points by orsorna 4 days ago | 0 comments
Why would you want to change weights directly versus running through a new training cycle? For example, I have collected a bunch of data I would like to train weights that I use local inference for. I figured a LoRa would be the way to go, perhaps be more cost effective and generalized too.
[–] dghlsakjg 4 days ago
[–] latentsea 4 days ago
Because text-to-weights is a learnable function. Everything else seems to be. So, why not? Why train weights if you could just prompt for them. If we managed to train image edit models, then why can't we train model-edit models?
[–] mycall 4 days ago
The deeper the layers you try to edit, the more compressed it gets, and the harder it is edit.
[–] latentsea 4 days ago
I remember when the original text-to-video dropped (awful as it was) and I thought "no fucking way". Same with seeing the first world models "no fucking way!". It'll come. I sometimes just sit and think "what if we had 100x more compute than we do now?" or "what if training got 10x faster" etc. So many impossible things seem pretty possible.
[–] MisterMunchkin 4 days ago
If you could figure out exactly what certain weights do it would be way quicker to directly edit them, whereas training is non-deterministic and takes ages.
[–] orsorna 4 days ago
And the modifications of those weights could be tracked in source control and overlayed on top of the base model? I see, there is a lot of potential in that.
[–] parineum 4 days ago
Something someone else brought up in one of the previous threads was to identify the refusal routes and remove them.
[–] smrtinsert 4 days ago
Speed, instant finetunes? Highly optimized iteration cycles? The applications are the same for any reason why you might want local llms. This is crazy exciting.
[–] elbear 4 days ago
Because training is more expensive I guess
[–] numpad0 4 days ago
It would take a lot less FLOPS presumably
I think your use case of incorporating novel data probably calls for training, but I'm sure there are use cases where you can tweak the weights to get what you want (say I wanted to tweak the model to be less sycophantic, or found a way to shrink it by removing weights associated with a language that I don't ever use)