Comment Comment by napsternxg We also did something similar in our NTULM paper at Twitter https://youtu.be/BjAmQjs0sZk?si=PBQyEGBx1MSkeUpXUsed in non generative language models like BERT but should help with generative models as well. parent napsternxg 2 years ago
Used in non generative language models like BERT but should help with generative models as well.