Adding Evaluation Results (#1)

- Adding Evaluation Results (00940dd0d1ce04c6f2c1b0fdf10cfe087bfab086)

README.md

@@ -2,13 +2,108 @@
 license: llama3.1
 library_name: transformers
 tags:
-  - moe
-  - frankenmoe
-  - merge
-  - mergekit
+- moe
+- frankenmoe
+- merge
+- mergekit
 base_model:
-  - Joseph717171/Llama-3.1-SuperNova-8B-Lite_TIES_with_Base
-  - ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.2
+- Joseph717171/Llama-3.1-SuperNova-8B-Lite_TIES_with_Base
+- ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.2
+model-index:
+- name: L3.1-Moe-2x8B-v0.2
+  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: 73.48
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=moeru-ai/L3.1-Moe-2x8B-v0.2
+      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: 32.95
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=moeru-ai/L3.1-Moe-2x8B-v0.2
+      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: 15.26
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=moeru-ai/L3.1-Moe-2x8B-v0.2
+      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: 6.71
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=moeru-ai/L3.1-Moe-2x8B-v0.2
+      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: 11.38
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=moeru-ai/L3.1-Moe-2x8B-v0.2
+      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: 31.76
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=moeru-ai/L3.1-Moe-2x8B-v0.2
+      name: Open LLM Leaderboard
 ---
 
 # L3.1-Moe-2x8B-v0.2
@@ -68,3 +163,17 @@ experts:
 ```
 
 </details>
+
+# [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_moeru-ai__L3.1-Moe-2x8B-v0.2)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |28.59|
+|IFEval (0-Shot)    |73.48|
+|BBH (3-Shot)       |32.95|
+|MATH Lvl 5 (4-Shot)|15.26|
+|GPQA (0-shot)      | 6.71|
+|MuSR (0-shot)      |11.38|
+|MMLU-PRO (5-shot)  |31.76|
+