Hacker News new | ask | show | jobs
by tkellogg 763 days ago
what even is “a model”? I’m not sure there is a technical definition that corresponds to how it’s used by the tech public

- single interconnected neural network (LLM attention layers break this, autoencoders complicate this)

- single training pass (LLMs have multiple passes, GANs have a single but produce multiple models)

1 comments

> - single training pass (LLMs have multiple passes, GANs have a single but produce multiple models)

LLMs have multiple passes? wdym?