Chase Kolozsy

I have had a chance to use Bunny through llama.cpp and it is awesome. It isn't preachy, enumerates its answers when appropriate. Seems to pick out more of the objects...

The following was performed on an M3 max 128gb macbook pro with pytorch 2.3 and torchvision 0.18. I set device to 'mps'. I used the vit_h checkpoint. The following preview...

> Hi Alethx, thanks for the question. We currently focus on lightweight MLLMs and don't plan to train with Llama3-70B. I was thinking about merging your bunny-llama3-8b-V model with llama3-70b,...

@AlexCheema Is it possible to have the active parameters favor an Nvidia Cuda GPU and let the other nodes store the inactive parameters?

I'm getting the same issue. I too am using an Ubuntu WSL on windows. Ubuntu 20.04. """ (base) chase@DESKTOP-6HJUF69:~$ plandex sign-in Use Plandex Cloud or another host? > Plandex Cloud...

> @ChaseKolozsy What do you get for `echo $TERM`? ``` (base) chase@DESKTOP-6HJUF69:~$ plandex sign-in ? Use Plandex Cloud or another host? > Plandex Cloud Another host 🚨 Error signing in...

Imagine, trying to work with Deepseek v3 and you have to download the model 9 times. Comcast only gives you 1200gb of data a month so you could only get...

> Might be a dumb idea and i have not had a chance to look into it, but perhaps mount shared storage between all the nodes so it looks at...