Commit
•
6ba5b1b
1
Parent(s):
f777c7d
Create README.md (#1)
Browse files- Create README.md (eabef980293a4a962bd57e185bee095de9e2b9b7)
README.md
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: llama3
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
# Smaug-Llama-3-70B-Instruct-ExPO
|
| 6 |
+
|
| 7 |
+
The extrapolated (ExPO) model based on [`abacusai/Smaug-Llama-3-70B-Instruct`](https://huggingface.co/abacusai/Smaug-Llama-3-70B-Instruct) and [`meta-llama/Meta-Llama-3-70B-Instruct`](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct), 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.
|