Update README.md
Browse files
README.md
CHANGED
|
@@ -38,6 +38,8 @@ extra_gated_fields:
|
|
| 38 |
|
| 39 |
<img src="https://i.imgur.com/PtqeTZw.png" alt="Primus Overview" width="60%">
|
| 40 |
|
|
|
|
|
|
|
| 41 |
>TL;DR: Llama-Primus-Reasoning is a reasoning model distilled from the reasoning steps with reflection data generated by o1-preview on cybersecurity tasks (_Primus-Reasoning_), based on Llama-Primus-Merged. It demonstrates a 🚀**10%** improvement in security certification (CISSP).
|
| 42 |
|
| 43 |
**🔥 For more details, please refer to the paper: [[📄Paper]](https://arxiv.org/abs/2502.11191).**
|
|
|
|
| 38 |
|
| 39 |
<img src="https://i.imgur.com/PtqeTZw.png" alt="Primus Overview" width="60%">
|
| 40 |
|
| 41 |
+
**First cybersecurity reasoning model!**
|
| 42 |
+
|
| 43 |
>TL;DR: Llama-Primus-Reasoning is a reasoning model distilled from the reasoning steps with reflection data generated by o1-preview on cybersecurity tasks (_Primus-Reasoning_), based on Llama-Primus-Merged. It demonstrates a 🚀**10%** improvement in security certification (CISSP).
|
| 44 |
|
| 45 |
**🔥 For more details, please refer to the paper: [[📄Paper]](https://arxiv.org/abs/2502.11191).**
|