Update README.md

README.md

@@ -48,7 +48,7 @@ This demonstrates advanced reasoning capabilities essential for top-tier math co
 
 
 To facilitate early community exploration of the reasoning capabilities of the trillion-parameter thinking model Ring-1T, we have decided to open-source its preview version, __Ring-1T-preview__, ahead of schedule. 
-This model retains the efficient MoE architecture of Ling 2.0, completed pre-training on 20T tokens of corpora, and underwent RLVR training tailored for reasoning abilities within our self-developed efficient reinforcement learning system __ASystem__ (the AReal framework of which has been open-sourced), leveraging the previously disclosed "__icepop__" method(https://ringtech.notion.site/icepop).
+This model retains the efficient MoE architecture of Ling 2.0, completed pre-training on 20T tokens of corpora, and underwent RLVR training tailored for reasoning abilities within our self-developed efficient reinforcement learning system __ASystem__ (the __AReaL__ framework of which has been open-sourced), leveraging the previously disclosed "__icepop__" method(https://ringtech.notion.site/icepop).
 
 
 __Ring-1T__ remains under continuous training.