Adding Evaluation Results (#1)

- Adding Evaluation Results (d1ab2b3e40b5e81050ce412f3c254322ff299a52)


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

README.md

@@ -1,15 +1,118 @@
 ---
-base_model:
-- FelixChao/Sectumsempra-7B-DPO
-- FelixChao/WestSeverus-7B-DPO-v2
-tags:
-- mergekit
-- merge
-license: mit
 language:
 - en
+license: mit
 library_name: transformers
+tags:
+- mergekit
+- merge
+base_model:
+- FelixChao/Sectumsempra-7B-DPO
+- FelixChao/WestSeverus-7B-DPO-v2
 pipeline_tag: text-generation
+model-index:
+- name: Severusectum-7B-DPO
+  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: 71.5
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=s3nh/Severusectum-7B-DPO
+      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: 88.55
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=s3nh/Severusectum-7B-DPO
+      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: 64.79
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=s3nh/Severusectum-7B-DPO
+      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: 72.45
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=s3nh/Severusectum-7B-DPO
+      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: 83.27
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=s3nh/Severusectum-7B-DPO
+      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: 70.51
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=s3nh/Severusectum-7B-DPO
+      name: Open LLM Leaderboard
 ---
 
 ![image](severus.png)
@@ -49,4 +152,17 @@ slices:
     model: FelixChao/Sectumsempra-7B-DPO
   - layer_range: [0, 32]
     model: FelixChao/WestSeverus-7B-DPO-v2
-```
+```
+# [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_s3nh__Severusectum-7B-DPO)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |75.18|
+|AI2 Reasoning Challenge (25-Shot)|71.50|
+|HellaSwag (10-Shot)              |88.55|
+|MMLU (5-Shot)                    |64.79|
+|TruthfulQA (0-shot)              |72.45|
+|Winogrande (5-shot)              |83.27|
+|GSM8k (5-shot)                   |70.51|
+