Commit
·
b630515
1
Parent(s):
40b496f
Update README.md
Browse files
README.md
CHANGED
|
@@ -81,7 +81,7 @@ where the model generates the text after the comments.
|
|
| 81 |
|
| 82 |
## Training
|
| 83 |
|
| 84 |
-
### Model
|
| 85 |
* Architecture: a Transformer-based model with next-word prediction objective
|
| 86 |
* Dataset size: 30B tokens
|
| 87 |
* Training tokens: 150B tokens
|
|
|
|
| 81 |
|
| 82 |
## Training
|
| 83 |
|
| 84 |
+
### Model
|
| 85 |
* Architecture: a Transformer-based model with next-word prediction objective
|
| 86 |
* Dataset size: 30B tokens
|
| 87 |
* Training tokens: 150B tokens
|