Adding Evaluation Results

README.md

@@ -1,12 +1,115 @@
 ---
-license: apache-2.0
-datasets:
-- meta-math/MetaMathQA
 language:
 - en
-pipeline_tag: text-generation
+license: apache-2.0
 tags:
 - Math
+datasets:
+- meta-math/MetaMathQA
+pipeline_tag: text-generation
+model-index:
+- name: Optimus-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: 65.44
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Q-bert/Optimus-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: 85.41
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Q-bert/Optimus-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: 63.61
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Q-bert/Optimus-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: 55.79
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Q-bert/Optimus-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: 78.77
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Q-bert/Optimus-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: 65.5
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Q-bert/Optimus-7B
+      name: Open LLM Leaderboard
 ---
 
 ## Optimus-7B
@@ -30,3 +133,17 @@ Detailed results can be found [Here](https://huggingface.co/datasets/open-llm-le
 | Winogrande (5-shot)   | 78.77               |
 | GSM8K (5-shot)        | 65.50               |
 
+
+# [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_Q-bert__Optimus-7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |69.09|
+|AI2 Reasoning Challenge (25-Shot)|65.44|
+|HellaSwag (10-Shot)              |85.41|
+|MMLU (5-Shot)                    |63.61|
+|TruthfulQA (0-shot)              |55.79|
+|Winogrande (5-shot)              |78.77|
+|GSM8k (5-shot)                   |65.50|
+