Gigatoken: Fastest Tokenizer

(twitter.com)

23 points | by convexstrictly 21 hours ago ago

6 comments

  • ramon156 10 hours ago ago

    Doesn't really explain why its faster. "Optimizing for every kind of CPU" is not really enough info.

    Cool project nonetheless, I will go through the code later tomorrow

  • convexstrictly 21 hours ago ago
    • Alifatisk 11 hours ago ago

      They even added a section ”AI Use Disclosure”, beautiful!

  • benj111 11 hours ago ago

    I kind of assumed the model would process the text 'directly', from what I understand, wouldn't this be biasing the input based on how you tokenise as it's lossy?

    I assume this tradeoff is purely for speed/compression. Or am I missing what's going on here?

    • convexstrictly 10 hours ago ago

      Tokenization is done on the CPU. Models never see the raw characters. That's why you get trick questions like the number of r's in strawberry.

      There are many research papers on models using characters directly. One challenge is that effective context length is smaller.

  • doosdom 13 hours ago ago

    [dead]