Understanding Ghost Attention in LLaMa 2
This blog post explains the Ghost Attention method of fine-tuning introduced in the LLaMa 2 paper.DALL-E generated image of a ghost llamaThe ProblemOften times, we want the LLM to be given an instruction once and then follow it until told otherwise. Nevertheless, as the below example shows LLMs can quickly forget instructions after a few turns of dialogue.Figure 9 from the LLaMa 2 paper illustrating how instructions can be ignored after a few turns of dialogueOne way to get the model to pay attention consistently is…