161: Leveraging Generative AI Models with Hagay Lupesko
Programming Throwdown
00:00
The Scaling Laws of Machine Learning
A paper published by OpenMind. basically talks about the scaling laws, which are all referring to very similar architecture. So a model like OPT or even GPT-3 was actually under trained for its size. You can take an actually a smaller model with less parameters, train it on more data and it will perform just as well or even better than a bigger model training on less data.
Transcript
Play full episode
