In this video, i'll show you how you can train or finetune your own LLM in the least amount of code possible. In addition, as a bonus, ill also show you how you can do the same without writing any code at all.
For the coding part, we will be using torch, transformers, peft and trl libraries.
For the no-code solution, we will be using autotrain-advanced. You can install autotrain-advanced using pip: "pip install autotrain-advanced"
I'll be using my home machine. No cloud needed!
Please subscribe and like the video to help me keep motivated to make awesome videos like this one. :)
My book, Approaching (Almost) Any Machine Learning problem, is available for free here: bit.ly/approachingml
Follow me on:
Twitter: / abhi1thakur
LinkedIn: / abhi1thakur
Kaggle: kaggle.com/abhishek
Негізгі бет Train LLMs in just 50 lines of code!
Пікірлер: 56