Add train_launcher.sh that detects local GPU VRAM and routes training
to local or Scaleway cloud. Auto-selects batch size per model based on
available VRAM tier. Maps model names to actual ml/examples/train_*.rs
cargo targets. Document Scaleway GPU instance types, setup procedure,
batch size tables, and cost estimates.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Fixes discovered during live provisioning: app.ini permissions
(root:gitea + 660→640 for token generation), HTTPS via acme.sh
DNS-01, setcap for port 443, admin user creation, INSTALL_LOCK
lifecycle. Secrets replaced with placeholders.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
