AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Using Chinchilla to Train a Computer Vision Model
Chinchilla has 70 billion parameters and then the ones we add on top, which is almost like a way to overwrite its little activations so that when it sees vision, it does kind of a correct computation. That adds an extra 10 billion parameters. So it's total 80 billion, the largest one we released. And then you train it on a few data sets that contain vision and language. It actually has this few shot learning ability and these emerging abilities that we didn't even measure once we were developing the model. Once developed, then as you play with the interface, you can start seeing wow okay yeah it's cool we can we can upload I think one of the tweets talking about