Adding Evaluation Results

README.md

@@ -18,6 +18,9 @@ model-index:
       args:
         num_few_shot: 0
     metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 59.76
+      name: strict accuracy
     - type: inst_level_strict_acc and prompt_level_strict_acc
       value: 59.76
       name: strict accuracy
@@ -33,6 +36,9 @@ model-index:
       args:
         num_few_shot: 3
     metrics:
+    - type: acc_norm
+      value: 24.06
+      name: normalized accuracy
     - type: acc_norm
       value: 24.06
       name: normalized accuracy
@@ -48,6 +54,9 @@ model-index:
       args:
         num_few_shot: 4
     metrics:
+    - type: exact_match
+      value: 6.8
+      name: exact match
     - type: exact_match
       value: 6.8
       name: exact match
@@ -63,6 +72,9 @@ model-index:
       args:
         num_few_shot: 0
     metrics:
+    - type: acc_norm
+      value: 7.61
+      name: acc_norm
     - type: acc_norm
       value: 7.61
       name: acc_norm
@@ -78,6 +90,9 @@ model-index:
       args:
         num_few_shot: 0
     metrics:
+    - type: acc_norm
+      value: 11.78
+      name: acc_norm
     - type: acc_norm
       value: 11.78
       name: acc_norm
@@ -95,6 +110,9 @@ model-index:
       args:
         num_few_shot: 5
     metrics:
+    - type: acc
+      value: 25.44
+      name: accuracy
     - type: acc
       value: 25.44
       name: accuracy
@@ -204,4 +222,17 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
       primaryClass={cs.CL},
       url={https://arxiv.org/abs/2401.02415}, 
 }
-```
+```
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Pretergeek__OpenChat-3.5-0106_8.11B-36Layers-Last)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |22.57|
+|IFEval (0-Shot)    |59.76|
+|BBH (3-Shot)       |24.06|
+|MATH Lvl 5 (4-Shot)| 6.80|
+|GPQA (0-shot)      | 7.61|
+|MuSR (0-shot)      |11.78|
+|MMLU-PRO (5-shot)  |25.44|
+