Dud

Running model in Int8 on a single GPU (24GB)

8

Hi all, This isn't my work, but the initial promise of this model for many people was that it could potentially be run on consumer hardware. https://github.com/tloen/llama-int8.git I found this...

Hey all, I've been struggling the past day trying either add the embedding layer as a fully trained layer or use it with LoRA. For context, I'm trying this with...