MarsupialAI
commited on
Commit
•
a700d50
1
Parent(s):
b042989
Update README.md
Browse files
README.md
CHANGED
@@ -26,4 +26,4 @@ Components of those models include Nous-Hermes-Llama2-70b, Xwin-LM-7B-V0.1, Myth
|
|
26 |
|
27 |
# WTF is a rotating-stack merge?
|
28 |
|
29 |
-
Jeb Carter found that
|
|
|
26 |
|
27 |
# WTF is a rotating-stack merge?
|
28 |
|
29 |
+
Inspired by Undi's work with stacked merges, Jeb Carter found that performance and creativity could be significantly improved by reversing the model order in the stack, and then doing a linear merge between the original and reversed stacks. That is what I did here, creating three stacked merges with the three source models, and then doing a 1:1:1 linear merge of all three stacks. The exact merge configs can be found in the recipe.txt file.
|