Create README.md
#1
by
chujiezheng
- opened
README.md
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: llama3
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
- zh
|
| 6 |
+
---
|
| 7 |
+
|
| 8 |
+
# Llama3-8B-Chinese-Chat-ExPO
|
| 9 |
+
|
| 10 |
+
The extrapolated (ExPO) model based on [`shenzhi-wang/Llama3-70B-Chinese-Chat`](https://huggingface.co/shenzhi-wang/Llama3-8B-Chinese-Chat) and [`meta-llama/Meta-Llama-3-70B-Instruct`](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct), as in the "[Weak-to-Strong Extrapolation Expedites Alignment](https://arxiv.org/abs/2404.16792)" paper.
|
| 11 |
+
|
| 12 |
+
Specifically, we obtain this model by extrapolating **(alpha = 0.3)** from the weights of the SFT and DPO/RLHF checkpoints, achieving superior alignment with human preference.
|