Adding Evaluation Results (#3)

- Adding Evaluation Results (3c832bf3e08d3b2aa11bd779400bb7a7e9c08918)


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

README.md

@@ -1,13 +1,116 @@
 ---
-license: cc-by-nc-sa-4.0
 language:
 - en
+license: cc-by-nc-sa-4.0
 library_name: transformers
-pipeline_tag: text-generation
 datasets:
 - psmathur/alpaca_orca
 - psmathur/dolly-v2_orca
 - psmathur/WizardLM_Orca
+pipeline_tag: text-generation
+model-index:
+- name: orca_mini_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: 43.94
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/orca_mini_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: 65.22
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/orca_mini_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: 29.97
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/orca_mini_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: 42.03
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/orca_mini_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: 66.06
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/orca_mini_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: 0.38
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/orca_mini_7b
+      name: Open LLM Leaderboard
 ---
 # orca_mini_7b
 
@@ -206,3 +309,17 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
 | Winogrande (5-shot)   | 66.06   |
 | GSM8K (5-shot)        | 0.38        |
 | DROP (3-shot)         | 14.14         |
+
+# [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_psmathur__orca_mini_7b)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |41.27|
+|AI2 Reasoning Challenge (25-Shot)|43.94|
+|HellaSwag (10-Shot)              |65.22|
+|MMLU (5-Shot)                    |29.97|
+|TruthfulQA (0-shot)              |42.03|
+|Winogrande (5-shot)              |66.06|
+|GSM8k (5-shot)                   | 0.38|
+