Comment on Is there any actual standalone AI software?
hendrik@palaver.p3x.de 3 months agoI don't think they break them down. For most models the math requires to start at the beginning and train each model individually from ground up.
But sure, a smaller model generally isn't as capable as a bigger one. And you can't train them indefinitly. So for a model series you'll maybe use the same dataset but feed more into the super big variant and not so much into the tiny one.
Rhaedas@fedia.io 3 months ago
The breaking down I mentioned is the quantization that forms a smaller model from the larger one. I didn't want to get technical because I don't understand the math details myself past how to use them. :)
hendrik@palaver.p3x.de 3 months ago
Ah, sure. I think a good way to phrase it is to say they lower the precision. That's basically what they do, convert the high precision numbers to lower precision fomats. That makes the compitations faster and the files smaller.
And it also doesn't apply to text, audio and images. As far as I know quantization is mainly used with LLMs. It's also possible with images and audio, but generally they don't do that. As far as I remember it leads to degradation and distortions pretty fast. There are other methods like pruning used with generative image models. That brings down their size substantially.