theapemachine
/

sparse-transformer-experiments

Model card Files Files and versions

sparse-transformer-experiments / paper

20.6 kB

Ctrl+K

Ctrl+K

1 contributor

History: 2 commits

theapemachine's picture

Major revision: add phantom momentum ablation, compute-matched baselines, multi-seed predictor accuracy

96bc237 verified 15 days ago

main.tex

20.6 kB
Major revision: add phantom momentum ablation, compute-matched baselines, multi-seed predictor accuracy 15 days ago