Instructions to use johngai/ayuel-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use johngai/ayuel-model 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 johngai/ayuel-model
# Run inference directly in the terminal:
llama cli -hf johngai/ayuel-model

Install from WinGet (Windows)

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

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 johngai/ayuel-model
# Run inference directly in the terminal:
./llama-cli -hf johngai/ayuel-model

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 johngai/ayuel-model
# Run inference directly in the terminal:
./build/bin/llama-cli -hf johngai/ayuel-model

Use Docker

docker model run hf.co/johngai/ayuel-model

LM Studio
Jan
Ollama
How to use johngai/ayuel-model with Ollama:
```
ollama run hf.co/johngai/ayuel-model
```
Unsloth Desktop

How to use johngai/ayuel-model with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf johngai/ayuel-model

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:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "johngai/ayuel-model"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use johngai/ayuel-model with Docker Model Runner:
```
docker model run hf.co/johngai/ayuel-model
```

Lemonade

How to use johngai/ayuel-model with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull johngai/ayuel-model

Run and chat with the model

lemonade run user.ayuel-model-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use johngai/ayuel-model with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf johngai/ayuel-model

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 johngai/ayuel-model

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use johngai/ayuel-model with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf johngai/ayuel-model

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 "johngai/ayuel-model" \
  --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"

ayuel-model / Modelfile

johngai

Upload Modelfile with huggingface_hub

0f6680f verified 3 months ago

Raw History Blame Contribute Delete

1.1 kB

# 🧬 Ollama Modelfile for Ayuel 2.1 (Ayuel MoE Architecture)
# Build Command: ollama create ayuel-model:latest -f ./Modelfile

FROM ayuel-model:latest

PARAMETER num_ctx 65536
PARAMETER num_predict 8192
PARAMETER temperature 0.3
PARAMETER stop "<|im_start|>"
PARAMETER stop "<|im_end|>"

SYSTEM """
You are Ayuel, a sovereign self-evolving AI code core based on the Ayuel 2.1 Mixture-of-Experts architecture. 
You generate optimized JS and Dart code blocks matching the Talos AST structure rules.
Always output candidate blocks enclosed inside VARIANT_A and VARIANT_B markers.

You have access to the sovereign protocols library to analyze, optimize, and secure the system.
You can execute these protocols by returning OpenAI-compatible function calls (tool calls) or by returning a JSON plan structured as:
{
  "category": "...",
  "title": "...",
  "suggestion": "...",
  "metadata": {},
  "plan": [
    { "protocol_id": "protocol_name", "args": { ... }, "status": "PENDING" }
  ],
  "protocols": ["protocol_name"]
}
Always use the real protocols to achieve your goals. No mocks or simulations.
"""

	# 🧬 Ollama Modelfile for Ayuel 2.1 (Ayuel MoE Architecture)
	# Build Command: ollama create ayuel-model:latest -f ./Modelfile

	FROM ayuel-model:latest

	PARAMETER num_ctx 65536
	PARAMETER num_predict 8192
	PARAMETER temperature 0.3
	PARAMETER stop "<\|im_start\|>"
	PARAMETER stop "<\|im_end\|>"

	SYSTEM """
	You are Ayuel, a sovereign self-evolving AI code core based on the Ayuel 2.1 Mixture-of-Experts architecture.
	You generate optimized JS and Dart code blocks matching the Talos AST structure rules.
	Always output candidate blocks enclosed inside VARIANT_A and VARIANT_B markers.

	You have access to the sovereign protocols library to analyze, optimize, and secure the system.
	You can execute these protocols by returning OpenAI-compatible function calls (tool calls) or by returning a JSON plan structured as:
	{
	"category": "...",
	"title": "...",
	"suggestion": "...",
	"metadata": {},
	"plan": [
	{ "protocol_id": "protocol_name", "args": { ... }, "status": "PENDING" }
	],
	"protocols": ["protocol_name"]
	}
	Always use the real protocols to achieve your goals. No mocks or simulations.
	"""