News for hackers. Stuff that matters.
Re:Fmllm: 4mb training data, 100mb model, Fibonacci embeddin... by vessenes on Friday August 22, 2025 @07:07AM (#44983048)
I understand you’re worried about publishing your code. I’d be happy to help do something with this at a larger scale, but I think I could use a litttle more detail. Are you saying the training task is to ask for the (fib_i)th token rather than the next token?

If that’s all you did, then I think you’ll probably benefit more from just publishing the code then holding it back. Check out for instance lucidrains (Phil Wang) repository on GitHub to see the speed at which a full academic paper is turned into a python codebase for replication.

Anyway, I suggest you add a little code snippet illustrating the key point, or just confirm on my q. I think it would be fun to train a larger model!

Re:Fmllm: 4mb training data, 100mb model, Fibonacci embeddin... by gabriel666smith on Friday August 22, 2025 @08:05AM (#44983494)
Thank you, I agree, I think it'd be helpful to publish aspects of it.

> Are you saying the training task is to ask for the (fib_i)th token rather than the next token?

Yes, functionally - I explained in more detail in another comment.

I'm not sure which is the key point (sort of what I'm trying to work out), but I'll get the model-generation code into the repo. Is that the best thing for you?