How do you run these models on AMD GPUs?
Show HN: Duplicate 3 layers in a 24B LLM, logical deduction .22→.76. No training
61–70 of 100 posts
Re: Show HN: Duplicate 3 layers in a 24B LLM, logical deduction .22→.76. No training
#62Heh, for a couple last days, I've been doing this exact kind of "neuroanatomy" on Qwen2.5/Qwen3 too. Fascinating stuff. To make it easier to fiddle with the network, I created a small inference engine that is stripped of all the framework magic, just raw matmuls and all (main inference loop is just 50 lines of code!). For example, it's trivial to remove a layer: i just skip it in code with a simple "if". I've found t…
Very interesting stuff
Re: Show HN: Duplicate 3 layers in a 24B LLM, logical deduction .22→.76. No training
#63This is very cool
Re: Show HN: Duplicate 3 layers in a 24B LLM, logical deduction .22→.76. No training
#64[dead]
Which types of tasks, in your experience, show negligable improvement when using larger models? And for what types of tasks do you feel even the best models deliver mediocre results?
Re: Show HN: Duplicate 3 layers in a 24B LLM, logical deduction .22→.76. No training
#65Re: Show HN: Duplicate 3 layers in a 24B LLM, logical deduction .22→.76. No training
#66Assuming the benchmarks are sound (rather than capturing a fluke), the provided explanation still does not pass the smell test. As far as I can tell, there is nothing about the training process of these models that would encourage them to make the output of any layer apart from (n-1) meaningful as the input of layer n, unless perhaps these layers were initialised as identity and the training process did not get to ch…
> As far as I can tell, there is nothing about the training process of these models that would encourage them to make the output of any layer apart from (n-1) meaningful as the input of layer n
Right, I had the same thought.
Even if the output was in the same "format", does the LLM even have any way to know which order the outputs will go in? The ordering of the nodes is part of our representation of the network, it's not fundamental to it.
It would be like shuffling the bytes in a PNG file and expecting the program still to understand it as a PNG file.
The more I think about this, the more I don't get this at all.
Re: Show HN: Duplicate 3 layers in a 24B LLM, logical deduction .22→.76. No training
#67Earlier quoted context omitted.
That's explicitly not the unexpected part. Read the rest of the post.
After reading both the original post and this submission, what do you think is new here?
> The weird part: different duplication patterns create different cognitive "modes" from the same weights. Double-pass boosts math. Triple-pass boosts emotional reasoning. Interleaved doubling (13,13,14,14,15,15,16) creates a pure math specialist. Same model, same VRAM, different routing.
As far as I can see that's not implied by the original post.
But that's beside the point: quoting the bit where the poster says "here's what I'm building on top of" and using that to imply they haven't done anything new is a bit pointless, no?
Re: Show HN: Duplicate 3 layers in a 24B LLM, logical deduction .22→.76. No training
#68[flagged]
Re: Show HN: Duplicate 3 layers in a 24B LLM, logical deduction .22→.76. No training
#69[flagged]
@dang ban this AI bot spam
>is doing a lot of work here. tidy story, fits the result
That's 100% AI talk
Re: Show HN: Duplicate 3 layers in a 24B LLM, logical deduction .22→.76. No training
#70That weird part is kind of what I was expecting. This goes to the thing that I posted on the thread a couple of days ago. https://news.ycombinator.com/item?id=47327132 What you need is a mechanism to pick the right looping pattern, Then it really does seem to be Mixture of experts on a different level. Break the model into input path, thinking, output path. and make the thinking phase a single looping layer of many e…
If you're adding a model to do the "routing" you're basically putting learned backward connections and you end up with a RNN