Adding Evaluation Results

README.md

@@ -1,9 +1,112 @@
 ---
+language:
+- en
 license: apache-2.0
 datasets:
 - garage-bAInd/Open-Platypus
-language:
-- en
+model-index:
+- name: Dolphin-Nebula-7B
+  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: 55.2
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Dolphin-Nebula-7B
+      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: 78.57
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Dolphin-Nebula-7B
+      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: 53.44
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Dolphin-Nebula-7B
+      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: 57.97
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Dolphin-Nebula-7B
+      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: 73.88
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Dolphin-Nebula-7B
+      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: 33.06
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Dolphin-Nebula-7B
+      name: Open LLM Leaderboard
 ---
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6468ce47e134d050a58aa89c/cKySe1S5IW_KnbZpKmozQ.png)
 
@@ -21,4 +124,17 @@ Dolphin-Nebula-7B is a merge of [ehartford/dolphin-2.0-mistral-7b](https://huggi
 | ARC (25-shot)         |        |
 | HellaSwag (10-shot)   |        |
 | MMLU (5-shot)         |        |
-| TruthfulQA (0-shot)   |        |
+| TruthfulQA (0-shot)   |        |
+# [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_Weyaxi__Dolphin-Nebula-7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |58.69|
+|AI2 Reasoning Challenge (25-Shot)|55.20|
+|HellaSwag (10-Shot)              |78.57|
+|MMLU (5-Shot)                    |53.44|
+|TruthfulQA (0-shot)              |57.97|
+|Winogrande (5-shot)              |73.88|
+|GSM8k (5-shot)                   |33.06|
+