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?

Why would you do a whole new expensive, time-consuming training run if you can just tweak some numbers to get the result you want?

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)

In my latest experiments with editing the weights directly, it has edited the weights of my decision head and LoRa checkpoint.

Essentially, my training introduced knowledge and structure which wasn't translating into results. I tried training in a few different ways, different ranks, different things, and I wasn't making any progress.

With weight editing, a larger model was able to eliminate some undesirable pathways which the model was often using. Without going into the nitty-gritty, it basically took my best LoRa checkpoint and gave it the skills that I was unable to get with further training.

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.

Because training is more expensive I guess

It would take a lot less FLOPS presumably

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.

Something someone else brought up in one of the previous threads was to identify the refusal routes and remove them.