AI Dynamics

Global AI News Aggregator

Expert Size and Number Match DeepSeek V3 Specifications

Probably also should have added that
– the expert size (2048) and number (256) is now exactly the same as in DeepSeek V3 / V3.2.

→ View original post on X — @rasbt,

Commentaires

Leave a Reply

Your email address will not be published. Required fields are marked *