ποΈβπ¨οΈ LLMs Opening Their Inner Eyes
And drastic cost reductions for pre-training LLaMA-2 level models
In this issue:
LLaMA-2 performance at 0.001x the price
Trying to unify LLM evaluation
How the βMindβs Eyeβ might help LLMs to βthinkβ better
Keep reading with a 7-day free trial
Subscribe to LLM Watch to keep reading this post and get 7 days of free access to the full post archives.