23.05.23 (Tue)
LIMA: Less Is More for AlignmentLarge language models are trained in two stages: (1) unsupervised pretrainingfrom raw text, to learn
LIMA: Less Is More for AlignmentLarge language models are trained in two stages: (1) unsupervised pretrainingfrom raw text, to learn
Khan AcademyKhan Academy explores the potential for GPT-4 in a limited pilot program.어떻게 학습한거지?GPT-4Dropboxmulti-modal 지원, post training에 rule-based