Commit
•
405cc12
1
Parent(s):
c68c3d7
Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
pipeline_tag: text-generation
|
| 3 |
+
license: other
|
| 4 |
+
language:
|
| 5 |
+
- en
|
| 6 |
+
- zh
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
# internlm2-chat-1_8b-ExPO
|
| 10 |
+
|
| 11 |
+
The extrapolated (ExPO) model based on [`internlm2-chat-1_8b`](https://huggingface.co/internlm/internlm2-chat-1_8b) and [`internlm/internlm2-chat-1_8b-sft`](https://huggingface.co/internlm/internlm2-chat-1_8b-sft), 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.
|