Update README.md
Browse files
README.md
CHANGED
@@ -1,4 +1,6 @@
|
|
1 |
-
|
|
|
|
|
2 |
router is roughly 70M params
|
3 |
|
4 |
no loss chart for this
|
|
|
1 |
+
# !! "moe" - routed inference between 3 different models without any tying
|
2 |
+
|
3 |
+
experimental MoE with 3 experts totalling 480m~ params
|
4 |
router is roughly 70M params
|
5 |
|
6 |
no loss chart for this
|