‹ BackHN Continuity

Thread

Show HN: Mini-AGI – Dynamic continual learning model trained on 8GB VRAM

277 points · 81 comments · volotat

  1. comboy · · focus · HN ↗
    what character prediction rates are you getting on some unseen datasets?
    1. volotat · · focus · HN ↗
      The held-out scores reported in the Readme IS the unseen dataset.
      1. comboy · · focus · HN ↗
        These are not successful prediction rate per char though.
        1. volotat · · focus · HN ↗
          I got you, will add later to the repository.
          1. comboy · · focus · HN ↗
            Thanks, it seems like a nice way to compare effectiveness of different non-typical methods which are not yet capable of some more ambitious benchmarks.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.