The Busy Person's Intro to Finetuning & Open Source AI - Wing Lian, Axolotl

**swyx** (0:12)
Welcome to Latent Space, a special edition with Wing Lian, but also with our new guest host, Alex.

**Alex Volkov** (0:18)
Hello, hello.

**swyx** (0:19)
Welcome, welcome. Again, needs no introduction. I think it's like your sixth time on Latent Space already.

**Alex Volkov** (0:23)
I think so, yeah.

**swyx** (0:24)
And welcome Wing, we just met, but you've been very prolific online.

**Wing Lian** (0:28)
All right, thanks for having me.

**swyx** (0:29)
Yeah, so you are in town. You're not local, you're in town. You're from Minneapolis?

**Wing Lian** (0:35)
Annapolis, yeah. It's funny, because a lot of people think it's Indianapolis. I've gotten Minneapolis.
But I used to live out at least in the San Francisco Bay Area years ago, from 2008 to 2014, so it's fairly familiar here.

**swyx** (0:50)
Yeah, you're the maintainer of Axolotl now, which we'll get into. You're very, very prolific in the open source AI community, and you're also the founder of the Open Access AI Collective.

**Wing Lian** (0:59)
Yeah.

**swyx** (1:00)
Cool, awesome. Maybe we can go over a little bit of your backgrounds into tech and then coming into AI and then we'll cover what happens and why you're here.

**Wing Lian** (1:10)
Back on tech, I started years ago. I started way back when I was scraping apartment websites for listings and then building SEO optimized pages and then just throwing Google AdSense on it, and that got me through college basically.

**swyx** (1:27)
Is that decent money? What year was this?

**Wing Lian** (1:29)
Like 2004, 2005

**swyx** (1:31)
Yeah, that's decent money.

**Wing Lian** (1:32)
It was like a thousand bucks a month, but as a college student, that's really good money.
Then there's just too much competition. It just died off. I was writing stuff in Perl back then using like who?
Nobody is hosting anything on Perl anymore. Still did a little bit more like computer tech support and then software and web more professionally, so I spent some time working on applications in the blood industry. I came out to San Francisco for, I was at SGN, so Social Gaming Network as a startup. They started doing with Facebook apps and then they pivoted into doing mobile apps and then from there I spent time of quite a few more startups since then and in the last few years I've been in the music space. So like I was at United Masters for a while and then the past year I've been at SoundCloud, but not doing that anymore and now that I have a lot more time it's just like all right, we're going full bore on Axolotl and we're gonna we're gonna crush AI.

**swyx** (2:34)
Yeah, totally. So you're here in town for the open source AI meetup that we had yesterday?

**Wing Lian** (2:39)
Yeah, yeah, that was amazing.

**swyx** (2:41)
Yeah, it was a big collection. Llama, Nous Research, Alignment Lab, anyone else that I missed? I mean, Jeremy Howard is his own thing.
And Alex, you're also there. You love to bring SF to the world. Your takes?

**Alex Volkov** (2:55)
It's incredible that we recorded a Thursday episode after that one and LDJ, who's usually co-hosts Thursday, I just like briefly mentioned. Oh, yeah, I talked like I saw Karpathy and then I talked with Jeremy Howard and the guy from Mistral came in. It's like he's talking about all these titans of industry, basically that outside of SF, you just don't meet casually hanging out in the same space. You can't pull somebody. He ran into the Laylow from Mistral. He ran into him while drinking water. He didn't even know he was there. It's just that type of stuff is really hard to find outside of SF. So absolutely, absolutely great. And also presentations from Alignment Labs, presentations from Nous Research. Nous Research just talked about Forge and some of the other stuff they announced.

**swyx** (3:34)
We can say now they're officially a company. Yeah, I met Teknium.

**Alex Volkov** (3:37)
Yeah, he came over here. He didn't want to get recorded, but maybe...

**swyx** (3:40)
Yeah, we'll wear him down at some point.

**Wing Lian** (3:42)
Yeah, I'm excited for Forge. They've positioned as this agentic sort of framework, where it's just drag and drop things and fill in text with where you want to inject different variables. And it opens up all of these potentials for data pipelines now, right? And using your own local LLMs and not relying on GPT-4 or anything like that.

**swyx** (4:01)
Yeah, yeah, good stuff.
Okay, so let's maybe go into the Axolotl origin story. And then we have some intro or background to do on the open source model universe and also on fine tuning. But maybe just since you're talking about your personal journey, what was your personal journey into Axolotl?