4 comments

  • xms17189 3 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 23 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 32 minutes ago

    Thanks for good vibes. This is awesome

  • mojosmojo 41 minutes ago

    extremely cool. I’ve had Claude walk model architectures to debug Loras and fine tunes, but this is delightful