TRL
Library for post-training foundation models with SFT, DPO, GRPO, and other RL methods.
About
TRL is a library from Hugging Face for post-training foundation models using techniques such as Supervised Fine-Tuning, Direct Preference Optimization, and Group Relative Policy Optimization. It is built on the Transformers ecosystem and supports many model architectures and modalities. The library scales from a single GPU to multi-node clusters and integrates with PEFT and quantization for memory-efficient training.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- Model Training & Fine-Tuning
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Advanced (4/5)
- License
- Apache-2.0
- Added
- May 7, 2026
Related Tools
No-code tool by Hugging Face for training ML models automatically.
Efficient LLM quantization preserving important weight channels.
Video model fine-tuning toolkit by Hugging Face Diffusers team.
Low-code framework for building custom AI models by Predibase.
Library for training LLMs with reinforcement learning (RLHF, DPO, PPO).
Efficient fine-tuning method using 4-bit quantized base model with LoRA adapters.