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)
LLaMA-Adapter v2 Adds Trainable RMSNorm and Bias Parameters
By
–
By
–
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)