emikulic·3 年前·議論Try https://huggingface.co/ehartford/WizardLM-7B-Uncensored and related models. They're not even trained on smut, just the neutered responses were removed before the RLHF stage (IIUC)
emikulic·3 年前·議論Emad said SD cost $600,000 to train. I wonder if Midjourney also had to pay that to train from scratch.
emikulic·3 年前·議論Last time I looked into this, the answer was "because huggingface transformers and torch.load are written to do it this way"You could absolutely do something streaming, or mmap the weights instead of loading them into system RAM. Just the default interfaces don't.
emikulic·3 年前·議論This used to be the case but nowadays you can just pip install e.g. https://libraries.io/pypi/nvidia-cuda-runtime-cu11
emikulic·4 年前·議論I hope you will run your own locally instead of letting Midjourney block and/or mess with your prompts.
emikulic·4 年前·議論If edge devices includes my gamer PC then yes. For apps I'd recommend https://github.com/AUTOMATIC1111/stable-diffusion-webui
emikulic·4 年前·議論You have to create an account and agree to some stuff and be logged in but you're correct that you don't have to pay.
emikulic·4 年前·議論Same. I've found the biggest problem was SNAT rewriting the (source) port number. netfilter, by default, doesn't do this. pf does but you can configure it not to.