Update README.md
Browse files
README.md
CHANGED
|
@@ -98,9 +98,7 @@ The model was pre-trained continuously on a single A10G GPU in an AWS instance f
|
|
| 98 |
|
| 99 |
Note:
|
| 100 |
|
| 101 |
-
Could be used as an encoder-only model
|
| 102 |
-
<br>Because there are already bert-based models with better inference time. (due to longer sequence length)
|
| 103 |
-
<br>This could be used in case a longer sequence length is required.
|
| 104 |
|
| 105 |
#### Authors:
|
| 106 |
|
|
|
|
| 98 |
|
| 99 |
Note:
|
| 100 |
|
| 101 |
+
Could be used as an encoder-only model using BartForSequenceClasssification.
|
|
|
|
|
|
|
| 102 |
|
| 103 |
#### Authors:
|
| 104 |
|