KT313 commited on
Commit
5fda600
·
verified ·
1 Parent(s): 8e1c2bb

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -4
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