vault backup: 2024-12-31 - 1 files

Affected files:
Resources/Understanding Transformers.md

Resources/Understanding Transformers.md

@@ -18,6 +18,8 @@ The Illustrated Transformer - [https://jalammar.github.io/illustrated-transform
 - GPT in 60LOC https://jaykmody.com/blog/gpt-from-scratch/
 	- pre read https://jaykmody.com/blog/attention-intuition/
 	- starts simple, ramps up. Fills in all the gaps between Attention is All You Need right up to coding every single line of a working GPT2 implementation yourself. Even ends with explanations of finetuning for classification, summarization, instruction tuning, and PEFT. 
+- encoder side of transformers
+	- https://x.com/rfeers/status/1872960705751908826?s=46
 - explore miniGPT and nanoGPT via Karpathy
 	- [makemore and neural networks zero to hero](https://www.youtube.com/watch?v=VMj-3S1tku0&list=PLAqhIrjkxbuWI23v9cThsA9GvCAUhRvKZ)
 	- [tweetstorm](https://twitter.com/karpathy/status/1468370605229547522?s=20) on convergence, tweetstorm on [expressive, optimizable, efficient/parallelizable](https://twitter.com/karpathy/status/1593417989830848512?s=20) - elaborated in [1hr stanford lecture](j) and [8min lex fridman summary](https://www.youtube.com/watch?v=9uw3F6rndnA)