Re:Show HN: I Created ErisForge, a Python Library for Ablite...
by nico on Monday January 27, 2025 @01:39PM
(#42844200)
> > Do these techniques train models while performing the modifications?
> Depend on what you mean by training, they change the weights.
What I wonder: is there a separate model, not the LLM, that gets trained only on how to modify LLMs?
I imagine a model that could learn something like: “if I remove this whole network here, then the LLM runs 50% faster, but drops 30% in accuracy for certain topics”, or “if I add these connections, the LLM will now be able to solve more complex mathematical problems”
So a model that is not an LLM, but is trained on how to modify them for certain goals
> Depend on what you mean by training, they change the weights.
What I wonder: is there a separate model, not the LLM, that gets trained only on how to modify LLMs?
I imagine a model that could learn something like: “if I remove this whole network here, then the LLM runs 50% faster, but drops 30% in accuracy for certain topics”, or “if I add these connections, the LLM will now be able to solve more complex mathematical problems”
So a model that is not an LLM, but is trained on how to modify them for certain goals
Is that how this tool works?