Update README.md
Browse files
README.md
CHANGED
|
@@ -22,7 +22,7 @@ As same as 42dot-PLM, the model is built upon a Transformer decoder architecture
|
|
| 22 |
|
| 23 |
| Params | Layers | Attention heads | Hidden size | FFN size | Max. length\* |
|
| 24 |
| -- | -- | -- | -- | -- | -- |
|
| 25 |
-
| 1.3B | 24 | 32 | 2,048 | 5,632 |
|
| 26 |
|
| 27 |
(\* unit: tokens)
|
| 28 |
### Supervised Fine-tuning
|
|
|
|
| 22 |
|
| 23 |
| Params | Layers | Attention heads | Hidden size | FFN size | Max. length\* |
|
| 24 |
| -- | -- | -- | -- | -- | -- |
|
| 25 |
+
| 1.3B | 24 | 32 | 2,048 | 5,632 | 4,096 |
|
| 26 |
|
| 27 |
(\* unit: tokens)
|
| 28 |
### Supervised Fine-tuning
|