Instructions to use sarv624/gardiner with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use sarv624/gardiner 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 sarv624/gardiner
# Run inference directly in the terminal:
llama cli -hf sarv624/gardiner

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf sarv624/gardiner
# Run inference directly in the terminal:
llama cli -hf sarv624/gardiner

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 sarv624/gardiner
# Run inference directly in the terminal:
./llama-cli -hf sarv624/gardiner

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 sarv624/gardiner
# Run inference directly in the terminal:
./build/bin/llama-cli -hf sarv624/gardiner

Use Docker

docker model run hf.co/sarv624/gardiner

LM Studio
Jan
Ollama
How to use sarv624/gardiner with Ollama:
```
ollama run hf.co/sarv624/gardiner
```

Unsloth Studio

How to use sarv624/gardiner 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 sarv624/gardiner 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 sarv624/gardiner to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for sarv624/gardiner to start chatting

How to use sarv624/gardiner with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf sarv624/gardiner

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": "sarv624/gardiner"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use sarv624/gardiner with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf sarv624/gardiner

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 sarv624/gardiner

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use sarv624/gardiner with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf sarv624/gardiner

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://127.0.0.1:8080/v1 \
  --custom-model-id "sarv624/gardiner" \
  --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"

Docker Model Runner
How to use sarv624/gardiner with Docker Model Runner:
```
docker model run hf.co/sarv624/gardiner
```

Lemonade

How to use sarv624/gardiner with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull sarv624/gardiner

Run and chat with the model

lemonade run user.gardiner-{{QUANT_TAG}}

List all available models

lemonade list

Gardiner — Experimental Hieroglyph Classification Model

🚧 Status: In Development
This model is actively evolving. Architecture, dataset and behavior may change in future versions.

📝 Project Description

Gardiner is an experimental language model trained specifically on the Gardiner Sign List, the classification system of Egyptian hieroglyphs created by the Egyptologist Sir Alan Gardiner.

The goal of this project is to provide a lightweight, local model capable of:

answering questions about the Gardiner classification system
identifying sign categories (A, B, C, …)
providing general information about hieroglyph groups
supporting educational and exploratory use cases

This model is distributed in GGUF format, making it compatible with:

Ollama
llama.cpp
LM Studio
any local inference engine supporting GGUF

🔧 Capabilities

Understands the structure of the Gardiner Sign List
Can respond to questions about hieroglyph categories
Provides explanations about sign groups and their classification
Lightweight and optimized for local inference
Suitable for experimentation and Egyptology‑related projects

📦 Current Version

Version: 0.3.1
Format: GGUF
Training Data: Gardiner Sign List (classification only)
License: MIT

🚧 Work in Progress

Planned improvements include:

Additional quantization formats
Expanded dataset
More detailed explanations for each sign group
Improved documentation and usage examples
Integration examples for Ollama and LM Studio

⚠️ Notes

This model is not intended to translate hieroglyphs or perform full Egyptological analysis.
Its purpose is to assist with classification‑related questions and provide a compact, local tool for enthusiasts, students, and developers.

Downloads last month: 15

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support