Chris ๐จ๐ฆ
@llm_wizard
Open Source Model Lover @ NVIDIA AI
Views my own.
๊ฐ์
June 2021
798 ํ๋ก์ ์ค 5.2K ํฌ
THAT'S MY GOAT!!!!!
Glean post-trained NVIDIA Nemotron 3 Nano for enterprise search and got 50% lower latency and 25% fewer tokens, "without any sort of loss in accuracy."
That's the example @NVIDIA's @Shashank__Verma gave on the Serve track at Open Intelligence Summit, behind a bigger point: "a model can be open source and frontier at the same time."
Serve track, Open Intelligence Summit.
๋ ๋ณด๊ธฐ
