Adding Evaluation Results

README.md

@@ -106,6 +106,98 @@ model-index:
     source:
       url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ibivibiv/multimaster-7b-v6
       name: Open LLM Leaderboard
+  - 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: 44.73
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ibivibiv/multimaster-7b-v6
+      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: 32.4
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ibivibiv/multimaster-7b-v6
+      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: 5.21
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ibivibiv/multimaster-7b-v6
+      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: 7.16
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ibivibiv/multimaster-7b-v6
+      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: 13.38
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ibivibiv/multimaster-7b-v6
+      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: 23.28
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ibivibiv/multimaster-7b-v6
+      name: Open LLM Leaderboard
 ---
 
 # Multi Master 7Bx5 v6
@@ -278,3 +370,17 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
 |Winogrande (5-shot)              |86.42|
 |GSM8k (5-shot)                   |70.36|
 
+
+# [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_ibivibiv__multimaster-7b-v6)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |21.03|
+|IFEval (0-Shot)    |44.73|
+|BBH (3-Shot)       |32.40|
+|MATH Lvl 5 (4-Shot)| 5.21|
+|GPQA (0-shot)      | 7.16|
+|MuSR (0-shot)      |13.38|
+|MMLU-PRO (5-shot)  |23.28|
+