Randomly the machine get stuck on loading model

[Sapessii]

Hi,

as the title suggests completely random, the machine gets stuck on

Using model weights format ['*.safetensors']

and I have to manually terminate the worker and restart it.

Do you have any suggestions?

[avacaondata]

I have also experienced this a couple of times, and haven't found a way to prevent it, I'm so sorry for not being able to help you here :( @Sapessii Maybe you should ping one of the maintainers for some advice, so they can instruct you on best practices to avoid this. Good luck :)

[nielsrolf]

Bumping this because I'm also experiencing it a lot, lately pretty much 100% of the time when trying to deploy 70b models