Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Trained on 1600 samples of LM-SYS conversational data having undergone the [REFLECT](https://arxiv.org/pdf/2601.18730) process.
|
| 2 |
+
|
| 3 |
+
Official finetuned model using REFLECT generated for analyzing trend in KL Divergence against Winrate as training progresses.
|