assemsabry commited on
Commit
bf3ec14
·
verified ·
1 Parent(s): 4b02e82

docs: correct verified parameter count

Browse files
Files changed (1) hide show
  1. docs/MODEL_SPECIFICATION.md +1 -1
docs/MODEL_SPECIFICATION.md CHANGED
@@ -3,7 +3,7 @@
3
  Neo is an English-only System One decision model.
4
 
5
  - Bidirectional Transformer encoder.
6
- - Approximately 110M parameters.
7
  - 8 layers, hidden size 512, 8 attention heads.
8
  - Intermediate size 2048.
9
  - Maximum context 1,024 tokens.
 
3
  Neo is an English-only System One decision model.
4
 
5
  - Bidirectional Transformer encoder.
6
+ - 41,391,654 trainable parameters (approximately 41.4M).
7
  - 8 layers, hidden size 512, 8 attention heads.
8
  - Intermediate size 2048.
9
  - Maximum context 1,024 tokens.