Byte Latent Transformer (BLT) by Meta AI - A Tokenizer-free LLM

Поділитися
Вставка
  • Опубліковано 11 лют 2025

КОМЕНТАРІ • 9

  • @avinashsuresh5221
    @avinashsuresh5221 17 днів тому

    My friend showed me this. I like the content, the detail and the way of your explanation. Earned a sub!

  • @camelCased
    @camelCased Місяць тому +2

    Can't wait for large-context-models (another paper by Meta) combined with BLT. It might noticeably improve the models while using the same training data.

  • @panzerofthelake4460
    @panzerofthelake4460 Місяць тому +5

    thank you! Now I understand the paper better!!! BLT was really hard to understand with just reading aint gon lie

  • @AarushAggarwal-b1p
    @AarushAggarwal-b1p Місяць тому

    Huge thanks to you. I cant thank you enough, your videos make things so easier to understand.

    • @aipapersacademy
      @aipapersacademy  Місяць тому

      Thank you so much for your kind words! It's amazing to know that 😊

  • @catman4859
    @catman4859 Місяць тому

    This was beautiful, thanks.

  • @leemgs
    @leemgs Місяць тому +1

    Awesome

  • @NickYoungblut
    @NickYoungblut Місяць тому +1

    First principles thinking: why not go to the fundamental level of all things digital? Byte-level LLMs (byte -> byte) are the most universal. So, no more trying to tokenize many human languages; byte-level models could handle ANY type of digital data. o1 predicts that byte-level LLMs will be cost effective by 2026-2028. We will see if that is correct...