nanowell commited on
Commit
7a2e3f4
·
verified ·
1 Parent(s): 37c4d38

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -2
README.md CHANGED
@@ -1,5 +1,6 @@
1
- Novel training procedure to deslopify models.
2
 
3
  No SFT.
4
 
5
- Pure RL with a good signal.
 
 
1
+ Novel training procedure to deslopify instruct/assistant models.
2
 
3
  No SFT.
4
 
5
+ Pure RL with a good signal.
6
+