Open dlvp opened 1 year ago
Hi,
Thanks for pointing this out! I think this is my bad, the right thing is to change "typical=0.95" to "typical_p=0.95". I will fix this code release and double check my experiments. This might just be something I dropped when migrating my code base from dev to release.
Thanks again!
Hello @XiangLi1999 and @ari-holtzman, I'm trying to follow the implementation of the typical decoding baselines in the code base. Here a
typical
argument is passed, but the generate method does not accept any such argument but only an optional argumenttypical_p
. At the same time I am unable to find any call tomodel_kwargs['"typical"]
anywhere so it seems no warping of the logits to do typical sampling is ever performed. Am I missing something trivial?