Update README.md
Browse files
README.md
CHANGED
|
@@ -6,4 +6,10 @@ base_model:
|
|
| 6 |
---
|
| 7 |
|
| 8 |
Used Open R1 (by Huggingface) to SFT my earlier thinker models. Encouraging results.
|
| 9 |
-
Checkpoints also present.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
---
|
| 7 |
|
| 8 |
Used Open R1 (by Huggingface) to SFT my earlier thinker models. Encouraging results.
|
| 9 |
+
Checkpoints also present.
|
| 10 |
+
|
| 11 |
+
https://github.com/ewre324/open-r1/tree/main
|
| 12 |
+
|
| 13 |
+
|
| 14 |
+
Based on DeepSeek R1 based method to train on specific reasoning dataset to ensure more thinking.
|
| 15 |
+
Still the <think> ... </think> tags are not generated. TODO.
|