Google released T5X checkpoints for MADLAD-400 a couple of months ago, but nobody could figure out how to run them. Turns out the vocabulary was wrong, but they uploaded the correct one last week.

I’ve converted the models to the safetensors format, and I created this space if you want to try the smaller model.

I also published quantized GGUF weights you can use with candle. It decodes at ~15tokens/s on a M2 Mac.

It seems that NLLB is the most popular machine translation model right now, but the license only allows non commercial usage. MADLAD-400 is CC BY 4.0.

  • Presence_Flat@alien.top
    cake
    B
    link
    fedilink
    English
    arrow-up
    1
    ·
    1 year ago

    this is nice, I’m doing some translation work with some sophisticated Arabic words (Arabic sometimes ranked as the most complicated language, we called the ones that master it scientists lol).
    how can I run this on my mac in layman terms.

    • jbochi@alien.topOPB
      link
      fedilink
      English
      arrow-up
      1
      ·
      1 year ago

      One approach is to install rust, candle, and then run one of the cargo commands from here.

      You can also try oobabooga, which has a one click installer, and should support this model, but I haven’t tested it.