Adding Evaluation Results

README.md

@@ -1,15 +1,110 @@
 ---
-license: apache-2.0
 language:
-  - en
-  - fr
-  - de
-  - es
-  - it
-  - pt
-  - ru
-  - zh
-  - ja
+- en
+- fr
+- de
+- es
+- it
+- pt
+- ru
+- zh
+- ja
+license: apache-2.0
+model-index:
+- name: mini-magnum-12b-v1.1
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: HuggingFaceH4/ifeval
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 51.56
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=intervitens/mini-magnum-12b-v1.1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: BBH
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 29.73
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=intervitens/mini-magnum-12b-v1.1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: hendrycks/competition_math
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 3.7
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=intervitens/mini-magnum-12b-v1.1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 5.15
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=intervitens/mini-magnum-12b-v1.1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MuSR (0-shot)
+      type: TAUR-Lab/MuSR
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 8.09
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=intervitens/mini-magnum-12b-v1.1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU-PRO (5-shot)
+      type: TIGER-Lab/MMLU-Pro
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 25.46
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=intervitens/mini-magnum-12b-v1.1
+      name: Open LLM Leaderboard
 ---
 
 ![](mini-magnum.png)
@@ -39,3 +134,17 @@ This model has been a team effort, credits go to:
 ## Safety
 ...
 
+
+# [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_intervitens__mini-magnum-12b-v1.1)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |20.61|
+|IFEval (0-Shot)    |51.56|
+|BBH (3-Shot)       |29.73|
+|MATH Lvl 5 (4-Shot)| 3.70|
+|GPQA (0-shot)      | 5.15|
+|MuSR (0-shot)      | 8.09|
+|MMLU-PRO (5-shot)  |25.46|
+