Update README.md

4 years ago · 8af6289d0c
parent fd098b1d2e
commit 8af6289d0c
1 changed files with 4 additions and 0 deletions
--- a/README.md
+++ b/README.md
@ -34,6 +34,10 @@ Moreover we multiply the final output of Time-mix layer by γ(t). The reason for
 ***
 p.s. There is a MHA_pro model in this repo with strong performance. Give it a try :)
 ***
 We also propose a new sampling method (as in src/utils.py):
 (1) Find the max probability p_max after softmax.