Locked 96-task benchmark, a corrected version, a leak-free split, audited SFT corpora, and the Dax-1 probes in its native patch contract.
Isaac Onyemaechi Ugwu
Isaacdnigerian
·
AI & ML interests
None yet
Recent Activity
updated a collection about 11 hours ago
PLUMB datasets: tasks, runs and traces updated a dataset about 11 hours ago
Isaacdnigerian/plumb-runs published a dataset about 11 hours ago
Isaacdnigerian/plumb-runs