parole-study-viper commited on
Commit
dd2030a
·
verified ·
1 Parent(s): f2194b3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -0
README.md CHANGED
@@ -38,3 +38,16 @@ if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not
38
 
39
  response = generate(model, tokenizer, prompt=prompt, verbose=True)
40
  ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
38
 
39
  response = generate(model, tokenizer, prompt=prompt, verbose=True)
40
  ```
41
+
42
+
43
+ ## Citation
44
+ ```
45
+ @misc{deepscaler2025,
46
+ title={DeepScaleR: Surpassing O1-Preview with a 1.5B Model by Scaling RL},
47
+ author={Michael Luo and Sijun Tan and Justin Wong and Xiaoxiang Shi and William Tang and Manan Roongta and Colin Cai and Jeffrey Luo and Tianjun Zhang and Erran Li and Raluca Ada Popa and Ion Stoica},
48
+ year={2025},
49
+ howpublished={\url{https://pretty-radio-b75.notion.site/DeepScaleR-Surpassing-O1-Preview-with-a-1-5B-Model-by-Scaling-RL-19681902c1468005bed8ca303013a4e2}},
50
+ note={Notion Blog}
51
+ year={2025}
52
+ }
53
+ ```