Update README.md
Browse files
README.md
CHANGED
|
@@ -6,4 +6,8 @@ datasets:
|
|
| 6 |
|
| 7 |
## Solarized-18B-truthy
|
| 8 |
|
| 9 |
-
Solarized-18B-dpo fine-tuned to improve truthfulness.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
|
| 7 |
## Solarized-18B-truthy
|
| 8 |
|
| 9 |
+
Solarized-18B-dpo fine-tuned to improve truthfulness.
|
| 10 |
+
|
| 11 |
+
It is a frankenmerge model created using mergekit, alternating layers of Nous-Hermes-2-SOLAR-10.7B and SOLAR-10.7B-Instruct. Then, we applied DPO over a high-quality preference dataset.
|
| 12 |
+
|
| 13 |
+
|