Justin Lee dc406b4769 setup meta-eval for benchmark, ray error hace 7 meses
..
__init__.py e52e1d1ab4 updated prompt migration to use benchmark and also mipro, added meta implementation hace 8 meses
datatypes.py e52e1d1ab4 updated prompt migration to use benchmark and also mipro, added meta implementation hace 8 meses
download_mmlu_pro.py e19b9e9e34 added fix split, gitignore and download mmlu script hace 7 meses
helpers.py e19b9e9e34 added fix split, gitignore and download mmlu script hace 7 meses
humaneval.py 314b6a874a added updated llama-mmlu-pro and added human-eva hace 8 meses
leaderboard_mmlu_pro.py e52e1d1ab4 updated prompt migration to use benchmark and also mipro, added meta implementation hace 8 meses
llama_mmlu_pro.py dc406b4769 setup meta-eval for benchmark, ray error hace 7 meses