(study this code to speedrun your understanding of LLMs - by alpha nerd karpathy himself):

https://github.com/karpathy/nanoGPT

https://github.com/karpathy/minGPT

https://www.youtube.com/watch?v=kCc8FmEb1nY

(intro to NNs and gradient descent, again karpathy is the best)

https://www.youtube.com/watch?v=VMj-3S1tku0&list=PLAqhIrjkxbuWI23v9cThsA9GvCAUhRvKZ

(amazing writeup on how transformers work)

(models and torrents)

/lmg/ Model Links and Torrents

(llava - training visual llms like gpt4)

https://github.com/haotian-liu/LLaVA

(prompting hacks : theory of mind)

Boosting Theory-of-Mind Performance in Large Language Models via Prompting