AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Is the Model Architecture Fundamentally Different?
The model itself was basically the same in the three cases. It's just how you're choosing to deploy it in ated in with the larger sulphor environment that you're in. I think, if there was more time, i would have loved to add a kind of upfront component, which would have been like, find two in the model. Take a pre trained model and find two in that model with just a little bit of data for slight different task or slightly different domain. And then sort of make it available in these three different ways. If you can sort of go through that process, i think you're really well set up to talk the language and understand how people go about their