Right now, it looks like model makers can only train a single model to one inference level, and the other models and inferences are just “filler.”


But they want to play precise “knife work” like Jensen Huang, and the result is that they only have one dessert—no high-performance beast, no low-end options—only high-inference “idiot” models and low-inference “idiot” models.
View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Repost
  • Share
Comment
Add a comment
Add a comment
No comments
  • Pinned