Sometimes models have like 15 separate downloads how do I know which one to use? Do I download all of them and put them in my oobabooga model folder and then load the first one?
How do I run a 70B llm on my 4090? Most of the 70B say they require like 40gb of Vram.
Sometimes models have like 15 separate downloads how do I know which one to use? Do I download all of them and put them in my oobabooga model folder and then load the first one?