DLO: Dynamic Layer Operation for Efficient Vertical Scaling of LLMs
This addresses the challenge of building efficient yet powerful LLMs for AI applications, though it is incremental as it builds on existing scaling methods.
The paper tackles the problem of efficiently scaling transformer-based Large Language Models (LLMs) in depth by introducing Dynamic Layer Operations (DLO), which dynamically manages layers based on feature similarity, eliminating the need for Continual Pre-Training and achieving comparable results to densely expanded models with improved efficiency.
In this paper, we introduce Dynamic Layer Operations (DLO), a novel approach for vertically scaling transformer-based Large Language Models (LLMs) by dynamically expanding, activating, or skipping layers using a sophisticated routing policy based on layerwise feature similarity. Unlike traditional Mixture-of-Experts (MoE) methods that focus on extending the model width, our approach targets model depth, addressing the redundancy observed across layer representations for various input samples. Our framework is integrated with the Supervised Fine-Tuning (SFT) stage, eliminating the need for resource-intensive Continual Pre-Training (CPT). Experimental results demonstrate that DLO not only outperforms the original unscaled models but also achieves comparable results to densely expanded models with significantly improved efficiency. Our work offers a promising direction for building efficient yet powerful LLMs. We will release our implementation and model weights upon acceptance.