Update README.md
Browse files
README.md
CHANGED
@@ -3,12 +3,13 @@ license: mit
|
|
3 |
---
|
4 |
|
5 |
A not-so-state-of-the-art 60M parameter transformer model.
|
|
|
6 |
Uses the olmo default architecture.
|
7 |
|
8 |
-
Heads: 8
|
9 |
-
Layers: 8
|
10 |
-
Dimension model: 512
|
11 |
-
Dimension mlp: 4096
|
12 |
|
13 |
Training Data:
|
14 |
|
|
|
3 |
---
|
4 |
|
5 |
A not-so-state-of-the-art 60M parameter transformer model.
|
6 |
+
|
7 |
Uses the olmo default architecture.
|
8 |
|
9 |
+
- Heads: 8
|
10 |
+
- Layers: 8
|
11 |
+
- Dimension model: 512
|
12 |
+
- Dimension mlp: 4096
|
13 |
|
14 |
Training Data:
|
15 |
|