top | item 46118033

(no title)

scottyeager | 2 months ago

You can read that 3.2 is live on web and app here: https://api-docs.deepseek.com/news/news251201

The pdf describes how they did "continued pre-training" and then post training to make 3.2. I guess what's missing is the full pre-training that absorbs most date sensitive knowledge. That's probably also the reason that the versions are 3.x still.

discuss

order

No comments yet.