#!/bin/bash
# Start the llama.cpp server in the background[citation:2]
llama-server -m /models/Wizard-Vicuna-13B-Uncensored.Q8_0.gguf --host 0.0.0.0 --port 8080 --n-gpu-layers 32 &

# Start the Diamond ecosystem Python application
cd /workspace/diamond
python diamond_api_server.py --host 0.0.0.0 --port 8000 &

# Keep the container running
wait