This software is under heavy development. It is not ready to work out of the box...(has to be cleaned up and further improved)! Main entry point is DartsScorer_1.py (DartsScorer.py is an older version ...
💡 What is Trinity-RFT? Trinity-RFT is a general-purpose, flexible and user-friendly framework for LLM reinforcement fine-tuning (RFT). It decouples RFT into three components that work in coordination ...