Download
trlX is a distributed training framework designed from the ground up to focus on fine-tuning large language models with reinforcement learning using either a provided reward function or a reward-labeled dataset. Training support for Hugging Face models is provided by Accelerate-backed trainers, allowing users to fine-tune causal and T5-based language models of up to 20B parameters, such as facebook/opt-6.7b, EleutherAI/gpt-neox-20b, and google/flan-t5-xxl. For models beyond 20B parameters, trlX provides NVIDIA NeMo-backed trainers that leverage efficient parallelism techniques to scale effectively.
Features
- Use a reward function
- Documentation available
- Use a reward-labeled dataset
- Launch distributed training
- Logging
- Examples included
Project Samples
Categories
Machine Learning, Reinforcement Learning Frameworks, Reinforcement Learning Libraries, Reinforcement Learning AlgorithmsLicense
MIT LicenseFollow Transformer Reinforcement Learning X
Other Useful Business Software
Gemini 3 and 200+ AI Models on One Platform
Build, govern, and optimize agents and models with Gemini Enterprise Agent Platform.
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of Transformer Reinforcement Learning X!
