details on how to distill from 12B model to 8B

#9
by ryan6027 - opened

Hi @ostris , congrats on releasing an amazing work! Some question:

  1. Can you give more details on how to distill from 12B model to 8B?
  2. Fine-tune which parameters and what losses are used.
  3. Are there any plans to open source distillation code?

thanks~

Your need to confirm your account before you can post a new comment.

Sign up or log in to comment