Will you please clarify flash-attention 2 usage in this model

by leocnj - opened Sep 20, 2023

leocnj

Sep 20, 2023

Thanks for posting this cool model !

Regarding using "flash-attention 2", do you mind elaborating more? Do you mean you are using FA-2 in your PEFT tuning?

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment