Adding Evaluation Results (#1)

- Adding Evaluation Results (21405ea4280d4d9080c0c21b70e73f9814aca8b5)

README.md

@@ -1,12 +1,106 @@
 ---
-base_model:
-- zelk12/MT3-Gen3-IMM-gemma-2-9B
-- zelk12/MT3-Gen3-GMAMUB-gemma-2-9B
 library_name: transformers
 tags:
 - mergekit
 - merge
-
+base_model:
+- zelk12/MT3-Gen3-IMM-gemma-2-9B
+- zelk12/MT3-Gen3-GMAMUB-gemma-2-9B
+model-index:
+- name: MT3-Gen3-gemma-2-9B
+  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: 78.56
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=zelk12/MT3-Gen3-gemma-2-9B
+      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: 43.78
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=zelk12/MT3-Gen3-gemma-2-9B
+      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: 9.06
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=zelk12/MT3-Gen3-gemma-2-9B
+      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: 13.53
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=zelk12/MT3-Gen3-gemma-2-9B
+      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: 12.52
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=zelk12/MT3-Gen3-gemma-2-9B
+      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: 36.7
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=zelk12/MT3-Gen3-gemma-2-9B
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -37,3 +131,17 @@ dtype: bfloat16
 parameters:
   t: 0.25
 ```
+
+# [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/zelk12__MT3-Gen3-gemma-2-9B-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |32.36|
+|IFEval (0-Shot)    |78.56|
+|BBH (3-Shot)       |43.78|
+|MATH Lvl 5 (4-Shot)| 9.06|
+|GPQA (0-shot)      |13.53|
+|MuSR (0-shot)      |12.52|
+|MMLU-PRO (5-shot)  |36.70|
+