Jacob Prince-Bieker

Awesome! Thanks for finding that. Looks quite complete, only thing I notice is that `layers.txt` and `latent_stack.txt` are the same content, so there might be a mistake on copy/paste or...

Thanks for pointing it out! That helps a lot

I would also like this support or something similar. Geospatial datasets come in netcdf which is derived from hdf5, or zarr. I've gotten zarr stores to work with datasets and...

No, this is a great place to talk about it! That test does use a lot of GPU memory, and I think that is just expected, the model is almost...

Yeah, a PR would be great! I'm currently working on mirroring the dataset on HuggingFace to make it easier for anyone else to reproduce the paper, but for now that...

I'm working on adding a training script that uses Deepspeed which should help reduce the gpu memory requirements, albeit with some reduced training speed. Other than that, my only other...

Nice! Your implementation looks quite good, does it train correctly? This repo's implementation still gives NaN values in the Sampler.

Yeah, they released the pseudocode, which is now also in this repo. So my attention is copied from theirs. Currently, I haven't worked with their data yet, so its just...

I am still working on it, the implementation should be fairly complete, it is nearly a 1 to 1 copy of their pseudocode, including for training. I haven't trained the...

Hi, glad you like this work! I hadn't thought about adding the metrics, but probably will at some point either here, or in HuggingFace Evaluate to have it be more...