Wing Lian: evaluation

Transcript context

…Wang, for, for folks who use Axolotl, your users, some people who maybe, Want to try it out? And do they need to know the differences? Do they need to know the implementation details of QLora versus ReLora? Or is it okay for them to just know that Axolotl is the place that already integrated them? And if that's true, if that's all they need to know, how do they choose which method to use? Yeah, so I think like, I think most people aren't going to be using ReLora. I think most people are going to be using either Lora or QLora. And I think they should have it. They should have an understanding of why they might want to use one over the other. Most people will say that with Qlora, the quality of the final model is not quite as good as like if you were to do a LoRa or a full fine tune, right? Just because, you've quantized these down, so your accuracy is probably a little off, and so that by the time you've done the Qlora, you're not moving the weights how you would on a full fine tune with the full parameter weights. Interesting. Okay, cool. For people who are more interested, obviously, read the papers. I just wanted to give people, like, a high level overview of what these things are. And you've done people a service by making it easy for people to try it out. I'm going to, I'm going to also ask a question which I know to be wrong, but I'm curious because I get asked this all the time. What is the difference between all these kinds of fine tunes…

Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.