license: apache-2.0
QuaLA-MiniLM: a Quantized Length Adaptive MiniLM
The article discusses the challenge of making transformer-based models efficient enough for practical use, given their size and computational requirements. The authors propose a new approach called QuaLA-MiniLM, which combines knowledge distillation, the length-adaptive transformer (LAT) technique, and low-bit quantization. This approach trains a single model that can adapt to any inference scenario with a given computational budget, achieving a superior accuracy-efficiency trade-off on the SQuAD1.1 dataset. The authors compare this approach to other efficient methods and find that it achieves up to an x8.8 speedup with less than 1% accuracy loss. The authors also provide their code publicly on GitHub. The article also discusses other related work in the field, including dynamic transformers and other knowledge distillation approaches.