Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,19 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
# 🧠Smol-Reason2🧠
|
| 6 |
+
|
| 7 |
+
This is my second GRPO reasoning model, I was exploring fine tuning on my own hardware, and found it to work with 3B models.
|
| 8 |
+
|
| 9 |
+
System prompt:
|
| 10 |
+
```
|
| 11 |
+
Respond in the following format:
|
| 12 |
+
<think>
|
| 13 |
+
|
| 14 |
+
...your reasoning here...
|
| 15 |
+
|
| 16 |
+
</think>
|
| 17 |
+
|
| 18 |
+
...your answer here...
|
| 19 |
+
```
|