This is a chatbot experiement in Rust Axum and SolidJS

---

To run this demo you would need to:

• Download Llama GGML model from https://huggingface.co/
• Go into chatbot-backend change the model name in model_path
• Install latest rust and cargo binary using rustup
• Install nodejs 16 and npm
• Go into the chatbot-backend folder and run cargo run
• Go into the chatbot-frontend folder and run npm install && npm run dev

The model wizardlm-7b-v1.0-uncensored.ggmlv3.q6_K.bin ran on commodity hardware with good performance to accuracy ratio.