Jeremie Kalfon 👨💻🧬🤖🚀 @jkobject.com · Jun 20 By using common fine-tuning mechanism we show how one can train from one scale to the next by back-propagating signal to the compressed tokens and lower scale model.
0 likes 1 replies
?
Replies
We show that this helps the models learn faster, achieve better results on many test metrics and create better representations. This is an early proof of concept toward this grand goal of modeling life across scales.