Adding Evaluation Results

README.md

@@ -1,10 +1,113 @@
 ---
-license: apache-2.0
 language:
-  - en
+- en
+license: apache-2.0
 tags:
-  - merge
-  - moe
+- merge
+- moe
+model-index:
+- name: mhm-8x7B-FrankenMoE-v1.0
+  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: 70.9
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=h2m/mhm-8x7B-FrankenMoE-v1.0
+      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: 87.75
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=h2m/mhm-8x7B-FrankenMoE-v1.0
+      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: 64.7
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=h2m/mhm-8x7B-FrankenMoE-v1.0
+      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: 67.1
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=h2m/mhm-8x7B-FrankenMoE-v1.0
+      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: 82.0
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=h2m/mhm-8x7B-FrankenMoE-v1.0
+      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: 71.57
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=h2m/mhm-8x7B-FrankenMoE-v1.0
+      name: Open LLM Leaderboard
 ---
 
 ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/6589d7e6586088fd2784a12c/dUkIQhg6CBAESsPkhtSkX.jpeg)
@@ -66,4 +169,17 @@ MoE model build with:
 
 For details check model files, there is config yaml I used to create that model.
 
-Come back later for more details.
+Come back later for more details.
+# [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_h2m__mhm-8x7B-FrankenMoE-v1.0)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |74.01|
+|AI2 Reasoning Challenge (25-Shot)|70.90|
+|HellaSwag (10-Shot)              |87.75|
+|MMLU (5-Shot)                    |64.70|
+|TruthfulQA (0-shot)              |67.10|
+|Winogrande (5-shot)              |82.00|
+|GSM8k (5-shot)                   |71.57|
+