Paul Xu

Sure! Here's what I understand what the issue is: suppose I have a regression `rt ~ 0 + (1|subject_idx)`. For `1|subj_idx`, I want to assign a custom bounded prior with...

Yeah the latter is what I was trying. There does seem to be a bug. Is there a way to make `bmb.Prior` more general in that it can accept bounds?...

@tomicapretto Thank you for looking into this! I think this is a slightly different issue. Sorry I should have included the error message so it's a bit more clear. Here's...

No I am just using your code to show that a different error can be caused. Please see the first block of code for the error.

Thanks @tomicapretto! Do you have a moment for a quick call? Please feel free to pm me on slack :)

Our users have reported similar errors with more contextual information. Please see this issue: https://github.com/lnccbrown/HSSM/issues/301

Thanks for looking into this, @tomicapretto! I am using MacOS (ARM64) with Python 3.11, but the user who reported the issue seems to be using linux, with Python versions both...

Thanks @tomicapretto! Looks like this fixed it on my end 👍

@tomicapretto We implemented a temporary solution which just samples the `posterior` group of the trace object and then pass it to `model.predict`. Do you foresee issues with this?

@tomicapretto Sure! I'll do a PR soon. Thanks!