COMMITS
/ eval/utils.py June 5, 2024
H
minor fixes
Hamish Ivison committed
March 29, 2024
Y
Add IFEval for formatting instruction following and Xstest evaluation for refusal (#133)
Yizhong Wang committed
March 4, 2024
D
Subfolder evaluation (#126)
David Wadden committed
February 23, 2024
H
refactor: load model sep. from tokenizer
Hamish Ivison committed
February 21, 2024
H
tokenizer util
Hamish Ivison committed
February 13, 2024
D
Trust HF OLMo models.
David Wadden committed
January 29, 2024
H
optional olmo import
Hamish Ivison committed
December 19, 2023
H
Fixes and changes for olmo
Hamish Ivison committed
October 3, 2023
Y
Support batch eval for trutufulqa mc setup.
yizhongw committed
September 22, 2023
Y
Merge pull request #62 from OyvindTafjord/fix-logprobs
Yizhong Wang committed
Y
Use fast tokenizer by default.
yizhongw committed
O
Fix merge issue
Oyvind Tafjord committed
O
Merge remote-tracking branch 'upstream/main' into fix-logprobs
Oyvind Tafjord committed
O
Fix MMLU answer prompts and logprobs normalization
Oyvind Tafjord committed
September 4, 2023
August 14, 2023
Y
Manually set the max length of OPT/Pythia tokenizers.
yizhongw committed
Y
Y
Y
Fix a bug: during evaluation, we add back special token by default.
yizhongw committed
July 24, 2023
Y
fix a bug in keyword stopping criteria
yizhongw committed
June 9, 2023
H
initial commit
Hamish Ivison committed