Skip to content

Conversation

@cdalinghaus
Copy link
Contributor

At least einops was required (and not installed per default in a new virtualenv) in my case.

As for accelerate:

For stability purposes, it is recommended to have accelerate installed when using this model in torch.float16, please install it with pip install accelerate

@ExponentialML ExponentialML merged commit dcf7ffd into ExponentialML:main Sep 14, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants