Update README.md
Browse files
README.md
CHANGED
|
@@ -25,8 +25,7 @@ OctoThinker-3B-Hybrid-Zero is trained using the R1-Zero-style reinforcement lear
|
|
| 25 |
### Training Recipe for OctoThinker-3B-Hybrid-Base
|
| 26 |
|
| 27 |
<div style="display: flex; justify-content: left; gap: 20px;">
|
| 28 |
-
<img src="https://cdn-uploads.huggingface.co/production/uploads/62cbeb2d72dfd24b86bdf977/
|
| 29 |
-
|
| 30 |
</div>
|
| 31 |
|
| 32 |
|
|
|
|
| 25 |
### Training Recipe for OctoThinker-3B-Hybrid-Base
|
| 26 |
|
| 27 |
<div style="display: flex; justify-content: left; gap: 20px;">
|
| 28 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/62cbeb2d72dfd24b86bdf977/XSSllxdLr3dcw250dFm7e.png" alt="Data Pipeline" style="width:90%;">
|
|
|
|
| 29 |
</div>
|
| 30 |
|
| 31 |
|