lm_eval/tasks/triviaqa.py · f08f7c791307ae41d0579bfbd2360e0a44e7cbe0 · gaoqiong / lm-evaluation-harness

Stella Biderman authored Aug 08, 2023

Removes the `_remove_prefixes` optimization as it's invalid for exact match metrics. Closes https://github.com/EleutherAI/lm-evaluation-harness/issues/726

f08f7c79

triviaqa.py 2.94 KB

Replace triviaqa.py