TRL
Open Source
Free Trial
Hugging Face library for training language models with RLHF, SFT, and DPO
TRL (Transformer Reinforcement Learning) is the standard Hugging Face library for fine-tuning language models. It supports supervised fine-tuning (SFT), reinforcement learning from human feedback (RLHF), direct preference optimization (DPO), and other alignment techniques. Built on top of Transformers and integrates with PEFT for parameter-efficient training.
Pricing: Free
HQ
🇺🇸 United States
GitHub
18,466 stars
TRL Alternatives
Explore 21 products in the Fine-tuning category. View all TRL alternatives.
Work on TRL? Feature it at the top of Fine-tuning.
Is your product missing?