Just How Resilient Are Large Language Models?

(rdrocket.com)

14 points | by decodebytes 3 days ago ago

3 comments

  • rglover an hour ago

    Interesting read. Was surprised to learn how much damage can be done to a model's parameters without making any discernible difference in its quality of output.

    • cma 8 minutes ago

      I didn't see any mention of dropout in the article, during training parameters or whole layers are removed in different places which helps force it into a distributed representation.

  • dataking 3 hours ago