support use_flash_attn in from_pretrained

by michael-guenther - opened May 30

←

Jina AI org May 30

•

This adds a shortcut to enable flash attention and xformer attention.

michael-guenther changed pull request status to open Jun 3

gmastrapas changed pull request status to merged Jun 3

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