This is great stuff and necessary.

by 1TBGPU4EVR - opened Apr 23

Apr 23

We need lighter models that can perform faster and function as modular parts in real-time workflows. I can't wait to try this with Flash Attention.

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