Tom Lieberum

fold in scaling by sqrt(d_model) into params

9ff4e7b about 1 year ago

75.5 MB

This file is stored with Xet . It is too big to display, but you can still download it.

SHA256:: dd54f7bb23d4c9b05eaea3cfb44eba76f1a009d9a3ab5d1e1f9d3b7ef1b64e79
Pointer size:: 133 Bytes
Size of remote file:: 75.5 MB
Xet backed hash:: af6ceda87e3e561883df5236f5a97ee97328f47f369998919d038b2d6493f8a5

Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.

google
/

gemma-scope-2b-pt-res