Chansung Park

also, notice that I make updates very frequently, so please `git pull` whenever you try

I would not recommend to use Colab since the connection is not stable. This error is due to the unstable connection that will eventually be terminated shortly (I don't know...

yeah since t5-vicuna is the smallest model which don't take too much time to load up

T5-Vicuna is 3B model, hence :)

for some models which uses bfloat16 data type, it can't be loaded up on mac.

Good one 👍 I just wanted to make sure everything works Ok and under control.

which orcamini did you choose? 7B or 13B?

Not yet. I have not looked into gptq yet, so currently dont know how to add it

Yeah but I usually run it in float16 mode which is faster 2023년 4월 3일 (월) 오후 8:46, Originalimoc ***@***.***>님이 작성: > 30B albeit 4bit using less than 20G VRAM...

This would be very helpful for many people! And sure! Please make a PR :)