Software Development
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.
- Publisher / source
- Hugging Face Skills
- Upstream record
- huggingface/skills
- Version
- Version 2
- Published
- Publication review
- Approved for publication · recorded passed scan 2026-10-01
- Content fingerprint
42c855bdc6171390abc7413cdb19bd4fd8dddfb31094d519a874427de08ddc2a