Commit History

fixed GLU implementation, added conversion of layer norms
9587227

Markus28 commited on

Added GLUMLP, changed config accordingly, added code to convert state_dict
0211324

Markus28 commited on

reference the flash attention GitHub
eec6c0e

Markus28 commited on

fix: move flash components into top-level
5944ec8

Markus28 commited on