Update README.md

README.md

@@ -27,7 +27,7 @@ model-index:
         num_few_shot: 0
     metrics:
     - type: inst_level_strict_acc and prompt_level_strict_acc
-      value: 55.37
+      value: 56.04
       name: strict accuracy
     source:
       url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/Llama-3.2-SUN-2.5B-chat
@@ -42,7 +42,7 @@ model-index:
         num_few_shot: 3
     metrics:
     - type: acc_norm
-      value: 7.17
+      value: 9.41
       name: normalized accuracy
     source:
       url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/Llama-3.2-SUN-2.5B-chat
@@ -57,7 +57,7 @@ model-index:
         num_few_shot: 4
     metrics:
     - type: exact_match
-      value: 1.28
+      value: 5.06
       name: exact match
     source:
       url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/Llama-3.2-SUN-2.5B-chat
@@ -72,7 +72,7 @@ model-index:
         num_few_shot: 0
     metrics:
     - type: acc_norm
-      value: 0.45
+      value: 1.23
       name: acc_norm
     source:
       url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/Llama-3.2-SUN-2.5B-chat
@@ -87,7 +87,7 @@ model-index:
         num_few_shot: 0
     metrics:
     - type: acc_norm
-      value: 0.13
+      value: 1.11
       name: acc_norm
     source:
       url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/Llama-3.2-SUN-2.5B-chat
@@ -104,7 +104,7 @@ model-index:
         num_few_shot: 5
     metrics:
     - type: acc
-      value: 7.17
+      value: 9.04
       name: accuracy
     source:
       url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/Llama-3.2-SUN-2.5B-chat
@@ -153,11 +153,11 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
 
 |      Metric       |Value|
 |-------------------|----:|
-|Avg.               |11.93|
-|IFEval (0-Shot)    |55.37|
-|BBH (3-Shot)       | 7.17|
-|MATH Lvl 5 (4-Shot)| 1.28|
-|GPQA (0-shot)      | 0.45|
-|MuSR (0-shot)      | 0.13|
-|MMLU-PRO (5-shot)  | 7.17|
+|Avg.               |13.65|
+|IFEval (0-Shot)    |56.04|
+|BBH (3-Shot)       | 9.41|
+|MATH Lvl 5 (4-Shot)| 5.06|
+|GPQA (0-shot)      | 1.23|
+|MuSR (0-shot)      | 1.11|
+|MMLU-PRO (5-shot)  | 9.04|