Test legat de ghid · Greu Nivel
Reinforcement Fine-Tuning with Graders Quiz
Tests how graders score model outputs, which tasks suit reinforcement fine-tuning, and how reward hacking and weak training signals arise.
Întrebare 1 de 8
Test legat de ghid · Greu Nivel
Tests how graders score model outputs, which tasks suit reinforcement fine-tuning, and how reward hacking and weak training signals arise.