This LLM from Meta skips the tokenizer, reading text like computers do (bytes!) for better performance. The training and inference code for BLT is released on GitHub. @AIatMeta just released the model weights for their 8B-param Dynamic Byte Latent Transformer (BLT), an https://t.co/iTDPbgyPG5 https://t.co/ohni3799lP
— Rohan Paul (@rohanpaul_ai) May 12, 2025
from Twitter https://twitter.com/rohanpaul_ai
May 12, 2025 at 05:13PM
via IFTTT
No comments:
Post a Comment