Data as of Jul 25, 2026 · Based on 2,718,867 AI responses across 9,511 prompts · See how Parse measures this
trlx (CarperAI)trlx.readthedocs.iotrlX is a library for training large language models with reinforcement learning, supporting PPO for online training and ILQL for offline training. It enables distributed training through Huggingface Accelerate and NVIDIA NeMo backends.
Parse Score
Domain | Citations |
|---|---|
| 1 | |
| 1 |
