Adding Evaluation Results

README.md

@@ -1,10 +1,113 @@
 ---
-license: apache-2.0
 language:
 - en
-pipeline_tag: text-generation
+license: apache-2.0
 tags:
 - merge
+pipeline_tag: text-generation
+model-index:
+- name: WildWest-Variant3-7B
+  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: 73.21
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BarryFutureman/WildWest-Variant3-7B
+      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: 88.37
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BarryFutureman/WildWest-Variant3-7B
+      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: 64.76
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BarryFutureman/WildWest-Variant3-7B
+      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: 68.09
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BarryFutureman/WildWest-Variant3-7B
+      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: 84.37
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BarryFutureman/WildWest-Variant3-7B
+      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: 70.05
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BarryFutureman/WildWest-Variant3-7B
+      name: Open LLM Leaderboard
 ---
 
 # WildWest-Variant3-7B
@@ -12,4 +115,17 @@ Based on a merge of the following models using mergekit
 * [BarryFutureman/NeuralTurdusVariant1-7B](https://huggingface.co/BarryFutureman/NeuralTurdusVariant1-7B)
 * [mlabonne/NeuralDaredevil-7B](https://huggingface.co/udkai/Turdus)
 * [senseable/WestLake-7B-v2](https://huggingface.co/senseable/WestLake-7B-v2)
-* [PetroGPT/Severus-7B-DPO](https://huggingface.co/PetroGPT/Severus-7B-DPO)
+* [PetroGPT/Severus-7B-DPO](https://huggingface.co/PetroGPT/Severus-7B-DPO)
+# [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_BarryFutureman__WildWest-Variant3-7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |74.81|
+|AI2 Reasoning Challenge (25-Shot)|73.21|
+|HellaSwag (10-Shot)              |88.37|
+|MMLU (5-Shot)                    |64.76|
+|TruthfulQA (0-shot)              |68.09|
+|Winogrande (5-shot)              |84.37|
+|GSM8k (5-shot)                   |70.05|
+