AI Dynamics

Global AI News Aggregator

Weights compatibility and numerical stability in LoRA fine-tuning

Yes, I think that's either maybe so that (1) people with older cards can use these weights as well and (2) we maybe have more stability when finetuning with LoRA etc (in case numbers become large)
It's interesting for sure

→ View original post on X — @rasbt,

Commentaires

Leave a Reply

Your email address will not be published. Required fields are marked *