Update README.md
Browse files
README.md
CHANGED
|
@@ -3,7 +3,7 @@ license: apache-2.0
|
|
| 3 |
library_name: transformers
|
| 4 |
---
|
| 5 |
|
| 6 |
-
i wanted to learn more about exposure bias mitigation in language models and came across ReMask
|
| 7 |
it's a neat idea, and i wanted to give it a go.
|
| 8 |
|
| 9 |
- during training, the model processes input sequences twice - once with the full sequence & once with masked sequence.
|
|
|
|
| 3 |
library_name: transformers
|
| 4 |
---
|
| 5 |
|
| 6 |
+
i wanted to learn more about exposure bias mitigation in language models and came across [ReMask](https://huggingface.co/euclaise/ReMask-3B).
|
| 7 |
it's a neat idea, and i wanted to give it a go.
|
| 8 |
|
| 9 |
- during training, the model processes input sequences twice - once with the full sequence & once with masked sequence.
|