Solves the TypeError issue in GPTNeoXLayer init, which also takes the layer id

by efederici - opened Sep 26

←

Sep 26

Due to recent changes to support k/v caching, we need to initialize the attention class with a layer index

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

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment