SoftLMs: Efficient Adaptive Low-Rank Approximation of Language Models using Soft-Thresholding Mechanism
This addresses the problem of deploying language models on resource-constrained devices, though it is incremental as it builds on existing compression techniques.
The paper tackles the computational and memory overheads of large language models by proposing a compression method using soft thresholding to dynamically determine layer ranks, achieving a speed-up of 1.33X to 1.72X and a 50% reduction in parameters.
Extensive efforts have been made to boost the performance in the domain of language models by introducing various attention-based transformers. However, the inclusion of linear layers with large dimensions contributes to significant computational and memory overheads. The escalating computational demands of these models necessitate the development of various compression techniques to ensure their deployment on devices, particularly in resource-constrained environments. In this paper, we propose a novel compression methodology that dynamically determines the rank of each layer using a soft thresholding mechanism, which clips the singular values with a small magnitude in a differentiable form. This approach automates the decision-making process to identify the optimal degree of compression for each layer. We have successfully applied the proposed technique to attention-based architectures, including BERT for discriminative tasks and GPT2 and TinyLlama for generative tasks. Additionally, we have validated our method on Mamba, a recently proposed state-space model. Our experiments demonstrate that the proposed technique achieves a speed-up of 1.33X to 1.72X in the encoder/ decoder with a 50% reduction in total parameters.