4 comments

  • xms17189 0 minutes ago
    How are you generating the architecture graph from model configs, and do you plan to surface tensor shapes or layer-level parameter counts as well?
  • alansml 21 minutes ago
    Love it, I thought it only shows the "guts" of a model, turns out it also estimates the cost of serving that model.
  • bicepjai 29 minutes ago
    Thanks for good vibes. This is awesome
  • mojosmojo 38 minutes ago
    extremely cool. I’ve had Claude walk model architectures to debug Loras and fine tunes, but this is delightful