• rubikcuber@programming.dev
    link
    fedilink
    English
    arrow-up
    30
    ·
    1 year ago

    The research specifically looked at lossless algorithms, so gzip

    “For example, the 70-billion parameter Chinchilla model impressively compressed data to 8.3% of its original size, significantly outperforming gzip and LZMA2, which managed 32.3% and 23% respectively.”

    However they do say that it’s not especially practical at the moment, given that gzip is a tiny executable compared to the many gigabytes of the LLM’s dataset.

      • Tibert@compuverse.uk
        link
        fedilink
        English
        arrow-up
        13
        ·
        1 year ago

        Well from the article a dataset is required, but not always the heavier one.

        Tho it doesn’t solve the speed issue, where the llm will take a lot more time to do the compression.

        gzip can compress 1GB of text in less than a minute on a CPU, an LLM with 3.2 million parameters requires an hour to compress