Update the model card with paper BibTeX citation (#10)
Browse files- Update the model card with paper BibTeX citation (eabc263010e65d60aa1792bab06f8413a16550b9)
README.md
CHANGED
|
@@ -237,4 +237,14 @@ This code repository is licensed under [the MIT License](https://github.com/incl
|
|
| 237 |
|
| 238 |
## FAQ
|
| 239 |
Recommended temperature? **0.6**
|
| 240 |
-
Recommended top_p? **0.95**
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 237 |
|
| 238 |
## FAQ
|
| 239 |
Recommended temperature? **0.6**
|
| 240 |
+
Recommended top_p? **0.95**
|
| 241 |
+
|
| 242 |
+
## Reference
|
| 243 |
+
```
|
| 244 |
+
@article{ling2025everystep,
|
| 245 |
+
title={Every Step Evolves: Scaling Reinforcement Learning for Trillion-Scale Thinking Model},
|
| 246 |
+
author={Team, Ling and Shen, Anqi and Li, Baihui and Hu, Bin and Jing, Bin and Chen, Cai and Huang, Chao and Zhang, Chao and Yang, Chaokun and Lin, Cheng and Wen, Chengyao and Li, Congqi and Zhao, Deng and Yuan, Dingbo and You, Donghai and Mao, Fagui and Meng, Fanzhuang and Xu, Feng and Li, Guojie and Wang, Guowei and Dai, Hao and Zheng, Haonan and others},
|
| 247 |
+
journal={arXiv preprint arXiv:2510.18855},
|
| 248 |
+
year={2025}
|
| 249 |
+
}
|
| 250 |
+
```
|