Adding Evaluation Results

README.md

@@ -80,6 +80,9 @@ model-index:
       args:
         num_few_shot: 0
     metrics:
+    - type: acc_norm
+      value: 9.09
+      name: acc_norm
     - type: acc_norm
       value: 9.09
       name: acc_norm
@@ -97,12 +100,79 @@ model-index:
       args:
         num_few_shot: 5
     metrics:
+    - type: acc
+      value: 32.26
+      name: accuracy
     - type: acc
       value: 32.26
       name: accuracy
     source:
       url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=T145/ZEUS-8B-V10
       name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: wis-k/instruction-following-eval
+      split: train
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 77.07
+      name: averaged accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=T145%2FZEUS-8B-V10
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: SaylorTwift/bbh
+      split: test
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 32.7
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=T145%2FZEUS-8B-V10
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: lighteval/MATH-Hard
+      split: test
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 20.09
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=T145%2FZEUS-8B-V10
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      split: train
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 9.96
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=T145%2FZEUS-8B-V10
+      name: Open LLM Leaderboard
 ---
 # ZEUS 8B 🌩️ V10
 
@@ -183,4 +253,17 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
 |MATH Lvl 5 (4-Shot)|-1.06|
 |GPQA (0-shot)      |+3.02|
 |MuSR (0-shot)      |+0.85|
-|MMLU-PRO (5-shot)  |+0.08|
+|MMLU-PRO (5-shot)  |+0.08|# [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/T145__ZEUS-8B-V10-details)!
+Summarized results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/contents/viewer/default/train?q=T145/ZEUS-8B-V10)!
+
+|      Metric       |Value (%)|
+|-------------------|--------:|
+|**Average**        |    30.19|
+|IFEval (0-Shot)    |    77.07|
+|BBH (3-Shot)       |    32.70|
+|MATH Lvl 5 (4-Shot)|    20.09|
+|GPQA (0-shot)      |     9.96|
+|MuSR (0-shot)      |     9.09|
+|MMLU-PRO (5-shot)  |    32.26|
+