• by xianshou on 7/3/2024, 1:12:19 AM

    Illustrated Transformer is amazing as a way of understanding the original transformer architecture step-by-step, but if you want to truly visualize how information flows through a decoder-only architecture - from nanoGPT all the way up to a fully represented GPT-3 - nothing beats this:

    https://bbycroft.net/llm

  • by ryan-duve on 7/2/2024, 11:28:25 PM

    I gave a talk on using Google BERT for financial services problems at a machine learning conference in early 2019. During my preparation, this was the only resource on transformers I could find that was even remotely understandable to me.

    I had a lot of trouble understand what was going on from just the original publication[0].

    [0] https://arxiv.org/abs/1706.03762

  • by crystal_revenge on 7/3/2024, 2:35:44 PM

    While I absolutely love this illustration (and frankly everything Jay Alammar does), it is worth recognizing there is a distinction between visualizing how a transformer (or any model really works) and what the transformer is doing.

    My favorite article on the latter is Cosma Shalizi's excellent post showing that all "attention" is really doing is kernel smoothing [0]. Personally having this 'click' was a bigger insight for me than walking through this post and implementing "attention is all you need".

    In a very real sense transformers are just performing compression and providing a soft lookup functionality on top of an unimaginably large dataset (basically the majority of human writing). This understanding of LLMs helps to better understand their limitations as well as their, imho untapped, usefulness.

    0. http://bactra.org/notebooks/nn-attention-and-transformers.ht...

  • by tomashm on 7/4/2024, 8:58:36 AM

    This is good, but what bade me finally understand the transformer architecture [0] and attention [1], are 3Blue1Brown's videos.

    0. https://www.youtube.com/watch?v=wjZofJX0v4M

    1. https://www.youtube.com/watch?v=eMlx5fFNoYc

  • by photon_lines on 7/3/2024, 7:32:29 PM

    Great post and write-up - I also made an in-depth explorations and did my best to use visuals - for anyone interested you can find it here: https://photonlines.substack.com/p/intuitive-and-visual-guid...

  • by jerpint on 7/3/2024, 12:49:43 AM

    I go back regligiously to this post whenever I need a quick visual refresh on how transformers work, I can’t overstate how fantastic it is