Porting v2 models to flash attention

#15

by Markus28 - opened Mar 22, 2024

←

Mar 22, 2024

•

The outputs of the converted model look very close to those of the original model, so it looks like everything is working.

Markus28 changed pull request status to open Mar 22, 2024

bwang0911 changed pull request status to merged Mar 23, 2024

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