Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

LLM Visualization

bbycroft.net

Post reply on HN
Print view View original

51–60 of 138 posts

Re: LLM Visualization

#51

Post by pizza »

kmeisthax wrote: post #43
atgctg wrote: post #39

A lot of transformer explanations fail to mention what makes self attention so powerful. Unlike traditional neural networks with fixed weights, self-attention layers adaptively weight connections between inputs based on context. This allows transformers to accomplish in a single layer what would take traditional networks multiple layers.

None of this seems obvious just reading the original Attention is all you need paper. Is there a more in-depth explanation of how this adaptive weighting works?

softmax(QK) gives you a probability matrix of shape [seq, seq]. Think of this like an adjacency matrix with edges with flow weights that are probabilities. Hence semantic routing of parts of X reduced with V.

where

- Q = X @ W_Q [query]

- K = X @ W_K [key]

- V = X @ V [value]

- X [input]

hence

attn_head_i = (softmax(Q@K/normalizing term) @ V)

Each head corresponds to a different concurrent routing system

The transformer just adds normalization and mlp feature learning parts around that.

Re: LLM Visualization

#52

Post by atonalfreerider »

arikrak wrote: post #41

This looks pretty cool! Anyone know of visualizations for simpler neural networks? I'm aware of tensorflow playground but that's just for a toy example, is there anything for visualizing a real example (e.g handwriting recognition)?

We made a VR visualization back in 2017 https://youtu.be/x6y14yAJ9rY

Re: LLM Visualization

#53

Post by thierrydamiba »

skadamat wrote: post #40

If folks want a lower dimensional version of this for their own models, I'm a big fan of the Netron library for model architecture visualization. Wrote about it here: https://about.xethub.com/blog/visualizing-ml-models-github-n...

Thanks for sharing.

What an exciting time to be learning about LLMs. Everyday I come across a new resource, and everything is free!

Re: LLM Visualization

#54

Post by kaimac »

kmeisthax wrote: post #43
atgctg wrote: post #39

A lot of transformer explanations fail to mention what makes self attention so powerful. Unlike traditional neural networks with fixed weights, self-attention layers adaptively weight connections between inputs based on context. This allows transformers to accomplish in a single layer what would take traditional networks multiple layers.

None of this seems obvious just reading the original Attention is all you need paper. Is there a more in-depth explanation of how this adaptive weighting works?

I found these notes very useful. They also contain a nice summary of how LLMs/transformers work. It doesn't help that people can't seem to help taking a concept that has been around for decades (kernel smoothing) and giving it a fancy new name (attention).

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

Re: LLM Visualization

#55

Post by albertzeyer »

kmeisthax wrote: post #43
atgctg wrote: post #39

A lot of transformer explanations fail to mention what makes self attention so powerful. Unlike traditional neural networks with fixed weights, self-attention layers adaptively weight connections between inputs based on context. This allows transformers to accomplish in a single layer what would take traditional networks multiple layers.

None of this seems obvious just reading the original Attention is all you need paper. Is there a more in-depth explanation of how this adaptive weighting works?

The audience of this paper are other researchers who already know the concept of attention, which was very well known already in the field. In such research papers, such things are never explained again, as all the researchers already know this or can read other sources, which are cited, but focus on the actual research questions. In this case, the research question was simply: Can we get away by just using attention and not using the LSTM anymore? Before that, everyone was using both together.

I think learning it following it more this historical development can be helpful. E.g. in this case here, learn the concept of attention, specifically cross attention first. And that is this paper: Bahdanau, Cho, Bengio, "Neural Machine Translation by Jointly Learning to Align and Translate", 2014, https://arxiv.org/abs/1409.0473

That paper introduces it. But even that is maybe quite dense, and to really grasp it, it helps to reimplement those things.

It's always dense, because those papers already have space constraints given by the conferences, max 9 pages or so. To get a better detailed overview, you can study the authors code, or other resources. There is a lot now about those topics, whole books, etc.

Re: LLM Visualization

#56

Post by airstrike »

WhitneyLand wrote: post #44
atgctg wrote: post #39

A lot of transformer explanations fail to mention what makes self attention so powerful. Unlike traditional neural networks with fixed weights, self-attention layers adaptively weight connections between inputs based on context. This allows transformers to accomplish in a single layer what would take traditional networks multiple layers.

In case it’s confusing for anyone to see “weight” as a verb and a noun so close together, there are indeed two different things going on: 1. There are the model weights, aka the parameters. These are what get adjusted during training to do the learning part. They always exist. 2. There are attention weights. These are part of the transformer architecture and they “weight” the context of the input. They are ephemeral.…

I always thought the verb was "weigh" not "weight", but apparently the latter is also in the dictionary as a verb.

Oh well... it seems like it's more confusing than I thought https://www.merriam-webster.com/wordplay/when-to-use-weigh-a...

Re: LLM Visualization

#57

Post by quickthrower2 »

gryfft wrote: post #2

Damn, this looks phenomenal. I've been wanting to do a deep dive like this for a while-- the 3D model is a spectacular pedagogic device.

Andrej Karpathy twisting his hands as he explains it is also a great device. Not being sarcastic, when he explains it I understand it for a good minute it two. Then need to rewatch as I forget (but that is just me)!

Re: LLM Visualization

#58

Post by andai »

kmeisthax wrote: post #43
atgctg wrote: post #39

A lot of transformer explanations fail to mention what makes self attention so powerful. Unlike traditional neural networks with fixed weights, self-attention layers adaptively weight connections between inputs based on context. This allows transformers to accomplish in a single layer what would take traditional networks multiple layers.

None of this seems obvious just reading the original Attention is all you need paper. Is there a more in-depth explanation of how this adaptive weighting works?

Turns out Attention is all you need isn't all you need!

(I'm sorry)

Re: LLM Visualization

#59

Post by andai »

WhitneyLand wrote: post #48
kmeisthax wrote: post #43

Earlier quoted context omitted.

None of this seems obvious just reading the original Attention is all you need paper. Is there a more in-depth explanation of how this adaptive weighting works?

It’s definitely not obvious no matter how smart you are! The common metaphor used is it’s like a conversation. Imagine you read one comment in some forum, posted in a long conversation thread. It wouldn’t be obvious what’s going on unless you read more of the thread right? A single paper is like a single comment, in a thread that goes on for years and years. For example, why don’t papers explain what tokens/vectors/e…

Is there a way of finding interesting "chains" of such papers, short of scanning the references / "cited by" page?

(For example, Google Scholar lists 98797 citations for Attention is all you need!)

Re: LLM Visualization

#60

Post by wrsh07 »

Arson9416 wrote: post #11
reqo wrote: post #4

I feel like visualizations like this are what is missing from univeristy curricula. Now imagine a professor going trough each animation describing exactly what is happening, I am pretty sure students would get a much more in-depth understanding!

Isn't it amazing that a random person on the internet can produce free educational content that trumps university courses? With all the resources and expertise that universities have, why do they get shown up all the time? Do they just not know how to educate?

You're betting on the hundreds of top university cs professors to produce better content than the hundreds of thousands of industry veterans or hobbyists...

Why does YouTube sometimes have better content than professionally produced media? It's a really long tail of creators and educators

Post reply on HN