5 Commits

Author	SHA1	Message	Date
Gnome Ann	67e28d2b5c	Typical sampling needs to use nansum instead of sum ... If `probs` is zero then `log_probs` will be negative infinity, and the calculation of `neg_entropy` would then give NaN because zero times infinity is a mathematically indeterminate value. We need to use nansum so that those NaN values are treated as zeros to ignore them in the entropy calculation.	2022-03-28 00:02:31 -04:00
Gnome Ann	e2cd49d552	Typo fix in TypicalLogitsWarper	2022-03-27 17:08:57 -04:00
Gnome Ann	bbd0a83fef	Fix TypicalLogitsWarper argument typing	2022-03-27 16:59:23 -04:00
Gnome Ann	20e48b11d7	Typical sampling	2022-03-27 16:25:50 -04:00
Gnome Ann	3f18888eec	Repetition penalty slope and range	2022-01-24 15:30:38 -05:00