-1

I can't find enough information on how to fine tune model microsoft/GODEL-v1_1-base-seq2seq on certain dialogs. Maybe someone can tell me more? What should the training data look like? How do the instruction, knowledge, dialog fields work? How to teach a model to communicate in a certain way?

Code in Python, please!

Thanks for your help!

I understood how to generate responses from the model, but from the Microsoft repository I didn't quite understand how to properly fine tune the model.

GODEL Repo

Artem M
  • 1
  • Please edit the question to limit it to a specific problem with enough detail to identify an adequate answer. – Community Aug 05 '23 at 09:34

0 Answers0