Adding Evaluation Results

README.md

@@ -1,10 +1,112 @@
-
 ---
+language:
+- en
 license: cc-by-nc-4.0
 datasets:
 - garage-bAInd/Open-Platypus
-language:
-- en
+model-index:
+- name: SynthIA-v1.3-Nebula-v2-7B
+  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: 59.39
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/SynthIA-v1.3-Nebula-v2-7B
+      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: 82.77
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/SynthIA-v1.3-Nebula-v2-7B
+      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: 57.57
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/SynthIA-v1.3-Nebula-v2-7B
+      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: 50.62
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/SynthIA-v1.3-Nebula-v2-7B
+      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: 74.74
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/SynthIA-v1.3-Nebula-v2-7B
+      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: 24.87
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/SynthIA-v1.3-Nebula-v2-7B
+      name: Open LLM Leaderboard
 ---
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6468ce47e134d050a58aa89c/cKySe1S5IW_KnbZpKmozQ.png)
 
@@ -26,3 +128,17 @@ SynthIA-v1.3-Nebula-v2-7B is a merge of [migtissera/SynthIA-7B-v1.3](https://hug
 | Winogrande (5-shot)   |           |
 | GSM8K (5-shot)        |           |
 | DROP (3-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__SynthIA-v1.3-Nebula-v2-7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |58.33|
+|AI2 Reasoning Challenge (25-Shot)|59.39|
+|HellaSwag (10-Shot)              |82.77|
+|MMLU (5-Shot)                    |57.57|
+|TruthfulQA (0-shot)              |50.62|
+|Winogrande (5-shot)              |74.74|
+|GSM8k (5-shot)                   |24.87|
+