start.sh

#!/usr/bin/env bash
set -e

echo "Starting Ollama..."
ollama serve &
sleep 5

echo "Pulling models..."
# LANGUAGE MODEL
ollama pull qwen3:0.6b
ollama pull qwen3:1.7b
ollama pull qwen3-vl:2b

# EMBEDDING MODEL
ollama pull embeddinggemma:300m

echo "Ollama ready."

# Hugging Face requires port 7860
exec socat TCP-LISTEN:7860,fork TCP:localhost:11434