chujiezheng
commited on
Commit
•
b483764
1
Parent(s):
3bce9e4
Update README.md
Browse files
README.md
CHANGED
@@ -8,6 +8,6 @@ language:
|
|
8 |
|
9 |
# tulu-2-dpo-13b-ExPO
|
10 |
|
11 |
-
The extrapolated (ExPO) model based on `allenai/tulu-2-dpo-13b` and `allenai/tulu-2-13b
|
12 |
|
13 |
Specifically, we obtain this model by extrapolating from the weights of the SFT and DPO/RLHF checkpoints, achieving superior alignment with human preference.
|
|
|
8 |
|
9 |
# tulu-2-dpo-13b-ExPO
|
10 |
|
11 |
+
The extrapolated (ExPO) model based on [`allenai/tulu-2-dpo-13b`](https://huggingface.co/allenai/tulu-2-dpo-13b) and [`allenai/tulu-2-13b`](https://huggingface.co/allenai/tulu-2-13b), as in the "[Weak-to-Strong Extrapolation Expedites Alignment](https://arxiv.org/abs/2404.16792)" paper.
|
12 |
|
13 |
Specifically, we obtain this model by extrapolating from the weights of the SFT and DPO/RLHF checkpoints, achieving superior alignment with human preference.
|