Probably the biggest highlight of this week is LLaMA 2 from Meta AI. LLaMA 2 is improved version of LLaMA 1. It was trained on more data(40% more than LLaMa 1) and it has 4K context length(double the previous context). LLaMA 2 release package contains 3 model sizes(7B, 13B,

→ View original post on X — @jeande_d,