flip

@arieltoledo , or others. Did you ever figure out if it's possible to add such a penalty with gpt-2 simple? I'm interested in doing the same

I'm actually enjoying reading this conversation, and it may be of help to me, as I'm interested in analogous projects. I vote for keeping the generically useful questions here. On...

This is exactly what I came here to ask about! I assume this feature isn't yet implemented? Until the feature is implemented, what is the "right" way to go about...

Perfect -- that's really easy. I'm using this in case it helps anybody: ``` partial(model, pred.var = "predictor", ice = TRUE, center = TRUE, plot = TRUE, plot.engine = "ggplot2",...

Has any progress been made on this front? It would be immensely helpful to have a variable importance measure that isn't sensitive to the total number of cut-points a variable...