Instructions to use Raiff1982/codette-llama-3.1-8b-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Raiff1982/codette-llama-3.1-8b-gguf 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 Raiff1982/codette-llama-3.1-8b-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Raiff1982/codette-llama-3.1-8b-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Raiff1982/codette-llama-3.1-8b-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Raiff1982/codette-llama-3.1-8b-gguf: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 Raiff1982/codette-llama-3.1-8b-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Raiff1982/codette-llama-3.1-8b-gguf: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 Raiff1982/codette-llama-3.1-8b-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Raiff1982/codette-llama-3.1-8b-gguf:Q4_K_M

Use Docker

docker model run hf.co/Raiff1982/codette-llama-3.1-8b-gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use Raiff1982/codette-llama-3.1-8b-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Raiff1982/codette-llama-3.1-8b-gguf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Raiff1982/codette-llama-3.1-8b-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Raiff1982/codette-llama-3.1-8b-gguf:Q4_K_M

Ollama
How to use Raiff1982/codette-llama-3.1-8b-gguf with Ollama:
```
ollama run hf.co/Raiff1982/codette-llama-3.1-8b-gguf:Q4_K_M
```

Unsloth Studio

How to use Raiff1982/codette-llama-3.1-8b-gguf 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 Raiff1982/codette-llama-3.1-8b-gguf 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 Raiff1982/codette-llama-3.1-8b-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Raiff1982/codette-llama-3.1-8b-gguf to start chatting

How to use Raiff1982/codette-llama-3.1-8b-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Raiff1982/codette-llama-3.1-8b-gguf: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": "Raiff1982/codette-llama-3.1-8b-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Raiff1982/codette-llama-3.1-8b-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Raiff1982/codette-llama-3.1-8b-gguf: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 Raiff1982/codette-llama-3.1-8b-gguf:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use Raiff1982/codette-llama-3.1-8b-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Raiff1982/codette-llama-3.1-8b-gguf: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://127.0.0.1:8080/v1 \
  --custom-model-id "Raiff1982/codette-llama-3.1-8b-gguf: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"

Docker Model Runner
How to use Raiff1982/codette-llama-3.1-8b-gguf with Docker Model Runner:
```
docker model run hf.co/Raiff1982/codette-llama-3.1-8b-gguf:Q4_K_M
```

Lemonade

How to use Raiff1982/codette-llama-3.1-8b-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Raiff1982/codette-llama-3.1-8b-gguf:Q4_K_M

Run and chat with the model

lemonade run user.codette-llama-3.1-8b-gguf-Q4_K_M

List all available models

lemonade list

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Codette Orchestrator GGUF - Llama 3.1 8B

Quantized GGUF model for the Codette Multi-Perspective Reasoning System.

This is a Llama 3.1 8B Instruct model with the orchestrator LoRA merged in and quantized to Q4_K_M format for efficient local inference via llama.cpp.

Model Details

Property	Value
Base Model	meta-llama/Llama-3.1-8B-Instruct
Merged Adapter	Orchestrator (query routing + debate coordination)
Quantization	Q4_K_M (4-bit, ~4.6 GB)
Context Length	4096 tokens
Format	GGUF (llama.cpp compatible)

What is Codette?

Codette is a multi-perspective AI reasoning system that approaches problems through 9 specialized cognitive lenses:

Adapter	Perspective
Newton	Analytical physics and systematic reasoning
DaVinci	Creative invention and cross-domain thinking
Empathy	Emotional intelligence and human understanding
Philosophy	Conceptual analysis and ethical reasoning
Quantum	Probabilistic thinking and uncertainty
Consciousness	Recursive cognition (RC+xi framework)
Multi-Perspective	Cross-lens synthesis
Systems Architecture	Modularity, scalability, engineering
Orchestrator	Query routing, debate coordination, coherence monitoring

Architecture (Phase 6+)

Semantic Tension Engine: Measures epistemic tension (xi) between perspectives
Coherence Field (Gamma): Real-time monitoring for reasoning collapse
Quantum Spiderweb: Belief propagation across adapter network
AEGIS Governance: 6-framework ethical validation
Executive Controller: Routes queries by complexity (SIMPLE/MEDIUM/COMPLEX)

Usage

With llama.cpp

./llama-server -m codette-orchestrator-Q4_K_M.gguf -c 4096 -ngl 35

With Codette Web UI

git clone https://github.com/Raiff1982/codette
cd codette
codette_web.bat

The GGUF model serves as the base, with 9 LoRA adapters hot-swapped at inference time for perspective-specific reasoning.

With llama-cpp-python

from llama_cpp import Llama

llm = Llama(
    model_path="codette-orchestrator-Q4_K_M.gguf",
    n_ctx=4096,
    n_gpu_layers=35,
)

response = llm.create_chat_completion(
    messages=[{"role": "user", "content": "Explain consciousness from multiple perspectives"}],
    max_tokens=512,
    temperature=0.7,
)
print(response["choices"][0]["message"]["content"])