Verified record · from the answer index
trl-training
skillofficialtested · static-verifiedscore 56/100signed passport ✓867 uses
Post-train LLMs with TRL (Transformers Reinforcement Learning) — SFT, DPO, GRPO, KTO, and reward-model training. Use when writing or debugging training code with the TRL Python API or the trl CLI.
Declared tools (1)
trl-training
skill:huggingface/skills/trl-training · published by huggingface · source repository