sinequa

/

passage-ranker.pistachio

like 1

could I ask to have the order of languages and datasets be the same as for the hazelnut model please?

I kept the same oder as the mango ranker, should I also change it?

Note that I changed the sentence "Note that the relevance score is computed as an average over 14 retrieval datasets (see...", using "several" instead of 14 because in case of polish it's not over 14 datasets 😁

@clarine ok I understand. I would be in favor of having EVERY model card unified, what do you think?

good for me