transformers

Running

Fixed typo in MQA explanation

by foldl - opened 8 days ago

←

foldl

nanochat students org 8 days ago

•

Maybe you've meant GQA instead of MQA, but number of key/value heads will be still off.

nanochat students org 5 days ago

Thanks @foldl !

burtenshaw changed pull request status to merged 5 days ago

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