Adding Evaluation Results (#1)

- Adding Evaluation Results (dc50a9159f1459120bfedb684e7b3f0c6e6b6e0a)

README.md

@@ -11,6 +11,105 @@ language:
 - en
 pipeline_tag: text-generation
 license: gemma
+model-index:
+- name: Gemma2-9B-AdvancedFuse
+  results:
+  - 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: 15.43
+      name: averaged accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=agentlans%2FGemma2-9B-AdvancedFuse
+      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: 40.52
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=agentlans%2FGemma2-9B-AdvancedFuse
+      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: 7.55
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=agentlans%2FGemma2-9B-AdvancedFuse
+      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: 11.3
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=agentlans%2FGemma2-9B-AdvancedFuse
+      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: 11.99
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=agentlans%2FGemma2-9B-AdvancedFuse
+      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: 33.34
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=agentlans%2FGemma2-9B-AdvancedFuse
+      name: Open LLM Leaderboard
 ---
 # Gemma2-9B-AdvancedFuse
 
@@ -35,4 +134,18 @@ As with most large language models:
 1. Use clear and specific instructions for optimal performance.
 2. Verify generated outputs for factual accuracy when critical information is involved.
 3. Avoid providing inputs that could lead to harmful or unethical responses.
-4. Consider using human review, especially in high-stakes applications.
+4. Consider using human review, especially in high-stakes applications.
+# [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/agentlans__Gemma2-9B-AdvancedFuse-details)!
+Summarized results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/contents/viewer/default/train?q=agentlans%2FGemma2-9B-AdvancedFuse&sort[column]=Average%20%E2%AC%86%EF%B8%8F&sort[direction]=desc)!
+
+|      Metric       |Value (%)|
+|-------------------|--------:|
+|**Average**        |    20.02|
+|IFEval (0-Shot)    |    15.43|
+|BBH (3-Shot)       |    40.52|
+|MATH Lvl 5 (4-Shot)|     7.55|
+|GPQA (0-shot)      |    11.30|
+|MuSR (0-shot)      |    11.99|
+|MMLU-PRO (5-shot)  |    33.34|
+