Massimo Caccia

That's a great idea! I'm doing a cleanup of the repo soon. Will create the section and add those. Thks

@TLESORT Instead of the `frontpage` tag, let's use a capital letter on the keyword

Hi Leslie! No sure what is left to be said. I guess it would be nice if there was some support for this :)

+1 this would be super useful.

I would also love to see an implementation of a Sparse DNC in chainer !

please add as per https://github.com/optimass/continual_learning_papers/blob/master/scripts/README.md

Hello, did anyone here manage to convert the finetuned ckpts into something that can be loaded in HF's `from_pretrained()` ?

looks like the default finetuning dataset is `torchtune.datasets.alpaca_dataset`, but I can't import it: ```python >>> import torchtune.datasets >>> import torchtune.datasets.alpaca_dataset Traceback (most recent call last): File "", line 1, in...

thanks! I scanned my hf cache but I could only find models. I found on stack overflow that `pip install -U datasets` might work, and it did ! [link](https://stackoverflow.com/questions/77433096/notimplementederror-loading-a-dataset-cached-in-a-localfilesystem-is-not-suppor).

Thanks for you help! Ok I got confused w/ the `safetensors`. Indeed, the weights are in `mode/original`, thanks!