Instructions to use jlind456/jason-ai-twin with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use jlind456/jason-ai-twin 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 jlind456/jason-ai-twin
# Run inference directly in the terminal:
llama cli -hf jlind456/jason-ai-twin

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf jlind456/jason-ai-twin
# Run inference directly in the terminal:
llama cli -hf jlind456/jason-ai-twin

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 jlind456/jason-ai-twin
# Run inference directly in the terminal:
./llama-cli -hf jlind456/jason-ai-twin

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 jlind456/jason-ai-twin
# Run inference directly in the terminal:
./build/bin/llama-cli -hf jlind456/jason-ai-twin

Use Docker

docker model run hf.co/jlind456/jason-ai-twin

LM Studio
Jan

vLLM

How to use jlind456/jason-ai-twin with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jlind456/jason-ai-twin"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jlind456/jason-ai-twin",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jlind456/jason-ai-twin

Ollama
How to use jlind456/jason-ai-twin with Ollama:
```
ollama run hf.co/jlind456/jason-ai-twin
```
Unsloth Desktop

How to use jlind456/jason-ai-twin with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jlind456/jason-ai-twin

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": "jlind456/jason-ai-twin"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use jlind456/jason-ai-twin with Docker Model Runner:
```
docker model run hf.co/jlind456/jason-ai-twin
```

Lemonade

How to use jlind456/jason-ai-twin with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull jlind456/jason-ai-twin

Run and chat with the model

lemonade run user.jason-ai-twin-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use jlind456/jason-ai-twin with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jlind456/jason-ai-twin

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 jlind456/jason-ai-twin

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use jlind456/jason-ai-twin with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jlind456/jason-ai-twin

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 "jlind456/jason-ai-twin" \
  --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"

Jason AI Twin (Offline Digital Twin & Cloned Voice)

An offline, privacy-first AI Digital Twin architecture featuring quantized local LLM reasoning, custom knowledge bases, GPU-accelerated speech recognition, and neural voice cloning.

🎙️ Cloned Voice & Audio Assets

The AI Twin features neural voice cloning sourced from /local-tts:

cloned_output.wav: High-fidelity cloned voice reference sample synthesized from Jason's voice profile. Used as the primary speaker reference for zero-shot Coqui XTTS v2 voice synthesis.
cloned_sample2.wav: Second verified neural synthesis sample generated with Coqui XTTS v2 on CUDA using Jason's vocal profile ("The voice cloning matrix is fully operational...").
my_voice_clean.wav: Cleaned, noise-reduced studio vocal sample of Jason's voice (22.05 kHz PCM) for fine-tuning and voice cloning alignment.
amy.onnx / amy.onnx.json: Ultra-fast, low-latency ONNX voice model for Piper TTS fallback.

🧠 Brain & Models

digital_twin_q4.gguf: Q4_K_M quantized LLM brain (jason_twin) trained and adapted on Jason's communication style, knowledge bases, and preferences.
Modelfile: Ollama configuration for launching jason_twin locally with optimized system prompt, temperature, and context length.

🚀 Interactive CLI Client (`chat_twin.py`)

The repository includes chat_twin.py, an interactive voice and text terminal client:

Two-Way Voice Interaction: Press [ENTER] on an empty prompt to record your voice; local Whisper (openai/whisper-tiny.en) transcribes it with GPU acceleration.
Neural Voice Synthesis: Speaks responses back in Jason's cloned voice using local XTTS v2 (--speaker_wav cloned_output.wav).
Multi-Engine Fallback: Gracefully falls back to Piper ONNX, spd-say, or espeak-ng if GPU voice cloning is unavailable.

In-Chat Commands:

Command	Action
`/voice cloned`	Activate Jason's cloned voice from `/local-tts`
`/voice <type>`	Switch to system voices (`male1`, `male2`, `female1`, etc.)
`/rate <val>`	Adjust speech rate (-100 to 100)
`/tts on\|off`	Toggle Text-to-Speech output
`/stop` or `/s`	Immediately silence current speech output
`/clear` or `/c`	Reset conversation context and clear terminal
`/help` or `/h`	Display digital twin command menu
`/exit`	Exit the application

🛠️ Quickstart

1. Run via Ollama

ollama create jason_twin -f Modelfile
ollama run jason_twin

2. Run Interactive Voice Twin CLI

# Ensure dependencies are installed
pip install TTS transformers torch torchaudio

# Launch voice chat client
python3 chat_twin.py

3. Desktop Shortcut

On Ubuntu systems, launch directly via the included AI_Twin.desktop or:

./launch_twin.sh

Downloads last month: 280

GGUF

Model size

3B params

Architecture

qwen2

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Jason AI Twin (Offline Digital Twin & Cloned Voice)

🎙️ Cloned Voice & Audio Assets

🧠 Brain & Models

🚀 Interactive CLI Client (chat_twin.py)

In-Chat Commands:

🛠️ Quickstart

1. Run via Ollama

2. Run Interactive Voice Twin CLI

3. Desktop Shortcut

🚀 Interactive CLI Client (`chat_twin.py`)