Adding Evaluation Results

README.md

@@ -1,7 +1,110 @@
 ---
-license: apache-2.0
 language:
 - en
+license: apache-2.0
+model-index:
+- name: WestSeverus-7B-DPO-v2
+  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: 71.42
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FelixChao/WestSeverus-7B-DPO-v2
+      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: 88.27
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FelixChao/WestSeverus-7B-DPO-v2
+      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=FelixChao/WestSeverus-7B-DPO-v2
+      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: 72.37
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FelixChao/WestSeverus-7B-DPO-v2
+      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=FelixChao/WestSeverus-7B-DPO-v2
+      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: 71.65
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FelixChao/WestSeverus-7B-DPO-v2
+      name: Open LLM Leaderboard
 ---
 # WestSeverus - 7B - DPO - v2
 
@@ -114,3 +217,17 @@ WestSeverus-7B-DPO-v2 was trained using the ChatML prompt templates with system
 * Thanks to @TheBloke, @s3nh, @MaziyarPanahi for Quantized Models.
 * Thanks to @mlabonne, @CultriX for YALL - Yet Another LLM Leaderboard.
 * Thank you to all the other people in the Open Source AI community who utilized this model for further research and improvement.
+
+# [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_FelixChao__WestSeverus-7B-DPO-v2)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |75.29|
+|AI2 Reasoning Challenge (25-Shot)|71.42|
+|HellaSwag (10-Shot)              |88.27|
+|MMLU (5-Shot)                    |64.79|
+|TruthfulQA (0-shot)              |72.37|
+|Winogrande (5-shot)              |83.27|
+|GSM8k (5-shot)                   |71.65|
+