Adding Evaluation Results

README.md

@@ -1,12 +1,115 @@
 ---
 license: apache-2.0
+tags:
+- mergekit
+- moe
 base_model:
 - nbeerbower/bruphin-epsilon
 - FelixChao/WestSeverus-7B-DPO-v2
 - jondurbin/airoboros-m-7b-3.1.2
-tags:
-- mergekit
-- moe
+model-index:
+- name: SuperBruphin-3x7B
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 71.16
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nbeerbower/SuperBruphin-3x7B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 87.74
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nbeerbower/SuperBruphin-3x7B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 64.58
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nbeerbower/SuperBruphin-3x7B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 66.85
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nbeerbower/SuperBruphin-3x7B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 81.53
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nbeerbower/SuperBruphin-3x7B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 70.66
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nbeerbower/SuperBruphin-3x7B
+      name: Open LLM Leaderboard
 ---
 
 # SuperBruphin-3x7B
@@ -40,3 +143,17 @@ experts:
     positive_prompts:
         - "Write a letter."
 ```
+
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_nbeerbower__SuperBruphin-3x7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |73.75|
+|AI2 Reasoning Challenge (25-Shot)|71.16|
+|HellaSwag (10-Shot)              |87.74|
+|MMLU (5-Shot)                    |64.58|
+|TruthfulQA (0-shot)              |66.85|
+|Winogrande (5-shot)              |81.53|
+|GSM8k (5-shot)                   |70.66|
+