We’re releasing model weights for our 8B- parameter Dynamic Byte Latent Transformer, an alternative to traditional tokenization methods with the potential to redefine the standards for language model efficiency and reliability.

Learn more about how Dynamic Byte Latent… pic.twitter.com/1XUtTpq95S

— AI at Meta (@AIatMeta) 12 mai 2025

We’re releasing model weights for our 8B- parameter Dynamic Byte Latent Transformer, an alternative to traditional tokenization methods with the potential to redefine the standards for language model efficiency and reliability. Learn more about how Dynamic Byte Latent

→ View original post on X — @aiatmeta,