Noah Lehmann-Haupt

@wontruefree Lucky should be relatively easy to implement - I've tried to make it relatively straightforward to just drop in "celestite_render()" instead of the framework's native render function (I just...

Just want to chime in here - I'm on an M1 Mac trying to build a dev version of the compiler and I'm running into this same error. I'm coming...

Thank you for the quick response @Optimox ! I just want to post a brief update that may or may not be helpful for others. Shortly after I posted the...

One quick update - I figured I should post the actual model creation code w/ params I'm using, if that's helpful: ``` clf = TabNetRegressor( cat_idxs=cat_idxs, cat_dims=cat_dims, cat_emb_dim=1, n_d=32, n_a=32,...

Oh wow you are legendary @Optimox! Thanks for uncovering that and I'm glad I was (indirectly) able to help fix a bug :) I'm retraining now and there's still a...

> I've just read this thread again and I just want to explain why the use of `torch.clamp` is solving your problem and why you need to be careful when...

> Thanks for pointing out the bug, glad that you can now properly train your tabnet model. > > Just out of curiosity, have you been able to benchmark tabnet...

> Maybe automatic field detection, or perhaps some clever DSLy field generation with the query macro can be done as a second round feature? Totally agreed. I'll get the initial...

Gonna jump into this starting this weekend - sorry for delay!

+1 to Crystal support. Just discovered Zed through your open source announcement (via Hacker News). Looks absolutely spectacular - looking forward to diving in. Unfortunately (or fortunately ;) I'm working...