yarn scale to 122,880 context length

#41

by nbroad - opened 1 day ago

←

nbroad

1 day ago

Please don't merge or close this. I'm just going to use this pr revision to run the model at 122k sequence length

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