My bet is on 10-15b param (maybe even smaller) LLM models outperforming all state of the art soon. Everyone will be able to run them locally for free. WDYT?
Small LLMs Poised to Outperform State-of-the-Art Models Soon
By
–
By
–
My bet is on 10-15b param (maybe even smaller) LLM models outperforming all state of the art soon. Everyone will be able to run them locally for free. WDYT?