Adding Evaluation Results (#1)

- Adding Evaluation Results (0336aed9c97cd6427657086bc0d7ce84baf3c9d7)


Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>

README.md

@@ -1,12 +1,115 @@
 ---
-base_model:
-- PetroGPT/WestSeverus-7B-DPO
-- bardsai/jaskier-7b-dpo-v6.1
+license: mit
 library_name: transformers
 tags:
 - mergekit
 - merge
-license: mit
+base_model:
+- PetroGPT/WestSeverus-7B-DPO
+- bardsai/jaskier-7b-dpo-v6.1
+model-index:
+- name: WestSeverusJaskier
+  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: 71.76
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vishnukv/WestSeverusJaskier
+      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: 88.16
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vishnukv/WestSeverusJaskier
+      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: 64.94
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vishnukv/WestSeverusJaskier
+      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: 73.18
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vishnukv/WestSeverusJaskier
+      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: 82.87
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vishnukv/WestSeverusJaskier
+      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: 73.09
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vishnukv/WestSeverusJaskier
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -22,3 +125,17 @@ The following models were included in the merge:
 * [PetroGPT/WestSeverus-7B-DPO](https://huggingface.co/PetroGPT/WestSeverus-7B-DPO)
 * [bardsai/jaskier-7b-dpo-v6.1](https://huggingface.co/bardsai/jaskier-7b-dpo-v6.1)
 
+
+# [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_vishnukv__WestSeverusJaskier)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |75.67|
+|AI2 Reasoning Challenge (25-Shot)|71.76|
+|HellaSwag (10-Shot)              |88.16|
+|MMLU (5-Shot)                    |64.94|
+|TruthfulQA (0-shot)              |73.18|
+|Winogrande (5-shot)              |82.87|
+|GSM8k (5-shot)                   |73.09|
+