Update README.md

README.md

@@ -6,9 +6,11 @@ datasets:
 
 # INTELLECT-2
 
-INTELLECT-2 is a 32B parameter reasoning model trained through a reinforcement learning run leveraging globally distributed community-contributed GPU resources.
+INTELLECT-2 is a 32 billion parameter language model trained through globally distributed reinforcement learning (RL) run on permissionless, community-contributed GPU resources.
 
-To learn more about how INTELLECT-2 was trained, you can check out its [technical report](link)
+The model was trained using [prime-rl], a framework designed for distributed asynchronous RL, using GRPO over verifiable rewards along with modifications for improved training stability.
+
+For detailed information, see our [technical report](link).
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64a32edf17b9f57eaec2ea65/0NFEBL9eAObkU4IQ_hAo0.png)