Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,7 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: llama3
|
| 3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: llama3
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
LLaMA-3-8B-SFR-Iterative-DPO-Concise-R
|
| 6 |
+
This is a concise version of Salesforce/SFR-Iterative-DPO-LLaMA-3-8B-R. In the training, a concise penalty is applied.
|
| 7 |
+
|