Update README.md
Browse files
README.md
CHANGED
|
@@ -6,7 +6,7 @@ metrics:
|
|
| 6 |
- accuracy
|
| 7 |
---
|
| 8 |
|
| 9 |
-
GPT2 large model trained on Anthropic/hh-rlhf harmless dataset. It is specifically used for harmful response detection.
|
| 10 |
|
| 11 |
It achieves an accuracy of 0.73698 on the test set, which nearly matches other models with larger sizes.
|
| 12 |
|
|
|
|
| 6 |
- accuracy
|
| 7 |
---
|
| 8 |
|
| 9 |
+
GPT2 large model trained on Anthropic/hh-rlhf harmless dataset. It is specifically used for harmful response detection or RLHF.
|
| 10 |
|
| 11 |
It achieves an accuracy of 0.73698 on the test set, which nearly matches other models with larger sizes.
|
| 12 |
|