"The paper introduces a technique called LoReFT (Low-rank Linear Subspace ReFT). Similar to LoRA (Low Rank Adaptation), it uses low-rank approximations to intervene on hidden representations. It shows that linear subspaces contain rich semantics that can be manipulated to steer model behaviors."
efficient method for fine-tuning LLM using LoRA and QLoRA, making it possible to train them even on consumer hardware
