NVIDIA basically compressed 30 years of its corporate memory into 13B parameters. Our greatest creations add up to 24B tokens, including chip designs, internal codebases, and engineering logs like bug reports. Let that sink in. The model "ChipNeMo" is deployed internally, like a… https://t.co/ivR61wJeKs https://t.co/maK7Kcc5nj
— Jim Fan (@DrJimFan) Nov 15, 2023
from Twitter https://twitter.com/DrJimFan
November 15, 2023 at 04:51PM
via IFTTT
No comments:
Post a Comment