trl
Config-driven LLM fine-tuning with safety evaluation, EU AI Act compliance, 6 alignment methods, and one-command bundled quickstart templates.
Behavioral health checks for HuggingFace/TRL fine-tuning runs
Distill teacher chains-of-thought into a LoRA adapter via a strict boxed-answer format contract and a two-phase Train→Nudge schedule (silver-medal NVIDIA Nemotron reasoning recipe).
Initialize TRUGS Agent in your project — a 190-word formal instruction language for LLM coding assistants
