Adding Evaluation Results (#4)

- Adding Evaluation Results (70f2b02775b9c72882218cac7d8f52e3dae6ab36)


Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>

README.md

@@ -15,6 +15,109 @@ base_model:
 - cognitivecomputations/dolphin-2.2-70b
 - cognitivecomputations/dolphin-2.2-70b
 - cognitivecomputations/dolphin-2.2-70b
+model-index:
+- name: MegaDolphin-120b
+  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: 69.03
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cognitivecomputations/MegaDolphin-120b
+      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: 87.8
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cognitivecomputations/MegaDolphin-120b
+      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: 69.26
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cognitivecomputations/MegaDolphin-120b
+      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: 59.28
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cognitivecomputations/MegaDolphin-120b
+      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: 81.85
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cognitivecomputations/MegaDolphin-120b
+      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: 46.25
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cognitivecomputations/MegaDolphin-120b
+      name: Open LLM Leaderboard
 ---
 
 MegaDolphin 2.2 120b 🐬
@@ -300,3 +403,17 @@ they're as smooth as pulling a rabbit out of a hat!
 - BTC - 3ENBV6zdwyqieAXzZP2i3EjeZtVwEmAuo4
 - ETH - 0xcac74542A7fF51E2fb03229A5d9D0717cB6d70C9
 - [Buy you a t-shirt](https://fa7113.myshopify.com/)
+
+# [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_cognitivecomputations__MegaDolphin-120b)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |68.91|
+|AI2 Reasoning Challenge (25-Shot)|69.03|
+|HellaSwag (10-Shot)              |87.80|
+|MMLU (5-Shot)                    |69.26|
+|TruthfulQA (0-shot)              |59.28|
+|Winogrande (5-shot)              |81.85|
+|GSM8k (5-shot)                   |46.25|
+