NeuroDonu
NeuroDonu
Would quantizing to .gguf and using a terabyte of RAM help? 🙃
if TheBloke is still doing model quantization, then you can ask him. I'll eventually try to do this, but I'm not sure it will work out well.
There is only one minus, the libraries are a little outdated, but I think a little old pytorch and cuda will not play a big role.
Wow! Damn, I didn't know. I put together the configuration for a couple of hours at random and still got an unusable model. Well then, I’ll compose it again tomorrow,...
Yes, yes, this was the problem with recording layers, as a result of which I ruined the model.
That's weird! I asked my friend to test it too and he said and showed me that the faces are heavily distorted. I don't know what to do about it
https://derkarta.com/index.php/s/k3ckfy95PW2jmcd I update it: remove old models, add models by FaceFusion. Idk, fix error, or no...
Oh, damn! I must have downloaded the .onnx version by mistake, not the .pth.
https://t.me/neuralchatik/1397/10730 i wish its a final fix
I'm glad it's working as it should, since I can't even test to see if it works.