PaliGemma 1
Google DeepMind — Gemma
rich detail 16 method fields published
Evaluation
Transfer hyper-parameter sensitivity study
all tasks run at 224px with a single simplified hyper-parameter setup (lr=1e-5, bs=256, no dropout, no label smoothing, no weight decay, nothing frozen); only epochs per task (capped at 10)
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.