Is it possible to finetune an LLM on the factual content without altering its linguistic characteristics?
With Stable Diffusion, you're able to use LoRAs to introduce specific characters, objects, concepts, etc. while maintaining the same visual qualities of the base model.
With Stable Diffusion, you're able to use LoRAs to introduce specific characters, objects, concepts, etc. while maintaining the same visual qualities of the base model.
Why can't something similar be done with an LLM?