4_K_M.gguf
2f944560c1cf0d3cc55fde121a5d46961e5c92ffce638b63aa035e7237454264 loras/trapdoor-style-klein4b-v1.safetensors
e819b7255cf7b0ad465c1c877a1a9b94368c7b7ca3dd6110340a2416460adf8d loras/trapdoor.json
- Downloads last month
- 55
4-bit
Model tree for wgruner/xork-i-assets
Base model
black-forest-labs/FLUX.2-klein-4B