Bigcow11
Bigcow11
> It will really just take a lot of money. We can finetune on the same datasets the others have been finetuned on in order to get a 65B model,...
> Am I the only one who is experiencing this or what? The 13B model is toxic! 😄 > > ### Example 1 >  > > ### Example 2...
> Also have this issue, but IDK this is normal or not. I don't believe its normal, on the readme page he includes the .gif of the speed which matches...
> What hardware? Likely the only issue I can think of. I'm running 7B, 13B, and 30B on 32GB RAM and a beefy cpu. 7B is snappy, 13B is still...
Have we found any solutions or successful work arounds?
Ditto, doesn't support it, just tried today