PaliGemma 1
Google DeepMind — Gemma
rich detail 17 method fields published
Evaluation
effect of Stage1 multimodal pretraining duration (down to completely skipping Stage1) on transfer performance; ablations run with Stage1 10x shorter (100M examples seen) unless noted
How it was run
Open a release to see the setup, scoring, and other details that the lab published. Only fields the lab actually disclosed are shown.
rich detail 17 method fields published