hibijibies

It's probably not that many people necessary for creating a decent model. Soofi was small team: https://news.ycombinator.com/item?id=48870978

I would think it's the fact that there's no secret sauce except data and compute to get to a decent model along with a good team. It's a Nemtron 3 Nano architecture as far as I understand, and of course there seems to be some special data curation for German.

Hi, I'm from Embedl (embedl.com / https://huggingface.co/embedl) and we made the hfviewer. Could you please elaborate more on why the Nemotron model visualization might be incorrect? A number of passes are performed to get the graph structure from the HuggingFace conf including sometimes exporting the model with torch.export and the recombining it to make the view meaningful. We would love to fix any issues and make the viewer better.

Nice article and explanations!

On a tangential note, I keep noticing "why x matters", "it's crucial here" that just remind me of Claude. Recently Claude has been gaslighting me in complex problems with such statements and seeing them on an article is low-key infuriating at this point. I can't trust Claude anymore on the most complex problems where it sometimes gets the answer right but completely misses the point and introduces huge complex blocks of code and logic with precisely "why it matters", "this is crucial here".

I like all the amazing comments and critique there but have we considered that somehow, the neural network was able to formulate the concept of gravity, emulate a chaotic system and do all of it using a constant computational cost? It is a bunch of interacting units that reconfigured itself using gradient descent to behave like a chaotic three body system. I find that quite fascinating. Although I would agree that the hype created is not justified but this neural network approach bypasses concepts of gravity, newtonian mechanics, chaos, ODE integration and gives a simple function to calculate position at arbitrary times. Quite interesting.