Hugging Face TRL
Library for training LLMs with reinforcement learning (RLHF, DPO, PPO).
About
TRL, Transformer Reinforcement Learning by Hugging Face, is a library for post-training language models with techniques including supervised fine-tuning, reward modeling, PPO, GRPO, and Direct Preference Optimization. Built on the Transformers and PEFT ecosystem, it supports many architectures and modalities and scales across hardware with DeepSpeed and FSDP. Released under the Apache 2.0 license.
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
- Intermediate (3/5)
- License
- Apache-2.0
- Minimum VRAM
- 8 GB
- Added
- Apr 3, 2026
Related Tools
Framework for generating synthetic data and AI feedback through composable LLM pipelines.
Subject-driven fine-tuning technique for personalizing diffusion models.
Video model fine-tuning toolkit by Hugging Face Diffusers team.
Efficient LLM quantization preserving important weight channels.
All-in-one Stable Diffusion fine-tuning tool with intuitive GUI.
No-code tool by Hugging Face for training ML models automatically.