Update README.md
Browse files
README.md
CHANGED
|
@@ -39,7 +39,7 @@ dimensions of each head. The model is trained with a tokenization vocabulary of
|
|
| 39 |
|
| 40 |
## Training data
|
| 41 |
|
| 42 |
-
GPT-NeoX-Ko was trained on 1.
|
| 43 |
|
| 44 |
## Training procedure
|
| 45 |
|
|
|
|
| 39 |
|
| 40 |
## Training data
|
| 41 |
|
| 42 |
+
GPT-NeoX-Ko was trained on 1.2TB Korean Dataset, a large-scale curated dataset created by [tunib-ai](https://tunib.ai/).
|
| 43 |
|
| 44 |
## Training procedure
|
| 45 |
|