PCL-Reasoner commited on
Commit
7f63412
·
verified ·
1 Parent(s): 90d1f92

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -1
README.md CHANGED
@@ -43,10 +43,14 @@ PCL-Reasoner-V1.5 attains **90.9% on AIME 2024** and **85.7% on AIME 2025**, sig
43
 
44
  We have fully open-sourced the **model weights**, **dataset**, and **training code** to foster transparency, reproducibility, and community innovation. Follow the tutorial below to deploy, evaluate, or extend PCL-Reasoner-V1.5 in your own research!
45
 
46
- ## Codes
47
 
48
  [GitHub Repository](https://github.com/PCL-Reasoner/V1.5)
49
 
 
 
 
 
50
 
51
  ## Evaluation
52
  All results are reported using the **Avg@32 metric** (average accuracy over 32 independent sampling attempts per problem), ensuring robust and fair comparison.
 
43
 
44
  We have fully open-sourced the **model weights**, **dataset**, and **training code** to foster transparency, reproducibility, and community innovation. Follow the tutorial below to deploy, evaluate, or extend PCL-Reasoner-V1.5 in your own research!
45
 
46
+ ## Code
47
 
48
  [GitHub Repository](https://github.com/PCL-Reasoner/V1.5)
49
 
50
+ ## RL Dataset
51
+
52
+ [Huggingface Dataset](https://huggingface.co/datasets/PCL-Reasoner/V1.5-RL-Math)
53
+
54
 
55
  ## Evaluation
56
  All results are reported using the **Avg@32 metric** (average accuracy over 32 independent sampling attempts per problem), ensuring robust and fair comparison.