Adding Evaluation Results

README.md

@@ -1,4 +1,8 @@
 ---
+license: cc-by-nc-4.0
+tags:
+- mergekit
+- merge
 base_model:
 - mistralai/Mixtral-8x7B-v0.1
 - jondurbin/bagel-dpo-8x7b-v0.2
@@ -6,10 +10,101 @@ base_model:
 - mistralai/Mixtral-8x7B-v0.1
 - Doctor-Shotgun/limarp-zloss-mixtral-8x7b-qlora
 - mistralai/Mixtral-8x7B-Instruct-v0.1
-tags:
-- mergekit
-- merge
-license: cc-by-nc-4.0
+model-index:
+- name: BagelMIsteryTour-v2-8x7B
+  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: 62.62
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ycros/BagelMIsteryTour-v2-8x7B
+      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: 31.37
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ycros/BagelMIsteryTour-v2-8x7B
+      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: 7.7
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ycros/BagelMIsteryTour-v2-8x7B
+      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: 7.72
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ycros/BagelMIsteryTour-v2-8x7B
+      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: 10.32
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ycros/BagelMIsteryTour-v2-8x7B
+      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: 27.56
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ycros/BagelMIsteryTour-v2-8x7B
+      name: Open LLM Leaderboard
 ---
 # BagelMIsteryTour-v2-8x7B
 
@@ -71,3 +166,17 @@ dtype: bfloat16
 
 
 ```
+
+# [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_ycros__BagelMIsteryTour-v2-8x7B)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |24.55|
+|IFEval (0-Shot)    |62.62|
+|BBH (3-Shot)       |31.37|
+|MATH Lvl 5 (4-Shot)| 7.70|
+|GPQA (0-shot)      | 7.72|
+|MuSR (0-shot)      |10.32|
+|MMLU-PRO (5-shot)  |27.56|
+