Update README.md

README.md

@@ -20,8 +20,9 @@ The additional details of the Aquila model will be presented in the official tec
 
 2023.10.25 🔥 Version 1.2 of Aquila2-34B models have been updated on [ModelHub](https://model.baai.ac.cn/model-detail/100119) and Hugging Face.
 
-Aquila2-34B model has improved by 6.9% in comprehensive objective evaluation. 
-The evaluation results of Aquila2-34B v1.2 on MMLU, TruthfulQA, CSL, TNEWS, OCNLI, BUSTM and other exam, understanding and reasoning datasets have respectively increased by 12%, 14%, 11%, 12%, 28%, 18%.
+**Aquila2-34B v1.2** is based on the previous **Aquila2-34B**. 
+The Aquila2-34B has achieved a 6.9% improvement in comprehensive evaluations, 
+with MMLU(+12%), TruthfulQA(+14%), CSL(+11%), TNEWS(+12%), OCNLI(+28%), and BUSTM(+18%)
 
 ## Chat Model Performance