Útmutatóhoz kapcsolódó kvíz · Kemény Szint
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.
kérdés 1 -ból 8
Útmutatóhoz kapcsolódó kvíz · Kemény Szint
Tests how graders score model outputs, which tasks suit reinforcement fine-tuning, and how reward hacking and weak training signals arise.