System Requirements

#38
by Robo0890 - opened

I’m hoping to fine tune this model on custom data for an upcoming project. I have an RTX-3060 and 16GB of RAM, should I be able to use this model for training or should I go with the 560m parameter version?

In my experience, fine-tuning this model need 32GB GPU RAM minimum. I fine-tuned this model on Google Colab Pro+. This task expense a lot of money.

Yeah, I’ll just stick with the little one

I recommend using the bloom 560m. It works fine as the same 1b1 one but need less GPU RAM.

Sign up or log in to comment