Adding Evaluation Results

README.md

@@ -1,15 +1,117 @@
 ---
 license: cc-by-nc-4.0
+library_name: transformers
+tags:
+- mergekit
+- merge
 base_model:
 - saishf/SOVLish-Maid-L3-8B
 - saishf/Ortho-SOVL-8B-L3
 - saishf/Merge-Mayhem-L3-V2
 - saishf/Merge-Mayhem-L3-V2.1
-library_name: transformers
-tags:
-- mergekit
-- merge
-
+model-index:
+- name: SOVL-Mega-Mash-L3-8B
+  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: 62.03
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/SOVL-Mega-Mash-L3-8B
+      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: 79.68
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/SOVL-Mega-Mash-L3-8B
+      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: 67.64
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/SOVL-Mega-Mash-L3-8B
+      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: 51.84
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/SOVL-Mega-Mash-L3-8B
+      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: 76.16
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/SOVL-Mega-Mash-L3-8B
+      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: 67.25
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/SOVL-Mega-Mash-L3-8B
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -42,3 +144,17 @@ merge_method: model_stock
 base_model: saishf/Ortho-SOVL-8B-L3
 dtype: bfloat16
 ```
+
+# [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_saishf__SOVL-Mega-Mash-L3-8B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |67.43|
+|AI2 Reasoning Challenge (25-Shot)|62.03|
+|HellaSwag (10-Shot)              |79.68|
+|MMLU (5-Shot)                    |67.64|
+|TruthfulQA (0-shot)              |51.84|
+|Winogrande (5-shot)              |76.16|
+|GSM8k (5-shot)                   |67.25|
+