Re:Byte Latent Transformer: Patches Scale Better Than Tokens
by cs702 on Saturday December 14, 2024 @04:23PM
(#42419554)
Thanks for the quick reply!
Interesting. I would have thought one of those "minimum viable" RNNs (like https://arxiv.org/abs/2410.01201) would have been ideal for this. I might tinker a bit with this :-)
Interesting. I would have thought one of those "minimum viable" RNNs (like https://arxiv.org/abs/2410.01201) would have been ideal for this. I might tinker a bit with this :-)