machine learning offline cache
Hi, I'm trying to run the machine learning container offline. There are errors related to files not being found. I'm assuming they would end up in the model_cache folder. I'e attempted to clone the models from huggingface so they are loaded from disk. It doesn't seem to work though.
Here is my mode_cache folder (note that I moved the models into the models--.. folders as they were created on startup).
6 Replies
Not all models are being cached to the correct folder yet, that's a bug we still need to fix 😅
It doesn't seem like any of them get loaded from cache, but it could just be erroring on the first one. Hmm would it then be in whatever cache huggingface makes by default?
Probably yeah
OK cool, I'll give it a try. Worst comes to worst it seems like huggingface might fall back to looking for pwd/org/modelname? Definitely interesting way to make downloads easy lol
Thanks
Cool, cwd worked!
Is there a relevant issue on GitHub?
I believe we fixed this issue in the Facial Recognition PR
it will me merged into main at some point before the next release