Update README.md

README.md

@@ -77,8 +77,9 @@ Nous Benchmark:
 |---------------------------------------------------|------:|------:|---------:|-------:|------:|
 |[Master-Yi-9B](https://huggingface.co/qnguyen3/Master-Yi-9B)|  43.55|  71.48|     48.54|   41.43|  51.25|
 
-```
+
 ### AGIEval
+```
 |             Task             |Version| Metric |Value|   |Stderr|
 |------------------------------|------:|--------|----:|---|-----:|
 |agieval_aqua_rat              |      0|acc     |35.83|±  |  3.01|
@@ -99,8 +100,10 @@ Nous Benchmark:
 |                              |       |acc_norm|47.73|±  |  3.38|
 
 Average: 43.55%
+```
 
 ### GPT4All
+```
 |    Task     |Version| Metric |Value|   |Stderr|
 |-------------|------:|--------|----:|---|-----:|
 |arc_challenge|      0|acc     |54.95|±  |  1.45|
@@ -117,16 +120,20 @@ Average: 43.55%
 |winogrande   |      0|acc     |72.61|±  |  1.25|
 
 Average: 71.48%
+```
 
 ### TruthfulQA
+```
 |    Task     |Version|Metric|Value|   |Stderr|
 |-------------|------:|------|----:|---|-----:|
 |truthfulqa_mc|      1|mc1   |33.05|±  |  1.65|
 |             |       |mc2   |48.54|±  |  1.54|
 
 Average: 48.54%
+```
 
 ### Bigbench
+```
 |                      Task                      |Version|       Metric        |Value|   |Stderr|
 |------------------------------------------------|------:|---------------------|----:|---|-----:|
 |bigbench_causal_judgement                       |      0|multiple_choice_grade|54.74|±  |  3.62|
@@ -160,8 +167,8 @@ OpenLLM Benchmark:
 |---------------------------------------------------|---:|--------:|----:|---------:|---------:|----:|------:|
 |[Master-Yi-9B](https://huggingface.co/qnguyen3/Master-Yi-9B)|61.6|    79.89|69.95|     48.59|     77.35|67.48|  67.48|
 
-```
 ### ARC
+```
 |    Task     |Version|       Metric       |    Value    |   |Stderr|
 |-------------|------:|--------------------|-------------|---|------|
 |arc_challenge|      1|acc,none            |         0.59|   |      |
@@ -171,8 +178,10 @@ OpenLLM Benchmark:
 |             |       |alias               |arc_challenge|   |      |
 
 Average: 61.6%
+```
 
 ### HellaSwag
+```
 |  Task   |Version|       Metric       |  Value  |   |Stderr|
 |---------|------:|--------------------|---------|---|------|
 |hellaswag|      1|acc,none            |     0.61|   |      |
@@ -182,8 +191,10 @@ Average: 61.6%
 |         |       |alias               |hellaswag|   |      |
 
 Average: 79.89%
+```
 
 ### MMLU
+```
 |                  Task                  |Version|    Metric     |                 Value                 |   |Stderr|
 |----------------------------------------|-------|---------------|---------------------------------------|---|------|
 |mmlu                                    |N/A    |acc,none       |                                    0.7|   |      |
@@ -374,8 +385,10 @@ Average: 79.89%
 |                                        |       |acc_stderr,none|0.03                                   |   |      |
 
 Average: 69.95%
+```
 
 ### TruthfulQA
+```
 |     Task     |Version|        Metric         |      Value      |   |Stderr|
 |--------------|-------|-----------------------|-----------------|---|------|
 |truthfulqa    |N/A    |bleu_acc,none          |             0.45|   |      |
@@ -438,8 +451,10 @@ Average: 69.95%
 |              |       |alias                  | - truthfulqa_mc2|   |      |
 
 Average: 48.59%
+```
 
 ### Winogrande
+```
 |   Task   |Version|    Metric     |  Value   |   |Stderr|
 |----------|------:|---------------|----------|---|------|
 |winogrande|      1|acc,none       |      0.77|   |      |
@@ -447,8 +462,10 @@ Average: 48.59%
 |          |       |alias          |winogrande|   |      |
 
 Average: 77.35%
+```
 
 ### GSM8K
+```
 |Task |Version|              Metric               |Value|   |Stderr|
 |-----|------:|-----------------------------------|-----|---|------|
 |gsm8k|      3|exact_match,strict-match           | 0.67|   |      |