Ask HN: Is anyone doing anything cool with tiny language models?

Re:Ask HN: Is anyone doing anything cool with tiny language ... by WithinReason on Tuesday January 21, 2025 @03:46PM (#42785009)

That size is on the edge of something you can train at home

[ Parent | on HN ]

Re:Ask HN: Is anyone doing anything cool with tiny language ... by vineyardmike on Tuesday January 21, 2025 @04:31PM (#42785431)

If you have modern hardware, you can absolutely train that at home. Or very affordable on a cloud service.

I’ve seen a number of “DIY GPT-2” tutorials that target this sweet spot. You won’t get amazing results unless you want to leave a personal computer running for a number of hours/days and you have solid data to train on locally, but fine-tuning should be in the realm of normal hobbyists patience.

[ Parent | on HN ]

Re:Ask HN: Is anyone doing anything cool with tiny language ... by nottorp on Tuesday January 21, 2025 @04:59PM (#42785617)

Hmm is there anything reasonably ready made* for this spot? Training and querying a llm locally on an existing codebase?

* I don't mind compiling it myself but i'd rather not write it.

[ Parent | on HN ]

Re:Ask HN: Is anyone doing anything cool with tiny language ... by Sohcahtoa82 on Tuesday January 21, 2025 @06:50PM (#42786773)

Not even on the edge. That's something you could train on a 2 GB GPU.

The general guidance I've used is that to train a model, you need an amount of RAM (or VRAM) equal to 8x the number of parameters, so a 0.125B model would need 1 GB of RAM to train.

[ Parent | on HN ]