Open-Bezoar Collection Small, Cost-Effective and Open Models Trained on Mixes of Instruction Data • 7 items • Updated Apr 19, 2024 • 6
CLIPA-v2: Scaling CLIP Training with 81.1% Zero-shot ImageNet Accuracy within a \10,000 Budget; An Extra 4,000 Unlocks 81.8% Accuracy Paper • 2306.15658 • Published Jun 27, 2023 • 12