Trl Training

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.

Hugging Face Updated 11.4k repo stars
TRL Banner

File contents

huggingface/trl commit 9046f03f97

Frequently asked questions

npx get-skill add huggingface/trl-training-3