Scaling Laws for Forgetting during Finetuning with Pretraining Data Injection.
Louis Bthune, David Grangier, Dan Busbridge, Eleonora Gualdoni, Marco Cuturi, Pierre Ablin
Browse the full ICML paper archive.
Louis Bthune, David Grangier, Dan Busbridge, Eleonora Gualdoni, Marco Cuturi, Pierre Ablin
Browse the full ICML paper archive.