[pu_pe]

I'm curious about it too. I think there are two bottlenecks, one is that training a relatively large LLM can be resource-intensive (so people go for RAGs and other shortcuts), and making it finetuned to your use cases might make it dumber overall.

[koakuma-chan]

> making it finetuned to your use cases might make it dumber overall.

LoRa doesn't overwrite weights.

[pu_pe]

Do you need to overwrite weights to produce the effect I mentioned above?

[koakuma-chan]

Good point