Replying to Avatar fiatjaf

So, these language models, when they are being trained, do they need someone telling them what they got wrong and what they got right? How do they know?
Avatar
paulo 2y ago

They have a reinforcement learning phase after they’ve been pretrained

For pretraining they just learn patterns from all the data they are seeing

Reply to this note

Please Login to reply.

Discussion

No replies yet.