Open Inc0mple opened 7 months ago
I do plan to support these kinds of models in the future. I need to hammer out how to adjust the existing architecture to handle them, but it'll happen in the not too far future. (I'm also looking at adding stable diffusion support, as that'll come pretty much free with encoder-decoder models.)
Waiting for T5. Hopefully it arrives sooner than expected
Yes, T5 support would be awesome.
Thanks you for amazing library. Great work!!
+1
Hi, thanks for sharing this awesome work! Are there any plans to support Encoder-Decoder models like T5? Are there any methods for merging such models?