New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

DocOwl2 using flash attention mandatorily #129

Open

nico-zck opened this issue Dec 10, 2024 · 0 comments

nico-zck commented Dec 10, 2024

DocOwl2 cannot be loaded without flash_attn because the implementation of the compressor mandatorily uses flash attention.

This issue causes DocOwl2 to not run on many non-NVIDIA devices. Please consider adding an option to disable or enable flash attention.

https://huggingface.co/mPLUG/DocOwl2/blob/205b9e18b0cb503c9ef0dde1e7b120e6925778d9/visual_compressor.py#L106

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment