• Tibert@compuverse.uk
    link
    fedilink
    English
    arrow-up
    12
    ·
    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

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

      I imagine that the compression is linked to the dataset, so if you update or retrain then you maybe lose access to the compressed data.