Update README.md (#9)
Browse files- Update README.md (a1f060ccdc059912665d9e665d27a259ee3b5a93)
Co-authored-by: Jian Hu <jianh-nvidia@users.noreply.huggingface.co>
README.md
CHANGED
|
@@ -108,7 +108,7 @@ model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-Research-Reasoning
|
|
| 108 |
## BroRL
|
| 109 |
In BroRL, we continued training for 419 steps based on a nearly fully trained ProRLv2 checkpoint, increasing the number of samples per prompt from 16 to 512. We found that the improvement of BroRL over ProRLv2 was greater than that of ProRLv2 over ProRLv1.
|
| 110 |
|
| 111 |
-
Link to [BroRL 419 steps checkpoint](
|
| 112 |
|
| 113 |
## License/Terms of Use
|
| 114 |
cc-by-nc-4.0
|
|
|
|
| 108 |
## BroRL
|
| 109 |
In BroRL, we continued training for 419 steps based on a nearly fully trained ProRLv2 checkpoint, increasing the number of samples per prompt from 16 to 512. We found that the improvement of BroRL over ProRLv2 was greater than that of ProRLv2 over ProRLv1.
|
| 110 |
|
| 111 |
+
Link to the [BroRL 419 steps checkpoint](https://huggingface.co/nvidia/Nemotron-Research-Reasoning-Qwen-1.5B/tree/brorl)
|
| 112 |
|
| 113 |
## License/Terms of Use
|
| 114 |
cc-by-nc-4.0
|