Commit
•
1667ad5
1
Parent(s):
bbeb07f
Update README.md
Browse files
README.md
CHANGED
|
@@ -2,4 +2,5 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
---
|
| 4 |
We train OPT-1.3B using three datasets: Dahoas/rm-static, Dahoas/full-hh-rlhf, and yitingxie/rlhf-reward-datasets.
|
|
|
|
| 5 |
Dahoas/synthetic-instruct-gptj-pairwise is not used because of the adsence of test dataset.
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
---
|
| 4 |
We train OPT-1.3B using three datasets: Dahoas/rm-static, Dahoas/full-hh-rlhf, and yitingxie/rlhf-reward-datasets.
|
| 5 |
+
|
| 6 |
Dahoas/synthetic-instruct-gptj-pairwise is not used because of the adsence of test dataset.
|