sabersalehk
commited on
Commit
•
036bb1a
1
Parent(s):
a190927
Update README.md
Browse files
README.md
CHANGED
@@ -4,4 +4,8 @@ datasets:
|
|
4 |
- HuggingFaceH4/ultrafeedback_binarized
|
5 |
base_model:
|
6 |
- princeton-nlp/Llama-3-Base-8B-SFT
|
7 |
-
---
|
|
|
|
|
|
|
|
|
|
4 |
- HuggingFaceH4/ultrafeedback_binarized
|
5 |
base_model:
|
6 |
- princeton-nlp/Llama-3-Base-8B-SFT
|
7 |
+
---
|
8 |
+
|
9 |
+
This is an aligned model based on princeton-nlp/Llama-3-Base-8B-SFT. The alignment loss has two parts, preference loss and a regularization term. The alignment loss does not require the assumption of an existing underlying reward model. Moreover, the distribution's ``softness" is adjustable via the softmax exponent, an algorithm parameter.
|
10 |
+
|
11 |
+
More information will be added later.
|