Tamas Molnar
Tamas Molnar
Was this feature ever implemented in the end?
Hi @michaelfeil, Some time has passed, what do you think about the comparison to TEI nowadays? So far I'm very happy with infinity, was using it for text embedding with...
I'm also wondering what the next best option is to host classification models on CPU? Pytorch enginge seems to load fine.
Hi @rochacbruno, Thanks for getting back to me! To me both syntaxes look fine. Since we already have to be cautious with double underscore, triple underscore doesn't sound so bad...
@rochacbruno could you point me to some example how I could implement this behaviour with a hook/loader? Thank you!
@TDesjardins could you provide a working example? Thanks a lot!
> Hey @molntamas, I'm working to update the documentation and examples. It will be available soonish this or in the following week. Thank you!