Adding Evaluation Results (#2)

- Adding Evaluation Results (0cf9059f71625458bfa2a4e77563fcf1404029e8)


Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

README.md

@@ -1,12 +1,115 @@
 ---
-license: apache-2.0
-datasets:
-- Intel/orca_dpo_pairs
 language:
 - en
+license: apache-2.0
 library_name: transformers
 tags:
 - code
+datasets:
+- Intel/orca_dpo_pairs
+model-index:
+- name: Orca-SOLAR-4x10.7b
+  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: 68.52
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/Orca-SOLAR-4x10.7b
+      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: 86.78
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/Orca-SOLAR-4x10.7b
+      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: 67.03
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/Orca-SOLAR-4x10.7b
+      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: 64.54
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/Orca-SOLAR-4x10.7b
+      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: 83.9
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/Orca-SOLAR-4x10.7b
+      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: 68.23
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/Orca-SOLAR-4x10.7b
+      name: Open LLM Leaderboard
 ---
 
 # 🌞🚀 Orca-SOLAR-4x10.7_36B 
@@ -92,4 +195,17 @@ https://huggingface.co/datasets/open-llm-leaderboard/details_macadeliccc__Orca-S
       archivePrefix={arXiv},
       primaryClass={cs.CL}
 }
-```
+```
+# [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_macadeliccc__Orca-SOLAR-4x10.7b)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |73.17|
+|AI2 Reasoning Challenge (25-Shot)|68.52|
+|HellaSwag (10-Shot)              |86.78|
+|MMLU (5-Shot)                    |67.03|
+|TruthfulQA (0-shot)              |64.54|
+|Winogrande (5-shot)              |83.90|
+|GSM8k (5-shot)                   |68.23|
+