Trl Python Packages

trloom

YAML-driven end-to-end fine-tuning on Hugging Face TRL — one config for model, dataset, W&B, and Modal GPUs.

forgelm

Config-driven LLM fine-tuning with safety evaluation, EU AI Act compliance, 6 alignment methods, and one-command bundled quickstart templates.

ftdoctor

Did your fine-tune overfit? Which checkpoint should you keep? What can you delete? For any HuggingFace Trainer run, local or on the Hub: TRL, Unsloth, LLaMA-Factory, Axolotl.

rldoctor

Diagnose why your GRPO/RLVR run is burning GPU-hours without learning. Reads the log you already have: W&B, TensorBoard, verl, TRL trainer_state.json.

crucible-rl

Turn any real software into a replayable RL environment for training AI agents — deterministic replay, verifiable rewards, TRL & verifiers adapters.

memaudit

Training-data memorization auditor for fine-tuned LLMs — Trainer/TRL plugin, canary MIA + regurgitation audit, Apache-2.0

tracedistill

Distill teacher chains-of-thought into a LoRA adapter via a strict boxed-answer format contract + two-phase Train→Nudge (silver-medal NVIDIA Nemotron reasoning recipe, as a tested library).

trugs-agent

One file teaches your LLM a complete development system — TRL + AAA + Memory

trainsafe

Behavioral health checks for HuggingFace / TRL fine-tuning. Monitors outputs at each checkpoint and stops training if something goes wrong.