We introduce Aligner, a novel Parameter-Efficient Fine-Tuning (PEFT) method for aligning multi-billion-parameter-sized Large Language Models (LLMs). Aligner employs a unique design that constructs a globally shared set of tunable tokens that modify the attention of every layer. Remarkably with this method, even when using one token accounting for a mere 5,000 parameters, Aligner can still perform comparably well to state-of-the-art LLM adaptation methods like LoRA that require millions of parameters. This capacity is substantiated in both instruction following and value alignment tasks. Besides the multiple order-of-magnitude improvement in parameter efficiency, the insight Aligner provides into the internal mechanisms of LLMs is also valuable. The architectural features and efficacy of our method, in addition to our experiments demonstrate that an LLM separates its internal handling of "form" and "knowledge" in a somewhat orthogonal manner. This finding promises to motivate new research into LLM mechanism understanding and value alignment.

SnapChat will soon be adding a feature that basically allows you deepfake yourself into a video or GIF for fun. The feature was first spotted by Snapchat users in France who received a test version of the tool over the weekend. The latest addition to the app is called Cameo, Snapchat confirmed to TechCrunch on Sunday. "Cameos aren't ready to take the stage yet, but stay tuned for their global debut soon!" the social networking app told TechCrunch. Based on screen captures posted by people on Twitter, Cameo uses your selfie to plaster your face on a digitized body.