Hacker News Reader

Interesting, seems like control vectors could reduce the need to fine-tune a model.

Not only that, you can change the behavior of the model as needed. With 5 finetunes you need to host 5 copies or load and unload them.

With control vectors you can modify the model as needed

I think you could layer them too

> With 5 finetunes you need to host 5 copies or load and unload them.

If you use LoRA, which many do when fine-tuning nowadays, you don't need five full copies. You only need to store adapters, which can be in the tens of MBs range for a given finetune.

You can also batch requests using different LoRAs. See "S-LoRA: Serving Thousands of Concurrent LoRA Adapters". https://arxiv.org/abs/2311.03285

Reply on news.ycombinator.com