better mmlu score

README.md

@@ -8,7 +8,7 @@ license: llama2
 
 0. using the updated [Meta's LLaMA-2 models](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf).
 1. support [4-bit qlora](https://arxiv.org/abs/2305.14314), extreme GPU memory and inference time saving;
-2. comparable MMLU evaluation dataset results, llama2-7b's 0.453 to our 0.4795 (+0.0265).
+2. better MMLU evaluation dataset results, llama2-7b's 45.3% to our 47.95% (+2.65%).
 
 ### Introduction
 Determine the rank of LoRA layers by the singular values of pretrained weight matrices.