Hacker News Reader

HNHacker News

Top New Best Ask Show Jobs

Comment by tsunamifury | Hacker News Reader

Full thread

tsunamifury·

Isn’t this basically what multimodal LLM does as well… it can do anything on the fly it can understand.

What’s different here?

View on HN

These are smaller scale model that you can export and run anywhere.

Even the smallest multimodal LLM would be wayyyyyyy bigger than an exported model from this

How small are these models? can I export a model here and embed it in an Android/ios app?

The website says they can be embedded in a web app, and export to a format called TensorFlow Lite. I am sure you could embed it.

https://www.tensorflow.org/lite

https://www.tensorflow.org/lite/android

TF Lite has first-class Android support with hardware acceleration if I'm not mistaken.

You can supposedly embed them for Arduinos, so an app should be no problem.

The teaching part is what matters, it’s training (tuning in this case) a model, not just using a model already trained for inference (which is what I assume you mean). You’re providing new data that is used to update the model. Inference across an existing multimodal model doesn’t change how it classifies in any way.

I think this is more like fine tuning an existing model to recognize features you specifically intend it to, and be light enough to run locally in a browser.

Thanks!

It's not even fine tuning, it's creating a model from scratch. This isn't like our modern huge models either, these tiny single-purpose models have been around for ages and are quite versatile. They're so small you can't just easily run them in the browser, but train them effectively, which is what this project lets you play around with! Super cool stuff.

Reply on news.ycombinator.com