d

  • Lambda@lemmy.ca
    link
    fedilink
    arrow-up
    11
    ·
    7 days ago

    Yeah, if words were actually encoded as 1-hot vectors this would be pretty trivial, but the rest of LLM training would be somewhere between infeasible and impossible. The actual embedding vectors obscure spelling even more.

    Side note: last time I checked, current embedding vectors were approximately 40 dimensional… Has that gone up significantly in the last couple of years?