Hacker News Reader

I think it's more likely to be the old base model checkpoint further trained on additional data.

Is that technically not a new pretrained model?

(Also not sure how that would work, but maybe I’ve missed a paper or two!)

I'd say for it to be called a new pretrained model, it'd need to be trained from scratch (like llama 1, 2, 3).

But it's just semantics.