Skip to content

Reproduce the dose-response + layer-sensitivity report card on small models (Qwen 1.5B/0.5B, T4)#17

Merged
bamdadd merged 9 commits into
mainfrom
feat/small-model-sweeps
Jul 20, 2026
Merged

Reproduce the dose-response + layer-sensitivity report card on small models (Qwen 1.5B/0.5B, T4)#17
bamdadd merged 9 commits into
mainfrom
feat/small-model-sweeps

Correct 0.5B claim: L23/0.96 argmax is REAL formal prose, not artifact

acab130
Select commit
Loading
Failed to load commit list.

Select a check to view from the sidebar