Update README.md

README.md

@@ -37,6 +37,9 @@ While previous models like Llama-ko and Llama-2-ko experienced diminished Englis
 
 LLaMA-Pro-Ko's performance is evaluated on two fronts: its proficiency in English and its mastery of Korean, showcasing its capabilities as a bilingual model.
 
+
+![](figure.svg)
+
 ### Korean Evaluation
 
 
@@ -64,4 +67,3 @@ LLaMA-Pro-Ko's performance is evaluated on two fronts: its proficiency in Englis
 | llama-pro-ko-8b                                              | **53.24** | <u>77.93</u> | **47.06** | <u>38.32</u> | <u>72.22</u> | <u>57.75</u> | **-0.51** |
 
 
-![](figure.svg)