kogasa,
@kogasa@programming.dev avatar

Semantic embeddings are a thing. LLMs “work with tokens” but they associate them with semantic models internally. You can externalize it via semantic embeddings so that the same semantic models can be shared between LLMs.

  • All
  • Subscribed
  • Moderated
  • Favorites
  • linux@lemmy.ml
  • localhost
  • All magazines
  • Loading…
    Loading the web debug toolbar…
    Attempt #