Sebastian Raschka
Sebastian Raschka
Hey @calvintwr , thanks again for bringing this up. It should be fixed now as of #1745
Thanks for raising this, something to look into. Could you print out the data inputs that are fed to the LLM to better see the issue? On that note, also,...
That's a good suggestion, thanks! But talking to some of my colleagues, this would currently not be preferred because we want to keep the number of dependencies low. But let's...
Thanks for the PR! > I noticed that some tests related to the tokenizer are failing. Note that these are not related to my updates (CC: @rasbt ). Do you...
@Andrei-Aksionov Sure, good point. Looks good!
No worries and no rush. I hope all is well, and safe travels.
> @rasbt @Andrei-Aksionov I was wondering. If we have access and can run gated tests locally, then ideally those tests should pass. I got issues with llama3.2 tokenizer tests. Do...
Thanks for the note. Not sure what happened there. Maybe I forgot to adjust the dataset as we updated the data loader. I will try to take a look next...
Of course, happy to assign you (I just see that @Andrei-Aksionov already beat me to it though 😅)
This would be amazing @rcmalli !