There is a lot of interest in large language models.

As a developer or researcher, you are probably looking for a guide on how to ramp up on LLMs.

Here is a study plan you could try:

My suggested study plan for now: 1) get familiar with concepts, 2) learn about Transformers, 3) learn about the foundation models, 4) continue keeping track of code, papers, and results, and 5) get building.
1) CS224N: Natural Language Processing with Deep Learning

It doesn't hurt to learn some of the concepts first. Depending on your level of knowledge it might be suitable to try a more basic course.

https://t.co/d9yoNz8912
2) Stanford CS25 - Transformers United

Learn all about transformers in this fantastic course.

https://t.co/Ygx90FFf8C
3) Foundation Models

You can learn about all types of foundation models like GPT-3, DINO, CLIP, Codex, among others.

https://t.co/9WmXAd8lsJ
4) Keeping track of LLMs

You can learn about the specific models, datasets, and benchmarks on Papers with Code.

Find some here: https://t.co/mUF2DK4Wth
5) Developing with LLMs

Nothing stops you from building as you learn. I found the @huggingface model hub very useful for trying out models and running experiments. There are several APIs out there as well but that's in case you're ready to build some serious stuff.
The study plan above is far from complete and probably contains gaps. It's always good practice to take a few steps back if you don't get something. As always, try to seek advice if you are stuck, and always build responsibly.

Follow me (@omarsar0) for future guides.
I am also working on a more detailed step-by-step guide which I will be publishing soon. Stay tuned!

More from elvis

Amazing resources to start learning MLOps, one of the most exciting areas in machine learning engineering:



📘 Introducing MLOps

An excellent primer to MLOps and how to scale machine learning in the enterprise.

https://t.co/GCnbZZaQEI


🎓 Machine Learning Engineering for Production (MLOps) Specialization

A new specialization by https://t.co/mEjqoGrnTW on machine learning engineering for production (MLOPs).

https://t.co/MAaiRlRRE7


⚙️ MLOps Tooling Landscape

A great blog post by Chip Huyen summarizing all the latest technologies/tools used in MLOps.

https://t.co/hsDH8DVloH


🎓 MLOps Course by Goku Mohandas

A series of lessons teaching how to apply machine learning to build production-grade products.

https://t.co/RrV3GNNsLW

More from All

You May Also Like