Adding Evaluation Results

README.md

@@ -1,5 +1,8 @@
 ---
+language:
+- en
 license: apache-2.0
+library_name: transformers
 tags:
 - moe
 - frankenmoe
@@ -16,10 +19,110 @@ base_model:
 - dvilasuero/DistilabelBeagle14-7B
 - beowolx/CodeNinja-1.0-OpenChat-7B
 - WizardLM/WizardMath-7B-V1.1
-language:
-- en
-library_name: transformers
 pipeline_tag: text-generation
+model-index:
+- name: Pearl-3x7B
+  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: 65.53
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=louisbrulenaudet/Pearl-3x7B
+      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: 85.54
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=louisbrulenaudet/Pearl-3x7B
+      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: 64.27
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=louisbrulenaudet/Pearl-3x7B
+      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: 52.17
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=louisbrulenaudet/Pearl-3x7B
+      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: 78.69
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=louisbrulenaudet/Pearl-3x7B
+      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: 57.16
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=louisbrulenaudet/Pearl-3x7B
+      name: Open LLM Leaderboard
 ---
 
 <center><img src='https://i.imgur.com/0xFTuAX.png' width='450px'></center>
@@ -143,4 +246,17 @@ If you use this code in your research, please use the following BibTeX entry.
 
 ## Feedback
 
-If you have any feedback, please reach out at [louisbrulenaudet@icloud.com](mailto:louisbrulenaudet@icloud.com).
+If you have any feedback, please reach out at [louisbrulenaudet@icloud.com](mailto:louisbrulenaudet@icloud.com).
+# [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_louisbrulenaudet__Pearl-3x7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |67.23|
+|AI2 Reasoning Challenge (25-Shot)|65.53|
+|HellaSwag (10-Shot)              |85.54|
+|MMLU (5-Shot)                    |64.27|
+|TruthfulQA (0-shot)              |52.17|
+|Winogrande (5-shot)              |78.69|
+|GSM8k (5-shot)                   |57.16|
+