novarobot
/
RWKV-LM
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update README.md

Browse Source
main
PENG Bo 3 years ago committed by GitHub
parent fc047a20b1
commit 6b59d8fee1
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File

2
README.md
Unescape Escape View File

@ -192,7 +192,7 @@ out.write(ss + "\n")
### Some ideas ### Some ideas
1. Now time decay is like 0.999^T (0.999 is learnable). Change it to something like (0.999^T + 0.1) where 0.1 is learnable too. The 0.1 part will be kept forever. 1. Now time decay is like 0.999^T (0.999 is learnable). Change it to something like (0.999^T + 0.1) where 0.1 is learnable too. The 0.1 part will be kept forever. Or try A^T + B^T = fast-decay + slow-decay.
2. Use complex-valued decay (so, rotation instead of decay) in some channels. 2. Use complex-valued decay (so, rotation instead of decay) in some channels.

Write Preview
Loading…
Cancel
Save