Update README.md

README.md

@@ -25,9 +25,10 @@ Sabiá-7B is Portuguese language model developed by [Maritaca AI](https://www.ma
 
 Given that Sabiá-7B was trained solely on a language modeling objective without fine-tuning for instruction following, it is recommended for few-shot tasks rather than zero-shot tasks.
 
-**Results** 
+**Results in Portuguese** 
 
-Below we show the results on the Poeta benchmark, which consists of 14 Portuguese datasets:
+Below we show the results on the Poeta benchmark, which consists of 14 Portuguese datasets.
+For more information on the Normalized Preferred Metric (NPM), please check out our paper.
 
 |Model | NPM |
 |--|--|
@@ -35,7 +36,16 @@ Below we show the results on the Poeta benchmark, which consists of 14 Portugues
 |LLaMA-2-7B| 43.7|
 |Sabiá-7B| 48.5|
 
-For more information on the Normalized Preferred Metric (NPM), please check out our paper.
+**Results in English** 
+
+Below we show the average results on 6 English datasets: PIQA, HellaSwag, WinoGrande, ARC-e, ARC-c, and OpenBookQA.
+
+|Model | NPM |
+|--|--|
+|LLaMA-1-7B| 50.1|
+|Sabiá-7B| 49.0|
+
+
 
 Please use the following bibtex to cite our paper: 
 ```