Hacker News new | ask | show | jobs
by Havoc 1021 days ago
What does “pretrain” mean in this context? It sounds like normal training
2 comments

GPT stands for Generative Pre-trained Transformer.

The "main" training step using huge amounts of inputs is called pre-training. The idea is that after that pre-training, you might fine tune the model for your specific use case.

I see...that makes sense. Thanks for explaining
As opposed to fine-tuning or in-context learning. It really is normal training.