Project #2: LLM Visualization
@BrendanBycroft5 B takipçi
1.203.673 görüntüleme
12 Yorum
Yorumlar X (Twitter) üzerindeki orijinal gönderiden alınmıştır

@BrendanBycroft
It also contains a walkthrough/guide of the steps, as well as a few interactive elements to play with. Why, you ask? For what purpose did I put all the time & effort into this project?
222 beğeni

@BrendanBycroft
There's a real advantage to unpacking a set of abstractions, flattening them out. Abstractions can be useful for terseness and management, but they can be a real blocker to seeing the big picture.
118 beğeni

@BrendanBycroft
With this, you can see the whole thing at once. You can see where the computation takes place, its complexity, and relative sizes of the tensors & weights.
194 beğeni

@BrendanBycroft
The model with all the animations is tiiny, to make it tractable. For comparison, I threw in a few of the larger models (GPT-2, GPT-3), render-only. And when you see what it takes to just produce a single value in a mat-mul, the sheer scale of these things becomes apparent.
137 beğeni

@BrendanBycroft
(Here's what goes into calculating a _single_ output value of a matrix-multiply)
108 beğeni

@BrendanBycroft
What about understanding what each layer does? Uhh, sorry, won't be much help. The project just came out of "Let's build a 3D viz!", so the scope is a bit limited. It's more: here's a way to learn & digest the algorithm, and perhaps think about how to optimize the process.
73 beğeni

@BrendanBycroft
As for what I got out of creating this: before I made it, I mostly knew how image convolution nets worked, but language-based models seemed kinda magical in comparison. Well, now I know them in a fair amount of detail!
58 beğeni

@BrendanBycroft
I also learnt a good amount of GL (dF/dx, fwidth, ubos, instancing), and animation approaches. So, uhh, even if no-one sees this, the project definitely has some value to me.
64 beğeni

@BrendanBycroft
Oh yeah, the link is here: Works best on desktop (sorry mobile). Left-click drag, right-click rotate, scroll to zoom. And hover over the tensor cells. Blue cells are weights/parameters, green cells are intermediate values. Each cell is a single number!
172 beğeni

@BrendanBycroft
Well, I hope you find it interesting. Let me know your thoughts! And if someone makes it through the walkthrough and finds it a little ~incomplete towards the end I might even getting around to fix it (my attention has largely turned to other projects oops)
82 beğeni

@BrendanBycroft
Short follow-up thread:
36 beğeni

@BrendanBycroft
A technical guide to how I built it:
25 beğeni