Update README.md

README.md

@@ -2,6 +2,7 @@
 language:
 - en
 - zh
+- tr
 license: mit
 pipeline_tag: text-generation
 tags:
@@ -19,7 +20,7 @@ Find the official code and training recipes on the [GitHub repository](https://g
 
 ## Model Description
 
-This is a reproduced version of rStar2-Agent, a 14B parameter math reasoning model that achieves performance comparable to 67B DeepSeek-R1 through pure agentic reinforcement learning. The model excels at planning, reasoning, and autonomously using coding tools to efficiently explore, verify, and reflect for complex problem-solving.
+This is a reproduced version of rStar2-Agent, a 14B parameter math reasoning model that achieves performance comparable to 671B DeepSeek-R1 through pure agentic reinforcement learning. The model excels at planning, reasoning, and autonomously using coding tools to efficiently explore, verify, and reflect for complex problem-solving.
 
 ## Usage