Update README.md

README.md

@@ -9,6 +9,8 @@ tags:
 license: mit
 language:
 - en
+datasets:
+- UCSC-VLAA/STAR-1
 ---
 
 SA stands for Safely and aligned.
@@ -32,6 +34,7 @@ Our training dataset consists of approximately 24K unique problem-tests pairs co
 - PrimeIntellect SYNTHETIC-1
 - LiveCodeBench v5 (5/1/23-7/31/24)
 
+- STAR-1
 ## Training Recipe
 
 Our training recipe relies on an improved version of GRPO (GRPO+) and iterative context lengthening, introduced in DeepScaleR.
@@ -103,6 +106,8 @@ This permissive license ensures that researchers, developers, and enthusiasts wo
 - Our model is trained on top of [`DeepSeek-R1-Distill-Qwen-14B`](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B).
 - Our work is done as part of  [Berkeley Sky Computing Lab](https://skycomputing.berkeley.edu/) and [Berkeley AI Research](https://bair.berkeley.edu/).
 
+- thanks to UCSC-VLAA
+
 ## Citation 
 ```bibtex
 @misc{deepcoder2025,
@@ -113,6 +118,8 @@ This permissive license ensures that researchers, developers, and enthusiasts wo
   year={2025}
 }
 
+
+
 # Uploaded  model
 
 - **Developed by:** EpistemeAI