Comment by charcircuit
8 hours ago
Scale is all you need.
That's why you see other attention free large language models work. But in a world with constraints on time and compute the architecture does matter because scaling does have a cost (which is dropping)
Pretty much. See “Scaling Laws for Neural Language Models”, a must read IMO https://arxiv.org/html/2001.08361v1
Compute, data, and parameter count are the three logarithmic values that correspond to model performance.
So if you find ways of improving training efficiency (the simplest conceptually is probably local/global sliding window attention like Gemma; the latest DeepSeek and Kimis have quite fancy ones), you will be able to have more effective compute, and train smarter models while keeping data and param count the same.
If you find this fascinating and want to dive more, I encourage checking out nanochat (solid GPT-2 repro; minimal LoC); and trying to make architectural tweaks with a coding agent.
“Learning through experimentation” has never been easier or more fun in my opinion. If you have a GPU, even an older 8GB card (or a few bucks for Runpod), you can pretrain your own small language model and start experimenting / tweaking it.
Yes if you took a transformer network and added connections until it became a full network, then it would still work (?) but it would be a lot more expensive.
(?) We actually don't know that but it is very likely.
In Qwen 3.5, 75% of the layers are linear attention. I think the theory is that linear attention is usually enough, but some regular attention layers help to handle more sophisticated long-range relationships.
[flagged]
[flagged]