AI Dynamics

Global AI News Aggregator

LLaMA-Adapter v2 Adds Trainable RMSNorm and Bias Parameters

Good question. Yes, because LLaMA-Adapter v2 is basically LLaMA-Adapter but it also has trainable RMSNorm parameters and trainable bias units (in FC layers)

→ View original post on X — @rasbt,

Commentaires

Leave a Reply

Your email address will not be published.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