Add us as a preferred source on Google

    Newsletter

    Subscribe to our newsletter

    Tufa Labs’ tufazip has compressed 1GB of information from Wikipedia into just 105MB of space, losslessly, without using any hand-built models, according to a research post. The method uses a 163-million-parameter Transformer model as a predictor instead, and similar compression or decompression would take two Nvidia B200 GPUs about a week to manage. It’s the smallest result on the Large Text Compression Benchmark from any entry that uses a neural network as its only predictor.

    Tufa Labs chart comparing compressed size against transferred model size for enwik9, with Cycle2 at 105.39 MB total, under the 105.98 MB online baseline, and L6 at 110.12 MB.

    (Image credit: Tufa Labs)

    Latest Videos FromTom’s Hardware

    Share.

    Comments are closed.