Alexandru Coca

Hi @HeyangQin, thanks for your great work! Is there any update on the timeline of merging T5 support?

@HeyangQin @loadams I take it that this is not on your roadmap?

Hi @ivo-1 , have you made any headway with this? I am interested in the same!

Good question, I was wondering if you figured this out?

Hi @niloofardadras , The calculations of the Shapley values using KernelShap needs to treat, in turn, each possible combination of inputs as "missing" (aka you estimate a contribution by seeing...

@niloofardadras , yes, you understood correctly. But using a model agnostic method is going to come with a significant computational cost. It is better to use the specialised models as...

> That is because the number of samples used by KernelExplainer determines its runtime (because it determines how many times it needs to run the underlying model). When you reduce...

Hi @slundberg , Thanks for the reply, your explanation makes sense. So simply put, I should also change `nsamples` to some smaller value to see the benefits, with the trade-off...

@slundberg I added some to alibi last year, you can direct people who are interested to our example.

Hi @psybuzz, Thanks for getting back, apologies for being late in responding -- a busy spell at this end. Let me get back to you with a proper answer to...