Instructions to use Frankenstein-Labs/Cortex.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Frankenstein-Labs/Cortex.0 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 Frankenstein-Labs/Cortex.0:Q8_0
# Run inference directly in the terminal:
llama cli -hf Frankenstein-Labs/Cortex.0:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Frankenstein-Labs/Cortex.0:Q8_0
# Run inference directly in the terminal:
llama cli -hf Frankenstein-Labs/Cortex.0:Q8_0

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 Frankenstein-Labs/Cortex.0:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf Frankenstein-Labs/Cortex.0:Q8_0

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 Frankenstein-Labs/Cortex.0:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Frankenstein-Labs/Cortex.0:Q8_0

Use Docker

docker model run hf.co/Frankenstein-Labs/Cortex.0:Q8_0

Llama new
LM Studio
Jan
Ollama
How to use Frankenstein-Labs/Cortex.0 with Ollama:
```
ollama run hf.co/Frankenstein-Labs/Cortex.0:Q8_0
```
Unsloth Desktop

How to use Frankenstein-Labs/Cortex.0 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Frankenstein-Labs/Cortex.0:Q8_0

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": "Frankenstein-Labs/Cortex.0:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Frankenstein-Labs/Cortex.0 with Docker Model Runner:
```
docker model run hf.co/Frankenstein-Labs/Cortex.0:Q8_0
```

Lemonade

How to use Frankenstein-Labs/Cortex.0 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Frankenstein-Labs/Cortex.0:Q8_0

Run and chat with the model

lemonade run user.Cortex.0-Q8_0

List all available models

lemonade list

Hermes Agent

How to use Frankenstein-Labs/Cortex.0 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Frankenstein-Labs/Cortex.0:Q8_0

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 Frankenstein-Labs/Cortex.0:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Frankenstein-Labs/Cortex.0 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Frankenstein-Labs/Cortex.0:Q8_0

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 "Frankenstein-Labs/Cortex.0:Q8_0" \
  --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"

Cortex.0 / cortex0 /llm.py

Frankenstein-Labs

initial commit

c429240 1 day ago

Raw History Blame Contribute Delete

1.14 kB

"""Build the SDK LLM object that points at a Cortex.0 inference server."""

from __future__ import annotations

from openhands.sdk.llm import LLM

from cortex0.settings import Cortex0Settings


def build_llm(settings: Cortex0Settings) -> LLM:
    """Create an LLM bound to the Cortex.0 OpenAI-compatible endpoint.
    Cortex.0 is a GGUF MoE model served by llama.cpp or SGLang. Both expose the
    OpenAI chat-completions protocol, so the SDK talks to it through ``base_url``
    with no adapter in between: the model sits directly in the agent loop.
    """
    return LLM(
        model=settings.model,
        base_url=settings.base_url,
        api_key=settings.api_key,
        max_output_tokens=settings.max_output_tokens,
        temperature=settings.temperature,
        top_p=settings.top_p,
        top_k=settings.top_k,
        num_retries=settings.num_retries,
        timeout=settings.timeout,
        native_tool_calling=settings.native_tool_calling,
        # Cortex.0 is served by local runtimes that reject unknown provider
        # parameters; dropping them keeps every request acceptable.
        drop_params=True,
    )

	"""Build the SDK LLM object that points at a Cortex.0 inference server."""

	from __future__ import annotations

	from openhands.sdk.llm import LLM

	from cortex0.settings import Cortex0Settings


	def build_llm(settings: Cortex0Settings) -> LLM:
	"""Create an LLM bound to the Cortex.0 OpenAI-compatible endpoint.

	Cortex.0 is a GGUF MoE model served by llama.cpp or SGLang. Both expose the
	OpenAI chat-completions protocol, so the SDK talks to it through ``base_url``
	with no adapter in between: the model sits directly in the agent loop.
	"""
	return LLM(
	model=settings.model,
	base_url=settings.base_url,
	api_key=settings.api_key,
	max_output_tokens=settings.max_output_tokens,
	temperature=settings.temperature,
	top_p=settings.top_p,
	top_k=settings.top_k,
	num_retries=settings.num_retries,
	timeout=settings.timeout,
	native_tool_calling=settings.native_tool_calling,
	# Cortex.0 is served by local runtimes that reject unknown provider
	# parameters; dropping them keeps every request acceptable.
	drop_params=True,
	)