8 accepted papers
Despite the superior performance, Large Language Models (LLMs) require significant computational resources for deployment and use. To overcome this issue, quantization methods have been widely applied to reduce the memory footprint of LLMs as well as increase the inference rate. However, a major cha…
Lightweight fine-tuning is widely used as an important technique for efficiently adapting pre-trained language models (PLM) to downstream tasks. Despite the reduction in trainable parameters, existing lightweight fine-tuning methods are found to be effective in low-resource settings but often fail i…
Increased training parameters have enabled large pre-trained models to excel in various downstream tasks. Nevertheless, the extensive computational requirements associated with these models hinder their widespread adoption within the community. We focus on Knowledge Distillation (KD), where a compac…
Key-value (KV) caching is an important technique to accelerate the inference of large language models (LLMs), but incurs significant memory overhead. To compress the size of KV cache, existing methods often compromise precision or require extra data for calibration, limiting their practicality in LL…
In this paper, we propose a highly parameter-efficient approach to scaling pre-trained language models (PLMs) to a deeper model depth. Unlike prior work that shares all parameters or uses extra blocks, we design a more capable parameter-sharing architecture based on matrix product operator (MPO), a…
By scaling the model size, large pre-trained language models (PLMs) have shown remarkable performance in various natural language processing tasks, mostly outperforming small PLMs by a large margin. However, due to the high computational cost, the huge number of parameters also restricts the applica…
Recently, Mixture-of-Experts (short as MoE) architecture has achieved remarkable success in increasing the model capacity of large-scale language models. However, MoE requires incorporating significantly more parameters than the base model being extended. In this paper, we propose building a paramet…
This paper presents a novel pre-trained language models (PLM) compression approach based on the matrix product operator (short as MPO) from quantum many-body physics. It can decompose an original matrix into central tensors (containing the core information) and auxiliary tensors (with only a small p…