Lossless and Near-Lossless Compression for Foundation Models

arXiv:2404.15198v1 Announce Type: new
Abstract: With the growth of model sizes and scale of their deployment, their sheer size burdens the infrastructure requiring more network and more storage to accommodate these. While there is a vast literature about reducing model sizes, we investigate a more traditional type of compression -- one that compresses the model to a smaller form and is coupled with a decompression algorithm that returns it to its original size -- namely lossless compression. Somewhat surprisingly, we …

abstract arxiv compression cs.it cs.lg deployment foundation growth infrastructure literature math.it near network scale storage type vast