Commit
•
a578fc8
1
Parent(s):
565016f
Update README.md
Browse files
README.md
CHANGED
|
@@ -4,6 +4,8 @@ language:
|
|
| 4 |
- en
|
| 5 |
---
|
| 6 |
|
|
|
|
|
|
|
| 7 |
The extrapolated (ExPO) model based on `berkeley-nest/Starling-LM-7B-alpha` and `openchat/openchat_3.5`, as in the "[Weak-to-Strong Extrapolation Expedites Alignment](https://arxiv.org/abs/2404.16792)" paper.
|
| 8 |
|
| 9 |
Specifically, we obtain this model by extrapolating from the weights of the SFT and DPO/RLHF checkpoints, achieving superior alignment with human preference.
|
|
|
|
| 4 |
- en
|
| 5 |
---
|
| 6 |
|
| 7 |
+
# Starling-LM-7B-alpha-ExPO
|
| 8 |
+
|
| 9 |
The extrapolated (ExPO) model based on `berkeley-nest/Starling-LM-7B-alpha` and `openchat/openchat_3.5`, as in the "[Weak-to-Strong Extrapolation Expedites Alignment](https://arxiv.org/abs/2404.16792)" paper.
|
| 10 |
|
| 11 |
Specifically, we obtain this model by extrapolating from the weights of the SFT and DPO/RLHF checkpoints, achieving superior alignment with human preference.
|