RoPE scaling guidance

by RonanMcGovern - opened Sep 7, 2023

Sep 7, 2023

Congrats on the model.

Is there guidance for using RoPE scaling beyond 16k?

How is performance at 32k or more? Thanks

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