lopho
lopho
No problem, I have excluded them for now, will keep an eye on this and reenable them once they're in.
I'll update the README. Testing still works the same locally.
I also need to make a few changes to make reg tests easier locally, right now it's a bit complicated messing with git, copying & restoring test data etc. Should...
Got some weird behaviour from git on the runner, still investigating sorry for the close/open, buttons are too close together :cry:
@rom1504 cleaned it up, workflow is less convoluted now. README is updated with instruction for regression test, util_test.py can now generate test data from arbitrary commits post v2.7.0). Would be...
I did not consider the minor python version changing in the GH runner, which invalidated the environment. I've changed the caching to cache for the specific version (e.g. 3.8.15 instead...
I think it's fine now.
This is an optional dependency and is only required to use models from huggingface.
~40gb vram to load ~45gb to infer full 2048 token length. About the twice the amount in cpu RAM (~81gb) as it currently is intantiated on the cpu and then...
You can skip betas, it's not a layer of the actual architecture but a stored parameter used for sampling and generating timestep embeddings. Same goes for alphas_cumprod, sqrt_alphas, and a...