Update README.md

README.md

@@ -73,7 +73,7 @@ print(response)
 
 ## Benchmarks 
 
-Nous Benchmark:
+### Nous Benchmark:
 
 |                       Model                       |AGIEval|GPT4All|TruthfulQA|Bigbench|Average|
 |---------------------------------------------------|------:|------:|---------:|-------:|------:|
@@ -159,11 +159,12 @@ Average: 48.54%
 |bigbench_tracking_shuffled_objects_three_objects|      0|multiple_choice_grade|44.00|±  |  2.87|
 
 Average: 41.43%
-
-Average score: 51.25%
 ```
 
-OpenLLM Benchmark:
+**Average score**: 51.25%
+
+
+### OpenLLM Benchmark:
 
 |                       Model                       |ARC |HellaSwag|MMLU |TruthfulQA|Winogrande|GSM8K|Average|
 |---------------------------------------------------|---:|--------:|----:|---------:|---------:|----:|------:|
@@ -477,6 +478,6 @@ Average: 77.35%
 |     |       |alias                              |gsm8k|   |      |
 
 Average: 67.48%
+```
 
-Average score: 67.48%
-```
+**Average score**: 67.48%