You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
[-] Setup Global MMLU Testing Pipeline with lm-eval harness (If needed, turn them intoa 10% subset for quicker eval)
-> No longer using Global MMLU but Include-base-44 (each language has ~500 examples)
Select the target languages for evaluation
[-] Setup Global MMLU Testing Pipeline with lm-eval harness (If needed, turn them intoa 10% subset for quicker eval)-> No longer using Global MMLU but Include-base-44 (each language has ~500 examples)